hyechanj
commited on
Commit
·
d3a841c
1
Parent(s):
2517326
Reverse question model
Browse files- all_results.json +18 -0
- config.json +74 -0
- eval_results.json +13 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- train_results.json +8 -0
- trainer_state.json +2149 -0
- training_args.bin +3 -0
- vocab.json +0 -0
all_results.json
ADDED
|
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_gen_len": 19.1239,
|
| 4 |
+
"eval_loss": 2.4417812824249268,
|
| 5 |
+
"eval_rouge1": 26.0258,
|
| 6 |
+
"eval_rouge2": 10.5329,
|
| 7 |
+
"eval_rougeL": 21.9381,
|
| 8 |
+
"eval_rougeLsum": 23.7652,
|
| 9 |
+
"eval_runtime": 1305.7847,
|
| 10 |
+
"eval_samples": 15000,
|
| 11 |
+
"eval_samples_per_second": 11.487,
|
| 12 |
+
"eval_steps_per_second": 2.872,
|
| 13 |
+
"train_loss": 2.263988757942984,
|
| 14 |
+
"train_runtime": 19136.7963,
|
| 15 |
+
"train_samples": 70803,
|
| 16 |
+
"train_samples_per_second": 36.998,
|
| 17 |
+
"train_steps_per_second": 9.25
|
| 18 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "facebook/bart-base",
|
| 3 |
+
"activation_dropout": 0.1,
|
| 4 |
+
"activation_function": "gelu",
|
| 5 |
+
"add_bias_logits": false,
|
| 6 |
+
"add_final_layer_norm": false,
|
| 7 |
+
"architectures": [
|
| 8 |
+
"BartForConditionalGeneration"
|
| 9 |
+
],
|
| 10 |
+
"attention_dropout": 0.1,
|
| 11 |
+
"bos_token_id": 0,
|
| 12 |
+
"classif_dropout": 0.1,
|
| 13 |
+
"classifier_dropout": 0.0,
|
| 14 |
+
"d_model": 768,
|
| 15 |
+
"decoder_attention_heads": 12,
|
| 16 |
+
"decoder_ffn_dim": 3072,
|
| 17 |
+
"decoder_layerdrop": 0.0,
|
| 18 |
+
"decoder_layers": 6,
|
| 19 |
+
"decoder_start_token_id": 2,
|
| 20 |
+
"dropout": 0.1,
|
| 21 |
+
"early_stopping": true,
|
| 22 |
+
"encoder_attention_heads": 12,
|
| 23 |
+
"encoder_ffn_dim": 3072,
|
| 24 |
+
"encoder_layerdrop": 0.0,
|
| 25 |
+
"encoder_layers": 6,
|
| 26 |
+
"eos_token_id": 2,
|
| 27 |
+
"forced_eos_token_id": 2,
|
| 28 |
+
"gradient_checkpointing": false,
|
| 29 |
+
"id2label": {
|
| 30 |
+
"0": "LABEL_0",
|
| 31 |
+
"1": "LABEL_1",
|
| 32 |
+
"2": "LABEL_2"
|
| 33 |
+
},
|
| 34 |
+
"init_std": 0.02,
|
| 35 |
+
"is_encoder_decoder": true,
|
| 36 |
+
"label2id": {
|
| 37 |
+
"LABEL_0": 0,
|
| 38 |
+
"LABEL_1": 1,
|
| 39 |
+
"LABEL_2": 2
|
| 40 |
+
},
|
| 41 |
+
"max_position_embeddings": 1024,
|
| 42 |
+
"model_type": "bart",
|
| 43 |
+
"no_repeat_ngram_size": 3,
|
| 44 |
+
"normalize_before": false,
|
| 45 |
+
"normalize_embedding": true,
|
| 46 |
+
"num_beams": 4,
|
| 47 |
+
"num_hidden_layers": 6,
|
| 48 |
+
"pad_token_id": 1,
|
| 49 |
+
"scale_embedding": false,
|
| 50 |
+
"task_specific_params": {
|
| 51 |
+
"summarization": {
|
| 52 |
+
"length_penalty": 1.0,
|
| 53 |
+
"max_length": 128,
|
| 54 |
+
"min_length": 12,
|
| 55 |
+
"num_beams": 4
|
| 56 |
+
},
|
| 57 |
+
"summarization_cnn": {
|
| 58 |
+
"length_penalty": 2.0,
|
| 59 |
+
"max_length": 142,
|
| 60 |
+
"min_length": 56,
|
| 61 |
+
"num_beams": 4
|
| 62 |
+
},
|
| 63 |
+
"summarization_xsum": {
|
| 64 |
+
"length_penalty": 1.0,
|
| 65 |
+
"max_length": 62,
|
| 66 |
+
"min_length": 11,
|
| 67 |
+
"num_beams": 6
|
| 68 |
+
}
|
| 69 |
+
},
|
| 70 |
+
"torch_dtype": "float32",
|
| 71 |
+
"transformers_version": "4.17.0.dev0",
|
| 72 |
+
"use_cache": true,
|
| 73 |
+
"vocab_size": 50265
|
| 74 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_gen_len": 19.1239,
|
| 4 |
+
"eval_loss": 2.4417812824249268,
|
| 5 |
+
"eval_rouge1": 26.0258,
|
| 6 |
+
"eval_rouge2": 10.5329,
|
| 7 |
+
"eval_rougeL": 21.9381,
|
| 8 |
+
"eval_rougeLsum": 23.7652,
|
| 9 |
+
"eval_runtime": 1305.7847,
|
| 10 |
+
"eval_samples": 15000,
|
| 11 |
+
"eval_samples_per_second": 11.487,
|
| 12 |
+
"eval_steps_per_second": 2.872
|
| 13 |
+
}
|
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 sha256:474f39c097d15d0cb05d17fe9e50176b3d6131c12f0620ed7fc003e725d85009
|
| 3 |
+
size 557979193
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"errors": "replace", "bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": "<mask>", "add_prefix_space": false, "trim_offsets": true, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "facebook/bart-base", "tokenizer_class": "BartTokenizer"}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"train_loss": 2.263988757942984,
|
| 4 |
+
"train_runtime": 19136.7963,
|
| 5 |
+
"train_samples": 70803,
|
| 6 |
+
"train_samples_per_second": 36.998,
|
| 7 |
+
"train_steps_per_second": 9.25
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2149 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 10.0,
|
| 5 |
+
"global_step": 177010,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.03,
|
| 12 |
+
"learning_rate": 4.985876504152308e-05,
|
| 13 |
+
"loss": 3.3413,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.06,
|
| 18 |
+
"learning_rate": 4.971753008304616e-05,
|
| 19 |
+
"loss": 3.2871,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.08,
|
| 24 |
+
"learning_rate": 4.9576295124569234e-05,
|
| 25 |
+
"loss": 3.2263,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.11,
|
| 30 |
+
"learning_rate": 4.943506016609231e-05,
|
| 31 |
+
"loss": 3.2316,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.14,
|
| 36 |
+
"learning_rate": 4.929382520761539e-05,
|
| 37 |
+
"loss": 3.1903,
|
| 38 |
+
"step": 2500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.17,
|
| 42 |
+
"learning_rate": 4.915259024913847e-05,
|
| 43 |
+
"loss": 3.1967,
|
| 44 |
+
"step": 3000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.2,
|
| 48 |
+
"learning_rate": 4.901135529066155e-05,
|
| 49 |
+
"loss": 3.181,
|
| 50 |
+
"step": 3500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.23,
|
| 54 |
+
"learning_rate": 4.8870120332184624e-05,
|
| 55 |
+
"loss": 3.1665,
|
| 56 |
+
"step": 4000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.25,
|
| 60 |
+
"learning_rate": 4.87288853737077e-05,
|
| 61 |
+
"loss": 3.1597,
|
| 62 |
+
"step": 4500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.28,
|
| 66 |
+
"learning_rate": 4.8587650415230776e-05,
|
| 67 |
+
"loss": 3.1482,
|
| 68 |
+
"step": 5000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.31,
|
| 72 |
+
"learning_rate": 4.8446415456753855e-05,
|
| 73 |
+
"loss": 3.1244,
|
| 74 |
+
"step": 5500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.34,
|
| 78 |
+
"learning_rate": 4.8305180498276935e-05,
|
| 79 |
+
"loss": 3.1668,
|
| 80 |
+
"step": 6000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.37,
|
| 84 |
+
"learning_rate": 4.8163945539800014e-05,
|
| 85 |
+
"loss": 3.1144,
|
| 86 |
+
"step": 6500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.4,
|
| 90 |
+
"learning_rate": 4.8022710581323093e-05,
|
| 91 |
+
"loss": 3.1353,
|
| 92 |
+
"step": 7000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.42,
|
| 96 |
+
"learning_rate": 4.7881475622846166e-05,
|
| 97 |
+
"loss": 3.1212,
|
| 98 |
+
"step": 7500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.45,
|
| 102 |
+
"learning_rate": 4.7740240664369245e-05,
|
| 103 |
+
"loss": 3.0918,
|
| 104 |
+
"step": 8000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.48,
|
| 108 |
+
"learning_rate": 4.7599005705892325e-05,
|
| 109 |
+
"loss": 3.1366,
|
| 110 |
+
"step": 8500
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.51,
|
| 114 |
+
"learning_rate": 4.7457770747415404e-05,
|
| 115 |
+
"loss": 3.1026,
|
| 116 |
+
"step": 9000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.54,
|
| 120 |
+
"learning_rate": 4.7316535788938484e-05,
|
| 121 |
+
"loss": 3.0913,
|
| 122 |
+
"step": 9500
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.56,
|
| 126 |
+
"learning_rate": 4.717530083046156e-05,
|
| 127 |
+
"loss": 3.0663,
|
| 128 |
+
"step": 10000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.59,
|
| 132 |
+
"learning_rate": 4.7034065871984636e-05,
|
| 133 |
+
"loss": 3.0958,
|
| 134 |
+
"step": 10500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.62,
|
| 138 |
+
"learning_rate": 4.6892830913507715e-05,
|
| 139 |
+
"loss": 3.0529,
|
| 140 |
+
"step": 11000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.65,
|
| 144 |
+
"learning_rate": 4.6751595955030794e-05,
|
| 145 |
+
"loss": 3.0909,
|
| 146 |
+
"step": 11500
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.68,
|
| 150 |
+
"learning_rate": 4.661036099655387e-05,
|
| 151 |
+
"loss": 3.0962,
|
| 152 |
+
"step": 12000
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.71,
|
| 156 |
+
"learning_rate": 4.6469126038076946e-05,
|
| 157 |
+
"loss": 3.0731,
|
| 158 |
+
"step": 12500
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.73,
|
| 162 |
+
"learning_rate": 4.632789107960002e-05,
|
| 163 |
+
"loss": 3.0736,
|
| 164 |
+
"step": 13000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.76,
|
| 168 |
+
"learning_rate": 4.61866561211231e-05,
|
| 169 |
+
"loss": 3.0786,
|
| 170 |
+
"step": 13500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.79,
|
| 174 |
+
"learning_rate": 4.604542116264618e-05,
|
| 175 |
+
"loss": 3.0708,
|
| 176 |
+
"step": 14000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.82,
|
| 180 |
+
"learning_rate": 4.590418620416926e-05,
|
| 181 |
+
"loss": 3.0641,
|
| 182 |
+
"step": 14500
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 0.85,
|
| 186 |
+
"learning_rate": 4.5762951245692336e-05,
|
| 187 |
+
"loss": 3.0344,
|
| 188 |
+
"step": 15000
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.88,
|
| 192 |
+
"learning_rate": 4.5621716287215416e-05,
|
| 193 |
+
"loss": 3.061,
|
| 194 |
+
"step": 15500
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.9,
|
| 198 |
+
"learning_rate": 4.548048132873849e-05,
|
| 199 |
+
"loss": 3.0766,
|
| 200 |
+
"step": 16000
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 0.93,
|
| 204 |
+
"learning_rate": 4.533924637026157e-05,
|
| 205 |
+
"loss": 3.0682,
|
| 206 |
+
"step": 16500
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.96,
|
| 210 |
+
"learning_rate": 4.519801141178465e-05,
|
| 211 |
+
"loss": 3.0431,
|
| 212 |
+
"step": 17000
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.99,
|
| 216 |
+
"learning_rate": 4.5056776453307727e-05,
|
| 217 |
+
"loss": 3.064,
|
| 218 |
+
"step": 17500
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 1.02,
|
| 222 |
+
"learning_rate": 4.4915541494830806e-05,
|
| 223 |
+
"loss": 2.8743,
|
| 224 |
+
"step": 18000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 1.05,
|
| 228 |
+
"learning_rate": 4.4774306536353885e-05,
|
| 229 |
+
"loss": 2.75,
|
| 230 |
+
"step": 18500
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 1.07,
|
| 234 |
+
"learning_rate": 4.463307157787696e-05,
|
| 235 |
+
"loss": 2.7833,
|
| 236 |
+
"step": 19000
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 1.1,
|
| 240 |
+
"learning_rate": 4.449183661940004e-05,
|
| 241 |
+
"loss": 2.7679,
|
| 242 |
+
"step": 19500
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 1.13,
|
| 246 |
+
"learning_rate": 4.435060166092312e-05,
|
| 247 |
+
"loss": 2.7905,
|
| 248 |
+
"step": 20000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 1.16,
|
| 252 |
+
"learning_rate": 4.420936670244619e-05,
|
| 253 |
+
"loss": 2.7913,
|
| 254 |
+
"step": 20500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 1.19,
|
| 258 |
+
"learning_rate": 4.406813174396927e-05,
|
| 259 |
+
"loss": 2.8132,
|
| 260 |
+
"step": 21000
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 1.21,
|
| 264 |
+
"learning_rate": 4.392689678549235e-05,
|
| 265 |
+
"loss": 2.7929,
|
| 266 |
+
"step": 21500
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 1.24,
|
| 270 |
+
"learning_rate": 4.378566182701542e-05,
|
| 271 |
+
"loss": 2.7994,
|
| 272 |
+
"step": 22000
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 1.27,
|
| 276 |
+
"learning_rate": 4.36444268685385e-05,
|
| 277 |
+
"loss": 2.7934,
|
| 278 |
+
"step": 22500
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 1.3,
|
| 282 |
+
"learning_rate": 4.350319191006158e-05,
|
| 283 |
+
"loss": 2.8068,
|
| 284 |
+
"step": 23000
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 1.33,
|
| 288 |
+
"learning_rate": 4.336195695158466e-05,
|
| 289 |
+
"loss": 2.7842,
|
| 290 |
+
"step": 23500
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 1.36,
|
| 294 |
+
"learning_rate": 4.322072199310774e-05,
|
| 295 |
+
"loss": 2.8079,
|
| 296 |
+
"step": 24000
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 1.38,
|
| 300 |
+
"learning_rate": 4.307948703463082e-05,
|
| 301 |
+
"loss": 2.7959,
|
| 302 |
+
"step": 24500
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 1.41,
|
| 306 |
+
"learning_rate": 4.293825207615389e-05,
|
| 307 |
+
"loss": 2.8159,
|
| 308 |
+
"step": 25000
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 1.44,
|
| 312 |
+
"learning_rate": 4.279701711767697e-05,
|
| 313 |
+
"loss": 2.8135,
|
| 314 |
+
"step": 25500
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 1.47,
|
| 318 |
+
"learning_rate": 4.265578215920005e-05,
|
| 319 |
+
"loss": 2.8063,
|
| 320 |
+
"step": 26000
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 1.5,
|
| 324 |
+
"learning_rate": 4.251454720072313e-05,
|
| 325 |
+
"loss": 2.8289,
|
| 326 |
+
"step": 26500
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 1.53,
|
| 330 |
+
"learning_rate": 4.237331224224621e-05,
|
| 331 |
+
"loss": 2.8124,
|
| 332 |
+
"step": 27000
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 1.55,
|
| 336 |
+
"learning_rate": 4.223207728376928e-05,
|
| 337 |
+
"loss": 2.8181,
|
| 338 |
+
"step": 27500
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 1.58,
|
| 342 |
+
"learning_rate": 4.209084232529236e-05,
|
| 343 |
+
"loss": 2.8284,
|
| 344 |
+
"step": 28000
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 1.61,
|
| 348 |
+
"learning_rate": 4.194960736681543e-05,
|
| 349 |
+
"loss": 2.8456,
|
| 350 |
+
"step": 28500
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 1.64,
|
| 354 |
+
"learning_rate": 4.180837240833851e-05,
|
| 355 |
+
"loss": 2.8413,
|
| 356 |
+
"step": 29000
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 1.67,
|
| 360 |
+
"learning_rate": 4.166713744986159e-05,
|
| 361 |
+
"loss": 2.7965,
|
| 362 |
+
"step": 29500
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 1.69,
|
| 366 |
+
"learning_rate": 4.152590249138467e-05,
|
| 367 |
+
"loss": 2.8385,
|
| 368 |
+
"step": 30000
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 1.72,
|
| 372 |
+
"learning_rate": 4.138466753290774e-05,
|
| 373 |
+
"loss": 2.8246,
|
| 374 |
+
"step": 30500
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 1.75,
|
| 378 |
+
"learning_rate": 4.124343257443082e-05,
|
| 379 |
+
"loss": 2.83,
|
| 380 |
+
"step": 31000
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 1.78,
|
| 384 |
+
"learning_rate": 4.11021976159539e-05,
|
| 385 |
+
"loss": 2.8387,
|
| 386 |
+
"step": 31500
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 1.81,
|
| 390 |
+
"learning_rate": 4.096096265747698e-05,
|
| 391 |
+
"loss": 2.8369,
|
| 392 |
+
"step": 32000
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 1.84,
|
| 396 |
+
"learning_rate": 4.081972769900006e-05,
|
| 397 |
+
"loss": 2.8197,
|
| 398 |
+
"step": 32500
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 1.86,
|
| 402 |
+
"learning_rate": 4.067849274052314e-05,
|
| 403 |
+
"loss": 2.8224,
|
| 404 |
+
"step": 33000
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 1.89,
|
| 408 |
+
"learning_rate": 4.053725778204621e-05,
|
| 409 |
+
"loss": 2.8123,
|
| 410 |
+
"step": 33500
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 1.92,
|
| 414 |
+
"learning_rate": 4.039602282356929e-05,
|
| 415 |
+
"loss": 2.8198,
|
| 416 |
+
"step": 34000
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 1.95,
|
| 420 |
+
"learning_rate": 4.025478786509237e-05,
|
| 421 |
+
"loss": 2.8318,
|
| 422 |
+
"step": 34500
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 1.98,
|
| 426 |
+
"learning_rate": 4.011355290661545e-05,
|
| 427 |
+
"loss": 2.8398,
|
| 428 |
+
"step": 35000
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 2.01,
|
| 432 |
+
"learning_rate": 3.997231794813853e-05,
|
| 433 |
+
"loss": 2.7405,
|
| 434 |
+
"step": 35500
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 2.03,
|
| 438 |
+
"learning_rate": 3.98310829896616e-05,
|
| 439 |
+
"loss": 2.5663,
|
| 440 |
+
"step": 36000
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 2.06,
|
| 444 |
+
"learning_rate": 3.968984803118468e-05,
|
| 445 |
+
"loss": 2.5434,
|
| 446 |
+
"step": 36500
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 2.09,
|
| 450 |
+
"learning_rate": 3.9548613072707755e-05,
|
| 451 |
+
"loss": 2.5603,
|
| 452 |
+
"step": 37000
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 2.12,
|
| 456 |
+
"learning_rate": 3.9407378114230834e-05,
|
| 457 |
+
"loss": 2.5647,
|
| 458 |
+
"step": 37500
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 2.15,
|
| 462 |
+
"learning_rate": 3.9266143155753913e-05,
|
| 463 |
+
"loss": 2.5591,
|
| 464 |
+
"step": 38000
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 2.18,
|
| 468 |
+
"learning_rate": 3.912490819727699e-05,
|
| 469 |
+
"loss": 2.557,
|
| 470 |
+
"step": 38500
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 2.2,
|
| 474 |
+
"learning_rate": 3.8983673238800065e-05,
|
| 475 |
+
"loss": 2.5874,
|
| 476 |
+
"step": 39000
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 2.23,
|
| 480 |
+
"learning_rate": 3.8842438280323145e-05,
|
| 481 |
+
"loss": 2.5848,
|
| 482 |
+
"step": 39500
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 2.26,
|
| 486 |
+
"learning_rate": 3.8701203321846224e-05,
|
| 487 |
+
"loss": 2.5693,
|
| 488 |
+
"step": 40000
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 2.29,
|
| 492 |
+
"learning_rate": 3.8559968363369304e-05,
|
| 493 |
+
"loss": 2.5997,
|
| 494 |
+
"step": 40500
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 2.32,
|
| 498 |
+
"learning_rate": 3.841873340489238e-05,
|
| 499 |
+
"loss": 2.5978,
|
| 500 |
+
"step": 41000
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 2.34,
|
| 504 |
+
"learning_rate": 3.827749844641546e-05,
|
| 505 |
+
"loss": 2.5705,
|
| 506 |
+
"step": 41500
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 2.37,
|
| 510 |
+
"learning_rate": 3.8136263487938535e-05,
|
| 511 |
+
"loss": 2.6125,
|
| 512 |
+
"step": 42000
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 2.4,
|
| 516 |
+
"learning_rate": 3.7995028529461614e-05,
|
| 517 |
+
"loss": 2.6105,
|
| 518 |
+
"step": 42500
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 2.43,
|
| 522 |
+
"learning_rate": 3.7853793570984694e-05,
|
| 523 |
+
"loss": 2.6086,
|
| 524 |
+
"step": 43000
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 2.46,
|
| 528 |
+
"learning_rate": 3.771255861250777e-05,
|
| 529 |
+
"loss": 2.6181,
|
| 530 |
+
"step": 43500
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 2.49,
|
| 534 |
+
"learning_rate": 3.7571323654030846e-05,
|
| 535 |
+
"loss": 2.5933,
|
| 536 |
+
"step": 44000
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 2.51,
|
| 540 |
+
"learning_rate": 3.7430088695553925e-05,
|
| 541 |
+
"loss": 2.6127,
|
| 542 |
+
"step": 44500
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 2.54,
|
| 546 |
+
"learning_rate": 3.7288853737077e-05,
|
| 547 |
+
"loss": 2.5906,
|
| 548 |
+
"step": 45000
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 2.57,
|
| 552 |
+
"learning_rate": 3.714761877860008e-05,
|
| 553 |
+
"loss": 2.6226,
|
| 554 |
+
"step": 45500
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 2.6,
|
| 558 |
+
"learning_rate": 3.7006383820123157e-05,
|
| 559 |
+
"loss": 2.6157,
|
| 560 |
+
"step": 46000
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 2.63,
|
| 564 |
+
"learning_rate": 3.6865148861646236e-05,
|
| 565 |
+
"loss": 2.6168,
|
| 566 |
+
"step": 46500
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 2.66,
|
| 570 |
+
"learning_rate": 3.6723913903169315e-05,
|
| 571 |
+
"loss": 2.6321,
|
| 572 |
+
"step": 47000
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 2.68,
|
| 576 |
+
"learning_rate": 3.6582678944692395e-05,
|
| 577 |
+
"loss": 2.631,
|
| 578 |
+
"step": 47500
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 2.71,
|
| 582 |
+
"learning_rate": 3.644144398621547e-05,
|
| 583 |
+
"loss": 2.6225,
|
| 584 |
+
"step": 48000
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 2.74,
|
| 588 |
+
"learning_rate": 3.630020902773855e-05,
|
| 589 |
+
"loss": 2.5985,
|
| 590 |
+
"step": 48500
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 2.77,
|
| 594 |
+
"learning_rate": 3.6158974069261626e-05,
|
| 595 |
+
"loss": 2.6194,
|
| 596 |
+
"step": 49000
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 2.8,
|
| 600 |
+
"learning_rate": 3.6017739110784705e-05,
|
| 601 |
+
"loss": 2.6228,
|
| 602 |
+
"step": 49500
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 2.82,
|
| 606 |
+
"learning_rate": 3.5876504152307785e-05,
|
| 607 |
+
"loss": 2.6266,
|
| 608 |
+
"step": 50000
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 2.85,
|
| 612 |
+
"learning_rate": 3.5735269193830864e-05,
|
| 613 |
+
"loss": 2.635,
|
| 614 |
+
"step": 50500
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 2.88,
|
| 618 |
+
"learning_rate": 3.559403423535394e-05,
|
| 619 |
+
"loss": 2.6387,
|
| 620 |
+
"step": 51000
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 2.91,
|
| 624 |
+
"learning_rate": 3.5452799276877016e-05,
|
| 625 |
+
"loss": 2.6477,
|
| 626 |
+
"step": 51500
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 2.94,
|
| 630 |
+
"learning_rate": 3.531156431840009e-05,
|
| 631 |
+
"loss": 2.637,
|
| 632 |
+
"step": 52000
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 2.97,
|
| 636 |
+
"learning_rate": 3.517032935992317e-05,
|
| 637 |
+
"loss": 2.6528,
|
| 638 |
+
"step": 52500
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 2.99,
|
| 642 |
+
"learning_rate": 3.502909440144625e-05,
|
| 643 |
+
"loss": 2.6596,
|
| 644 |
+
"step": 53000
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 3.02,
|
| 648 |
+
"learning_rate": 3.488785944296932e-05,
|
| 649 |
+
"loss": 2.4093,
|
| 650 |
+
"step": 53500
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 3.05,
|
| 654 |
+
"learning_rate": 3.47466244844924e-05,
|
| 655 |
+
"loss": 2.3596,
|
| 656 |
+
"step": 54000
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 3.08,
|
| 660 |
+
"learning_rate": 3.460538952601548e-05,
|
| 661 |
+
"loss": 2.3662,
|
| 662 |
+
"step": 54500
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 3.11,
|
| 666 |
+
"learning_rate": 3.446415456753856e-05,
|
| 667 |
+
"loss": 2.3709,
|
| 668 |
+
"step": 55000
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 3.14,
|
| 672 |
+
"learning_rate": 3.432291960906164e-05,
|
| 673 |
+
"loss": 2.3823,
|
| 674 |
+
"step": 55500
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 3.16,
|
| 678 |
+
"learning_rate": 3.418168465058472e-05,
|
| 679 |
+
"loss": 2.3749,
|
| 680 |
+
"step": 56000
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 3.19,
|
| 684 |
+
"learning_rate": 3.404044969210779e-05,
|
| 685 |
+
"loss": 2.3889,
|
| 686 |
+
"step": 56500
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 3.22,
|
| 690 |
+
"learning_rate": 3.389921473363087e-05,
|
| 691 |
+
"loss": 2.3777,
|
| 692 |
+
"step": 57000
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 3.25,
|
| 696 |
+
"learning_rate": 3.375797977515395e-05,
|
| 697 |
+
"loss": 2.4009,
|
| 698 |
+
"step": 57500
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 3.28,
|
| 702 |
+
"learning_rate": 3.361674481667703e-05,
|
| 703 |
+
"loss": 2.403,
|
| 704 |
+
"step": 58000
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 3.3,
|
| 708 |
+
"learning_rate": 3.347550985820011e-05,
|
| 709 |
+
"loss": 2.4091,
|
| 710 |
+
"step": 58500
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 3.33,
|
| 714 |
+
"learning_rate": 3.3334274899723187e-05,
|
| 715 |
+
"loss": 2.4504,
|
| 716 |
+
"step": 59000
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 3.36,
|
| 720 |
+
"learning_rate": 3.319303994124626e-05,
|
| 721 |
+
"loss": 2.4165,
|
| 722 |
+
"step": 59500
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 3.39,
|
| 726 |
+
"learning_rate": 3.305180498276934e-05,
|
| 727 |
+
"loss": 2.408,
|
| 728 |
+
"step": 60000
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 3.42,
|
| 732 |
+
"learning_rate": 3.291057002429241e-05,
|
| 733 |
+
"loss": 2.4213,
|
| 734 |
+
"step": 60500
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 3.45,
|
| 738 |
+
"learning_rate": 3.276933506581549e-05,
|
| 739 |
+
"loss": 2.4162,
|
| 740 |
+
"step": 61000
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 3.47,
|
| 744 |
+
"learning_rate": 3.262810010733857e-05,
|
| 745 |
+
"loss": 2.4156,
|
| 746 |
+
"step": 61500
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 3.5,
|
| 750 |
+
"learning_rate": 3.248686514886165e-05,
|
| 751 |
+
"loss": 2.4263,
|
| 752 |
+
"step": 62000
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 3.53,
|
| 756 |
+
"learning_rate": 3.234563019038472e-05,
|
| 757 |
+
"loss": 2.4268,
|
| 758 |
+
"step": 62500
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 3.56,
|
| 762 |
+
"learning_rate": 3.22043952319078e-05,
|
| 763 |
+
"loss": 2.4019,
|
| 764 |
+
"step": 63000
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 3.59,
|
| 768 |
+
"learning_rate": 3.206316027343088e-05,
|
| 769 |
+
"loss": 2.4252,
|
| 770 |
+
"step": 63500
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 3.62,
|
| 774 |
+
"learning_rate": 3.192192531495396e-05,
|
| 775 |
+
"loss": 2.442,
|
| 776 |
+
"step": 64000
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 3.64,
|
| 780 |
+
"learning_rate": 3.178069035647704e-05,
|
| 781 |
+
"loss": 2.4226,
|
| 782 |
+
"step": 64500
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 3.67,
|
| 786 |
+
"learning_rate": 3.163945539800011e-05,
|
| 787 |
+
"loss": 2.4471,
|
| 788 |
+
"step": 65000
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 3.7,
|
| 792 |
+
"learning_rate": 3.149822043952319e-05,
|
| 793 |
+
"loss": 2.4206,
|
| 794 |
+
"step": 65500
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 3.73,
|
| 798 |
+
"learning_rate": 3.135698548104627e-05,
|
| 799 |
+
"loss": 2.4499,
|
| 800 |
+
"step": 66000
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 3.76,
|
| 804 |
+
"learning_rate": 3.121575052256935e-05,
|
| 805 |
+
"loss": 2.446,
|
| 806 |
+
"step": 66500
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"epoch": 3.79,
|
| 810 |
+
"learning_rate": 3.107451556409243e-05,
|
| 811 |
+
"loss": 2.4632,
|
| 812 |
+
"step": 67000
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 3.81,
|
| 816 |
+
"learning_rate": 3.09332806056155e-05,
|
| 817 |
+
"loss": 2.462,
|
| 818 |
+
"step": 67500
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 3.84,
|
| 822 |
+
"learning_rate": 3.079204564713858e-05,
|
| 823 |
+
"loss": 2.4722,
|
| 824 |
+
"step": 68000
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 3.87,
|
| 828 |
+
"learning_rate": 3.0650810688661654e-05,
|
| 829 |
+
"loss": 2.4678,
|
| 830 |
+
"step": 68500
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 3.9,
|
| 834 |
+
"learning_rate": 3.0509575730184737e-05,
|
| 835 |
+
"loss": 2.4871,
|
| 836 |
+
"step": 69000
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 3.93,
|
| 840 |
+
"learning_rate": 3.0368340771707816e-05,
|
| 841 |
+
"loss": 2.4585,
|
| 842 |
+
"step": 69500
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 3.95,
|
| 846 |
+
"learning_rate": 3.0227105813230892e-05,
|
| 847 |
+
"loss": 2.4802,
|
| 848 |
+
"step": 70000
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 3.98,
|
| 852 |
+
"learning_rate": 3.0085870854753972e-05,
|
| 853 |
+
"loss": 2.4703,
|
| 854 |
+
"step": 70500
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 4.01,
|
| 858 |
+
"learning_rate": 2.9944635896277044e-05,
|
| 859 |
+
"loss": 2.3879,
|
| 860 |
+
"step": 71000
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"epoch": 4.04,
|
| 864 |
+
"learning_rate": 2.9803400937800124e-05,
|
| 865 |
+
"loss": 2.2056,
|
| 866 |
+
"step": 71500
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 4.07,
|
| 870 |
+
"learning_rate": 2.9662165979323203e-05,
|
| 871 |
+
"loss": 2.209,
|
| 872 |
+
"step": 72000
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 4.1,
|
| 876 |
+
"learning_rate": 2.9520931020846282e-05,
|
| 877 |
+
"loss": 2.2496,
|
| 878 |
+
"step": 72500
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 4.12,
|
| 882 |
+
"learning_rate": 2.9379696062369362e-05,
|
| 883 |
+
"loss": 2.2075,
|
| 884 |
+
"step": 73000
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 4.15,
|
| 888 |
+
"learning_rate": 2.9238461103892438e-05,
|
| 889 |
+
"loss": 2.2253,
|
| 890 |
+
"step": 73500
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 4.18,
|
| 894 |
+
"learning_rate": 2.9097226145415514e-05,
|
| 895 |
+
"loss": 2.2405,
|
| 896 |
+
"step": 74000
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 4.21,
|
| 900 |
+
"learning_rate": 2.895599118693859e-05,
|
| 901 |
+
"loss": 2.2353,
|
| 902 |
+
"step": 74500
|
| 903 |
+
},
|
| 904 |
+
{
|
| 905 |
+
"epoch": 4.24,
|
| 906 |
+
"learning_rate": 2.881475622846167e-05,
|
| 907 |
+
"loss": 2.2074,
|
| 908 |
+
"step": 75000
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 4.27,
|
| 912 |
+
"learning_rate": 2.867352126998475e-05,
|
| 913 |
+
"loss": 2.2315,
|
| 914 |
+
"step": 75500
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 4.29,
|
| 918 |
+
"learning_rate": 2.8532286311507828e-05,
|
| 919 |
+
"loss": 2.2407,
|
| 920 |
+
"step": 76000
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 4.32,
|
| 924 |
+
"learning_rate": 2.83910513530309e-05,
|
| 925 |
+
"loss": 2.2213,
|
| 926 |
+
"step": 76500
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 4.35,
|
| 930 |
+
"learning_rate": 2.824981639455398e-05,
|
| 931 |
+
"loss": 2.2676,
|
| 932 |
+
"step": 77000
|
| 933 |
+
},
|
| 934 |
+
{
|
| 935 |
+
"epoch": 4.38,
|
| 936 |
+
"learning_rate": 2.810858143607706e-05,
|
| 937 |
+
"loss": 2.2671,
|
| 938 |
+
"step": 77500
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 4.41,
|
| 942 |
+
"learning_rate": 2.7967346477600135e-05,
|
| 943 |
+
"loss": 2.2482,
|
| 944 |
+
"step": 78000
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"epoch": 4.43,
|
| 948 |
+
"learning_rate": 2.7826111519123215e-05,
|
| 949 |
+
"loss": 2.2563,
|
| 950 |
+
"step": 78500
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 4.46,
|
| 954 |
+
"learning_rate": 2.7684876560646294e-05,
|
| 955 |
+
"loss": 2.2629,
|
| 956 |
+
"step": 79000
|
| 957 |
+
},
|
| 958 |
+
{
|
| 959 |
+
"epoch": 4.49,
|
| 960 |
+
"learning_rate": 2.7543641602169367e-05,
|
| 961 |
+
"loss": 2.2547,
|
| 962 |
+
"step": 79500
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 4.52,
|
| 966 |
+
"learning_rate": 2.7402406643692446e-05,
|
| 967 |
+
"loss": 2.2762,
|
| 968 |
+
"step": 80000
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 4.55,
|
| 972 |
+
"learning_rate": 2.7261171685215525e-05,
|
| 973 |
+
"loss": 2.2484,
|
| 974 |
+
"step": 80500
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 4.58,
|
| 978 |
+
"learning_rate": 2.7119936726738605e-05,
|
| 979 |
+
"loss": 2.2779,
|
| 980 |
+
"step": 81000
|
| 981 |
+
},
|
| 982 |
+
{
|
| 983 |
+
"epoch": 4.6,
|
| 984 |
+
"learning_rate": 2.6978701768261684e-05,
|
| 985 |
+
"loss": 2.2956,
|
| 986 |
+
"step": 81500
|
| 987 |
+
},
|
| 988 |
+
{
|
| 989 |
+
"epoch": 4.63,
|
| 990 |
+
"learning_rate": 2.683746680978476e-05,
|
| 991 |
+
"loss": 2.2861,
|
| 992 |
+
"step": 82000
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 4.66,
|
| 996 |
+
"learning_rate": 2.6696231851307836e-05,
|
| 997 |
+
"loss": 2.2722,
|
| 998 |
+
"step": 82500
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 4.69,
|
| 1002 |
+
"learning_rate": 2.6554996892830912e-05,
|
| 1003 |
+
"loss": 2.2839,
|
| 1004 |
+
"step": 83000
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 4.72,
|
| 1008 |
+
"learning_rate": 2.641376193435399e-05,
|
| 1009 |
+
"loss": 2.3063,
|
| 1010 |
+
"step": 83500
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 4.75,
|
| 1014 |
+
"learning_rate": 2.627252697587707e-05,
|
| 1015 |
+
"loss": 2.2823,
|
| 1016 |
+
"step": 84000
|
| 1017 |
+
},
|
| 1018 |
+
{
|
| 1019 |
+
"epoch": 4.77,
|
| 1020 |
+
"learning_rate": 2.613129201740015e-05,
|
| 1021 |
+
"loss": 2.3072,
|
| 1022 |
+
"step": 84500
|
| 1023 |
+
},
|
| 1024 |
+
{
|
| 1025 |
+
"epoch": 4.8,
|
| 1026 |
+
"learning_rate": 2.599005705892323e-05,
|
| 1027 |
+
"loss": 2.2991,
|
| 1028 |
+
"step": 85000
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"epoch": 4.83,
|
| 1032 |
+
"learning_rate": 2.5848822100446302e-05,
|
| 1033 |
+
"loss": 2.3157,
|
| 1034 |
+
"step": 85500
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 4.86,
|
| 1038 |
+
"learning_rate": 2.5707587141969382e-05,
|
| 1039 |
+
"loss": 2.2799,
|
| 1040 |
+
"step": 86000
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 4.89,
|
| 1044 |
+
"learning_rate": 2.5566352183492458e-05,
|
| 1045 |
+
"loss": 2.2816,
|
| 1046 |
+
"step": 86500
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 4.91,
|
| 1050 |
+
"learning_rate": 2.5425117225015537e-05,
|
| 1051 |
+
"loss": 2.2798,
|
| 1052 |
+
"step": 87000
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 4.94,
|
| 1056 |
+
"learning_rate": 2.5283882266538617e-05,
|
| 1057 |
+
"loss": 2.307,
|
| 1058 |
+
"step": 87500
|
| 1059 |
+
},
|
| 1060 |
+
{
|
| 1061 |
+
"epoch": 4.97,
|
| 1062 |
+
"learning_rate": 2.5142647308061696e-05,
|
| 1063 |
+
"loss": 2.2899,
|
| 1064 |
+
"step": 88000
|
| 1065 |
+
},
|
| 1066 |
+
{
|
| 1067 |
+
"epoch": 5.0,
|
| 1068 |
+
"learning_rate": 2.500141234958477e-05,
|
| 1069 |
+
"loss": 2.3,
|
| 1070 |
+
"step": 88500
|
| 1071 |
+
},
|
| 1072 |
+
{
|
| 1073 |
+
"epoch": 5.03,
|
| 1074 |
+
"learning_rate": 2.4860177391107848e-05,
|
| 1075 |
+
"loss": 2.0441,
|
| 1076 |
+
"step": 89000
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 5.06,
|
| 1080 |
+
"learning_rate": 2.4718942432630927e-05,
|
| 1081 |
+
"loss": 2.0678,
|
| 1082 |
+
"step": 89500
|
| 1083 |
+
},
|
| 1084 |
+
{
|
| 1085 |
+
"epoch": 5.08,
|
| 1086 |
+
"learning_rate": 2.4577707474154003e-05,
|
| 1087 |
+
"loss": 2.074,
|
| 1088 |
+
"step": 90000
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 5.11,
|
| 1092 |
+
"learning_rate": 2.443647251567708e-05,
|
| 1093 |
+
"loss": 2.0784,
|
| 1094 |
+
"step": 90500
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 5.14,
|
| 1098 |
+
"learning_rate": 2.429523755720016e-05,
|
| 1099 |
+
"loss": 2.0702,
|
| 1100 |
+
"step": 91000
|
| 1101 |
+
},
|
| 1102 |
+
{
|
| 1103 |
+
"epoch": 5.17,
|
| 1104 |
+
"learning_rate": 2.4154002598723238e-05,
|
| 1105 |
+
"loss": 2.0951,
|
| 1106 |
+
"step": 91500
|
| 1107 |
+
},
|
| 1108 |
+
{
|
| 1109 |
+
"epoch": 5.2,
|
| 1110 |
+
"learning_rate": 2.4012767640246314e-05,
|
| 1111 |
+
"loss": 2.0874,
|
| 1112 |
+
"step": 92000
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 5.23,
|
| 1116 |
+
"learning_rate": 2.3871532681769393e-05,
|
| 1117 |
+
"loss": 2.088,
|
| 1118 |
+
"step": 92500
|
| 1119 |
+
},
|
| 1120 |
+
{
|
| 1121 |
+
"epoch": 5.25,
|
| 1122 |
+
"learning_rate": 2.3730297723292473e-05,
|
| 1123 |
+
"loss": 2.102,
|
| 1124 |
+
"step": 93000
|
| 1125 |
+
},
|
| 1126 |
+
{
|
| 1127 |
+
"epoch": 5.28,
|
| 1128 |
+
"learning_rate": 2.358906276481555e-05,
|
| 1129 |
+
"loss": 2.0919,
|
| 1130 |
+
"step": 93500
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 5.31,
|
| 1134 |
+
"learning_rate": 2.3447827806338625e-05,
|
| 1135 |
+
"loss": 2.1272,
|
| 1136 |
+
"step": 94000
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 5.34,
|
| 1140 |
+
"learning_rate": 2.3306592847861704e-05,
|
| 1141 |
+
"loss": 2.0911,
|
| 1142 |
+
"step": 94500
|
| 1143 |
+
},
|
| 1144 |
+
{
|
| 1145 |
+
"epoch": 5.37,
|
| 1146 |
+
"learning_rate": 2.316535788938478e-05,
|
| 1147 |
+
"loss": 2.1141,
|
| 1148 |
+
"step": 95000
|
| 1149 |
+
},
|
| 1150 |
+
{
|
| 1151 |
+
"epoch": 5.4,
|
| 1152 |
+
"learning_rate": 2.302412293090786e-05,
|
| 1153 |
+
"loss": 2.1297,
|
| 1154 |
+
"step": 95500
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 5.42,
|
| 1158 |
+
"learning_rate": 2.2882887972430936e-05,
|
| 1159 |
+
"loss": 2.1072,
|
| 1160 |
+
"step": 96000
|
| 1161 |
+
},
|
| 1162 |
+
{
|
| 1163 |
+
"epoch": 5.45,
|
| 1164 |
+
"learning_rate": 2.2741653013954015e-05,
|
| 1165 |
+
"loss": 2.1144,
|
| 1166 |
+
"step": 96500
|
| 1167 |
+
},
|
| 1168 |
+
{
|
| 1169 |
+
"epoch": 5.48,
|
| 1170 |
+
"learning_rate": 2.2600418055477094e-05,
|
| 1171 |
+
"loss": 2.1087,
|
| 1172 |
+
"step": 97000
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 5.51,
|
| 1176 |
+
"learning_rate": 2.245918309700017e-05,
|
| 1177 |
+
"loss": 2.1283,
|
| 1178 |
+
"step": 97500
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 5.54,
|
| 1182 |
+
"learning_rate": 2.231794813852325e-05,
|
| 1183 |
+
"loss": 2.1053,
|
| 1184 |
+
"step": 98000
|
| 1185 |
+
},
|
| 1186 |
+
{
|
| 1187 |
+
"epoch": 5.56,
|
| 1188 |
+
"learning_rate": 2.2176713180046326e-05,
|
| 1189 |
+
"loss": 2.1368,
|
| 1190 |
+
"step": 98500
|
| 1191 |
+
},
|
| 1192 |
+
{
|
| 1193 |
+
"epoch": 5.59,
|
| 1194 |
+
"learning_rate": 2.20354782215694e-05,
|
| 1195 |
+
"loss": 2.1244,
|
| 1196 |
+
"step": 99000
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 5.62,
|
| 1200 |
+
"learning_rate": 2.189424326309248e-05,
|
| 1201 |
+
"loss": 2.1426,
|
| 1202 |
+
"step": 99500
|
| 1203 |
+
},
|
| 1204 |
+
{
|
| 1205 |
+
"epoch": 5.65,
|
| 1206 |
+
"learning_rate": 2.175300830461556e-05,
|
| 1207 |
+
"loss": 2.132,
|
| 1208 |
+
"step": 100000
|
| 1209 |
+
},
|
| 1210 |
+
{
|
| 1211 |
+
"epoch": 5.68,
|
| 1212 |
+
"learning_rate": 2.1611773346138636e-05,
|
| 1213 |
+
"loss": 2.1389,
|
| 1214 |
+
"step": 100500
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 5.71,
|
| 1218 |
+
"learning_rate": 2.1470538387661716e-05,
|
| 1219 |
+
"loss": 2.13,
|
| 1220 |
+
"step": 101000
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 5.73,
|
| 1224 |
+
"learning_rate": 2.1329303429184795e-05,
|
| 1225 |
+
"loss": 2.1177,
|
| 1226 |
+
"step": 101500
|
| 1227 |
+
},
|
| 1228 |
+
{
|
| 1229 |
+
"epoch": 5.76,
|
| 1230 |
+
"learning_rate": 2.118806847070787e-05,
|
| 1231 |
+
"loss": 2.1378,
|
| 1232 |
+
"step": 102000
|
| 1233 |
+
},
|
| 1234 |
+
{
|
| 1235 |
+
"epoch": 5.79,
|
| 1236 |
+
"learning_rate": 2.1046833512230947e-05,
|
| 1237 |
+
"loss": 2.1325,
|
| 1238 |
+
"step": 102500
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 5.82,
|
| 1242 |
+
"learning_rate": 2.0905598553754027e-05,
|
| 1243 |
+
"loss": 2.139,
|
| 1244 |
+
"step": 103000
|
| 1245 |
+
},
|
| 1246 |
+
{
|
| 1247 |
+
"epoch": 5.85,
|
| 1248 |
+
"learning_rate": 2.0764363595277103e-05,
|
| 1249 |
+
"loss": 2.1274,
|
| 1250 |
+
"step": 103500
|
| 1251 |
+
},
|
| 1252 |
+
{
|
| 1253 |
+
"epoch": 5.88,
|
| 1254 |
+
"learning_rate": 2.0623128636800182e-05,
|
| 1255 |
+
"loss": 2.1305,
|
| 1256 |
+
"step": 104000
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 5.9,
|
| 1260 |
+
"learning_rate": 2.048189367832326e-05,
|
| 1261 |
+
"loss": 2.127,
|
| 1262 |
+
"step": 104500
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 5.93,
|
| 1266 |
+
"learning_rate": 2.0340658719846337e-05,
|
| 1267 |
+
"loss": 2.1525,
|
| 1268 |
+
"step": 105000
|
| 1269 |
+
},
|
| 1270 |
+
{
|
| 1271 |
+
"epoch": 5.96,
|
| 1272 |
+
"learning_rate": 2.0199423761369417e-05,
|
| 1273 |
+
"loss": 2.1471,
|
| 1274 |
+
"step": 105500
|
| 1275 |
+
},
|
| 1276 |
+
{
|
| 1277 |
+
"epoch": 5.99,
|
| 1278 |
+
"learning_rate": 2.0058188802892493e-05,
|
| 1279 |
+
"loss": 2.1616,
|
| 1280 |
+
"step": 106000
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 6.02,
|
| 1284 |
+
"learning_rate": 1.991695384441557e-05,
|
| 1285 |
+
"loss": 2.0195,
|
| 1286 |
+
"step": 106500
|
| 1287 |
+
},
|
| 1288 |
+
{
|
| 1289 |
+
"epoch": 6.04,
|
| 1290 |
+
"learning_rate": 1.9775718885938648e-05,
|
| 1291 |
+
"loss": 1.9568,
|
| 1292 |
+
"step": 107000
|
| 1293 |
+
},
|
| 1294 |
+
{
|
| 1295 |
+
"epoch": 6.07,
|
| 1296 |
+
"learning_rate": 1.9634483927461727e-05,
|
| 1297 |
+
"loss": 1.9251,
|
| 1298 |
+
"step": 107500
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 6.1,
|
| 1302 |
+
"learning_rate": 1.9493248968984803e-05,
|
| 1303 |
+
"loss": 1.9556,
|
| 1304 |
+
"step": 108000
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 6.13,
|
| 1308 |
+
"learning_rate": 1.9352014010507883e-05,
|
| 1309 |
+
"loss": 1.9674,
|
| 1310 |
+
"step": 108500
|
| 1311 |
+
},
|
| 1312 |
+
{
|
| 1313 |
+
"epoch": 6.16,
|
| 1314 |
+
"learning_rate": 1.921077905203096e-05,
|
| 1315 |
+
"loss": 1.9599,
|
| 1316 |
+
"step": 109000
|
| 1317 |
+
},
|
| 1318 |
+
{
|
| 1319 |
+
"epoch": 6.19,
|
| 1320 |
+
"learning_rate": 1.9069544093554038e-05,
|
| 1321 |
+
"loss": 1.9753,
|
| 1322 |
+
"step": 109500
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 6.21,
|
| 1326 |
+
"learning_rate": 1.8928309135077114e-05,
|
| 1327 |
+
"loss": 1.951,
|
| 1328 |
+
"step": 110000
|
| 1329 |
+
},
|
| 1330 |
+
{
|
| 1331 |
+
"epoch": 6.24,
|
| 1332 |
+
"learning_rate": 1.878707417660019e-05,
|
| 1333 |
+
"loss": 1.9851,
|
| 1334 |
+
"step": 110500
|
| 1335 |
+
},
|
| 1336 |
+
{
|
| 1337 |
+
"epoch": 6.27,
|
| 1338 |
+
"learning_rate": 1.864583921812327e-05,
|
| 1339 |
+
"loss": 1.9678,
|
| 1340 |
+
"step": 111000
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 6.3,
|
| 1344 |
+
"learning_rate": 1.850460425964635e-05,
|
| 1345 |
+
"loss": 1.9631,
|
| 1346 |
+
"step": 111500
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 6.33,
|
| 1350 |
+
"learning_rate": 1.8363369301169425e-05,
|
| 1351 |
+
"loss": 1.9813,
|
| 1352 |
+
"step": 112000
|
| 1353 |
+
},
|
| 1354 |
+
{
|
| 1355 |
+
"epoch": 6.36,
|
| 1356 |
+
"learning_rate": 1.8222134342692504e-05,
|
| 1357 |
+
"loss": 1.9736,
|
| 1358 |
+
"step": 112500
|
| 1359 |
+
},
|
| 1360 |
+
{
|
| 1361 |
+
"epoch": 6.38,
|
| 1362 |
+
"learning_rate": 1.8080899384215584e-05,
|
| 1363 |
+
"loss": 1.9931,
|
| 1364 |
+
"step": 113000
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 6.41,
|
| 1368 |
+
"learning_rate": 1.793966442573866e-05,
|
| 1369 |
+
"loss": 1.9856,
|
| 1370 |
+
"step": 113500
|
| 1371 |
+
},
|
| 1372 |
+
{
|
| 1373 |
+
"epoch": 6.44,
|
| 1374 |
+
"learning_rate": 1.779842946726174e-05,
|
| 1375 |
+
"loss": 1.9701,
|
| 1376 |
+
"step": 114000
|
| 1377 |
+
},
|
| 1378 |
+
{
|
| 1379 |
+
"epoch": 6.47,
|
| 1380 |
+
"learning_rate": 1.7657194508784815e-05,
|
| 1381 |
+
"loss": 1.9627,
|
| 1382 |
+
"step": 114500
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 6.5,
|
| 1386 |
+
"learning_rate": 1.751595955030789e-05,
|
| 1387 |
+
"loss": 1.9749,
|
| 1388 |
+
"step": 115000
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 6.53,
|
| 1392 |
+
"learning_rate": 1.737472459183097e-05,
|
| 1393 |
+
"loss": 1.9957,
|
| 1394 |
+
"step": 115500
|
| 1395 |
+
},
|
| 1396 |
+
{
|
| 1397 |
+
"epoch": 6.55,
|
| 1398 |
+
"learning_rate": 1.723348963335405e-05,
|
| 1399 |
+
"loss": 1.9793,
|
| 1400 |
+
"step": 116000
|
| 1401 |
+
},
|
| 1402 |
+
{
|
| 1403 |
+
"epoch": 6.58,
|
| 1404 |
+
"learning_rate": 1.7092254674877126e-05,
|
| 1405 |
+
"loss": 1.9792,
|
| 1406 |
+
"step": 116500
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 6.61,
|
| 1410 |
+
"learning_rate": 1.6951019716400205e-05,
|
| 1411 |
+
"loss": 1.9809,
|
| 1412 |
+
"step": 117000
|
| 1413 |
+
},
|
| 1414 |
+
{
|
| 1415 |
+
"epoch": 6.64,
|
| 1416 |
+
"learning_rate": 1.6809784757923285e-05,
|
| 1417 |
+
"loss": 1.984,
|
| 1418 |
+
"step": 117500
|
| 1419 |
+
},
|
| 1420 |
+
{
|
| 1421 |
+
"epoch": 6.67,
|
| 1422 |
+
"learning_rate": 1.666854979944636e-05,
|
| 1423 |
+
"loss": 1.9844,
|
| 1424 |
+
"step": 118000
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 6.69,
|
| 1428 |
+
"learning_rate": 1.6527314840969437e-05,
|
| 1429 |
+
"loss": 1.9945,
|
| 1430 |
+
"step": 118500
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 6.72,
|
| 1434 |
+
"learning_rate": 1.6386079882492516e-05,
|
| 1435 |
+
"loss": 2.0097,
|
| 1436 |
+
"step": 119000
|
| 1437 |
+
},
|
| 1438 |
+
{
|
| 1439 |
+
"epoch": 6.75,
|
| 1440 |
+
"learning_rate": 1.6244844924015592e-05,
|
| 1441 |
+
"loss": 2.0085,
|
| 1442 |
+
"step": 119500
|
| 1443 |
+
},
|
| 1444 |
+
{
|
| 1445 |
+
"epoch": 6.78,
|
| 1446 |
+
"learning_rate": 1.610360996553867e-05,
|
| 1447 |
+
"loss": 1.9903,
|
| 1448 |
+
"step": 120000
|
| 1449 |
+
},
|
| 1450 |
+
{
|
| 1451 |
+
"epoch": 6.81,
|
| 1452 |
+
"learning_rate": 1.596237500706175e-05,
|
| 1453 |
+
"loss": 1.9873,
|
| 1454 |
+
"step": 120500
|
| 1455 |
+
},
|
| 1456 |
+
{
|
| 1457 |
+
"epoch": 6.84,
|
| 1458 |
+
"learning_rate": 1.5821140048584827e-05,
|
| 1459 |
+
"loss": 2.0064,
|
| 1460 |
+
"step": 121000
|
| 1461 |
+
},
|
| 1462 |
+
{
|
| 1463 |
+
"epoch": 6.86,
|
| 1464 |
+
"learning_rate": 1.5679905090107906e-05,
|
| 1465 |
+
"loss": 1.9923,
|
| 1466 |
+
"step": 121500
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 6.89,
|
| 1470 |
+
"learning_rate": 1.5538670131630982e-05,
|
| 1471 |
+
"loss": 2.0165,
|
| 1472 |
+
"step": 122000
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 6.92,
|
| 1476 |
+
"learning_rate": 1.5397435173154058e-05,
|
| 1477 |
+
"loss": 1.9874,
|
| 1478 |
+
"step": 122500
|
| 1479 |
+
},
|
| 1480 |
+
{
|
| 1481 |
+
"epoch": 6.95,
|
| 1482 |
+
"learning_rate": 1.5256200214677137e-05,
|
| 1483 |
+
"loss": 2.0166,
|
| 1484 |
+
"step": 123000
|
| 1485 |
+
},
|
| 1486 |
+
{
|
| 1487 |
+
"epoch": 6.98,
|
| 1488 |
+
"learning_rate": 1.5114965256200213e-05,
|
| 1489 |
+
"loss": 1.9818,
|
| 1490 |
+
"step": 123500
|
| 1491 |
+
},
|
| 1492 |
+
{
|
| 1493 |
+
"epoch": 7.01,
|
| 1494 |
+
"learning_rate": 1.4973730297723293e-05,
|
| 1495 |
+
"loss": 1.9813,
|
| 1496 |
+
"step": 124000
|
| 1497 |
+
},
|
| 1498 |
+
{
|
| 1499 |
+
"epoch": 7.03,
|
| 1500 |
+
"learning_rate": 1.4832495339246372e-05,
|
| 1501 |
+
"loss": 1.8291,
|
| 1502 |
+
"step": 124500
|
| 1503 |
+
},
|
| 1504 |
+
{
|
| 1505 |
+
"epoch": 7.06,
|
| 1506 |
+
"learning_rate": 1.4691260380769448e-05,
|
| 1507 |
+
"loss": 1.8125,
|
| 1508 |
+
"step": 125000
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 7.09,
|
| 1512 |
+
"learning_rate": 1.4550025422292526e-05,
|
| 1513 |
+
"loss": 1.8245,
|
| 1514 |
+
"step": 125500
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 7.12,
|
| 1518 |
+
"learning_rate": 1.4408790463815605e-05,
|
| 1519 |
+
"loss": 1.8357,
|
| 1520 |
+
"step": 126000
|
| 1521 |
+
},
|
| 1522 |
+
{
|
| 1523 |
+
"epoch": 7.15,
|
| 1524 |
+
"learning_rate": 1.4267555505338681e-05,
|
| 1525 |
+
"loss": 1.8543,
|
| 1526 |
+
"step": 126500
|
| 1527 |
+
},
|
| 1528 |
+
{
|
| 1529 |
+
"epoch": 7.17,
|
| 1530 |
+
"learning_rate": 1.412632054686176e-05,
|
| 1531 |
+
"loss": 1.8331,
|
| 1532 |
+
"step": 127000
|
| 1533 |
+
},
|
| 1534 |
+
{
|
| 1535 |
+
"epoch": 7.2,
|
| 1536 |
+
"learning_rate": 1.3985085588384838e-05,
|
| 1537 |
+
"loss": 1.8727,
|
| 1538 |
+
"step": 127500
|
| 1539 |
+
},
|
| 1540 |
+
{
|
| 1541 |
+
"epoch": 7.23,
|
| 1542 |
+
"learning_rate": 1.3843850629907914e-05,
|
| 1543 |
+
"loss": 1.8471,
|
| 1544 |
+
"step": 128000
|
| 1545 |
+
},
|
| 1546 |
+
{
|
| 1547 |
+
"epoch": 7.26,
|
| 1548 |
+
"learning_rate": 1.3702615671430994e-05,
|
| 1549 |
+
"loss": 1.8413,
|
| 1550 |
+
"step": 128500
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 7.29,
|
| 1554 |
+
"learning_rate": 1.3561380712954071e-05,
|
| 1555 |
+
"loss": 1.8588,
|
| 1556 |
+
"step": 129000
|
| 1557 |
+
},
|
| 1558 |
+
{
|
| 1559 |
+
"epoch": 7.32,
|
| 1560 |
+
"learning_rate": 1.3420145754477147e-05,
|
| 1561 |
+
"loss": 1.8544,
|
| 1562 |
+
"step": 129500
|
| 1563 |
+
},
|
| 1564 |
+
{
|
| 1565 |
+
"epoch": 7.34,
|
| 1566 |
+
"learning_rate": 1.3278910796000227e-05,
|
| 1567 |
+
"loss": 1.865,
|
| 1568 |
+
"step": 130000
|
| 1569 |
+
},
|
| 1570 |
+
{
|
| 1571 |
+
"epoch": 7.37,
|
| 1572 |
+
"learning_rate": 1.3137675837523306e-05,
|
| 1573 |
+
"loss": 1.8314,
|
| 1574 |
+
"step": 130500
|
| 1575 |
+
},
|
| 1576 |
+
{
|
| 1577 |
+
"epoch": 7.4,
|
| 1578 |
+
"learning_rate": 1.2996440879046382e-05,
|
| 1579 |
+
"loss": 1.8607,
|
| 1580 |
+
"step": 131000
|
| 1581 |
+
},
|
| 1582 |
+
{
|
| 1583 |
+
"epoch": 7.43,
|
| 1584 |
+
"learning_rate": 1.285520592056946e-05,
|
| 1585 |
+
"loss": 1.8674,
|
| 1586 |
+
"step": 131500
|
| 1587 |
+
},
|
| 1588 |
+
{
|
| 1589 |
+
"epoch": 7.46,
|
| 1590 |
+
"learning_rate": 1.271397096209254e-05,
|
| 1591 |
+
"loss": 1.8549,
|
| 1592 |
+
"step": 132000
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 7.49,
|
| 1596 |
+
"learning_rate": 1.2572736003615615e-05,
|
| 1597 |
+
"loss": 1.8412,
|
| 1598 |
+
"step": 132500
|
| 1599 |
+
},
|
| 1600 |
+
{
|
| 1601 |
+
"epoch": 7.51,
|
| 1602 |
+
"learning_rate": 1.2431501045138693e-05,
|
| 1603 |
+
"loss": 1.8871,
|
| 1604 |
+
"step": 133000
|
| 1605 |
+
},
|
| 1606 |
+
{
|
| 1607 |
+
"epoch": 7.54,
|
| 1608 |
+
"learning_rate": 1.229026608666177e-05,
|
| 1609 |
+
"loss": 1.8812,
|
| 1610 |
+
"step": 133500
|
| 1611 |
+
},
|
| 1612 |
+
{
|
| 1613 |
+
"epoch": 7.57,
|
| 1614 |
+
"learning_rate": 1.2149031128184848e-05,
|
| 1615 |
+
"loss": 1.8689,
|
| 1616 |
+
"step": 134000
|
| 1617 |
+
},
|
| 1618 |
+
{
|
| 1619 |
+
"epoch": 7.6,
|
| 1620 |
+
"learning_rate": 1.2007796169707928e-05,
|
| 1621 |
+
"loss": 1.8721,
|
| 1622 |
+
"step": 134500
|
| 1623 |
+
},
|
| 1624 |
+
{
|
| 1625 |
+
"epoch": 7.63,
|
| 1626 |
+
"learning_rate": 1.1866561211231005e-05,
|
| 1627 |
+
"loss": 1.8857,
|
| 1628 |
+
"step": 135000
|
| 1629 |
+
},
|
| 1630 |
+
{
|
| 1631 |
+
"epoch": 7.65,
|
| 1632 |
+
"learning_rate": 1.1725326252754081e-05,
|
| 1633 |
+
"loss": 1.8846,
|
| 1634 |
+
"step": 135500
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 7.68,
|
| 1638 |
+
"learning_rate": 1.158409129427716e-05,
|
| 1639 |
+
"loss": 1.8804,
|
| 1640 |
+
"step": 136000
|
| 1641 |
+
},
|
| 1642 |
+
{
|
| 1643 |
+
"epoch": 7.71,
|
| 1644 |
+
"learning_rate": 1.1442856335800238e-05,
|
| 1645 |
+
"loss": 1.892,
|
| 1646 |
+
"step": 136500
|
| 1647 |
+
},
|
| 1648 |
+
{
|
| 1649 |
+
"epoch": 7.74,
|
| 1650 |
+
"learning_rate": 1.1301621377323316e-05,
|
| 1651 |
+
"loss": 1.8921,
|
| 1652 |
+
"step": 137000
|
| 1653 |
+
},
|
| 1654 |
+
{
|
| 1655 |
+
"epoch": 7.77,
|
| 1656 |
+
"learning_rate": 1.1160386418846392e-05,
|
| 1657 |
+
"loss": 1.8881,
|
| 1658 |
+
"step": 137500
|
| 1659 |
+
},
|
| 1660 |
+
{
|
| 1661 |
+
"epoch": 7.8,
|
| 1662 |
+
"learning_rate": 1.1019151460369472e-05,
|
| 1663 |
+
"loss": 1.9009,
|
| 1664 |
+
"step": 138000
|
| 1665 |
+
},
|
| 1666 |
+
{
|
| 1667 |
+
"epoch": 7.82,
|
| 1668 |
+
"learning_rate": 1.087791650189255e-05,
|
| 1669 |
+
"loss": 1.9004,
|
| 1670 |
+
"step": 138500
|
| 1671 |
+
},
|
| 1672 |
+
{
|
| 1673 |
+
"epoch": 7.85,
|
| 1674 |
+
"learning_rate": 1.0736681543415627e-05,
|
| 1675 |
+
"loss": 1.8725,
|
| 1676 |
+
"step": 139000
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 7.88,
|
| 1680 |
+
"learning_rate": 1.0595446584938705e-05,
|
| 1681 |
+
"loss": 1.8726,
|
| 1682 |
+
"step": 139500
|
| 1683 |
+
},
|
| 1684 |
+
{
|
| 1685 |
+
"epoch": 7.91,
|
| 1686 |
+
"learning_rate": 1.0454211626461782e-05,
|
| 1687 |
+
"loss": 1.8767,
|
| 1688 |
+
"step": 140000
|
| 1689 |
+
},
|
| 1690 |
+
{
|
| 1691 |
+
"epoch": 7.94,
|
| 1692 |
+
"learning_rate": 1.031297666798486e-05,
|
| 1693 |
+
"loss": 1.858,
|
| 1694 |
+
"step": 140500
|
| 1695 |
+
},
|
| 1696 |
+
{
|
| 1697 |
+
"epoch": 7.97,
|
| 1698 |
+
"learning_rate": 1.0171741709507938e-05,
|
| 1699 |
+
"loss": 1.8896,
|
| 1700 |
+
"step": 141000
|
| 1701 |
+
},
|
| 1702 |
+
{
|
| 1703 |
+
"epoch": 7.99,
|
| 1704 |
+
"learning_rate": 1.0030506751031015e-05,
|
| 1705 |
+
"loss": 1.8879,
|
| 1706 |
+
"step": 141500
|
| 1707 |
+
},
|
| 1708 |
+
{
|
| 1709 |
+
"epoch": 8.02,
|
| 1710 |
+
"learning_rate": 9.889271792554093e-06,
|
| 1711 |
+
"loss": 1.7842,
|
| 1712 |
+
"step": 142000
|
| 1713 |
+
},
|
| 1714 |
+
{
|
| 1715 |
+
"epoch": 8.05,
|
| 1716 |
+
"learning_rate": 9.748036834077172e-06,
|
| 1717 |
+
"loss": 1.7351,
|
| 1718 |
+
"step": 142500
|
| 1719 |
+
},
|
| 1720 |
+
{
|
| 1721 |
+
"epoch": 8.08,
|
| 1722 |
+
"learning_rate": 9.606801875600248e-06,
|
| 1723 |
+
"loss": 1.7494,
|
| 1724 |
+
"step": 143000
|
| 1725 |
+
},
|
| 1726 |
+
{
|
| 1727 |
+
"epoch": 8.11,
|
| 1728 |
+
"learning_rate": 9.465566917123326e-06,
|
| 1729 |
+
"loss": 1.7528,
|
| 1730 |
+
"step": 143500
|
| 1731 |
+
},
|
| 1732 |
+
{
|
| 1733 |
+
"epoch": 8.14,
|
| 1734 |
+
"learning_rate": 9.324331958646404e-06,
|
| 1735 |
+
"loss": 1.7742,
|
| 1736 |
+
"step": 144000
|
| 1737 |
+
},
|
| 1738 |
+
{
|
| 1739 |
+
"epoch": 8.16,
|
| 1740 |
+
"learning_rate": 9.183097000169483e-06,
|
| 1741 |
+
"loss": 1.7612,
|
| 1742 |
+
"step": 144500
|
| 1743 |
+
},
|
| 1744 |
+
{
|
| 1745 |
+
"epoch": 8.19,
|
| 1746 |
+
"learning_rate": 9.041862041692561e-06,
|
| 1747 |
+
"loss": 1.7453,
|
| 1748 |
+
"step": 145000
|
| 1749 |
+
},
|
| 1750 |
+
{
|
| 1751 |
+
"epoch": 8.22,
|
| 1752 |
+
"learning_rate": 8.900627083215637e-06,
|
| 1753 |
+
"loss": 1.7342,
|
| 1754 |
+
"step": 145500
|
| 1755 |
+
},
|
| 1756 |
+
{
|
| 1757 |
+
"epoch": 8.25,
|
| 1758 |
+
"learning_rate": 8.759392124738716e-06,
|
| 1759 |
+
"loss": 1.7353,
|
| 1760 |
+
"step": 146000
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"epoch": 8.28,
|
| 1764 |
+
"learning_rate": 8.618157166261794e-06,
|
| 1765 |
+
"loss": 1.7624,
|
| 1766 |
+
"step": 146500
|
| 1767 |
+
},
|
| 1768 |
+
{
|
| 1769 |
+
"epoch": 8.3,
|
| 1770 |
+
"learning_rate": 8.476922207784872e-06,
|
| 1771 |
+
"loss": 1.7459,
|
| 1772 |
+
"step": 147000
|
| 1773 |
+
},
|
| 1774 |
+
{
|
| 1775 |
+
"epoch": 8.33,
|
| 1776 |
+
"learning_rate": 8.33568724930795e-06,
|
| 1777 |
+
"loss": 1.7687,
|
| 1778 |
+
"step": 147500
|
| 1779 |
+
},
|
| 1780 |
+
{
|
| 1781 |
+
"epoch": 8.36,
|
| 1782 |
+
"learning_rate": 8.194452290831027e-06,
|
| 1783 |
+
"loss": 1.7511,
|
| 1784 |
+
"step": 148000
|
| 1785 |
+
},
|
| 1786 |
+
{
|
| 1787 |
+
"epoch": 8.39,
|
| 1788 |
+
"learning_rate": 8.053217332354105e-06,
|
| 1789 |
+
"loss": 1.7673,
|
| 1790 |
+
"step": 148500
|
| 1791 |
+
},
|
| 1792 |
+
{
|
| 1793 |
+
"epoch": 8.42,
|
| 1794 |
+
"learning_rate": 7.911982373877182e-06,
|
| 1795 |
+
"loss": 1.7693,
|
| 1796 |
+
"step": 149000
|
| 1797 |
+
},
|
| 1798 |
+
{
|
| 1799 |
+
"epoch": 8.45,
|
| 1800 |
+
"learning_rate": 7.77074741540026e-06,
|
| 1801 |
+
"loss": 1.7681,
|
| 1802 |
+
"step": 149500
|
| 1803 |
+
},
|
| 1804 |
+
{
|
| 1805 |
+
"epoch": 8.47,
|
| 1806 |
+
"learning_rate": 7.629512456923338e-06,
|
| 1807 |
+
"loss": 1.7464,
|
| 1808 |
+
"step": 150000
|
| 1809 |
+
},
|
| 1810 |
+
{
|
| 1811 |
+
"epoch": 8.5,
|
| 1812 |
+
"learning_rate": 7.4882774984464154e-06,
|
| 1813 |
+
"loss": 1.7448,
|
| 1814 |
+
"step": 150500
|
| 1815 |
+
},
|
| 1816 |
+
{
|
| 1817 |
+
"epoch": 8.53,
|
| 1818 |
+
"learning_rate": 7.347042539969494e-06,
|
| 1819 |
+
"loss": 1.7741,
|
| 1820 |
+
"step": 151000
|
| 1821 |
+
},
|
| 1822 |
+
{
|
| 1823 |
+
"epoch": 8.56,
|
| 1824 |
+
"learning_rate": 7.205807581492572e-06,
|
| 1825 |
+
"loss": 1.7667,
|
| 1826 |
+
"step": 151500
|
| 1827 |
+
},
|
| 1828 |
+
{
|
| 1829 |
+
"epoch": 8.59,
|
| 1830 |
+
"learning_rate": 7.0645726230156485e-06,
|
| 1831 |
+
"loss": 1.753,
|
| 1832 |
+
"step": 152000
|
| 1833 |
+
},
|
| 1834 |
+
{
|
| 1835 |
+
"epoch": 8.62,
|
| 1836 |
+
"learning_rate": 6.923337664538727e-06,
|
| 1837 |
+
"loss": 1.7807,
|
| 1838 |
+
"step": 152500
|
| 1839 |
+
},
|
| 1840 |
+
{
|
| 1841 |
+
"epoch": 8.64,
|
| 1842 |
+
"learning_rate": 6.782102706061805e-06,
|
| 1843 |
+
"loss": 1.7919,
|
| 1844 |
+
"step": 153000
|
| 1845 |
+
},
|
| 1846 |
+
{
|
| 1847 |
+
"epoch": 8.67,
|
| 1848 |
+
"learning_rate": 6.640867747584882e-06,
|
| 1849 |
+
"loss": 1.763,
|
| 1850 |
+
"step": 153500
|
| 1851 |
+
},
|
| 1852 |
+
{
|
| 1853 |
+
"epoch": 8.7,
|
| 1854 |
+
"learning_rate": 6.499632789107961e-06,
|
| 1855 |
+
"loss": 1.7789,
|
| 1856 |
+
"step": 154000
|
| 1857 |
+
},
|
| 1858 |
+
{
|
| 1859 |
+
"epoch": 8.73,
|
| 1860 |
+
"learning_rate": 6.358397830631039e-06,
|
| 1861 |
+
"loss": 1.7715,
|
| 1862 |
+
"step": 154500
|
| 1863 |
+
},
|
| 1864 |
+
{
|
| 1865 |
+
"epoch": 8.76,
|
| 1866 |
+
"learning_rate": 6.2171628721541155e-06,
|
| 1867 |
+
"loss": 1.761,
|
| 1868 |
+
"step": 155000
|
| 1869 |
+
},
|
| 1870 |
+
{
|
| 1871 |
+
"epoch": 8.78,
|
| 1872 |
+
"learning_rate": 6.075927913677194e-06,
|
| 1873 |
+
"loss": 1.797,
|
| 1874 |
+
"step": 155500
|
| 1875 |
+
},
|
| 1876 |
+
{
|
| 1877 |
+
"epoch": 8.81,
|
| 1878 |
+
"learning_rate": 5.934692955200272e-06,
|
| 1879 |
+
"loss": 1.7882,
|
| 1880 |
+
"step": 156000
|
| 1881 |
+
},
|
| 1882 |
+
{
|
| 1883 |
+
"epoch": 8.84,
|
| 1884 |
+
"learning_rate": 5.793457996723349e-06,
|
| 1885 |
+
"loss": 1.777,
|
| 1886 |
+
"step": 156500
|
| 1887 |
+
},
|
| 1888 |
+
{
|
| 1889 |
+
"epoch": 8.87,
|
| 1890 |
+
"learning_rate": 5.652223038246427e-06,
|
| 1891 |
+
"loss": 1.7599,
|
| 1892 |
+
"step": 157000
|
| 1893 |
+
},
|
| 1894 |
+
{
|
| 1895 |
+
"epoch": 8.9,
|
| 1896 |
+
"learning_rate": 5.510988079769505e-06,
|
| 1897 |
+
"loss": 1.7721,
|
| 1898 |
+
"step": 157500
|
| 1899 |
+
},
|
| 1900 |
+
{
|
| 1901 |
+
"epoch": 8.93,
|
| 1902 |
+
"learning_rate": 5.3697531212925825e-06,
|
| 1903 |
+
"loss": 1.7702,
|
| 1904 |
+
"step": 158000
|
| 1905 |
+
},
|
| 1906 |
+
{
|
| 1907 |
+
"epoch": 8.95,
|
| 1908 |
+
"learning_rate": 5.22851816281566e-06,
|
| 1909 |
+
"loss": 1.7694,
|
| 1910 |
+
"step": 158500
|
| 1911 |
+
},
|
| 1912 |
+
{
|
| 1913 |
+
"epoch": 8.98,
|
| 1914 |
+
"learning_rate": 5.087283204338738e-06,
|
| 1915 |
+
"loss": 1.7717,
|
| 1916 |
+
"step": 159000
|
| 1917 |
+
},
|
| 1918 |
+
{
|
| 1919 |
+
"epoch": 9.01,
|
| 1920 |
+
"learning_rate": 4.946048245861816e-06,
|
| 1921 |
+
"loss": 1.7488,
|
| 1922 |
+
"step": 159500
|
| 1923 |
+
},
|
| 1924 |
+
{
|
| 1925 |
+
"epoch": 9.04,
|
| 1926 |
+
"learning_rate": 4.804813287384894e-06,
|
| 1927 |
+
"loss": 1.6852,
|
| 1928 |
+
"step": 160000
|
| 1929 |
+
},
|
| 1930 |
+
{
|
| 1931 |
+
"epoch": 9.07,
|
| 1932 |
+
"learning_rate": 4.663578328907972e-06,
|
| 1933 |
+
"loss": 1.6784,
|
| 1934 |
+
"step": 160500
|
| 1935 |
+
},
|
| 1936 |
+
{
|
| 1937 |
+
"epoch": 9.1,
|
| 1938 |
+
"learning_rate": 4.5223433704310494e-06,
|
| 1939 |
+
"loss": 1.6848,
|
| 1940 |
+
"step": 161000
|
| 1941 |
+
},
|
| 1942 |
+
{
|
| 1943 |
+
"epoch": 9.12,
|
| 1944 |
+
"learning_rate": 4.381108411954127e-06,
|
| 1945 |
+
"loss": 1.6925,
|
| 1946 |
+
"step": 161500
|
| 1947 |
+
},
|
| 1948 |
+
{
|
| 1949 |
+
"epoch": 9.15,
|
| 1950 |
+
"learning_rate": 4.239873453477205e-06,
|
| 1951 |
+
"loss": 1.6813,
|
| 1952 |
+
"step": 162000
|
| 1953 |
+
},
|
| 1954 |
+
{
|
| 1955 |
+
"epoch": 9.18,
|
| 1956 |
+
"learning_rate": 4.0986384950002825e-06,
|
| 1957 |
+
"loss": 1.6906,
|
| 1958 |
+
"step": 162500
|
| 1959 |
+
},
|
| 1960 |
+
{
|
| 1961 |
+
"epoch": 9.21,
|
| 1962 |
+
"learning_rate": 3.95740353652336e-06,
|
| 1963 |
+
"loss": 1.6695,
|
| 1964 |
+
"step": 163000
|
| 1965 |
+
},
|
| 1966 |
+
{
|
| 1967 |
+
"epoch": 9.24,
|
| 1968 |
+
"learning_rate": 3.816168578046439e-06,
|
| 1969 |
+
"loss": 1.6827,
|
| 1970 |
+
"step": 163500
|
| 1971 |
+
},
|
| 1972 |
+
{
|
| 1973 |
+
"epoch": 9.27,
|
| 1974 |
+
"learning_rate": 3.6749336195695156e-06,
|
| 1975 |
+
"loss": 1.6993,
|
| 1976 |
+
"step": 164000
|
| 1977 |
+
},
|
| 1978 |
+
{
|
| 1979 |
+
"epoch": 9.29,
|
| 1980 |
+
"learning_rate": 3.5336986610925937e-06,
|
| 1981 |
+
"loss": 1.6758,
|
| 1982 |
+
"step": 164500
|
| 1983 |
+
},
|
| 1984 |
+
{
|
| 1985 |
+
"epoch": 9.32,
|
| 1986 |
+
"learning_rate": 3.3924637026156718e-06,
|
| 1987 |
+
"loss": 1.6987,
|
| 1988 |
+
"step": 165000
|
| 1989 |
+
},
|
| 1990 |
+
{
|
| 1991 |
+
"epoch": 9.35,
|
| 1992 |
+
"learning_rate": 3.251228744138749e-06,
|
| 1993 |
+
"loss": 1.6765,
|
| 1994 |
+
"step": 165500
|
| 1995 |
+
},
|
| 1996 |
+
{
|
| 1997 |
+
"epoch": 9.38,
|
| 1998 |
+
"learning_rate": 3.109993785661827e-06,
|
| 1999 |
+
"loss": 1.6728,
|
| 2000 |
+
"step": 166000
|
| 2001 |
+
},
|
| 2002 |
+
{
|
| 2003 |
+
"epoch": 9.41,
|
| 2004 |
+
"learning_rate": 2.968758827184905e-06,
|
| 2005 |
+
"loss": 1.6944,
|
| 2006 |
+
"step": 166500
|
| 2007 |
+
},
|
| 2008 |
+
{
|
| 2009 |
+
"epoch": 9.43,
|
| 2010 |
+
"learning_rate": 2.8275238687079825e-06,
|
| 2011 |
+
"loss": 1.6823,
|
| 2012 |
+
"step": 167000
|
| 2013 |
+
},
|
| 2014 |
+
{
|
| 2015 |
+
"epoch": 9.46,
|
| 2016 |
+
"learning_rate": 2.6862889102310607e-06,
|
| 2017 |
+
"loss": 1.6906,
|
| 2018 |
+
"step": 167500
|
| 2019 |
+
},
|
| 2020 |
+
{
|
| 2021 |
+
"epoch": 9.49,
|
| 2022 |
+
"learning_rate": 2.5450539517541383e-06,
|
| 2023 |
+
"loss": 1.7025,
|
| 2024 |
+
"step": 168000
|
| 2025 |
+
},
|
| 2026 |
+
{
|
| 2027 |
+
"epoch": 9.52,
|
| 2028 |
+
"learning_rate": 2.403818993277216e-06,
|
| 2029 |
+
"loss": 1.71,
|
| 2030 |
+
"step": 168500
|
| 2031 |
+
},
|
| 2032 |
+
{
|
| 2033 |
+
"epoch": 9.55,
|
| 2034 |
+
"learning_rate": 2.2625840348002937e-06,
|
| 2035 |
+
"loss": 1.6926,
|
| 2036 |
+
"step": 169000
|
| 2037 |
+
},
|
| 2038 |
+
{
|
| 2039 |
+
"epoch": 9.58,
|
| 2040 |
+
"learning_rate": 2.121349076323372e-06,
|
| 2041 |
+
"loss": 1.6908,
|
| 2042 |
+
"step": 169500
|
| 2043 |
+
},
|
| 2044 |
+
{
|
| 2045 |
+
"epoch": 9.6,
|
| 2046 |
+
"learning_rate": 1.9801141178464495e-06,
|
| 2047 |
+
"loss": 1.7204,
|
| 2048 |
+
"step": 170000
|
| 2049 |
+
},
|
| 2050 |
+
{
|
| 2051 |
+
"epoch": 9.63,
|
| 2052 |
+
"learning_rate": 1.8388791593695272e-06,
|
| 2053 |
+
"loss": 1.7023,
|
| 2054 |
+
"step": 170500
|
| 2055 |
+
},
|
| 2056 |
+
{
|
| 2057 |
+
"epoch": 9.66,
|
| 2058 |
+
"learning_rate": 1.697644200892605e-06,
|
| 2059 |
+
"loss": 1.6624,
|
| 2060 |
+
"step": 171000
|
| 2061 |
+
},
|
| 2062 |
+
{
|
| 2063 |
+
"epoch": 9.69,
|
| 2064 |
+
"learning_rate": 1.5564092424156828e-06,
|
| 2065 |
+
"loss": 1.6915,
|
| 2066 |
+
"step": 171500
|
| 2067 |
+
},
|
| 2068 |
+
{
|
| 2069 |
+
"epoch": 9.72,
|
| 2070 |
+
"learning_rate": 1.4151742839387605e-06,
|
| 2071 |
+
"loss": 1.7074,
|
| 2072 |
+
"step": 172000
|
| 2073 |
+
},
|
| 2074 |
+
{
|
| 2075 |
+
"epoch": 9.75,
|
| 2076 |
+
"learning_rate": 1.2739393254618384e-06,
|
| 2077 |
+
"loss": 1.6899,
|
| 2078 |
+
"step": 172500
|
| 2079 |
+
},
|
| 2080 |
+
{
|
| 2081 |
+
"epoch": 9.77,
|
| 2082 |
+
"learning_rate": 1.132704366984916e-06,
|
| 2083 |
+
"loss": 1.7185,
|
| 2084 |
+
"step": 173000
|
| 2085 |
+
},
|
| 2086 |
+
{
|
| 2087 |
+
"epoch": 9.8,
|
| 2088 |
+
"learning_rate": 9.91469408507994e-07,
|
| 2089 |
+
"loss": 1.6943,
|
| 2090 |
+
"step": 173500
|
| 2091 |
+
},
|
| 2092 |
+
{
|
| 2093 |
+
"epoch": 9.83,
|
| 2094 |
+
"learning_rate": 8.502344500310717e-07,
|
| 2095 |
+
"loss": 1.6682,
|
| 2096 |
+
"step": 174000
|
| 2097 |
+
},
|
| 2098 |
+
{
|
| 2099 |
+
"epoch": 9.86,
|
| 2100 |
+
"learning_rate": 7.089994915541495e-07,
|
| 2101 |
+
"loss": 1.6977,
|
| 2102 |
+
"step": 174500
|
| 2103 |
+
},
|
| 2104 |
+
{
|
| 2105 |
+
"epoch": 9.89,
|
| 2106 |
+
"learning_rate": 5.677645330772273e-07,
|
| 2107 |
+
"loss": 1.6837,
|
| 2108 |
+
"step": 175000
|
| 2109 |
+
},
|
| 2110 |
+
{
|
| 2111 |
+
"epoch": 9.91,
|
| 2112 |
+
"learning_rate": 4.265295746003051e-07,
|
| 2113 |
+
"loss": 1.694,
|
| 2114 |
+
"step": 175500
|
| 2115 |
+
},
|
| 2116 |
+
{
|
| 2117 |
+
"epoch": 9.94,
|
| 2118 |
+
"learning_rate": 2.852946161233829e-07,
|
| 2119 |
+
"loss": 1.7053,
|
| 2120 |
+
"step": 176000
|
| 2121 |
+
},
|
| 2122 |
+
{
|
| 2123 |
+
"epoch": 9.97,
|
| 2124 |
+
"learning_rate": 1.4405965764646066e-07,
|
| 2125 |
+
"loss": 1.7092,
|
| 2126 |
+
"step": 176500
|
| 2127 |
+
},
|
| 2128 |
+
{
|
| 2129 |
+
"epoch": 10.0,
|
| 2130 |
+
"learning_rate": 2.824699169538444e-09,
|
| 2131 |
+
"loss": 1.6876,
|
| 2132 |
+
"step": 177000
|
| 2133 |
+
},
|
| 2134 |
+
{
|
| 2135 |
+
"epoch": 10.0,
|
| 2136 |
+
"step": 177010,
|
| 2137 |
+
"total_flos": 7.956896853814272e+16,
|
| 2138 |
+
"train_loss": 2.263988757942984,
|
| 2139 |
+
"train_runtime": 19136.7963,
|
| 2140 |
+
"train_samples_per_second": 36.998,
|
| 2141 |
+
"train_steps_per_second": 9.25
|
| 2142 |
+
}
|
| 2143 |
+
],
|
| 2144 |
+
"max_steps": 177010,
|
| 2145 |
+
"num_train_epochs": 10,
|
| 2146 |
+
"total_flos": 7.956896853814272e+16,
|
| 2147 |
+
"trial_name": null,
|
| 2148 |
+
"trial_params": null
|
| 2149 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:298809430faa5a0acd62296d56806c5c1840d875d4c25b3f752670c1bc76cd9e
|
| 3 |
+
size 3183
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|