Initial Commit
Browse files- checkpoint-320000/config.json +25 -0
- checkpoint-320000/optimizer.pt +3 -0
- checkpoint-320000/pytorch_model.bin +3 -0
- checkpoint-320000/rng_state.pth +3 -0
- checkpoint-320000/scheduler.pt +3 -0
- checkpoint-320000/trainer_state.json +3856 -0
- checkpoint-320000/training_args.bin +3 -0
- checkpoint-330000/config.json +25 -0
- checkpoint-330000/optimizer.pt +3 -0
- checkpoint-330000/pytorch_model.bin +3 -0
- checkpoint-330000/rng_state.pth +3 -0
- checkpoint-330000/scheduler.pt +3 -0
- checkpoint-330000/trainer_state.json +3976 -0
- checkpoint-330000/training_args.bin +3 -0
- config.json +25 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- training_args.bin +3 -0
- vocab.json +0 -0
checkpoint-320000/config.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"RobertaForMaskedLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"bos_token_id": 0,
|
| 7 |
+
"eos_token_id": 2,
|
| 8 |
+
"gradient_checkpointing": false,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 3072,
|
| 14 |
+
"layer_norm_eps": 1e-12,
|
| 15 |
+
"max_position_embeddings": 512,
|
| 16 |
+
"model_type": "roberta",
|
| 17 |
+
"num_attention_heads": 12,
|
| 18 |
+
"num_hidden_layers": 6,
|
| 19 |
+
"pad_token_id": 1,
|
| 20 |
+
"position_embedding_type": "absolute",
|
| 21 |
+
"transformers_version": "4.6.1",
|
| 22 |
+
"type_vocab_size": 1,
|
| 23 |
+
"use_cache": true,
|
| 24 |
+
"vocab_size": 55000
|
| 25 |
+
}
|
checkpoint-320000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:607422a668a04faab051965d5919ce6b4bf98681eaa989a31047803e7798ab3d
|
| 3 |
+
size 686545359
|
checkpoint-320000/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8b6d60bd7e65d81fd9faaeb4cc6f2385b96755bed7d4fdc09c59d44ce8ed91b5
|
| 3 |
+
size 343289095
|
checkpoint-320000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fd98bed0e477d1d176ed9452a9f663ff5978a31e376283cd1b903a66aba449a3
|
| 3 |
+
size 14655
|
checkpoint-320000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1c6121761efe965eb2aafd0f15cbdfccb0528fe104f928117f8e474d7ead2b31
|
| 3 |
+
size 623
|
checkpoint-320000/trainer_state.json
ADDED
|
@@ -0,0 +1,3856 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.9549530730091467,
|
| 5 |
+
"global_step": 320000,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.0,
|
| 12 |
+
"learning_rate": 4.9925394291171165e-05,
|
| 13 |
+
"loss": 8.8395,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.0,
|
| 18 |
+
"learning_rate": 4.985078858234232e-05,
|
| 19 |
+
"loss": 8.3374,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.0,
|
| 24 |
+
"learning_rate": 4.9776182873513485e-05,
|
| 25 |
+
"loss": 8.1726,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.01,
|
| 30 |
+
"learning_rate": 4.970157716468464e-05,
|
| 31 |
+
"loss": 8.0495,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.01,
|
| 36 |
+
"learning_rate": 4.9626971455855804e-05,
|
| 37 |
+
"loss": 7.9605,
|
| 38 |
+
"step": 2500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.01,
|
| 42 |
+
"learning_rate": 4.955236574702696e-05,
|
| 43 |
+
"loss": 7.9116,
|
| 44 |
+
"step": 3000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.01,
|
| 48 |
+
"learning_rate": 4.947776003819812e-05,
|
| 49 |
+
"loss": 7.8568,
|
| 50 |
+
"step": 3500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.01,
|
| 54 |
+
"learning_rate": 4.9403154329369286e-05,
|
| 55 |
+
"loss": 7.8353,
|
| 56 |
+
"step": 4000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.01,
|
| 60 |
+
"learning_rate": 4.932854862054044e-05,
|
| 61 |
+
"loss": 7.7883,
|
| 62 |
+
"step": 4500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.01,
|
| 66 |
+
"learning_rate": 4.925394291171161e-05,
|
| 67 |
+
"loss": 7.7753,
|
| 68 |
+
"step": 5000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.02,
|
| 72 |
+
"learning_rate": 4.917933720288277e-05,
|
| 73 |
+
"loss": 7.7461,
|
| 74 |
+
"step": 5500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.02,
|
| 78 |
+
"learning_rate": 4.910473149405393e-05,
|
| 79 |
+
"loss": 7.7202,
|
| 80 |
+
"step": 6000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.02,
|
| 84 |
+
"learning_rate": 4.903012578522509e-05,
|
| 85 |
+
"loss": 7.7102,
|
| 86 |
+
"step": 6500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.02,
|
| 90 |
+
"learning_rate": 4.895552007639625e-05,
|
| 91 |
+
"loss": 7.6642,
|
| 92 |
+
"step": 7000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.02,
|
| 96 |
+
"learning_rate": 4.888091436756741e-05,
|
| 97 |
+
"loss": 7.6294,
|
| 98 |
+
"step": 7500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.02,
|
| 102 |
+
"learning_rate": 4.880630865873857e-05,
|
| 103 |
+
"loss": 7.6012,
|
| 104 |
+
"step": 8000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.03,
|
| 108 |
+
"learning_rate": 4.873170294990973e-05,
|
| 109 |
+
"loss": 7.5369,
|
| 110 |
+
"step": 8500
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.03,
|
| 114 |
+
"learning_rate": 4.865709724108089e-05,
|
| 115 |
+
"loss": 7.4688,
|
| 116 |
+
"step": 9000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.03,
|
| 120 |
+
"learning_rate": 4.858249153225205e-05,
|
| 121 |
+
"loss": 7.3744,
|
| 122 |
+
"step": 9500
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.03,
|
| 126 |
+
"learning_rate": 4.850788582342321e-05,
|
| 127 |
+
"loss": 7.2764,
|
| 128 |
+
"step": 10000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.03,
|
| 132 |
+
"learning_rate": 4.843328011459437e-05,
|
| 133 |
+
"loss": 7.1243,
|
| 134 |
+
"step": 10500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.03,
|
| 138 |
+
"learning_rate": 4.835867440576553e-05,
|
| 139 |
+
"loss": 7.0236,
|
| 140 |
+
"step": 11000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.03,
|
| 144 |
+
"learning_rate": 4.828406869693669e-05,
|
| 145 |
+
"loss": 6.8878,
|
| 146 |
+
"step": 11500
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.04,
|
| 150 |
+
"learning_rate": 4.820946298810785e-05,
|
| 151 |
+
"loss": 6.795,
|
| 152 |
+
"step": 12000
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.04,
|
| 156 |
+
"learning_rate": 4.813485727927901e-05,
|
| 157 |
+
"loss": 6.694,
|
| 158 |
+
"step": 12500
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.04,
|
| 162 |
+
"learning_rate": 4.806025157045017e-05,
|
| 163 |
+
"loss": 6.6033,
|
| 164 |
+
"step": 13000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.04,
|
| 168 |
+
"learning_rate": 4.798564586162133e-05,
|
| 169 |
+
"loss": 6.492,
|
| 170 |
+
"step": 13500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.04,
|
| 174 |
+
"learning_rate": 4.791104015279249e-05,
|
| 175 |
+
"loss": 6.4154,
|
| 176 |
+
"step": 14000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.04,
|
| 180 |
+
"learning_rate": 4.7836434443963654e-05,
|
| 181 |
+
"loss": 6.3564,
|
| 182 |
+
"step": 14500
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 0.04,
|
| 186 |
+
"learning_rate": 4.776182873513482e-05,
|
| 187 |
+
"loss": 6.2773,
|
| 188 |
+
"step": 15000
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.05,
|
| 192 |
+
"learning_rate": 4.768722302630598e-05,
|
| 193 |
+
"loss": 6.2294,
|
| 194 |
+
"step": 15500
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.05,
|
| 198 |
+
"learning_rate": 4.7612617317477136e-05,
|
| 199 |
+
"loss": 6.1543,
|
| 200 |
+
"step": 16000
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 0.05,
|
| 204 |
+
"learning_rate": 4.75380116086483e-05,
|
| 205 |
+
"loss": 6.1043,
|
| 206 |
+
"step": 16500
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.05,
|
| 210 |
+
"learning_rate": 4.7463405899819455e-05,
|
| 211 |
+
"loss": 6.0266,
|
| 212 |
+
"step": 17000
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.05,
|
| 216 |
+
"learning_rate": 4.738880019099062e-05,
|
| 217 |
+
"loss": 5.9925,
|
| 218 |
+
"step": 17500
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.05,
|
| 222 |
+
"learning_rate": 4.731419448216178e-05,
|
| 223 |
+
"loss": 5.955,
|
| 224 |
+
"step": 18000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.06,
|
| 228 |
+
"learning_rate": 4.723958877333294e-05,
|
| 229 |
+
"loss": 5.8802,
|
| 230 |
+
"step": 18500
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 0.06,
|
| 234 |
+
"learning_rate": 4.71649830645041e-05,
|
| 235 |
+
"loss": 5.8472,
|
| 236 |
+
"step": 19000
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 0.06,
|
| 240 |
+
"learning_rate": 4.7090377355675256e-05,
|
| 241 |
+
"loss": 5.7843,
|
| 242 |
+
"step": 19500
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 0.06,
|
| 246 |
+
"learning_rate": 4.701577164684642e-05,
|
| 247 |
+
"loss": 5.7739,
|
| 248 |
+
"step": 20000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.06,
|
| 252 |
+
"learning_rate": 4.6941165938017575e-05,
|
| 253 |
+
"loss": 5.6922,
|
| 254 |
+
"step": 20500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.06,
|
| 258 |
+
"learning_rate": 4.686656022918874e-05,
|
| 259 |
+
"loss": 5.6593,
|
| 260 |
+
"step": 21000
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 0.06,
|
| 264 |
+
"learning_rate": 4.67919545203599e-05,
|
| 265 |
+
"loss": 5.6313,
|
| 266 |
+
"step": 21500
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 0.07,
|
| 270 |
+
"learning_rate": 4.671734881153106e-05,
|
| 271 |
+
"loss": 5.593,
|
| 272 |
+
"step": 22000
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 0.07,
|
| 276 |
+
"learning_rate": 4.664274310270222e-05,
|
| 277 |
+
"loss": 5.5471,
|
| 278 |
+
"step": 22500
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 0.07,
|
| 282 |
+
"learning_rate": 4.656813739387338e-05,
|
| 283 |
+
"loss": 5.49,
|
| 284 |
+
"step": 23000
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 0.07,
|
| 288 |
+
"learning_rate": 4.6493531685044546e-05,
|
| 289 |
+
"loss": 5.4655,
|
| 290 |
+
"step": 23500
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.07,
|
| 294 |
+
"learning_rate": 4.64189259762157e-05,
|
| 295 |
+
"loss": 5.4349,
|
| 296 |
+
"step": 24000
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.07,
|
| 300 |
+
"learning_rate": 4.6344320267386866e-05,
|
| 301 |
+
"loss": 5.3876,
|
| 302 |
+
"step": 24500
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 0.07,
|
| 306 |
+
"learning_rate": 4.626971455855802e-05,
|
| 307 |
+
"loss": 5.378,
|
| 308 |
+
"step": 25000
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 0.08,
|
| 312 |
+
"learning_rate": 4.6195108849729185e-05,
|
| 313 |
+
"loss": 5.3231,
|
| 314 |
+
"step": 25500
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.08,
|
| 318 |
+
"learning_rate": 4.612050314090035e-05,
|
| 319 |
+
"loss": 5.2968,
|
| 320 |
+
"step": 26000
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 0.08,
|
| 324 |
+
"learning_rate": 4.6045897432071504e-05,
|
| 325 |
+
"loss": 5.2649,
|
| 326 |
+
"step": 26500
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 0.08,
|
| 330 |
+
"learning_rate": 4.597129172324267e-05,
|
| 331 |
+
"loss": 5.2329,
|
| 332 |
+
"step": 27000
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.08,
|
| 336 |
+
"learning_rate": 4.589668601441382e-05,
|
| 337 |
+
"loss": 5.2015,
|
| 338 |
+
"step": 27500
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.08,
|
| 342 |
+
"learning_rate": 4.5822080305584986e-05,
|
| 343 |
+
"loss": 5.1858,
|
| 344 |
+
"step": 28000
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 0.09,
|
| 348 |
+
"learning_rate": 4.574747459675615e-05,
|
| 349 |
+
"loss": 5.1435,
|
| 350 |
+
"step": 28500
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 0.09,
|
| 354 |
+
"learning_rate": 4.5672868887927305e-05,
|
| 355 |
+
"loss": 5.1239,
|
| 356 |
+
"step": 29000
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 0.09,
|
| 360 |
+
"learning_rate": 4.559826317909847e-05,
|
| 361 |
+
"loss": 5.0947,
|
| 362 |
+
"step": 29500
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 0.09,
|
| 366 |
+
"learning_rate": 4.5523657470269624e-05,
|
| 367 |
+
"loss": 5.0852,
|
| 368 |
+
"step": 30000
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 0.09,
|
| 372 |
+
"learning_rate": 4.544905176144079e-05,
|
| 373 |
+
"loss": 5.0373,
|
| 374 |
+
"step": 30500
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.09,
|
| 378 |
+
"learning_rate": 4.5374446052611943e-05,
|
| 379 |
+
"loss": 5.0134,
|
| 380 |
+
"step": 31000
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.09,
|
| 384 |
+
"learning_rate": 4.5299840343783106e-05,
|
| 385 |
+
"loss": 5.0094,
|
| 386 |
+
"step": 31500
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 0.1,
|
| 390 |
+
"learning_rate": 4.522523463495427e-05,
|
| 391 |
+
"loss": 4.9855,
|
| 392 |
+
"step": 32000
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 0.1,
|
| 396 |
+
"learning_rate": 4.5150628926125426e-05,
|
| 397 |
+
"loss": 4.943,
|
| 398 |
+
"step": 32500
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 0.1,
|
| 402 |
+
"learning_rate": 4.5076023217296595e-05,
|
| 403 |
+
"loss": 4.9091,
|
| 404 |
+
"step": 33000
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 0.1,
|
| 408 |
+
"learning_rate": 4.500141750846775e-05,
|
| 409 |
+
"loss": 4.8988,
|
| 410 |
+
"step": 33500
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.1,
|
| 414 |
+
"learning_rate": 4.4926811799638914e-05,
|
| 415 |
+
"loss": 4.8703,
|
| 416 |
+
"step": 34000
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.1,
|
| 420 |
+
"learning_rate": 4.485220609081007e-05,
|
| 421 |
+
"loss": 4.8395,
|
| 422 |
+
"step": 34500
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.1,
|
| 426 |
+
"learning_rate": 4.4777600381981234e-05,
|
| 427 |
+
"loss": 4.8175,
|
| 428 |
+
"step": 35000
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 0.11,
|
| 432 |
+
"learning_rate": 4.470299467315239e-05,
|
| 433 |
+
"loss": 4.8181,
|
| 434 |
+
"step": 35500
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 0.11,
|
| 438 |
+
"learning_rate": 4.462838896432355e-05,
|
| 439 |
+
"loss": 4.8026,
|
| 440 |
+
"step": 36000
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 0.11,
|
| 444 |
+
"learning_rate": 4.4553783255494716e-05,
|
| 445 |
+
"loss": 4.7798,
|
| 446 |
+
"step": 36500
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 0.11,
|
| 450 |
+
"learning_rate": 4.447917754666587e-05,
|
| 451 |
+
"loss": 4.741,
|
| 452 |
+
"step": 37000
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 0.11,
|
| 456 |
+
"learning_rate": 4.4404571837837035e-05,
|
| 457 |
+
"loss": 4.7337,
|
| 458 |
+
"step": 37500
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.11,
|
| 462 |
+
"learning_rate": 4.432996612900819e-05,
|
| 463 |
+
"loss": 4.7278,
|
| 464 |
+
"step": 38000
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.11,
|
| 468 |
+
"learning_rate": 4.4255360420179354e-05,
|
| 469 |
+
"loss": 4.7057,
|
| 470 |
+
"step": 38500
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 0.12,
|
| 474 |
+
"learning_rate": 4.418075471135052e-05,
|
| 475 |
+
"loss": 4.6702,
|
| 476 |
+
"step": 39000
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 0.12,
|
| 480 |
+
"learning_rate": 4.410614900252167e-05,
|
| 481 |
+
"loss": 4.6704,
|
| 482 |
+
"step": 39500
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 0.12,
|
| 486 |
+
"learning_rate": 4.4031543293692836e-05,
|
| 487 |
+
"loss": 4.647,
|
| 488 |
+
"step": 40000
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 0.12,
|
| 492 |
+
"learning_rate": 4.395693758486399e-05,
|
| 493 |
+
"loss": 4.6325,
|
| 494 |
+
"step": 40500
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 0.12,
|
| 498 |
+
"learning_rate": 4.3882331876035155e-05,
|
| 499 |
+
"loss": 4.6142,
|
| 500 |
+
"step": 41000
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.12,
|
| 504 |
+
"learning_rate": 4.380772616720631e-05,
|
| 505 |
+
"loss": 4.5979,
|
| 506 |
+
"step": 41500
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.13,
|
| 510 |
+
"learning_rate": 4.3733120458377474e-05,
|
| 511 |
+
"loss": 4.5934,
|
| 512 |
+
"step": 42000
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 0.13,
|
| 516 |
+
"learning_rate": 4.365851474954864e-05,
|
| 517 |
+
"loss": 4.558,
|
| 518 |
+
"step": 42500
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 0.13,
|
| 522 |
+
"learning_rate": 4.35839090407198e-05,
|
| 523 |
+
"loss": 4.5537,
|
| 524 |
+
"step": 43000
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 0.13,
|
| 528 |
+
"learning_rate": 4.350930333189096e-05,
|
| 529 |
+
"loss": 4.5202,
|
| 530 |
+
"step": 43500
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 0.13,
|
| 534 |
+
"learning_rate": 4.343469762306212e-05,
|
| 535 |
+
"loss": 4.5238,
|
| 536 |
+
"step": 44000
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 0.13,
|
| 540 |
+
"learning_rate": 4.336009191423328e-05,
|
| 541 |
+
"loss": 4.5052,
|
| 542 |
+
"step": 44500
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.13,
|
| 546 |
+
"learning_rate": 4.328548620540444e-05,
|
| 547 |
+
"loss": 4.4972,
|
| 548 |
+
"step": 45000
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.14,
|
| 552 |
+
"learning_rate": 4.32108804965756e-05,
|
| 553 |
+
"loss": 4.4751,
|
| 554 |
+
"step": 45500
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 0.14,
|
| 558 |
+
"learning_rate": 4.313627478774676e-05,
|
| 559 |
+
"loss": 4.4441,
|
| 560 |
+
"step": 46000
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 0.14,
|
| 564 |
+
"learning_rate": 4.306166907891792e-05,
|
| 565 |
+
"loss": 4.4482,
|
| 566 |
+
"step": 46500
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 0.14,
|
| 570 |
+
"learning_rate": 4.2987063370089084e-05,
|
| 571 |
+
"loss": 4.4365,
|
| 572 |
+
"step": 47000
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 0.14,
|
| 576 |
+
"learning_rate": 4.291245766126024e-05,
|
| 577 |
+
"loss": 4.4211,
|
| 578 |
+
"step": 47500
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 0.14,
|
| 582 |
+
"learning_rate": 4.28378519524314e-05,
|
| 583 |
+
"loss": 4.4135,
|
| 584 |
+
"step": 48000
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.14,
|
| 588 |
+
"learning_rate": 4.276324624360256e-05,
|
| 589 |
+
"loss": 4.3697,
|
| 590 |
+
"step": 48500
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.15,
|
| 594 |
+
"learning_rate": 4.268864053477372e-05,
|
| 595 |
+
"loss": 4.4008,
|
| 596 |
+
"step": 49000
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 0.15,
|
| 600 |
+
"learning_rate": 4.2614034825944885e-05,
|
| 601 |
+
"loss": 4.3786,
|
| 602 |
+
"step": 49500
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 0.15,
|
| 606 |
+
"learning_rate": 4.253942911711604e-05,
|
| 607 |
+
"loss": 4.3466,
|
| 608 |
+
"step": 50000
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 0.15,
|
| 612 |
+
"learning_rate": 4.2464823408287204e-05,
|
| 613 |
+
"loss": 4.3375,
|
| 614 |
+
"step": 50500
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 0.15,
|
| 618 |
+
"learning_rate": 4.239021769945836e-05,
|
| 619 |
+
"loss": 4.3199,
|
| 620 |
+
"step": 51000
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 0.15,
|
| 624 |
+
"learning_rate": 4.231561199062952e-05,
|
| 625 |
+
"loss": 4.3171,
|
| 626 |
+
"step": 51500
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.16,
|
| 630 |
+
"learning_rate": 4.2241006281800686e-05,
|
| 631 |
+
"loss": 4.3012,
|
| 632 |
+
"step": 52000
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.16,
|
| 636 |
+
"learning_rate": 4.216640057297185e-05,
|
| 637 |
+
"loss": 4.273,
|
| 638 |
+
"step": 52500
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 0.16,
|
| 642 |
+
"learning_rate": 4.2091794864143005e-05,
|
| 643 |
+
"loss": 4.287,
|
| 644 |
+
"step": 53000
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 0.16,
|
| 648 |
+
"learning_rate": 4.201718915531417e-05,
|
| 649 |
+
"loss": 4.2666,
|
| 650 |
+
"step": 53500
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 0.16,
|
| 654 |
+
"learning_rate": 4.194258344648533e-05,
|
| 655 |
+
"loss": 4.2536,
|
| 656 |
+
"step": 54000
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 0.16,
|
| 660 |
+
"learning_rate": 4.186797773765649e-05,
|
| 661 |
+
"loss": 4.2345,
|
| 662 |
+
"step": 54500
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 0.16,
|
| 666 |
+
"learning_rate": 4.179337202882765e-05,
|
| 667 |
+
"loss": 4.2495,
|
| 668 |
+
"step": 55000
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.17,
|
| 672 |
+
"learning_rate": 4.1718766319998807e-05,
|
| 673 |
+
"loss": 4.2232,
|
| 674 |
+
"step": 55500
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.17,
|
| 678 |
+
"learning_rate": 4.164416061116997e-05,
|
| 679 |
+
"loss": 4.219,
|
| 680 |
+
"step": 56000
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 0.17,
|
| 684 |
+
"learning_rate": 4.1569554902341126e-05,
|
| 685 |
+
"loss": 4.203,
|
| 686 |
+
"step": 56500
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 0.17,
|
| 690 |
+
"learning_rate": 4.149494919351229e-05,
|
| 691 |
+
"loss": 4.208,
|
| 692 |
+
"step": 57000
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 0.17,
|
| 696 |
+
"learning_rate": 4.142034348468345e-05,
|
| 697 |
+
"loss": 4.1815,
|
| 698 |
+
"step": 57500
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 0.17,
|
| 702 |
+
"learning_rate": 4.134573777585461e-05,
|
| 703 |
+
"loss": 4.1828,
|
| 704 |
+
"step": 58000
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 0.17,
|
| 708 |
+
"learning_rate": 4.127113206702577e-05,
|
| 709 |
+
"loss": 4.1539,
|
| 710 |
+
"step": 58500
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 0.18,
|
| 714 |
+
"learning_rate": 4.119652635819693e-05,
|
| 715 |
+
"loss": 4.1365,
|
| 716 |
+
"step": 59000
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 0.18,
|
| 720 |
+
"learning_rate": 4.112192064936809e-05,
|
| 721 |
+
"loss": 4.1362,
|
| 722 |
+
"step": 59500
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 0.18,
|
| 726 |
+
"learning_rate": 4.104731494053925e-05,
|
| 727 |
+
"loss": 4.1366,
|
| 728 |
+
"step": 60000
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 0.18,
|
| 732 |
+
"learning_rate": 4.097270923171041e-05,
|
| 733 |
+
"loss": 4.1265,
|
| 734 |
+
"step": 60500
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 0.18,
|
| 738 |
+
"learning_rate": 4.089810352288157e-05,
|
| 739 |
+
"loss": 4.1251,
|
| 740 |
+
"step": 61000
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 0.18,
|
| 744 |
+
"learning_rate": 4.0823497814052735e-05,
|
| 745 |
+
"loss": 4.1033,
|
| 746 |
+
"step": 61500
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 0.19,
|
| 750 |
+
"learning_rate": 4.07488921052239e-05,
|
| 751 |
+
"loss": 4.0914,
|
| 752 |
+
"step": 62000
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 0.19,
|
| 756 |
+
"learning_rate": 4.0674286396395054e-05,
|
| 757 |
+
"loss": 4.064,
|
| 758 |
+
"step": 62500
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 0.19,
|
| 762 |
+
"learning_rate": 4.059968068756622e-05,
|
| 763 |
+
"loss": 4.0919,
|
| 764 |
+
"step": 63000
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 0.19,
|
| 768 |
+
"learning_rate": 4.052507497873737e-05,
|
| 769 |
+
"loss": 4.0719,
|
| 770 |
+
"step": 63500
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 0.19,
|
| 774 |
+
"learning_rate": 4.0450469269908536e-05,
|
| 775 |
+
"loss": 4.0527,
|
| 776 |
+
"step": 64000
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 0.19,
|
| 780 |
+
"learning_rate": 4.03758635610797e-05,
|
| 781 |
+
"loss": 4.0483,
|
| 782 |
+
"step": 64500
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 0.19,
|
| 786 |
+
"learning_rate": 4.0301257852250855e-05,
|
| 787 |
+
"loss": 4.0287,
|
| 788 |
+
"step": 65000
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 0.2,
|
| 792 |
+
"learning_rate": 4.022665214342202e-05,
|
| 793 |
+
"loss": 4.0354,
|
| 794 |
+
"step": 65500
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 0.2,
|
| 798 |
+
"learning_rate": 4.0152046434593175e-05,
|
| 799 |
+
"loss": 4.0273,
|
| 800 |
+
"step": 66000
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 0.2,
|
| 804 |
+
"learning_rate": 4.007744072576434e-05,
|
| 805 |
+
"loss": 4.0207,
|
| 806 |
+
"step": 66500
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"epoch": 0.2,
|
| 810 |
+
"learning_rate": 4.0002835016935494e-05,
|
| 811 |
+
"loss": 4.0063,
|
| 812 |
+
"step": 67000
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 0.2,
|
| 816 |
+
"learning_rate": 3.992822930810666e-05,
|
| 817 |
+
"loss": 3.9946,
|
| 818 |
+
"step": 67500
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 0.2,
|
| 822 |
+
"learning_rate": 3.985362359927782e-05,
|
| 823 |
+
"loss": 3.9905,
|
| 824 |
+
"step": 68000
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 0.2,
|
| 828 |
+
"learning_rate": 3.9779017890448976e-05,
|
| 829 |
+
"loss": 3.9737,
|
| 830 |
+
"step": 68500
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 0.21,
|
| 834 |
+
"learning_rate": 3.970441218162014e-05,
|
| 835 |
+
"loss": 3.965,
|
| 836 |
+
"step": 69000
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 0.21,
|
| 840 |
+
"learning_rate": 3.9629806472791295e-05,
|
| 841 |
+
"loss": 3.9595,
|
| 842 |
+
"step": 69500
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.21,
|
| 846 |
+
"learning_rate": 3.955520076396246e-05,
|
| 847 |
+
"loss": 3.9496,
|
| 848 |
+
"step": 70000
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 0.21,
|
| 852 |
+
"learning_rate": 3.948059505513362e-05,
|
| 853 |
+
"loss": 3.9545,
|
| 854 |
+
"step": 70500
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 0.21,
|
| 858 |
+
"learning_rate": 3.9405989346304784e-05,
|
| 859 |
+
"loss": 3.9179,
|
| 860 |
+
"step": 71000
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"epoch": 0.21,
|
| 864 |
+
"learning_rate": 3.933138363747595e-05,
|
| 865 |
+
"loss": 3.9365,
|
| 866 |
+
"step": 71500
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 0.21,
|
| 870 |
+
"learning_rate": 3.92567779286471e-05,
|
| 871 |
+
"loss": 3.9161,
|
| 872 |
+
"step": 72000
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 0.22,
|
| 876 |
+
"learning_rate": 3.9182172219818266e-05,
|
| 877 |
+
"loss": 3.8996,
|
| 878 |
+
"step": 72500
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 0.22,
|
| 882 |
+
"learning_rate": 3.910756651098942e-05,
|
| 883 |
+
"loss": 3.8962,
|
| 884 |
+
"step": 73000
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 0.22,
|
| 888 |
+
"learning_rate": 3.9032960802160585e-05,
|
| 889 |
+
"loss": 3.8996,
|
| 890 |
+
"step": 73500
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 0.22,
|
| 894 |
+
"learning_rate": 3.895835509333174e-05,
|
| 895 |
+
"loss": 3.8986,
|
| 896 |
+
"step": 74000
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 0.22,
|
| 900 |
+
"learning_rate": 3.8883749384502904e-05,
|
| 901 |
+
"loss": 3.8726,
|
| 902 |
+
"step": 74500
|
| 903 |
+
},
|
| 904 |
+
{
|
| 905 |
+
"epoch": 0.22,
|
| 906 |
+
"learning_rate": 3.880914367567407e-05,
|
| 907 |
+
"loss": 3.8836,
|
| 908 |
+
"step": 75000
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 0.23,
|
| 912 |
+
"learning_rate": 3.8734537966845223e-05,
|
| 913 |
+
"loss": 3.8637,
|
| 914 |
+
"step": 75500
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 0.23,
|
| 918 |
+
"learning_rate": 3.8659932258016386e-05,
|
| 919 |
+
"loss": 3.8579,
|
| 920 |
+
"step": 76000
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 0.23,
|
| 924 |
+
"learning_rate": 3.858532654918754e-05,
|
| 925 |
+
"loss": 3.8529,
|
| 926 |
+
"step": 76500
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 0.23,
|
| 930 |
+
"learning_rate": 3.8510720840358706e-05,
|
| 931 |
+
"loss": 3.8406,
|
| 932 |
+
"step": 77000
|
| 933 |
+
},
|
| 934 |
+
{
|
| 935 |
+
"epoch": 0.23,
|
| 936 |
+
"learning_rate": 3.843611513152986e-05,
|
| 937 |
+
"loss": 3.8452,
|
| 938 |
+
"step": 77500
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 0.23,
|
| 942 |
+
"learning_rate": 3.8361509422701025e-05,
|
| 943 |
+
"loss": 3.8343,
|
| 944 |
+
"step": 78000
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"epoch": 0.23,
|
| 948 |
+
"learning_rate": 3.828690371387219e-05,
|
| 949 |
+
"loss": 3.8337,
|
| 950 |
+
"step": 78500
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 0.24,
|
| 954 |
+
"learning_rate": 3.8212298005043344e-05,
|
| 955 |
+
"loss": 3.82,
|
| 956 |
+
"step": 79000
|
| 957 |
+
},
|
| 958 |
+
{
|
| 959 |
+
"epoch": 0.24,
|
| 960 |
+
"learning_rate": 3.813769229621451e-05,
|
| 961 |
+
"loss": 3.8208,
|
| 962 |
+
"step": 79500
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 0.24,
|
| 966 |
+
"learning_rate": 3.806308658738567e-05,
|
| 967 |
+
"loss": 3.8178,
|
| 968 |
+
"step": 80000
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 0.24,
|
| 972 |
+
"learning_rate": 3.798848087855683e-05,
|
| 973 |
+
"loss": 3.7932,
|
| 974 |
+
"step": 80500
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 0.24,
|
| 978 |
+
"learning_rate": 3.791387516972799e-05,
|
| 979 |
+
"loss": 3.7966,
|
| 980 |
+
"step": 81000
|
| 981 |
+
},
|
| 982 |
+
{
|
| 983 |
+
"epoch": 0.24,
|
| 984 |
+
"learning_rate": 3.783926946089915e-05,
|
| 985 |
+
"loss": 3.7977,
|
| 986 |
+
"step": 81500
|
| 987 |
+
},
|
| 988 |
+
{
|
| 989 |
+
"epoch": 0.24,
|
| 990 |
+
"learning_rate": 3.7764663752070315e-05,
|
| 991 |
+
"loss": 3.7823,
|
| 992 |
+
"step": 82000
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 0.25,
|
| 996 |
+
"learning_rate": 3.769005804324147e-05,
|
| 997 |
+
"loss": 3.7802,
|
| 998 |
+
"step": 82500
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 0.25,
|
| 1002 |
+
"learning_rate": 3.7615452334412634e-05,
|
| 1003 |
+
"loss": 3.7686,
|
| 1004 |
+
"step": 83000
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 0.25,
|
| 1008 |
+
"learning_rate": 3.754084662558379e-05,
|
| 1009 |
+
"loss": 3.7709,
|
| 1010 |
+
"step": 83500
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 0.25,
|
| 1014 |
+
"learning_rate": 3.746624091675495e-05,
|
| 1015 |
+
"loss": 3.7671,
|
| 1016 |
+
"step": 84000
|
| 1017 |
+
},
|
| 1018 |
+
{
|
| 1019 |
+
"epoch": 0.25,
|
| 1020 |
+
"learning_rate": 3.739163520792611e-05,
|
| 1021 |
+
"loss": 3.7559,
|
| 1022 |
+
"step": 84500
|
| 1023 |
+
},
|
| 1024 |
+
{
|
| 1025 |
+
"epoch": 0.25,
|
| 1026 |
+
"learning_rate": 3.731702949909727e-05,
|
| 1027 |
+
"loss": 3.7743,
|
| 1028 |
+
"step": 85000
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"epoch": 0.26,
|
| 1032 |
+
"learning_rate": 3.7242423790268435e-05,
|
| 1033 |
+
"loss": 3.7467,
|
| 1034 |
+
"step": 85500
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 0.26,
|
| 1038 |
+
"learning_rate": 3.716781808143959e-05,
|
| 1039 |
+
"loss": 3.745,
|
| 1040 |
+
"step": 86000
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 0.26,
|
| 1044 |
+
"learning_rate": 3.7093212372610754e-05,
|
| 1045 |
+
"loss": 3.7379,
|
| 1046 |
+
"step": 86500
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 0.26,
|
| 1050 |
+
"learning_rate": 3.701860666378191e-05,
|
| 1051 |
+
"loss": 3.7105,
|
| 1052 |
+
"step": 87000
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 0.26,
|
| 1056 |
+
"learning_rate": 3.6944000954953074e-05,
|
| 1057 |
+
"loss": 3.7341,
|
| 1058 |
+
"step": 87500
|
| 1059 |
+
},
|
| 1060 |
+
{
|
| 1061 |
+
"epoch": 0.26,
|
| 1062 |
+
"learning_rate": 3.6869395246124237e-05,
|
| 1063 |
+
"loss": 3.7121,
|
| 1064 |
+
"step": 88000
|
| 1065 |
+
},
|
| 1066 |
+
{
|
| 1067 |
+
"epoch": 0.26,
|
| 1068 |
+
"learning_rate": 3.679478953729539e-05,
|
| 1069 |
+
"loss": 3.7154,
|
| 1070 |
+
"step": 88500
|
| 1071 |
+
},
|
| 1072 |
+
{
|
| 1073 |
+
"epoch": 0.27,
|
| 1074 |
+
"learning_rate": 3.6720183828466556e-05,
|
| 1075 |
+
"loss": 3.6959,
|
| 1076 |
+
"step": 89000
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 0.27,
|
| 1080 |
+
"learning_rate": 3.664557811963772e-05,
|
| 1081 |
+
"loss": 3.6943,
|
| 1082 |
+
"step": 89500
|
| 1083 |
+
},
|
| 1084 |
+
{
|
| 1085 |
+
"epoch": 0.27,
|
| 1086 |
+
"learning_rate": 3.657097241080888e-05,
|
| 1087 |
+
"loss": 3.6909,
|
| 1088 |
+
"step": 90000
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 0.27,
|
| 1092 |
+
"learning_rate": 3.649636670198004e-05,
|
| 1093 |
+
"loss": 3.6937,
|
| 1094 |
+
"step": 90500
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 0.27,
|
| 1098 |
+
"learning_rate": 3.64217609931512e-05,
|
| 1099 |
+
"loss": 3.6994,
|
| 1100 |
+
"step": 91000
|
| 1101 |
+
},
|
| 1102 |
+
{
|
| 1103 |
+
"epoch": 0.27,
|
| 1104 |
+
"learning_rate": 3.634715528432236e-05,
|
| 1105 |
+
"loss": 3.6758,
|
| 1106 |
+
"step": 91500
|
| 1107 |
+
},
|
| 1108 |
+
{
|
| 1109 |
+
"epoch": 0.27,
|
| 1110 |
+
"learning_rate": 3.627254957549352e-05,
|
| 1111 |
+
"loss": 3.6812,
|
| 1112 |
+
"step": 92000
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 0.28,
|
| 1116 |
+
"learning_rate": 3.619794386666468e-05,
|
| 1117 |
+
"loss": 3.6782,
|
| 1118 |
+
"step": 92500
|
| 1119 |
+
},
|
| 1120 |
+
{
|
| 1121 |
+
"epoch": 0.28,
|
| 1122 |
+
"learning_rate": 3.612333815783584e-05,
|
| 1123 |
+
"loss": 3.6732,
|
| 1124 |
+
"step": 93000
|
| 1125 |
+
},
|
| 1126 |
+
{
|
| 1127 |
+
"epoch": 0.28,
|
| 1128 |
+
"learning_rate": 3.6048732449007e-05,
|
| 1129 |
+
"loss": 3.6677,
|
| 1130 |
+
"step": 93500
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 0.28,
|
| 1134 |
+
"learning_rate": 3.597412674017816e-05,
|
| 1135 |
+
"loss": 3.6845,
|
| 1136 |
+
"step": 94000
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 0.28,
|
| 1140 |
+
"learning_rate": 3.589952103134932e-05,
|
| 1141 |
+
"loss": 3.6512,
|
| 1142 |
+
"step": 94500
|
| 1143 |
+
},
|
| 1144 |
+
{
|
| 1145 |
+
"epoch": 0.28,
|
| 1146 |
+
"learning_rate": 3.582491532252048e-05,
|
| 1147 |
+
"loss": 3.6636,
|
| 1148 |
+
"step": 95000
|
| 1149 |
+
},
|
| 1150 |
+
{
|
| 1151 |
+
"epoch": 0.28,
|
| 1152 |
+
"learning_rate": 3.575030961369164e-05,
|
| 1153 |
+
"loss": 3.6355,
|
| 1154 |
+
"step": 95500
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 0.29,
|
| 1158 |
+
"learning_rate": 3.56757039048628e-05,
|
| 1159 |
+
"loss": 3.6325,
|
| 1160 |
+
"step": 96000
|
| 1161 |
+
},
|
| 1162 |
+
{
|
| 1163 |
+
"epoch": 0.29,
|
| 1164 |
+
"learning_rate": 3.560109819603396e-05,
|
| 1165 |
+
"loss": 3.6498,
|
| 1166 |
+
"step": 96500
|
| 1167 |
+
},
|
| 1168 |
+
{
|
| 1169 |
+
"epoch": 0.29,
|
| 1170 |
+
"learning_rate": 3.552649248720512e-05,
|
| 1171 |
+
"loss": 3.6384,
|
| 1172 |
+
"step": 97000
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 0.29,
|
| 1176 |
+
"learning_rate": 3.545188677837628e-05,
|
| 1177 |
+
"loss": 3.6325,
|
| 1178 |
+
"step": 97500
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 0.29,
|
| 1182 |
+
"learning_rate": 3.537728106954744e-05,
|
| 1183 |
+
"loss": 3.6313,
|
| 1184 |
+
"step": 98000
|
| 1185 |
+
},
|
| 1186 |
+
{
|
| 1187 |
+
"epoch": 0.29,
|
| 1188 |
+
"learning_rate": 3.5302675360718605e-05,
|
| 1189 |
+
"loss": 3.6097,
|
| 1190 |
+
"step": 98500
|
| 1191 |
+
},
|
| 1192 |
+
{
|
| 1193 |
+
"epoch": 0.3,
|
| 1194 |
+
"learning_rate": 3.522806965188977e-05,
|
| 1195 |
+
"loss": 3.6196,
|
| 1196 |
+
"step": 99000
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 0.3,
|
| 1200 |
+
"learning_rate": 3.5153463943060924e-05,
|
| 1201 |
+
"loss": 3.6109,
|
| 1202 |
+
"step": 99500
|
| 1203 |
+
},
|
| 1204 |
+
{
|
| 1205 |
+
"epoch": 0.3,
|
| 1206 |
+
"learning_rate": 3.507885823423209e-05,
|
| 1207 |
+
"loss": 3.6011,
|
| 1208 |
+
"step": 100000
|
| 1209 |
+
},
|
| 1210 |
+
{
|
| 1211 |
+
"epoch": 0.3,
|
| 1212 |
+
"learning_rate": 3.500425252540325e-05,
|
| 1213 |
+
"loss": 3.6124,
|
| 1214 |
+
"step": 100500
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 0.3,
|
| 1218 |
+
"learning_rate": 3.4929646816574406e-05,
|
| 1219 |
+
"loss": 3.5833,
|
| 1220 |
+
"step": 101000
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 0.3,
|
| 1224 |
+
"learning_rate": 3.485504110774557e-05,
|
| 1225 |
+
"loss": 3.6067,
|
| 1226 |
+
"step": 101500
|
| 1227 |
+
},
|
| 1228 |
+
{
|
| 1229 |
+
"epoch": 0.3,
|
| 1230 |
+
"learning_rate": 3.4780435398916725e-05,
|
| 1231 |
+
"loss": 3.5863,
|
| 1232 |
+
"step": 102000
|
| 1233 |
+
},
|
| 1234 |
+
{
|
| 1235 |
+
"epoch": 0.31,
|
| 1236 |
+
"learning_rate": 3.470582969008789e-05,
|
| 1237 |
+
"loss": 3.6031,
|
| 1238 |
+
"step": 102500
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 0.31,
|
| 1242 |
+
"learning_rate": 3.463122398125905e-05,
|
| 1243 |
+
"loss": 3.571,
|
| 1244 |
+
"step": 103000
|
| 1245 |
+
},
|
| 1246 |
+
{
|
| 1247 |
+
"epoch": 0.31,
|
| 1248 |
+
"learning_rate": 3.455661827243021e-05,
|
| 1249 |
+
"loss": 3.5863,
|
| 1250 |
+
"step": 103500
|
| 1251 |
+
},
|
| 1252 |
+
{
|
| 1253 |
+
"epoch": 0.31,
|
| 1254 |
+
"learning_rate": 3.448201256360137e-05,
|
| 1255 |
+
"loss": 3.5817,
|
| 1256 |
+
"step": 104000
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 0.31,
|
| 1260 |
+
"learning_rate": 3.4407406854772526e-05,
|
| 1261 |
+
"loss": 3.5754,
|
| 1262 |
+
"step": 104500
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 0.31,
|
| 1266 |
+
"learning_rate": 3.433280114594369e-05,
|
| 1267 |
+
"loss": 3.5687,
|
| 1268 |
+
"step": 105000
|
| 1269 |
+
},
|
| 1270 |
+
{
|
| 1271 |
+
"epoch": 0.31,
|
| 1272 |
+
"learning_rate": 3.4258195437114845e-05,
|
| 1273 |
+
"loss": 3.5607,
|
| 1274 |
+
"step": 105500
|
| 1275 |
+
},
|
| 1276 |
+
{
|
| 1277 |
+
"epoch": 0.32,
|
| 1278 |
+
"learning_rate": 3.418358972828601e-05,
|
| 1279 |
+
"loss": 3.5635,
|
| 1280 |
+
"step": 106000
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 0.32,
|
| 1284 |
+
"learning_rate": 3.410898401945717e-05,
|
| 1285 |
+
"loss": 3.5597,
|
| 1286 |
+
"step": 106500
|
| 1287 |
+
},
|
| 1288 |
+
{
|
| 1289 |
+
"epoch": 0.32,
|
| 1290 |
+
"learning_rate": 3.403437831062833e-05,
|
| 1291 |
+
"loss": 3.5514,
|
| 1292 |
+
"step": 107000
|
| 1293 |
+
},
|
| 1294 |
+
{
|
| 1295 |
+
"epoch": 0.32,
|
| 1296 |
+
"learning_rate": 3.395977260179949e-05,
|
| 1297 |
+
"loss": 3.5589,
|
| 1298 |
+
"step": 107500
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 0.32,
|
| 1302 |
+
"learning_rate": 3.388516689297065e-05,
|
| 1303 |
+
"loss": 3.5548,
|
| 1304 |
+
"step": 108000
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 0.32,
|
| 1308 |
+
"learning_rate": 3.3810561184141816e-05,
|
| 1309 |
+
"loss": 3.5499,
|
| 1310 |
+
"step": 108500
|
| 1311 |
+
},
|
| 1312 |
+
{
|
| 1313 |
+
"epoch": 0.33,
|
| 1314 |
+
"learning_rate": 3.373595547531297e-05,
|
| 1315 |
+
"loss": 3.5236,
|
| 1316 |
+
"step": 109000
|
| 1317 |
+
},
|
| 1318 |
+
{
|
| 1319 |
+
"epoch": 0.33,
|
| 1320 |
+
"learning_rate": 3.3661349766484135e-05,
|
| 1321 |
+
"loss": 3.5433,
|
| 1322 |
+
"step": 109500
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 0.33,
|
| 1326 |
+
"learning_rate": 3.358674405765529e-05,
|
| 1327 |
+
"loss": 3.5355,
|
| 1328 |
+
"step": 110000
|
| 1329 |
+
},
|
| 1330 |
+
{
|
| 1331 |
+
"epoch": 0.33,
|
| 1332 |
+
"learning_rate": 3.3512138348826455e-05,
|
| 1333 |
+
"loss": 3.5246,
|
| 1334 |
+
"step": 110500
|
| 1335 |
+
},
|
| 1336 |
+
{
|
| 1337 |
+
"epoch": 0.33,
|
| 1338 |
+
"learning_rate": 3.343753263999762e-05,
|
| 1339 |
+
"loss": 3.5352,
|
| 1340 |
+
"step": 111000
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 0.33,
|
| 1344 |
+
"learning_rate": 3.3362926931168774e-05,
|
| 1345 |
+
"loss": 3.5268,
|
| 1346 |
+
"step": 111500
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 0.33,
|
| 1350 |
+
"learning_rate": 3.328832122233994e-05,
|
| 1351 |
+
"loss": 3.5209,
|
| 1352 |
+
"step": 112000
|
| 1353 |
+
},
|
| 1354 |
+
{
|
| 1355 |
+
"epoch": 0.34,
|
| 1356 |
+
"learning_rate": 3.321371551351109e-05,
|
| 1357 |
+
"loss": 3.4999,
|
| 1358 |
+
"step": 112500
|
| 1359 |
+
},
|
| 1360 |
+
{
|
| 1361 |
+
"epoch": 0.34,
|
| 1362 |
+
"learning_rate": 3.3139109804682256e-05,
|
| 1363 |
+
"loss": 3.5197,
|
| 1364 |
+
"step": 113000
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 0.34,
|
| 1368 |
+
"learning_rate": 3.306450409585342e-05,
|
| 1369 |
+
"loss": 3.5116,
|
| 1370 |
+
"step": 113500
|
| 1371 |
+
},
|
| 1372 |
+
{
|
| 1373 |
+
"epoch": 0.34,
|
| 1374 |
+
"learning_rate": 3.2989898387024575e-05,
|
| 1375 |
+
"loss": 3.5009,
|
| 1376 |
+
"step": 114000
|
| 1377 |
+
},
|
| 1378 |
+
{
|
| 1379 |
+
"epoch": 0.34,
|
| 1380 |
+
"learning_rate": 3.291529267819574e-05,
|
| 1381 |
+
"loss": 3.5102,
|
| 1382 |
+
"step": 114500
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 0.34,
|
| 1386 |
+
"learning_rate": 3.2840686969366894e-05,
|
| 1387 |
+
"loss": 3.5053,
|
| 1388 |
+
"step": 115000
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 0.34,
|
| 1392 |
+
"learning_rate": 3.276608126053806e-05,
|
| 1393 |
+
"loss": 3.4856,
|
| 1394 |
+
"step": 115500
|
| 1395 |
+
},
|
| 1396 |
+
{
|
| 1397 |
+
"epoch": 0.35,
|
| 1398 |
+
"learning_rate": 3.269147555170921e-05,
|
| 1399 |
+
"loss": 3.4952,
|
| 1400 |
+
"step": 116000
|
| 1401 |
+
},
|
| 1402 |
+
{
|
| 1403 |
+
"epoch": 0.35,
|
| 1404 |
+
"learning_rate": 3.2616869842880376e-05,
|
| 1405 |
+
"loss": 3.4888,
|
| 1406 |
+
"step": 116500
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 0.35,
|
| 1410 |
+
"learning_rate": 3.254226413405154e-05,
|
| 1411 |
+
"loss": 3.493,
|
| 1412 |
+
"step": 117000
|
| 1413 |
+
},
|
| 1414 |
+
{
|
| 1415 |
+
"epoch": 0.35,
|
| 1416 |
+
"learning_rate": 3.24676584252227e-05,
|
| 1417 |
+
"loss": 3.4838,
|
| 1418 |
+
"step": 117500
|
| 1419 |
+
},
|
| 1420 |
+
{
|
| 1421 |
+
"epoch": 0.35,
|
| 1422 |
+
"learning_rate": 3.2393052716393865e-05,
|
| 1423 |
+
"loss": 3.4716,
|
| 1424 |
+
"step": 118000
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 0.35,
|
| 1428 |
+
"learning_rate": 3.231844700756502e-05,
|
| 1429 |
+
"loss": 3.4816,
|
| 1430 |
+
"step": 118500
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 0.36,
|
| 1434 |
+
"learning_rate": 3.2243841298736184e-05,
|
| 1435 |
+
"loss": 3.4613,
|
| 1436 |
+
"step": 119000
|
| 1437 |
+
},
|
| 1438 |
+
{
|
| 1439 |
+
"epoch": 0.36,
|
| 1440 |
+
"learning_rate": 3.216923558990734e-05,
|
| 1441 |
+
"loss": 3.4446,
|
| 1442 |
+
"step": 119500
|
| 1443 |
+
},
|
| 1444 |
+
{
|
| 1445 |
+
"epoch": 0.36,
|
| 1446 |
+
"learning_rate": 3.2094629881078503e-05,
|
| 1447 |
+
"loss": 3.4699,
|
| 1448 |
+
"step": 120000
|
| 1449 |
+
},
|
| 1450 |
+
{
|
| 1451 |
+
"epoch": 0.36,
|
| 1452 |
+
"learning_rate": 3.202002417224966e-05,
|
| 1453 |
+
"loss": 3.4482,
|
| 1454 |
+
"step": 120500
|
| 1455 |
+
},
|
| 1456 |
+
{
|
| 1457 |
+
"epoch": 0.36,
|
| 1458 |
+
"learning_rate": 3.194541846342082e-05,
|
| 1459 |
+
"loss": 3.464,
|
| 1460 |
+
"step": 121000
|
| 1461 |
+
},
|
| 1462 |
+
{
|
| 1463 |
+
"epoch": 0.36,
|
| 1464 |
+
"learning_rate": 3.1870812754591986e-05,
|
| 1465 |
+
"loss": 3.4557,
|
| 1466 |
+
"step": 121500
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 0.36,
|
| 1470 |
+
"learning_rate": 3.179620704576314e-05,
|
| 1471 |
+
"loss": 3.4628,
|
| 1472 |
+
"step": 122000
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 0.37,
|
| 1476 |
+
"learning_rate": 3.1721601336934305e-05,
|
| 1477 |
+
"loss": 3.4543,
|
| 1478 |
+
"step": 122500
|
| 1479 |
+
},
|
| 1480 |
+
{
|
| 1481 |
+
"epoch": 0.37,
|
| 1482 |
+
"learning_rate": 3.164699562810546e-05,
|
| 1483 |
+
"loss": 3.4459,
|
| 1484 |
+
"step": 123000
|
| 1485 |
+
},
|
| 1486 |
+
{
|
| 1487 |
+
"epoch": 0.37,
|
| 1488 |
+
"learning_rate": 3.1572389919276624e-05,
|
| 1489 |
+
"loss": 3.4314,
|
| 1490 |
+
"step": 123500
|
| 1491 |
+
},
|
| 1492 |
+
{
|
| 1493 |
+
"epoch": 0.37,
|
| 1494 |
+
"learning_rate": 3.149778421044779e-05,
|
| 1495 |
+
"loss": 3.4374,
|
| 1496 |
+
"step": 124000
|
| 1497 |
+
},
|
| 1498 |
+
{
|
| 1499 |
+
"epoch": 0.37,
|
| 1500 |
+
"learning_rate": 3.142317850161894e-05,
|
| 1501 |
+
"loss": 3.4492,
|
| 1502 |
+
"step": 124500
|
| 1503 |
+
},
|
| 1504 |
+
{
|
| 1505 |
+
"epoch": 0.37,
|
| 1506 |
+
"learning_rate": 3.1348572792790106e-05,
|
| 1507 |
+
"loss": 3.4237,
|
| 1508 |
+
"step": 125000
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 0.37,
|
| 1512 |
+
"learning_rate": 3.127396708396126e-05,
|
| 1513 |
+
"loss": 3.4221,
|
| 1514 |
+
"step": 125500
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 0.38,
|
| 1518 |
+
"learning_rate": 3.1199361375132425e-05,
|
| 1519 |
+
"loss": 3.4291,
|
| 1520 |
+
"step": 126000
|
| 1521 |
+
},
|
| 1522 |
+
{
|
| 1523 |
+
"epoch": 0.38,
|
| 1524 |
+
"learning_rate": 3.112475566630358e-05,
|
| 1525 |
+
"loss": 3.4286,
|
| 1526 |
+
"step": 126500
|
| 1527 |
+
},
|
| 1528 |
+
{
|
| 1529 |
+
"epoch": 0.38,
|
| 1530 |
+
"learning_rate": 3.105014995747475e-05,
|
| 1531 |
+
"loss": 3.4244,
|
| 1532 |
+
"step": 127000
|
| 1533 |
+
},
|
| 1534 |
+
{
|
| 1535 |
+
"epoch": 0.38,
|
| 1536 |
+
"learning_rate": 3.097554424864591e-05,
|
| 1537 |
+
"loss": 3.4044,
|
| 1538 |
+
"step": 127500
|
| 1539 |
+
},
|
| 1540 |
+
{
|
| 1541 |
+
"epoch": 0.38,
|
| 1542 |
+
"learning_rate": 3.090093853981707e-05,
|
| 1543 |
+
"loss": 3.414,
|
| 1544 |
+
"step": 128000
|
| 1545 |
+
},
|
| 1546 |
+
{
|
| 1547 |
+
"epoch": 0.38,
|
| 1548 |
+
"learning_rate": 3.082633283098823e-05,
|
| 1549 |
+
"loss": 3.3993,
|
| 1550 |
+
"step": 128500
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 0.38,
|
| 1554 |
+
"learning_rate": 3.075172712215939e-05,
|
| 1555 |
+
"loss": 3.3988,
|
| 1556 |
+
"step": 129000
|
| 1557 |
+
},
|
| 1558 |
+
{
|
| 1559 |
+
"epoch": 0.39,
|
| 1560 |
+
"learning_rate": 3.067712141333055e-05,
|
| 1561 |
+
"loss": 3.4115,
|
| 1562 |
+
"step": 129500
|
| 1563 |
+
},
|
| 1564 |
+
{
|
| 1565 |
+
"epoch": 0.39,
|
| 1566 |
+
"learning_rate": 3.060251570450171e-05,
|
| 1567 |
+
"loss": 3.4092,
|
| 1568 |
+
"step": 130000
|
| 1569 |
+
},
|
| 1570 |
+
{
|
| 1571 |
+
"epoch": 0.39,
|
| 1572 |
+
"learning_rate": 3.052790999567287e-05,
|
| 1573 |
+
"loss": 3.4079,
|
| 1574 |
+
"step": 130500
|
| 1575 |
+
},
|
| 1576 |
+
{
|
| 1577 |
+
"epoch": 0.39,
|
| 1578 |
+
"learning_rate": 3.045330428684403e-05,
|
| 1579 |
+
"loss": 3.4052,
|
| 1580 |
+
"step": 131000
|
| 1581 |
+
},
|
| 1582 |
+
{
|
| 1583 |
+
"epoch": 0.39,
|
| 1584 |
+
"learning_rate": 3.037869857801519e-05,
|
| 1585 |
+
"loss": 3.4042,
|
| 1586 |
+
"step": 131500
|
| 1587 |
+
},
|
| 1588 |
+
{
|
| 1589 |
+
"epoch": 0.39,
|
| 1590 |
+
"learning_rate": 3.030409286918635e-05,
|
| 1591 |
+
"loss": 3.4048,
|
| 1592 |
+
"step": 132000
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 0.4,
|
| 1596 |
+
"learning_rate": 3.022948716035751e-05,
|
| 1597 |
+
"loss": 3.394,
|
| 1598 |
+
"step": 132500
|
| 1599 |
+
},
|
| 1600 |
+
{
|
| 1601 |
+
"epoch": 0.4,
|
| 1602 |
+
"learning_rate": 3.0154881451528673e-05,
|
| 1603 |
+
"loss": 3.3992,
|
| 1604 |
+
"step": 133000
|
| 1605 |
+
},
|
| 1606 |
+
{
|
| 1607 |
+
"epoch": 0.4,
|
| 1608 |
+
"learning_rate": 3.0080275742699832e-05,
|
| 1609 |
+
"loss": 3.3902,
|
| 1610 |
+
"step": 133500
|
| 1611 |
+
},
|
| 1612 |
+
{
|
| 1613 |
+
"epoch": 0.4,
|
| 1614 |
+
"learning_rate": 3.0005670033870992e-05,
|
| 1615 |
+
"loss": 3.3865,
|
| 1616 |
+
"step": 134000
|
| 1617 |
+
},
|
| 1618 |
+
{
|
| 1619 |
+
"epoch": 0.4,
|
| 1620 |
+
"learning_rate": 2.993106432504215e-05,
|
| 1621 |
+
"loss": 3.3717,
|
| 1622 |
+
"step": 134500
|
| 1623 |
+
},
|
| 1624 |
+
{
|
| 1625 |
+
"epoch": 0.4,
|
| 1626 |
+
"learning_rate": 2.985645861621331e-05,
|
| 1627 |
+
"loss": 3.3644,
|
| 1628 |
+
"step": 135000
|
| 1629 |
+
},
|
| 1630 |
+
{
|
| 1631 |
+
"epoch": 0.4,
|
| 1632 |
+
"learning_rate": 2.978185290738447e-05,
|
| 1633 |
+
"loss": 3.3742,
|
| 1634 |
+
"step": 135500
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 0.41,
|
| 1638 |
+
"learning_rate": 2.9707247198555634e-05,
|
| 1639 |
+
"loss": 3.3768,
|
| 1640 |
+
"step": 136000
|
| 1641 |
+
},
|
| 1642 |
+
{
|
| 1643 |
+
"epoch": 0.41,
|
| 1644 |
+
"learning_rate": 2.9632641489726797e-05,
|
| 1645 |
+
"loss": 3.3777,
|
| 1646 |
+
"step": 136500
|
| 1647 |
+
},
|
| 1648 |
+
{
|
| 1649 |
+
"epoch": 0.41,
|
| 1650 |
+
"learning_rate": 2.955803578089796e-05,
|
| 1651 |
+
"loss": 3.3829,
|
| 1652 |
+
"step": 137000
|
| 1653 |
+
},
|
| 1654 |
+
{
|
| 1655 |
+
"epoch": 0.41,
|
| 1656 |
+
"learning_rate": 2.948343007206912e-05,
|
| 1657 |
+
"loss": 3.3844,
|
| 1658 |
+
"step": 137500
|
| 1659 |
+
},
|
| 1660 |
+
{
|
| 1661 |
+
"epoch": 0.41,
|
| 1662 |
+
"learning_rate": 2.940882436324028e-05,
|
| 1663 |
+
"loss": 3.3808,
|
| 1664 |
+
"step": 138000
|
| 1665 |
+
},
|
| 1666 |
+
{
|
| 1667 |
+
"epoch": 0.41,
|
| 1668 |
+
"learning_rate": 2.9334218654411438e-05,
|
| 1669 |
+
"loss": 3.383,
|
| 1670 |
+
"step": 138500
|
| 1671 |
+
},
|
| 1672 |
+
{
|
| 1673 |
+
"epoch": 0.41,
|
| 1674 |
+
"learning_rate": 2.9259612945582598e-05,
|
| 1675 |
+
"loss": 3.3472,
|
| 1676 |
+
"step": 139000
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 0.42,
|
| 1680 |
+
"learning_rate": 2.9185007236753757e-05,
|
| 1681 |
+
"loss": 3.3513,
|
| 1682 |
+
"step": 139500
|
| 1683 |
+
},
|
| 1684 |
+
{
|
| 1685 |
+
"epoch": 0.42,
|
| 1686 |
+
"learning_rate": 2.911040152792492e-05,
|
| 1687 |
+
"loss": 3.3708,
|
| 1688 |
+
"step": 140000
|
| 1689 |
+
},
|
| 1690 |
+
{
|
| 1691 |
+
"epoch": 0.42,
|
| 1692 |
+
"learning_rate": 2.903579581909608e-05,
|
| 1693 |
+
"loss": 3.3629,
|
| 1694 |
+
"step": 140500
|
| 1695 |
+
},
|
| 1696 |
+
{
|
| 1697 |
+
"epoch": 0.42,
|
| 1698 |
+
"learning_rate": 2.896119011026724e-05,
|
| 1699 |
+
"loss": 3.347,
|
| 1700 |
+
"step": 141000
|
| 1701 |
+
},
|
| 1702 |
+
{
|
| 1703 |
+
"epoch": 0.42,
|
| 1704 |
+
"learning_rate": 2.88865844014384e-05,
|
| 1705 |
+
"loss": 3.3549,
|
| 1706 |
+
"step": 141500
|
| 1707 |
+
},
|
| 1708 |
+
{
|
| 1709 |
+
"epoch": 0.42,
|
| 1710 |
+
"learning_rate": 2.881197869260956e-05,
|
| 1711 |
+
"loss": 3.3466,
|
| 1712 |
+
"step": 142000
|
| 1713 |
+
},
|
| 1714 |
+
{
|
| 1715 |
+
"epoch": 0.43,
|
| 1716 |
+
"learning_rate": 2.8737372983780718e-05,
|
| 1717 |
+
"loss": 3.3347,
|
| 1718 |
+
"step": 142500
|
| 1719 |
+
},
|
| 1720 |
+
{
|
| 1721 |
+
"epoch": 0.43,
|
| 1722 |
+
"learning_rate": 2.8662767274951878e-05,
|
| 1723 |
+
"loss": 3.3401,
|
| 1724 |
+
"step": 143000
|
| 1725 |
+
},
|
| 1726 |
+
{
|
| 1727 |
+
"epoch": 0.43,
|
| 1728 |
+
"learning_rate": 2.858816156612304e-05,
|
| 1729 |
+
"loss": 3.3469,
|
| 1730 |
+
"step": 143500
|
| 1731 |
+
},
|
| 1732 |
+
{
|
| 1733 |
+
"epoch": 0.43,
|
| 1734 |
+
"learning_rate": 2.85135558572942e-05,
|
| 1735 |
+
"loss": 3.338,
|
| 1736 |
+
"step": 144000
|
| 1737 |
+
},
|
| 1738 |
+
{
|
| 1739 |
+
"epoch": 0.43,
|
| 1740 |
+
"learning_rate": 2.843895014846536e-05,
|
| 1741 |
+
"loss": 3.3338,
|
| 1742 |
+
"step": 144500
|
| 1743 |
+
},
|
| 1744 |
+
{
|
| 1745 |
+
"epoch": 0.43,
|
| 1746 |
+
"learning_rate": 2.836434443963652e-05,
|
| 1747 |
+
"loss": 3.3499,
|
| 1748 |
+
"step": 145000
|
| 1749 |
+
},
|
| 1750 |
+
{
|
| 1751 |
+
"epoch": 0.43,
|
| 1752 |
+
"learning_rate": 2.828973873080768e-05,
|
| 1753 |
+
"loss": 3.3313,
|
| 1754 |
+
"step": 145500
|
| 1755 |
+
},
|
| 1756 |
+
{
|
| 1757 |
+
"epoch": 0.44,
|
| 1758 |
+
"learning_rate": 2.8215133021978845e-05,
|
| 1759 |
+
"loss": 3.3263,
|
| 1760 |
+
"step": 146000
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"epoch": 0.44,
|
| 1764 |
+
"learning_rate": 2.8140527313150005e-05,
|
| 1765 |
+
"loss": 3.3386,
|
| 1766 |
+
"step": 146500
|
| 1767 |
+
},
|
| 1768 |
+
{
|
| 1769 |
+
"epoch": 0.44,
|
| 1770 |
+
"learning_rate": 2.8065921604321165e-05,
|
| 1771 |
+
"loss": 3.3229,
|
| 1772 |
+
"step": 147000
|
| 1773 |
+
},
|
| 1774 |
+
{
|
| 1775 |
+
"epoch": 0.44,
|
| 1776 |
+
"learning_rate": 2.7991315895492327e-05,
|
| 1777 |
+
"loss": 3.3186,
|
| 1778 |
+
"step": 147500
|
| 1779 |
+
},
|
| 1780 |
+
{
|
| 1781 |
+
"epoch": 0.44,
|
| 1782 |
+
"learning_rate": 2.7916710186663487e-05,
|
| 1783 |
+
"loss": 3.3272,
|
| 1784 |
+
"step": 148000
|
| 1785 |
+
},
|
| 1786 |
+
{
|
| 1787 |
+
"epoch": 0.44,
|
| 1788 |
+
"learning_rate": 2.7842104477834647e-05,
|
| 1789 |
+
"loss": 3.3052,
|
| 1790 |
+
"step": 148500
|
| 1791 |
+
},
|
| 1792 |
+
{
|
| 1793 |
+
"epoch": 0.44,
|
| 1794 |
+
"learning_rate": 2.7767498769005806e-05,
|
| 1795 |
+
"loss": 3.321,
|
| 1796 |
+
"step": 149000
|
| 1797 |
+
},
|
| 1798 |
+
{
|
| 1799 |
+
"epoch": 0.45,
|
| 1800 |
+
"learning_rate": 2.7692893060176966e-05,
|
| 1801 |
+
"loss": 3.3188,
|
| 1802 |
+
"step": 149500
|
| 1803 |
+
},
|
| 1804 |
+
{
|
| 1805 |
+
"epoch": 0.45,
|
| 1806 |
+
"learning_rate": 2.7618287351348125e-05,
|
| 1807 |
+
"loss": 3.3118,
|
| 1808 |
+
"step": 150000
|
| 1809 |
+
},
|
| 1810 |
+
{
|
| 1811 |
+
"epoch": 0.45,
|
| 1812 |
+
"learning_rate": 2.7543681642519288e-05,
|
| 1813 |
+
"loss": 3.3176,
|
| 1814 |
+
"step": 150500
|
| 1815 |
+
},
|
| 1816 |
+
{
|
| 1817 |
+
"epoch": 0.45,
|
| 1818 |
+
"learning_rate": 2.7469075933690448e-05,
|
| 1819 |
+
"loss": 3.3039,
|
| 1820 |
+
"step": 151000
|
| 1821 |
+
},
|
| 1822 |
+
{
|
| 1823 |
+
"epoch": 0.45,
|
| 1824 |
+
"learning_rate": 2.7394470224861607e-05,
|
| 1825 |
+
"loss": 3.2896,
|
| 1826 |
+
"step": 151500
|
| 1827 |
+
},
|
| 1828 |
+
{
|
| 1829 |
+
"epoch": 0.45,
|
| 1830 |
+
"learning_rate": 2.7319864516032767e-05,
|
| 1831 |
+
"loss": 3.2964,
|
| 1832 |
+
"step": 152000
|
| 1833 |
+
},
|
| 1834 |
+
{
|
| 1835 |
+
"epoch": 0.46,
|
| 1836 |
+
"learning_rate": 2.7245258807203927e-05,
|
| 1837 |
+
"loss": 3.2906,
|
| 1838 |
+
"step": 152500
|
| 1839 |
+
},
|
| 1840 |
+
{
|
| 1841 |
+
"epoch": 0.46,
|
| 1842 |
+
"learning_rate": 2.7170653098375086e-05,
|
| 1843 |
+
"loss": 3.2886,
|
| 1844 |
+
"step": 153000
|
| 1845 |
+
},
|
| 1846 |
+
{
|
| 1847 |
+
"epoch": 0.46,
|
| 1848 |
+
"learning_rate": 2.709604738954625e-05,
|
| 1849 |
+
"loss": 3.2987,
|
| 1850 |
+
"step": 153500
|
| 1851 |
+
},
|
| 1852 |
+
{
|
| 1853 |
+
"epoch": 0.46,
|
| 1854 |
+
"learning_rate": 2.702144168071741e-05,
|
| 1855 |
+
"loss": 3.272,
|
| 1856 |
+
"step": 154000
|
| 1857 |
+
},
|
| 1858 |
+
{
|
| 1859 |
+
"epoch": 0.46,
|
| 1860 |
+
"learning_rate": 2.6946835971888568e-05,
|
| 1861 |
+
"loss": 3.2735,
|
| 1862 |
+
"step": 154500
|
| 1863 |
+
},
|
| 1864 |
+
{
|
| 1865 |
+
"epoch": 0.46,
|
| 1866 |
+
"learning_rate": 2.6872230263059735e-05,
|
| 1867 |
+
"loss": 3.2632,
|
| 1868 |
+
"step": 155000
|
| 1869 |
+
},
|
| 1870 |
+
{
|
| 1871 |
+
"epoch": 0.46,
|
| 1872 |
+
"learning_rate": 2.6797624554230894e-05,
|
| 1873 |
+
"loss": 3.2933,
|
| 1874 |
+
"step": 155500
|
| 1875 |
+
},
|
| 1876 |
+
{
|
| 1877 |
+
"epoch": 0.47,
|
| 1878 |
+
"learning_rate": 2.6723018845402054e-05,
|
| 1879 |
+
"loss": 3.2911,
|
| 1880 |
+
"step": 156000
|
| 1881 |
+
},
|
| 1882 |
+
{
|
| 1883 |
+
"epoch": 0.47,
|
| 1884 |
+
"learning_rate": 2.6648413136573213e-05,
|
| 1885 |
+
"loss": 3.3155,
|
| 1886 |
+
"step": 156500
|
| 1887 |
+
},
|
| 1888 |
+
{
|
| 1889 |
+
"epoch": 0.47,
|
| 1890 |
+
"learning_rate": 2.6573807427744373e-05,
|
| 1891 |
+
"loss": 3.2821,
|
| 1892 |
+
"step": 157000
|
| 1893 |
+
},
|
| 1894 |
+
{
|
| 1895 |
+
"epoch": 0.47,
|
| 1896 |
+
"learning_rate": 2.6499201718915532e-05,
|
| 1897 |
+
"loss": 3.287,
|
| 1898 |
+
"step": 157500
|
| 1899 |
+
},
|
| 1900 |
+
{
|
| 1901 |
+
"epoch": 0.47,
|
| 1902 |
+
"learning_rate": 2.6424596010086695e-05,
|
| 1903 |
+
"loss": 3.2701,
|
| 1904 |
+
"step": 158000
|
| 1905 |
+
},
|
| 1906 |
+
{
|
| 1907 |
+
"epoch": 0.47,
|
| 1908 |
+
"learning_rate": 2.6349990301257855e-05,
|
| 1909 |
+
"loss": 3.2554,
|
| 1910 |
+
"step": 158500
|
| 1911 |
+
},
|
| 1912 |
+
{
|
| 1913 |
+
"epoch": 0.47,
|
| 1914 |
+
"learning_rate": 2.6275384592429015e-05,
|
| 1915 |
+
"loss": 3.2938,
|
| 1916 |
+
"step": 159000
|
| 1917 |
+
},
|
| 1918 |
+
{
|
| 1919 |
+
"epoch": 0.48,
|
| 1920 |
+
"learning_rate": 2.6200778883600174e-05,
|
| 1921 |
+
"loss": 3.2812,
|
| 1922 |
+
"step": 159500
|
| 1923 |
+
},
|
| 1924 |
+
{
|
| 1925 |
+
"epoch": 0.48,
|
| 1926 |
+
"learning_rate": 2.6126173174771334e-05,
|
| 1927 |
+
"loss": 3.2739,
|
| 1928 |
+
"step": 160000
|
| 1929 |
+
},
|
| 1930 |
+
{
|
| 1931 |
+
"epoch": 0.48,
|
| 1932 |
+
"learning_rate": 2.6051567465942493e-05,
|
| 1933 |
+
"loss": 3.2512,
|
| 1934 |
+
"step": 160500
|
| 1935 |
+
},
|
| 1936 |
+
{
|
| 1937 |
+
"epoch": 0.48,
|
| 1938 |
+
"learning_rate": 2.5976961757113656e-05,
|
| 1939 |
+
"loss": 3.2567,
|
| 1940 |
+
"step": 161000
|
| 1941 |
+
},
|
| 1942 |
+
{
|
| 1943 |
+
"epoch": 0.48,
|
| 1944 |
+
"learning_rate": 2.5902356048284816e-05,
|
| 1945 |
+
"loss": 3.2687,
|
| 1946 |
+
"step": 161500
|
| 1947 |
+
},
|
| 1948 |
+
{
|
| 1949 |
+
"epoch": 0.48,
|
| 1950 |
+
"learning_rate": 2.5827750339455975e-05,
|
| 1951 |
+
"loss": 3.2876,
|
| 1952 |
+
"step": 162000
|
| 1953 |
+
},
|
| 1954 |
+
{
|
| 1955 |
+
"epoch": 0.48,
|
| 1956 |
+
"learning_rate": 2.5753144630627135e-05,
|
| 1957 |
+
"loss": 3.2741,
|
| 1958 |
+
"step": 162500
|
| 1959 |
+
},
|
| 1960 |
+
{
|
| 1961 |
+
"epoch": 0.49,
|
| 1962 |
+
"learning_rate": 2.5678538921798295e-05,
|
| 1963 |
+
"loss": 3.2556,
|
| 1964 |
+
"step": 163000
|
| 1965 |
+
},
|
| 1966 |
+
{
|
| 1967 |
+
"epoch": 0.49,
|
| 1968 |
+
"learning_rate": 2.5603933212969454e-05,
|
| 1969 |
+
"loss": 3.2568,
|
| 1970 |
+
"step": 163500
|
| 1971 |
+
},
|
| 1972 |
+
{
|
| 1973 |
+
"epoch": 0.49,
|
| 1974 |
+
"learning_rate": 2.5529327504140617e-05,
|
| 1975 |
+
"loss": 3.2432,
|
| 1976 |
+
"step": 164000
|
| 1977 |
+
},
|
| 1978 |
+
{
|
| 1979 |
+
"epoch": 0.49,
|
| 1980 |
+
"learning_rate": 2.545472179531178e-05,
|
| 1981 |
+
"loss": 3.2467,
|
| 1982 |
+
"step": 164500
|
| 1983 |
+
},
|
| 1984 |
+
{
|
| 1985 |
+
"epoch": 0.49,
|
| 1986 |
+
"learning_rate": 2.538011608648294e-05,
|
| 1987 |
+
"loss": 3.2575,
|
| 1988 |
+
"step": 165000
|
| 1989 |
+
},
|
| 1990 |
+
{
|
| 1991 |
+
"epoch": 0.49,
|
| 1992 |
+
"learning_rate": 2.5305510377654103e-05,
|
| 1993 |
+
"loss": 3.248,
|
| 1994 |
+
"step": 165500
|
| 1995 |
+
},
|
| 1996 |
+
{
|
| 1997 |
+
"epoch": 0.5,
|
| 1998 |
+
"learning_rate": 2.5230904668825262e-05,
|
| 1999 |
+
"loss": 3.2438,
|
| 2000 |
+
"step": 166000
|
| 2001 |
+
},
|
| 2002 |
+
{
|
| 2003 |
+
"epoch": 0.5,
|
| 2004 |
+
"learning_rate": 2.5156298959996422e-05,
|
| 2005 |
+
"loss": 3.2516,
|
| 2006 |
+
"step": 166500
|
| 2007 |
+
},
|
| 2008 |
+
{
|
| 2009 |
+
"epoch": 0.5,
|
| 2010 |
+
"learning_rate": 2.508169325116758e-05,
|
| 2011 |
+
"loss": 3.2483,
|
| 2012 |
+
"step": 167000
|
| 2013 |
+
},
|
| 2014 |
+
{
|
| 2015 |
+
"epoch": 0.5,
|
| 2016 |
+
"learning_rate": 2.500708754233874e-05,
|
| 2017 |
+
"loss": 3.2313,
|
| 2018 |
+
"step": 167500
|
| 2019 |
+
},
|
| 2020 |
+
{
|
| 2021 |
+
"epoch": 0.5,
|
| 2022 |
+
"learning_rate": 2.49324818335099e-05,
|
| 2023 |
+
"loss": 3.2331,
|
| 2024 |
+
"step": 168000
|
| 2025 |
+
},
|
| 2026 |
+
{
|
| 2027 |
+
"epoch": 0.5,
|
| 2028 |
+
"learning_rate": 2.4857876124681063e-05,
|
| 2029 |
+
"loss": 3.2462,
|
| 2030 |
+
"step": 168500
|
| 2031 |
+
},
|
| 2032 |
+
{
|
| 2033 |
+
"epoch": 0.5,
|
| 2034 |
+
"learning_rate": 2.4783270415852223e-05,
|
| 2035 |
+
"loss": 3.2219,
|
| 2036 |
+
"step": 169000
|
| 2037 |
+
},
|
| 2038 |
+
{
|
| 2039 |
+
"epoch": 0.51,
|
| 2040 |
+
"learning_rate": 2.4708664707023383e-05,
|
| 2041 |
+
"loss": 3.2406,
|
| 2042 |
+
"step": 169500
|
| 2043 |
+
},
|
| 2044 |
+
{
|
| 2045 |
+
"epoch": 0.51,
|
| 2046 |
+
"learning_rate": 2.4634058998194542e-05,
|
| 2047 |
+
"loss": 3.2086,
|
| 2048 |
+
"step": 170000
|
| 2049 |
+
},
|
| 2050 |
+
{
|
| 2051 |
+
"epoch": 0.51,
|
| 2052 |
+
"learning_rate": 2.4559453289365702e-05,
|
| 2053 |
+
"loss": 3.2183,
|
| 2054 |
+
"step": 170500
|
| 2055 |
+
},
|
| 2056 |
+
{
|
| 2057 |
+
"epoch": 0.51,
|
| 2058 |
+
"learning_rate": 2.448484758053686e-05,
|
| 2059 |
+
"loss": 3.222,
|
| 2060 |
+
"step": 171000
|
| 2061 |
+
},
|
| 2062 |
+
{
|
| 2063 |
+
"epoch": 0.51,
|
| 2064 |
+
"learning_rate": 2.4410241871708024e-05,
|
| 2065 |
+
"loss": 3.2144,
|
| 2066 |
+
"step": 171500
|
| 2067 |
+
},
|
| 2068 |
+
{
|
| 2069 |
+
"epoch": 0.51,
|
| 2070 |
+
"learning_rate": 2.4335636162879187e-05,
|
| 2071 |
+
"loss": 3.2212,
|
| 2072 |
+
"step": 172000
|
| 2073 |
+
},
|
| 2074 |
+
{
|
| 2075 |
+
"epoch": 0.51,
|
| 2076 |
+
"learning_rate": 2.4261030454050347e-05,
|
| 2077 |
+
"loss": 3.2072,
|
| 2078 |
+
"step": 172500
|
| 2079 |
+
},
|
| 2080 |
+
{
|
| 2081 |
+
"epoch": 0.52,
|
| 2082 |
+
"learning_rate": 2.4186424745221506e-05,
|
| 2083 |
+
"loss": 3.2082,
|
| 2084 |
+
"step": 173000
|
| 2085 |
+
},
|
| 2086 |
+
{
|
| 2087 |
+
"epoch": 0.52,
|
| 2088 |
+
"learning_rate": 2.4111819036392666e-05,
|
| 2089 |
+
"loss": 3.2211,
|
| 2090 |
+
"step": 173500
|
| 2091 |
+
},
|
| 2092 |
+
{
|
| 2093 |
+
"epoch": 0.52,
|
| 2094 |
+
"learning_rate": 2.4037213327563826e-05,
|
| 2095 |
+
"loss": 3.1991,
|
| 2096 |
+
"step": 174000
|
| 2097 |
+
},
|
| 2098 |
+
{
|
| 2099 |
+
"epoch": 0.52,
|
| 2100 |
+
"learning_rate": 2.3962607618734985e-05,
|
| 2101 |
+
"loss": 3.222,
|
| 2102 |
+
"step": 174500
|
| 2103 |
+
},
|
| 2104 |
+
{
|
| 2105 |
+
"epoch": 0.52,
|
| 2106 |
+
"learning_rate": 2.3888001909906148e-05,
|
| 2107 |
+
"loss": 3.1956,
|
| 2108 |
+
"step": 175000
|
| 2109 |
+
},
|
| 2110 |
+
{
|
| 2111 |
+
"epoch": 0.52,
|
| 2112 |
+
"learning_rate": 2.3813396201077308e-05,
|
| 2113 |
+
"loss": 3.2101,
|
| 2114 |
+
"step": 175500
|
| 2115 |
+
},
|
| 2116 |
+
{
|
| 2117 |
+
"epoch": 0.53,
|
| 2118 |
+
"learning_rate": 2.3738790492248467e-05,
|
| 2119 |
+
"loss": 3.197,
|
| 2120 |
+
"step": 176000
|
| 2121 |
+
},
|
| 2122 |
+
{
|
| 2123 |
+
"epoch": 0.53,
|
| 2124 |
+
"learning_rate": 2.366418478341963e-05,
|
| 2125 |
+
"loss": 3.2057,
|
| 2126 |
+
"step": 176500
|
| 2127 |
+
},
|
| 2128 |
+
{
|
| 2129 |
+
"epoch": 0.53,
|
| 2130 |
+
"learning_rate": 2.358957907459079e-05,
|
| 2131 |
+
"loss": 3.1931,
|
| 2132 |
+
"step": 177000
|
| 2133 |
+
},
|
| 2134 |
+
{
|
| 2135 |
+
"epoch": 0.53,
|
| 2136 |
+
"learning_rate": 2.351497336576195e-05,
|
| 2137 |
+
"loss": 3.2,
|
| 2138 |
+
"step": 177500
|
| 2139 |
+
},
|
| 2140 |
+
{
|
| 2141 |
+
"epoch": 0.53,
|
| 2142 |
+
"learning_rate": 2.344036765693311e-05,
|
| 2143 |
+
"loss": 3.1849,
|
| 2144 |
+
"step": 178000
|
| 2145 |
+
},
|
| 2146 |
+
{
|
| 2147 |
+
"epoch": 0.53,
|
| 2148 |
+
"learning_rate": 2.336576194810427e-05,
|
| 2149 |
+
"loss": 3.2024,
|
| 2150 |
+
"step": 178500
|
| 2151 |
+
},
|
| 2152 |
+
{
|
| 2153 |
+
"epoch": 0.53,
|
| 2154 |
+
"learning_rate": 2.329115623927543e-05,
|
| 2155 |
+
"loss": 3.1923,
|
| 2156 |
+
"step": 179000
|
| 2157 |
+
},
|
| 2158 |
+
{
|
| 2159 |
+
"epoch": 0.54,
|
| 2160 |
+
"learning_rate": 2.321655053044659e-05,
|
| 2161 |
+
"loss": 3.1988,
|
| 2162 |
+
"step": 179500
|
| 2163 |
+
},
|
| 2164 |
+
{
|
| 2165 |
+
"epoch": 0.54,
|
| 2166 |
+
"learning_rate": 2.314194482161775e-05,
|
| 2167 |
+
"loss": 3.1788,
|
| 2168 |
+
"step": 180000
|
| 2169 |
+
},
|
| 2170 |
+
{
|
| 2171 |
+
"epoch": 0.54,
|
| 2172 |
+
"learning_rate": 2.306733911278891e-05,
|
| 2173 |
+
"loss": 3.1927,
|
| 2174 |
+
"step": 180500
|
| 2175 |
+
},
|
| 2176 |
+
{
|
| 2177 |
+
"epoch": 0.54,
|
| 2178 |
+
"learning_rate": 2.2992733403960073e-05,
|
| 2179 |
+
"loss": 3.1854,
|
| 2180 |
+
"step": 181000
|
| 2181 |
+
},
|
| 2182 |
+
{
|
| 2183 |
+
"epoch": 0.54,
|
| 2184 |
+
"learning_rate": 2.2918127695131233e-05,
|
| 2185 |
+
"loss": 3.2029,
|
| 2186 |
+
"step": 181500
|
| 2187 |
+
},
|
| 2188 |
+
{
|
| 2189 |
+
"epoch": 0.54,
|
| 2190 |
+
"learning_rate": 2.2843521986302392e-05,
|
| 2191 |
+
"loss": 3.1958,
|
| 2192 |
+
"step": 182000
|
| 2193 |
+
},
|
| 2194 |
+
{
|
| 2195 |
+
"epoch": 0.54,
|
| 2196 |
+
"learning_rate": 2.2768916277473555e-05,
|
| 2197 |
+
"loss": 3.1791,
|
| 2198 |
+
"step": 182500
|
| 2199 |
+
},
|
| 2200 |
+
{
|
| 2201 |
+
"epoch": 0.55,
|
| 2202 |
+
"learning_rate": 2.2694310568644715e-05,
|
| 2203 |
+
"loss": 3.1791,
|
| 2204 |
+
"step": 183000
|
| 2205 |
+
},
|
| 2206 |
+
{
|
| 2207 |
+
"epoch": 0.55,
|
| 2208 |
+
"learning_rate": 2.2619704859815874e-05,
|
| 2209 |
+
"loss": 3.1921,
|
| 2210 |
+
"step": 183500
|
| 2211 |
+
},
|
| 2212 |
+
{
|
| 2213 |
+
"epoch": 0.55,
|
| 2214 |
+
"learning_rate": 2.2545099150987034e-05,
|
| 2215 |
+
"loss": 3.193,
|
| 2216 |
+
"step": 184000
|
| 2217 |
+
},
|
| 2218 |
+
{
|
| 2219 |
+
"epoch": 0.55,
|
| 2220 |
+
"learning_rate": 2.2470493442158194e-05,
|
| 2221 |
+
"loss": 3.2009,
|
| 2222 |
+
"step": 184500
|
| 2223 |
+
},
|
| 2224 |
+
{
|
| 2225 |
+
"epoch": 0.55,
|
| 2226 |
+
"learning_rate": 2.2395887733329353e-05,
|
| 2227 |
+
"loss": 3.1873,
|
| 2228 |
+
"step": 185000
|
| 2229 |
+
},
|
| 2230 |
+
{
|
| 2231 |
+
"epoch": 0.55,
|
| 2232 |
+
"learning_rate": 2.2321282024500516e-05,
|
| 2233 |
+
"loss": 3.1703,
|
| 2234 |
+
"step": 185500
|
| 2235 |
+
},
|
| 2236 |
+
{
|
| 2237 |
+
"epoch": 0.56,
|
| 2238 |
+
"learning_rate": 2.2246676315671676e-05,
|
| 2239 |
+
"loss": 3.1822,
|
| 2240 |
+
"step": 186000
|
| 2241 |
+
},
|
| 2242 |
+
{
|
| 2243 |
+
"epoch": 0.56,
|
| 2244 |
+
"learning_rate": 2.217207060684284e-05,
|
| 2245 |
+
"loss": 3.1651,
|
| 2246 |
+
"step": 186500
|
| 2247 |
+
},
|
| 2248 |
+
{
|
| 2249 |
+
"epoch": 0.56,
|
| 2250 |
+
"learning_rate": 2.2097464898013998e-05,
|
| 2251 |
+
"loss": 3.161,
|
| 2252 |
+
"step": 187000
|
| 2253 |
+
},
|
| 2254 |
+
{
|
| 2255 |
+
"epoch": 0.56,
|
| 2256 |
+
"learning_rate": 2.2022859189185158e-05,
|
| 2257 |
+
"loss": 3.1794,
|
| 2258 |
+
"step": 187500
|
| 2259 |
+
},
|
| 2260 |
+
{
|
| 2261 |
+
"epoch": 0.56,
|
| 2262 |
+
"learning_rate": 2.1948253480356317e-05,
|
| 2263 |
+
"loss": 3.166,
|
| 2264 |
+
"step": 188000
|
| 2265 |
+
},
|
| 2266 |
+
{
|
| 2267 |
+
"epoch": 0.56,
|
| 2268 |
+
"learning_rate": 2.1873647771527477e-05,
|
| 2269 |
+
"loss": 3.1738,
|
| 2270 |
+
"step": 188500
|
| 2271 |
+
},
|
| 2272 |
+
{
|
| 2273 |
+
"epoch": 0.56,
|
| 2274 |
+
"learning_rate": 2.1799042062698636e-05,
|
| 2275 |
+
"loss": 3.1563,
|
| 2276 |
+
"step": 189000
|
| 2277 |
+
},
|
| 2278 |
+
{
|
| 2279 |
+
"epoch": 0.57,
|
| 2280 |
+
"learning_rate": 2.17244363538698e-05,
|
| 2281 |
+
"loss": 3.1549,
|
| 2282 |
+
"step": 189500
|
| 2283 |
+
},
|
| 2284 |
+
{
|
| 2285 |
+
"epoch": 0.57,
|
| 2286 |
+
"learning_rate": 2.164983064504096e-05,
|
| 2287 |
+
"loss": 3.152,
|
| 2288 |
+
"step": 190000
|
| 2289 |
+
},
|
| 2290 |
+
{
|
| 2291 |
+
"epoch": 0.57,
|
| 2292 |
+
"learning_rate": 2.1575224936212122e-05,
|
| 2293 |
+
"loss": 3.1475,
|
| 2294 |
+
"step": 190500
|
| 2295 |
+
},
|
| 2296 |
+
{
|
| 2297 |
+
"epoch": 0.57,
|
| 2298 |
+
"learning_rate": 2.150061922738328e-05,
|
| 2299 |
+
"loss": 3.1561,
|
| 2300 |
+
"step": 191000
|
| 2301 |
+
},
|
| 2302 |
+
{
|
| 2303 |
+
"epoch": 0.57,
|
| 2304 |
+
"learning_rate": 2.142601351855444e-05,
|
| 2305 |
+
"loss": 3.1452,
|
| 2306 |
+
"step": 191500
|
| 2307 |
+
},
|
| 2308 |
+
{
|
| 2309 |
+
"epoch": 0.57,
|
| 2310 |
+
"learning_rate": 2.13514078097256e-05,
|
| 2311 |
+
"loss": 3.1559,
|
| 2312 |
+
"step": 192000
|
| 2313 |
+
},
|
| 2314 |
+
{
|
| 2315 |
+
"epoch": 0.57,
|
| 2316 |
+
"learning_rate": 2.127680210089676e-05,
|
| 2317 |
+
"loss": 3.1523,
|
| 2318 |
+
"step": 192500
|
| 2319 |
+
},
|
| 2320 |
+
{
|
| 2321 |
+
"epoch": 0.58,
|
| 2322 |
+
"learning_rate": 2.1202196392067923e-05,
|
| 2323 |
+
"loss": 3.1547,
|
| 2324 |
+
"step": 193000
|
| 2325 |
+
},
|
| 2326 |
+
{
|
| 2327 |
+
"epoch": 0.58,
|
| 2328 |
+
"learning_rate": 2.1127590683239083e-05,
|
| 2329 |
+
"loss": 3.1415,
|
| 2330 |
+
"step": 193500
|
| 2331 |
+
},
|
| 2332 |
+
{
|
| 2333 |
+
"epoch": 0.58,
|
| 2334 |
+
"learning_rate": 2.1052984974410242e-05,
|
| 2335 |
+
"loss": 3.1577,
|
| 2336 |
+
"step": 194000
|
| 2337 |
+
},
|
| 2338 |
+
{
|
| 2339 |
+
"epoch": 0.58,
|
| 2340 |
+
"learning_rate": 2.0978379265581402e-05,
|
| 2341 |
+
"loss": 3.1476,
|
| 2342 |
+
"step": 194500
|
| 2343 |
+
},
|
| 2344 |
+
{
|
| 2345 |
+
"epoch": 0.58,
|
| 2346 |
+
"learning_rate": 2.0903773556752565e-05,
|
| 2347 |
+
"loss": 3.1473,
|
| 2348 |
+
"step": 195000
|
| 2349 |
+
},
|
| 2350 |
+
{
|
| 2351 |
+
"epoch": 0.58,
|
| 2352 |
+
"learning_rate": 2.0829167847923725e-05,
|
| 2353 |
+
"loss": 3.1553,
|
| 2354 |
+
"step": 195500
|
| 2355 |
+
},
|
| 2356 |
+
{
|
| 2357 |
+
"epoch": 0.58,
|
| 2358 |
+
"learning_rate": 2.0754562139094884e-05,
|
| 2359 |
+
"loss": 3.1435,
|
| 2360 |
+
"step": 196000
|
| 2361 |
+
},
|
| 2362 |
+
{
|
| 2363 |
+
"epoch": 0.59,
|
| 2364 |
+
"learning_rate": 2.0679956430266047e-05,
|
| 2365 |
+
"loss": 3.1384,
|
| 2366 |
+
"step": 196500
|
| 2367 |
+
},
|
| 2368 |
+
{
|
| 2369 |
+
"epoch": 0.59,
|
| 2370 |
+
"learning_rate": 2.0605350721437207e-05,
|
| 2371 |
+
"loss": 3.1253,
|
| 2372 |
+
"step": 197000
|
| 2373 |
+
},
|
| 2374 |
+
{
|
| 2375 |
+
"epoch": 0.59,
|
| 2376 |
+
"learning_rate": 2.0530745012608366e-05,
|
| 2377 |
+
"loss": 3.1279,
|
| 2378 |
+
"step": 197500
|
| 2379 |
+
},
|
| 2380 |
+
{
|
| 2381 |
+
"epoch": 0.59,
|
| 2382 |
+
"learning_rate": 2.0456139303779526e-05,
|
| 2383 |
+
"loss": 3.1418,
|
| 2384 |
+
"step": 198000
|
| 2385 |
+
},
|
| 2386 |
+
{
|
| 2387 |
+
"epoch": 0.59,
|
| 2388 |
+
"learning_rate": 2.0381533594950685e-05,
|
| 2389 |
+
"loss": 3.1448,
|
| 2390 |
+
"step": 198500
|
| 2391 |
+
},
|
| 2392 |
+
{
|
| 2393 |
+
"epoch": 0.59,
|
| 2394 |
+
"learning_rate": 2.0306927886121845e-05,
|
| 2395 |
+
"loss": 3.1398,
|
| 2396 |
+
"step": 199000
|
| 2397 |
+
},
|
| 2398 |
+
{
|
| 2399 |
+
"epoch": 0.6,
|
| 2400 |
+
"learning_rate": 2.0232322177293004e-05,
|
| 2401 |
+
"loss": 3.1293,
|
| 2402 |
+
"step": 199500
|
| 2403 |
+
},
|
| 2404 |
+
{
|
| 2405 |
+
"epoch": 0.6,
|
| 2406 |
+
"learning_rate": 2.0157716468464167e-05,
|
| 2407 |
+
"loss": 3.1252,
|
| 2408 |
+
"step": 200000
|
| 2409 |
+
},
|
| 2410 |
+
{
|
| 2411 |
+
"epoch": 0.6,
|
| 2412 |
+
"learning_rate": 2.008311075963533e-05,
|
| 2413 |
+
"loss": 3.1121,
|
| 2414 |
+
"step": 200500
|
| 2415 |
+
},
|
| 2416 |
+
{
|
| 2417 |
+
"epoch": 0.6,
|
| 2418 |
+
"learning_rate": 2.000850505080649e-05,
|
| 2419 |
+
"loss": 3.1314,
|
| 2420 |
+
"step": 201000
|
| 2421 |
+
},
|
| 2422 |
+
{
|
| 2423 |
+
"epoch": 0.6,
|
| 2424 |
+
"learning_rate": 1.993389934197765e-05,
|
| 2425 |
+
"loss": 3.1345,
|
| 2426 |
+
"step": 201500
|
| 2427 |
+
},
|
| 2428 |
+
{
|
| 2429 |
+
"epoch": 0.6,
|
| 2430 |
+
"learning_rate": 1.985929363314881e-05,
|
| 2431 |
+
"loss": 3.1291,
|
| 2432 |
+
"step": 202000
|
| 2433 |
+
},
|
| 2434 |
+
{
|
| 2435 |
+
"epoch": 0.6,
|
| 2436 |
+
"learning_rate": 1.978468792431997e-05,
|
| 2437 |
+
"loss": 3.1316,
|
| 2438 |
+
"step": 202500
|
| 2439 |
+
},
|
| 2440 |
+
{
|
| 2441 |
+
"epoch": 0.61,
|
| 2442 |
+
"learning_rate": 1.9710082215491128e-05,
|
| 2443 |
+
"loss": 3.1365,
|
| 2444 |
+
"step": 203000
|
| 2445 |
+
},
|
| 2446 |
+
{
|
| 2447 |
+
"epoch": 0.61,
|
| 2448 |
+
"learning_rate": 1.963547650666229e-05,
|
| 2449 |
+
"loss": 3.1363,
|
| 2450 |
+
"step": 203500
|
| 2451 |
+
},
|
| 2452 |
+
{
|
| 2453 |
+
"epoch": 0.61,
|
| 2454 |
+
"learning_rate": 1.956087079783345e-05,
|
| 2455 |
+
"loss": 3.1304,
|
| 2456 |
+
"step": 204000
|
| 2457 |
+
},
|
| 2458 |
+
{
|
| 2459 |
+
"epoch": 0.61,
|
| 2460 |
+
"learning_rate": 1.9486265089004614e-05,
|
| 2461 |
+
"loss": 3.1117,
|
| 2462 |
+
"step": 204500
|
| 2463 |
+
},
|
| 2464 |
+
{
|
| 2465 |
+
"epoch": 0.61,
|
| 2466 |
+
"learning_rate": 1.9411659380175773e-05,
|
| 2467 |
+
"loss": 3.116,
|
| 2468 |
+
"step": 205000
|
| 2469 |
+
},
|
| 2470 |
+
{
|
| 2471 |
+
"epoch": 0.61,
|
| 2472 |
+
"learning_rate": 1.9337053671346933e-05,
|
| 2473 |
+
"loss": 3.1004,
|
| 2474 |
+
"step": 205500
|
| 2475 |
+
},
|
| 2476 |
+
{
|
| 2477 |
+
"epoch": 0.61,
|
| 2478 |
+
"learning_rate": 1.9262447962518092e-05,
|
| 2479 |
+
"loss": 3.1145,
|
| 2480 |
+
"step": 206000
|
| 2481 |
+
},
|
| 2482 |
+
{
|
| 2483 |
+
"epoch": 0.62,
|
| 2484 |
+
"learning_rate": 1.9187842253689252e-05,
|
| 2485 |
+
"loss": 3.1189,
|
| 2486 |
+
"step": 206500
|
| 2487 |
+
},
|
| 2488 |
+
{
|
| 2489 |
+
"epoch": 0.62,
|
| 2490 |
+
"learning_rate": 1.9113236544860415e-05,
|
| 2491 |
+
"loss": 3.1107,
|
| 2492 |
+
"step": 207000
|
| 2493 |
+
},
|
| 2494 |
+
{
|
| 2495 |
+
"epoch": 0.62,
|
| 2496 |
+
"learning_rate": 1.9038630836031575e-05,
|
| 2497 |
+
"loss": 3.1045,
|
| 2498 |
+
"step": 207500
|
| 2499 |
+
},
|
| 2500 |
+
{
|
| 2501 |
+
"epoch": 0.62,
|
| 2502 |
+
"learning_rate": 1.8964025127202734e-05,
|
| 2503 |
+
"loss": 3.1394,
|
| 2504 |
+
"step": 208000
|
| 2505 |
+
},
|
| 2506 |
+
{
|
| 2507 |
+
"epoch": 0.62,
|
| 2508 |
+
"learning_rate": 1.8889419418373894e-05,
|
| 2509 |
+
"loss": 3.1042,
|
| 2510 |
+
"step": 208500
|
| 2511 |
+
},
|
| 2512 |
+
{
|
| 2513 |
+
"epoch": 0.62,
|
| 2514 |
+
"learning_rate": 1.8814813709545057e-05,
|
| 2515 |
+
"loss": 3.1121,
|
| 2516 |
+
"step": 209000
|
| 2517 |
+
},
|
| 2518 |
+
{
|
| 2519 |
+
"epoch": 0.63,
|
| 2520 |
+
"learning_rate": 1.8740208000716216e-05,
|
| 2521 |
+
"loss": 3.1009,
|
| 2522 |
+
"step": 209500
|
| 2523 |
+
},
|
| 2524 |
+
{
|
| 2525 |
+
"epoch": 0.63,
|
| 2526 |
+
"learning_rate": 1.8665602291887376e-05,
|
| 2527 |
+
"loss": 3.1056,
|
| 2528 |
+
"step": 210000
|
| 2529 |
+
},
|
| 2530 |
+
{
|
| 2531 |
+
"epoch": 0.63,
|
| 2532 |
+
"learning_rate": 1.8590996583058535e-05,
|
| 2533 |
+
"loss": 3.1007,
|
| 2534 |
+
"step": 210500
|
| 2535 |
+
},
|
| 2536 |
+
{
|
| 2537 |
+
"epoch": 0.63,
|
| 2538 |
+
"learning_rate": 1.85163908742297e-05,
|
| 2539 |
+
"loss": 3.0885,
|
| 2540 |
+
"step": 211000
|
| 2541 |
+
},
|
| 2542 |
+
{
|
| 2543 |
+
"epoch": 0.63,
|
| 2544 |
+
"learning_rate": 1.8441785165400858e-05,
|
| 2545 |
+
"loss": 3.0931,
|
| 2546 |
+
"step": 211500
|
| 2547 |
+
},
|
| 2548 |
+
{
|
| 2549 |
+
"epoch": 0.63,
|
| 2550 |
+
"learning_rate": 1.8367179456572018e-05,
|
| 2551 |
+
"loss": 3.0962,
|
| 2552 |
+
"step": 212000
|
| 2553 |
+
},
|
| 2554 |
+
{
|
| 2555 |
+
"epoch": 0.63,
|
| 2556 |
+
"learning_rate": 1.8292573747743177e-05,
|
| 2557 |
+
"loss": 3.0888,
|
| 2558 |
+
"step": 212500
|
| 2559 |
+
},
|
| 2560 |
+
{
|
| 2561 |
+
"epoch": 0.64,
|
| 2562 |
+
"learning_rate": 1.8217968038914337e-05,
|
| 2563 |
+
"loss": 3.0904,
|
| 2564 |
+
"step": 213000
|
| 2565 |
+
},
|
| 2566 |
+
{
|
| 2567 |
+
"epoch": 0.64,
|
| 2568 |
+
"learning_rate": 1.8143362330085496e-05,
|
| 2569 |
+
"loss": 3.1059,
|
| 2570 |
+
"step": 213500
|
| 2571 |
+
},
|
| 2572 |
+
{
|
| 2573 |
+
"epoch": 0.64,
|
| 2574 |
+
"learning_rate": 1.806875662125666e-05,
|
| 2575 |
+
"loss": 3.1071,
|
| 2576 |
+
"step": 214000
|
| 2577 |
+
},
|
| 2578 |
+
{
|
| 2579 |
+
"epoch": 0.64,
|
| 2580 |
+
"learning_rate": 1.7994150912427822e-05,
|
| 2581 |
+
"loss": 3.0838,
|
| 2582 |
+
"step": 214500
|
| 2583 |
+
},
|
| 2584 |
+
{
|
| 2585 |
+
"epoch": 0.64,
|
| 2586 |
+
"learning_rate": 1.7919545203598982e-05,
|
| 2587 |
+
"loss": 3.1019,
|
| 2588 |
+
"step": 215000
|
| 2589 |
+
},
|
| 2590 |
+
{
|
| 2591 |
+
"epoch": 0.64,
|
| 2592 |
+
"learning_rate": 1.784493949477014e-05,
|
| 2593 |
+
"loss": 3.0909,
|
| 2594 |
+
"step": 215500
|
| 2595 |
+
},
|
| 2596 |
+
{
|
| 2597 |
+
"epoch": 0.64,
|
| 2598 |
+
"learning_rate": 1.77703337859413e-05,
|
| 2599 |
+
"loss": 3.0948,
|
| 2600 |
+
"step": 216000
|
| 2601 |
+
},
|
| 2602 |
+
{
|
| 2603 |
+
"epoch": 0.65,
|
| 2604 |
+
"learning_rate": 1.769572807711246e-05,
|
| 2605 |
+
"loss": 3.0653,
|
| 2606 |
+
"step": 216500
|
| 2607 |
+
},
|
| 2608 |
+
{
|
| 2609 |
+
"epoch": 0.65,
|
| 2610 |
+
"learning_rate": 1.762112236828362e-05,
|
| 2611 |
+
"loss": 3.1038,
|
| 2612 |
+
"step": 217000
|
| 2613 |
+
},
|
| 2614 |
+
{
|
| 2615 |
+
"epoch": 0.65,
|
| 2616 |
+
"learning_rate": 1.7546516659454783e-05,
|
| 2617 |
+
"loss": 3.0913,
|
| 2618 |
+
"step": 217500
|
| 2619 |
+
},
|
| 2620 |
+
{
|
| 2621 |
+
"epoch": 0.65,
|
| 2622 |
+
"learning_rate": 1.7471910950625943e-05,
|
| 2623 |
+
"loss": 3.0811,
|
| 2624 |
+
"step": 218000
|
| 2625 |
+
},
|
| 2626 |
+
{
|
| 2627 |
+
"epoch": 0.65,
|
| 2628 |
+
"learning_rate": 1.7397305241797106e-05,
|
| 2629 |
+
"loss": 3.0839,
|
| 2630 |
+
"step": 218500
|
| 2631 |
+
},
|
| 2632 |
+
{
|
| 2633 |
+
"epoch": 0.65,
|
| 2634 |
+
"learning_rate": 1.7322699532968265e-05,
|
| 2635 |
+
"loss": 3.0852,
|
| 2636 |
+
"step": 219000
|
| 2637 |
+
},
|
| 2638 |
+
{
|
| 2639 |
+
"epoch": 0.66,
|
| 2640 |
+
"learning_rate": 1.7248093824139425e-05,
|
| 2641 |
+
"loss": 3.0573,
|
| 2642 |
+
"step": 219500
|
| 2643 |
+
},
|
| 2644 |
+
{
|
| 2645 |
+
"epoch": 0.66,
|
| 2646 |
+
"learning_rate": 1.7173488115310584e-05,
|
| 2647 |
+
"loss": 3.0985,
|
| 2648 |
+
"step": 220000
|
| 2649 |
+
},
|
| 2650 |
+
{
|
| 2651 |
+
"epoch": 0.66,
|
| 2652 |
+
"learning_rate": 1.7098882406481744e-05,
|
| 2653 |
+
"loss": 3.0628,
|
| 2654 |
+
"step": 220500
|
| 2655 |
+
},
|
| 2656 |
+
{
|
| 2657 |
+
"epoch": 0.66,
|
| 2658 |
+
"learning_rate": 1.7024276697652903e-05,
|
| 2659 |
+
"loss": 3.076,
|
| 2660 |
+
"step": 221000
|
| 2661 |
+
},
|
| 2662 |
+
{
|
| 2663 |
+
"epoch": 0.66,
|
| 2664 |
+
"learning_rate": 1.6949670988824066e-05,
|
| 2665 |
+
"loss": 3.0765,
|
| 2666 |
+
"step": 221500
|
| 2667 |
+
},
|
| 2668 |
+
{
|
| 2669 |
+
"epoch": 0.66,
|
| 2670 |
+
"learning_rate": 1.6875065279995226e-05,
|
| 2671 |
+
"loss": 3.0835,
|
| 2672 |
+
"step": 222000
|
| 2673 |
+
},
|
| 2674 |
+
{
|
| 2675 |
+
"epoch": 0.66,
|
| 2676 |
+
"learning_rate": 1.6800459571166386e-05,
|
| 2677 |
+
"loss": 3.0633,
|
| 2678 |
+
"step": 222500
|
| 2679 |
+
},
|
| 2680 |
+
{
|
| 2681 |
+
"epoch": 0.67,
|
| 2682 |
+
"learning_rate": 1.672585386233755e-05,
|
| 2683 |
+
"loss": 3.0676,
|
| 2684 |
+
"step": 223000
|
| 2685 |
+
},
|
| 2686 |
+
{
|
| 2687 |
+
"epoch": 0.67,
|
| 2688 |
+
"learning_rate": 1.6651248153508708e-05,
|
| 2689 |
+
"loss": 3.0719,
|
| 2690 |
+
"step": 223500
|
| 2691 |
+
},
|
| 2692 |
+
{
|
| 2693 |
+
"epoch": 0.67,
|
| 2694 |
+
"learning_rate": 1.6576642444679868e-05,
|
| 2695 |
+
"loss": 3.0795,
|
| 2696 |
+
"step": 224000
|
| 2697 |
+
},
|
| 2698 |
+
{
|
| 2699 |
+
"epoch": 0.67,
|
| 2700 |
+
"learning_rate": 1.6502036735851027e-05,
|
| 2701 |
+
"loss": 3.0631,
|
| 2702 |
+
"step": 224500
|
| 2703 |
+
},
|
| 2704 |
+
{
|
| 2705 |
+
"epoch": 0.67,
|
| 2706 |
+
"learning_rate": 1.642743102702219e-05,
|
| 2707 |
+
"loss": 3.0544,
|
| 2708 |
+
"step": 225000
|
| 2709 |
+
},
|
| 2710 |
+
{
|
| 2711 |
+
"epoch": 0.67,
|
| 2712 |
+
"learning_rate": 1.635282531819335e-05,
|
| 2713 |
+
"loss": 3.0803,
|
| 2714 |
+
"step": 225500
|
| 2715 |
+
},
|
| 2716 |
+
{
|
| 2717 |
+
"epoch": 0.67,
|
| 2718 |
+
"learning_rate": 1.627821960936451e-05,
|
| 2719 |
+
"loss": 3.0572,
|
| 2720 |
+
"step": 226000
|
| 2721 |
+
},
|
| 2722 |
+
{
|
| 2723 |
+
"epoch": 0.68,
|
| 2724 |
+
"learning_rate": 1.620361390053567e-05,
|
| 2725 |
+
"loss": 3.0625,
|
| 2726 |
+
"step": 226500
|
| 2727 |
+
},
|
| 2728 |
+
{
|
| 2729 |
+
"epoch": 0.68,
|
| 2730 |
+
"learning_rate": 1.612900819170683e-05,
|
| 2731 |
+
"loss": 3.076,
|
| 2732 |
+
"step": 227000
|
| 2733 |
+
},
|
| 2734 |
+
{
|
| 2735 |
+
"epoch": 0.68,
|
| 2736 |
+
"learning_rate": 1.6054402482877988e-05,
|
| 2737 |
+
"loss": 3.059,
|
| 2738 |
+
"step": 227500
|
| 2739 |
+
},
|
| 2740 |
+
{
|
| 2741 |
+
"epoch": 0.68,
|
| 2742 |
+
"learning_rate": 1.597979677404915e-05,
|
| 2743 |
+
"loss": 3.0651,
|
| 2744 |
+
"step": 228000
|
| 2745 |
+
},
|
| 2746 |
+
{
|
| 2747 |
+
"epoch": 0.68,
|
| 2748 |
+
"learning_rate": 1.5905191065220314e-05,
|
| 2749 |
+
"loss": 3.0331,
|
| 2750 |
+
"step": 228500
|
| 2751 |
+
},
|
| 2752 |
+
{
|
| 2753 |
+
"epoch": 0.68,
|
| 2754 |
+
"learning_rate": 1.5830585356391474e-05,
|
| 2755 |
+
"loss": 3.073,
|
| 2756 |
+
"step": 229000
|
| 2757 |
+
},
|
| 2758 |
+
{
|
| 2759 |
+
"epoch": 0.68,
|
| 2760 |
+
"learning_rate": 1.5755979647562633e-05,
|
| 2761 |
+
"loss": 3.0653,
|
| 2762 |
+
"step": 229500
|
| 2763 |
+
},
|
| 2764 |
+
{
|
| 2765 |
+
"epoch": 0.69,
|
| 2766 |
+
"learning_rate": 1.5681373938733793e-05,
|
| 2767 |
+
"loss": 3.0541,
|
| 2768 |
+
"step": 230000
|
| 2769 |
+
},
|
| 2770 |
+
{
|
| 2771 |
+
"epoch": 0.69,
|
| 2772 |
+
"learning_rate": 1.5606768229904952e-05,
|
| 2773 |
+
"loss": 3.0459,
|
| 2774 |
+
"step": 230500
|
| 2775 |
+
},
|
| 2776 |
+
{
|
| 2777 |
+
"epoch": 0.69,
|
| 2778 |
+
"learning_rate": 1.5532162521076112e-05,
|
| 2779 |
+
"loss": 3.0559,
|
| 2780 |
+
"step": 231000
|
| 2781 |
+
},
|
| 2782 |
+
{
|
| 2783 |
+
"epoch": 0.69,
|
| 2784 |
+
"learning_rate": 1.545755681224727e-05,
|
| 2785 |
+
"loss": 3.0597,
|
| 2786 |
+
"step": 231500
|
| 2787 |
+
},
|
| 2788 |
+
{
|
| 2789 |
+
"epoch": 0.69,
|
| 2790 |
+
"learning_rate": 1.5382951103418434e-05,
|
| 2791 |
+
"loss": 3.0524,
|
| 2792 |
+
"step": 232000
|
| 2793 |
+
},
|
| 2794 |
+
{
|
| 2795 |
+
"epoch": 0.69,
|
| 2796 |
+
"learning_rate": 1.5308345394589597e-05,
|
| 2797 |
+
"loss": 3.0592,
|
| 2798 |
+
"step": 232500
|
| 2799 |
+
},
|
| 2800 |
+
{
|
| 2801 |
+
"epoch": 0.7,
|
| 2802 |
+
"learning_rate": 1.5233739685760757e-05,
|
| 2803 |
+
"loss": 3.0682,
|
| 2804 |
+
"step": 233000
|
| 2805 |
+
},
|
| 2806 |
+
{
|
| 2807 |
+
"epoch": 0.7,
|
| 2808 |
+
"learning_rate": 1.5159133976931917e-05,
|
| 2809 |
+
"loss": 3.0332,
|
| 2810 |
+
"step": 233500
|
| 2811 |
+
},
|
| 2812 |
+
{
|
| 2813 |
+
"epoch": 0.7,
|
| 2814 |
+
"learning_rate": 1.5084528268103076e-05,
|
| 2815 |
+
"loss": 3.0509,
|
| 2816 |
+
"step": 234000
|
| 2817 |
+
},
|
| 2818 |
+
{
|
| 2819 |
+
"epoch": 0.7,
|
| 2820 |
+
"learning_rate": 1.5009922559274237e-05,
|
| 2821 |
+
"loss": 3.0395,
|
| 2822 |
+
"step": 234500
|
| 2823 |
+
},
|
| 2824 |
+
{
|
| 2825 |
+
"epoch": 0.7,
|
| 2826 |
+
"learning_rate": 1.4935316850445397e-05,
|
| 2827 |
+
"loss": 3.063,
|
| 2828 |
+
"step": 235000
|
| 2829 |
+
},
|
| 2830 |
+
{
|
| 2831 |
+
"epoch": 0.7,
|
| 2832 |
+
"learning_rate": 1.4860711141616556e-05,
|
| 2833 |
+
"loss": 3.0484,
|
| 2834 |
+
"step": 235500
|
| 2835 |
+
},
|
| 2836 |
+
{
|
| 2837 |
+
"epoch": 0.7,
|
| 2838 |
+
"learning_rate": 1.4786105432787716e-05,
|
| 2839 |
+
"loss": 3.0505,
|
| 2840 |
+
"step": 236000
|
| 2841 |
+
},
|
| 2842 |
+
{
|
| 2843 |
+
"epoch": 0.71,
|
| 2844 |
+
"learning_rate": 1.4711499723958877e-05,
|
| 2845 |
+
"loss": 3.0375,
|
| 2846 |
+
"step": 236500
|
| 2847 |
+
},
|
| 2848 |
+
{
|
| 2849 |
+
"epoch": 0.71,
|
| 2850 |
+
"learning_rate": 1.4636894015130037e-05,
|
| 2851 |
+
"loss": 3.0443,
|
| 2852 |
+
"step": 237000
|
| 2853 |
+
},
|
| 2854 |
+
{
|
| 2855 |
+
"epoch": 0.71,
|
| 2856 |
+
"learning_rate": 1.45622883063012e-05,
|
| 2857 |
+
"loss": 3.0334,
|
| 2858 |
+
"step": 237500
|
| 2859 |
+
},
|
| 2860 |
+
{
|
| 2861 |
+
"epoch": 0.71,
|
| 2862 |
+
"learning_rate": 1.448768259747236e-05,
|
| 2863 |
+
"loss": 3.0349,
|
| 2864 |
+
"step": 238000
|
| 2865 |
+
},
|
| 2866 |
+
{
|
| 2867 |
+
"epoch": 0.71,
|
| 2868 |
+
"learning_rate": 1.441307688864352e-05,
|
| 2869 |
+
"loss": 3.0277,
|
| 2870 |
+
"step": 238500
|
| 2871 |
+
},
|
| 2872 |
+
{
|
| 2873 |
+
"epoch": 0.71,
|
| 2874 |
+
"learning_rate": 1.433847117981468e-05,
|
| 2875 |
+
"loss": 3.0345,
|
| 2876 |
+
"step": 239000
|
| 2877 |
+
},
|
| 2878 |
+
{
|
| 2879 |
+
"epoch": 0.71,
|
| 2880 |
+
"learning_rate": 1.426386547098584e-05,
|
| 2881 |
+
"loss": 3.0494,
|
| 2882 |
+
"step": 239500
|
| 2883 |
+
},
|
| 2884 |
+
{
|
| 2885 |
+
"epoch": 0.72,
|
| 2886 |
+
"learning_rate": 1.4189259762157001e-05,
|
| 2887 |
+
"loss": 3.0363,
|
| 2888 |
+
"step": 240000
|
| 2889 |
+
},
|
| 2890 |
+
{
|
| 2891 |
+
"epoch": 0.72,
|
| 2892 |
+
"learning_rate": 1.411465405332816e-05,
|
| 2893 |
+
"loss": 3.0398,
|
| 2894 |
+
"step": 240500
|
| 2895 |
+
},
|
| 2896 |
+
{
|
| 2897 |
+
"epoch": 0.72,
|
| 2898 |
+
"learning_rate": 1.404004834449932e-05,
|
| 2899 |
+
"loss": 3.0372,
|
| 2900 |
+
"step": 241000
|
| 2901 |
+
},
|
| 2902 |
+
{
|
| 2903 |
+
"epoch": 0.72,
|
| 2904 |
+
"learning_rate": 1.3965442635670482e-05,
|
| 2905 |
+
"loss": 3.0286,
|
| 2906 |
+
"step": 241500
|
| 2907 |
+
},
|
| 2908 |
+
{
|
| 2909 |
+
"epoch": 0.72,
|
| 2910 |
+
"learning_rate": 1.3890836926841645e-05,
|
| 2911 |
+
"loss": 3.034,
|
| 2912 |
+
"step": 242000
|
| 2913 |
+
},
|
| 2914 |
+
{
|
| 2915 |
+
"epoch": 0.72,
|
| 2916 |
+
"learning_rate": 1.3816231218012804e-05,
|
| 2917 |
+
"loss": 3.0132,
|
| 2918 |
+
"step": 242500
|
| 2919 |
+
},
|
| 2920 |
+
{
|
| 2921 |
+
"epoch": 0.73,
|
| 2922 |
+
"learning_rate": 1.3741625509183964e-05,
|
| 2923 |
+
"loss": 3.0232,
|
| 2924 |
+
"step": 243000
|
| 2925 |
+
},
|
| 2926 |
+
{
|
| 2927 |
+
"epoch": 0.73,
|
| 2928 |
+
"learning_rate": 1.3667019800355125e-05,
|
| 2929 |
+
"loss": 3.0399,
|
| 2930 |
+
"step": 243500
|
| 2931 |
+
},
|
| 2932 |
+
{
|
| 2933 |
+
"epoch": 0.73,
|
| 2934 |
+
"learning_rate": 1.3592414091526284e-05,
|
| 2935 |
+
"loss": 3.029,
|
| 2936 |
+
"step": 244000
|
| 2937 |
+
},
|
| 2938 |
+
{
|
| 2939 |
+
"epoch": 0.73,
|
| 2940 |
+
"learning_rate": 1.3517808382697444e-05,
|
| 2941 |
+
"loss": 3.0386,
|
| 2942 |
+
"step": 244500
|
| 2943 |
+
},
|
| 2944 |
+
{
|
| 2945 |
+
"epoch": 0.73,
|
| 2946 |
+
"learning_rate": 1.3443202673868605e-05,
|
| 2947 |
+
"loss": 3.0186,
|
| 2948 |
+
"step": 245000
|
| 2949 |
+
},
|
| 2950 |
+
{
|
| 2951 |
+
"epoch": 0.73,
|
| 2952 |
+
"learning_rate": 1.3368596965039765e-05,
|
| 2953 |
+
"loss": 3.0282,
|
| 2954 |
+
"step": 245500
|
| 2955 |
+
},
|
| 2956 |
+
{
|
| 2957 |
+
"epoch": 0.73,
|
| 2958 |
+
"learning_rate": 1.3293991256210924e-05,
|
| 2959 |
+
"loss": 3.0252,
|
| 2960 |
+
"step": 246000
|
| 2961 |
+
},
|
| 2962 |
+
{
|
| 2963 |
+
"epoch": 0.74,
|
| 2964 |
+
"learning_rate": 1.3219385547382087e-05,
|
| 2965 |
+
"loss": 3.0175,
|
| 2966 |
+
"step": 246500
|
| 2967 |
+
},
|
| 2968 |
+
{
|
| 2969 |
+
"epoch": 0.74,
|
| 2970 |
+
"learning_rate": 1.3144779838553247e-05,
|
| 2971 |
+
"loss": 3.0221,
|
| 2972 |
+
"step": 247000
|
| 2973 |
+
},
|
| 2974 |
+
{
|
| 2975 |
+
"epoch": 0.74,
|
| 2976 |
+
"learning_rate": 1.3070174129724408e-05,
|
| 2977 |
+
"loss": 3.0187,
|
| 2978 |
+
"step": 247500
|
| 2979 |
+
},
|
| 2980 |
+
{
|
| 2981 |
+
"epoch": 0.74,
|
| 2982 |
+
"learning_rate": 1.2995568420895568e-05,
|
| 2983 |
+
"loss": 3.0149,
|
| 2984 |
+
"step": 248000
|
| 2985 |
+
},
|
| 2986 |
+
{
|
| 2987 |
+
"epoch": 0.74,
|
| 2988 |
+
"learning_rate": 1.2920962712066727e-05,
|
| 2989 |
+
"loss": 3.021,
|
| 2990 |
+
"step": 248500
|
| 2991 |
+
},
|
| 2992 |
+
{
|
| 2993 |
+
"epoch": 0.74,
|
| 2994 |
+
"learning_rate": 1.2846357003237889e-05,
|
| 2995 |
+
"loss": 3.0241,
|
| 2996 |
+
"step": 249000
|
| 2997 |
+
},
|
| 2998 |
+
{
|
| 2999 |
+
"epoch": 0.74,
|
| 3000 |
+
"learning_rate": 1.2771751294409048e-05,
|
| 3001 |
+
"loss": 3.005,
|
| 3002 |
+
"step": 249500
|
| 3003 |
+
},
|
| 3004 |
+
{
|
| 3005 |
+
"epoch": 0.75,
|
| 3006 |
+
"learning_rate": 1.2697145585580208e-05,
|
| 3007 |
+
"loss": 3.0068,
|
| 3008 |
+
"step": 250000
|
| 3009 |
+
},
|
| 3010 |
+
{
|
| 3011 |
+
"epoch": 0.75,
|
| 3012 |
+
"learning_rate": 1.2622539876751369e-05,
|
| 3013 |
+
"loss": 3.0047,
|
| 3014 |
+
"step": 250500
|
| 3015 |
+
},
|
| 3016 |
+
{
|
| 3017 |
+
"epoch": 0.75,
|
| 3018 |
+
"learning_rate": 1.2547934167922529e-05,
|
| 3019 |
+
"loss": 3.0196,
|
| 3020 |
+
"step": 251000
|
| 3021 |
+
},
|
| 3022 |
+
{
|
| 3023 |
+
"epoch": 0.75,
|
| 3024 |
+
"learning_rate": 1.247332845909369e-05,
|
| 3025 |
+
"loss": 3.0043,
|
| 3026 |
+
"step": 251500
|
| 3027 |
+
},
|
| 3028 |
+
{
|
| 3029 |
+
"epoch": 0.75,
|
| 3030 |
+
"learning_rate": 1.239872275026485e-05,
|
| 3031 |
+
"loss": 3.0094,
|
| 3032 |
+
"step": 252000
|
| 3033 |
+
},
|
| 3034 |
+
{
|
| 3035 |
+
"epoch": 0.75,
|
| 3036 |
+
"learning_rate": 1.2324117041436013e-05,
|
| 3037 |
+
"loss": 3.0014,
|
| 3038 |
+
"step": 252500
|
| 3039 |
+
},
|
| 3040 |
+
{
|
| 3041 |
+
"epoch": 0.76,
|
| 3042 |
+
"learning_rate": 1.2249511332607172e-05,
|
| 3043 |
+
"loss": 2.9893,
|
| 3044 |
+
"step": 253000
|
| 3045 |
+
},
|
| 3046 |
+
{
|
| 3047 |
+
"epoch": 0.76,
|
| 3048 |
+
"learning_rate": 1.2174905623778332e-05,
|
| 3049 |
+
"loss": 2.9995,
|
| 3050 |
+
"step": 253500
|
| 3051 |
+
},
|
| 3052 |
+
{
|
| 3053 |
+
"epoch": 0.76,
|
| 3054 |
+
"learning_rate": 1.2100299914949493e-05,
|
| 3055 |
+
"loss": 3.0127,
|
| 3056 |
+
"step": 254000
|
| 3057 |
+
},
|
| 3058 |
+
{
|
| 3059 |
+
"epoch": 0.76,
|
| 3060 |
+
"learning_rate": 1.2025694206120652e-05,
|
| 3061 |
+
"loss": 3.0093,
|
| 3062 |
+
"step": 254500
|
| 3063 |
+
},
|
| 3064 |
+
{
|
| 3065 |
+
"epoch": 0.76,
|
| 3066 |
+
"learning_rate": 1.1951088497291814e-05,
|
| 3067 |
+
"loss": 3.002,
|
| 3068 |
+
"step": 255000
|
| 3069 |
+
},
|
| 3070 |
+
{
|
| 3071 |
+
"epoch": 0.76,
|
| 3072 |
+
"learning_rate": 1.1876482788462973e-05,
|
| 3073 |
+
"loss": 3.0212,
|
| 3074 |
+
"step": 255500
|
| 3075 |
+
},
|
| 3076 |
+
{
|
| 3077 |
+
"epoch": 0.76,
|
| 3078 |
+
"learning_rate": 1.1801877079634135e-05,
|
| 3079 |
+
"loss": 3.0069,
|
| 3080 |
+
"step": 256000
|
| 3081 |
+
},
|
| 3082 |
+
{
|
| 3083 |
+
"epoch": 0.77,
|
| 3084 |
+
"learning_rate": 1.1727271370805294e-05,
|
| 3085 |
+
"loss": 3.0155,
|
| 3086 |
+
"step": 256500
|
| 3087 |
+
},
|
| 3088 |
+
{
|
| 3089 |
+
"epoch": 0.77,
|
| 3090 |
+
"learning_rate": 1.1652665661976454e-05,
|
| 3091 |
+
"loss": 2.9904,
|
| 3092 |
+
"step": 257000
|
| 3093 |
+
},
|
| 3094 |
+
{
|
| 3095 |
+
"epoch": 0.77,
|
| 3096 |
+
"learning_rate": 1.1578059953147615e-05,
|
| 3097 |
+
"loss": 2.9839,
|
| 3098 |
+
"step": 257500
|
| 3099 |
+
},
|
| 3100 |
+
{
|
| 3101 |
+
"epoch": 0.77,
|
| 3102 |
+
"learning_rate": 1.1503454244318776e-05,
|
| 3103 |
+
"loss": 3.0073,
|
| 3104 |
+
"step": 258000
|
| 3105 |
+
},
|
| 3106 |
+
{
|
| 3107 |
+
"epoch": 0.77,
|
| 3108 |
+
"learning_rate": 1.1428848535489936e-05,
|
| 3109 |
+
"loss": 2.9917,
|
| 3110 |
+
"step": 258500
|
| 3111 |
+
},
|
| 3112 |
+
{
|
| 3113 |
+
"epoch": 0.77,
|
| 3114 |
+
"learning_rate": 1.1354242826661095e-05,
|
| 3115 |
+
"loss": 3.0195,
|
| 3116 |
+
"step": 259000
|
| 3117 |
+
},
|
| 3118 |
+
{
|
| 3119 |
+
"epoch": 0.77,
|
| 3120 |
+
"learning_rate": 1.1279637117832258e-05,
|
| 3121 |
+
"loss": 3.0205,
|
| 3122 |
+
"step": 259500
|
| 3123 |
+
},
|
| 3124 |
+
{
|
| 3125 |
+
"epoch": 0.78,
|
| 3126 |
+
"learning_rate": 1.1205031409003418e-05,
|
| 3127 |
+
"loss": 2.9868,
|
| 3128 |
+
"step": 260000
|
| 3129 |
+
},
|
| 3130 |
+
{
|
| 3131 |
+
"epoch": 0.78,
|
| 3132 |
+
"learning_rate": 1.1130425700174578e-05,
|
| 3133 |
+
"loss": 2.9808,
|
| 3134 |
+
"step": 260500
|
| 3135 |
+
},
|
| 3136 |
+
{
|
| 3137 |
+
"epoch": 0.78,
|
| 3138 |
+
"learning_rate": 1.1055819991345739e-05,
|
| 3139 |
+
"loss": 3.0043,
|
| 3140 |
+
"step": 261000
|
| 3141 |
+
},
|
| 3142 |
+
{
|
| 3143 |
+
"epoch": 0.78,
|
| 3144 |
+
"learning_rate": 1.0981214282516898e-05,
|
| 3145 |
+
"loss": 3.0056,
|
| 3146 |
+
"step": 261500
|
| 3147 |
+
},
|
| 3148 |
+
{
|
| 3149 |
+
"epoch": 0.78,
|
| 3150 |
+
"learning_rate": 1.090660857368806e-05,
|
| 3151 |
+
"loss": 2.995,
|
| 3152 |
+
"step": 262000
|
| 3153 |
+
},
|
| 3154 |
+
{
|
| 3155 |
+
"epoch": 0.78,
|
| 3156 |
+
"learning_rate": 1.083200286485922e-05,
|
| 3157 |
+
"loss": 2.997,
|
| 3158 |
+
"step": 262500
|
| 3159 |
+
},
|
| 3160 |
+
{
|
| 3161 |
+
"epoch": 0.78,
|
| 3162 |
+
"learning_rate": 1.075739715603038e-05,
|
| 3163 |
+
"loss": 2.9913,
|
| 3164 |
+
"step": 263000
|
| 3165 |
+
},
|
| 3166 |
+
{
|
| 3167 |
+
"epoch": 0.79,
|
| 3168 |
+
"learning_rate": 1.068279144720154e-05,
|
| 3169 |
+
"loss": 2.9802,
|
| 3170 |
+
"step": 263500
|
| 3171 |
+
},
|
| 3172 |
+
{
|
| 3173 |
+
"epoch": 0.79,
|
| 3174 |
+
"learning_rate": 1.06081857383727e-05,
|
| 3175 |
+
"loss": 2.9788,
|
| 3176 |
+
"step": 264000
|
| 3177 |
+
},
|
| 3178 |
+
{
|
| 3179 |
+
"epoch": 0.79,
|
| 3180 |
+
"learning_rate": 1.0533580029543861e-05,
|
| 3181 |
+
"loss": 2.9925,
|
| 3182 |
+
"step": 264500
|
| 3183 |
+
},
|
| 3184 |
+
{
|
| 3185 |
+
"epoch": 0.79,
|
| 3186 |
+
"learning_rate": 1.0458974320715022e-05,
|
| 3187 |
+
"loss": 3.0028,
|
| 3188 |
+
"step": 265000
|
| 3189 |
+
},
|
| 3190 |
+
{
|
| 3191 |
+
"epoch": 0.79,
|
| 3192 |
+
"learning_rate": 1.0384368611886182e-05,
|
| 3193 |
+
"loss": 2.9988,
|
| 3194 |
+
"step": 265500
|
| 3195 |
+
},
|
| 3196 |
+
{
|
| 3197 |
+
"epoch": 0.79,
|
| 3198 |
+
"learning_rate": 1.0309762903057341e-05,
|
| 3199 |
+
"loss": 2.9944,
|
| 3200 |
+
"step": 266000
|
| 3201 |
+
},
|
| 3202 |
+
{
|
| 3203 |
+
"epoch": 0.8,
|
| 3204 |
+
"learning_rate": 1.0235157194228504e-05,
|
| 3205 |
+
"loss": 2.9768,
|
| 3206 |
+
"step": 266500
|
| 3207 |
+
},
|
| 3208 |
+
{
|
| 3209 |
+
"epoch": 0.8,
|
| 3210 |
+
"learning_rate": 1.0160551485399664e-05,
|
| 3211 |
+
"loss": 2.9891,
|
| 3212 |
+
"step": 267000
|
| 3213 |
+
},
|
| 3214 |
+
{
|
| 3215 |
+
"epoch": 0.8,
|
| 3216 |
+
"learning_rate": 1.0085945776570823e-05,
|
| 3217 |
+
"loss": 2.9815,
|
| 3218 |
+
"step": 267500
|
| 3219 |
+
},
|
| 3220 |
+
{
|
| 3221 |
+
"epoch": 0.8,
|
| 3222 |
+
"learning_rate": 1.0011340067741983e-05,
|
| 3223 |
+
"loss": 2.9839,
|
| 3224 |
+
"step": 268000
|
| 3225 |
+
},
|
| 3226 |
+
{
|
| 3227 |
+
"epoch": 0.8,
|
| 3228 |
+
"learning_rate": 9.936734358913144e-06,
|
| 3229 |
+
"loss": 2.9852,
|
| 3230 |
+
"step": 268500
|
| 3231 |
+
},
|
| 3232 |
+
{
|
| 3233 |
+
"epoch": 0.8,
|
| 3234 |
+
"learning_rate": 9.862128650084306e-06,
|
| 3235 |
+
"loss": 2.9759,
|
| 3236 |
+
"step": 269000
|
| 3237 |
+
},
|
| 3238 |
+
{
|
| 3239 |
+
"epoch": 0.8,
|
| 3240 |
+
"learning_rate": 9.787522941255465e-06,
|
| 3241 |
+
"loss": 2.985,
|
| 3242 |
+
"step": 269500
|
| 3243 |
+
},
|
| 3244 |
+
{
|
| 3245 |
+
"epoch": 0.81,
|
| 3246 |
+
"learning_rate": 9.712917232426626e-06,
|
| 3247 |
+
"loss": 2.9627,
|
| 3248 |
+
"step": 270000
|
| 3249 |
+
},
|
| 3250 |
+
{
|
| 3251 |
+
"epoch": 0.81,
|
| 3252 |
+
"learning_rate": 9.638311523597786e-06,
|
| 3253 |
+
"loss": 2.9925,
|
| 3254 |
+
"step": 270500
|
| 3255 |
+
},
|
| 3256 |
+
{
|
| 3257 |
+
"epoch": 0.81,
|
| 3258 |
+
"learning_rate": 9.563705814768946e-06,
|
| 3259 |
+
"loss": 2.9701,
|
| 3260 |
+
"step": 271000
|
| 3261 |
+
},
|
| 3262 |
+
{
|
| 3263 |
+
"epoch": 0.81,
|
| 3264 |
+
"learning_rate": 9.489100105940107e-06,
|
| 3265 |
+
"loss": 2.9856,
|
| 3266 |
+
"step": 271500
|
| 3267 |
+
},
|
| 3268 |
+
{
|
| 3269 |
+
"epoch": 0.81,
|
| 3270 |
+
"learning_rate": 9.414494397111268e-06,
|
| 3271 |
+
"loss": 2.9915,
|
| 3272 |
+
"step": 272000
|
| 3273 |
+
},
|
| 3274 |
+
{
|
| 3275 |
+
"epoch": 0.81,
|
| 3276 |
+
"learning_rate": 9.339888688282428e-06,
|
| 3277 |
+
"loss": 2.9746,
|
| 3278 |
+
"step": 272500
|
| 3279 |
+
},
|
| 3280 |
+
{
|
| 3281 |
+
"epoch": 0.81,
|
| 3282 |
+
"learning_rate": 9.265282979453587e-06,
|
| 3283 |
+
"loss": 2.9878,
|
| 3284 |
+
"step": 273000
|
| 3285 |
+
},
|
| 3286 |
+
{
|
| 3287 |
+
"epoch": 0.82,
|
| 3288 |
+
"learning_rate": 9.190677270624748e-06,
|
| 3289 |
+
"loss": 2.9855,
|
| 3290 |
+
"step": 273500
|
| 3291 |
+
},
|
| 3292 |
+
{
|
| 3293 |
+
"epoch": 0.82,
|
| 3294 |
+
"learning_rate": 9.11607156179591e-06,
|
| 3295 |
+
"loss": 2.96,
|
| 3296 |
+
"step": 274000
|
| 3297 |
+
},
|
| 3298 |
+
{
|
| 3299 |
+
"epoch": 0.82,
|
| 3300 |
+
"learning_rate": 9.04146585296707e-06,
|
| 3301 |
+
"loss": 2.9613,
|
| 3302 |
+
"step": 274500
|
| 3303 |
+
},
|
| 3304 |
+
{
|
| 3305 |
+
"epoch": 0.82,
|
| 3306 |
+
"learning_rate": 8.966860144138229e-06,
|
| 3307 |
+
"loss": 2.9575,
|
| 3308 |
+
"step": 275000
|
| 3309 |
+
},
|
| 3310 |
+
{
|
| 3311 |
+
"epoch": 0.82,
|
| 3312 |
+
"learning_rate": 8.89225443530939e-06,
|
| 3313 |
+
"loss": 2.9729,
|
| 3314 |
+
"step": 275500
|
| 3315 |
+
},
|
| 3316 |
+
{
|
| 3317 |
+
"epoch": 0.82,
|
| 3318 |
+
"learning_rate": 8.817648726480551e-06,
|
| 3319 |
+
"loss": 2.9773,
|
| 3320 |
+
"step": 276000
|
| 3321 |
+
},
|
| 3322 |
+
{
|
| 3323 |
+
"epoch": 0.83,
|
| 3324 |
+
"learning_rate": 8.743043017651711e-06,
|
| 3325 |
+
"loss": 2.9643,
|
| 3326 |
+
"step": 276500
|
| 3327 |
+
},
|
| 3328 |
+
{
|
| 3329 |
+
"epoch": 0.83,
|
| 3330 |
+
"learning_rate": 8.668437308822872e-06,
|
| 3331 |
+
"loss": 2.9676,
|
| 3332 |
+
"step": 277000
|
| 3333 |
+
},
|
| 3334 |
+
{
|
| 3335 |
+
"epoch": 0.83,
|
| 3336 |
+
"learning_rate": 8.593831599994032e-06,
|
| 3337 |
+
"loss": 2.953,
|
| 3338 |
+
"step": 277500
|
| 3339 |
+
},
|
| 3340 |
+
{
|
| 3341 |
+
"epoch": 0.83,
|
| 3342 |
+
"learning_rate": 8.519225891165191e-06,
|
| 3343 |
+
"loss": 2.9523,
|
| 3344 |
+
"step": 278000
|
| 3345 |
+
},
|
| 3346 |
+
{
|
| 3347 |
+
"epoch": 0.83,
|
| 3348 |
+
"learning_rate": 8.444620182336353e-06,
|
| 3349 |
+
"loss": 2.9833,
|
| 3350 |
+
"step": 278500
|
| 3351 |
+
},
|
| 3352 |
+
{
|
| 3353 |
+
"epoch": 0.83,
|
| 3354 |
+
"learning_rate": 8.370014473507514e-06,
|
| 3355 |
+
"loss": 2.971,
|
| 3356 |
+
"step": 279000
|
| 3357 |
+
},
|
| 3358 |
+
{
|
| 3359 |
+
"epoch": 0.83,
|
| 3360 |
+
"learning_rate": 8.295408764678674e-06,
|
| 3361 |
+
"loss": 2.9665,
|
| 3362 |
+
"step": 279500
|
| 3363 |
+
},
|
| 3364 |
+
{
|
| 3365 |
+
"epoch": 0.84,
|
| 3366 |
+
"learning_rate": 8.220803055849833e-06,
|
| 3367 |
+
"loss": 2.9677,
|
| 3368 |
+
"step": 280000
|
| 3369 |
+
},
|
| 3370 |
+
{
|
| 3371 |
+
"epoch": 0.84,
|
| 3372 |
+
"learning_rate": 8.146197347020994e-06,
|
| 3373 |
+
"loss": 2.9644,
|
| 3374 |
+
"step": 280500
|
| 3375 |
+
},
|
| 3376 |
+
{
|
| 3377 |
+
"epoch": 0.84,
|
| 3378 |
+
"learning_rate": 8.071591638192156e-06,
|
| 3379 |
+
"loss": 2.9662,
|
| 3380 |
+
"step": 281000
|
| 3381 |
+
},
|
| 3382 |
+
{
|
| 3383 |
+
"epoch": 0.84,
|
| 3384 |
+
"learning_rate": 7.996985929363315e-06,
|
| 3385 |
+
"loss": 2.9606,
|
| 3386 |
+
"step": 281500
|
| 3387 |
+
},
|
| 3388 |
+
{
|
| 3389 |
+
"epoch": 0.84,
|
| 3390 |
+
"learning_rate": 7.922380220534475e-06,
|
| 3391 |
+
"loss": 2.9538,
|
| 3392 |
+
"step": 282000
|
| 3393 |
+
},
|
| 3394 |
+
{
|
| 3395 |
+
"epoch": 0.84,
|
| 3396 |
+
"learning_rate": 7.847774511705636e-06,
|
| 3397 |
+
"loss": 2.956,
|
| 3398 |
+
"step": 282500
|
| 3399 |
+
},
|
| 3400 |
+
{
|
| 3401 |
+
"epoch": 0.84,
|
| 3402 |
+
"learning_rate": 7.773168802876797e-06,
|
| 3403 |
+
"loss": 2.9607,
|
| 3404 |
+
"step": 283000
|
| 3405 |
+
},
|
| 3406 |
+
{
|
| 3407 |
+
"epoch": 0.85,
|
| 3408 |
+
"learning_rate": 7.698563094047957e-06,
|
| 3409 |
+
"loss": 2.9597,
|
| 3410 |
+
"step": 283500
|
| 3411 |
+
},
|
| 3412 |
+
{
|
| 3413 |
+
"epoch": 0.85,
|
| 3414 |
+
"learning_rate": 7.623957385219117e-06,
|
| 3415 |
+
"loss": 2.959,
|
| 3416 |
+
"step": 284000
|
| 3417 |
+
},
|
| 3418 |
+
{
|
| 3419 |
+
"epoch": 0.85,
|
| 3420 |
+
"learning_rate": 7.549351676390278e-06,
|
| 3421 |
+
"loss": 2.9556,
|
| 3422 |
+
"step": 284500
|
| 3423 |
+
},
|
| 3424 |
+
{
|
| 3425 |
+
"epoch": 0.85,
|
| 3426 |
+
"learning_rate": 7.474745967561437e-06,
|
| 3427 |
+
"loss": 2.956,
|
| 3428 |
+
"step": 285000
|
| 3429 |
+
},
|
| 3430 |
+
{
|
| 3431 |
+
"epoch": 0.85,
|
| 3432 |
+
"learning_rate": 7.4001402587325994e-06,
|
| 3433 |
+
"loss": 2.9547,
|
| 3434 |
+
"step": 285500
|
| 3435 |
+
},
|
| 3436 |
+
{
|
| 3437 |
+
"epoch": 0.85,
|
| 3438 |
+
"learning_rate": 7.325534549903759e-06,
|
| 3439 |
+
"loss": 2.9661,
|
| 3440 |
+
"step": 286000
|
| 3441 |
+
},
|
| 3442 |
+
{
|
| 3443 |
+
"epoch": 0.85,
|
| 3444 |
+
"learning_rate": 7.2509288410749194e-06,
|
| 3445 |
+
"loss": 2.9524,
|
| 3446 |
+
"step": 286500
|
| 3447 |
+
},
|
| 3448 |
+
{
|
| 3449 |
+
"epoch": 0.86,
|
| 3450 |
+
"learning_rate": 7.176323132246079e-06,
|
| 3451 |
+
"loss": 2.9557,
|
| 3452 |
+
"step": 287000
|
| 3453 |
+
},
|
| 3454 |
+
{
|
| 3455 |
+
"epoch": 0.86,
|
| 3456 |
+
"learning_rate": 7.1017174234172394e-06,
|
| 3457 |
+
"loss": 2.9675,
|
| 3458 |
+
"step": 287500
|
| 3459 |
+
},
|
| 3460 |
+
{
|
| 3461 |
+
"epoch": 0.86,
|
| 3462 |
+
"learning_rate": 7.027111714588401e-06,
|
| 3463 |
+
"loss": 2.9587,
|
| 3464 |
+
"step": 288000
|
| 3465 |
+
},
|
| 3466 |
+
{
|
| 3467 |
+
"epoch": 0.86,
|
| 3468 |
+
"learning_rate": 6.952506005759561e-06,
|
| 3469 |
+
"loss": 2.9318,
|
| 3470 |
+
"step": 288500
|
| 3471 |
+
},
|
| 3472 |
+
{
|
| 3473 |
+
"epoch": 0.86,
|
| 3474 |
+
"learning_rate": 6.8779002969307216e-06,
|
| 3475 |
+
"loss": 2.9583,
|
| 3476 |
+
"step": 289000
|
| 3477 |
+
},
|
| 3478 |
+
{
|
| 3479 |
+
"epoch": 0.86,
|
| 3480 |
+
"learning_rate": 6.803294588101881e-06,
|
| 3481 |
+
"loss": 2.9556,
|
| 3482 |
+
"step": 289500
|
| 3483 |
+
},
|
| 3484 |
+
{
|
| 3485 |
+
"epoch": 0.87,
|
| 3486 |
+
"learning_rate": 6.728688879273043e-06,
|
| 3487 |
+
"loss": 2.9436,
|
| 3488 |
+
"step": 290000
|
| 3489 |
+
},
|
| 3490 |
+
{
|
| 3491 |
+
"epoch": 0.87,
|
| 3492 |
+
"learning_rate": 6.654083170444203e-06,
|
| 3493 |
+
"loss": 2.954,
|
| 3494 |
+
"step": 290500
|
| 3495 |
+
},
|
| 3496 |
+
{
|
| 3497 |
+
"epoch": 0.87,
|
| 3498 |
+
"learning_rate": 6.579477461615363e-06,
|
| 3499 |
+
"loss": 2.9691,
|
| 3500 |
+
"step": 291000
|
| 3501 |
+
},
|
| 3502 |
+
{
|
| 3503 |
+
"epoch": 0.87,
|
| 3504 |
+
"learning_rate": 6.504871752786524e-06,
|
| 3505 |
+
"loss": 2.9443,
|
| 3506 |
+
"step": 291500
|
| 3507 |
+
},
|
| 3508 |
+
{
|
| 3509 |
+
"epoch": 0.87,
|
| 3510 |
+
"learning_rate": 6.430266043957683e-06,
|
| 3511 |
+
"loss": 2.9236,
|
| 3512 |
+
"step": 292000
|
| 3513 |
+
},
|
| 3514 |
+
{
|
| 3515 |
+
"epoch": 0.87,
|
| 3516 |
+
"learning_rate": 6.3556603351288445e-06,
|
| 3517 |
+
"loss": 2.9331,
|
| 3518 |
+
"step": 292500
|
| 3519 |
+
},
|
| 3520 |
+
{
|
| 3521 |
+
"epoch": 0.87,
|
| 3522 |
+
"learning_rate": 6.281054626300005e-06,
|
| 3523 |
+
"loss": 2.9342,
|
| 3524 |
+
"step": 293000
|
| 3525 |
+
},
|
| 3526 |
+
{
|
| 3527 |
+
"epoch": 0.88,
|
| 3528 |
+
"learning_rate": 6.206448917471165e-06,
|
| 3529 |
+
"loss": 2.9598,
|
| 3530 |
+
"step": 293500
|
| 3531 |
+
},
|
| 3532 |
+
{
|
| 3533 |
+
"epoch": 0.88,
|
| 3534 |
+
"learning_rate": 6.131843208642326e-06,
|
| 3535 |
+
"loss": 2.9562,
|
| 3536 |
+
"step": 294000
|
| 3537 |
+
},
|
| 3538 |
+
{
|
| 3539 |
+
"epoch": 0.88,
|
| 3540 |
+
"learning_rate": 6.057237499813486e-06,
|
| 3541 |
+
"loss": 2.9264,
|
| 3542 |
+
"step": 294500
|
| 3543 |
+
},
|
| 3544 |
+
{
|
| 3545 |
+
"epoch": 0.88,
|
| 3546 |
+
"learning_rate": 5.982631790984647e-06,
|
| 3547 |
+
"loss": 2.9349,
|
| 3548 |
+
"step": 295000
|
| 3549 |
+
},
|
| 3550 |
+
{
|
| 3551 |
+
"epoch": 0.88,
|
| 3552 |
+
"learning_rate": 5.908026082155807e-06,
|
| 3553 |
+
"loss": 2.9384,
|
| 3554 |
+
"step": 295500
|
| 3555 |
+
},
|
| 3556 |
+
{
|
| 3557 |
+
"epoch": 0.88,
|
| 3558 |
+
"learning_rate": 5.8334203733269674e-06,
|
| 3559 |
+
"loss": 2.9622,
|
| 3560 |
+
"step": 296000
|
| 3561 |
+
},
|
| 3562 |
+
{
|
| 3563 |
+
"epoch": 0.88,
|
| 3564 |
+
"learning_rate": 5.758814664498128e-06,
|
| 3565 |
+
"loss": 2.9589,
|
| 3566 |
+
"step": 296500
|
| 3567 |
+
},
|
| 3568 |
+
{
|
| 3569 |
+
"epoch": 0.89,
|
| 3570 |
+
"learning_rate": 5.684208955669288e-06,
|
| 3571 |
+
"loss": 2.9395,
|
| 3572 |
+
"step": 297000
|
| 3573 |
+
},
|
| 3574 |
+
{
|
| 3575 |
+
"epoch": 0.89,
|
| 3576 |
+
"learning_rate": 5.609603246840448e-06,
|
| 3577 |
+
"loss": 2.9342,
|
| 3578 |
+
"step": 297500
|
| 3579 |
+
},
|
| 3580 |
+
{
|
| 3581 |
+
"epoch": 0.89,
|
| 3582 |
+
"learning_rate": 5.534997538011609e-06,
|
| 3583 |
+
"loss": 2.9262,
|
| 3584 |
+
"step": 298000
|
| 3585 |
+
},
|
| 3586 |
+
{
|
| 3587 |
+
"epoch": 0.89,
|
| 3588 |
+
"learning_rate": 5.460391829182769e-06,
|
| 3589 |
+
"loss": 2.9391,
|
| 3590 |
+
"step": 298500
|
| 3591 |
+
},
|
| 3592 |
+
{
|
| 3593 |
+
"epoch": 0.89,
|
| 3594 |
+
"learning_rate": 5.38578612035393e-06,
|
| 3595 |
+
"loss": 2.9451,
|
| 3596 |
+
"step": 299000
|
| 3597 |
+
},
|
| 3598 |
+
{
|
| 3599 |
+
"epoch": 0.89,
|
| 3600 |
+
"learning_rate": 5.31118041152509e-06,
|
| 3601 |
+
"loss": 2.9182,
|
| 3602 |
+
"step": 299500
|
| 3603 |
+
},
|
| 3604 |
+
{
|
| 3605 |
+
"epoch": 0.9,
|
| 3606 |
+
"learning_rate": 5.236574702696251e-06,
|
| 3607 |
+
"loss": 2.9519,
|
| 3608 |
+
"step": 300000
|
| 3609 |
+
},
|
| 3610 |
+
{
|
| 3611 |
+
"epoch": 0.9,
|
| 3612 |
+
"learning_rate": 5.161968993867411e-06,
|
| 3613 |
+
"loss": 2.9299,
|
| 3614 |
+
"step": 300500
|
| 3615 |
+
},
|
| 3616 |
+
{
|
| 3617 |
+
"epoch": 0.9,
|
| 3618 |
+
"learning_rate": 5.087363285038571e-06,
|
| 3619 |
+
"loss": 2.9176,
|
| 3620 |
+
"step": 301000
|
| 3621 |
+
},
|
| 3622 |
+
{
|
| 3623 |
+
"epoch": 0.9,
|
| 3624 |
+
"learning_rate": 5.012757576209732e-06,
|
| 3625 |
+
"loss": 2.9499,
|
| 3626 |
+
"step": 301500
|
| 3627 |
+
},
|
| 3628 |
+
{
|
| 3629 |
+
"epoch": 0.9,
|
| 3630 |
+
"learning_rate": 4.938151867380892e-06,
|
| 3631 |
+
"loss": 2.9258,
|
| 3632 |
+
"step": 302000
|
| 3633 |
+
},
|
| 3634 |
+
{
|
| 3635 |
+
"epoch": 0.9,
|
| 3636 |
+
"learning_rate": 4.863546158552053e-06,
|
| 3637 |
+
"loss": 2.9396,
|
| 3638 |
+
"step": 302500
|
| 3639 |
+
},
|
| 3640 |
+
{
|
| 3641 |
+
"epoch": 0.9,
|
| 3642 |
+
"learning_rate": 4.788940449723213e-06,
|
| 3643 |
+
"loss": 2.941,
|
| 3644 |
+
"step": 303000
|
| 3645 |
+
},
|
| 3646 |
+
{
|
| 3647 |
+
"epoch": 0.91,
|
| 3648 |
+
"learning_rate": 4.714334740894374e-06,
|
| 3649 |
+
"loss": 2.9308,
|
| 3650 |
+
"step": 303500
|
| 3651 |
+
},
|
| 3652 |
+
{
|
| 3653 |
+
"epoch": 0.91,
|
| 3654 |
+
"learning_rate": 4.639729032065534e-06,
|
| 3655 |
+
"loss": 2.9213,
|
| 3656 |
+
"step": 304000
|
| 3657 |
+
},
|
| 3658 |
+
{
|
| 3659 |
+
"epoch": 0.91,
|
| 3660 |
+
"learning_rate": 4.565123323236694e-06,
|
| 3661 |
+
"loss": 2.9097,
|
| 3662 |
+
"step": 304500
|
| 3663 |
+
},
|
| 3664 |
+
{
|
| 3665 |
+
"epoch": 0.91,
|
| 3666 |
+
"learning_rate": 4.490517614407855e-06,
|
| 3667 |
+
"loss": 2.9218,
|
| 3668 |
+
"step": 305000
|
| 3669 |
+
},
|
| 3670 |
+
{
|
| 3671 |
+
"epoch": 0.91,
|
| 3672 |
+
"learning_rate": 4.415911905579015e-06,
|
| 3673 |
+
"loss": 2.9276,
|
| 3674 |
+
"step": 305500
|
| 3675 |
+
},
|
| 3676 |
+
{
|
| 3677 |
+
"epoch": 0.91,
|
| 3678 |
+
"learning_rate": 4.341306196750176e-06,
|
| 3679 |
+
"loss": 2.9296,
|
| 3680 |
+
"step": 306000
|
| 3681 |
+
},
|
| 3682 |
+
{
|
| 3683 |
+
"epoch": 0.91,
|
| 3684 |
+
"learning_rate": 4.2667004879213354e-06,
|
| 3685 |
+
"loss": 2.9332,
|
| 3686 |
+
"step": 306500
|
| 3687 |
+
},
|
| 3688 |
+
{
|
| 3689 |
+
"epoch": 0.92,
|
| 3690 |
+
"learning_rate": 4.192094779092497e-06,
|
| 3691 |
+
"loss": 2.9266,
|
| 3692 |
+
"step": 307000
|
| 3693 |
+
},
|
| 3694 |
+
{
|
| 3695 |
+
"epoch": 0.92,
|
| 3696 |
+
"learning_rate": 4.117489070263657e-06,
|
| 3697 |
+
"loss": 2.9239,
|
| 3698 |
+
"step": 307500
|
| 3699 |
+
},
|
| 3700 |
+
{
|
| 3701 |
+
"epoch": 0.92,
|
| 3702 |
+
"learning_rate": 4.042883361434817e-06,
|
| 3703 |
+
"loss": 2.9279,
|
| 3704 |
+
"step": 308000
|
| 3705 |
+
},
|
| 3706 |
+
{
|
| 3707 |
+
"epoch": 0.92,
|
| 3708 |
+
"learning_rate": 3.968277652605978e-06,
|
| 3709 |
+
"loss": 2.9062,
|
| 3710 |
+
"step": 308500
|
| 3711 |
+
},
|
| 3712 |
+
{
|
| 3713 |
+
"epoch": 0.92,
|
| 3714 |
+
"learning_rate": 3.8936719437771375e-06,
|
| 3715 |
+
"loss": 2.9261,
|
| 3716 |
+
"step": 309000
|
| 3717 |
+
},
|
| 3718 |
+
{
|
| 3719 |
+
"epoch": 0.92,
|
| 3720 |
+
"learning_rate": 3.819066234948299e-06,
|
| 3721 |
+
"loss": 2.9265,
|
| 3722 |
+
"step": 309500
|
| 3723 |
+
},
|
| 3724 |
+
{
|
| 3725 |
+
"epoch": 0.93,
|
| 3726 |
+
"learning_rate": 3.744460526119459e-06,
|
| 3727 |
+
"loss": 2.9235,
|
| 3728 |
+
"step": 310000
|
| 3729 |
+
},
|
| 3730 |
+
{
|
| 3731 |
+
"epoch": 0.93,
|
| 3732 |
+
"learning_rate": 3.6698548172906197e-06,
|
| 3733 |
+
"loss": 2.9121,
|
| 3734 |
+
"step": 310500
|
| 3735 |
+
},
|
| 3736 |
+
{
|
| 3737 |
+
"epoch": 0.93,
|
| 3738 |
+
"learning_rate": 3.5952491084617797e-06,
|
| 3739 |
+
"loss": 2.9207,
|
| 3740 |
+
"step": 311000
|
| 3741 |
+
},
|
| 3742 |
+
{
|
| 3743 |
+
"epoch": 0.93,
|
| 3744 |
+
"learning_rate": 3.5206433996329397e-06,
|
| 3745 |
+
"loss": 2.9282,
|
| 3746 |
+
"step": 311500
|
| 3747 |
+
},
|
| 3748 |
+
{
|
| 3749 |
+
"epoch": 0.93,
|
| 3750 |
+
"learning_rate": 3.4460376908041005e-06,
|
| 3751 |
+
"loss": 2.9205,
|
| 3752 |
+
"step": 312000
|
| 3753 |
+
},
|
| 3754 |
+
{
|
| 3755 |
+
"epoch": 0.93,
|
| 3756 |
+
"learning_rate": 3.371431981975261e-06,
|
| 3757 |
+
"loss": 2.9228,
|
| 3758 |
+
"step": 312500
|
| 3759 |
+
},
|
| 3760 |
+
{
|
| 3761 |
+
"epoch": 0.93,
|
| 3762 |
+
"learning_rate": 3.2968262731464213e-06,
|
| 3763 |
+
"loss": 2.9271,
|
| 3764 |
+
"step": 313000
|
| 3765 |
+
},
|
| 3766 |
+
{
|
| 3767 |
+
"epoch": 0.94,
|
| 3768 |
+
"learning_rate": 3.2222205643175818e-06,
|
| 3769 |
+
"loss": 2.9108,
|
| 3770 |
+
"step": 313500
|
| 3771 |
+
},
|
| 3772 |
+
{
|
| 3773 |
+
"epoch": 0.94,
|
| 3774 |
+
"learning_rate": 3.1476148554887426e-06,
|
| 3775 |
+
"loss": 2.9248,
|
| 3776 |
+
"step": 314000
|
| 3777 |
+
},
|
| 3778 |
+
{
|
| 3779 |
+
"epoch": 0.94,
|
| 3780 |
+
"learning_rate": 3.0730091466599026e-06,
|
| 3781 |
+
"loss": 2.9111,
|
| 3782 |
+
"step": 314500
|
| 3783 |
+
},
|
| 3784 |
+
{
|
| 3785 |
+
"epoch": 0.94,
|
| 3786 |
+
"learning_rate": 2.998403437831063e-06,
|
| 3787 |
+
"loss": 2.9206,
|
| 3788 |
+
"step": 315000
|
| 3789 |
+
},
|
| 3790 |
+
{
|
| 3791 |
+
"epoch": 0.94,
|
| 3792 |
+
"learning_rate": 2.9237977290022234e-06,
|
| 3793 |
+
"loss": 2.9175,
|
| 3794 |
+
"step": 315500
|
| 3795 |
+
},
|
| 3796 |
+
{
|
| 3797 |
+
"epoch": 0.94,
|
| 3798 |
+
"learning_rate": 2.8491920201733834e-06,
|
| 3799 |
+
"loss": 2.9326,
|
| 3800 |
+
"step": 316000
|
| 3801 |
+
},
|
| 3802 |
+
{
|
| 3803 |
+
"epoch": 0.94,
|
| 3804 |
+
"learning_rate": 2.7745863113445443e-06,
|
| 3805 |
+
"loss": 2.9216,
|
| 3806 |
+
"step": 316500
|
| 3807 |
+
},
|
| 3808 |
+
{
|
| 3809 |
+
"epoch": 0.95,
|
| 3810 |
+
"learning_rate": 2.6999806025157047e-06,
|
| 3811 |
+
"loss": 2.9272,
|
| 3812 |
+
"step": 317000
|
| 3813 |
+
},
|
| 3814 |
+
{
|
| 3815 |
+
"epoch": 0.95,
|
| 3816 |
+
"learning_rate": 2.625374893686865e-06,
|
| 3817 |
+
"loss": 2.903,
|
| 3818 |
+
"step": 317500
|
| 3819 |
+
},
|
| 3820 |
+
{
|
| 3821 |
+
"epoch": 0.95,
|
| 3822 |
+
"learning_rate": 2.5507691848580256e-06,
|
| 3823 |
+
"loss": 2.8962,
|
| 3824 |
+
"step": 318000
|
| 3825 |
+
},
|
| 3826 |
+
{
|
| 3827 |
+
"epoch": 0.95,
|
| 3828 |
+
"learning_rate": 2.476163476029186e-06,
|
| 3829 |
+
"loss": 2.9097,
|
| 3830 |
+
"step": 318500
|
| 3831 |
+
},
|
| 3832 |
+
{
|
| 3833 |
+
"epoch": 0.95,
|
| 3834 |
+
"learning_rate": 2.4015577672003464e-06,
|
| 3835 |
+
"loss": 2.9369,
|
| 3836 |
+
"step": 319000
|
| 3837 |
+
},
|
| 3838 |
+
{
|
| 3839 |
+
"epoch": 0.95,
|
| 3840 |
+
"learning_rate": 2.3269520583715064e-06,
|
| 3841 |
+
"loss": 2.9132,
|
| 3842 |
+
"step": 319500
|
| 3843 |
+
},
|
| 3844 |
+
{
|
| 3845 |
+
"epoch": 0.95,
|
| 3846 |
+
"learning_rate": 2.252346349542667e-06,
|
| 3847 |
+
"loss": 2.9185,
|
| 3848 |
+
"step": 320000
|
| 3849 |
+
}
|
| 3850 |
+
],
|
| 3851 |
+
"max_steps": 335095,
|
| 3852 |
+
"num_train_epochs": 1,
|
| 3853 |
+
"total_flos": 2.1086164784256e+16,
|
| 3854 |
+
"trial_name": null,
|
| 3855 |
+
"trial_params": null
|
| 3856 |
+
}
|
checkpoint-320000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3d35089d0c3a6b47b1c8df0ddfa08b310484c437d7fde3fd7b723448ffc0097d
|
| 3 |
+
size 2415
|
checkpoint-330000/config.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"RobertaForMaskedLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"bos_token_id": 0,
|
| 7 |
+
"eos_token_id": 2,
|
| 8 |
+
"gradient_checkpointing": false,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 3072,
|
| 14 |
+
"layer_norm_eps": 1e-12,
|
| 15 |
+
"max_position_embeddings": 512,
|
| 16 |
+
"model_type": "roberta",
|
| 17 |
+
"num_attention_heads": 12,
|
| 18 |
+
"num_hidden_layers": 6,
|
| 19 |
+
"pad_token_id": 1,
|
| 20 |
+
"position_embedding_type": "absolute",
|
| 21 |
+
"transformers_version": "4.6.1",
|
| 22 |
+
"type_vocab_size": 1,
|
| 23 |
+
"use_cache": true,
|
| 24 |
+
"vocab_size": 55000
|
| 25 |
+
}
|
checkpoint-330000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ba1ad987989f29651aafa3d65f80a69ebc4c2c8ec0bcdc45068874d89dc9e005
|
| 3 |
+
size 686545359
|
checkpoint-330000/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c0723b5156f47cc33c7870c7d4657ca3e341564c152229f34a313c950edda266
|
| 3 |
+
size 343289095
|
checkpoint-330000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b0a335da35bdf02d6bc1960070b27cd288789fcad037d2076e57114f60805ed7
|
| 3 |
+
size 14655
|
checkpoint-330000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:38ef596e49f762f7d1eeedc2573bce8e3eae3c7c468b7ac0b528d917e1109cbb
|
| 3 |
+
size 623
|
checkpoint-330000/trainer_state.json
ADDED
|
@@ -0,0 +1,3976 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.9847953565406825,
|
| 5 |
+
"global_step": 330000,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.0,
|
| 12 |
+
"learning_rate": 4.9925394291171165e-05,
|
| 13 |
+
"loss": 8.8395,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.0,
|
| 18 |
+
"learning_rate": 4.985078858234232e-05,
|
| 19 |
+
"loss": 8.3374,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.0,
|
| 24 |
+
"learning_rate": 4.9776182873513485e-05,
|
| 25 |
+
"loss": 8.1726,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.01,
|
| 30 |
+
"learning_rate": 4.970157716468464e-05,
|
| 31 |
+
"loss": 8.0495,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.01,
|
| 36 |
+
"learning_rate": 4.9626971455855804e-05,
|
| 37 |
+
"loss": 7.9605,
|
| 38 |
+
"step": 2500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.01,
|
| 42 |
+
"learning_rate": 4.955236574702696e-05,
|
| 43 |
+
"loss": 7.9116,
|
| 44 |
+
"step": 3000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.01,
|
| 48 |
+
"learning_rate": 4.947776003819812e-05,
|
| 49 |
+
"loss": 7.8568,
|
| 50 |
+
"step": 3500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.01,
|
| 54 |
+
"learning_rate": 4.9403154329369286e-05,
|
| 55 |
+
"loss": 7.8353,
|
| 56 |
+
"step": 4000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.01,
|
| 60 |
+
"learning_rate": 4.932854862054044e-05,
|
| 61 |
+
"loss": 7.7883,
|
| 62 |
+
"step": 4500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.01,
|
| 66 |
+
"learning_rate": 4.925394291171161e-05,
|
| 67 |
+
"loss": 7.7753,
|
| 68 |
+
"step": 5000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.02,
|
| 72 |
+
"learning_rate": 4.917933720288277e-05,
|
| 73 |
+
"loss": 7.7461,
|
| 74 |
+
"step": 5500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.02,
|
| 78 |
+
"learning_rate": 4.910473149405393e-05,
|
| 79 |
+
"loss": 7.7202,
|
| 80 |
+
"step": 6000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.02,
|
| 84 |
+
"learning_rate": 4.903012578522509e-05,
|
| 85 |
+
"loss": 7.7102,
|
| 86 |
+
"step": 6500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.02,
|
| 90 |
+
"learning_rate": 4.895552007639625e-05,
|
| 91 |
+
"loss": 7.6642,
|
| 92 |
+
"step": 7000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.02,
|
| 96 |
+
"learning_rate": 4.888091436756741e-05,
|
| 97 |
+
"loss": 7.6294,
|
| 98 |
+
"step": 7500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.02,
|
| 102 |
+
"learning_rate": 4.880630865873857e-05,
|
| 103 |
+
"loss": 7.6012,
|
| 104 |
+
"step": 8000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.03,
|
| 108 |
+
"learning_rate": 4.873170294990973e-05,
|
| 109 |
+
"loss": 7.5369,
|
| 110 |
+
"step": 8500
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.03,
|
| 114 |
+
"learning_rate": 4.865709724108089e-05,
|
| 115 |
+
"loss": 7.4688,
|
| 116 |
+
"step": 9000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.03,
|
| 120 |
+
"learning_rate": 4.858249153225205e-05,
|
| 121 |
+
"loss": 7.3744,
|
| 122 |
+
"step": 9500
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.03,
|
| 126 |
+
"learning_rate": 4.850788582342321e-05,
|
| 127 |
+
"loss": 7.2764,
|
| 128 |
+
"step": 10000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.03,
|
| 132 |
+
"learning_rate": 4.843328011459437e-05,
|
| 133 |
+
"loss": 7.1243,
|
| 134 |
+
"step": 10500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.03,
|
| 138 |
+
"learning_rate": 4.835867440576553e-05,
|
| 139 |
+
"loss": 7.0236,
|
| 140 |
+
"step": 11000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.03,
|
| 144 |
+
"learning_rate": 4.828406869693669e-05,
|
| 145 |
+
"loss": 6.8878,
|
| 146 |
+
"step": 11500
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.04,
|
| 150 |
+
"learning_rate": 4.820946298810785e-05,
|
| 151 |
+
"loss": 6.795,
|
| 152 |
+
"step": 12000
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.04,
|
| 156 |
+
"learning_rate": 4.813485727927901e-05,
|
| 157 |
+
"loss": 6.694,
|
| 158 |
+
"step": 12500
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.04,
|
| 162 |
+
"learning_rate": 4.806025157045017e-05,
|
| 163 |
+
"loss": 6.6033,
|
| 164 |
+
"step": 13000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.04,
|
| 168 |
+
"learning_rate": 4.798564586162133e-05,
|
| 169 |
+
"loss": 6.492,
|
| 170 |
+
"step": 13500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.04,
|
| 174 |
+
"learning_rate": 4.791104015279249e-05,
|
| 175 |
+
"loss": 6.4154,
|
| 176 |
+
"step": 14000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.04,
|
| 180 |
+
"learning_rate": 4.7836434443963654e-05,
|
| 181 |
+
"loss": 6.3564,
|
| 182 |
+
"step": 14500
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 0.04,
|
| 186 |
+
"learning_rate": 4.776182873513482e-05,
|
| 187 |
+
"loss": 6.2773,
|
| 188 |
+
"step": 15000
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.05,
|
| 192 |
+
"learning_rate": 4.768722302630598e-05,
|
| 193 |
+
"loss": 6.2294,
|
| 194 |
+
"step": 15500
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.05,
|
| 198 |
+
"learning_rate": 4.7612617317477136e-05,
|
| 199 |
+
"loss": 6.1543,
|
| 200 |
+
"step": 16000
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 0.05,
|
| 204 |
+
"learning_rate": 4.75380116086483e-05,
|
| 205 |
+
"loss": 6.1043,
|
| 206 |
+
"step": 16500
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.05,
|
| 210 |
+
"learning_rate": 4.7463405899819455e-05,
|
| 211 |
+
"loss": 6.0266,
|
| 212 |
+
"step": 17000
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.05,
|
| 216 |
+
"learning_rate": 4.738880019099062e-05,
|
| 217 |
+
"loss": 5.9925,
|
| 218 |
+
"step": 17500
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.05,
|
| 222 |
+
"learning_rate": 4.731419448216178e-05,
|
| 223 |
+
"loss": 5.955,
|
| 224 |
+
"step": 18000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.06,
|
| 228 |
+
"learning_rate": 4.723958877333294e-05,
|
| 229 |
+
"loss": 5.8802,
|
| 230 |
+
"step": 18500
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 0.06,
|
| 234 |
+
"learning_rate": 4.71649830645041e-05,
|
| 235 |
+
"loss": 5.8472,
|
| 236 |
+
"step": 19000
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 0.06,
|
| 240 |
+
"learning_rate": 4.7090377355675256e-05,
|
| 241 |
+
"loss": 5.7843,
|
| 242 |
+
"step": 19500
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 0.06,
|
| 246 |
+
"learning_rate": 4.701577164684642e-05,
|
| 247 |
+
"loss": 5.7739,
|
| 248 |
+
"step": 20000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.06,
|
| 252 |
+
"learning_rate": 4.6941165938017575e-05,
|
| 253 |
+
"loss": 5.6922,
|
| 254 |
+
"step": 20500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.06,
|
| 258 |
+
"learning_rate": 4.686656022918874e-05,
|
| 259 |
+
"loss": 5.6593,
|
| 260 |
+
"step": 21000
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 0.06,
|
| 264 |
+
"learning_rate": 4.67919545203599e-05,
|
| 265 |
+
"loss": 5.6313,
|
| 266 |
+
"step": 21500
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 0.07,
|
| 270 |
+
"learning_rate": 4.671734881153106e-05,
|
| 271 |
+
"loss": 5.593,
|
| 272 |
+
"step": 22000
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 0.07,
|
| 276 |
+
"learning_rate": 4.664274310270222e-05,
|
| 277 |
+
"loss": 5.5471,
|
| 278 |
+
"step": 22500
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 0.07,
|
| 282 |
+
"learning_rate": 4.656813739387338e-05,
|
| 283 |
+
"loss": 5.49,
|
| 284 |
+
"step": 23000
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 0.07,
|
| 288 |
+
"learning_rate": 4.6493531685044546e-05,
|
| 289 |
+
"loss": 5.4655,
|
| 290 |
+
"step": 23500
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.07,
|
| 294 |
+
"learning_rate": 4.64189259762157e-05,
|
| 295 |
+
"loss": 5.4349,
|
| 296 |
+
"step": 24000
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.07,
|
| 300 |
+
"learning_rate": 4.6344320267386866e-05,
|
| 301 |
+
"loss": 5.3876,
|
| 302 |
+
"step": 24500
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 0.07,
|
| 306 |
+
"learning_rate": 4.626971455855802e-05,
|
| 307 |
+
"loss": 5.378,
|
| 308 |
+
"step": 25000
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 0.08,
|
| 312 |
+
"learning_rate": 4.6195108849729185e-05,
|
| 313 |
+
"loss": 5.3231,
|
| 314 |
+
"step": 25500
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.08,
|
| 318 |
+
"learning_rate": 4.612050314090035e-05,
|
| 319 |
+
"loss": 5.2968,
|
| 320 |
+
"step": 26000
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 0.08,
|
| 324 |
+
"learning_rate": 4.6045897432071504e-05,
|
| 325 |
+
"loss": 5.2649,
|
| 326 |
+
"step": 26500
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 0.08,
|
| 330 |
+
"learning_rate": 4.597129172324267e-05,
|
| 331 |
+
"loss": 5.2329,
|
| 332 |
+
"step": 27000
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.08,
|
| 336 |
+
"learning_rate": 4.589668601441382e-05,
|
| 337 |
+
"loss": 5.2015,
|
| 338 |
+
"step": 27500
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.08,
|
| 342 |
+
"learning_rate": 4.5822080305584986e-05,
|
| 343 |
+
"loss": 5.1858,
|
| 344 |
+
"step": 28000
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 0.09,
|
| 348 |
+
"learning_rate": 4.574747459675615e-05,
|
| 349 |
+
"loss": 5.1435,
|
| 350 |
+
"step": 28500
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 0.09,
|
| 354 |
+
"learning_rate": 4.5672868887927305e-05,
|
| 355 |
+
"loss": 5.1239,
|
| 356 |
+
"step": 29000
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 0.09,
|
| 360 |
+
"learning_rate": 4.559826317909847e-05,
|
| 361 |
+
"loss": 5.0947,
|
| 362 |
+
"step": 29500
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 0.09,
|
| 366 |
+
"learning_rate": 4.5523657470269624e-05,
|
| 367 |
+
"loss": 5.0852,
|
| 368 |
+
"step": 30000
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 0.09,
|
| 372 |
+
"learning_rate": 4.544905176144079e-05,
|
| 373 |
+
"loss": 5.0373,
|
| 374 |
+
"step": 30500
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.09,
|
| 378 |
+
"learning_rate": 4.5374446052611943e-05,
|
| 379 |
+
"loss": 5.0134,
|
| 380 |
+
"step": 31000
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.09,
|
| 384 |
+
"learning_rate": 4.5299840343783106e-05,
|
| 385 |
+
"loss": 5.0094,
|
| 386 |
+
"step": 31500
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 0.1,
|
| 390 |
+
"learning_rate": 4.522523463495427e-05,
|
| 391 |
+
"loss": 4.9855,
|
| 392 |
+
"step": 32000
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 0.1,
|
| 396 |
+
"learning_rate": 4.5150628926125426e-05,
|
| 397 |
+
"loss": 4.943,
|
| 398 |
+
"step": 32500
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 0.1,
|
| 402 |
+
"learning_rate": 4.5076023217296595e-05,
|
| 403 |
+
"loss": 4.9091,
|
| 404 |
+
"step": 33000
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 0.1,
|
| 408 |
+
"learning_rate": 4.500141750846775e-05,
|
| 409 |
+
"loss": 4.8988,
|
| 410 |
+
"step": 33500
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.1,
|
| 414 |
+
"learning_rate": 4.4926811799638914e-05,
|
| 415 |
+
"loss": 4.8703,
|
| 416 |
+
"step": 34000
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.1,
|
| 420 |
+
"learning_rate": 4.485220609081007e-05,
|
| 421 |
+
"loss": 4.8395,
|
| 422 |
+
"step": 34500
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.1,
|
| 426 |
+
"learning_rate": 4.4777600381981234e-05,
|
| 427 |
+
"loss": 4.8175,
|
| 428 |
+
"step": 35000
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 0.11,
|
| 432 |
+
"learning_rate": 4.470299467315239e-05,
|
| 433 |
+
"loss": 4.8181,
|
| 434 |
+
"step": 35500
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 0.11,
|
| 438 |
+
"learning_rate": 4.462838896432355e-05,
|
| 439 |
+
"loss": 4.8026,
|
| 440 |
+
"step": 36000
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 0.11,
|
| 444 |
+
"learning_rate": 4.4553783255494716e-05,
|
| 445 |
+
"loss": 4.7798,
|
| 446 |
+
"step": 36500
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 0.11,
|
| 450 |
+
"learning_rate": 4.447917754666587e-05,
|
| 451 |
+
"loss": 4.741,
|
| 452 |
+
"step": 37000
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 0.11,
|
| 456 |
+
"learning_rate": 4.4404571837837035e-05,
|
| 457 |
+
"loss": 4.7337,
|
| 458 |
+
"step": 37500
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.11,
|
| 462 |
+
"learning_rate": 4.432996612900819e-05,
|
| 463 |
+
"loss": 4.7278,
|
| 464 |
+
"step": 38000
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.11,
|
| 468 |
+
"learning_rate": 4.4255360420179354e-05,
|
| 469 |
+
"loss": 4.7057,
|
| 470 |
+
"step": 38500
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 0.12,
|
| 474 |
+
"learning_rate": 4.418075471135052e-05,
|
| 475 |
+
"loss": 4.6702,
|
| 476 |
+
"step": 39000
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 0.12,
|
| 480 |
+
"learning_rate": 4.410614900252167e-05,
|
| 481 |
+
"loss": 4.6704,
|
| 482 |
+
"step": 39500
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 0.12,
|
| 486 |
+
"learning_rate": 4.4031543293692836e-05,
|
| 487 |
+
"loss": 4.647,
|
| 488 |
+
"step": 40000
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 0.12,
|
| 492 |
+
"learning_rate": 4.395693758486399e-05,
|
| 493 |
+
"loss": 4.6325,
|
| 494 |
+
"step": 40500
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 0.12,
|
| 498 |
+
"learning_rate": 4.3882331876035155e-05,
|
| 499 |
+
"loss": 4.6142,
|
| 500 |
+
"step": 41000
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.12,
|
| 504 |
+
"learning_rate": 4.380772616720631e-05,
|
| 505 |
+
"loss": 4.5979,
|
| 506 |
+
"step": 41500
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.13,
|
| 510 |
+
"learning_rate": 4.3733120458377474e-05,
|
| 511 |
+
"loss": 4.5934,
|
| 512 |
+
"step": 42000
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 0.13,
|
| 516 |
+
"learning_rate": 4.365851474954864e-05,
|
| 517 |
+
"loss": 4.558,
|
| 518 |
+
"step": 42500
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 0.13,
|
| 522 |
+
"learning_rate": 4.35839090407198e-05,
|
| 523 |
+
"loss": 4.5537,
|
| 524 |
+
"step": 43000
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 0.13,
|
| 528 |
+
"learning_rate": 4.350930333189096e-05,
|
| 529 |
+
"loss": 4.5202,
|
| 530 |
+
"step": 43500
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 0.13,
|
| 534 |
+
"learning_rate": 4.343469762306212e-05,
|
| 535 |
+
"loss": 4.5238,
|
| 536 |
+
"step": 44000
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 0.13,
|
| 540 |
+
"learning_rate": 4.336009191423328e-05,
|
| 541 |
+
"loss": 4.5052,
|
| 542 |
+
"step": 44500
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.13,
|
| 546 |
+
"learning_rate": 4.328548620540444e-05,
|
| 547 |
+
"loss": 4.4972,
|
| 548 |
+
"step": 45000
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.14,
|
| 552 |
+
"learning_rate": 4.32108804965756e-05,
|
| 553 |
+
"loss": 4.4751,
|
| 554 |
+
"step": 45500
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 0.14,
|
| 558 |
+
"learning_rate": 4.313627478774676e-05,
|
| 559 |
+
"loss": 4.4441,
|
| 560 |
+
"step": 46000
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 0.14,
|
| 564 |
+
"learning_rate": 4.306166907891792e-05,
|
| 565 |
+
"loss": 4.4482,
|
| 566 |
+
"step": 46500
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 0.14,
|
| 570 |
+
"learning_rate": 4.2987063370089084e-05,
|
| 571 |
+
"loss": 4.4365,
|
| 572 |
+
"step": 47000
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 0.14,
|
| 576 |
+
"learning_rate": 4.291245766126024e-05,
|
| 577 |
+
"loss": 4.4211,
|
| 578 |
+
"step": 47500
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 0.14,
|
| 582 |
+
"learning_rate": 4.28378519524314e-05,
|
| 583 |
+
"loss": 4.4135,
|
| 584 |
+
"step": 48000
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.14,
|
| 588 |
+
"learning_rate": 4.276324624360256e-05,
|
| 589 |
+
"loss": 4.3697,
|
| 590 |
+
"step": 48500
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.15,
|
| 594 |
+
"learning_rate": 4.268864053477372e-05,
|
| 595 |
+
"loss": 4.4008,
|
| 596 |
+
"step": 49000
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 0.15,
|
| 600 |
+
"learning_rate": 4.2614034825944885e-05,
|
| 601 |
+
"loss": 4.3786,
|
| 602 |
+
"step": 49500
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 0.15,
|
| 606 |
+
"learning_rate": 4.253942911711604e-05,
|
| 607 |
+
"loss": 4.3466,
|
| 608 |
+
"step": 50000
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 0.15,
|
| 612 |
+
"learning_rate": 4.2464823408287204e-05,
|
| 613 |
+
"loss": 4.3375,
|
| 614 |
+
"step": 50500
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 0.15,
|
| 618 |
+
"learning_rate": 4.239021769945836e-05,
|
| 619 |
+
"loss": 4.3199,
|
| 620 |
+
"step": 51000
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 0.15,
|
| 624 |
+
"learning_rate": 4.231561199062952e-05,
|
| 625 |
+
"loss": 4.3171,
|
| 626 |
+
"step": 51500
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.16,
|
| 630 |
+
"learning_rate": 4.2241006281800686e-05,
|
| 631 |
+
"loss": 4.3012,
|
| 632 |
+
"step": 52000
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.16,
|
| 636 |
+
"learning_rate": 4.216640057297185e-05,
|
| 637 |
+
"loss": 4.273,
|
| 638 |
+
"step": 52500
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 0.16,
|
| 642 |
+
"learning_rate": 4.2091794864143005e-05,
|
| 643 |
+
"loss": 4.287,
|
| 644 |
+
"step": 53000
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 0.16,
|
| 648 |
+
"learning_rate": 4.201718915531417e-05,
|
| 649 |
+
"loss": 4.2666,
|
| 650 |
+
"step": 53500
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 0.16,
|
| 654 |
+
"learning_rate": 4.194258344648533e-05,
|
| 655 |
+
"loss": 4.2536,
|
| 656 |
+
"step": 54000
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 0.16,
|
| 660 |
+
"learning_rate": 4.186797773765649e-05,
|
| 661 |
+
"loss": 4.2345,
|
| 662 |
+
"step": 54500
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 0.16,
|
| 666 |
+
"learning_rate": 4.179337202882765e-05,
|
| 667 |
+
"loss": 4.2495,
|
| 668 |
+
"step": 55000
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.17,
|
| 672 |
+
"learning_rate": 4.1718766319998807e-05,
|
| 673 |
+
"loss": 4.2232,
|
| 674 |
+
"step": 55500
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.17,
|
| 678 |
+
"learning_rate": 4.164416061116997e-05,
|
| 679 |
+
"loss": 4.219,
|
| 680 |
+
"step": 56000
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 0.17,
|
| 684 |
+
"learning_rate": 4.1569554902341126e-05,
|
| 685 |
+
"loss": 4.203,
|
| 686 |
+
"step": 56500
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 0.17,
|
| 690 |
+
"learning_rate": 4.149494919351229e-05,
|
| 691 |
+
"loss": 4.208,
|
| 692 |
+
"step": 57000
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 0.17,
|
| 696 |
+
"learning_rate": 4.142034348468345e-05,
|
| 697 |
+
"loss": 4.1815,
|
| 698 |
+
"step": 57500
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 0.17,
|
| 702 |
+
"learning_rate": 4.134573777585461e-05,
|
| 703 |
+
"loss": 4.1828,
|
| 704 |
+
"step": 58000
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 0.17,
|
| 708 |
+
"learning_rate": 4.127113206702577e-05,
|
| 709 |
+
"loss": 4.1539,
|
| 710 |
+
"step": 58500
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 0.18,
|
| 714 |
+
"learning_rate": 4.119652635819693e-05,
|
| 715 |
+
"loss": 4.1365,
|
| 716 |
+
"step": 59000
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 0.18,
|
| 720 |
+
"learning_rate": 4.112192064936809e-05,
|
| 721 |
+
"loss": 4.1362,
|
| 722 |
+
"step": 59500
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 0.18,
|
| 726 |
+
"learning_rate": 4.104731494053925e-05,
|
| 727 |
+
"loss": 4.1366,
|
| 728 |
+
"step": 60000
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 0.18,
|
| 732 |
+
"learning_rate": 4.097270923171041e-05,
|
| 733 |
+
"loss": 4.1265,
|
| 734 |
+
"step": 60500
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 0.18,
|
| 738 |
+
"learning_rate": 4.089810352288157e-05,
|
| 739 |
+
"loss": 4.1251,
|
| 740 |
+
"step": 61000
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 0.18,
|
| 744 |
+
"learning_rate": 4.0823497814052735e-05,
|
| 745 |
+
"loss": 4.1033,
|
| 746 |
+
"step": 61500
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 0.19,
|
| 750 |
+
"learning_rate": 4.07488921052239e-05,
|
| 751 |
+
"loss": 4.0914,
|
| 752 |
+
"step": 62000
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 0.19,
|
| 756 |
+
"learning_rate": 4.0674286396395054e-05,
|
| 757 |
+
"loss": 4.064,
|
| 758 |
+
"step": 62500
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 0.19,
|
| 762 |
+
"learning_rate": 4.059968068756622e-05,
|
| 763 |
+
"loss": 4.0919,
|
| 764 |
+
"step": 63000
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 0.19,
|
| 768 |
+
"learning_rate": 4.052507497873737e-05,
|
| 769 |
+
"loss": 4.0719,
|
| 770 |
+
"step": 63500
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 0.19,
|
| 774 |
+
"learning_rate": 4.0450469269908536e-05,
|
| 775 |
+
"loss": 4.0527,
|
| 776 |
+
"step": 64000
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 0.19,
|
| 780 |
+
"learning_rate": 4.03758635610797e-05,
|
| 781 |
+
"loss": 4.0483,
|
| 782 |
+
"step": 64500
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 0.19,
|
| 786 |
+
"learning_rate": 4.0301257852250855e-05,
|
| 787 |
+
"loss": 4.0287,
|
| 788 |
+
"step": 65000
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 0.2,
|
| 792 |
+
"learning_rate": 4.022665214342202e-05,
|
| 793 |
+
"loss": 4.0354,
|
| 794 |
+
"step": 65500
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 0.2,
|
| 798 |
+
"learning_rate": 4.0152046434593175e-05,
|
| 799 |
+
"loss": 4.0273,
|
| 800 |
+
"step": 66000
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 0.2,
|
| 804 |
+
"learning_rate": 4.007744072576434e-05,
|
| 805 |
+
"loss": 4.0207,
|
| 806 |
+
"step": 66500
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"epoch": 0.2,
|
| 810 |
+
"learning_rate": 4.0002835016935494e-05,
|
| 811 |
+
"loss": 4.0063,
|
| 812 |
+
"step": 67000
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 0.2,
|
| 816 |
+
"learning_rate": 3.992822930810666e-05,
|
| 817 |
+
"loss": 3.9946,
|
| 818 |
+
"step": 67500
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 0.2,
|
| 822 |
+
"learning_rate": 3.985362359927782e-05,
|
| 823 |
+
"loss": 3.9905,
|
| 824 |
+
"step": 68000
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 0.2,
|
| 828 |
+
"learning_rate": 3.9779017890448976e-05,
|
| 829 |
+
"loss": 3.9737,
|
| 830 |
+
"step": 68500
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 0.21,
|
| 834 |
+
"learning_rate": 3.970441218162014e-05,
|
| 835 |
+
"loss": 3.965,
|
| 836 |
+
"step": 69000
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 0.21,
|
| 840 |
+
"learning_rate": 3.9629806472791295e-05,
|
| 841 |
+
"loss": 3.9595,
|
| 842 |
+
"step": 69500
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.21,
|
| 846 |
+
"learning_rate": 3.955520076396246e-05,
|
| 847 |
+
"loss": 3.9496,
|
| 848 |
+
"step": 70000
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 0.21,
|
| 852 |
+
"learning_rate": 3.948059505513362e-05,
|
| 853 |
+
"loss": 3.9545,
|
| 854 |
+
"step": 70500
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 0.21,
|
| 858 |
+
"learning_rate": 3.9405989346304784e-05,
|
| 859 |
+
"loss": 3.9179,
|
| 860 |
+
"step": 71000
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"epoch": 0.21,
|
| 864 |
+
"learning_rate": 3.933138363747595e-05,
|
| 865 |
+
"loss": 3.9365,
|
| 866 |
+
"step": 71500
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 0.21,
|
| 870 |
+
"learning_rate": 3.92567779286471e-05,
|
| 871 |
+
"loss": 3.9161,
|
| 872 |
+
"step": 72000
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 0.22,
|
| 876 |
+
"learning_rate": 3.9182172219818266e-05,
|
| 877 |
+
"loss": 3.8996,
|
| 878 |
+
"step": 72500
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 0.22,
|
| 882 |
+
"learning_rate": 3.910756651098942e-05,
|
| 883 |
+
"loss": 3.8962,
|
| 884 |
+
"step": 73000
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 0.22,
|
| 888 |
+
"learning_rate": 3.9032960802160585e-05,
|
| 889 |
+
"loss": 3.8996,
|
| 890 |
+
"step": 73500
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 0.22,
|
| 894 |
+
"learning_rate": 3.895835509333174e-05,
|
| 895 |
+
"loss": 3.8986,
|
| 896 |
+
"step": 74000
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 0.22,
|
| 900 |
+
"learning_rate": 3.8883749384502904e-05,
|
| 901 |
+
"loss": 3.8726,
|
| 902 |
+
"step": 74500
|
| 903 |
+
},
|
| 904 |
+
{
|
| 905 |
+
"epoch": 0.22,
|
| 906 |
+
"learning_rate": 3.880914367567407e-05,
|
| 907 |
+
"loss": 3.8836,
|
| 908 |
+
"step": 75000
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 0.23,
|
| 912 |
+
"learning_rate": 3.8734537966845223e-05,
|
| 913 |
+
"loss": 3.8637,
|
| 914 |
+
"step": 75500
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 0.23,
|
| 918 |
+
"learning_rate": 3.8659932258016386e-05,
|
| 919 |
+
"loss": 3.8579,
|
| 920 |
+
"step": 76000
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 0.23,
|
| 924 |
+
"learning_rate": 3.858532654918754e-05,
|
| 925 |
+
"loss": 3.8529,
|
| 926 |
+
"step": 76500
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 0.23,
|
| 930 |
+
"learning_rate": 3.8510720840358706e-05,
|
| 931 |
+
"loss": 3.8406,
|
| 932 |
+
"step": 77000
|
| 933 |
+
},
|
| 934 |
+
{
|
| 935 |
+
"epoch": 0.23,
|
| 936 |
+
"learning_rate": 3.843611513152986e-05,
|
| 937 |
+
"loss": 3.8452,
|
| 938 |
+
"step": 77500
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 0.23,
|
| 942 |
+
"learning_rate": 3.8361509422701025e-05,
|
| 943 |
+
"loss": 3.8343,
|
| 944 |
+
"step": 78000
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"epoch": 0.23,
|
| 948 |
+
"learning_rate": 3.828690371387219e-05,
|
| 949 |
+
"loss": 3.8337,
|
| 950 |
+
"step": 78500
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 0.24,
|
| 954 |
+
"learning_rate": 3.8212298005043344e-05,
|
| 955 |
+
"loss": 3.82,
|
| 956 |
+
"step": 79000
|
| 957 |
+
},
|
| 958 |
+
{
|
| 959 |
+
"epoch": 0.24,
|
| 960 |
+
"learning_rate": 3.813769229621451e-05,
|
| 961 |
+
"loss": 3.8208,
|
| 962 |
+
"step": 79500
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 0.24,
|
| 966 |
+
"learning_rate": 3.806308658738567e-05,
|
| 967 |
+
"loss": 3.8178,
|
| 968 |
+
"step": 80000
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 0.24,
|
| 972 |
+
"learning_rate": 3.798848087855683e-05,
|
| 973 |
+
"loss": 3.7932,
|
| 974 |
+
"step": 80500
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 0.24,
|
| 978 |
+
"learning_rate": 3.791387516972799e-05,
|
| 979 |
+
"loss": 3.7966,
|
| 980 |
+
"step": 81000
|
| 981 |
+
},
|
| 982 |
+
{
|
| 983 |
+
"epoch": 0.24,
|
| 984 |
+
"learning_rate": 3.783926946089915e-05,
|
| 985 |
+
"loss": 3.7977,
|
| 986 |
+
"step": 81500
|
| 987 |
+
},
|
| 988 |
+
{
|
| 989 |
+
"epoch": 0.24,
|
| 990 |
+
"learning_rate": 3.7764663752070315e-05,
|
| 991 |
+
"loss": 3.7823,
|
| 992 |
+
"step": 82000
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 0.25,
|
| 996 |
+
"learning_rate": 3.769005804324147e-05,
|
| 997 |
+
"loss": 3.7802,
|
| 998 |
+
"step": 82500
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 0.25,
|
| 1002 |
+
"learning_rate": 3.7615452334412634e-05,
|
| 1003 |
+
"loss": 3.7686,
|
| 1004 |
+
"step": 83000
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 0.25,
|
| 1008 |
+
"learning_rate": 3.754084662558379e-05,
|
| 1009 |
+
"loss": 3.7709,
|
| 1010 |
+
"step": 83500
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 0.25,
|
| 1014 |
+
"learning_rate": 3.746624091675495e-05,
|
| 1015 |
+
"loss": 3.7671,
|
| 1016 |
+
"step": 84000
|
| 1017 |
+
},
|
| 1018 |
+
{
|
| 1019 |
+
"epoch": 0.25,
|
| 1020 |
+
"learning_rate": 3.739163520792611e-05,
|
| 1021 |
+
"loss": 3.7559,
|
| 1022 |
+
"step": 84500
|
| 1023 |
+
},
|
| 1024 |
+
{
|
| 1025 |
+
"epoch": 0.25,
|
| 1026 |
+
"learning_rate": 3.731702949909727e-05,
|
| 1027 |
+
"loss": 3.7743,
|
| 1028 |
+
"step": 85000
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"epoch": 0.26,
|
| 1032 |
+
"learning_rate": 3.7242423790268435e-05,
|
| 1033 |
+
"loss": 3.7467,
|
| 1034 |
+
"step": 85500
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 0.26,
|
| 1038 |
+
"learning_rate": 3.716781808143959e-05,
|
| 1039 |
+
"loss": 3.745,
|
| 1040 |
+
"step": 86000
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 0.26,
|
| 1044 |
+
"learning_rate": 3.7093212372610754e-05,
|
| 1045 |
+
"loss": 3.7379,
|
| 1046 |
+
"step": 86500
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 0.26,
|
| 1050 |
+
"learning_rate": 3.701860666378191e-05,
|
| 1051 |
+
"loss": 3.7105,
|
| 1052 |
+
"step": 87000
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 0.26,
|
| 1056 |
+
"learning_rate": 3.6944000954953074e-05,
|
| 1057 |
+
"loss": 3.7341,
|
| 1058 |
+
"step": 87500
|
| 1059 |
+
},
|
| 1060 |
+
{
|
| 1061 |
+
"epoch": 0.26,
|
| 1062 |
+
"learning_rate": 3.6869395246124237e-05,
|
| 1063 |
+
"loss": 3.7121,
|
| 1064 |
+
"step": 88000
|
| 1065 |
+
},
|
| 1066 |
+
{
|
| 1067 |
+
"epoch": 0.26,
|
| 1068 |
+
"learning_rate": 3.679478953729539e-05,
|
| 1069 |
+
"loss": 3.7154,
|
| 1070 |
+
"step": 88500
|
| 1071 |
+
},
|
| 1072 |
+
{
|
| 1073 |
+
"epoch": 0.27,
|
| 1074 |
+
"learning_rate": 3.6720183828466556e-05,
|
| 1075 |
+
"loss": 3.6959,
|
| 1076 |
+
"step": 89000
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 0.27,
|
| 1080 |
+
"learning_rate": 3.664557811963772e-05,
|
| 1081 |
+
"loss": 3.6943,
|
| 1082 |
+
"step": 89500
|
| 1083 |
+
},
|
| 1084 |
+
{
|
| 1085 |
+
"epoch": 0.27,
|
| 1086 |
+
"learning_rate": 3.657097241080888e-05,
|
| 1087 |
+
"loss": 3.6909,
|
| 1088 |
+
"step": 90000
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 0.27,
|
| 1092 |
+
"learning_rate": 3.649636670198004e-05,
|
| 1093 |
+
"loss": 3.6937,
|
| 1094 |
+
"step": 90500
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 0.27,
|
| 1098 |
+
"learning_rate": 3.64217609931512e-05,
|
| 1099 |
+
"loss": 3.6994,
|
| 1100 |
+
"step": 91000
|
| 1101 |
+
},
|
| 1102 |
+
{
|
| 1103 |
+
"epoch": 0.27,
|
| 1104 |
+
"learning_rate": 3.634715528432236e-05,
|
| 1105 |
+
"loss": 3.6758,
|
| 1106 |
+
"step": 91500
|
| 1107 |
+
},
|
| 1108 |
+
{
|
| 1109 |
+
"epoch": 0.27,
|
| 1110 |
+
"learning_rate": 3.627254957549352e-05,
|
| 1111 |
+
"loss": 3.6812,
|
| 1112 |
+
"step": 92000
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 0.28,
|
| 1116 |
+
"learning_rate": 3.619794386666468e-05,
|
| 1117 |
+
"loss": 3.6782,
|
| 1118 |
+
"step": 92500
|
| 1119 |
+
},
|
| 1120 |
+
{
|
| 1121 |
+
"epoch": 0.28,
|
| 1122 |
+
"learning_rate": 3.612333815783584e-05,
|
| 1123 |
+
"loss": 3.6732,
|
| 1124 |
+
"step": 93000
|
| 1125 |
+
},
|
| 1126 |
+
{
|
| 1127 |
+
"epoch": 0.28,
|
| 1128 |
+
"learning_rate": 3.6048732449007e-05,
|
| 1129 |
+
"loss": 3.6677,
|
| 1130 |
+
"step": 93500
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 0.28,
|
| 1134 |
+
"learning_rate": 3.597412674017816e-05,
|
| 1135 |
+
"loss": 3.6845,
|
| 1136 |
+
"step": 94000
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 0.28,
|
| 1140 |
+
"learning_rate": 3.589952103134932e-05,
|
| 1141 |
+
"loss": 3.6512,
|
| 1142 |
+
"step": 94500
|
| 1143 |
+
},
|
| 1144 |
+
{
|
| 1145 |
+
"epoch": 0.28,
|
| 1146 |
+
"learning_rate": 3.582491532252048e-05,
|
| 1147 |
+
"loss": 3.6636,
|
| 1148 |
+
"step": 95000
|
| 1149 |
+
},
|
| 1150 |
+
{
|
| 1151 |
+
"epoch": 0.28,
|
| 1152 |
+
"learning_rate": 3.575030961369164e-05,
|
| 1153 |
+
"loss": 3.6355,
|
| 1154 |
+
"step": 95500
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 0.29,
|
| 1158 |
+
"learning_rate": 3.56757039048628e-05,
|
| 1159 |
+
"loss": 3.6325,
|
| 1160 |
+
"step": 96000
|
| 1161 |
+
},
|
| 1162 |
+
{
|
| 1163 |
+
"epoch": 0.29,
|
| 1164 |
+
"learning_rate": 3.560109819603396e-05,
|
| 1165 |
+
"loss": 3.6498,
|
| 1166 |
+
"step": 96500
|
| 1167 |
+
},
|
| 1168 |
+
{
|
| 1169 |
+
"epoch": 0.29,
|
| 1170 |
+
"learning_rate": 3.552649248720512e-05,
|
| 1171 |
+
"loss": 3.6384,
|
| 1172 |
+
"step": 97000
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 0.29,
|
| 1176 |
+
"learning_rate": 3.545188677837628e-05,
|
| 1177 |
+
"loss": 3.6325,
|
| 1178 |
+
"step": 97500
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 0.29,
|
| 1182 |
+
"learning_rate": 3.537728106954744e-05,
|
| 1183 |
+
"loss": 3.6313,
|
| 1184 |
+
"step": 98000
|
| 1185 |
+
},
|
| 1186 |
+
{
|
| 1187 |
+
"epoch": 0.29,
|
| 1188 |
+
"learning_rate": 3.5302675360718605e-05,
|
| 1189 |
+
"loss": 3.6097,
|
| 1190 |
+
"step": 98500
|
| 1191 |
+
},
|
| 1192 |
+
{
|
| 1193 |
+
"epoch": 0.3,
|
| 1194 |
+
"learning_rate": 3.522806965188977e-05,
|
| 1195 |
+
"loss": 3.6196,
|
| 1196 |
+
"step": 99000
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 0.3,
|
| 1200 |
+
"learning_rate": 3.5153463943060924e-05,
|
| 1201 |
+
"loss": 3.6109,
|
| 1202 |
+
"step": 99500
|
| 1203 |
+
},
|
| 1204 |
+
{
|
| 1205 |
+
"epoch": 0.3,
|
| 1206 |
+
"learning_rate": 3.507885823423209e-05,
|
| 1207 |
+
"loss": 3.6011,
|
| 1208 |
+
"step": 100000
|
| 1209 |
+
},
|
| 1210 |
+
{
|
| 1211 |
+
"epoch": 0.3,
|
| 1212 |
+
"learning_rate": 3.500425252540325e-05,
|
| 1213 |
+
"loss": 3.6124,
|
| 1214 |
+
"step": 100500
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 0.3,
|
| 1218 |
+
"learning_rate": 3.4929646816574406e-05,
|
| 1219 |
+
"loss": 3.5833,
|
| 1220 |
+
"step": 101000
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 0.3,
|
| 1224 |
+
"learning_rate": 3.485504110774557e-05,
|
| 1225 |
+
"loss": 3.6067,
|
| 1226 |
+
"step": 101500
|
| 1227 |
+
},
|
| 1228 |
+
{
|
| 1229 |
+
"epoch": 0.3,
|
| 1230 |
+
"learning_rate": 3.4780435398916725e-05,
|
| 1231 |
+
"loss": 3.5863,
|
| 1232 |
+
"step": 102000
|
| 1233 |
+
},
|
| 1234 |
+
{
|
| 1235 |
+
"epoch": 0.31,
|
| 1236 |
+
"learning_rate": 3.470582969008789e-05,
|
| 1237 |
+
"loss": 3.6031,
|
| 1238 |
+
"step": 102500
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 0.31,
|
| 1242 |
+
"learning_rate": 3.463122398125905e-05,
|
| 1243 |
+
"loss": 3.571,
|
| 1244 |
+
"step": 103000
|
| 1245 |
+
},
|
| 1246 |
+
{
|
| 1247 |
+
"epoch": 0.31,
|
| 1248 |
+
"learning_rate": 3.455661827243021e-05,
|
| 1249 |
+
"loss": 3.5863,
|
| 1250 |
+
"step": 103500
|
| 1251 |
+
},
|
| 1252 |
+
{
|
| 1253 |
+
"epoch": 0.31,
|
| 1254 |
+
"learning_rate": 3.448201256360137e-05,
|
| 1255 |
+
"loss": 3.5817,
|
| 1256 |
+
"step": 104000
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 0.31,
|
| 1260 |
+
"learning_rate": 3.4407406854772526e-05,
|
| 1261 |
+
"loss": 3.5754,
|
| 1262 |
+
"step": 104500
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 0.31,
|
| 1266 |
+
"learning_rate": 3.433280114594369e-05,
|
| 1267 |
+
"loss": 3.5687,
|
| 1268 |
+
"step": 105000
|
| 1269 |
+
},
|
| 1270 |
+
{
|
| 1271 |
+
"epoch": 0.31,
|
| 1272 |
+
"learning_rate": 3.4258195437114845e-05,
|
| 1273 |
+
"loss": 3.5607,
|
| 1274 |
+
"step": 105500
|
| 1275 |
+
},
|
| 1276 |
+
{
|
| 1277 |
+
"epoch": 0.32,
|
| 1278 |
+
"learning_rate": 3.418358972828601e-05,
|
| 1279 |
+
"loss": 3.5635,
|
| 1280 |
+
"step": 106000
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 0.32,
|
| 1284 |
+
"learning_rate": 3.410898401945717e-05,
|
| 1285 |
+
"loss": 3.5597,
|
| 1286 |
+
"step": 106500
|
| 1287 |
+
},
|
| 1288 |
+
{
|
| 1289 |
+
"epoch": 0.32,
|
| 1290 |
+
"learning_rate": 3.403437831062833e-05,
|
| 1291 |
+
"loss": 3.5514,
|
| 1292 |
+
"step": 107000
|
| 1293 |
+
},
|
| 1294 |
+
{
|
| 1295 |
+
"epoch": 0.32,
|
| 1296 |
+
"learning_rate": 3.395977260179949e-05,
|
| 1297 |
+
"loss": 3.5589,
|
| 1298 |
+
"step": 107500
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 0.32,
|
| 1302 |
+
"learning_rate": 3.388516689297065e-05,
|
| 1303 |
+
"loss": 3.5548,
|
| 1304 |
+
"step": 108000
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 0.32,
|
| 1308 |
+
"learning_rate": 3.3810561184141816e-05,
|
| 1309 |
+
"loss": 3.5499,
|
| 1310 |
+
"step": 108500
|
| 1311 |
+
},
|
| 1312 |
+
{
|
| 1313 |
+
"epoch": 0.33,
|
| 1314 |
+
"learning_rate": 3.373595547531297e-05,
|
| 1315 |
+
"loss": 3.5236,
|
| 1316 |
+
"step": 109000
|
| 1317 |
+
},
|
| 1318 |
+
{
|
| 1319 |
+
"epoch": 0.33,
|
| 1320 |
+
"learning_rate": 3.3661349766484135e-05,
|
| 1321 |
+
"loss": 3.5433,
|
| 1322 |
+
"step": 109500
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 0.33,
|
| 1326 |
+
"learning_rate": 3.358674405765529e-05,
|
| 1327 |
+
"loss": 3.5355,
|
| 1328 |
+
"step": 110000
|
| 1329 |
+
},
|
| 1330 |
+
{
|
| 1331 |
+
"epoch": 0.33,
|
| 1332 |
+
"learning_rate": 3.3512138348826455e-05,
|
| 1333 |
+
"loss": 3.5246,
|
| 1334 |
+
"step": 110500
|
| 1335 |
+
},
|
| 1336 |
+
{
|
| 1337 |
+
"epoch": 0.33,
|
| 1338 |
+
"learning_rate": 3.343753263999762e-05,
|
| 1339 |
+
"loss": 3.5352,
|
| 1340 |
+
"step": 111000
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 0.33,
|
| 1344 |
+
"learning_rate": 3.3362926931168774e-05,
|
| 1345 |
+
"loss": 3.5268,
|
| 1346 |
+
"step": 111500
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 0.33,
|
| 1350 |
+
"learning_rate": 3.328832122233994e-05,
|
| 1351 |
+
"loss": 3.5209,
|
| 1352 |
+
"step": 112000
|
| 1353 |
+
},
|
| 1354 |
+
{
|
| 1355 |
+
"epoch": 0.34,
|
| 1356 |
+
"learning_rate": 3.321371551351109e-05,
|
| 1357 |
+
"loss": 3.4999,
|
| 1358 |
+
"step": 112500
|
| 1359 |
+
},
|
| 1360 |
+
{
|
| 1361 |
+
"epoch": 0.34,
|
| 1362 |
+
"learning_rate": 3.3139109804682256e-05,
|
| 1363 |
+
"loss": 3.5197,
|
| 1364 |
+
"step": 113000
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 0.34,
|
| 1368 |
+
"learning_rate": 3.306450409585342e-05,
|
| 1369 |
+
"loss": 3.5116,
|
| 1370 |
+
"step": 113500
|
| 1371 |
+
},
|
| 1372 |
+
{
|
| 1373 |
+
"epoch": 0.34,
|
| 1374 |
+
"learning_rate": 3.2989898387024575e-05,
|
| 1375 |
+
"loss": 3.5009,
|
| 1376 |
+
"step": 114000
|
| 1377 |
+
},
|
| 1378 |
+
{
|
| 1379 |
+
"epoch": 0.34,
|
| 1380 |
+
"learning_rate": 3.291529267819574e-05,
|
| 1381 |
+
"loss": 3.5102,
|
| 1382 |
+
"step": 114500
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 0.34,
|
| 1386 |
+
"learning_rate": 3.2840686969366894e-05,
|
| 1387 |
+
"loss": 3.5053,
|
| 1388 |
+
"step": 115000
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 0.34,
|
| 1392 |
+
"learning_rate": 3.276608126053806e-05,
|
| 1393 |
+
"loss": 3.4856,
|
| 1394 |
+
"step": 115500
|
| 1395 |
+
},
|
| 1396 |
+
{
|
| 1397 |
+
"epoch": 0.35,
|
| 1398 |
+
"learning_rate": 3.269147555170921e-05,
|
| 1399 |
+
"loss": 3.4952,
|
| 1400 |
+
"step": 116000
|
| 1401 |
+
},
|
| 1402 |
+
{
|
| 1403 |
+
"epoch": 0.35,
|
| 1404 |
+
"learning_rate": 3.2616869842880376e-05,
|
| 1405 |
+
"loss": 3.4888,
|
| 1406 |
+
"step": 116500
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 0.35,
|
| 1410 |
+
"learning_rate": 3.254226413405154e-05,
|
| 1411 |
+
"loss": 3.493,
|
| 1412 |
+
"step": 117000
|
| 1413 |
+
},
|
| 1414 |
+
{
|
| 1415 |
+
"epoch": 0.35,
|
| 1416 |
+
"learning_rate": 3.24676584252227e-05,
|
| 1417 |
+
"loss": 3.4838,
|
| 1418 |
+
"step": 117500
|
| 1419 |
+
},
|
| 1420 |
+
{
|
| 1421 |
+
"epoch": 0.35,
|
| 1422 |
+
"learning_rate": 3.2393052716393865e-05,
|
| 1423 |
+
"loss": 3.4716,
|
| 1424 |
+
"step": 118000
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 0.35,
|
| 1428 |
+
"learning_rate": 3.231844700756502e-05,
|
| 1429 |
+
"loss": 3.4816,
|
| 1430 |
+
"step": 118500
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 0.36,
|
| 1434 |
+
"learning_rate": 3.2243841298736184e-05,
|
| 1435 |
+
"loss": 3.4613,
|
| 1436 |
+
"step": 119000
|
| 1437 |
+
},
|
| 1438 |
+
{
|
| 1439 |
+
"epoch": 0.36,
|
| 1440 |
+
"learning_rate": 3.216923558990734e-05,
|
| 1441 |
+
"loss": 3.4446,
|
| 1442 |
+
"step": 119500
|
| 1443 |
+
},
|
| 1444 |
+
{
|
| 1445 |
+
"epoch": 0.36,
|
| 1446 |
+
"learning_rate": 3.2094629881078503e-05,
|
| 1447 |
+
"loss": 3.4699,
|
| 1448 |
+
"step": 120000
|
| 1449 |
+
},
|
| 1450 |
+
{
|
| 1451 |
+
"epoch": 0.36,
|
| 1452 |
+
"learning_rate": 3.202002417224966e-05,
|
| 1453 |
+
"loss": 3.4482,
|
| 1454 |
+
"step": 120500
|
| 1455 |
+
},
|
| 1456 |
+
{
|
| 1457 |
+
"epoch": 0.36,
|
| 1458 |
+
"learning_rate": 3.194541846342082e-05,
|
| 1459 |
+
"loss": 3.464,
|
| 1460 |
+
"step": 121000
|
| 1461 |
+
},
|
| 1462 |
+
{
|
| 1463 |
+
"epoch": 0.36,
|
| 1464 |
+
"learning_rate": 3.1870812754591986e-05,
|
| 1465 |
+
"loss": 3.4557,
|
| 1466 |
+
"step": 121500
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 0.36,
|
| 1470 |
+
"learning_rate": 3.179620704576314e-05,
|
| 1471 |
+
"loss": 3.4628,
|
| 1472 |
+
"step": 122000
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 0.37,
|
| 1476 |
+
"learning_rate": 3.1721601336934305e-05,
|
| 1477 |
+
"loss": 3.4543,
|
| 1478 |
+
"step": 122500
|
| 1479 |
+
},
|
| 1480 |
+
{
|
| 1481 |
+
"epoch": 0.37,
|
| 1482 |
+
"learning_rate": 3.164699562810546e-05,
|
| 1483 |
+
"loss": 3.4459,
|
| 1484 |
+
"step": 123000
|
| 1485 |
+
},
|
| 1486 |
+
{
|
| 1487 |
+
"epoch": 0.37,
|
| 1488 |
+
"learning_rate": 3.1572389919276624e-05,
|
| 1489 |
+
"loss": 3.4314,
|
| 1490 |
+
"step": 123500
|
| 1491 |
+
},
|
| 1492 |
+
{
|
| 1493 |
+
"epoch": 0.37,
|
| 1494 |
+
"learning_rate": 3.149778421044779e-05,
|
| 1495 |
+
"loss": 3.4374,
|
| 1496 |
+
"step": 124000
|
| 1497 |
+
},
|
| 1498 |
+
{
|
| 1499 |
+
"epoch": 0.37,
|
| 1500 |
+
"learning_rate": 3.142317850161894e-05,
|
| 1501 |
+
"loss": 3.4492,
|
| 1502 |
+
"step": 124500
|
| 1503 |
+
},
|
| 1504 |
+
{
|
| 1505 |
+
"epoch": 0.37,
|
| 1506 |
+
"learning_rate": 3.1348572792790106e-05,
|
| 1507 |
+
"loss": 3.4237,
|
| 1508 |
+
"step": 125000
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 0.37,
|
| 1512 |
+
"learning_rate": 3.127396708396126e-05,
|
| 1513 |
+
"loss": 3.4221,
|
| 1514 |
+
"step": 125500
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 0.38,
|
| 1518 |
+
"learning_rate": 3.1199361375132425e-05,
|
| 1519 |
+
"loss": 3.4291,
|
| 1520 |
+
"step": 126000
|
| 1521 |
+
},
|
| 1522 |
+
{
|
| 1523 |
+
"epoch": 0.38,
|
| 1524 |
+
"learning_rate": 3.112475566630358e-05,
|
| 1525 |
+
"loss": 3.4286,
|
| 1526 |
+
"step": 126500
|
| 1527 |
+
},
|
| 1528 |
+
{
|
| 1529 |
+
"epoch": 0.38,
|
| 1530 |
+
"learning_rate": 3.105014995747475e-05,
|
| 1531 |
+
"loss": 3.4244,
|
| 1532 |
+
"step": 127000
|
| 1533 |
+
},
|
| 1534 |
+
{
|
| 1535 |
+
"epoch": 0.38,
|
| 1536 |
+
"learning_rate": 3.097554424864591e-05,
|
| 1537 |
+
"loss": 3.4044,
|
| 1538 |
+
"step": 127500
|
| 1539 |
+
},
|
| 1540 |
+
{
|
| 1541 |
+
"epoch": 0.38,
|
| 1542 |
+
"learning_rate": 3.090093853981707e-05,
|
| 1543 |
+
"loss": 3.414,
|
| 1544 |
+
"step": 128000
|
| 1545 |
+
},
|
| 1546 |
+
{
|
| 1547 |
+
"epoch": 0.38,
|
| 1548 |
+
"learning_rate": 3.082633283098823e-05,
|
| 1549 |
+
"loss": 3.3993,
|
| 1550 |
+
"step": 128500
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 0.38,
|
| 1554 |
+
"learning_rate": 3.075172712215939e-05,
|
| 1555 |
+
"loss": 3.3988,
|
| 1556 |
+
"step": 129000
|
| 1557 |
+
},
|
| 1558 |
+
{
|
| 1559 |
+
"epoch": 0.39,
|
| 1560 |
+
"learning_rate": 3.067712141333055e-05,
|
| 1561 |
+
"loss": 3.4115,
|
| 1562 |
+
"step": 129500
|
| 1563 |
+
},
|
| 1564 |
+
{
|
| 1565 |
+
"epoch": 0.39,
|
| 1566 |
+
"learning_rate": 3.060251570450171e-05,
|
| 1567 |
+
"loss": 3.4092,
|
| 1568 |
+
"step": 130000
|
| 1569 |
+
},
|
| 1570 |
+
{
|
| 1571 |
+
"epoch": 0.39,
|
| 1572 |
+
"learning_rate": 3.052790999567287e-05,
|
| 1573 |
+
"loss": 3.4079,
|
| 1574 |
+
"step": 130500
|
| 1575 |
+
},
|
| 1576 |
+
{
|
| 1577 |
+
"epoch": 0.39,
|
| 1578 |
+
"learning_rate": 3.045330428684403e-05,
|
| 1579 |
+
"loss": 3.4052,
|
| 1580 |
+
"step": 131000
|
| 1581 |
+
},
|
| 1582 |
+
{
|
| 1583 |
+
"epoch": 0.39,
|
| 1584 |
+
"learning_rate": 3.037869857801519e-05,
|
| 1585 |
+
"loss": 3.4042,
|
| 1586 |
+
"step": 131500
|
| 1587 |
+
},
|
| 1588 |
+
{
|
| 1589 |
+
"epoch": 0.39,
|
| 1590 |
+
"learning_rate": 3.030409286918635e-05,
|
| 1591 |
+
"loss": 3.4048,
|
| 1592 |
+
"step": 132000
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 0.4,
|
| 1596 |
+
"learning_rate": 3.022948716035751e-05,
|
| 1597 |
+
"loss": 3.394,
|
| 1598 |
+
"step": 132500
|
| 1599 |
+
},
|
| 1600 |
+
{
|
| 1601 |
+
"epoch": 0.4,
|
| 1602 |
+
"learning_rate": 3.0154881451528673e-05,
|
| 1603 |
+
"loss": 3.3992,
|
| 1604 |
+
"step": 133000
|
| 1605 |
+
},
|
| 1606 |
+
{
|
| 1607 |
+
"epoch": 0.4,
|
| 1608 |
+
"learning_rate": 3.0080275742699832e-05,
|
| 1609 |
+
"loss": 3.3902,
|
| 1610 |
+
"step": 133500
|
| 1611 |
+
},
|
| 1612 |
+
{
|
| 1613 |
+
"epoch": 0.4,
|
| 1614 |
+
"learning_rate": 3.0005670033870992e-05,
|
| 1615 |
+
"loss": 3.3865,
|
| 1616 |
+
"step": 134000
|
| 1617 |
+
},
|
| 1618 |
+
{
|
| 1619 |
+
"epoch": 0.4,
|
| 1620 |
+
"learning_rate": 2.993106432504215e-05,
|
| 1621 |
+
"loss": 3.3717,
|
| 1622 |
+
"step": 134500
|
| 1623 |
+
},
|
| 1624 |
+
{
|
| 1625 |
+
"epoch": 0.4,
|
| 1626 |
+
"learning_rate": 2.985645861621331e-05,
|
| 1627 |
+
"loss": 3.3644,
|
| 1628 |
+
"step": 135000
|
| 1629 |
+
},
|
| 1630 |
+
{
|
| 1631 |
+
"epoch": 0.4,
|
| 1632 |
+
"learning_rate": 2.978185290738447e-05,
|
| 1633 |
+
"loss": 3.3742,
|
| 1634 |
+
"step": 135500
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 0.41,
|
| 1638 |
+
"learning_rate": 2.9707247198555634e-05,
|
| 1639 |
+
"loss": 3.3768,
|
| 1640 |
+
"step": 136000
|
| 1641 |
+
},
|
| 1642 |
+
{
|
| 1643 |
+
"epoch": 0.41,
|
| 1644 |
+
"learning_rate": 2.9632641489726797e-05,
|
| 1645 |
+
"loss": 3.3777,
|
| 1646 |
+
"step": 136500
|
| 1647 |
+
},
|
| 1648 |
+
{
|
| 1649 |
+
"epoch": 0.41,
|
| 1650 |
+
"learning_rate": 2.955803578089796e-05,
|
| 1651 |
+
"loss": 3.3829,
|
| 1652 |
+
"step": 137000
|
| 1653 |
+
},
|
| 1654 |
+
{
|
| 1655 |
+
"epoch": 0.41,
|
| 1656 |
+
"learning_rate": 2.948343007206912e-05,
|
| 1657 |
+
"loss": 3.3844,
|
| 1658 |
+
"step": 137500
|
| 1659 |
+
},
|
| 1660 |
+
{
|
| 1661 |
+
"epoch": 0.41,
|
| 1662 |
+
"learning_rate": 2.940882436324028e-05,
|
| 1663 |
+
"loss": 3.3808,
|
| 1664 |
+
"step": 138000
|
| 1665 |
+
},
|
| 1666 |
+
{
|
| 1667 |
+
"epoch": 0.41,
|
| 1668 |
+
"learning_rate": 2.9334218654411438e-05,
|
| 1669 |
+
"loss": 3.383,
|
| 1670 |
+
"step": 138500
|
| 1671 |
+
},
|
| 1672 |
+
{
|
| 1673 |
+
"epoch": 0.41,
|
| 1674 |
+
"learning_rate": 2.9259612945582598e-05,
|
| 1675 |
+
"loss": 3.3472,
|
| 1676 |
+
"step": 139000
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 0.42,
|
| 1680 |
+
"learning_rate": 2.9185007236753757e-05,
|
| 1681 |
+
"loss": 3.3513,
|
| 1682 |
+
"step": 139500
|
| 1683 |
+
},
|
| 1684 |
+
{
|
| 1685 |
+
"epoch": 0.42,
|
| 1686 |
+
"learning_rate": 2.911040152792492e-05,
|
| 1687 |
+
"loss": 3.3708,
|
| 1688 |
+
"step": 140000
|
| 1689 |
+
},
|
| 1690 |
+
{
|
| 1691 |
+
"epoch": 0.42,
|
| 1692 |
+
"learning_rate": 2.903579581909608e-05,
|
| 1693 |
+
"loss": 3.3629,
|
| 1694 |
+
"step": 140500
|
| 1695 |
+
},
|
| 1696 |
+
{
|
| 1697 |
+
"epoch": 0.42,
|
| 1698 |
+
"learning_rate": 2.896119011026724e-05,
|
| 1699 |
+
"loss": 3.347,
|
| 1700 |
+
"step": 141000
|
| 1701 |
+
},
|
| 1702 |
+
{
|
| 1703 |
+
"epoch": 0.42,
|
| 1704 |
+
"learning_rate": 2.88865844014384e-05,
|
| 1705 |
+
"loss": 3.3549,
|
| 1706 |
+
"step": 141500
|
| 1707 |
+
},
|
| 1708 |
+
{
|
| 1709 |
+
"epoch": 0.42,
|
| 1710 |
+
"learning_rate": 2.881197869260956e-05,
|
| 1711 |
+
"loss": 3.3466,
|
| 1712 |
+
"step": 142000
|
| 1713 |
+
},
|
| 1714 |
+
{
|
| 1715 |
+
"epoch": 0.43,
|
| 1716 |
+
"learning_rate": 2.8737372983780718e-05,
|
| 1717 |
+
"loss": 3.3347,
|
| 1718 |
+
"step": 142500
|
| 1719 |
+
},
|
| 1720 |
+
{
|
| 1721 |
+
"epoch": 0.43,
|
| 1722 |
+
"learning_rate": 2.8662767274951878e-05,
|
| 1723 |
+
"loss": 3.3401,
|
| 1724 |
+
"step": 143000
|
| 1725 |
+
},
|
| 1726 |
+
{
|
| 1727 |
+
"epoch": 0.43,
|
| 1728 |
+
"learning_rate": 2.858816156612304e-05,
|
| 1729 |
+
"loss": 3.3469,
|
| 1730 |
+
"step": 143500
|
| 1731 |
+
},
|
| 1732 |
+
{
|
| 1733 |
+
"epoch": 0.43,
|
| 1734 |
+
"learning_rate": 2.85135558572942e-05,
|
| 1735 |
+
"loss": 3.338,
|
| 1736 |
+
"step": 144000
|
| 1737 |
+
},
|
| 1738 |
+
{
|
| 1739 |
+
"epoch": 0.43,
|
| 1740 |
+
"learning_rate": 2.843895014846536e-05,
|
| 1741 |
+
"loss": 3.3338,
|
| 1742 |
+
"step": 144500
|
| 1743 |
+
},
|
| 1744 |
+
{
|
| 1745 |
+
"epoch": 0.43,
|
| 1746 |
+
"learning_rate": 2.836434443963652e-05,
|
| 1747 |
+
"loss": 3.3499,
|
| 1748 |
+
"step": 145000
|
| 1749 |
+
},
|
| 1750 |
+
{
|
| 1751 |
+
"epoch": 0.43,
|
| 1752 |
+
"learning_rate": 2.828973873080768e-05,
|
| 1753 |
+
"loss": 3.3313,
|
| 1754 |
+
"step": 145500
|
| 1755 |
+
},
|
| 1756 |
+
{
|
| 1757 |
+
"epoch": 0.44,
|
| 1758 |
+
"learning_rate": 2.8215133021978845e-05,
|
| 1759 |
+
"loss": 3.3263,
|
| 1760 |
+
"step": 146000
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"epoch": 0.44,
|
| 1764 |
+
"learning_rate": 2.8140527313150005e-05,
|
| 1765 |
+
"loss": 3.3386,
|
| 1766 |
+
"step": 146500
|
| 1767 |
+
},
|
| 1768 |
+
{
|
| 1769 |
+
"epoch": 0.44,
|
| 1770 |
+
"learning_rate": 2.8065921604321165e-05,
|
| 1771 |
+
"loss": 3.3229,
|
| 1772 |
+
"step": 147000
|
| 1773 |
+
},
|
| 1774 |
+
{
|
| 1775 |
+
"epoch": 0.44,
|
| 1776 |
+
"learning_rate": 2.7991315895492327e-05,
|
| 1777 |
+
"loss": 3.3186,
|
| 1778 |
+
"step": 147500
|
| 1779 |
+
},
|
| 1780 |
+
{
|
| 1781 |
+
"epoch": 0.44,
|
| 1782 |
+
"learning_rate": 2.7916710186663487e-05,
|
| 1783 |
+
"loss": 3.3272,
|
| 1784 |
+
"step": 148000
|
| 1785 |
+
},
|
| 1786 |
+
{
|
| 1787 |
+
"epoch": 0.44,
|
| 1788 |
+
"learning_rate": 2.7842104477834647e-05,
|
| 1789 |
+
"loss": 3.3052,
|
| 1790 |
+
"step": 148500
|
| 1791 |
+
},
|
| 1792 |
+
{
|
| 1793 |
+
"epoch": 0.44,
|
| 1794 |
+
"learning_rate": 2.7767498769005806e-05,
|
| 1795 |
+
"loss": 3.321,
|
| 1796 |
+
"step": 149000
|
| 1797 |
+
},
|
| 1798 |
+
{
|
| 1799 |
+
"epoch": 0.45,
|
| 1800 |
+
"learning_rate": 2.7692893060176966e-05,
|
| 1801 |
+
"loss": 3.3188,
|
| 1802 |
+
"step": 149500
|
| 1803 |
+
},
|
| 1804 |
+
{
|
| 1805 |
+
"epoch": 0.45,
|
| 1806 |
+
"learning_rate": 2.7618287351348125e-05,
|
| 1807 |
+
"loss": 3.3118,
|
| 1808 |
+
"step": 150000
|
| 1809 |
+
},
|
| 1810 |
+
{
|
| 1811 |
+
"epoch": 0.45,
|
| 1812 |
+
"learning_rate": 2.7543681642519288e-05,
|
| 1813 |
+
"loss": 3.3176,
|
| 1814 |
+
"step": 150500
|
| 1815 |
+
},
|
| 1816 |
+
{
|
| 1817 |
+
"epoch": 0.45,
|
| 1818 |
+
"learning_rate": 2.7469075933690448e-05,
|
| 1819 |
+
"loss": 3.3039,
|
| 1820 |
+
"step": 151000
|
| 1821 |
+
},
|
| 1822 |
+
{
|
| 1823 |
+
"epoch": 0.45,
|
| 1824 |
+
"learning_rate": 2.7394470224861607e-05,
|
| 1825 |
+
"loss": 3.2896,
|
| 1826 |
+
"step": 151500
|
| 1827 |
+
},
|
| 1828 |
+
{
|
| 1829 |
+
"epoch": 0.45,
|
| 1830 |
+
"learning_rate": 2.7319864516032767e-05,
|
| 1831 |
+
"loss": 3.2964,
|
| 1832 |
+
"step": 152000
|
| 1833 |
+
},
|
| 1834 |
+
{
|
| 1835 |
+
"epoch": 0.46,
|
| 1836 |
+
"learning_rate": 2.7245258807203927e-05,
|
| 1837 |
+
"loss": 3.2906,
|
| 1838 |
+
"step": 152500
|
| 1839 |
+
},
|
| 1840 |
+
{
|
| 1841 |
+
"epoch": 0.46,
|
| 1842 |
+
"learning_rate": 2.7170653098375086e-05,
|
| 1843 |
+
"loss": 3.2886,
|
| 1844 |
+
"step": 153000
|
| 1845 |
+
},
|
| 1846 |
+
{
|
| 1847 |
+
"epoch": 0.46,
|
| 1848 |
+
"learning_rate": 2.709604738954625e-05,
|
| 1849 |
+
"loss": 3.2987,
|
| 1850 |
+
"step": 153500
|
| 1851 |
+
},
|
| 1852 |
+
{
|
| 1853 |
+
"epoch": 0.46,
|
| 1854 |
+
"learning_rate": 2.702144168071741e-05,
|
| 1855 |
+
"loss": 3.272,
|
| 1856 |
+
"step": 154000
|
| 1857 |
+
},
|
| 1858 |
+
{
|
| 1859 |
+
"epoch": 0.46,
|
| 1860 |
+
"learning_rate": 2.6946835971888568e-05,
|
| 1861 |
+
"loss": 3.2735,
|
| 1862 |
+
"step": 154500
|
| 1863 |
+
},
|
| 1864 |
+
{
|
| 1865 |
+
"epoch": 0.46,
|
| 1866 |
+
"learning_rate": 2.6872230263059735e-05,
|
| 1867 |
+
"loss": 3.2632,
|
| 1868 |
+
"step": 155000
|
| 1869 |
+
},
|
| 1870 |
+
{
|
| 1871 |
+
"epoch": 0.46,
|
| 1872 |
+
"learning_rate": 2.6797624554230894e-05,
|
| 1873 |
+
"loss": 3.2933,
|
| 1874 |
+
"step": 155500
|
| 1875 |
+
},
|
| 1876 |
+
{
|
| 1877 |
+
"epoch": 0.47,
|
| 1878 |
+
"learning_rate": 2.6723018845402054e-05,
|
| 1879 |
+
"loss": 3.2911,
|
| 1880 |
+
"step": 156000
|
| 1881 |
+
},
|
| 1882 |
+
{
|
| 1883 |
+
"epoch": 0.47,
|
| 1884 |
+
"learning_rate": 2.6648413136573213e-05,
|
| 1885 |
+
"loss": 3.3155,
|
| 1886 |
+
"step": 156500
|
| 1887 |
+
},
|
| 1888 |
+
{
|
| 1889 |
+
"epoch": 0.47,
|
| 1890 |
+
"learning_rate": 2.6573807427744373e-05,
|
| 1891 |
+
"loss": 3.2821,
|
| 1892 |
+
"step": 157000
|
| 1893 |
+
},
|
| 1894 |
+
{
|
| 1895 |
+
"epoch": 0.47,
|
| 1896 |
+
"learning_rate": 2.6499201718915532e-05,
|
| 1897 |
+
"loss": 3.287,
|
| 1898 |
+
"step": 157500
|
| 1899 |
+
},
|
| 1900 |
+
{
|
| 1901 |
+
"epoch": 0.47,
|
| 1902 |
+
"learning_rate": 2.6424596010086695e-05,
|
| 1903 |
+
"loss": 3.2701,
|
| 1904 |
+
"step": 158000
|
| 1905 |
+
},
|
| 1906 |
+
{
|
| 1907 |
+
"epoch": 0.47,
|
| 1908 |
+
"learning_rate": 2.6349990301257855e-05,
|
| 1909 |
+
"loss": 3.2554,
|
| 1910 |
+
"step": 158500
|
| 1911 |
+
},
|
| 1912 |
+
{
|
| 1913 |
+
"epoch": 0.47,
|
| 1914 |
+
"learning_rate": 2.6275384592429015e-05,
|
| 1915 |
+
"loss": 3.2938,
|
| 1916 |
+
"step": 159000
|
| 1917 |
+
},
|
| 1918 |
+
{
|
| 1919 |
+
"epoch": 0.48,
|
| 1920 |
+
"learning_rate": 2.6200778883600174e-05,
|
| 1921 |
+
"loss": 3.2812,
|
| 1922 |
+
"step": 159500
|
| 1923 |
+
},
|
| 1924 |
+
{
|
| 1925 |
+
"epoch": 0.48,
|
| 1926 |
+
"learning_rate": 2.6126173174771334e-05,
|
| 1927 |
+
"loss": 3.2739,
|
| 1928 |
+
"step": 160000
|
| 1929 |
+
},
|
| 1930 |
+
{
|
| 1931 |
+
"epoch": 0.48,
|
| 1932 |
+
"learning_rate": 2.6051567465942493e-05,
|
| 1933 |
+
"loss": 3.2512,
|
| 1934 |
+
"step": 160500
|
| 1935 |
+
},
|
| 1936 |
+
{
|
| 1937 |
+
"epoch": 0.48,
|
| 1938 |
+
"learning_rate": 2.5976961757113656e-05,
|
| 1939 |
+
"loss": 3.2567,
|
| 1940 |
+
"step": 161000
|
| 1941 |
+
},
|
| 1942 |
+
{
|
| 1943 |
+
"epoch": 0.48,
|
| 1944 |
+
"learning_rate": 2.5902356048284816e-05,
|
| 1945 |
+
"loss": 3.2687,
|
| 1946 |
+
"step": 161500
|
| 1947 |
+
},
|
| 1948 |
+
{
|
| 1949 |
+
"epoch": 0.48,
|
| 1950 |
+
"learning_rate": 2.5827750339455975e-05,
|
| 1951 |
+
"loss": 3.2876,
|
| 1952 |
+
"step": 162000
|
| 1953 |
+
},
|
| 1954 |
+
{
|
| 1955 |
+
"epoch": 0.48,
|
| 1956 |
+
"learning_rate": 2.5753144630627135e-05,
|
| 1957 |
+
"loss": 3.2741,
|
| 1958 |
+
"step": 162500
|
| 1959 |
+
},
|
| 1960 |
+
{
|
| 1961 |
+
"epoch": 0.49,
|
| 1962 |
+
"learning_rate": 2.5678538921798295e-05,
|
| 1963 |
+
"loss": 3.2556,
|
| 1964 |
+
"step": 163000
|
| 1965 |
+
},
|
| 1966 |
+
{
|
| 1967 |
+
"epoch": 0.49,
|
| 1968 |
+
"learning_rate": 2.5603933212969454e-05,
|
| 1969 |
+
"loss": 3.2568,
|
| 1970 |
+
"step": 163500
|
| 1971 |
+
},
|
| 1972 |
+
{
|
| 1973 |
+
"epoch": 0.49,
|
| 1974 |
+
"learning_rate": 2.5529327504140617e-05,
|
| 1975 |
+
"loss": 3.2432,
|
| 1976 |
+
"step": 164000
|
| 1977 |
+
},
|
| 1978 |
+
{
|
| 1979 |
+
"epoch": 0.49,
|
| 1980 |
+
"learning_rate": 2.545472179531178e-05,
|
| 1981 |
+
"loss": 3.2467,
|
| 1982 |
+
"step": 164500
|
| 1983 |
+
},
|
| 1984 |
+
{
|
| 1985 |
+
"epoch": 0.49,
|
| 1986 |
+
"learning_rate": 2.538011608648294e-05,
|
| 1987 |
+
"loss": 3.2575,
|
| 1988 |
+
"step": 165000
|
| 1989 |
+
},
|
| 1990 |
+
{
|
| 1991 |
+
"epoch": 0.49,
|
| 1992 |
+
"learning_rate": 2.5305510377654103e-05,
|
| 1993 |
+
"loss": 3.248,
|
| 1994 |
+
"step": 165500
|
| 1995 |
+
},
|
| 1996 |
+
{
|
| 1997 |
+
"epoch": 0.5,
|
| 1998 |
+
"learning_rate": 2.5230904668825262e-05,
|
| 1999 |
+
"loss": 3.2438,
|
| 2000 |
+
"step": 166000
|
| 2001 |
+
},
|
| 2002 |
+
{
|
| 2003 |
+
"epoch": 0.5,
|
| 2004 |
+
"learning_rate": 2.5156298959996422e-05,
|
| 2005 |
+
"loss": 3.2516,
|
| 2006 |
+
"step": 166500
|
| 2007 |
+
},
|
| 2008 |
+
{
|
| 2009 |
+
"epoch": 0.5,
|
| 2010 |
+
"learning_rate": 2.508169325116758e-05,
|
| 2011 |
+
"loss": 3.2483,
|
| 2012 |
+
"step": 167000
|
| 2013 |
+
},
|
| 2014 |
+
{
|
| 2015 |
+
"epoch": 0.5,
|
| 2016 |
+
"learning_rate": 2.500708754233874e-05,
|
| 2017 |
+
"loss": 3.2313,
|
| 2018 |
+
"step": 167500
|
| 2019 |
+
},
|
| 2020 |
+
{
|
| 2021 |
+
"epoch": 0.5,
|
| 2022 |
+
"learning_rate": 2.49324818335099e-05,
|
| 2023 |
+
"loss": 3.2331,
|
| 2024 |
+
"step": 168000
|
| 2025 |
+
},
|
| 2026 |
+
{
|
| 2027 |
+
"epoch": 0.5,
|
| 2028 |
+
"learning_rate": 2.4857876124681063e-05,
|
| 2029 |
+
"loss": 3.2462,
|
| 2030 |
+
"step": 168500
|
| 2031 |
+
},
|
| 2032 |
+
{
|
| 2033 |
+
"epoch": 0.5,
|
| 2034 |
+
"learning_rate": 2.4783270415852223e-05,
|
| 2035 |
+
"loss": 3.2219,
|
| 2036 |
+
"step": 169000
|
| 2037 |
+
},
|
| 2038 |
+
{
|
| 2039 |
+
"epoch": 0.51,
|
| 2040 |
+
"learning_rate": 2.4708664707023383e-05,
|
| 2041 |
+
"loss": 3.2406,
|
| 2042 |
+
"step": 169500
|
| 2043 |
+
},
|
| 2044 |
+
{
|
| 2045 |
+
"epoch": 0.51,
|
| 2046 |
+
"learning_rate": 2.4634058998194542e-05,
|
| 2047 |
+
"loss": 3.2086,
|
| 2048 |
+
"step": 170000
|
| 2049 |
+
},
|
| 2050 |
+
{
|
| 2051 |
+
"epoch": 0.51,
|
| 2052 |
+
"learning_rate": 2.4559453289365702e-05,
|
| 2053 |
+
"loss": 3.2183,
|
| 2054 |
+
"step": 170500
|
| 2055 |
+
},
|
| 2056 |
+
{
|
| 2057 |
+
"epoch": 0.51,
|
| 2058 |
+
"learning_rate": 2.448484758053686e-05,
|
| 2059 |
+
"loss": 3.222,
|
| 2060 |
+
"step": 171000
|
| 2061 |
+
},
|
| 2062 |
+
{
|
| 2063 |
+
"epoch": 0.51,
|
| 2064 |
+
"learning_rate": 2.4410241871708024e-05,
|
| 2065 |
+
"loss": 3.2144,
|
| 2066 |
+
"step": 171500
|
| 2067 |
+
},
|
| 2068 |
+
{
|
| 2069 |
+
"epoch": 0.51,
|
| 2070 |
+
"learning_rate": 2.4335636162879187e-05,
|
| 2071 |
+
"loss": 3.2212,
|
| 2072 |
+
"step": 172000
|
| 2073 |
+
},
|
| 2074 |
+
{
|
| 2075 |
+
"epoch": 0.51,
|
| 2076 |
+
"learning_rate": 2.4261030454050347e-05,
|
| 2077 |
+
"loss": 3.2072,
|
| 2078 |
+
"step": 172500
|
| 2079 |
+
},
|
| 2080 |
+
{
|
| 2081 |
+
"epoch": 0.52,
|
| 2082 |
+
"learning_rate": 2.4186424745221506e-05,
|
| 2083 |
+
"loss": 3.2082,
|
| 2084 |
+
"step": 173000
|
| 2085 |
+
},
|
| 2086 |
+
{
|
| 2087 |
+
"epoch": 0.52,
|
| 2088 |
+
"learning_rate": 2.4111819036392666e-05,
|
| 2089 |
+
"loss": 3.2211,
|
| 2090 |
+
"step": 173500
|
| 2091 |
+
},
|
| 2092 |
+
{
|
| 2093 |
+
"epoch": 0.52,
|
| 2094 |
+
"learning_rate": 2.4037213327563826e-05,
|
| 2095 |
+
"loss": 3.1991,
|
| 2096 |
+
"step": 174000
|
| 2097 |
+
},
|
| 2098 |
+
{
|
| 2099 |
+
"epoch": 0.52,
|
| 2100 |
+
"learning_rate": 2.3962607618734985e-05,
|
| 2101 |
+
"loss": 3.222,
|
| 2102 |
+
"step": 174500
|
| 2103 |
+
},
|
| 2104 |
+
{
|
| 2105 |
+
"epoch": 0.52,
|
| 2106 |
+
"learning_rate": 2.3888001909906148e-05,
|
| 2107 |
+
"loss": 3.1956,
|
| 2108 |
+
"step": 175000
|
| 2109 |
+
},
|
| 2110 |
+
{
|
| 2111 |
+
"epoch": 0.52,
|
| 2112 |
+
"learning_rate": 2.3813396201077308e-05,
|
| 2113 |
+
"loss": 3.2101,
|
| 2114 |
+
"step": 175500
|
| 2115 |
+
},
|
| 2116 |
+
{
|
| 2117 |
+
"epoch": 0.53,
|
| 2118 |
+
"learning_rate": 2.3738790492248467e-05,
|
| 2119 |
+
"loss": 3.197,
|
| 2120 |
+
"step": 176000
|
| 2121 |
+
},
|
| 2122 |
+
{
|
| 2123 |
+
"epoch": 0.53,
|
| 2124 |
+
"learning_rate": 2.366418478341963e-05,
|
| 2125 |
+
"loss": 3.2057,
|
| 2126 |
+
"step": 176500
|
| 2127 |
+
},
|
| 2128 |
+
{
|
| 2129 |
+
"epoch": 0.53,
|
| 2130 |
+
"learning_rate": 2.358957907459079e-05,
|
| 2131 |
+
"loss": 3.1931,
|
| 2132 |
+
"step": 177000
|
| 2133 |
+
},
|
| 2134 |
+
{
|
| 2135 |
+
"epoch": 0.53,
|
| 2136 |
+
"learning_rate": 2.351497336576195e-05,
|
| 2137 |
+
"loss": 3.2,
|
| 2138 |
+
"step": 177500
|
| 2139 |
+
},
|
| 2140 |
+
{
|
| 2141 |
+
"epoch": 0.53,
|
| 2142 |
+
"learning_rate": 2.344036765693311e-05,
|
| 2143 |
+
"loss": 3.1849,
|
| 2144 |
+
"step": 178000
|
| 2145 |
+
},
|
| 2146 |
+
{
|
| 2147 |
+
"epoch": 0.53,
|
| 2148 |
+
"learning_rate": 2.336576194810427e-05,
|
| 2149 |
+
"loss": 3.2024,
|
| 2150 |
+
"step": 178500
|
| 2151 |
+
},
|
| 2152 |
+
{
|
| 2153 |
+
"epoch": 0.53,
|
| 2154 |
+
"learning_rate": 2.329115623927543e-05,
|
| 2155 |
+
"loss": 3.1923,
|
| 2156 |
+
"step": 179000
|
| 2157 |
+
},
|
| 2158 |
+
{
|
| 2159 |
+
"epoch": 0.54,
|
| 2160 |
+
"learning_rate": 2.321655053044659e-05,
|
| 2161 |
+
"loss": 3.1988,
|
| 2162 |
+
"step": 179500
|
| 2163 |
+
},
|
| 2164 |
+
{
|
| 2165 |
+
"epoch": 0.54,
|
| 2166 |
+
"learning_rate": 2.314194482161775e-05,
|
| 2167 |
+
"loss": 3.1788,
|
| 2168 |
+
"step": 180000
|
| 2169 |
+
},
|
| 2170 |
+
{
|
| 2171 |
+
"epoch": 0.54,
|
| 2172 |
+
"learning_rate": 2.306733911278891e-05,
|
| 2173 |
+
"loss": 3.1927,
|
| 2174 |
+
"step": 180500
|
| 2175 |
+
},
|
| 2176 |
+
{
|
| 2177 |
+
"epoch": 0.54,
|
| 2178 |
+
"learning_rate": 2.2992733403960073e-05,
|
| 2179 |
+
"loss": 3.1854,
|
| 2180 |
+
"step": 181000
|
| 2181 |
+
},
|
| 2182 |
+
{
|
| 2183 |
+
"epoch": 0.54,
|
| 2184 |
+
"learning_rate": 2.2918127695131233e-05,
|
| 2185 |
+
"loss": 3.2029,
|
| 2186 |
+
"step": 181500
|
| 2187 |
+
},
|
| 2188 |
+
{
|
| 2189 |
+
"epoch": 0.54,
|
| 2190 |
+
"learning_rate": 2.2843521986302392e-05,
|
| 2191 |
+
"loss": 3.1958,
|
| 2192 |
+
"step": 182000
|
| 2193 |
+
},
|
| 2194 |
+
{
|
| 2195 |
+
"epoch": 0.54,
|
| 2196 |
+
"learning_rate": 2.2768916277473555e-05,
|
| 2197 |
+
"loss": 3.1791,
|
| 2198 |
+
"step": 182500
|
| 2199 |
+
},
|
| 2200 |
+
{
|
| 2201 |
+
"epoch": 0.55,
|
| 2202 |
+
"learning_rate": 2.2694310568644715e-05,
|
| 2203 |
+
"loss": 3.1791,
|
| 2204 |
+
"step": 183000
|
| 2205 |
+
},
|
| 2206 |
+
{
|
| 2207 |
+
"epoch": 0.55,
|
| 2208 |
+
"learning_rate": 2.2619704859815874e-05,
|
| 2209 |
+
"loss": 3.1921,
|
| 2210 |
+
"step": 183500
|
| 2211 |
+
},
|
| 2212 |
+
{
|
| 2213 |
+
"epoch": 0.55,
|
| 2214 |
+
"learning_rate": 2.2545099150987034e-05,
|
| 2215 |
+
"loss": 3.193,
|
| 2216 |
+
"step": 184000
|
| 2217 |
+
},
|
| 2218 |
+
{
|
| 2219 |
+
"epoch": 0.55,
|
| 2220 |
+
"learning_rate": 2.2470493442158194e-05,
|
| 2221 |
+
"loss": 3.2009,
|
| 2222 |
+
"step": 184500
|
| 2223 |
+
},
|
| 2224 |
+
{
|
| 2225 |
+
"epoch": 0.55,
|
| 2226 |
+
"learning_rate": 2.2395887733329353e-05,
|
| 2227 |
+
"loss": 3.1873,
|
| 2228 |
+
"step": 185000
|
| 2229 |
+
},
|
| 2230 |
+
{
|
| 2231 |
+
"epoch": 0.55,
|
| 2232 |
+
"learning_rate": 2.2321282024500516e-05,
|
| 2233 |
+
"loss": 3.1703,
|
| 2234 |
+
"step": 185500
|
| 2235 |
+
},
|
| 2236 |
+
{
|
| 2237 |
+
"epoch": 0.56,
|
| 2238 |
+
"learning_rate": 2.2246676315671676e-05,
|
| 2239 |
+
"loss": 3.1822,
|
| 2240 |
+
"step": 186000
|
| 2241 |
+
},
|
| 2242 |
+
{
|
| 2243 |
+
"epoch": 0.56,
|
| 2244 |
+
"learning_rate": 2.217207060684284e-05,
|
| 2245 |
+
"loss": 3.1651,
|
| 2246 |
+
"step": 186500
|
| 2247 |
+
},
|
| 2248 |
+
{
|
| 2249 |
+
"epoch": 0.56,
|
| 2250 |
+
"learning_rate": 2.2097464898013998e-05,
|
| 2251 |
+
"loss": 3.161,
|
| 2252 |
+
"step": 187000
|
| 2253 |
+
},
|
| 2254 |
+
{
|
| 2255 |
+
"epoch": 0.56,
|
| 2256 |
+
"learning_rate": 2.2022859189185158e-05,
|
| 2257 |
+
"loss": 3.1794,
|
| 2258 |
+
"step": 187500
|
| 2259 |
+
},
|
| 2260 |
+
{
|
| 2261 |
+
"epoch": 0.56,
|
| 2262 |
+
"learning_rate": 2.1948253480356317e-05,
|
| 2263 |
+
"loss": 3.166,
|
| 2264 |
+
"step": 188000
|
| 2265 |
+
},
|
| 2266 |
+
{
|
| 2267 |
+
"epoch": 0.56,
|
| 2268 |
+
"learning_rate": 2.1873647771527477e-05,
|
| 2269 |
+
"loss": 3.1738,
|
| 2270 |
+
"step": 188500
|
| 2271 |
+
},
|
| 2272 |
+
{
|
| 2273 |
+
"epoch": 0.56,
|
| 2274 |
+
"learning_rate": 2.1799042062698636e-05,
|
| 2275 |
+
"loss": 3.1563,
|
| 2276 |
+
"step": 189000
|
| 2277 |
+
},
|
| 2278 |
+
{
|
| 2279 |
+
"epoch": 0.57,
|
| 2280 |
+
"learning_rate": 2.17244363538698e-05,
|
| 2281 |
+
"loss": 3.1549,
|
| 2282 |
+
"step": 189500
|
| 2283 |
+
},
|
| 2284 |
+
{
|
| 2285 |
+
"epoch": 0.57,
|
| 2286 |
+
"learning_rate": 2.164983064504096e-05,
|
| 2287 |
+
"loss": 3.152,
|
| 2288 |
+
"step": 190000
|
| 2289 |
+
},
|
| 2290 |
+
{
|
| 2291 |
+
"epoch": 0.57,
|
| 2292 |
+
"learning_rate": 2.1575224936212122e-05,
|
| 2293 |
+
"loss": 3.1475,
|
| 2294 |
+
"step": 190500
|
| 2295 |
+
},
|
| 2296 |
+
{
|
| 2297 |
+
"epoch": 0.57,
|
| 2298 |
+
"learning_rate": 2.150061922738328e-05,
|
| 2299 |
+
"loss": 3.1561,
|
| 2300 |
+
"step": 191000
|
| 2301 |
+
},
|
| 2302 |
+
{
|
| 2303 |
+
"epoch": 0.57,
|
| 2304 |
+
"learning_rate": 2.142601351855444e-05,
|
| 2305 |
+
"loss": 3.1452,
|
| 2306 |
+
"step": 191500
|
| 2307 |
+
},
|
| 2308 |
+
{
|
| 2309 |
+
"epoch": 0.57,
|
| 2310 |
+
"learning_rate": 2.13514078097256e-05,
|
| 2311 |
+
"loss": 3.1559,
|
| 2312 |
+
"step": 192000
|
| 2313 |
+
},
|
| 2314 |
+
{
|
| 2315 |
+
"epoch": 0.57,
|
| 2316 |
+
"learning_rate": 2.127680210089676e-05,
|
| 2317 |
+
"loss": 3.1523,
|
| 2318 |
+
"step": 192500
|
| 2319 |
+
},
|
| 2320 |
+
{
|
| 2321 |
+
"epoch": 0.58,
|
| 2322 |
+
"learning_rate": 2.1202196392067923e-05,
|
| 2323 |
+
"loss": 3.1547,
|
| 2324 |
+
"step": 193000
|
| 2325 |
+
},
|
| 2326 |
+
{
|
| 2327 |
+
"epoch": 0.58,
|
| 2328 |
+
"learning_rate": 2.1127590683239083e-05,
|
| 2329 |
+
"loss": 3.1415,
|
| 2330 |
+
"step": 193500
|
| 2331 |
+
},
|
| 2332 |
+
{
|
| 2333 |
+
"epoch": 0.58,
|
| 2334 |
+
"learning_rate": 2.1052984974410242e-05,
|
| 2335 |
+
"loss": 3.1577,
|
| 2336 |
+
"step": 194000
|
| 2337 |
+
},
|
| 2338 |
+
{
|
| 2339 |
+
"epoch": 0.58,
|
| 2340 |
+
"learning_rate": 2.0978379265581402e-05,
|
| 2341 |
+
"loss": 3.1476,
|
| 2342 |
+
"step": 194500
|
| 2343 |
+
},
|
| 2344 |
+
{
|
| 2345 |
+
"epoch": 0.58,
|
| 2346 |
+
"learning_rate": 2.0903773556752565e-05,
|
| 2347 |
+
"loss": 3.1473,
|
| 2348 |
+
"step": 195000
|
| 2349 |
+
},
|
| 2350 |
+
{
|
| 2351 |
+
"epoch": 0.58,
|
| 2352 |
+
"learning_rate": 2.0829167847923725e-05,
|
| 2353 |
+
"loss": 3.1553,
|
| 2354 |
+
"step": 195500
|
| 2355 |
+
},
|
| 2356 |
+
{
|
| 2357 |
+
"epoch": 0.58,
|
| 2358 |
+
"learning_rate": 2.0754562139094884e-05,
|
| 2359 |
+
"loss": 3.1435,
|
| 2360 |
+
"step": 196000
|
| 2361 |
+
},
|
| 2362 |
+
{
|
| 2363 |
+
"epoch": 0.59,
|
| 2364 |
+
"learning_rate": 2.0679956430266047e-05,
|
| 2365 |
+
"loss": 3.1384,
|
| 2366 |
+
"step": 196500
|
| 2367 |
+
},
|
| 2368 |
+
{
|
| 2369 |
+
"epoch": 0.59,
|
| 2370 |
+
"learning_rate": 2.0605350721437207e-05,
|
| 2371 |
+
"loss": 3.1253,
|
| 2372 |
+
"step": 197000
|
| 2373 |
+
},
|
| 2374 |
+
{
|
| 2375 |
+
"epoch": 0.59,
|
| 2376 |
+
"learning_rate": 2.0530745012608366e-05,
|
| 2377 |
+
"loss": 3.1279,
|
| 2378 |
+
"step": 197500
|
| 2379 |
+
},
|
| 2380 |
+
{
|
| 2381 |
+
"epoch": 0.59,
|
| 2382 |
+
"learning_rate": 2.0456139303779526e-05,
|
| 2383 |
+
"loss": 3.1418,
|
| 2384 |
+
"step": 198000
|
| 2385 |
+
},
|
| 2386 |
+
{
|
| 2387 |
+
"epoch": 0.59,
|
| 2388 |
+
"learning_rate": 2.0381533594950685e-05,
|
| 2389 |
+
"loss": 3.1448,
|
| 2390 |
+
"step": 198500
|
| 2391 |
+
},
|
| 2392 |
+
{
|
| 2393 |
+
"epoch": 0.59,
|
| 2394 |
+
"learning_rate": 2.0306927886121845e-05,
|
| 2395 |
+
"loss": 3.1398,
|
| 2396 |
+
"step": 199000
|
| 2397 |
+
},
|
| 2398 |
+
{
|
| 2399 |
+
"epoch": 0.6,
|
| 2400 |
+
"learning_rate": 2.0232322177293004e-05,
|
| 2401 |
+
"loss": 3.1293,
|
| 2402 |
+
"step": 199500
|
| 2403 |
+
},
|
| 2404 |
+
{
|
| 2405 |
+
"epoch": 0.6,
|
| 2406 |
+
"learning_rate": 2.0157716468464167e-05,
|
| 2407 |
+
"loss": 3.1252,
|
| 2408 |
+
"step": 200000
|
| 2409 |
+
},
|
| 2410 |
+
{
|
| 2411 |
+
"epoch": 0.6,
|
| 2412 |
+
"learning_rate": 2.008311075963533e-05,
|
| 2413 |
+
"loss": 3.1121,
|
| 2414 |
+
"step": 200500
|
| 2415 |
+
},
|
| 2416 |
+
{
|
| 2417 |
+
"epoch": 0.6,
|
| 2418 |
+
"learning_rate": 2.000850505080649e-05,
|
| 2419 |
+
"loss": 3.1314,
|
| 2420 |
+
"step": 201000
|
| 2421 |
+
},
|
| 2422 |
+
{
|
| 2423 |
+
"epoch": 0.6,
|
| 2424 |
+
"learning_rate": 1.993389934197765e-05,
|
| 2425 |
+
"loss": 3.1345,
|
| 2426 |
+
"step": 201500
|
| 2427 |
+
},
|
| 2428 |
+
{
|
| 2429 |
+
"epoch": 0.6,
|
| 2430 |
+
"learning_rate": 1.985929363314881e-05,
|
| 2431 |
+
"loss": 3.1291,
|
| 2432 |
+
"step": 202000
|
| 2433 |
+
},
|
| 2434 |
+
{
|
| 2435 |
+
"epoch": 0.6,
|
| 2436 |
+
"learning_rate": 1.978468792431997e-05,
|
| 2437 |
+
"loss": 3.1316,
|
| 2438 |
+
"step": 202500
|
| 2439 |
+
},
|
| 2440 |
+
{
|
| 2441 |
+
"epoch": 0.61,
|
| 2442 |
+
"learning_rate": 1.9710082215491128e-05,
|
| 2443 |
+
"loss": 3.1365,
|
| 2444 |
+
"step": 203000
|
| 2445 |
+
},
|
| 2446 |
+
{
|
| 2447 |
+
"epoch": 0.61,
|
| 2448 |
+
"learning_rate": 1.963547650666229e-05,
|
| 2449 |
+
"loss": 3.1363,
|
| 2450 |
+
"step": 203500
|
| 2451 |
+
},
|
| 2452 |
+
{
|
| 2453 |
+
"epoch": 0.61,
|
| 2454 |
+
"learning_rate": 1.956087079783345e-05,
|
| 2455 |
+
"loss": 3.1304,
|
| 2456 |
+
"step": 204000
|
| 2457 |
+
},
|
| 2458 |
+
{
|
| 2459 |
+
"epoch": 0.61,
|
| 2460 |
+
"learning_rate": 1.9486265089004614e-05,
|
| 2461 |
+
"loss": 3.1117,
|
| 2462 |
+
"step": 204500
|
| 2463 |
+
},
|
| 2464 |
+
{
|
| 2465 |
+
"epoch": 0.61,
|
| 2466 |
+
"learning_rate": 1.9411659380175773e-05,
|
| 2467 |
+
"loss": 3.116,
|
| 2468 |
+
"step": 205000
|
| 2469 |
+
},
|
| 2470 |
+
{
|
| 2471 |
+
"epoch": 0.61,
|
| 2472 |
+
"learning_rate": 1.9337053671346933e-05,
|
| 2473 |
+
"loss": 3.1004,
|
| 2474 |
+
"step": 205500
|
| 2475 |
+
},
|
| 2476 |
+
{
|
| 2477 |
+
"epoch": 0.61,
|
| 2478 |
+
"learning_rate": 1.9262447962518092e-05,
|
| 2479 |
+
"loss": 3.1145,
|
| 2480 |
+
"step": 206000
|
| 2481 |
+
},
|
| 2482 |
+
{
|
| 2483 |
+
"epoch": 0.62,
|
| 2484 |
+
"learning_rate": 1.9187842253689252e-05,
|
| 2485 |
+
"loss": 3.1189,
|
| 2486 |
+
"step": 206500
|
| 2487 |
+
},
|
| 2488 |
+
{
|
| 2489 |
+
"epoch": 0.62,
|
| 2490 |
+
"learning_rate": 1.9113236544860415e-05,
|
| 2491 |
+
"loss": 3.1107,
|
| 2492 |
+
"step": 207000
|
| 2493 |
+
},
|
| 2494 |
+
{
|
| 2495 |
+
"epoch": 0.62,
|
| 2496 |
+
"learning_rate": 1.9038630836031575e-05,
|
| 2497 |
+
"loss": 3.1045,
|
| 2498 |
+
"step": 207500
|
| 2499 |
+
},
|
| 2500 |
+
{
|
| 2501 |
+
"epoch": 0.62,
|
| 2502 |
+
"learning_rate": 1.8964025127202734e-05,
|
| 2503 |
+
"loss": 3.1394,
|
| 2504 |
+
"step": 208000
|
| 2505 |
+
},
|
| 2506 |
+
{
|
| 2507 |
+
"epoch": 0.62,
|
| 2508 |
+
"learning_rate": 1.8889419418373894e-05,
|
| 2509 |
+
"loss": 3.1042,
|
| 2510 |
+
"step": 208500
|
| 2511 |
+
},
|
| 2512 |
+
{
|
| 2513 |
+
"epoch": 0.62,
|
| 2514 |
+
"learning_rate": 1.8814813709545057e-05,
|
| 2515 |
+
"loss": 3.1121,
|
| 2516 |
+
"step": 209000
|
| 2517 |
+
},
|
| 2518 |
+
{
|
| 2519 |
+
"epoch": 0.63,
|
| 2520 |
+
"learning_rate": 1.8740208000716216e-05,
|
| 2521 |
+
"loss": 3.1009,
|
| 2522 |
+
"step": 209500
|
| 2523 |
+
},
|
| 2524 |
+
{
|
| 2525 |
+
"epoch": 0.63,
|
| 2526 |
+
"learning_rate": 1.8665602291887376e-05,
|
| 2527 |
+
"loss": 3.1056,
|
| 2528 |
+
"step": 210000
|
| 2529 |
+
},
|
| 2530 |
+
{
|
| 2531 |
+
"epoch": 0.63,
|
| 2532 |
+
"learning_rate": 1.8590996583058535e-05,
|
| 2533 |
+
"loss": 3.1007,
|
| 2534 |
+
"step": 210500
|
| 2535 |
+
},
|
| 2536 |
+
{
|
| 2537 |
+
"epoch": 0.63,
|
| 2538 |
+
"learning_rate": 1.85163908742297e-05,
|
| 2539 |
+
"loss": 3.0885,
|
| 2540 |
+
"step": 211000
|
| 2541 |
+
},
|
| 2542 |
+
{
|
| 2543 |
+
"epoch": 0.63,
|
| 2544 |
+
"learning_rate": 1.8441785165400858e-05,
|
| 2545 |
+
"loss": 3.0931,
|
| 2546 |
+
"step": 211500
|
| 2547 |
+
},
|
| 2548 |
+
{
|
| 2549 |
+
"epoch": 0.63,
|
| 2550 |
+
"learning_rate": 1.8367179456572018e-05,
|
| 2551 |
+
"loss": 3.0962,
|
| 2552 |
+
"step": 212000
|
| 2553 |
+
},
|
| 2554 |
+
{
|
| 2555 |
+
"epoch": 0.63,
|
| 2556 |
+
"learning_rate": 1.8292573747743177e-05,
|
| 2557 |
+
"loss": 3.0888,
|
| 2558 |
+
"step": 212500
|
| 2559 |
+
},
|
| 2560 |
+
{
|
| 2561 |
+
"epoch": 0.64,
|
| 2562 |
+
"learning_rate": 1.8217968038914337e-05,
|
| 2563 |
+
"loss": 3.0904,
|
| 2564 |
+
"step": 213000
|
| 2565 |
+
},
|
| 2566 |
+
{
|
| 2567 |
+
"epoch": 0.64,
|
| 2568 |
+
"learning_rate": 1.8143362330085496e-05,
|
| 2569 |
+
"loss": 3.1059,
|
| 2570 |
+
"step": 213500
|
| 2571 |
+
},
|
| 2572 |
+
{
|
| 2573 |
+
"epoch": 0.64,
|
| 2574 |
+
"learning_rate": 1.806875662125666e-05,
|
| 2575 |
+
"loss": 3.1071,
|
| 2576 |
+
"step": 214000
|
| 2577 |
+
},
|
| 2578 |
+
{
|
| 2579 |
+
"epoch": 0.64,
|
| 2580 |
+
"learning_rate": 1.7994150912427822e-05,
|
| 2581 |
+
"loss": 3.0838,
|
| 2582 |
+
"step": 214500
|
| 2583 |
+
},
|
| 2584 |
+
{
|
| 2585 |
+
"epoch": 0.64,
|
| 2586 |
+
"learning_rate": 1.7919545203598982e-05,
|
| 2587 |
+
"loss": 3.1019,
|
| 2588 |
+
"step": 215000
|
| 2589 |
+
},
|
| 2590 |
+
{
|
| 2591 |
+
"epoch": 0.64,
|
| 2592 |
+
"learning_rate": 1.784493949477014e-05,
|
| 2593 |
+
"loss": 3.0909,
|
| 2594 |
+
"step": 215500
|
| 2595 |
+
},
|
| 2596 |
+
{
|
| 2597 |
+
"epoch": 0.64,
|
| 2598 |
+
"learning_rate": 1.77703337859413e-05,
|
| 2599 |
+
"loss": 3.0948,
|
| 2600 |
+
"step": 216000
|
| 2601 |
+
},
|
| 2602 |
+
{
|
| 2603 |
+
"epoch": 0.65,
|
| 2604 |
+
"learning_rate": 1.769572807711246e-05,
|
| 2605 |
+
"loss": 3.0653,
|
| 2606 |
+
"step": 216500
|
| 2607 |
+
},
|
| 2608 |
+
{
|
| 2609 |
+
"epoch": 0.65,
|
| 2610 |
+
"learning_rate": 1.762112236828362e-05,
|
| 2611 |
+
"loss": 3.1038,
|
| 2612 |
+
"step": 217000
|
| 2613 |
+
},
|
| 2614 |
+
{
|
| 2615 |
+
"epoch": 0.65,
|
| 2616 |
+
"learning_rate": 1.7546516659454783e-05,
|
| 2617 |
+
"loss": 3.0913,
|
| 2618 |
+
"step": 217500
|
| 2619 |
+
},
|
| 2620 |
+
{
|
| 2621 |
+
"epoch": 0.65,
|
| 2622 |
+
"learning_rate": 1.7471910950625943e-05,
|
| 2623 |
+
"loss": 3.0811,
|
| 2624 |
+
"step": 218000
|
| 2625 |
+
},
|
| 2626 |
+
{
|
| 2627 |
+
"epoch": 0.65,
|
| 2628 |
+
"learning_rate": 1.7397305241797106e-05,
|
| 2629 |
+
"loss": 3.0839,
|
| 2630 |
+
"step": 218500
|
| 2631 |
+
},
|
| 2632 |
+
{
|
| 2633 |
+
"epoch": 0.65,
|
| 2634 |
+
"learning_rate": 1.7322699532968265e-05,
|
| 2635 |
+
"loss": 3.0852,
|
| 2636 |
+
"step": 219000
|
| 2637 |
+
},
|
| 2638 |
+
{
|
| 2639 |
+
"epoch": 0.66,
|
| 2640 |
+
"learning_rate": 1.7248093824139425e-05,
|
| 2641 |
+
"loss": 3.0573,
|
| 2642 |
+
"step": 219500
|
| 2643 |
+
},
|
| 2644 |
+
{
|
| 2645 |
+
"epoch": 0.66,
|
| 2646 |
+
"learning_rate": 1.7173488115310584e-05,
|
| 2647 |
+
"loss": 3.0985,
|
| 2648 |
+
"step": 220000
|
| 2649 |
+
},
|
| 2650 |
+
{
|
| 2651 |
+
"epoch": 0.66,
|
| 2652 |
+
"learning_rate": 1.7098882406481744e-05,
|
| 2653 |
+
"loss": 3.0628,
|
| 2654 |
+
"step": 220500
|
| 2655 |
+
},
|
| 2656 |
+
{
|
| 2657 |
+
"epoch": 0.66,
|
| 2658 |
+
"learning_rate": 1.7024276697652903e-05,
|
| 2659 |
+
"loss": 3.076,
|
| 2660 |
+
"step": 221000
|
| 2661 |
+
},
|
| 2662 |
+
{
|
| 2663 |
+
"epoch": 0.66,
|
| 2664 |
+
"learning_rate": 1.6949670988824066e-05,
|
| 2665 |
+
"loss": 3.0765,
|
| 2666 |
+
"step": 221500
|
| 2667 |
+
},
|
| 2668 |
+
{
|
| 2669 |
+
"epoch": 0.66,
|
| 2670 |
+
"learning_rate": 1.6875065279995226e-05,
|
| 2671 |
+
"loss": 3.0835,
|
| 2672 |
+
"step": 222000
|
| 2673 |
+
},
|
| 2674 |
+
{
|
| 2675 |
+
"epoch": 0.66,
|
| 2676 |
+
"learning_rate": 1.6800459571166386e-05,
|
| 2677 |
+
"loss": 3.0633,
|
| 2678 |
+
"step": 222500
|
| 2679 |
+
},
|
| 2680 |
+
{
|
| 2681 |
+
"epoch": 0.67,
|
| 2682 |
+
"learning_rate": 1.672585386233755e-05,
|
| 2683 |
+
"loss": 3.0676,
|
| 2684 |
+
"step": 223000
|
| 2685 |
+
},
|
| 2686 |
+
{
|
| 2687 |
+
"epoch": 0.67,
|
| 2688 |
+
"learning_rate": 1.6651248153508708e-05,
|
| 2689 |
+
"loss": 3.0719,
|
| 2690 |
+
"step": 223500
|
| 2691 |
+
},
|
| 2692 |
+
{
|
| 2693 |
+
"epoch": 0.67,
|
| 2694 |
+
"learning_rate": 1.6576642444679868e-05,
|
| 2695 |
+
"loss": 3.0795,
|
| 2696 |
+
"step": 224000
|
| 2697 |
+
},
|
| 2698 |
+
{
|
| 2699 |
+
"epoch": 0.67,
|
| 2700 |
+
"learning_rate": 1.6502036735851027e-05,
|
| 2701 |
+
"loss": 3.0631,
|
| 2702 |
+
"step": 224500
|
| 2703 |
+
},
|
| 2704 |
+
{
|
| 2705 |
+
"epoch": 0.67,
|
| 2706 |
+
"learning_rate": 1.642743102702219e-05,
|
| 2707 |
+
"loss": 3.0544,
|
| 2708 |
+
"step": 225000
|
| 2709 |
+
},
|
| 2710 |
+
{
|
| 2711 |
+
"epoch": 0.67,
|
| 2712 |
+
"learning_rate": 1.635282531819335e-05,
|
| 2713 |
+
"loss": 3.0803,
|
| 2714 |
+
"step": 225500
|
| 2715 |
+
},
|
| 2716 |
+
{
|
| 2717 |
+
"epoch": 0.67,
|
| 2718 |
+
"learning_rate": 1.627821960936451e-05,
|
| 2719 |
+
"loss": 3.0572,
|
| 2720 |
+
"step": 226000
|
| 2721 |
+
},
|
| 2722 |
+
{
|
| 2723 |
+
"epoch": 0.68,
|
| 2724 |
+
"learning_rate": 1.620361390053567e-05,
|
| 2725 |
+
"loss": 3.0625,
|
| 2726 |
+
"step": 226500
|
| 2727 |
+
},
|
| 2728 |
+
{
|
| 2729 |
+
"epoch": 0.68,
|
| 2730 |
+
"learning_rate": 1.612900819170683e-05,
|
| 2731 |
+
"loss": 3.076,
|
| 2732 |
+
"step": 227000
|
| 2733 |
+
},
|
| 2734 |
+
{
|
| 2735 |
+
"epoch": 0.68,
|
| 2736 |
+
"learning_rate": 1.6054402482877988e-05,
|
| 2737 |
+
"loss": 3.059,
|
| 2738 |
+
"step": 227500
|
| 2739 |
+
},
|
| 2740 |
+
{
|
| 2741 |
+
"epoch": 0.68,
|
| 2742 |
+
"learning_rate": 1.597979677404915e-05,
|
| 2743 |
+
"loss": 3.0651,
|
| 2744 |
+
"step": 228000
|
| 2745 |
+
},
|
| 2746 |
+
{
|
| 2747 |
+
"epoch": 0.68,
|
| 2748 |
+
"learning_rate": 1.5905191065220314e-05,
|
| 2749 |
+
"loss": 3.0331,
|
| 2750 |
+
"step": 228500
|
| 2751 |
+
},
|
| 2752 |
+
{
|
| 2753 |
+
"epoch": 0.68,
|
| 2754 |
+
"learning_rate": 1.5830585356391474e-05,
|
| 2755 |
+
"loss": 3.073,
|
| 2756 |
+
"step": 229000
|
| 2757 |
+
},
|
| 2758 |
+
{
|
| 2759 |
+
"epoch": 0.68,
|
| 2760 |
+
"learning_rate": 1.5755979647562633e-05,
|
| 2761 |
+
"loss": 3.0653,
|
| 2762 |
+
"step": 229500
|
| 2763 |
+
},
|
| 2764 |
+
{
|
| 2765 |
+
"epoch": 0.69,
|
| 2766 |
+
"learning_rate": 1.5681373938733793e-05,
|
| 2767 |
+
"loss": 3.0541,
|
| 2768 |
+
"step": 230000
|
| 2769 |
+
},
|
| 2770 |
+
{
|
| 2771 |
+
"epoch": 0.69,
|
| 2772 |
+
"learning_rate": 1.5606768229904952e-05,
|
| 2773 |
+
"loss": 3.0459,
|
| 2774 |
+
"step": 230500
|
| 2775 |
+
},
|
| 2776 |
+
{
|
| 2777 |
+
"epoch": 0.69,
|
| 2778 |
+
"learning_rate": 1.5532162521076112e-05,
|
| 2779 |
+
"loss": 3.0559,
|
| 2780 |
+
"step": 231000
|
| 2781 |
+
},
|
| 2782 |
+
{
|
| 2783 |
+
"epoch": 0.69,
|
| 2784 |
+
"learning_rate": 1.545755681224727e-05,
|
| 2785 |
+
"loss": 3.0597,
|
| 2786 |
+
"step": 231500
|
| 2787 |
+
},
|
| 2788 |
+
{
|
| 2789 |
+
"epoch": 0.69,
|
| 2790 |
+
"learning_rate": 1.5382951103418434e-05,
|
| 2791 |
+
"loss": 3.0524,
|
| 2792 |
+
"step": 232000
|
| 2793 |
+
},
|
| 2794 |
+
{
|
| 2795 |
+
"epoch": 0.69,
|
| 2796 |
+
"learning_rate": 1.5308345394589597e-05,
|
| 2797 |
+
"loss": 3.0592,
|
| 2798 |
+
"step": 232500
|
| 2799 |
+
},
|
| 2800 |
+
{
|
| 2801 |
+
"epoch": 0.7,
|
| 2802 |
+
"learning_rate": 1.5233739685760757e-05,
|
| 2803 |
+
"loss": 3.0682,
|
| 2804 |
+
"step": 233000
|
| 2805 |
+
},
|
| 2806 |
+
{
|
| 2807 |
+
"epoch": 0.7,
|
| 2808 |
+
"learning_rate": 1.5159133976931917e-05,
|
| 2809 |
+
"loss": 3.0332,
|
| 2810 |
+
"step": 233500
|
| 2811 |
+
},
|
| 2812 |
+
{
|
| 2813 |
+
"epoch": 0.7,
|
| 2814 |
+
"learning_rate": 1.5084528268103076e-05,
|
| 2815 |
+
"loss": 3.0509,
|
| 2816 |
+
"step": 234000
|
| 2817 |
+
},
|
| 2818 |
+
{
|
| 2819 |
+
"epoch": 0.7,
|
| 2820 |
+
"learning_rate": 1.5009922559274237e-05,
|
| 2821 |
+
"loss": 3.0395,
|
| 2822 |
+
"step": 234500
|
| 2823 |
+
},
|
| 2824 |
+
{
|
| 2825 |
+
"epoch": 0.7,
|
| 2826 |
+
"learning_rate": 1.4935316850445397e-05,
|
| 2827 |
+
"loss": 3.063,
|
| 2828 |
+
"step": 235000
|
| 2829 |
+
},
|
| 2830 |
+
{
|
| 2831 |
+
"epoch": 0.7,
|
| 2832 |
+
"learning_rate": 1.4860711141616556e-05,
|
| 2833 |
+
"loss": 3.0484,
|
| 2834 |
+
"step": 235500
|
| 2835 |
+
},
|
| 2836 |
+
{
|
| 2837 |
+
"epoch": 0.7,
|
| 2838 |
+
"learning_rate": 1.4786105432787716e-05,
|
| 2839 |
+
"loss": 3.0505,
|
| 2840 |
+
"step": 236000
|
| 2841 |
+
},
|
| 2842 |
+
{
|
| 2843 |
+
"epoch": 0.71,
|
| 2844 |
+
"learning_rate": 1.4711499723958877e-05,
|
| 2845 |
+
"loss": 3.0375,
|
| 2846 |
+
"step": 236500
|
| 2847 |
+
},
|
| 2848 |
+
{
|
| 2849 |
+
"epoch": 0.71,
|
| 2850 |
+
"learning_rate": 1.4636894015130037e-05,
|
| 2851 |
+
"loss": 3.0443,
|
| 2852 |
+
"step": 237000
|
| 2853 |
+
},
|
| 2854 |
+
{
|
| 2855 |
+
"epoch": 0.71,
|
| 2856 |
+
"learning_rate": 1.45622883063012e-05,
|
| 2857 |
+
"loss": 3.0334,
|
| 2858 |
+
"step": 237500
|
| 2859 |
+
},
|
| 2860 |
+
{
|
| 2861 |
+
"epoch": 0.71,
|
| 2862 |
+
"learning_rate": 1.448768259747236e-05,
|
| 2863 |
+
"loss": 3.0349,
|
| 2864 |
+
"step": 238000
|
| 2865 |
+
},
|
| 2866 |
+
{
|
| 2867 |
+
"epoch": 0.71,
|
| 2868 |
+
"learning_rate": 1.441307688864352e-05,
|
| 2869 |
+
"loss": 3.0277,
|
| 2870 |
+
"step": 238500
|
| 2871 |
+
},
|
| 2872 |
+
{
|
| 2873 |
+
"epoch": 0.71,
|
| 2874 |
+
"learning_rate": 1.433847117981468e-05,
|
| 2875 |
+
"loss": 3.0345,
|
| 2876 |
+
"step": 239000
|
| 2877 |
+
},
|
| 2878 |
+
{
|
| 2879 |
+
"epoch": 0.71,
|
| 2880 |
+
"learning_rate": 1.426386547098584e-05,
|
| 2881 |
+
"loss": 3.0494,
|
| 2882 |
+
"step": 239500
|
| 2883 |
+
},
|
| 2884 |
+
{
|
| 2885 |
+
"epoch": 0.72,
|
| 2886 |
+
"learning_rate": 1.4189259762157001e-05,
|
| 2887 |
+
"loss": 3.0363,
|
| 2888 |
+
"step": 240000
|
| 2889 |
+
},
|
| 2890 |
+
{
|
| 2891 |
+
"epoch": 0.72,
|
| 2892 |
+
"learning_rate": 1.411465405332816e-05,
|
| 2893 |
+
"loss": 3.0398,
|
| 2894 |
+
"step": 240500
|
| 2895 |
+
},
|
| 2896 |
+
{
|
| 2897 |
+
"epoch": 0.72,
|
| 2898 |
+
"learning_rate": 1.404004834449932e-05,
|
| 2899 |
+
"loss": 3.0372,
|
| 2900 |
+
"step": 241000
|
| 2901 |
+
},
|
| 2902 |
+
{
|
| 2903 |
+
"epoch": 0.72,
|
| 2904 |
+
"learning_rate": 1.3965442635670482e-05,
|
| 2905 |
+
"loss": 3.0286,
|
| 2906 |
+
"step": 241500
|
| 2907 |
+
},
|
| 2908 |
+
{
|
| 2909 |
+
"epoch": 0.72,
|
| 2910 |
+
"learning_rate": 1.3890836926841645e-05,
|
| 2911 |
+
"loss": 3.034,
|
| 2912 |
+
"step": 242000
|
| 2913 |
+
},
|
| 2914 |
+
{
|
| 2915 |
+
"epoch": 0.72,
|
| 2916 |
+
"learning_rate": 1.3816231218012804e-05,
|
| 2917 |
+
"loss": 3.0132,
|
| 2918 |
+
"step": 242500
|
| 2919 |
+
},
|
| 2920 |
+
{
|
| 2921 |
+
"epoch": 0.73,
|
| 2922 |
+
"learning_rate": 1.3741625509183964e-05,
|
| 2923 |
+
"loss": 3.0232,
|
| 2924 |
+
"step": 243000
|
| 2925 |
+
},
|
| 2926 |
+
{
|
| 2927 |
+
"epoch": 0.73,
|
| 2928 |
+
"learning_rate": 1.3667019800355125e-05,
|
| 2929 |
+
"loss": 3.0399,
|
| 2930 |
+
"step": 243500
|
| 2931 |
+
},
|
| 2932 |
+
{
|
| 2933 |
+
"epoch": 0.73,
|
| 2934 |
+
"learning_rate": 1.3592414091526284e-05,
|
| 2935 |
+
"loss": 3.029,
|
| 2936 |
+
"step": 244000
|
| 2937 |
+
},
|
| 2938 |
+
{
|
| 2939 |
+
"epoch": 0.73,
|
| 2940 |
+
"learning_rate": 1.3517808382697444e-05,
|
| 2941 |
+
"loss": 3.0386,
|
| 2942 |
+
"step": 244500
|
| 2943 |
+
},
|
| 2944 |
+
{
|
| 2945 |
+
"epoch": 0.73,
|
| 2946 |
+
"learning_rate": 1.3443202673868605e-05,
|
| 2947 |
+
"loss": 3.0186,
|
| 2948 |
+
"step": 245000
|
| 2949 |
+
},
|
| 2950 |
+
{
|
| 2951 |
+
"epoch": 0.73,
|
| 2952 |
+
"learning_rate": 1.3368596965039765e-05,
|
| 2953 |
+
"loss": 3.0282,
|
| 2954 |
+
"step": 245500
|
| 2955 |
+
},
|
| 2956 |
+
{
|
| 2957 |
+
"epoch": 0.73,
|
| 2958 |
+
"learning_rate": 1.3293991256210924e-05,
|
| 2959 |
+
"loss": 3.0252,
|
| 2960 |
+
"step": 246000
|
| 2961 |
+
},
|
| 2962 |
+
{
|
| 2963 |
+
"epoch": 0.74,
|
| 2964 |
+
"learning_rate": 1.3219385547382087e-05,
|
| 2965 |
+
"loss": 3.0175,
|
| 2966 |
+
"step": 246500
|
| 2967 |
+
},
|
| 2968 |
+
{
|
| 2969 |
+
"epoch": 0.74,
|
| 2970 |
+
"learning_rate": 1.3144779838553247e-05,
|
| 2971 |
+
"loss": 3.0221,
|
| 2972 |
+
"step": 247000
|
| 2973 |
+
},
|
| 2974 |
+
{
|
| 2975 |
+
"epoch": 0.74,
|
| 2976 |
+
"learning_rate": 1.3070174129724408e-05,
|
| 2977 |
+
"loss": 3.0187,
|
| 2978 |
+
"step": 247500
|
| 2979 |
+
},
|
| 2980 |
+
{
|
| 2981 |
+
"epoch": 0.74,
|
| 2982 |
+
"learning_rate": 1.2995568420895568e-05,
|
| 2983 |
+
"loss": 3.0149,
|
| 2984 |
+
"step": 248000
|
| 2985 |
+
},
|
| 2986 |
+
{
|
| 2987 |
+
"epoch": 0.74,
|
| 2988 |
+
"learning_rate": 1.2920962712066727e-05,
|
| 2989 |
+
"loss": 3.021,
|
| 2990 |
+
"step": 248500
|
| 2991 |
+
},
|
| 2992 |
+
{
|
| 2993 |
+
"epoch": 0.74,
|
| 2994 |
+
"learning_rate": 1.2846357003237889e-05,
|
| 2995 |
+
"loss": 3.0241,
|
| 2996 |
+
"step": 249000
|
| 2997 |
+
},
|
| 2998 |
+
{
|
| 2999 |
+
"epoch": 0.74,
|
| 3000 |
+
"learning_rate": 1.2771751294409048e-05,
|
| 3001 |
+
"loss": 3.005,
|
| 3002 |
+
"step": 249500
|
| 3003 |
+
},
|
| 3004 |
+
{
|
| 3005 |
+
"epoch": 0.75,
|
| 3006 |
+
"learning_rate": 1.2697145585580208e-05,
|
| 3007 |
+
"loss": 3.0068,
|
| 3008 |
+
"step": 250000
|
| 3009 |
+
},
|
| 3010 |
+
{
|
| 3011 |
+
"epoch": 0.75,
|
| 3012 |
+
"learning_rate": 1.2622539876751369e-05,
|
| 3013 |
+
"loss": 3.0047,
|
| 3014 |
+
"step": 250500
|
| 3015 |
+
},
|
| 3016 |
+
{
|
| 3017 |
+
"epoch": 0.75,
|
| 3018 |
+
"learning_rate": 1.2547934167922529e-05,
|
| 3019 |
+
"loss": 3.0196,
|
| 3020 |
+
"step": 251000
|
| 3021 |
+
},
|
| 3022 |
+
{
|
| 3023 |
+
"epoch": 0.75,
|
| 3024 |
+
"learning_rate": 1.247332845909369e-05,
|
| 3025 |
+
"loss": 3.0043,
|
| 3026 |
+
"step": 251500
|
| 3027 |
+
},
|
| 3028 |
+
{
|
| 3029 |
+
"epoch": 0.75,
|
| 3030 |
+
"learning_rate": 1.239872275026485e-05,
|
| 3031 |
+
"loss": 3.0094,
|
| 3032 |
+
"step": 252000
|
| 3033 |
+
},
|
| 3034 |
+
{
|
| 3035 |
+
"epoch": 0.75,
|
| 3036 |
+
"learning_rate": 1.2324117041436013e-05,
|
| 3037 |
+
"loss": 3.0014,
|
| 3038 |
+
"step": 252500
|
| 3039 |
+
},
|
| 3040 |
+
{
|
| 3041 |
+
"epoch": 0.76,
|
| 3042 |
+
"learning_rate": 1.2249511332607172e-05,
|
| 3043 |
+
"loss": 2.9893,
|
| 3044 |
+
"step": 253000
|
| 3045 |
+
},
|
| 3046 |
+
{
|
| 3047 |
+
"epoch": 0.76,
|
| 3048 |
+
"learning_rate": 1.2174905623778332e-05,
|
| 3049 |
+
"loss": 2.9995,
|
| 3050 |
+
"step": 253500
|
| 3051 |
+
},
|
| 3052 |
+
{
|
| 3053 |
+
"epoch": 0.76,
|
| 3054 |
+
"learning_rate": 1.2100299914949493e-05,
|
| 3055 |
+
"loss": 3.0127,
|
| 3056 |
+
"step": 254000
|
| 3057 |
+
},
|
| 3058 |
+
{
|
| 3059 |
+
"epoch": 0.76,
|
| 3060 |
+
"learning_rate": 1.2025694206120652e-05,
|
| 3061 |
+
"loss": 3.0093,
|
| 3062 |
+
"step": 254500
|
| 3063 |
+
},
|
| 3064 |
+
{
|
| 3065 |
+
"epoch": 0.76,
|
| 3066 |
+
"learning_rate": 1.1951088497291814e-05,
|
| 3067 |
+
"loss": 3.002,
|
| 3068 |
+
"step": 255000
|
| 3069 |
+
},
|
| 3070 |
+
{
|
| 3071 |
+
"epoch": 0.76,
|
| 3072 |
+
"learning_rate": 1.1876482788462973e-05,
|
| 3073 |
+
"loss": 3.0212,
|
| 3074 |
+
"step": 255500
|
| 3075 |
+
},
|
| 3076 |
+
{
|
| 3077 |
+
"epoch": 0.76,
|
| 3078 |
+
"learning_rate": 1.1801877079634135e-05,
|
| 3079 |
+
"loss": 3.0069,
|
| 3080 |
+
"step": 256000
|
| 3081 |
+
},
|
| 3082 |
+
{
|
| 3083 |
+
"epoch": 0.77,
|
| 3084 |
+
"learning_rate": 1.1727271370805294e-05,
|
| 3085 |
+
"loss": 3.0155,
|
| 3086 |
+
"step": 256500
|
| 3087 |
+
},
|
| 3088 |
+
{
|
| 3089 |
+
"epoch": 0.77,
|
| 3090 |
+
"learning_rate": 1.1652665661976454e-05,
|
| 3091 |
+
"loss": 2.9904,
|
| 3092 |
+
"step": 257000
|
| 3093 |
+
},
|
| 3094 |
+
{
|
| 3095 |
+
"epoch": 0.77,
|
| 3096 |
+
"learning_rate": 1.1578059953147615e-05,
|
| 3097 |
+
"loss": 2.9839,
|
| 3098 |
+
"step": 257500
|
| 3099 |
+
},
|
| 3100 |
+
{
|
| 3101 |
+
"epoch": 0.77,
|
| 3102 |
+
"learning_rate": 1.1503454244318776e-05,
|
| 3103 |
+
"loss": 3.0073,
|
| 3104 |
+
"step": 258000
|
| 3105 |
+
},
|
| 3106 |
+
{
|
| 3107 |
+
"epoch": 0.77,
|
| 3108 |
+
"learning_rate": 1.1428848535489936e-05,
|
| 3109 |
+
"loss": 2.9917,
|
| 3110 |
+
"step": 258500
|
| 3111 |
+
},
|
| 3112 |
+
{
|
| 3113 |
+
"epoch": 0.77,
|
| 3114 |
+
"learning_rate": 1.1354242826661095e-05,
|
| 3115 |
+
"loss": 3.0195,
|
| 3116 |
+
"step": 259000
|
| 3117 |
+
},
|
| 3118 |
+
{
|
| 3119 |
+
"epoch": 0.77,
|
| 3120 |
+
"learning_rate": 1.1279637117832258e-05,
|
| 3121 |
+
"loss": 3.0205,
|
| 3122 |
+
"step": 259500
|
| 3123 |
+
},
|
| 3124 |
+
{
|
| 3125 |
+
"epoch": 0.78,
|
| 3126 |
+
"learning_rate": 1.1205031409003418e-05,
|
| 3127 |
+
"loss": 2.9868,
|
| 3128 |
+
"step": 260000
|
| 3129 |
+
},
|
| 3130 |
+
{
|
| 3131 |
+
"epoch": 0.78,
|
| 3132 |
+
"learning_rate": 1.1130425700174578e-05,
|
| 3133 |
+
"loss": 2.9808,
|
| 3134 |
+
"step": 260500
|
| 3135 |
+
},
|
| 3136 |
+
{
|
| 3137 |
+
"epoch": 0.78,
|
| 3138 |
+
"learning_rate": 1.1055819991345739e-05,
|
| 3139 |
+
"loss": 3.0043,
|
| 3140 |
+
"step": 261000
|
| 3141 |
+
},
|
| 3142 |
+
{
|
| 3143 |
+
"epoch": 0.78,
|
| 3144 |
+
"learning_rate": 1.0981214282516898e-05,
|
| 3145 |
+
"loss": 3.0056,
|
| 3146 |
+
"step": 261500
|
| 3147 |
+
},
|
| 3148 |
+
{
|
| 3149 |
+
"epoch": 0.78,
|
| 3150 |
+
"learning_rate": 1.090660857368806e-05,
|
| 3151 |
+
"loss": 2.995,
|
| 3152 |
+
"step": 262000
|
| 3153 |
+
},
|
| 3154 |
+
{
|
| 3155 |
+
"epoch": 0.78,
|
| 3156 |
+
"learning_rate": 1.083200286485922e-05,
|
| 3157 |
+
"loss": 2.997,
|
| 3158 |
+
"step": 262500
|
| 3159 |
+
},
|
| 3160 |
+
{
|
| 3161 |
+
"epoch": 0.78,
|
| 3162 |
+
"learning_rate": 1.075739715603038e-05,
|
| 3163 |
+
"loss": 2.9913,
|
| 3164 |
+
"step": 263000
|
| 3165 |
+
},
|
| 3166 |
+
{
|
| 3167 |
+
"epoch": 0.79,
|
| 3168 |
+
"learning_rate": 1.068279144720154e-05,
|
| 3169 |
+
"loss": 2.9802,
|
| 3170 |
+
"step": 263500
|
| 3171 |
+
},
|
| 3172 |
+
{
|
| 3173 |
+
"epoch": 0.79,
|
| 3174 |
+
"learning_rate": 1.06081857383727e-05,
|
| 3175 |
+
"loss": 2.9788,
|
| 3176 |
+
"step": 264000
|
| 3177 |
+
},
|
| 3178 |
+
{
|
| 3179 |
+
"epoch": 0.79,
|
| 3180 |
+
"learning_rate": 1.0533580029543861e-05,
|
| 3181 |
+
"loss": 2.9925,
|
| 3182 |
+
"step": 264500
|
| 3183 |
+
},
|
| 3184 |
+
{
|
| 3185 |
+
"epoch": 0.79,
|
| 3186 |
+
"learning_rate": 1.0458974320715022e-05,
|
| 3187 |
+
"loss": 3.0028,
|
| 3188 |
+
"step": 265000
|
| 3189 |
+
},
|
| 3190 |
+
{
|
| 3191 |
+
"epoch": 0.79,
|
| 3192 |
+
"learning_rate": 1.0384368611886182e-05,
|
| 3193 |
+
"loss": 2.9988,
|
| 3194 |
+
"step": 265500
|
| 3195 |
+
},
|
| 3196 |
+
{
|
| 3197 |
+
"epoch": 0.79,
|
| 3198 |
+
"learning_rate": 1.0309762903057341e-05,
|
| 3199 |
+
"loss": 2.9944,
|
| 3200 |
+
"step": 266000
|
| 3201 |
+
},
|
| 3202 |
+
{
|
| 3203 |
+
"epoch": 0.8,
|
| 3204 |
+
"learning_rate": 1.0235157194228504e-05,
|
| 3205 |
+
"loss": 2.9768,
|
| 3206 |
+
"step": 266500
|
| 3207 |
+
},
|
| 3208 |
+
{
|
| 3209 |
+
"epoch": 0.8,
|
| 3210 |
+
"learning_rate": 1.0160551485399664e-05,
|
| 3211 |
+
"loss": 2.9891,
|
| 3212 |
+
"step": 267000
|
| 3213 |
+
},
|
| 3214 |
+
{
|
| 3215 |
+
"epoch": 0.8,
|
| 3216 |
+
"learning_rate": 1.0085945776570823e-05,
|
| 3217 |
+
"loss": 2.9815,
|
| 3218 |
+
"step": 267500
|
| 3219 |
+
},
|
| 3220 |
+
{
|
| 3221 |
+
"epoch": 0.8,
|
| 3222 |
+
"learning_rate": 1.0011340067741983e-05,
|
| 3223 |
+
"loss": 2.9839,
|
| 3224 |
+
"step": 268000
|
| 3225 |
+
},
|
| 3226 |
+
{
|
| 3227 |
+
"epoch": 0.8,
|
| 3228 |
+
"learning_rate": 9.936734358913144e-06,
|
| 3229 |
+
"loss": 2.9852,
|
| 3230 |
+
"step": 268500
|
| 3231 |
+
},
|
| 3232 |
+
{
|
| 3233 |
+
"epoch": 0.8,
|
| 3234 |
+
"learning_rate": 9.862128650084306e-06,
|
| 3235 |
+
"loss": 2.9759,
|
| 3236 |
+
"step": 269000
|
| 3237 |
+
},
|
| 3238 |
+
{
|
| 3239 |
+
"epoch": 0.8,
|
| 3240 |
+
"learning_rate": 9.787522941255465e-06,
|
| 3241 |
+
"loss": 2.985,
|
| 3242 |
+
"step": 269500
|
| 3243 |
+
},
|
| 3244 |
+
{
|
| 3245 |
+
"epoch": 0.81,
|
| 3246 |
+
"learning_rate": 9.712917232426626e-06,
|
| 3247 |
+
"loss": 2.9627,
|
| 3248 |
+
"step": 270000
|
| 3249 |
+
},
|
| 3250 |
+
{
|
| 3251 |
+
"epoch": 0.81,
|
| 3252 |
+
"learning_rate": 9.638311523597786e-06,
|
| 3253 |
+
"loss": 2.9925,
|
| 3254 |
+
"step": 270500
|
| 3255 |
+
},
|
| 3256 |
+
{
|
| 3257 |
+
"epoch": 0.81,
|
| 3258 |
+
"learning_rate": 9.563705814768946e-06,
|
| 3259 |
+
"loss": 2.9701,
|
| 3260 |
+
"step": 271000
|
| 3261 |
+
},
|
| 3262 |
+
{
|
| 3263 |
+
"epoch": 0.81,
|
| 3264 |
+
"learning_rate": 9.489100105940107e-06,
|
| 3265 |
+
"loss": 2.9856,
|
| 3266 |
+
"step": 271500
|
| 3267 |
+
},
|
| 3268 |
+
{
|
| 3269 |
+
"epoch": 0.81,
|
| 3270 |
+
"learning_rate": 9.414494397111268e-06,
|
| 3271 |
+
"loss": 2.9915,
|
| 3272 |
+
"step": 272000
|
| 3273 |
+
},
|
| 3274 |
+
{
|
| 3275 |
+
"epoch": 0.81,
|
| 3276 |
+
"learning_rate": 9.339888688282428e-06,
|
| 3277 |
+
"loss": 2.9746,
|
| 3278 |
+
"step": 272500
|
| 3279 |
+
},
|
| 3280 |
+
{
|
| 3281 |
+
"epoch": 0.81,
|
| 3282 |
+
"learning_rate": 9.265282979453587e-06,
|
| 3283 |
+
"loss": 2.9878,
|
| 3284 |
+
"step": 273000
|
| 3285 |
+
},
|
| 3286 |
+
{
|
| 3287 |
+
"epoch": 0.82,
|
| 3288 |
+
"learning_rate": 9.190677270624748e-06,
|
| 3289 |
+
"loss": 2.9855,
|
| 3290 |
+
"step": 273500
|
| 3291 |
+
},
|
| 3292 |
+
{
|
| 3293 |
+
"epoch": 0.82,
|
| 3294 |
+
"learning_rate": 9.11607156179591e-06,
|
| 3295 |
+
"loss": 2.96,
|
| 3296 |
+
"step": 274000
|
| 3297 |
+
},
|
| 3298 |
+
{
|
| 3299 |
+
"epoch": 0.82,
|
| 3300 |
+
"learning_rate": 9.04146585296707e-06,
|
| 3301 |
+
"loss": 2.9613,
|
| 3302 |
+
"step": 274500
|
| 3303 |
+
},
|
| 3304 |
+
{
|
| 3305 |
+
"epoch": 0.82,
|
| 3306 |
+
"learning_rate": 8.966860144138229e-06,
|
| 3307 |
+
"loss": 2.9575,
|
| 3308 |
+
"step": 275000
|
| 3309 |
+
},
|
| 3310 |
+
{
|
| 3311 |
+
"epoch": 0.82,
|
| 3312 |
+
"learning_rate": 8.89225443530939e-06,
|
| 3313 |
+
"loss": 2.9729,
|
| 3314 |
+
"step": 275500
|
| 3315 |
+
},
|
| 3316 |
+
{
|
| 3317 |
+
"epoch": 0.82,
|
| 3318 |
+
"learning_rate": 8.817648726480551e-06,
|
| 3319 |
+
"loss": 2.9773,
|
| 3320 |
+
"step": 276000
|
| 3321 |
+
},
|
| 3322 |
+
{
|
| 3323 |
+
"epoch": 0.83,
|
| 3324 |
+
"learning_rate": 8.743043017651711e-06,
|
| 3325 |
+
"loss": 2.9643,
|
| 3326 |
+
"step": 276500
|
| 3327 |
+
},
|
| 3328 |
+
{
|
| 3329 |
+
"epoch": 0.83,
|
| 3330 |
+
"learning_rate": 8.668437308822872e-06,
|
| 3331 |
+
"loss": 2.9676,
|
| 3332 |
+
"step": 277000
|
| 3333 |
+
},
|
| 3334 |
+
{
|
| 3335 |
+
"epoch": 0.83,
|
| 3336 |
+
"learning_rate": 8.593831599994032e-06,
|
| 3337 |
+
"loss": 2.953,
|
| 3338 |
+
"step": 277500
|
| 3339 |
+
},
|
| 3340 |
+
{
|
| 3341 |
+
"epoch": 0.83,
|
| 3342 |
+
"learning_rate": 8.519225891165191e-06,
|
| 3343 |
+
"loss": 2.9523,
|
| 3344 |
+
"step": 278000
|
| 3345 |
+
},
|
| 3346 |
+
{
|
| 3347 |
+
"epoch": 0.83,
|
| 3348 |
+
"learning_rate": 8.444620182336353e-06,
|
| 3349 |
+
"loss": 2.9833,
|
| 3350 |
+
"step": 278500
|
| 3351 |
+
},
|
| 3352 |
+
{
|
| 3353 |
+
"epoch": 0.83,
|
| 3354 |
+
"learning_rate": 8.370014473507514e-06,
|
| 3355 |
+
"loss": 2.971,
|
| 3356 |
+
"step": 279000
|
| 3357 |
+
},
|
| 3358 |
+
{
|
| 3359 |
+
"epoch": 0.83,
|
| 3360 |
+
"learning_rate": 8.295408764678674e-06,
|
| 3361 |
+
"loss": 2.9665,
|
| 3362 |
+
"step": 279500
|
| 3363 |
+
},
|
| 3364 |
+
{
|
| 3365 |
+
"epoch": 0.84,
|
| 3366 |
+
"learning_rate": 8.220803055849833e-06,
|
| 3367 |
+
"loss": 2.9677,
|
| 3368 |
+
"step": 280000
|
| 3369 |
+
},
|
| 3370 |
+
{
|
| 3371 |
+
"epoch": 0.84,
|
| 3372 |
+
"learning_rate": 8.146197347020994e-06,
|
| 3373 |
+
"loss": 2.9644,
|
| 3374 |
+
"step": 280500
|
| 3375 |
+
},
|
| 3376 |
+
{
|
| 3377 |
+
"epoch": 0.84,
|
| 3378 |
+
"learning_rate": 8.071591638192156e-06,
|
| 3379 |
+
"loss": 2.9662,
|
| 3380 |
+
"step": 281000
|
| 3381 |
+
},
|
| 3382 |
+
{
|
| 3383 |
+
"epoch": 0.84,
|
| 3384 |
+
"learning_rate": 7.996985929363315e-06,
|
| 3385 |
+
"loss": 2.9606,
|
| 3386 |
+
"step": 281500
|
| 3387 |
+
},
|
| 3388 |
+
{
|
| 3389 |
+
"epoch": 0.84,
|
| 3390 |
+
"learning_rate": 7.922380220534475e-06,
|
| 3391 |
+
"loss": 2.9538,
|
| 3392 |
+
"step": 282000
|
| 3393 |
+
},
|
| 3394 |
+
{
|
| 3395 |
+
"epoch": 0.84,
|
| 3396 |
+
"learning_rate": 7.847774511705636e-06,
|
| 3397 |
+
"loss": 2.956,
|
| 3398 |
+
"step": 282500
|
| 3399 |
+
},
|
| 3400 |
+
{
|
| 3401 |
+
"epoch": 0.84,
|
| 3402 |
+
"learning_rate": 7.773168802876797e-06,
|
| 3403 |
+
"loss": 2.9607,
|
| 3404 |
+
"step": 283000
|
| 3405 |
+
},
|
| 3406 |
+
{
|
| 3407 |
+
"epoch": 0.85,
|
| 3408 |
+
"learning_rate": 7.698563094047957e-06,
|
| 3409 |
+
"loss": 2.9597,
|
| 3410 |
+
"step": 283500
|
| 3411 |
+
},
|
| 3412 |
+
{
|
| 3413 |
+
"epoch": 0.85,
|
| 3414 |
+
"learning_rate": 7.623957385219117e-06,
|
| 3415 |
+
"loss": 2.959,
|
| 3416 |
+
"step": 284000
|
| 3417 |
+
},
|
| 3418 |
+
{
|
| 3419 |
+
"epoch": 0.85,
|
| 3420 |
+
"learning_rate": 7.549351676390278e-06,
|
| 3421 |
+
"loss": 2.9556,
|
| 3422 |
+
"step": 284500
|
| 3423 |
+
},
|
| 3424 |
+
{
|
| 3425 |
+
"epoch": 0.85,
|
| 3426 |
+
"learning_rate": 7.474745967561437e-06,
|
| 3427 |
+
"loss": 2.956,
|
| 3428 |
+
"step": 285000
|
| 3429 |
+
},
|
| 3430 |
+
{
|
| 3431 |
+
"epoch": 0.85,
|
| 3432 |
+
"learning_rate": 7.4001402587325994e-06,
|
| 3433 |
+
"loss": 2.9547,
|
| 3434 |
+
"step": 285500
|
| 3435 |
+
},
|
| 3436 |
+
{
|
| 3437 |
+
"epoch": 0.85,
|
| 3438 |
+
"learning_rate": 7.325534549903759e-06,
|
| 3439 |
+
"loss": 2.9661,
|
| 3440 |
+
"step": 286000
|
| 3441 |
+
},
|
| 3442 |
+
{
|
| 3443 |
+
"epoch": 0.85,
|
| 3444 |
+
"learning_rate": 7.2509288410749194e-06,
|
| 3445 |
+
"loss": 2.9524,
|
| 3446 |
+
"step": 286500
|
| 3447 |
+
},
|
| 3448 |
+
{
|
| 3449 |
+
"epoch": 0.86,
|
| 3450 |
+
"learning_rate": 7.176323132246079e-06,
|
| 3451 |
+
"loss": 2.9557,
|
| 3452 |
+
"step": 287000
|
| 3453 |
+
},
|
| 3454 |
+
{
|
| 3455 |
+
"epoch": 0.86,
|
| 3456 |
+
"learning_rate": 7.1017174234172394e-06,
|
| 3457 |
+
"loss": 2.9675,
|
| 3458 |
+
"step": 287500
|
| 3459 |
+
},
|
| 3460 |
+
{
|
| 3461 |
+
"epoch": 0.86,
|
| 3462 |
+
"learning_rate": 7.027111714588401e-06,
|
| 3463 |
+
"loss": 2.9587,
|
| 3464 |
+
"step": 288000
|
| 3465 |
+
},
|
| 3466 |
+
{
|
| 3467 |
+
"epoch": 0.86,
|
| 3468 |
+
"learning_rate": 6.952506005759561e-06,
|
| 3469 |
+
"loss": 2.9318,
|
| 3470 |
+
"step": 288500
|
| 3471 |
+
},
|
| 3472 |
+
{
|
| 3473 |
+
"epoch": 0.86,
|
| 3474 |
+
"learning_rate": 6.8779002969307216e-06,
|
| 3475 |
+
"loss": 2.9583,
|
| 3476 |
+
"step": 289000
|
| 3477 |
+
},
|
| 3478 |
+
{
|
| 3479 |
+
"epoch": 0.86,
|
| 3480 |
+
"learning_rate": 6.803294588101881e-06,
|
| 3481 |
+
"loss": 2.9556,
|
| 3482 |
+
"step": 289500
|
| 3483 |
+
},
|
| 3484 |
+
{
|
| 3485 |
+
"epoch": 0.87,
|
| 3486 |
+
"learning_rate": 6.728688879273043e-06,
|
| 3487 |
+
"loss": 2.9436,
|
| 3488 |
+
"step": 290000
|
| 3489 |
+
},
|
| 3490 |
+
{
|
| 3491 |
+
"epoch": 0.87,
|
| 3492 |
+
"learning_rate": 6.654083170444203e-06,
|
| 3493 |
+
"loss": 2.954,
|
| 3494 |
+
"step": 290500
|
| 3495 |
+
},
|
| 3496 |
+
{
|
| 3497 |
+
"epoch": 0.87,
|
| 3498 |
+
"learning_rate": 6.579477461615363e-06,
|
| 3499 |
+
"loss": 2.9691,
|
| 3500 |
+
"step": 291000
|
| 3501 |
+
},
|
| 3502 |
+
{
|
| 3503 |
+
"epoch": 0.87,
|
| 3504 |
+
"learning_rate": 6.504871752786524e-06,
|
| 3505 |
+
"loss": 2.9443,
|
| 3506 |
+
"step": 291500
|
| 3507 |
+
},
|
| 3508 |
+
{
|
| 3509 |
+
"epoch": 0.87,
|
| 3510 |
+
"learning_rate": 6.430266043957683e-06,
|
| 3511 |
+
"loss": 2.9236,
|
| 3512 |
+
"step": 292000
|
| 3513 |
+
},
|
| 3514 |
+
{
|
| 3515 |
+
"epoch": 0.87,
|
| 3516 |
+
"learning_rate": 6.3556603351288445e-06,
|
| 3517 |
+
"loss": 2.9331,
|
| 3518 |
+
"step": 292500
|
| 3519 |
+
},
|
| 3520 |
+
{
|
| 3521 |
+
"epoch": 0.87,
|
| 3522 |
+
"learning_rate": 6.281054626300005e-06,
|
| 3523 |
+
"loss": 2.9342,
|
| 3524 |
+
"step": 293000
|
| 3525 |
+
},
|
| 3526 |
+
{
|
| 3527 |
+
"epoch": 0.88,
|
| 3528 |
+
"learning_rate": 6.206448917471165e-06,
|
| 3529 |
+
"loss": 2.9598,
|
| 3530 |
+
"step": 293500
|
| 3531 |
+
},
|
| 3532 |
+
{
|
| 3533 |
+
"epoch": 0.88,
|
| 3534 |
+
"learning_rate": 6.131843208642326e-06,
|
| 3535 |
+
"loss": 2.9562,
|
| 3536 |
+
"step": 294000
|
| 3537 |
+
},
|
| 3538 |
+
{
|
| 3539 |
+
"epoch": 0.88,
|
| 3540 |
+
"learning_rate": 6.057237499813486e-06,
|
| 3541 |
+
"loss": 2.9264,
|
| 3542 |
+
"step": 294500
|
| 3543 |
+
},
|
| 3544 |
+
{
|
| 3545 |
+
"epoch": 0.88,
|
| 3546 |
+
"learning_rate": 5.982631790984647e-06,
|
| 3547 |
+
"loss": 2.9349,
|
| 3548 |
+
"step": 295000
|
| 3549 |
+
},
|
| 3550 |
+
{
|
| 3551 |
+
"epoch": 0.88,
|
| 3552 |
+
"learning_rate": 5.908026082155807e-06,
|
| 3553 |
+
"loss": 2.9384,
|
| 3554 |
+
"step": 295500
|
| 3555 |
+
},
|
| 3556 |
+
{
|
| 3557 |
+
"epoch": 0.88,
|
| 3558 |
+
"learning_rate": 5.8334203733269674e-06,
|
| 3559 |
+
"loss": 2.9622,
|
| 3560 |
+
"step": 296000
|
| 3561 |
+
},
|
| 3562 |
+
{
|
| 3563 |
+
"epoch": 0.88,
|
| 3564 |
+
"learning_rate": 5.758814664498128e-06,
|
| 3565 |
+
"loss": 2.9589,
|
| 3566 |
+
"step": 296500
|
| 3567 |
+
},
|
| 3568 |
+
{
|
| 3569 |
+
"epoch": 0.89,
|
| 3570 |
+
"learning_rate": 5.684208955669288e-06,
|
| 3571 |
+
"loss": 2.9395,
|
| 3572 |
+
"step": 297000
|
| 3573 |
+
},
|
| 3574 |
+
{
|
| 3575 |
+
"epoch": 0.89,
|
| 3576 |
+
"learning_rate": 5.609603246840448e-06,
|
| 3577 |
+
"loss": 2.9342,
|
| 3578 |
+
"step": 297500
|
| 3579 |
+
},
|
| 3580 |
+
{
|
| 3581 |
+
"epoch": 0.89,
|
| 3582 |
+
"learning_rate": 5.534997538011609e-06,
|
| 3583 |
+
"loss": 2.9262,
|
| 3584 |
+
"step": 298000
|
| 3585 |
+
},
|
| 3586 |
+
{
|
| 3587 |
+
"epoch": 0.89,
|
| 3588 |
+
"learning_rate": 5.460391829182769e-06,
|
| 3589 |
+
"loss": 2.9391,
|
| 3590 |
+
"step": 298500
|
| 3591 |
+
},
|
| 3592 |
+
{
|
| 3593 |
+
"epoch": 0.89,
|
| 3594 |
+
"learning_rate": 5.38578612035393e-06,
|
| 3595 |
+
"loss": 2.9451,
|
| 3596 |
+
"step": 299000
|
| 3597 |
+
},
|
| 3598 |
+
{
|
| 3599 |
+
"epoch": 0.89,
|
| 3600 |
+
"learning_rate": 5.31118041152509e-06,
|
| 3601 |
+
"loss": 2.9182,
|
| 3602 |
+
"step": 299500
|
| 3603 |
+
},
|
| 3604 |
+
{
|
| 3605 |
+
"epoch": 0.9,
|
| 3606 |
+
"learning_rate": 5.236574702696251e-06,
|
| 3607 |
+
"loss": 2.9519,
|
| 3608 |
+
"step": 300000
|
| 3609 |
+
},
|
| 3610 |
+
{
|
| 3611 |
+
"epoch": 0.9,
|
| 3612 |
+
"learning_rate": 5.161968993867411e-06,
|
| 3613 |
+
"loss": 2.9299,
|
| 3614 |
+
"step": 300500
|
| 3615 |
+
},
|
| 3616 |
+
{
|
| 3617 |
+
"epoch": 0.9,
|
| 3618 |
+
"learning_rate": 5.087363285038571e-06,
|
| 3619 |
+
"loss": 2.9176,
|
| 3620 |
+
"step": 301000
|
| 3621 |
+
},
|
| 3622 |
+
{
|
| 3623 |
+
"epoch": 0.9,
|
| 3624 |
+
"learning_rate": 5.012757576209732e-06,
|
| 3625 |
+
"loss": 2.9499,
|
| 3626 |
+
"step": 301500
|
| 3627 |
+
},
|
| 3628 |
+
{
|
| 3629 |
+
"epoch": 0.9,
|
| 3630 |
+
"learning_rate": 4.938151867380892e-06,
|
| 3631 |
+
"loss": 2.9258,
|
| 3632 |
+
"step": 302000
|
| 3633 |
+
},
|
| 3634 |
+
{
|
| 3635 |
+
"epoch": 0.9,
|
| 3636 |
+
"learning_rate": 4.863546158552053e-06,
|
| 3637 |
+
"loss": 2.9396,
|
| 3638 |
+
"step": 302500
|
| 3639 |
+
},
|
| 3640 |
+
{
|
| 3641 |
+
"epoch": 0.9,
|
| 3642 |
+
"learning_rate": 4.788940449723213e-06,
|
| 3643 |
+
"loss": 2.941,
|
| 3644 |
+
"step": 303000
|
| 3645 |
+
},
|
| 3646 |
+
{
|
| 3647 |
+
"epoch": 0.91,
|
| 3648 |
+
"learning_rate": 4.714334740894374e-06,
|
| 3649 |
+
"loss": 2.9308,
|
| 3650 |
+
"step": 303500
|
| 3651 |
+
},
|
| 3652 |
+
{
|
| 3653 |
+
"epoch": 0.91,
|
| 3654 |
+
"learning_rate": 4.639729032065534e-06,
|
| 3655 |
+
"loss": 2.9213,
|
| 3656 |
+
"step": 304000
|
| 3657 |
+
},
|
| 3658 |
+
{
|
| 3659 |
+
"epoch": 0.91,
|
| 3660 |
+
"learning_rate": 4.565123323236694e-06,
|
| 3661 |
+
"loss": 2.9097,
|
| 3662 |
+
"step": 304500
|
| 3663 |
+
},
|
| 3664 |
+
{
|
| 3665 |
+
"epoch": 0.91,
|
| 3666 |
+
"learning_rate": 4.490517614407855e-06,
|
| 3667 |
+
"loss": 2.9218,
|
| 3668 |
+
"step": 305000
|
| 3669 |
+
},
|
| 3670 |
+
{
|
| 3671 |
+
"epoch": 0.91,
|
| 3672 |
+
"learning_rate": 4.415911905579015e-06,
|
| 3673 |
+
"loss": 2.9276,
|
| 3674 |
+
"step": 305500
|
| 3675 |
+
},
|
| 3676 |
+
{
|
| 3677 |
+
"epoch": 0.91,
|
| 3678 |
+
"learning_rate": 4.341306196750176e-06,
|
| 3679 |
+
"loss": 2.9296,
|
| 3680 |
+
"step": 306000
|
| 3681 |
+
},
|
| 3682 |
+
{
|
| 3683 |
+
"epoch": 0.91,
|
| 3684 |
+
"learning_rate": 4.2667004879213354e-06,
|
| 3685 |
+
"loss": 2.9332,
|
| 3686 |
+
"step": 306500
|
| 3687 |
+
},
|
| 3688 |
+
{
|
| 3689 |
+
"epoch": 0.92,
|
| 3690 |
+
"learning_rate": 4.192094779092497e-06,
|
| 3691 |
+
"loss": 2.9266,
|
| 3692 |
+
"step": 307000
|
| 3693 |
+
},
|
| 3694 |
+
{
|
| 3695 |
+
"epoch": 0.92,
|
| 3696 |
+
"learning_rate": 4.117489070263657e-06,
|
| 3697 |
+
"loss": 2.9239,
|
| 3698 |
+
"step": 307500
|
| 3699 |
+
},
|
| 3700 |
+
{
|
| 3701 |
+
"epoch": 0.92,
|
| 3702 |
+
"learning_rate": 4.042883361434817e-06,
|
| 3703 |
+
"loss": 2.9279,
|
| 3704 |
+
"step": 308000
|
| 3705 |
+
},
|
| 3706 |
+
{
|
| 3707 |
+
"epoch": 0.92,
|
| 3708 |
+
"learning_rate": 3.968277652605978e-06,
|
| 3709 |
+
"loss": 2.9062,
|
| 3710 |
+
"step": 308500
|
| 3711 |
+
},
|
| 3712 |
+
{
|
| 3713 |
+
"epoch": 0.92,
|
| 3714 |
+
"learning_rate": 3.8936719437771375e-06,
|
| 3715 |
+
"loss": 2.9261,
|
| 3716 |
+
"step": 309000
|
| 3717 |
+
},
|
| 3718 |
+
{
|
| 3719 |
+
"epoch": 0.92,
|
| 3720 |
+
"learning_rate": 3.819066234948299e-06,
|
| 3721 |
+
"loss": 2.9265,
|
| 3722 |
+
"step": 309500
|
| 3723 |
+
},
|
| 3724 |
+
{
|
| 3725 |
+
"epoch": 0.93,
|
| 3726 |
+
"learning_rate": 3.744460526119459e-06,
|
| 3727 |
+
"loss": 2.9235,
|
| 3728 |
+
"step": 310000
|
| 3729 |
+
},
|
| 3730 |
+
{
|
| 3731 |
+
"epoch": 0.93,
|
| 3732 |
+
"learning_rate": 3.6698548172906197e-06,
|
| 3733 |
+
"loss": 2.9121,
|
| 3734 |
+
"step": 310500
|
| 3735 |
+
},
|
| 3736 |
+
{
|
| 3737 |
+
"epoch": 0.93,
|
| 3738 |
+
"learning_rate": 3.5952491084617797e-06,
|
| 3739 |
+
"loss": 2.9207,
|
| 3740 |
+
"step": 311000
|
| 3741 |
+
},
|
| 3742 |
+
{
|
| 3743 |
+
"epoch": 0.93,
|
| 3744 |
+
"learning_rate": 3.5206433996329397e-06,
|
| 3745 |
+
"loss": 2.9282,
|
| 3746 |
+
"step": 311500
|
| 3747 |
+
},
|
| 3748 |
+
{
|
| 3749 |
+
"epoch": 0.93,
|
| 3750 |
+
"learning_rate": 3.4460376908041005e-06,
|
| 3751 |
+
"loss": 2.9205,
|
| 3752 |
+
"step": 312000
|
| 3753 |
+
},
|
| 3754 |
+
{
|
| 3755 |
+
"epoch": 0.93,
|
| 3756 |
+
"learning_rate": 3.371431981975261e-06,
|
| 3757 |
+
"loss": 2.9228,
|
| 3758 |
+
"step": 312500
|
| 3759 |
+
},
|
| 3760 |
+
{
|
| 3761 |
+
"epoch": 0.93,
|
| 3762 |
+
"learning_rate": 3.2968262731464213e-06,
|
| 3763 |
+
"loss": 2.9271,
|
| 3764 |
+
"step": 313000
|
| 3765 |
+
},
|
| 3766 |
+
{
|
| 3767 |
+
"epoch": 0.94,
|
| 3768 |
+
"learning_rate": 3.2222205643175818e-06,
|
| 3769 |
+
"loss": 2.9108,
|
| 3770 |
+
"step": 313500
|
| 3771 |
+
},
|
| 3772 |
+
{
|
| 3773 |
+
"epoch": 0.94,
|
| 3774 |
+
"learning_rate": 3.1476148554887426e-06,
|
| 3775 |
+
"loss": 2.9248,
|
| 3776 |
+
"step": 314000
|
| 3777 |
+
},
|
| 3778 |
+
{
|
| 3779 |
+
"epoch": 0.94,
|
| 3780 |
+
"learning_rate": 3.0730091466599026e-06,
|
| 3781 |
+
"loss": 2.9111,
|
| 3782 |
+
"step": 314500
|
| 3783 |
+
},
|
| 3784 |
+
{
|
| 3785 |
+
"epoch": 0.94,
|
| 3786 |
+
"learning_rate": 2.998403437831063e-06,
|
| 3787 |
+
"loss": 2.9206,
|
| 3788 |
+
"step": 315000
|
| 3789 |
+
},
|
| 3790 |
+
{
|
| 3791 |
+
"epoch": 0.94,
|
| 3792 |
+
"learning_rate": 2.9237977290022234e-06,
|
| 3793 |
+
"loss": 2.9175,
|
| 3794 |
+
"step": 315500
|
| 3795 |
+
},
|
| 3796 |
+
{
|
| 3797 |
+
"epoch": 0.94,
|
| 3798 |
+
"learning_rate": 2.8491920201733834e-06,
|
| 3799 |
+
"loss": 2.9326,
|
| 3800 |
+
"step": 316000
|
| 3801 |
+
},
|
| 3802 |
+
{
|
| 3803 |
+
"epoch": 0.94,
|
| 3804 |
+
"learning_rate": 2.7745863113445443e-06,
|
| 3805 |
+
"loss": 2.9216,
|
| 3806 |
+
"step": 316500
|
| 3807 |
+
},
|
| 3808 |
+
{
|
| 3809 |
+
"epoch": 0.95,
|
| 3810 |
+
"learning_rate": 2.6999806025157047e-06,
|
| 3811 |
+
"loss": 2.9272,
|
| 3812 |
+
"step": 317000
|
| 3813 |
+
},
|
| 3814 |
+
{
|
| 3815 |
+
"epoch": 0.95,
|
| 3816 |
+
"learning_rate": 2.625374893686865e-06,
|
| 3817 |
+
"loss": 2.903,
|
| 3818 |
+
"step": 317500
|
| 3819 |
+
},
|
| 3820 |
+
{
|
| 3821 |
+
"epoch": 0.95,
|
| 3822 |
+
"learning_rate": 2.5507691848580256e-06,
|
| 3823 |
+
"loss": 2.8962,
|
| 3824 |
+
"step": 318000
|
| 3825 |
+
},
|
| 3826 |
+
{
|
| 3827 |
+
"epoch": 0.95,
|
| 3828 |
+
"learning_rate": 2.476163476029186e-06,
|
| 3829 |
+
"loss": 2.9097,
|
| 3830 |
+
"step": 318500
|
| 3831 |
+
},
|
| 3832 |
+
{
|
| 3833 |
+
"epoch": 0.95,
|
| 3834 |
+
"learning_rate": 2.4015577672003464e-06,
|
| 3835 |
+
"loss": 2.9369,
|
| 3836 |
+
"step": 319000
|
| 3837 |
+
},
|
| 3838 |
+
{
|
| 3839 |
+
"epoch": 0.95,
|
| 3840 |
+
"learning_rate": 2.3269520583715064e-06,
|
| 3841 |
+
"loss": 2.9132,
|
| 3842 |
+
"step": 319500
|
| 3843 |
+
},
|
| 3844 |
+
{
|
| 3845 |
+
"epoch": 0.95,
|
| 3846 |
+
"learning_rate": 2.252346349542667e-06,
|
| 3847 |
+
"loss": 2.9185,
|
| 3848 |
+
"step": 320000
|
| 3849 |
+
},
|
| 3850 |
+
{
|
| 3851 |
+
"epoch": 0.96,
|
| 3852 |
+
"learning_rate": 2.1777406407138277e-06,
|
| 3853 |
+
"loss": 2.9108,
|
| 3854 |
+
"step": 320500
|
| 3855 |
+
},
|
| 3856 |
+
{
|
| 3857 |
+
"epoch": 0.96,
|
| 3858 |
+
"learning_rate": 2.103134931884988e-06,
|
| 3859 |
+
"loss": 2.902,
|
| 3860 |
+
"step": 321000
|
| 3861 |
+
},
|
| 3862 |
+
{
|
| 3863 |
+
"epoch": 0.96,
|
| 3864 |
+
"learning_rate": 2.0285292230561485e-06,
|
| 3865 |
+
"loss": 2.8994,
|
| 3866 |
+
"step": 321500
|
| 3867 |
+
},
|
| 3868 |
+
{
|
| 3869 |
+
"epoch": 0.96,
|
| 3870 |
+
"learning_rate": 1.953923514227309e-06,
|
| 3871 |
+
"loss": 2.9028,
|
| 3872 |
+
"step": 322000
|
| 3873 |
+
},
|
| 3874 |
+
{
|
| 3875 |
+
"epoch": 0.96,
|
| 3876 |
+
"learning_rate": 1.8793178053984693e-06,
|
| 3877 |
+
"loss": 2.9165,
|
| 3878 |
+
"step": 322500
|
| 3879 |
+
},
|
| 3880 |
+
{
|
| 3881 |
+
"epoch": 0.96,
|
| 3882 |
+
"learning_rate": 1.8047120965696295e-06,
|
| 3883 |
+
"loss": 2.9271,
|
| 3884 |
+
"step": 323000
|
| 3885 |
+
},
|
| 3886 |
+
{
|
| 3887 |
+
"epoch": 0.97,
|
| 3888 |
+
"learning_rate": 1.73010638774079e-06,
|
| 3889 |
+
"loss": 2.913,
|
| 3890 |
+
"step": 323500
|
| 3891 |
+
},
|
| 3892 |
+
{
|
| 3893 |
+
"epoch": 0.97,
|
| 3894 |
+
"learning_rate": 1.6555006789119504e-06,
|
| 3895 |
+
"loss": 2.9103,
|
| 3896 |
+
"step": 324000
|
| 3897 |
+
},
|
| 3898 |
+
{
|
| 3899 |
+
"epoch": 0.97,
|
| 3900 |
+
"learning_rate": 1.5808949700831108e-06,
|
| 3901 |
+
"loss": 2.9059,
|
| 3902 |
+
"step": 324500
|
| 3903 |
+
},
|
| 3904 |
+
{
|
| 3905 |
+
"epoch": 0.97,
|
| 3906 |
+
"learning_rate": 1.5062892612542712e-06,
|
| 3907 |
+
"loss": 2.9289,
|
| 3908 |
+
"step": 325000
|
| 3909 |
+
},
|
| 3910 |
+
{
|
| 3911 |
+
"epoch": 0.97,
|
| 3912 |
+
"learning_rate": 1.4316835524254317e-06,
|
| 3913 |
+
"loss": 2.9166,
|
| 3914 |
+
"step": 325500
|
| 3915 |
+
},
|
| 3916 |
+
{
|
| 3917 |
+
"epoch": 0.97,
|
| 3918 |
+
"learning_rate": 1.357077843596592e-06,
|
| 3919 |
+
"loss": 2.9104,
|
| 3920 |
+
"step": 326000
|
| 3921 |
+
},
|
| 3922 |
+
{
|
| 3923 |
+
"epoch": 0.97,
|
| 3924 |
+
"learning_rate": 1.2824721347677525e-06,
|
| 3925 |
+
"loss": 2.9265,
|
| 3926 |
+
"step": 326500
|
| 3927 |
+
},
|
| 3928 |
+
{
|
| 3929 |
+
"epoch": 0.98,
|
| 3930 |
+
"learning_rate": 1.207866425938913e-06,
|
| 3931 |
+
"loss": 2.9004,
|
| 3932 |
+
"step": 327000
|
| 3933 |
+
},
|
| 3934 |
+
{
|
| 3935 |
+
"epoch": 0.98,
|
| 3936 |
+
"learning_rate": 1.1332607171100733e-06,
|
| 3937 |
+
"loss": 2.9195,
|
| 3938 |
+
"step": 327500
|
| 3939 |
+
},
|
| 3940 |
+
{
|
| 3941 |
+
"epoch": 0.98,
|
| 3942 |
+
"learning_rate": 1.0586550082812338e-06,
|
| 3943 |
+
"loss": 2.9032,
|
| 3944 |
+
"step": 328000
|
| 3945 |
+
},
|
| 3946 |
+
{
|
| 3947 |
+
"epoch": 0.98,
|
| 3948 |
+
"learning_rate": 9.840492994523942e-07,
|
| 3949 |
+
"loss": 2.9139,
|
| 3950 |
+
"step": 328500
|
| 3951 |
+
},
|
| 3952 |
+
{
|
| 3953 |
+
"epoch": 0.98,
|
| 3954 |
+
"learning_rate": 9.094435906235545e-07,
|
| 3955 |
+
"loss": 2.9229,
|
| 3956 |
+
"step": 329000
|
| 3957 |
+
},
|
| 3958 |
+
{
|
| 3959 |
+
"epoch": 0.98,
|
| 3960 |
+
"learning_rate": 8.348378817947149e-07,
|
| 3961 |
+
"loss": 2.9139,
|
| 3962 |
+
"step": 329500
|
| 3963 |
+
},
|
| 3964 |
+
{
|
| 3965 |
+
"epoch": 0.98,
|
| 3966 |
+
"learning_rate": 7.602321729658753e-07,
|
| 3967 |
+
"loss": 2.9237,
|
| 3968 |
+
"step": 330000
|
| 3969 |
+
}
|
| 3970 |
+
],
|
| 3971 |
+
"max_steps": 335095,
|
| 3972 |
+
"num_train_epochs": 1,
|
| 3973 |
+
"total_flos": 2.108603298028032e+16,
|
| 3974 |
+
"trial_name": null,
|
| 3975 |
+
"trial_params": null
|
| 3976 |
+
}
|
checkpoint-330000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3d35089d0c3a6b47b1c8df0ddfa08b310484c437d7fde3fd7b723448ffc0097d
|
| 3 |
+
size 2415
|
config.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"RobertaForMaskedLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"bos_token_id": 0,
|
| 7 |
+
"eos_token_id": 2,
|
| 8 |
+
"gradient_checkpointing": false,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 3072,
|
| 14 |
+
"layer_norm_eps": 1e-12,
|
| 15 |
+
"max_position_embeddings": 512,
|
| 16 |
+
"model_type": "roberta",
|
| 17 |
+
"num_attention_heads": 12,
|
| 18 |
+
"num_hidden_layers": 6,
|
| 19 |
+
"pad_token_id": 1,
|
| 20 |
+
"position_embedding_type": "absolute",
|
| 21 |
+
"transformers_version": "4.6.1",
|
| 22 |
+
"type_vocab_size": 1,
|
| 23 |
+
"use_cache": true,
|
| 24 |
+
"vocab_size": 55000
|
| 25 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7289c7b79e9c6dc203509bbd74cb5b2665832862fc4248ad9f2e70f9689fe7d7
|
| 3 |
+
size 343289095
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3d35089d0c3a6b47b1c8df0ddfa08b310484c437d7fde3fd7b723448ffc0097d
|
| 3 |
+
size 2415
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|