Commit
·
6105845
1
Parent(s):
e34ed1f
initialize model repository
Browse files- README.md +55 -1
- all_results.json +15 -0
- config.json +47 -0
- eval_results.json +10 -0
- generation_config.json +5 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +15 -0
- trainer_state.json +3472 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
README.md
CHANGED
|
@@ -1,3 +1,57 @@
|
|
| 1 |
---
|
| 2 |
-
license:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
+
license: mit
|
| 3 |
+
base_model: indobenchmark/indobert-large-p2
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
metrics:
|
| 7 |
+
- accuracy
|
| 8 |
+
model-index:
|
| 9 |
+
- name: out
|
| 10 |
+
results: []
|
| 11 |
---
|
| 12 |
+
|
| 13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 14 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
+
|
| 16 |
+
# out
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [indobenchmark/indobert-large-p2](https://huggingface.co/indobenchmark/indobert-large-p2) on an unknown dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 1.6595
|
| 21 |
+
- Accuracy: 0.6803
|
| 22 |
+
|
| 23 |
+
## Model description
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Intended uses & limitations
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training and evaluation data
|
| 32 |
+
|
| 33 |
+
More information needed
|
| 34 |
+
|
| 35 |
+
## Training procedure
|
| 36 |
+
|
| 37 |
+
### Training hyperparameters
|
| 38 |
+
|
| 39 |
+
The following hyperparameters were used during training:
|
| 40 |
+
- learning_rate: 5e-05
|
| 41 |
+
- train_batch_size: 8
|
| 42 |
+
- eval_batch_size: 8
|
| 43 |
+
- seed: 42
|
| 44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
+
- lr_scheduler_type: linear
|
| 46 |
+
- num_epochs: 3.0
|
| 47 |
+
|
| 48 |
+
### Training results
|
| 49 |
+
|
| 50 |
+
|
| 51 |
+
|
| 52 |
+
### Framework versions
|
| 53 |
+
|
| 54 |
+
- Transformers 4.33.1
|
| 55 |
+
- Pytorch 2.1.2+cu121
|
| 56 |
+
- Datasets 2.16.1
|
| 57 |
+
- Tokenizers 0.13.3
|
all_results.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_accuracy": 0.680344407644915,
|
| 4 |
+
"eval_loss": 1.6595289707183838,
|
| 5 |
+
"eval_runtime": 118.3166,
|
| 6 |
+
"eval_samples": 18002,
|
| 7 |
+
"eval_samples_per_second": 152.151,
|
| 8 |
+
"eval_steps_per_second": 19.025,
|
| 9 |
+
"perplexity": 5.256834138384373,
|
| 10 |
+
"train_loss": 2.060935147813305,
|
| 11 |
+
"train_runtime": 51665.6711,
|
| 12 |
+
"train_samples": 765530,
|
| 13 |
+
"train_samples_per_second": 44.451,
|
| 14 |
+
"train_steps_per_second": 5.556
|
| 15 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "indobenchmark/indobert-large-p2",
|
| 3 |
+
"_num_labels": 5,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"BertForMaskedLM"
|
| 6 |
+
],
|
| 7 |
+
"attention_probs_dropout_prob": 0.1,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"directionality": "bidi",
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout_prob": 0.1,
|
| 12 |
+
"hidden_size": 1024,
|
| 13 |
+
"id2label": {
|
| 14 |
+
"0": "LABEL_0",
|
| 15 |
+
"1": "LABEL_1",
|
| 16 |
+
"2": "LABEL_2",
|
| 17 |
+
"3": "LABEL_3",
|
| 18 |
+
"4": "LABEL_4"
|
| 19 |
+
},
|
| 20 |
+
"initializer_range": 0.02,
|
| 21 |
+
"intermediate_size": 4096,
|
| 22 |
+
"label2id": {
|
| 23 |
+
"LABEL_0": 0,
|
| 24 |
+
"LABEL_1": 1,
|
| 25 |
+
"LABEL_2": 2,
|
| 26 |
+
"LABEL_3": 3,
|
| 27 |
+
"LABEL_4": 4
|
| 28 |
+
},
|
| 29 |
+
"layer_norm_eps": 1e-12,
|
| 30 |
+
"max_position_embeddings": 512,
|
| 31 |
+
"model_type": "bert",
|
| 32 |
+
"num_attention_heads": 16,
|
| 33 |
+
"num_hidden_layers": 24,
|
| 34 |
+
"output_past": true,
|
| 35 |
+
"pad_token_id": 0,
|
| 36 |
+
"pooler_fc_size": 768,
|
| 37 |
+
"pooler_num_attention_heads": 12,
|
| 38 |
+
"pooler_num_fc_layers": 3,
|
| 39 |
+
"pooler_size_per_head": 128,
|
| 40 |
+
"pooler_type": "first_token_transform",
|
| 41 |
+
"position_embedding_type": "absolute",
|
| 42 |
+
"torch_dtype": "float32",
|
| 43 |
+
"transformers_version": "4.33.1",
|
| 44 |
+
"type_vocab_size": 2,
|
| 45 |
+
"use_cache": true,
|
| 46 |
+
"vocab_size": 30522
|
| 47 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_accuracy": 0.680344407644915,
|
| 4 |
+
"eval_loss": 1.6595289707183838,
|
| 5 |
+
"eval_runtime": 118.3166,
|
| 6 |
+
"eval_samples": 18002,
|
| 7 |
+
"eval_samples_per_second": 152.151,
|
| 8 |
+
"eval_steps_per_second": 19.025,
|
| 9 |
+
"perplexity": 5.256834138384373
|
| 10 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"pad_token_id": 0,
|
| 4 |
+
"transformers_version": "4.33.1"
|
| 5 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:76b96f733918c43e9596b290cf75f66fe86dd7fa0d2ecaba76b0beaed204705d
|
| 3 |
+
size 1340833266
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"clean_up_tokenization_spaces": true,
|
| 3 |
+
"cls_token": "[CLS]",
|
| 4 |
+
"do_basic_tokenize": true,
|
| 5 |
+
"do_lower_case": true,
|
| 6 |
+
"mask_token": "[MASK]",
|
| 7 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 8 |
+
"never_split": null,
|
| 9 |
+
"pad_token": "[PAD]",
|
| 10 |
+
"sep_token": "[SEP]",
|
| 11 |
+
"strip_accents": null,
|
| 12 |
+
"tokenize_chinese_chars": true,
|
| 13 |
+
"tokenizer_class": "BertTokenizer",
|
| 14 |
+
"unk_token": "[UNK]"
|
| 15 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,3472 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 287076,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.01,
|
| 13 |
+
"learning_rate": 4.991291504688654e-05,
|
| 14 |
+
"loss": 5.9932,
|
| 15 |
+
"step": 500
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.01,
|
| 19 |
+
"learning_rate": 4.982583009377308e-05,
|
| 20 |
+
"loss": 4.5752,
|
| 21 |
+
"step": 1000
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.02,
|
| 25 |
+
"learning_rate": 4.973874514065962e-05,
|
| 26 |
+
"loss": 3.9864,
|
| 27 |
+
"step": 1500
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.02,
|
| 31 |
+
"learning_rate": 4.9651660187546154e-05,
|
| 32 |
+
"loss": 3.7187,
|
| 33 |
+
"step": 2000
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.03,
|
| 37 |
+
"learning_rate": 4.95645752344327e-05,
|
| 38 |
+
"loss": 3.5442,
|
| 39 |
+
"step": 2500
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.03,
|
| 43 |
+
"learning_rate": 4.947749028131923e-05,
|
| 44 |
+
"loss": 3.378,
|
| 45 |
+
"step": 3000
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.04,
|
| 49 |
+
"learning_rate": 4.939040532820577e-05,
|
| 50 |
+
"loss": 3.2869,
|
| 51 |
+
"step": 3500
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.04,
|
| 55 |
+
"learning_rate": 4.930332037509231e-05,
|
| 56 |
+
"loss": 3.2232,
|
| 57 |
+
"step": 4000
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.05,
|
| 61 |
+
"learning_rate": 4.921623542197885e-05,
|
| 62 |
+
"loss": 3.1339,
|
| 63 |
+
"step": 4500
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.05,
|
| 67 |
+
"learning_rate": 4.912915046886539e-05,
|
| 68 |
+
"loss": 3.1246,
|
| 69 |
+
"step": 5000
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.06,
|
| 73 |
+
"learning_rate": 4.904206551575193e-05,
|
| 74 |
+
"loss": 3.0439,
|
| 75 |
+
"step": 5500
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.06,
|
| 79 |
+
"learning_rate": 4.895498056263847e-05,
|
| 80 |
+
"loss": 2.9875,
|
| 81 |
+
"step": 6000
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.07,
|
| 85 |
+
"learning_rate": 4.8867895609525004e-05,
|
| 86 |
+
"loss": 2.9797,
|
| 87 |
+
"step": 6500
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.07,
|
| 91 |
+
"learning_rate": 4.878081065641154e-05,
|
| 92 |
+
"loss": 2.9155,
|
| 93 |
+
"step": 7000
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.08,
|
| 97 |
+
"learning_rate": 4.869372570329808e-05,
|
| 98 |
+
"loss": 2.9334,
|
| 99 |
+
"step": 7500
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.08,
|
| 103 |
+
"learning_rate": 4.860664075018462e-05,
|
| 104 |
+
"loss": 2.8763,
|
| 105 |
+
"step": 8000
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.09,
|
| 109 |
+
"learning_rate": 4.851955579707116e-05,
|
| 110 |
+
"loss": 2.8501,
|
| 111 |
+
"step": 8500
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.09,
|
| 115 |
+
"learning_rate": 4.84324708439577e-05,
|
| 116 |
+
"loss": 2.825,
|
| 117 |
+
"step": 9000
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.1,
|
| 121 |
+
"learning_rate": 4.834538589084424e-05,
|
| 122 |
+
"loss": 2.8267,
|
| 123 |
+
"step": 9500
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.1,
|
| 127 |
+
"learning_rate": 4.8258300937730774e-05,
|
| 128 |
+
"loss": 2.7971,
|
| 129 |
+
"step": 10000
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.11,
|
| 133 |
+
"learning_rate": 4.817121598461732e-05,
|
| 134 |
+
"loss": 2.7697,
|
| 135 |
+
"step": 10500
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.11,
|
| 139 |
+
"learning_rate": 4.808413103150385e-05,
|
| 140 |
+
"loss": 2.7516,
|
| 141 |
+
"step": 11000
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.12,
|
| 145 |
+
"learning_rate": 4.799704607839039e-05,
|
| 146 |
+
"loss": 2.721,
|
| 147 |
+
"step": 11500
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.13,
|
| 151 |
+
"learning_rate": 4.790996112527693e-05,
|
| 152 |
+
"loss": 2.6979,
|
| 153 |
+
"step": 12000
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.13,
|
| 157 |
+
"learning_rate": 4.782287617216347e-05,
|
| 158 |
+
"loss": 2.6872,
|
| 159 |
+
"step": 12500
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.14,
|
| 163 |
+
"learning_rate": 4.7735791219050005e-05,
|
| 164 |
+
"loss": 2.6909,
|
| 165 |
+
"step": 13000
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.14,
|
| 169 |
+
"learning_rate": 4.764870626593655e-05,
|
| 170 |
+
"loss": 2.664,
|
| 171 |
+
"step": 13500
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.15,
|
| 175 |
+
"learning_rate": 4.7561621312823084e-05,
|
| 176 |
+
"loss": 2.6515,
|
| 177 |
+
"step": 14000
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.15,
|
| 181 |
+
"learning_rate": 4.747453635970962e-05,
|
| 182 |
+
"loss": 2.655,
|
| 183 |
+
"step": 14500
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.16,
|
| 187 |
+
"learning_rate": 4.738745140659617e-05,
|
| 188 |
+
"loss": 2.6327,
|
| 189 |
+
"step": 15000
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.16,
|
| 193 |
+
"learning_rate": 4.73003664534827e-05,
|
| 194 |
+
"loss": 2.6356,
|
| 195 |
+
"step": 15500
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.17,
|
| 199 |
+
"learning_rate": 4.721328150036924e-05,
|
| 200 |
+
"loss": 2.6308,
|
| 201 |
+
"step": 16000
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.17,
|
| 205 |
+
"learning_rate": 4.712619654725578e-05,
|
| 206 |
+
"loss": 2.6302,
|
| 207 |
+
"step": 16500
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.18,
|
| 211 |
+
"learning_rate": 4.703911159414232e-05,
|
| 212 |
+
"loss": 2.6208,
|
| 213 |
+
"step": 17000
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.18,
|
| 217 |
+
"learning_rate": 4.6952026641028854e-05,
|
| 218 |
+
"loss": 2.6159,
|
| 219 |
+
"step": 17500
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.19,
|
| 223 |
+
"learning_rate": 4.68649416879154e-05,
|
| 224 |
+
"loss": 2.5992,
|
| 225 |
+
"step": 18000
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.19,
|
| 229 |
+
"learning_rate": 4.677785673480193e-05,
|
| 230 |
+
"loss": 2.5901,
|
| 231 |
+
"step": 18500
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.2,
|
| 235 |
+
"learning_rate": 4.669077178168847e-05,
|
| 236 |
+
"loss": 2.5911,
|
| 237 |
+
"step": 19000
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.2,
|
| 241 |
+
"learning_rate": 4.660368682857502e-05,
|
| 242 |
+
"loss": 2.5278,
|
| 243 |
+
"step": 19500
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.21,
|
| 247 |
+
"learning_rate": 4.651660187546155e-05,
|
| 248 |
+
"loss": 2.5569,
|
| 249 |
+
"step": 20000
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.21,
|
| 253 |
+
"learning_rate": 4.642951692234809e-05,
|
| 254 |
+
"loss": 2.5522,
|
| 255 |
+
"step": 20500
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.22,
|
| 259 |
+
"learning_rate": 4.634243196923463e-05,
|
| 260 |
+
"loss": 2.5293,
|
| 261 |
+
"step": 21000
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.22,
|
| 265 |
+
"learning_rate": 4.625534701612117e-05,
|
| 266 |
+
"loss": 2.5006,
|
| 267 |
+
"step": 21500
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.23,
|
| 271 |
+
"learning_rate": 4.6168262063007704e-05,
|
| 272 |
+
"loss": 2.5361,
|
| 273 |
+
"step": 22000
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.24,
|
| 277 |
+
"learning_rate": 4.608117710989425e-05,
|
| 278 |
+
"loss": 2.5116,
|
| 279 |
+
"step": 22500
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.24,
|
| 283 |
+
"learning_rate": 4.599409215678078e-05,
|
| 284 |
+
"loss": 2.4744,
|
| 285 |
+
"step": 23000
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.25,
|
| 289 |
+
"learning_rate": 4.590700720366732e-05,
|
| 290 |
+
"loss": 2.5232,
|
| 291 |
+
"step": 23500
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 0.25,
|
| 295 |
+
"learning_rate": 4.581992225055386e-05,
|
| 296 |
+
"loss": 2.4808,
|
| 297 |
+
"step": 24000
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.26,
|
| 301 |
+
"learning_rate": 4.57328372974404e-05,
|
| 302 |
+
"loss": 2.4899,
|
| 303 |
+
"step": 24500
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.26,
|
| 307 |
+
"learning_rate": 4.564575234432694e-05,
|
| 308 |
+
"loss": 2.4656,
|
| 309 |
+
"step": 25000
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.27,
|
| 313 |
+
"learning_rate": 4.555866739121348e-05,
|
| 314 |
+
"loss": 2.4816,
|
| 315 |
+
"step": 25500
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 0.27,
|
| 319 |
+
"learning_rate": 4.547158243810002e-05,
|
| 320 |
+
"loss": 2.4736,
|
| 321 |
+
"step": 26000
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.28,
|
| 325 |
+
"learning_rate": 4.538449748498655e-05,
|
| 326 |
+
"loss": 2.4767,
|
| 327 |
+
"step": 26500
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 0.28,
|
| 331 |
+
"learning_rate": 4.529741253187309e-05,
|
| 332 |
+
"loss": 2.4841,
|
| 333 |
+
"step": 27000
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 0.29,
|
| 337 |
+
"learning_rate": 4.521032757875963e-05,
|
| 338 |
+
"loss": 2.4883,
|
| 339 |
+
"step": 27500
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.29,
|
| 343 |
+
"learning_rate": 4.512324262564617e-05,
|
| 344 |
+
"loss": 2.4851,
|
| 345 |
+
"step": 28000
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.3,
|
| 349 |
+
"learning_rate": 4.503615767253271e-05,
|
| 350 |
+
"loss": 2.4384,
|
| 351 |
+
"step": 28500
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 0.3,
|
| 355 |
+
"learning_rate": 4.494907271941925e-05,
|
| 356 |
+
"loss": 2.4828,
|
| 357 |
+
"step": 29000
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 0.31,
|
| 361 |
+
"learning_rate": 4.486198776630579e-05,
|
| 362 |
+
"loss": 2.4509,
|
| 363 |
+
"step": 29500
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 0.31,
|
| 367 |
+
"learning_rate": 4.4774902813192324e-05,
|
| 368 |
+
"loss": 2.4772,
|
| 369 |
+
"step": 30000
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.32,
|
| 373 |
+
"learning_rate": 4.468781786007887e-05,
|
| 374 |
+
"loss": 2.4236,
|
| 375 |
+
"step": 30500
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.32,
|
| 379 |
+
"learning_rate": 4.46007329069654e-05,
|
| 380 |
+
"loss": 2.4359,
|
| 381 |
+
"step": 31000
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.33,
|
| 385 |
+
"learning_rate": 4.451364795385194e-05,
|
| 386 |
+
"loss": 2.4348,
|
| 387 |
+
"step": 31500
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.33,
|
| 391 |
+
"learning_rate": 4.442656300073848e-05,
|
| 392 |
+
"loss": 2.4512,
|
| 393 |
+
"step": 32000
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 0.34,
|
| 397 |
+
"learning_rate": 4.433947804762502e-05,
|
| 398 |
+
"loss": 2.4132,
|
| 399 |
+
"step": 32500
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 0.34,
|
| 403 |
+
"learning_rate": 4.425239309451156e-05,
|
| 404 |
+
"loss": 2.4363,
|
| 405 |
+
"step": 33000
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 0.35,
|
| 409 |
+
"learning_rate": 4.41653081413981e-05,
|
| 410 |
+
"loss": 2.4347,
|
| 411 |
+
"step": 33500
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 0.36,
|
| 415 |
+
"learning_rate": 4.407822318828464e-05,
|
| 416 |
+
"loss": 2.3936,
|
| 417 |
+
"step": 34000
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.36,
|
| 421 |
+
"learning_rate": 4.399113823517117e-05,
|
| 422 |
+
"loss": 2.4141,
|
| 423 |
+
"step": 34500
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.37,
|
| 427 |
+
"learning_rate": 4.390405328205772e-05,
|
| 428 |
+
"loss": 2.4454,
|
| 429 |
+
"step": 35000
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.37,
|
| 433 |
+
"learning_rate": 4.381696832894425e-05,
|
| 434 |
+
"loss": 2.398,
|
| 435 |
+
"step": 35500
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 0.38,
|
| 439 |
+
"learning_rate": 4.372988337583079e-05,
|
| 440 |
+
"loss": 2.4122,
|
| 441 |
+
"step": 36000
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 0.38,
|
| 445 |
+
"learning_rate": 4.364279842271733e-05,
|
| 446 |
+
"loss": 2.4089,
|
| 447 |
+
"step": 36500
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 0.39,
|
| 451 |
+
"learning_rate": 4.355571346960387e-05,
|
| 452 |
+
"loss": 2.3848,
|
| 453 |
+
"step": 37000
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.39,
|
| 457 |
+
"learning_rate": 4.3468628516490404e-05,
|
| 458 |
+
"loss": 2.3909,
|
| 459 |
+
"step": 37500
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.4,
|
| 463 |
+
"learning_rate": 4.338154356337695e-05,
|
| 464 |
+
"loss": 2.4077,
|
| 465 |
+
"step": 38000
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.4,
|
| 469 |
+
"learning_rate": 4.329445861026349e-05,
|
| 470 |
+
"loss": 2.3876,
|
| 471 |
+
"step": 38500
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.41,
|
| 475 |
+
"learning_rate": 4.320737365715002e-05,
|
| 476 |
+
"loss": 2.3946,
|
| 477 |
+
"step": 39000
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 0.41,
|
| 481 |
+
"learning_rate": 4.312028870403656e-05,
|
| 482 |
+
"loss": 2.3676,
|
| 483 |
+
"step": 39500
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 0.42,
|
| 487 |
+
"learning_rate": 4.30332037509231e-05,
|
| 488 |
+
"loss": 2.3862,
|
| 489 |
+
"step": 40000
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.42,
|
| 493 |
+
"learning_rate": 4.294611879780964e-05,
|
| 494 |
+
"loss": 2.3724,
|
| 495 |
+
"step": 40500
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 0.43,
|
| 499 |
+
"learning_rate": 4.285903384469618e-05,
|
| 500 |
+
"loss": 2.3735,
|
| 501 |
+
"step": 41000
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.43,
|
| 505 |
+
"learning_rate": 4.277194889158272e-05,
|
| 506 |
+
"loss": 2.3679,
|
| 507 |
+
"step": 41500
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.44,
|
| 511 |
+
"learning_rate": 4.268486393846925e-05,
|
| 512 |
+
"loss": 2.3536,
|
| 513 |
+
"step": 42000
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.44,
|
| 517 |
+
"learning_rate": 4.259777898535579e-05,
|
| 518 |
+
"loss": 2.3705,
|
| 519 |
+
"step": 42500
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 0.45,
|
| 523 |
+
"learning_rate": 4.251069403224234e-05,
|
| 524 |
+
"loss": 2.3386,
|
| 525 |
+
"step": 43000
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 0.45,
|
| 529 |
+
"learning_rate": 4.242360907912887e-05,
|
| 530 |
+
"loss": 2.3387,
|
| 531 |
+
"step": 43500
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 0.46,
|
| 535 |
+
"learning_rate": 4.233652412601541e-05,
|
| 536 |
+
"loss": 2.3283,
|
| 537 |
+
"step": 44000
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 0.47,
|
| 541 |
+
"learning_rate": 4.224943917290195e-05,
|
| 542 |
+
"loss": 2.3456,
|
| 543 |
+
"step": 44500
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 0.47,
|
| 547 |
+
"learning_rate": 4.216235421978849e-05,
|
| 548 |
+
"loss": 2.3318,
|
| 549 |
+
"step": 45000
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.48,
|
| 553 |
+
"learning_rate": 4.2075269266675024e-05,
|
| 554 |
+
"loss": 2.3478,
|
| 555 |
+
"step": 45500
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.48,
|
| 559 |
+
"learning_rate": 4.198818431356157e-05,
|
| 560 |
+
"loss": 2.3435,
|
| 561 |
+
"step": 46000
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 0.49,
|
| 565 |
+
"learning_rate": 4.19010993604481e-05,
|
| 566 |
+
"loss": 2.3509,
|
| 567 |
+
"step": 46500
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 0.49,
|
| 571 |
+
"learning_rate": 4.181401440733464e-05,
|
| 572 |
+
"loss": 2.3666,
|
| 573 |
+
"step": 47000
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 0.5,
|
| 577 |
+
"learning_rate": 4.172692945422119e-05,
|
| 578 |
+
"loss": 2.3244,
|
| 579 |
+
"step": 47500
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 0.5,
|
| 583 |
+
"learning_rate": 4.163984450110772e-05,
|
| 584 |
+
"loss": 2.3507,
|
| 585 |
+
"step": 48000
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.51,
|
| 589 |
+
"learning_rate": 4.155275954799426e-05,
|
| 590 |
+
"loss": 2.2845,
|
| 591 |
+
"step": 48500
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.51,
|
| 595 |
+
"learning_rate": 4.14656745948808e-05,
|
| 596 |
+
"loss": 2.3202,
|
| 597 |
+
"step": 49000
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.52,
|
| 601 |
+
"learning_rate": 4.137858964176734e-05,
|
| 602 |
+
"loss": 2.3355,
|
| 603 |
+
"step": 49500
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 0.52,
|
| 607 |
+
"learning_rate": 4.129150468865387e-05,
|
| 608 |
+
"loss": 2.31,
|
| 609 |
+
"step": 50000
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 0.53,
|
| 613 |
+
"learning_rate": 4.120441973554042e-05,
|
| 614 |
+
"loss": 2.2929,
|
| 615 |
+
"step": 50500
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 0.53,
|
| 619 |
+
"learning_rate": 4.111733478242695e-05,
|
| 620 |
+
"loss": 2.2909,
|
| 621 |
+
"step": 51000
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 0.54,
|
| 625 |
+
"learning_rate": 4.103024982931349e-05,
|
| 626 |
+
"loss": 2.2868,
|
| 627 |
+
"step": 51500
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 0.54,
|
| 631 |
+
"learning_rate": 4.094316487620004e-05,
|
| 632 |
+
"loss": 2.2951,
|
| 633 |
+
"step": 52000
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.55,
|
| 637 |
+
"learning_rate": 4.085607992308657e-05,
|
| 638 |
+
"loss": 2.2917,
|
| 639 |
+
"step": 52500
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.55,
|
| 643 |
+
"learning_rate": 4.076899496997311e-05,
|
| 644 |
+
"loss": 2.3179,
|
| 645 |
+
"step": 53000
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 0.56,
|
| 649 |
+
"learning_rate": 4.068191001685965e-05,
|
| 650 |
+
"loss": 2.2887,
|
| 651 |
+
"step": 53500
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 0.56,
|
| 655 |
+
"learning_rate": 4.059482506374619e-05,
|
| 656 |
+
"loss": 2.2864,
|
| 657 |
+
"step": 54000
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 0.57,
|
| 661 |
+
"learning_rate": 4.050774011063272e-05,
|
| 662 |
+
"loss": 2.2646,
|
| 663 |
+
"step": 54500
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 0.57,
|
| 667 |
+
"learning_rate": 4.042065515751927e-05,
|
| 668 |
+
"loss": 2.3021,
|
| 669 |
+
"step": 55000
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.58,
|
| 673 |
+
"learning_rate": 4.03335702044058e-05,
|
| 674 |
+
"loss": 2.2817,
|
| 675 |
+
"step": 55500
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.59,
|
| 679 |
+
"learning_rate": 4.024648525129234e-05,
|
| 680 |
+
"loss": 2.2674,
|
| 681 |
+
"step": 56000
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.59,
|
| 685 |
+
"learning_rate": 4.015940029817888e-05,
|
| 686 |
+
"loss": 2.296,
|
| 687 |
+
"step": 56500
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 0.6,
|
| 691 |
+
"learning_rate": 4.007231534506542e-05,
|
| 692 |
+
"loss": 2.2639,
|
| 693 |
+
"step": 57000
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 0.6,
|
| 697 |
+
"learning_rate": 3.998523039195196e-05,
|
| 698 |
+
"loss": 2.2967,
|
| 699 |
+
"step": 57500
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 0.61,
|
| 703 |
+
"learning_rate": 3.98981454388385e-05,
|
| 704 |
+
"loss": 2.245,
|
| 705 |
+
"step": 58000
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 0.61,
|
| 709 |
+
"learning_rate": 3.981106048572504e-05,
|
| 710 |
+
"loss": 2.2482,
|
| 711 |
+
"step": 58500
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.62,
|
| 715 |
+
"learning_rate": 3.972397553261157e-05,
|
| 716 |
+
"loss": 2.2715,
|
| 717 |
+
"step": 59000
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.62,
|
| 721 |
+
"learning_rate": 3.963689057949811e-05,
|
| 722 |
+
"loss": 2.251,
|
| 723 |
+
"step": 59500
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.63,
|
| 727 |
+
"learning_rate": 3.954980562638465e-05,
|
| 728 |
+
"loss": 2.2595,
|
| 729 |
+
"step": 60000
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 0.63,
|
| 733 |
+
"learning_rate": 3.946272067327119e-05,
|
| 734 |
+
"loss": 2.2864,
|
| 735 |
+
"step": 60500
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 0.64,
|
| 739 |
+
"learning_rate": 3.937563572015773e-05,
|
| 740 |
+
"loss": 2.2546,
|
| 741 |
+
"step": 61000
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 0.64,
|
| 745 |
+
"learning_rate": 3.928855076704427e-05,
|
| 746 |
+
"loss": 2.2461,
|
| 747 |
+
"step": 61500
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 0.65,
|
| 751 |
+
"learning_rate": 3.920146581393081e-05,
|
| 752 |
+
"loss": 2.2758,
|
| 753 |
+
"step": 62000
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 0.65,
|
| 757 |
+
"learning_rate": 3.911438086081734e-05,
|
| 758 |
+
"loss": 2.2608,
|
| 759 |
+
"step": 62500
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.66,
|
| 763 |
+
"learning_rate": 3.902729590770389e-05,
|
| 764 |
+
"loss": 2.2611,
|
| 765 |
+
"step": 63000
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.66,
|
| 769 |
+
"learning_rate": 3.894021095459042e-05,
|
| 770 |
+
"loss": 2.252,
|
| 771 |
+
"step": 63500
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 0.67,
|
| 775 |
+
"learning_rate": 3.885312600147696e-05,
|
| 776 |
+
"loss": 2.2721,
|
| 777 |
+
"step": 64000
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 0.67,
|
| 781 |
+
"learning_rate": 3.87660410483635e-05,
|
| 782 |
+
"loss": 2.2638,
|
| 783 |
+
"step": 64500
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 0.68,
|
| 787 |
+
"learning_rate": 3.867895609525004e-05,
|
| 788 |
+
"loss": 2.2493,
|
| 789 |
+
"step": 65000
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 0.68,
|
| 793 |
+
"learning_rate": 3.859187114213657e-05,
|
| 794 |
+
"loss": 2.2404,
|
| 795 |
+
"step": 65500
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 0.69,
|
| 799 |
+
"learning_rate": 3.850478618902312e-05,
|
| 800 |
+
"loss": 2.2588,
|
| 801 |
+
"step": 66000
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.69,
|
| 805 |
+
"learning_rate": 3.841770123590966e-05,
|
| 806 |
+
"loss": 2.2567,
|
| 807 |
+
"step": 66500
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.7,
|
| 811 |
+
"learning_rate": 3.833061628279619e-05,
|
| 812 |
+
"loss": 2.2333,
|
| 813 |
+
"step": 67000
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 0.71,
|
| 817 |
+
"learning_rate": 3.824353132968274e-05,
|
| 818 |
+
"loss": 2.2266,
|
| 819 |
+
"step": 67500
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 0.71,
|
| 823 |
+
"learning_rate": 3.815644637656927e-05,
|
| 824 |
+
"loss": 2.2122,
|
| 825 |
+
"step": 68000
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 0.72,
|
| 829 |
+
"learning_rate": 3.806936142345581e-05,
|
| 830 |
+
"loss": 2.2624,
|
| 831 |
+
"step": 68500
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 0.72,
|
| 835 |
+
"learning_rate": 3.798227647034235e-05,
|
| 836 |
+
"loss": 2.1801,
|
| 837 |
+
"step": 69000
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 0.73,
|
| 841 |
+
"learning_rate": 3.789519151722889e-05,
|
| 842 |
+
"loss": 2.2352,
|
| 843 |
+
"step": 69500
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 0.73,
|
| 847 |
+
"learning_rate": 3.780810656411542e-05,
|
| 848 |
+
"loss": 2.2211,
|
| 849 |
+
"step": 70000
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.74,
|
| 853 |
+
"learning_rate": 3.772102161100197e-05,
|
| 854 |
+
"loss": 2.2461,
|
| 855 |
+
"step": 70500
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 0.74,
|
| 859 |
+
"learning_rate": 3.763393665788851e-05,
|
| 860 |
+
"loss": 2.2082,
|
| 861 |
+
"step": 71000
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 0.75,
|
| 865 |
+
"learning_rate": 3.754685170477504e-05,
|
| 866 |
+
"loss": 2.2128,
|
| 867 |
+
"step": 71500
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 0.75,
|
| 871 |
+
"learning_rate": 3.745976675166159e-05,
|
| 872 |
+
"loss": 2.2142,
|
| 873 |
+
"step": 72000
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 0.76,
|
| 877 |
+
"learning_rate": 3.737268179854812e-05,
|
| 878 |
+
"loss": 2.2365,
|
| 879 |
+
"step": 72500
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 0.76,
|
| 883 |
+
"learning_rate": 3.728559684543466e-05,
|
| 884 |
+
"loss": 2.2143,
|
| 885 |
+
"step": 73000
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 0.77,
|
| 889 |
+
"learning_rate": 3.71985118923212e-05,
|
| 890 |
+
"loss": 2.2392,
|
| 891 |
+
"step": 73500
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.77,
|
| 895 |
+
"learning_rate": 3.711142693920774e-05,
|
| 896 |
+
"loss": 2.2237,
|
| 897 |
+
"step": 74000
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 0.78,
|
| 901 |
+
"learning_rate": 3.702434198609427e-05,
|
| 902 |
+
"loss": 2.1729,
|
| 903 |
+
"step": 74500
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 0.78,
|
| 907 |
+
"learning_rate": 3.693725703298082e-05,
|
| 908 |
+
"loss": 2.2192,
|
| 909 |
+
"step": 75000
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 0.79,
|
| 913 |
+
"learning_rate": 3.685017207986736e-05,
|
| 914 |
+
"loss": 2.2138,
|
| 915 |
+
"step": 75500
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 0.79,
|
| 919 |
+
"learning_rate": 3.676308712675389e-05,
|
| 920 |
+
"loss": 2.2359,
|
| 921 |
+
"step": 76000
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 0.8,
|
| 925 |
+
"learning_rate": 3.667600217364043e-05,
|
| 926 |
+
"loss": 2.1912,
|
| 927 |
+
"step": 76500
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 0.8,
|
| 931 |
+
"learning_rate": 3.658891722052697e-05,
|
| 932 |
+
"loss": 2.2056,
|
| 933 |
+
"step": 77000
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.81,
|
| 937 |
+
"learning_rate": 3.650183226741351e-05,
|
| 938 |
+
"loss": 2.1702,
|
| 939 |
+
"step": 77500
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 0.82,
|
| 943 |
+
"learning_rate": 3.641474731430004e-05,
|
| 944 |
+
"loss": 2.1527,
|
| 945 |
+
"step": 78000
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 0.82,
|
| 949 |
+
"learning_rate": 3.632766236118659e-05,
|
| 950 |
+
"loss": 2.1872,
|
| 951 |
+
"step": 78500
|
| 952 |
+
},
|
| 953 |
+
{
|
| 954 |
+
"epoch": 0.83,
|
| 955 |
+
"learning_rate": 3.624057740807312e-05,
|
| 956 |
+
"loss": 2.1901,
|
| 957 |
+
"step": 79000
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 0.83,
|
| 961 |
+
"learning_rate": 3.615349245495966e-05,
|
| 962 |
+
"loss": 2.1773,
|
| 963 |
+
"step": 79500
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 0.84,
|
| 967 |
+
"learning_rate": 3.60664075018462e-05,
|
| 968 |
+
"loss": 2.1708,
|
| 969 |
+
"step": 80000
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.84,
|
| 973 |
+
"learning_rate": 3.597932254873274e-05,
|
| 974 |
+
"loss": 2.2007,
|
| 975 |
+
"step": 80500
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.85,
|
| 979 |
+
"learning_rate": 3.589223759561928e-05,
|
| 980 |
+
"loss": 2.1826,
|
| 981 |
+
"step": 81000
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 0.85,
|
| 985 |
+
"learning_rate": 3.580515264250582e-05,
|
| 986 |
+
"loss": 2.1822,
|
| 987 |
+
"step": 81500
|
| 988 |
+
},
|
| 989 |
+
{
|
| 990 |
+
"epoch": 0.86,
|
| 991 |
+
"learning_rate": 3.571806768939236e-05,
|
| 992 |
+
"loss": 2.1832,
|
| 993 |
+
"step": 82000
|
| 994 |
+
},
|
| 995 |
+
{
|
| 996 |
+
"epoch": 0.86,
|
| 997 |
+
"learning_rate": 3.563098273627889e-05,
|
| 998 |
+
"loss": 2.1715,
|
| 999 |
+
"step": 82500
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 0.87,
|
| 1003 |
+
"learning_rate": 3.554389778316544e-05,
|
| 1004 |
+
"loss": 2.1889,
|
| 1005 |
+
"step": 83000
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 0.87,
|
| 1009 |
+
"learning_rate": 3.545681283005197e-05,
|
| 1010 |
+
"loss": 2.1901,
|
| 1011 |
+
"step": 83500
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 0.88,
|
| 1015 |
+
"learning_rate": 3.536972787693851e-05,
|
| 1016 |
+
"loss": 2.1805,
|
| 1017 |
+
"step": 84000
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.88,
|
| 1021 |
+
"learning_rate": 3.528264292382505e-05,
|
| 1022 |
+
"loss": 2.1482,
|
| 1023 |
+
"step": 84500
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 0.89,
|
| 1027 |
+
"learning_rate": 3.519555797071159e-05,
|
| 1028 |
+
"loss": 2.189,
|
| 1029 |
+
"step": 85000
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"epoch": 0.89,
|
| 1033 |
+
"learning_rate": 3.510847301759813e-05,
|
| 1034 |
+
"loss": 2.1871,
|
| 1035 |
+
"step": 85500
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 0.9,
|
| 1039 |
+
"learning_rate": 3.502138806448467e-05,
|
| 1040 |
+
"loss": 2.1471,
|
| 1041 |
+
"step": 86000
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 0.9,
|
| 1045 |
+
"learning_rate": 3.493430311137121e-05,
|
| 1046 |
+
"loss": 2.1751,
|
| 1047 |
+
"step": 86500
|
| 1048 |
+
},
|
| 1049 |
+
{
|
| 1050 |
+
"epoch": 0.91,
|
| 1051 |
+
"learning_rate": 3.484721815825774e-05,
|
| 1052 |
+
"loss": 2.1785,
|
| 1053 |
+
"step": 87000
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 0.91,
|
| 1057 |
+
"learning_rate": 3.476013320514429e-05,
|
| 1058 |
+
"loss": 2.1597,
|
| 1059 |
+
"step": 87500
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.92,
|
| 1063 |
+
"learning_rate": 3.467304825203082e-05,
|
| 1064 |
+
"loss": 2.1878,
|
| 1065 |
+
"step": 88000
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 0.92,
|
| 1069 |
+
"learning_rate": 3.458596329891736e-05,
|
| 1070 |
+
"loss": 2.168,
|
| 1071 |
+
"step": 88500
|
| 1072 |
+
},
|
| 1073 |
+
{
|
| 1074 |
+
"epoch": 0.93,
|
| 1075 |
+
"learning_rate": 3.44988783458039e-05,
|
| 1076 |
+
"loss": 2.1748,
|
| 1077 |
+
"step": 89000
|
| 1078 |
+
},
|
| 1079 |
+
{
|
| 1080 |
+
"epoch": 0.94,
|
| 1081 |
+
"learning_rate": 3.441179339269044e-05,
|
| 1082 |
+
"loss": 2.2079,
|
| 1083 |
+
"step": 89500
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 0.94,
|
| 1087 |
+
"learning_rate": 3.432470843957698e-05,
|
| 1088 |
+
"loss": 2.1503,
|
| 1089 |
+
"step": 90000
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 0.95,
|
| 1093 |
+
"learning_rate": 3.423762348646352e-05,
|
| 1094 |
+
"loss": 2.1362,
|
| 1095 |
+
"step": 90500
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 0.95,
|
| 1099 |
+
"learning_rate": 3.415053853335006e-05,
|
| 1100 |
+
"loss": 2.1269,
|
| 1101 |
+
"step": 91000
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.96,
|
| 1105 |
+
"learning_rate": 3.406345358023659e-05,
|
| 1106 |
+
"loss": 2.1609,
|
| 1107 |
+
"step": 91500
|
| 1108 |
+
},
|
| 1109 |
+
{
|
| 1110 |
+
"epoch": 0.96,
|
| 1111 |
+
"learning_rate": 3.397636862712313e-05,
|
| 1112 |
+
"loss": 2.1505,
|
| 1113 |
+
"step": 92000
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 0.97,
|
| 1117 |
+
"learning_rate": 3.388928367400967e-05,
|
| 1118 |
+
"loss": 2.1131,
|
| 1119 |
+
"step": 92500
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.97,
|
| 1123 |
+
"learning_rate": 3.380219872089621e-05,
|
| 1124 |
+
"loss": 2.1455,
|
| 1125 |
+
"step": 93000
|
| 1126 |
+
},
|
| 1127 |
+
{
|
| 1128 |
+
"epoch": 0.98,
|
| 1129 |
+
"learning_rate": 3.371511376778275e-05,
|
| 1130 |
+
"loss": 2.1455,
|
| 1131 |
+
"step": 93500
|
| 1132 |
+
},
|
| 1133 |
+
{
|
| 1134 |
+
"epoch": 0.98,
|
| 1135 |
+
"learning_rate": 3.362802881466929e-05,
|
| 1136 |
+
"loss": 2.1504,
|
| 1137 |
+
"step": 94000
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 0.99,
|
| 1141 |
+
"learning_rate": 3.354094386155583e-05,
|
| 1142 |
+
"loss": 2.1506,
|
| 1143 |
+
"step": 94500
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.99,
|
| 1147 |
+
"learning_rate": 3.345385890844236e-05,
|
| 1148 |
+
"loss": 2.1657,
|
| 1149 |
+
"step": 95000
|
| 1150 |
+
},
|
| 1151 |
+
{
|
| 1152 |
+
"epoch": 1.0,
|
| 1153 |
+
"learning_rate": 3.336677395532891e-05,
|
| 1154 |
+
"loss": 2.1465,
|
| 1155 |
+
"step": 95500
|
| 1156 |
+
},
|
| 1157 |
+
{
|
| 1158 |
+
"epoch": 1.0,
|
| 1159 |
+
"learning_rate": 3.327968900221544e-05,
|
| 1160 |
+
"loss": 2.1235,
|
| 1161 |
+
"step": 96000
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 1.01,
|
| 1165 |
+
"learning_rate": 3.319260404910198e-05,
|
| 1166 |
+
"loss": 2.101,
|
| 1167 |
+
"step": 96500
|
| 1168 |
+
},
|
| 1169 |
+
{
|
| 1170 |
+
"epoch": 1.01,
|
| 1171 |
+
"learning_rate": 3.310551909598852e-05,
|
| 1172 |
+
"loss": 2.1058,
|
| 1173 |
+
"step": 97000
|
| 1174 |
+
},
|
| 1175 |
+
{
|
| 1176 |
+
"epoch": 1.02,
|
| 1177 |
+
"learning_rate": 3.301843414287506e-05,
|
| 1178 |
+
"loss": 2.0882,
|
| 1179 |
+
"step": 97500
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 1.02,
|
| 1183 |
+
"learning_rate": 3.293134918976159e-05,
|
| 1184 |
+
"loss": 2.0591,
|
| 1185 |
+
"step": 98000
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 1.03,
|
| 1189 |
+
"learning_rate": 3.284426423664814e-05,
|
| 1190 |
+
"loss": 2.123,
|
| 1191 |
+
"step": 98500
|
| 1192 |
+
},
|
| 1193 |
+
{
|
| 1194 |
+
"epoch": 1.03,
|
| 1195 |
+
"learning_rate": 3.275717928353468e-05,
|
| 1196 |
+
"loss": 2.07,
|
| 1197 |
+
"step": 99000
|
| 1198 |
+
},
|
| 1199 |
+
{
|
| 1200 |
+
"epoch": 1.04,
|
| 1201 |
+
"learning_rate": 3.267009433042121e-05,
|
| 1202 |
+
"loss": 2.1077,
|
| 1203 |
+
"step": 99500
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 1.05,
|
| 1207 |
+
"learning_rate": 3.258300937730776e-05,
|
| 1208 |
+
"loss": 2.0761,
|
| 1209 |
+
"step": 100000
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 1.05,
|
| 1213 |
+
"learning_rate": 3.249592442419429e-05,
|
| 1214 |
+
"loss": 2.0634,
|
| 1215 |
+
"step": 100500
|
| 1216 |
+
},
|
| 1217 |
+
{
|
| 1218 |
+
"epoch": 1.06,
|
| 1219 |
+
"learning_rate": 3.240883947108083e-05,
|
| 1220 |
+
"loss": 2.1005,
|
| 1221 |
+
"step": 101000
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 1.06,
|
| 1225 |
+
"learning_rate": 3.232175451796737e-05,
|
| 1226 |
+
"loss": 2.108,
|
| 1227 |
+
"step": 101500
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 1.07,
|
| 1231 |
+
"learning_rate": 3.223466956485391e-05,
|
| 1232 |
+
"loss": 2.0803,
|
| 1233 |
+
"step": 102000
|
| 1234 |
+
},
|
| 1235 |
+
{
|
| 1236 |
+
"epoch": 1.07,
|
| 1237 |
+
"learning_rate": 3.214758461174044e-05,
|
| 1238 |
+
"loss": 2.1421,
|
| 1239 |
+
"step": 102500
|
| 1240 |
+
},
|
| 1241 |
+
{
|
| 1242 |
+
"epoch": 1.08,
|
| 1243 |
+
"learning_rate": 3.206049965862699e-05,
|
| 1244 |
+
"loss": 2.1066,
|
| 1245 |
+
"step": 103000
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 1.08,
|
| 1249 |
+
"learning_rate": 3.197341470551352e-05,
|
| 1250 |
+
"loss": 2.0903,
|
| 1251 |
+
"step": 103500
|
| 1252 |
+
},
|
| 1253 |
+
{
|
| 1254 |
+
"epoch": 1.09,
|
| 1255 |
+
"learning_rate": 3.188632975240006e-05,
|
| 1256 |
+
"loss": 2.0872,
|
| 1257 |
+
"step": 104000
|
| 1258 |
+
},
|
| 1259 |
+
{
|
| 1260 |
+
"epoch": 1.09,
|
| 1261 |
+
"learning_rate": 3.179924479928661e-05,
|
| 1262 |
+
"loss": 2.1146,
|
| 1263 |
+
"step": 104500
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 1.1,
|
| 1267 |
+
"learning_rate": 3.171215984617314e-05,
|
| 1268 |
+
"loss": 2.1223,
|
| 1269 |
+
"step": 105000
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 1.1,
|
| 1273 |
+
"learning_rate": 3.162507489305968e-05,
|
| 1274 |
+
"loss": 2.1103,
|
| 1275 |
+
"step": 105500
|
| 1276 |
+
},
|
| 1277 |
+
{
|
| 1278 |
+
"epoch": 1.11,
|
| 1279 |
+
"learning_rate": 3.153798993994622e-05,
|
| 1280 |
+
"loss": 2.0907,
|
| 1281 |
+
"step": 106000
|
| 1282 |
+
},
|
| 1283 |
+
{
|
| 1284 |
+
"epoch": 1.11,
|
| 1285 |
+
"learning_rate": 3.145090498683276e-05,
|
| 1286 |
+
"loss": 2.0805,
|
| 1287 |
+
"step": 106500
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 1.12,
|
| 1291 |
+
"learning_rate": 3.136382003371929e-05,
|
| 1292 |
+
"loss": 2.0863,
|
| 1293 |
+
"step": 107000
|
| 1294 |
+
},
|
| 1295 |
+
{
|
| 1296 |
+
"epoch": 1.12,
|
| 1297 |
+
"learning_rate": 3.127673508060584e-05,
|
| 1298 |
+
"loss": 2.0719,
|
| 1299 |
+
"step": 107500
|
| 1300 |
+
},
|
| 1301 |
+
{
|
| 1302 |
+
"epoch": 1.13,
|
| 1303 |
+
"learning_rate": 3.118965012749237e-05,
|
| 1304 |
+
"loss": 2.0808,
|
| 1305 |
+
"step": 108000
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 1.13,
|
| 1309 |
+
"learning_rate": 3.110256517437891e-05,
|
| 1310 |
+
"loss": 2.0602,
|
| 1311 |
+
"step": 108500
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 1.14,
|
| 1315 |
+
"learning_rate": 3.101548022126545e-05,
|
| 1316 |
+
"loss": 2.0837,
|
| 1317 |
+
"step": 109000
|
| 1318 |
+
},
|
| 1319 |
+
{
|
| 1320 |
+
"epoch": 1.14,
|
| 1321 |
+
"learning_rate": 3.092839526815199e-05,
|
| 1322 |
+
"loss": 2.0494,
|
| 1323 |
+
"step": 109500
|
| 1324 |
+
},
|
| 1325 |
+
{
|
| 1326 |
+
"epoch": 1.15,
|
| 1327 |
+
"learning_rate": 3.084131031503853e-05,
|
| 1328 |
+
"loss": 2.0456,
|
| 1329 |
+
"step": 110000
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 1.15,
|
| 1333 |
+
"learning_rate": 3.075422536192507e-05,
|
| 1334 |
+
"loss": 2.0486,
|
| 1335 |
+
"step": 110500
|
| 1336 |
+
},
|
| 1337 |
+
{
|
| 1338 |
+
"epoch": 1.16,
|
| 1339 |
+
"learning_rate": 3.066714040881161e-05,
|
| 1340 |
+
"loss": 2.0681,
|
| 1341 |
+
"step": 111000
|
| 1342 |
+
},
|
| 1343 |
+
{
|
| 1344 |
+
"epoch": 1.17,
|
| 1345 |
+
"learning_rate": 3.058005545569814e-05,
|
| 1346 |
+
"loss": 2.071,
|
| 1347 |
+
"step": 111500
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 1.17,
|
| 1351 |
+
"learning_rate": 3.0492970502584684e-05,
|
| 1352 |
+
"loss": 2.0743,
|
| 1353 |
+
"step": 112000
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 1.18,
|
| 1357 |
+
"learning_rate": 3.040588554947122e-05,
|
| 1358 |
+
"loss": 2.0461,
|
| 1359 |
+
"step": 112500
|
| 1360 |
+
},
|
| 1361 |
+
{
|
| 1362 |
+
"epoch": 1.18,
|
| 1363 |
+
"learning_rate": 3.031880059635776e-05,
|
| 1364 |
+
"loss": 2.0534,
|
| 1365 |
+
"step": 113000
|
| 1366 |
+
},
|
| 1367 |
+
{
|
| 1368 |
+
"epoch": 1.19,
|
| 1369 |
+
"learning_rate": 3.0231715643244303e-05,
|
| 1370 |
+
"loss": 2.0593,
|
| 1371 |
+
"step": 113500
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 1.19,
|
| 1375 |
+
"learning_rate": 3.014463069013084e-05,
|
| 1376 |
+
"loss": 2.0678,
|
| 1377 |
+
"step": 114000
|
| 1378 |
+
},
|
| 1379 |
+
{
|
| 1380 |
+
"epoch": 1.2,
|
| 1381 |
+
"learning_rate": 3.005754573701738e-05,
|
| 1382 |
+
"loss": 2.0111,
|
| 1383 |
+
"step": 114500
|
| 1384 |
+
},
|
| 1385 |
+
{
|
| 1386 |
+
"epoch": 1.2,
|
| 1387 |
+
"learning_rate": 2.9970460783903915e-05,
|
| 1388 |
+
"loss": 2.0568,
|
| 1389 |
+
"step": 115000
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 1.21,
|
| 1393 |
+
"learning_rate": 2.9883375830790454e-05,
|
| 1394 |
+
"loss": 2.0486,
|
| 1395 |
+
"step": 115500
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 1.21,
|
| 1399 |
+
"learning_rate": 2.979629087767699e-05,
|
| 1400 |
+
"loss": 2.07,
|
| 1401 |
+
"step": 116000
|
| 1402 |
+
},
|
| 1403 |
+
{
|
| 1404 |
+
"epoch": 1.22,
|
| 1405 |
+
"learning_rate": 2.9709205924563534e-05,
|
| 1406 |
+
"loss": 2.0438,
|
| 1407 |
+
"step": 116500
|
| 1408 |
+
},
|
| 1409 |
+
{
|
| 1410 |
+
"epoch": 1.22,
|
| 1411 |
+
"learning_rate": 2.9622120971450066e-05,
|
| 1412 |
+
"loss": 2.063,
|
| 1413 |
+
"step": 117000
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 1.23,
|
| 1417 |
+
"learning_rate": 2.953503601833661e-05,
|
| 1418 |
+
"loss": 2.0837,
|
| 1419 |
+
"step": 117500
|
| 1420 |
+
},
|
| 1421 |
+
{
|
| 1422 |
+
"epoch": 1.23,
|
| 1423 |
+
"learning_rate": 2.944795106522315e-05,
|
| 1424 |
+
"loss": 2.0608,
|
| 1425 |
+
"step": 118000
|
| 1426 |
+
},
|
| 1427 |
+
{
|
| 1428 |
+
"epoch": 1.24,
|
| 1429 |
+
"learning_rate": 2.9360866112109685e-05,
|
| 1430 |
+
"loss": 2.0656,
|
| 1431 |
+
"step": 118500
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 1.24,
|
| 1435 |
+
"learning_rate": 2.9273781158996228e-05,
|
| 1436 |
+
"loss": 2.0592,
|
| 1437 |
+
"step": 119000
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 1.25,
|
| 1441 |
+
"learning_rate": 2.9186696205882764e-05,
|
| 1442 |
+
"loss": 2.0735,
|
| 1443 |
+
"step": 119500
|
| 1444 |
+
},
|
| 1445 |
+
{
|
| 1446 |
+
"epoch": 1.25,
|
| 1447 |
+
"learning_rate": 2.9099611252769304e-05,
|
| 1448 |
+
"loss": 2.0314,
|
| 1449 |
+
"step": 120000
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 1.26,
|
| 1453 |
+
"learning_rate": 2.901252629965584e-05,
|
| 1454 |
+
"loss": 2.0442,
|
| 1455 |
+
"step": 120500
|
| 1456 |
+
},
|
| 1457 |
+
{
|
| 1458 |
+
"epoch": 1.26,
|
| 1459 |
+
"learning_rate": 2.892544134654238e-05,
|
| 1460 |
+
"loss": 2.0758,
|
| 1461 |
+
"step": 121000
|
| 1462 |
+
},
|
| 1463 |
+
{
|
| 1464 |
+
"epoch": 1.27,
|
| 1465 |
+
"learning_rate": 2.8838356393428916e-05,
|
| 1466 |
+
"loss": 2.0281,
|
| 1467 |
+
"step": 121500
|
| 1468 |
+
},
|
| 1469 |
+
{
|
| 1470 |
+
"epoch": 1.27,
|
| 1471 |
+
"learning_rate": 2.875127144031546e-05,
|
| 1472 |
+
"loss": 2.0676,
|
| 1473 |
+
"step": 122000
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 1.28,
|
| 1477 |
+
"learning_rate": 2.8664186487202e-05,
|
| 1478 |
+
"loss": 2.0562,
|
| 1479 |
+
"step": 122500
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 1.29,
|
| 1483 |
+
"learning_rate": 2.8577101534088535e-05,
|
| 1484 |
+
"loss": 2.0334,
|
| 1485 |
+
"step": 123000
|
| 1486 |
+
},
|
| 1487 |
+
{
|
| 1488 |
+
"epoch": 1.29,
|
| 1489 |
+
"learning_rate": 2.8490016580975078e-05,
|
| 1490 |
+
"loss": 2.04,
|
| 1491 |
+
"step": 123500
|
| 1492 |
+
},
|
| 1493 |
+
{
|
| 1494 |
+
"epoch": 1.3,
|
| 1495 |
+
"learning_rate": 2.840293162786161e-05,
|
| 1496 |
+
"loss": 2.0521,
|
| 1497 |
+
"step": 124000
|
| 1498 |
+
},
|
| 1499 |
+
{
|
| 1500 |
+
"epoch": 1.3,
|
| 1501 |
+
"learning_rate": 2.8315846674748153e-05,
|
| 1502 |
+
"loss": 2.0218,
|
| 1503 |
+
"step": 124500
|
| 1504 |
+
},
|
| 1505 |
+
{
|
| 1506 |
+
"epoch": 1.31,
|
| 1507 |
+
"learning_rate": 2.822876172163469e-05,
|
| 1508 |
+
"loss": 2.0267,
|
| 1509 |
+
"step": 125000
|
| 1510 |
+
},
|
| 1511 |
+
{
|
| 1512 |
+
"epoch": 1.31,
|
| 1513 |
+
"learning_rate": 2.814167676852123e-05,
|
| 1514 |
+
"loss": 2.0198,
|
| 1515 |
+
"step": 125500
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 1.32,
|
| 1519 |
+
"learning_rate": 2.8054591815407765e-05,
|
| 1520 |
+
"loss": 2.0346,
|
| 1521 |
+
"step": 126000
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 1.32,
|
| 1525 |
+
"learning_rate": 2.796750686229431e-05,
|
| 1526 |
+
"loss": 2.0275,
|
| 1527 |
+
"step": 126500
|
| 1528 |
+
},
|
| 1529 |
+
{
|
| 1530 |
+
"epoch": 1.33,
|
| 1531 |
+
"learning_rate": 2.788042190918084e-05,
|
| 1532 |
+
"loss": 2.0263,
|
| 1533 |
+
"step": 127000
|
| 1534 |
+
},
|
| 1535 |
+
{
|
| 1536 |
+
"epoch": 1.33,
|
| 1537 |
+
"learning_rate": 2.7793336956067384e-05,
|
| 1538 |
+
"loss": 2.0065,
|
| 1539 |
+
"step": 127500
|
| 1540 |
+
},
|
| 1541 |
+
{
|
| 1542 |
+
"epoch": 1.34,
|
| 1543 |
+
"learning_rate": 2.7706252002953924e-05,
|
| 1544 |
+
"loss": 2.0181,
|
| 1545 |
+
"step": 128000
|
| 1546 |
+
},
|
| 1547 |
+
{
|
| 1548 |
+
"epoch": 1.34,
|
| 1549 |
+
"learning_rate": 2.761916704984046e-05,
|
| 1550 |
+
"loss": 2.0094,
|
| 1551 |
+
"step": 128500
|
| 1552 |
+
},
|
| 1553 |
+
{
|
| 1554 |
+
"epoch": 1.35,
|
| 1555 |
+
"learning_rate": 2.7532082096727003e-05,
|
| 1556 |
+
"loss": 2.0347,
|
| 1557 |
+
"step": 129000
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 1.35,
|
| 1561 |
+
"learning_rate": 2.744499714361354e-05,
|
| 1562 |
+
"loss": 2.0015,
|
| 1563 |
+
"step": 129500
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 1.36,
|
| 1567 |
+
"learning_rate": 2.735791219050008e-05,
|
| 1568 |
+
"loss": 1.9911,
|
| 1569 |
+
"step": 130000
|
| 1570 |
+
},
|
| 1571 |
+
{
|
| 1572 |
+
"epoch": 1.36,
|
| 1573 |
+
"learning_rate": 2.7270827237386615e-05,
|
| 1574 |
+
"loss": 2.0332,
|
| 1575 |
+
"step": 130500
|
| 1576 |
+
},
|
| 1577 |
+
{
|
| 1578 |
+
"epoch": 1.37,
|
| 1579 |
+
"learning_rate": 2.7183742284273155e-05,
|
| 1580 |
+
"loss": 2.0351,
|
| 1581 |
+
"step": 131000
|
| 1582 |
+
},
|
| 1583 |
+
{
|
| 1584 |
+
"epoch": 1.37,
|
| 1585 |
+
"learning_rate": 2.709665733115969e-05,
|
| 1586 |
+
"loss": 2.0185,
|
| 1587 |
+
"step": 131500
|
| 1588 |
+
},
|
| 1589 |
+
{
|
| 1590 |
+
"epoch": 1.38,
|
| 1591 |
+
"learning_rate": 2.7009572378046234e-05,
|
| 1592 |
+
"loss": 2.0057,
|
| 1593 |
+
"step": 132000
|
| 1594 |
+
},
|
| 1595 |
+
{
|
| 1596 |
+
"epoch": 1.38,
|
| 1597 |
+
"learning_rate": 2.6922487424932773e-05,
|
| 1598 |
+
"loss": 2.0095,
|
| 1599 |
+
"step": 132500
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 1.39,
|
| 1603 |
+
"learning_rate": 2.683540247181931e-05,
|
| 1604 |
+
"loss": 2.0363,
|
| 1605 |
+
"step": 133000
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 1.4,
|
| 1609 |
+
"learning_rate": 2.6748317518705852e-05,
|
| 1610 |
+
"loss": 2.0017,
|
| 1611 |
+
"step": 133500
|
| 1612 |
+
},
|
| 1613 |
+
{
|
| 1614 |
+
"epoch": 1.4,
|
| 1615 |
+
"learning_rate": 2.6661232565592385e-05,
|
| 1616 |
+
"loss": 2.0176,
|
| 1617 |
+
"step": 134000
|
| 1618 |
+
},
|
| 1619 |
+
{
|
| 1620 |
+
"epoch": 1.41,
|
| 1621 |
+
"learning_rate": 2.6574147612478928e-05,
|
| 1622 |
+
"loss": 1.9988,
|
| 1623 |
+
"step": 134500
|
| 1624 |
+
},
|
| 1625 |
+
{
|
| 1626 |
+
"epoch": 1.41,
|
| 1627 |
+
"learning_rate": 2.6487062659365464e-05,
|
| 1628 |
+
"loss": 2.0006,
|
| 1629 |
+
"step": 135000
|
| 1630 |
+
},
|
| 1631 |
+
{
|
| 1632 |
+
"epoch": 1.42,
|
| 1633 |
+
"learning_rate": 2.6399977706252004e-05,
|
| 1634 |
+
"loss": 1.9966,
|
| 1635 |
+
"step": 135500
|
| 1636 |
+
},
|
| 1637 |
+
{
|
| 1638 |
+
"epoch": 1.42,
|
| 1639 |
+
"learning_rate": 2.631289275313854e-05,
|
| 1640 |
+
"loss": 1.9746,
|
| 1641 |
+
"step": 136000
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 1.43,
|
| 1645 |
+
"learning_rate": 2.6225807800025083e-05,
|
| 1646 |
+
"loss": 2.0186,
|
| 1647 |
+
"step": 136500
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 1.43,
|
| 1651 |
+
"learning_rate": 2.6138722846911623e-05,
|
| 1652 |
+
"loss": 1.9999,
|
| 1653 |
+
"step": 137000
|
| 1654 |
+
},
|
| 1655 |
+
{
|
| 1656 |
+
"epoch": 1.44,
|
| 1657 |
+
"learning_rate": 2.605163789379816e-05,
|
| 1658 |
+
"loss": 2.0056,
|
| 1659 |
+
"step": 137500
|
| 1660 |
+
},
|
| 1661 |
+
{
|
| 1662 |
+
"epoch": 1.44,
|
| 1663 |
+
"learning_rate": 2.59645529406847e-05,
|
| 1664 |
+
"loss": 1.9837,
|
| 1665 |
+
"step": 138000
|
| 1666 |
+
},
|
| 1667 |
+
{
|
| 1668 |
+
"epoch": 1.45,
|
| 1669 |
+
"learning_rate": 2.5877467987571235e-05,
|
| 1670 |
+
"loss": 1.9683,
|
| 1671 |
+
"step": 138500
|
| 1672 |
+
},
|
| 1673 |
+
{
|
| 1674 |
+
"epoch": 1.45,
|
| 1675 |
+
"learning_rate": 2.5790383034457778e-05,
|
| 1676 |
+
"loss": 2.0063,
|
| 1677 |
+
"step": 139000
|
| 1678 |
+
},
|
| 1679 |
+
{
|
| 1680 |
+
"epoch": 1.46,
|
| 1681 |
+
"learning_rate": 2.5703298081344314e-05,
|
| 1682 |
+
"loss": 1.9752,
|
| 1683 |
+
"step": 139500
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 1.46,
|
| 1687 |
+
"learning_rate": 2.5616213128230854e-05,
|
| 1688 |
+
"loss": 1.977,
|
| 1689 |
+
"step": 140000
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 1.47,
|
| 1693 |
+
"learning_rate": 2.552912817511739e-05,
|
| 1694 |
+
"loss": 1.9953,
|
| 1695 |
+
"step": 140500
|
| 1696 |
+
},
|
| 1697 |
+
{
|
| 1698 |
+
"epoch": 1.47,
|
| 1699 |
+
"learning_rate": 2.544204322200393e-05,
|
| 1700 |
+
"loss": 1.9789,
|
| 1701 |
+
"step": 141000
|
| 1702 |
+
},
|
| 1703 |
+
{
|
| 1704 |
+
"epoch": 1.48,
|
| 1705 |
+
"learning_rate": 2.5354958268890472e-05,
|
| 1706 |
+
"loss": 2.0108,
|
| 1707 |
+
"step": 141500
|
| 1708 |
+
},
|
| 1709 |
+
{
|
| 1710 |
+
"epoch": 1.48,
|
| 1711 |
+
"learning_rate": 2.526787331577701e-05,
|
| 1712 |
+
"loss": 1.9867,
|
| 1713 |
+
"step": 142000
|
| 1714 |
+
},
|
| 1715 |
+
{
|
| 1716 |
+
"epoch": 1.49,
|
| 1717 |
+
"learning_rate": 2.5180788362663548e-05,
|
| 1718 |
+
"loss": 1.993,
|
| 1719 |
+
"step": 142500
|
| 1720 |
+
},
|
| 1721 |
+
{
|
| 1722 |
+
"epoch": 1.49,
|
| 1723 |
+
"learning_rate": 2.5093703409550084e-05,
|
| 1724 |
+
"loss": 1.9721,
|
| 1725 |
+
"step": 143000
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 1.5,
|
| 1729 |
+
"learning_rate": 2.5006618456436627e-05,
|
| 1730 |
+
"loss": 1.9846,
|
| 1731 |
+
"step": 143500
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 1.5,
|
| 1735 |
+
"learning_rate": 2.4919533503323164e-05,
|
| 1736 |
+
"loss": 1.9779,
|
| 1737 |
+
"step": 144000
|
| 1738 |
+
},
|
| 1739 |
+
{
|
| 1740 |
+
"epoch": 1.51,
|
| 1741 |
+
"learning_rate": 2.4832448550209703e-05,
|
| 1742 |
+
"loss": 1.9963,
|
| 1743 |
+
"step": 144500
|
| 1744 |
+
},
|
| 1745 |
+
{
|
| 1746 |
+
"epoch": 1.52,
|
| 1747 |
+
"learning_rate": 2.4745363597096243e-05,
|
| 1748 |
+
"loss": 1.9521,
|
| 1749 |
+
"step": 145000
|
| 1750 |
+
},
|
| 1751 |
+
{
|
| 1752 |
+
"epoch": 1.52,
|
| 1753 |
+
"learning_rate": 2.465827864398278e-05,
|
| 1754 |
+
"loss": 1.9644,
|
| 1755 |
+
"step": 145500
|
| 1756 |
+
},
|
| 1757 |
+
{
|
| 1758 |
+
"epoch": 1.53,
|
| 1759 |
+
"learning_rate": 2.457119369086932e-05,
|
| 1760 |
+
"loss": 1.97,
|
| 1761 |
+
"step": 146000
|
| 1762 |
+
},
|
| 1763 |
+
{
|
| 1764 |
+
"epoch": 1.53,
|
| 1765 |
+
"learning_rate": 2.4484108737755858e-05,
|
| 1766 |
+
"loss": 1.9816,
|
| 1767 |
+
"step": 146500
|
| 1768 |
+
},
|
| 1769 |
+
{
|
| 1770 |
+
"epoch": 1.54,
|
| 1771 |
+
"learning_rate": 2.4397023784642394e-05,
|
| 1772 |
+
"loss": 1.9872,
|
| 1773 |
+
"step": 147000
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 1.54,
|
| 1777 |
+
"learning_rate": 2.4309938831528934e-05,
|
| 1778 |
+
"loss": 1.9639,
|
| 1779 |
+
"step": 147500
|
| 1780 |
+
},
|
| 1781 |
+
{
|
| 1782 |
+
"epoch": 1.55,
|
| 1783 |
+
"learning_rate": 2.4222853878415473e-05,
|
| 1784 |
+
"loss": 1.9679,
|
| 1785 |
+
"step": 148000
|
| 1786 |
+
},
|
| 1787 |
+
{
|
| 1788 |
+
"epoch": 1.55,
|
| 1789 |
+
"learning_rate": 2.4135768925302013e-05,
|
| 1790 |
+
"loss": 1.966,
|
| 1791 |
+
"step": 148500
|
| 1792 |
+
},
|
| 1793 |
+
{
|
| 1794 |
+
"epoch": 1.56,
|
| 1795 |
+
"learning_rate": 2.4048683972188553e-05,
|
| 1796 |
+
"loss": 1.9513,
|
| 1797 |
+
"step": 149000
|
| 1798 |
+
},
|
| 1799 |
+
{
|
| 1800 |
+
"epoch": 1.56,
|
| 1801 |
+
"learning_rate": 2.396159901907509e-05,
|
| 1802 |
+
"loss": 1.9739,
|
| 1803 |
+
"step": 149500
|
| 1804 |
+
},
|
| 1805 |
+
{
|
| 1806 |
+
"epoch": 1.57,
|
| 1807 |
+
"learning_rate": 2.387451406596163e-05,
|
| 1808 |
+
"loss": 1.9763,
|
| 1809 |
+
"step": 150000
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 1.57,
|
| 1813 |
+
"learning_rate": 2.3787429112848168e-05,
|
| 1814 |
+
"loss": 1.943,
|
| 1815 |
+
"step": 150500
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 1.58,
|
| 1819 |
+
"learning_rate": 2.3700344159734704e-05,
|
| 1820 |
+
"loss": 1.9663,
|
| 1821 |
+
"step": 151000
|
| 1822 |
+
},
|
| 1823 |
+
{
|
| 1824 |
+
"epoch": 1.58,
|
| 1825 |
+
"learning_rate": 2.3613259206621244e-05,
|
| 1826 |
+
"loss": 1.9904,
|
| 1827 |
+
"step": 151500
|
| 1828 |
+
},
|
| 1829 |
+
{
|
| 1830 |
+
"epoch": 1.59,
|
| 1831 |
+
"learning_rate": 2.3526174253507783e-05,
|
| 1832 |
+
"loss": 1.9495,
|
| 1833 |
+
"step": 152000
|
| 1834 |
+
},
|
| 1835 |
+
{
|
| 1836 |
+
"epoch": 1.59,
|
| 1837 |
+
"learning_rate": 2.343908930039432e-05,
|
| 1838 |
+
"loss": 1.9218,
|
| 1839 |
+
"step": 152500
|
| 1840 |
+
},
|
| 1841 |
+
{
|
| 1842 |
+
"epoch": 1.6,
|
| 1843 |
+
"learning_rate": 2.335200434728086e-05,
|
| 1844 |
+
"loss": 1.9479,
|
| 1845 |
+
"step": 153000
|
| 1846 |
+
},
|
| 1847 |
+
{
|
| 1848 |
+
"epoch": 1.6,
|
| 1849 |
+
"learning_rate": 2.32649193941674e-05,
|
| 1850 |
+
"loss": 1.9625,
|
| 1851 |
+
"step": 153500
|
| 1852 |
+
},
|
| 1853 |
+
{
|
| 1854 |
+
"epoch": 1.61,
|
| 1855 |
+
"learning_rate": 2.317783444105394e-05,
|
| 1856 |
+
"loss": 1.9426,
|
| 1857 |
+
"step": 154000
|
| 1858 |
+
},
|
| 1859 |
+
{
|
| 1860 |
+
"epoch": 1.61,
|
| 1861 |
+
"learning_rate": 2.3090749487940478e-05,
|
| 1862 |
+
"loss": 1.94,
|
| 1863 |
+
"step": 154500
|
| 1864 |
+
},
|
| 1865 |
+
{
|
| 1866 |
+
"epoch": 1.62,
|
| 1867 |
+
"learning_rate": 2.3003664534827014e-05,
|
| 1868 |
+
"loss": 1.9457,
|
| 1869 |
+
"step": 155000
|
| 1870 |
+
},
|
| 1871 |
+
{
|
| 1872 |
+
"epoch": 1.63,
|
| 1873 |
+
"learning_rate": 2.2916579581713554e-05,
|
| 1874 |
+
"loss": 1.9589,
|
| 1875 |
+
"step": 155500
|
| 1876 |
+
},
|
| 1877 |
+
{
|
| 1878 |
+
"epoch": 1.63,
|
| 1879 |
+
"learning_rate": 2.2829494628600093e-05,
|
| 1880 |
+
"loss": 1.9571,
|
| 1881 |
+
"step": 156000
|
| 1882 |
+
},
|
| 1883 |
+
{
|
| 1884 |
+
"epoch": 1.64,
|
| 1885 |
+
"learning_rate": 2.274240967548663e-05,
|
| 1886 |
+
"loss": 1.9398,
|
| 1887 |
+
"step": 156500
|
| 1888 |
+
},
|
| 1889 |
+
{
|
| 1890 |
+
"epoch": 1.64,
|
| 1891 |
+
"learning_rate": 2.265532472237317e-05,
|
| 1892 |
+
"loss": 1.9584,
|
| 1893 |
+
"step": 157000
|
| 1894 |
+
},
|
| 1895 |
+
{
|
| 1896 |
+
"epoch": 1.65,
|
| 1897 |
+
"learning_rate": 2.256823976925971e-05,
|
| 1898 |
+
"loss": 1.9351,
|
| 1899 |
+
"step": 157500
|
| 1900 |
+
},
|
| 1901 |
+
{
|
| 1902 |
+
"epoch": 1.65,
|
| 1903 |
+
"learning_rate": 2.2481154816146248e-05,
|
| 1904 |
+
"loss": 1.9612,
|
| 1905 |
+
"step": 158000
|
| 1906 |
+
},
|
| 1907 |
+
{
|
| 1908 |
+
"epoch": 1.66,
|
| 1909 |
+
"learning_rate": 2.2394069863032788e-05,
|
| 1910 |
+
"loss": 1.9398,
|
| 1911 |
+
"step": 158500
|
| 1912 |
+
},
|
| 1913 |
+
{
|
| 1914 |
+
"epoch": 1.66,
|
| 1915 |
+
"learning_rate": 2.2306984909919327e-05,
|
| 1916 |
+
"loss": 1.9425,
|
| 1917 |
+
"step": 159000
|
| 1918 |
+
},
|
| 1919 |
+
{
|
| 1920 |
+
"epoch": 1.67,
|
| 1921 |
+
"learning_rate": 2.2219899956805864e-05,
|
| 1922 |
+
"loss": 1.9639,
|
| 1923 |
+
"step": 159500
|
| 1924 |
+
},
|
| 1925 |
+
{
|
| 1926 |
+
"epoch": 1.67,
|
| 1927 |
+
"learning_rate": 2.2132815003692403e-05,
|
| 1928 |
+
"loss": 1.9281,
|
| 1929 |
+
"step": 160000
|
| 1930 |
+
},
|
| 1931 |
+
{
|
| 1932 |
+
"epoch": 1.68,
|
| 1933 |
+
"learning_rate": 2.2045730050578943e-05,
|
| 1934 |
+
"loss": 1.9447,
|
| 1935 |
+
"step": 160500
|
| 1936 |
+
},
|
| 1937 |
+
{
|
| 1938 |
+
"epoch": 1.68,
|
| 1939 |
+
"learning_rate": 2.195864509746548e-05,
|
| 1940 |
+
"loss": 1.9255,
|
| 1941 |
+
"step": 161000
|
| 1942 |
+
},
|
| 1943 |
+
{
|
| 1944 |
+
"epoch": 1.69,
|
| 1945 |
+
"learning_rate": 2.187156014435202e-05,
|
| 1946 |
+
"loss": 1.9457,
|
| 1947 |
+
"step": 161500
|
| 1948 |
+
},
|
| 1949 |
+
{
|
| 1950 |
+
"epoch": 1.69,
|
| 1951 |
+
"learning_rate": 2.1784475191238558e-05,
|
| 1952 |
+
"loss": 1.945,
|
| 1953 |
+
"step": 162000
|
| 1954 |
+
},
|
| 1955 |
+
{
|
| 1956 |
+
"epoch": 1.7,
|
| 1957 |
+
"learning_rate": 2.1697390238125098e-05,
|
| 1958 |
+
"loss": 1.9559,
|
| 1959 |
+
"step": 162500
|
| 1960 |
+
},
|
| 1961 |
+
{
|
| 1962 |
+
"epoch": 1.7,
|
| 1963 |
+
"learning_rate": 2.1610305285011637e-05,
|
| 1964 |
+
"loss": 1.9303,
|
| 1965 |
+
"step": 163000
|
| 1966 |
+
},
|
| 1967 |
+
{
|
| 1968 |
+
"epoch": 1.71,
|
| 1969 |
+
"learning_rate": 2.1523220331898174e-05,
|
| 1970 |
+
"loss": 1.9174,
|
| 1971 |
+
"step": 163500
|
| 1972 |
+
},
|
| 1973 |
+
{
|
| 1974 |
+
"epoch": 1.71,
|
| 1975 |
+
"learning_rate": 2.1436135378784713e-05,
|
| 1976 |
+
"loss": 1.9374,
|
| 1977 |
+
"step": 164000
|
| 1978 |
+
},
|
| 1979 |
+
{
|
| 1980 |
+
"epoch": 1.72,
|
| 1981 |
+
"learning_rate": 2.1349050425671253e-05,
|
| 1982 |
+
"loss": 1.941,
|
| 1983 |
+
"step": 164500
|
| 1984 |
+
},
|
| 1985 |
+
{
|
| 1986 |
+
"epoch": 1.72,
|
| 1987 |
+
"learning_rate": 2.126196547255779e-05,
|
| 1988 |
+
"loss": 1.9235,
|
| 1989 |
+
"step": 165000
|
| 1990 |
+
},
|
| 1991 |
+
{
|
| 1992 |
+
"epoch": 1.73,
|
| 1993 |
+
"learning_rate": 2.117488051944433e-05,
|
| 1994 |
+
"loss": 1.9325,
|
| 1995 |
+
"step": 165500
|
| 1996 |
+
},
|
| 1997 |
+
{
|
| 1998 |
+
"epoch": 1.73,
|
| 1999 |
+
"learning_rate": 2.1087795566330868e-05,
|
| 2000 |
+
"loss": 1.9497,
|
| 2001 |
+
"step": 166000
|
| 2002 |
+
},
|
| 2003 |
+
{
|
| 2004 |
+
"epoch": 1.74,
|
| 2005 |
+
"learning_rate": 2.1000710613217404e-05,
|
| 2006 |
+
"loss": 1.9277,
|
| 2007 |
+
"step": 166500
|
| 2008 |
+
},
|
| 2009 |
+
{
|
| 2010 |
+
"epoch": 1.75,
|
| 2011 |
+
"learning_rate": 2.0913625660103944e-05,
|
| 2012 |
+
"loss": 1.9326,
|
| 2013 |
+
"step": 167000
|
| 2014 |
+
},
|
| 2015 |
+
{
|
| 2016 |
+
"epoch": 1.75,
|
| 2017 |
+
"learning_rate": 2.0826540706990487e-05,
|
| 2018 |
+
"loss": 1.9026,
|
| 2019 |
+
"step": 167500
|
| 2020 |
+
},
|
| 2021 |
+
{
|
| 2022 |
+
"epoch": 1.76,
|
| 2023 |
+
"learning_rate": 2.0739455753877023e-05,
|
| 2024 |
+
"loss": 1.9175,
|
| 2025 |
+
"step": 168000
|
| 2026 |
+
},
|
| 2027 |
+
{
|
| 2028 |
+
"epoch": 1.76,
|
| 2029 |
+
"learning_rate": 2.0652370800763563e-05,
|
| 2030 |
+
"loss": 1.9002,
|
| 2031 |
+
"step": 168500
|
| 2032 |
+
},
|
| 2033 |
+
{
|
| 2034 |
+
"epoch": 1.77,
|
| 2035 |
+
"learning_rate": 2.0565285847650102e-05,
|
| 2036 |
+
"loss": 1.9534,
|
| 2037 |
+
"step": 169000
|
| 2038 |
+
},
|
| 2039 |
+
{
|
| 2040 |
+
"epoch": 1.77,
|
| 2041 |
+
"learning_rate": 2.047820089453664e-05,
|
| 2042 |
+
"loss": 1.9303,
|
| 2043 |
+
"step": 169500
|
| 2044 |
+
},
|
| 2045 |
+
{
|
| 2046 |
+
"epoch": 1.78,
|
| 2047 |
+
"learning_rate": 2.0391115941423178e-05,
|
| 2048 |
+
"loss": 1.9324,
|
| 2049 |
+
"step": 170000
|
| 2050 |
+
},
|
| 2051 |
+
{
|
| 2052 |
+
"epoch": 1.78,
|
| 2053 |
+
"learning_rate": 2.0304030988309718e-05,
|
| 2054 |
+
"loss": 1.9322,
|
| 2055 |
+
"step": 170500
|
| 2056 |
+
},
|
| 2057 |
+
{
|
| 2058 |
+
"epoch": 1.79,
|
| 2059 |
+
"learning_rate": 2.0216946035196254e-05,
|
| 2060 |
+
"loss": 1.9185,
|
| 2061 |
+
"step": 171000
|
| 2062 |
+
},
|
| 2063 |
+
{
|
| 2064 |
+
"epoch": 1.79,
|
| 2065 |
+
"learning_rate": 2.0129861082082793e-05,
|
| 2066 |
+
"loss": 1.9078,
|
| 2067 |
+
"step": 171500
|
| 2068 |
+
},
|
| 2069 |
+
{
|
| 2070 |
+
"epoch": 1.8,
|
| 2071 |
+
"learning_rate": 2.0042776128969333e-05,
|
| 2072 |
+
"loss": 1.8907,
|
| 2073 |
+
"step": 172000
|
| 2074 |
+
},
|
| 2075 |
+
{
|
| 2076 |
+
"epoch": 1.8,
|
| 2077 |
+
"learning_rate": 1.9955691175855873e-05,
|
| 2078 |
+
"loss": 1.8814,
|
| 2079 |
+
"step": 172500
|
| 2080 |
+
},
|
| 2081 |
+
{
|
| 2082 |
+
"epoch": 1.81,
|
| 2083 |
+
"learning_rate": 1.9868606222742412e-05,
|
| 2084 |
+
"loss": 1.9388,
|
| 2085 |
+
"step": 173000
|
| 2086 |
+
},
|
| 2087 |
+
{
|
| 2088 |
+
"epoch": 1.81,
|
| 2089 |
+
"learning_rate": 1.978152126962895e-05,
|
| 2090 |
+
"loss": 1.898,
|
| 2091 |
+
"step": 173500
|
| 2092 |
+
},
|
| 2093 |
+
{
|
| 2094 |
+
"epoch": 1.82,
|
| 2095 |
+
"learning_rate": 1.9694436316515488e-05,
|
| 2096 |
+
"loss": 1.9195,
|
| 2097 |
+
"step": 174000
|
| 2098 |
+
},
|
| 2099 |
+
{
|
| 2100 |
+
"epoch": 1.82,
|
| 2101 |
+
"learning_rate": 1.9607351363402028e-05,
|
| 2102 |
+
"loss": 1.911,
|
| 2103 |
+
"step": 174500
|
| 2104 |
+
},
|
| 2105 |
+
{
|
| 2106 |
+
"epoch": 1.83,
|
| 2107 |
+
"learning_rate": 1.9520266410288564e-05,
|
| 2108 |
+
"loss": 1.8908,
|
| 2109 |
+
"step": 175000
|
| 2110 |
+
},
|
| 2111 |
+
{
|
| 2112 |
+
"epoch": 1.83,
|
| 2113 |
+
"learning_rate": 1.9433181457175103e-05,
|
| 2114 |
+
"loss": 1.8934,
|
| 2115 |
+
"step": 175500
|
| 2116 |
+
},
|
| 2117 |
+
{
|
| 2118 |
+
"epoch": 1.84,
|
| 2119 |
+
"learning_rate": 1.9346096504061643e-05,
|
| 2120 |
+
"loss": 1.8823,
|
| 2121 |
+
"step": 176000
|
| 2122 |
+
},
|
| 2123 |
+
{
|
| 2124 |
+
"epoch": 1.84,
|
| 2125 |
+
"learning_rate": 1.925901155094818e-05,
|
| 2126 |
+
"loss": 1.8952,
|
| 2127 |
+
"step": 176500
|
| 2128 |
+
},
|
| 2129 |
+
{
|
| 2130 |
+
"epoch": 1.85,
|
| 2131 |
+
"learning_rate": 1.9171926597834722e-05,
|
| 2132 |
+
"loss": 1.917,
|
| 2133 |
+
"step": 177000
|
| 2134 |
+
},
|
| 2135 |
+
{
|
| 2136 |
+
"epoch": 1.85,
|
| 2137 |
+
"learning_rate": 1.9084841644721262e-05,
|
| 2138 |
+
"loss": 1.9191,
|
| 2139 |
+
"step": 177500
|
| 2140 |
+
},
|
| 2141 |
+
{
|
| 2142 |
+
"epoch": 1.86,
|
| 2143 |
+
"learning_rate": 1.8997756691607798e-05,
|
| 2144 |
+
"loss": 1.8784,
|
| 2145 |
+
"step": 178000
|
| 2146 |
+
},
|
| 2147 |
+
{
|
| 2148 |
+
"epoch": 1.87,
|
| 2149 |
+
"learning_rate": 1.8910671738494338e-05,
|
| 2150 |
+
"loss": 1.8598,
|
| 2151 |
+
"step": 178500
|
| 2152 |
+
},
|
| 2153 |
+
{
|
| 2154 |
+
"epoch": 1.87,
|
| 2155 |
+
"learning_rate": 1.8823586785380877e-05,
|
| 2156 |
+
"loss": 1.9008,
|
| 2157 |
+
"step": 179000
|
| 2158 |
+
},
|
| 2159 |
+
{
|
| 2160 |
+
"epoch": 1.88,
|
| 2161 |
+
"learning_rate": 1.8736501832267413e-05,
|
| 2162 |
+
"loss": 1.9135,
|
| 2163 |
+
"step": 179500
|
| 2164 |
+
},
|
| 2165 |
+
{
|
| 2166 |
+
"epoch": 1.88,
|
| 2167 |
+
"learning_rate": 1.8649416879153953e-05,
|
| 2168 |
+
"loss": 1.8975,
|
| 2169 |
+
"step": 180000
|
| 2170 |
+
},
|
| 2171 |
+
{
|
| 2172 |
+
"epoch": 1.89,
|
| 2173 |
+
"learning_rate": 1.8562331926040493e-05,
|
| 2174 |
+
"loss": 1.8977,
|
| 2175 |
+
"step": 180500
|
| 2176 |
+
},
|
| 2177 |
+
{
|
| 2178 |
+
"epoch": 1.89,
|
| 2179 |
+
"learning_rate": 1.847524697292703e-05,
|
| 2180 |
+
"loss": 1.9034,
|
| 2181 |
+
"step": 181000
|
| 2182 |
+
},
|
| 2183 |
+
{
|
| 2184 |
+
"epoch": 1.9,
|
| 2185 |
+
"learning_rate": 1.8388162019813572e-05,
|
| 2186 |
+
"loss": 1.8742,
|
| 2187 |
+
"step": 181500
|
| 2188 |
+
},
|
| 2189 |
+
{
|
| 2190 |
+
"epoch": 1.9,
|
| 2191 |
+
"learning_rate": 1.8301077066700108e-05,
|
| 2192 |
+
"loss": 1.9012,
|
| 2193 |
+
"step": 182000
|
| 2194 |
+
},
|
| 2195 |
+
{
|
| 2196 |
+
"epoch": 1.91,
|
| 2197 |
+
"learning_rate": 1.8213992113586647e-05,
|
| 2198 |
+
"loss": 1.8909,
|
| 2199 |
+
"step": 182500
|
| 2200 |
+
},
|
| 2201 |
+
{
|
| 2202 |
+
"epoch": 1.91,
|
| 2203 |
+
"learning_rate": 1.8126907160473187e-05,
|
| 2204 |
+
"loss": 1.8979,
|
| 2205 |
+
"step": 183000
|
| 2206 |
+
},
|
| 2207 |
+
{
|
| 2208 |
+
"epoch": 1.92,
|
| 2209 |
+
"learning_rate": 1.8039822207359723e-05,
|
| 2210 |
+
"loss": 1.8946,
|
| 2211 |
+
"step": 183500
|
| 2212 |
+
},
|
| 2213 |
+
{
|
| 2214 |
+
"epoch": 1.92,
|
| 2215 |
+
"learning_rate": 1.7952737254246263e-05,
|
| 2216 |
+
"loss": 1.9101,
|
| 2217 |
+
"step": 184000
|
| 2218 |
+
},
|
| 2219 |
+
{
|
| 2220 |
+
"epoch": 1.93,
|
| 2221 |
+
"learning_rate": 1.7865652301132802e-05,
|
| 2222 |
+
"loss": 1.8848,
|
| 2223 |
+
"step": 184500
|
| 2224 |
+
},
|
| 2225 |
+
{
|
| 2226 |
+
"epoch": 1.93,
|
| 2227 |
+
"learning_rate": 1.777856734801934e-05,
|
| 2228 |
+
"loss": 1.8875,
|
| 2229 |
+
"step": 185000
|
| 2230 |
+
},
|
| 2231 |
+
{
|
| 2232 |
+
"epoch": 1.94,
|
| 2233 |
+
"learning_rate": 1.7691482394905878e-05,
|
| 2234 |
+
"loss": 1.8915,
|
| 2235 |
+
"step": 185500
|
| 2236 |
+
},
|
| 2237 |
+
{
|
| 2238 |
+
"epoch": 1.94,
|
| 2239 |
+
"learning_rate": 1.760439744179242e-05,
|
| 2240 |
+
"loss": 1.9019,
|
| 2241 |
+
"step": 186000
|
| 2242 |
+
},
|
| 2243 |
+
{
|
| 2244 |
+
"epoch": 1.95,
|
| 2245 |
+
"learning_rate": 1.7517312488678957e-05,
|
| 2246 |
+
"loss": 1.8698,
|
| 2247 |
+
"step": 186500
|
| 2248 |
+
},
|
| 2249 |
+
{
|
| 2250 |
+
"epoch": 1.95,
|
| 2251 |
+
"learning_rate": 1.7430227535565497e-05,
|
| 2252 |
+
"loss": 1.887,
|
| 2253 |
+
"step": 187000
|
| 2254 |
+
},
|
| 2255 |
+
{
|
| 2256 |
+
"epoch": 1.96,
|
| 2257 |
+
"learning_rate": 1.7343142582452037e-05,
|
| 2258 |
+
"loss": 1.8691,
|
| 2259 |
+
"step": 187500
|
| 2260 |
+
},
|
| 2261 |
+
{
|
| 2262 |
+
"epoch": 1.96,
|
| 2263 |
+
"learning_rate": 1.7256057629338573e-05,
|
| 2264 |
+
"loss": 1.8669,
|
| 2265 |
+
"step": 188000
|
| 2266 |
+
},
|
| 2267 |
+
{
|
| 2268 |
+
"epoch": 1.97,
|
| 2269 |
+
"learning_rate": 1.7168972676225112e-05,
|
| 2270 |
+
"loss": 1.9039,
|
| 2271 |
+
"step": 188500
|
| 2272 |
+
},
|
| 2273 |
+
{
|
| 2274 |
+
"epoch": 1.98,
|
| 2275 |
+
"learning_rate": 1.7081887723111652e-05,
|
| 2276 |
+
"loss": 1.893,
|
| 2277 |
+
"step": 189000
|
| 2278 |
+
},
|
| 2279 |
+
{
|
| 2280 |
+
"epoch": 1.98,
|
| 2281 |
+
"learning_rate": 1.6994802769998188e-05,
|
| 2282 |
+
"loss": 1.8628,
|
| 2283 |
+
"step": 189500
|
| 2284 |
+
},
|
| 2285 |
+
{
|
| 2286 |
+
"epoch": 1.99,
|
| 2287 |
+
"learning_rate": 1.6907717816884728e-05,
|
| 2288 |
+
"loss": 1.8672,
|
| 2289 |
+
"step": 190000
|
| 2290 |
+
},
|
| 2291 |
+
{
|
| 2292 |
+
"epoch": 1.99,
|
| 2293 |
+
"learning_rate": 1.6820632863771267e-05,
|
| 2294 |
+
"loss": 1.8714,
|
| 2295 |
+
"step": 190500
|
| 2296 |
+
},
|
| 2297 |
+
{
|
| 2298 |
+
"epoch": 2.0,
|
| 2299 |
+
"learning_rate": 1.6733547910657807e-05,
|
| 2300 |
+
"loss": 1.8499,
|
| 2301 |
+
"step": 191000
|
| 2302 |
+
},
|
| 2303 |
+
{
|
| 2304 |
+
"epoch": 2.0,
|
| 2305 |
+
"learning_rate": 1.6646462957544347e-05,
|
| 2306 |
+
"loss": 1.8405,
|
| 2307 |
+
"step": 191500
|
| 2308 |
+
},
|
| 2309 |
+
{
|
| 2310 |
+
"epoch": 2.01,
|
| 2311 |
+
"learning_rate": 1.6559378004430883e-05,
|
| 2312 |
+
"loss": 1.8392,
|
| 2313 |
+
"step": 192000
|
| 2314 |
+
},
|
| 2315 |
+
{
|
| 2316 |
+
"epoch": 2.01,
|
| 2317 |
+
"learning_rate": 1.6472293051317422e-05,
|
| 2318 |
+
"loss": 1.8528,
|
| 2319 |
+
"step": 192500
|
| 2320 |
+
},
|
| 2321 |
+
{
|
| 2322 |
+
"epoch": 2.02,
|
| 2323 |
+
"learning_rate": 1.6385208098203962e-05,
|
| 2324 |
+
"loss": 1.8385,
|
| 2325 |
+
"step": 193000
|
| 2326 |
+
},
|
| 2327 |
+
{
|
| 2328 |
+
"epoch": 2.02,
|
| 2329 |
+
"learning_rate": 1.6298123145090498e-05,
|
| 2330 |
+
"loss": 1.8326,
|
| 2331 |
+
"step": 193500
|
| 2332 |
+
},
|
| 2333 |
+
{
|
| 2334 |
+
"epoch": 2.03,
|
| 2335 |
+
"learning_rate": 1.6211038191977038e-05,
|
| 2336 |
+
"loss": 1.8424,
|
| 2337 |
+
"step": 194000
|
| 2338 |
+
},
|
| 2339 |
+
{
|
| 2340 |
+
"epoch": 2.03,
|
| 2341 |
+
"learning_rate": 1.6123953238863577e-05,
|
| 2342 |
+
"loss": 1.8147,
|
| 2343 |
+
"step": 194500
|
| 2344 |
+
},
|
| 2345 |
+
{
|
| 2346 |
+
"epoch": 2.04,
|
| 2347 |
+
"learning_rate": 1.6036868285750114e-05,
|
| 2348 |
+
"loss": 1.8671,
|
| 2349 |
+
"step": 195000
|
| 2350 |
+
},
|
| 2351 |
+
{
|
| 2352 |
+
"epoch": 2.04,
|
| 2353 |
+
"learning_rate": 1.5949783332636656e-05,
|
| 2354 |
+
"loss": 1.823,
|
| 2355 |
+
"step": 195500
|
| 2356 |
+
},
|
| 2357 |
+
{
|
| 2358 |
+
"epoch": 2.05,
|
| 2359 |
+
"learning_rate": 1.5862698379523193e-05,
|
| 2360 |
+
"loss": 1.8271,
|
| 2361 |
+
"step": 196000
|
| 2362 |
+
},
|
| 2363 |
+
{
|
| 2364 |
+
"epoch": 2.05,
|
| 2365 |
+
"learning_rate": 1.5775613426409732e-05,
|
| 2366 |
+
"loss": 1.8385,
|
| 2367 |
+
"step": 196500
|
| 2368 |
+
},
|
| 2369 |
+
{
|
| 2370 |
+
"epoch": 2.06,
|
| 2371 |
+
"learning_rate": 1.5688528473296272e-05,
|
| 2372 |
+
"loss": 1.8401,
|
| 2373 |
+
"step": 197000
|
| 2374 |
+
},
|
| 2375 |
+
{
|
| 2376 |
+
"epoch": 2.06,
|
| 2377 |
+
"learning_rate": 1.5601443520182808e-05,
|
| 2378 |
+
"loss": 1.8166,
|
| 2379 |
+
"step": 197500
|
| 2380 |
+
},
|
| 2381 |
+
{
|
| 2382 |
+
"epoch": 2.07,
|
| 2383 |
+
"learning_rate": 1.5514358567069348e-05,
|
| 2384 |
+
"loss": 1.8358,
|
| 2385 |
+
"step": 198000
|
| 2386 |
+
},
|
| 2387 |
+
{
|
| 2388 |
+
"epoch": 2.07,
|
| 2389 |
+
"learning_rate": 1.5427273613955887e-05,
|
| 2390 |
+
"loss": 1.8174,
|
| 2391 |
+
"step": 198500
|
| 2392 |
+
},
|
| 2393 |
+
{
|
| 2394 |
+
"epoch": 2.08,
|
| 2395 |
+
"learning_rate": 1.5340188660842423e-05,
|
| 2396 |
+
"loss": 1.8661,
|
| 2397 |
+
"step": 199000
|
| 2398 |
+
},
|
| 2399 |
+
{
|
| 2400 |
+
"epoch": 2.08,
|
| 2401 |
+
"learning_rate": 1.5253103707728963e-05,
|
| 2402 |
+
"loss": 1.8418,
|
| 2403 |
+
"step": 199500
|
| 2404 |
+
},
|
| 2405 |
+
{
|
| 2406 |
+
"epoch": 2.09,
|
| 2407 |
+
"learning_rate": 1.5166018754615503e-05,
|
| 2408 |
+
"loss": 1.8458,
|
| 2409 |
+
"step": 200000
|
| 2410 |
+
},
|
| 2411 |
+
{
|
| 2412 |
+
"epoch": 2.1,
|
| 2413 |
+
"learning_rate": 1.5078933801502044e-05,
|
| 2414 |
+
"loss": 1.8425,
|
| 2415 |
+
"step": 200500
|
| 2416 |
+
},
|
| 2417 |
+
{
|
| 2418 |
+
"epoch": 2.1,
|
| 2419 |
+
"learning_rate": 1.4991848848388582e-05,
|
| 2420 |
+
"loss": 1.8042,
|
| 2421 |
+
"step": 201000
|
| 2422 |
+
},
|
| 2423 |
+
{
|
| 2424 |
+
"epoch": 2.11,
|
| 2425 |
+
"learning_rate": 1.490476389527512e-05,
|
| 2426 |
+
"loss": 1.811,
|
| 2427 |
+
"step": 201500
|
| 2428 |
+
},
|
| 2429 |
+
{
|
| 2430 |
+
"epoch": 2.11,
|
| 2431 |
+
"learning_rate": 1.481767894216166e-05,
|
| 2432 |
+
"loss": 1.827,
|
| 2433 |
+
"step": 202000
|
| 2434 |
+
},
|
| 2435 |
+
{
|
| 2436 |
+
"epoch": 2.12,
|
| 2437 |
+
"learning_rate": 1.4730593989048197e-05,
|
| 2438 |
+
"loss": 1.8273,
|
| 2439 |
+
"step": 202500
|
| 2440 |
+
},
|
| 2441 |
+
{
|
| 2442 |
+
"epoch": 2.12,
|
| 2443 |
+
"learning_rate": 1.4643509035934735e-05,
|
| 2444 |
+
"loss": 1.8124,
|
| 2445 |
+
"step": 203000
|
| 2446 |
+
},
|
| 2447 |
+
{
|
| 2448 |
+
"epoch": 2.13,
|
| 2449 |
+
"learning_rate": 1.4556424082821275e-05,
|
| 2450 |
+
"loss": 1.8035,
|
| 2451 |
+
"step": 203500
|
| 2452 |
+
},
|
| 2453 |
+
{
|
| 2454 |
+
"epoch": 2.13,
|
| 2455 |
+
"learning_rate": 1.4469339129707813e-05,
|
| 2456 |
+
"loss": 1.8408,
|
| 2457 |
+
"step": 204000
|
| 2458 |
+
},
|
| 2459 |
+
{
|
| 2460 |
+
"epoch": 2.14,
|
| 2461 |
+
"learning_rate": 1.438225417659435e-05,
|
| 2462 |
+
"loss": 1.7842,
|
| 2463 |
+
"step": 204500
|
| 2464 |
+
},
|
| 2465 |
+
{
|
| 2466 |
+
"epoch": 2.14,
|
| 2467 |
+
"learning_rate": 1.4295169223480892e-05,
|
| 2468 |
+
"loss": 1.8058,
|
| 2469 |
+
"step": 205000
|
| 2470 |
+
},
|
| 2471 |
+
{
|
| 2472 |
+
"epoch": 2.15,
|
| 2473 |
+
"learning_rate": 1.4208084270367431e-05,
|
| 2474 |
+
"loss": 1.8098,
|
| 2475 |
+
"step": 205500
|
| 2476 |
+
},
|
| 2477 |
+
{
|
| 2478 |
+
"epoch": 2.15,
|
| 2479 |
+
"learning_rate": 1.412099931725397e-05,
|
| 2480 |
+
"loss": 1.8061,
|
| 2481 |
+
"step": 206000
|
| 2482 |
+
},
|
| 2483 |
+
{
|
| 2484 |
+
"epoch": 2.16,
|
| 2485 |
+
"learning_rate": 1.4033914364140507e-05,
|
| 2486 |
+
"loss": 1.8077,
|
| 2487 |
+
"step": 206500
|
| 2488 |
+
},
|
| 2489 |
+
{
|
| 2490 |
+
"epoch": 2.16,
|
| 2491 |
+
"learning_rate": 1.3946829411027047e-05,
|
| 2492 |
+
"loss": 1.8174,
|
| 2493 |
+
"step": 207000
|
| 2494 |
+
},
|
| 2495 |
+
{
|
| 2496 |
+
"epoch": 2.17,
|
| 2497 |
+
"learning_rate": 1.3859744457913585e-05,
|
| 2498 |
+
"loss": 1.7933,
|
| 2499 |
+
"step": 207500
|
| 2500 |
+
},
|
| 2501 |
+
{
|
| 2502 |
+
"epoch": 2.17,
|
| 2503 |
+
"learning_rate": 1.3772659504800122e-05,
|
| 2504 |
+
"loss": 1.7864,
|
| 2505 |
+
"step": 208000
|
| 2506 |
+
},
|
| 2507 |
+
{
|
| 2508 |
+
"epoch": 2.18,
|
| 2509 |
+
"learning_rate": 1.3685574551686662e-05,
|
| 2510 |
+
"loss": 1.8072,
|
| 2511 |
+
"step": 208500
|
| 2512 |
+
},
|
| 2513 |
+
{
|
| 2514 |
+
"epoch": 2.18,
|
| 2515 |
+
"learning_rate": 1.35984895985732e-05,
|
| 2516 |
+
"loss": 1.8226,
|
| 2517 |
+
"step": 209000
|
| 2518 |
+
},
|
| 2519 |
+
{
|
| 2520 |
+
"epoch": 2.19,
|
| 2521 |
+
"learning_rate": 1.3511404645459738e-05,
|
| 2522 |
+
"loss": 1.8134,
|
| 2523 |
+
"step": 209500
|
| 2524 |
+
},
|
| 2525 |
+
{
|
| 2526 |
+
"epoch": 2.19,
|
| 2527 |
+
"learning_rate": 1.342431969234628e-05,
|
| 2528 |
+
"loss": 1.8193,
|
| 2529 |
+
"step": 210000
|
| 2530 |
+
},
|
| 2531 |
+
{
|
| 2532 |
+
"epoch": 2.2,
|
| 2533 |
+
"learning_rate": 1.3337234739232817e-05,
|
| 2534 |
+
"loss": 1.8274,
|
| 2535 |
+
"step": 210500
|
| 2536 |
+
},
|
| 2537 |
+
{
|
| 2538 |
+
"epoch": 2.2,
|
| 2539 |
+
"learning_rate": 1.3250149786119357e-05,
|
| 2540 |
+
"loss": 1.8083,
|
| 2541 |
+
"step": 211000
|
| 2542 |
+
},
|
| 2543 |
+
{
|
| 2544 |
+
"epoch": 2.21,
|
| 2545 |
+
"learning_rate": 1.3163064833005895e-05,
|
| 2546 |
+
"loss": 1.8299,
|
| 2547 |
+
"step": 211500
|
| 2548 |
+
},
|
| 2549 |
+
{
|
| 2550 |
+
"epoch": 2.22,
|
| 2551 |
+
"learning_rate": 1.3075979879892432e-05,
|
| 2552 |
+
"loss": 1.7945,
|
| 2553 |
+
"step": 212000
|
| 2554 |
+
},
|
| 2555 |
+
{
|
| 2556 |
+
"epoch": 2.22,
|
| 2557 |
+
"learning_rate": 1.2988894926778972e-05,
|
| 2558 |
+
"loss": 1.8197,
|
| 2559 |
+
"step": 212500
|
| 2560 |
+
},
|
| 2561 |
+
{
|
| 2562 |
+
"epoch": 2.23,
|
| 2563 |
+
"learning_rate": 1.290180997366551e-05,
|
| 2564 |
+
"loss": 1.801,
|
| 2565 |
+
"step": 213000
|
| 2566 |
+
},
|
| 2567 |
+
{
|
| 2568 |
+
"epoch": 2.23,
|
| 2569 |
+
"learning_rate": 1.2814725020552048e-05,
|
| 2570 |
+
"loss": 1.7869,
|
| 2571 |
+
"step": 213500
|
| 2572 |
+
},
|
| 2573 |
+
{
|
| 2574 |
+
"epoch": 2.24,
|
| 2575 |
+
"learning_rate": 1.2727640067438587e-05,
|
| 2576 |
+
"loss": 1.787,
|
| 2577 |
+
"step": 214000
|
| 2578 |
+
},
|
| 2579 |
+
{
|
| 2580 |
+
"epoch": 2.24,
|
| 2581 |
+
"learning_rate": 1.2640555114325129e-05,
|
| 2582 |
+
"loss": 1.795,
|
| 2583 |
+
"step": 214500
|
| 2584 |
+
},
|
| 2585 |
+
{
|
| 2586 |
+
"epoch": 2.25,
|
| 2587 |
+
"learning_rate": 1.2553470161211667e-05,
|
| 2588 |
+
"loss": 1.8039,
|
| 2589 |
+
"step": 215000
|
| 2590 |
+
},
|
| 2591 |
+
{
|
| 2592 |
+
"epoch": 2.25,
|
| 2593 |
+
"learning_rate": 1.2466385208098204e-05,
|
| 2594 |
+
"loss": 1.7862,
|
| 2595 |
+
"step": 215500
|
| 2596 |
+
},
|
| 2597 |
+
{
|
| 2598 |
+
"epoch": 2.26,
|
| 2599 |
+
"learning_rate": 1.2379300254984744e-05,
|
| 2600 |
+
"loss": 1.7948,
|
| 2601 |
+
"step": 216000
|
| 2602 |
+
},
|
| 2603 |
+
{
|
| 2604 |
+
"epoch": 2.26,
|
| 2605 |
+
"learning_rate": 1.2292215301871282e-05,
|
| 2606 |
+
"loss": 1.7791,
|
| 2607 |
+
"step": 216500
|
| 2608 |
+
},
|
| 2609 |
+
{
|
| 2610 |
+
"epoch": 2.27,
|
| 2611 |
+
"learning_rate": 1.220513034875782e-05,
|
| 2612 |
+
"loss": 1.7978,
|
| 2613 |
+
"step": 217000
|
| 2614 |
+
},
|
| 2615 |
+
{
|
| 2616 |
+
"epoch": 2.27,
|
| 2617 |
+
"learning_rate": 1.211804539564436e-05,
|
| 2618 |
+
"loss": 1.8121,
|
| 2619 |
+
"step": 217500
|
| 2620 |
+
},
|
| 2621 |
+
{
|
| 2622 |
+
"epoch": 2.28,
|
| 2623 |
+
"learning_rate": 1.2030960442530899e-05,
|
| 2624 |
+
"loss": 1.8106,
|
| 2625 |
+
"step": 218000
|
| 2626 |
+
},
|
| 2627 |
+
{
|
| 2628 |
+
"epoch": 2.28,
|
| 2629 |
+
"learning_rate": 1.1943875489417437e-05,
|
| 2630 |
+
"loss": 1.812,
|
| 2631 |
+
"step": 218500
|
| 2632 |
+
},
|
| 2633 |
+
{
|
| 2634 |
+
"epoch": 2.29,
|
| 2635 |
+
"learning_rate": 1.1856790536303977e-05,
|
| 2636 |
+
"loss": 1.7548,
|
| 2637 |
+
"step": 219000
|
| 2638 |
+
},
|
| 2639 |
+
{
|
| 2640 |
+
"epoch": 2.29,
|
| 2641 |
+
"learning_rate": 1.1769705583190514e-05,
|
| 2642 |
+
"loss": 1.7806,
|
| 2643 |
+
"step": 219500
|
| 2644 |
+
},
|
| 2645 |
+
{
|
| 2646 |
+
"epoch": 2.3,
|
| 2647 |
+
"learning_rate": 1.1682620630077052e-05,
|
| 2648 |
+
"loss": 1.7942,
|
| 2649 |
+
"step": 220000
|
| 2650 |
+
},
|
| 2651 |
+
{
|
| 2652 |
+
"epoch": 2.3,
|
| 2653 |
+
"learning_rate": 1.1595535676963592e-05,
|
| 2654 |
+
"loss": 1.8271,
|
| 2655 |
+
"step": 220500
|
| 2656 |
+
},
|
| 2657 |
+
{
|
| 2658 |
+
"epoch": 2.31,
|
| 2659 |
+
"learning_rate": 1.1508450723850131e-05,
|
| 2660 |
+
"loss": 1.765,
|
| 2661 |
+
"step": 221000
|
| 2662 |
+
},
|
| 2663 |
+
{
|
| 2664 |
+
"epoch": 2.31,
|
| 2665 |
+
"learning_rate": 1.142136577073667e-05,
|
| 2666 |
+
"loss": 1.8056,
|
| 2667 |
+
"step": 221500
|
| 2668 |
+
},
|
| 2669 |
+
{
|
| 2670 |
+
"epoch": 2.32,
|
| 2671 |
+
"learning_rate": 1.1334280817623207e-05,
|
| 2672 |
+
"loss": 1.7853,
|
| 2673 |
+
"step": 222000
|
| 2674 |
+
},
|
| 2675 |
+
{
|
| 2676 |
+
"epoch": 2.33,
|
| 2677 |
+
"learning_rate": 1.1247195864509749e-05,
|
| 2678 |
+
"loss": 1.7754,
|
| 2679 |
+
"step": 222500
|
| 2680 |
+
},
|
| 2681 |
+
{
|
| 2682 |
+
"epoch": 2.33,
|
| 2683 |
+
"learning_rate": 1.1160110911396286e-05,
|
| 2684 |
+
"loss": 1.7931,
|
| 2685 |
+
"step": 223000
|
| 2686 |
+
},
|
| 2687 |
+
{
|
| 2688 |
+
"epoch": 2.34,
|
| 2689 |
+
"learning_rate": 1.1073025958282824e-05,
|
| 2690 |
+
"loss": 1.7868,
|
| 2691 |
+
"step": 223500
|
| 2692 |
+
},
|
| 2693 |
+
{
|
| 2694 |
+
"epoch": 2.34,
|
| 2695 |
+
"learning_rate": 1.0985941005169364e-05,
|
| 2696 |
+
"loss": 1.7744,
|
| 2697 |
+
"step": 224000
|
| 2698 |
+
},
|
| 2699 |
+
{
|
| 2700 |
+
"epoch": 2.35,
|
| 2701 |
+
"learning_rate": 1.0898856052055902e-05,
|
| 2702 |
+
"loss": 1.7919,
|
| 2703 |
+
"step": 224500
|
| 2704 |
+
},
|
| 2705 |
+
{
|
| 2706 |
+
"epoch": 2.35,
|
| 2707 |
+
"learning_rate": 1.0811771098942441e-05,
|
| 2708 |
+
"loss": 1.7822,
|
| 2709 |
+
"step": 225000
|
| 2710 |
+
},
|
| 2711 |
+
{
|
| 2712 |
+
"epoch": 2.36,
|
| 2713 |
+
"learning_rate": 1.072468614582898e-05,
|
| 2714 |
+
"loss": 1.7738,
|
| 2715 |
+
"step": 225500
|
| 2716 |
+
},
|
| 2717 |
+
{
|
| 2718 |
+
"epoch": 2.36,
|
| 2719 |
+
"learning_rate": 1.0637601192715519e-05,
|
| 2720 |
+
"loss": 1.779,
|
| 2721 |
+
"step": 226000
|
| 2722 |
+
},
|
| 2723 |
+
{
|
| 2724 |
+
"epoch": 2.37,
|
| 2725 |
+
"learning_rate": 1.0550516239602057e-05,
|
| 2726 |
+
"loss": 1.7856,
|
| 2727 |
+
"step": 226500
|
| 2728 |
+
},
|
| 2729 |
+
{
|
| 2730 |
+
"epoch": 2.37,
|
| 2731 |
+
"learning_rate": 1.0463431286488595e-05,
|
| 2732 |
+
"loss": 1.8012,
|
| 2733 |
+
"step": 227000
|
| 2734 |
+
},
|
| 2735 |
+
{
|
| 2736 |
+
"epoch": 2.38,
|
| 2737 |
+
"learning_rate": 1.0376346333375134e-05,
|
| 2738 |
+
"loss": 1.7557,
|
| 2739 |
+
"step": 227500
|
| 2740 |
+
},
|
| 2741 |
+
{
|
| 2742 |
+
"epoch": 2.38,
|
| 2743 |
+
"learning_rate": 1.0289261380261674e-05,
|
| 2744 |
+
"loss": 1.7674,
|
| 2745 |
+
"step": 228000
|
| 2746 |
+
},
|
| 2747 |
+
{
|
| 2748 |
+
"epoch": 2.39,
|
| 2749 |
+
"learning_rate": 1.0202176427148212e-05,
|
| 2750 |
+
"loss": 1.7739,
|
| 2751 |
+
"step": 228500
|
| 2752 |
+
},
|
| 2753 |
+
{
|
| 2754 |
+
"epoch": 2.39,
|
| 2755 |
+
"learning_rate": 1.011509147403475e-05,
|
| 2756 |
+
"loss": 1.7393,
|
| 2757 |
+
"step": 229000
|
| 2758 |
+
},
|
| 2759 |
+
{
|
| 2760 |
+
"epoch": 2.4,
|
| 2761 |
+
"learning_rate": 1.002800652092129e-05,
|
| 2762 |
+
"loss": 1.7869,
|
| 2763 |
+
"step": 229500
|
| 2764 |
+
},
|
| 2765 |
+
{
|
| 2766 |
+
"epoch": 2.4,
|
| 2767 |
+
"learning_rate": 9.940921567807829e-06,
|
| 2768 |
+
"loss": 1.7764,
|
| 2769 |
+
"step": 230000
|
| 2770 |
+
},
|
| 2771 |
+
{
|
| 2772 |
+
"epoch": 2.41,
|
| 2773 |
+
"learning_rate": 9.853836614694367e-06,
|
| 2774 |
+
"loss": 1.7298,
|
| 2775 |
+
"step": 230500
|
| 2776 |
+
},
|
| 2777 |
+
{
|
| 2778 |
+
"epoch": 2.41,
|
| 2779 |
+
"learning_rate": 9.766751661580906e-06,
|
| 2780 |
+
"loss": 1.7476,
|
| 2781 |
+
"step": 231000
|
| 2782 |
+
},
|
| 2783 |
+
{
|
| 2784 |
+
"epoch": 2.42,
|
| 2785 |
+
"learning_rate": 9.679666708467444e-06,
|
| 2786 |
+
"loss": 1.7576,
|
| 2787 |
+
"step": 231500
|
| 2788 |
+
},
|
| 2789 |
+
{
|
| 2790 |
+
"epoch": 2.42,
|
| 2791 |
+
"learning_rate": 9.592581755353984e-06,
|
| 2792 |
+
"loss": 1.7482,
|
| 2793 |
+
"step": 232000
|
| 2794 |
+
},
|
| 2795 |
+
{
|
| 2796 |
+
"epoch": 2.43,
|
| 2797 |
+
"learning_rate": 9.505496802240522e-06,
|
| 2798 |
+
"loss": 1.7533,
|
| 2799 |
+
"step": 232500
|
| 2800 |
+
},
|
| 2801 |
+
{
|
| 2802 |
+
"epoch": 2.43,
|
| 2803 |
+
"learning_rate": 9.418411849127061e-06,
|
| 2804 |
+
"loss": 1.7642,
|
| 2805 |
+
"step": 233000
|
| 2806 |
+
},
|
| 2807 |
+
{
|
| 2808 |
+
"epoch": 2.44,
|
| 2809 |
+
"learning_rate": 9.3313268960136e-06,
|
| 2810 |
+
"loss": 1.7546,
|
| 2811 |
+
"step": 233500
|
| 2812 |
+
},
|
| 2813 |
+
{
|
| 2814 |
+
"epoch": 2.45,
|
| 2815 |
+
"learning_rate": 9.244241942900137e-06,
|
| 2816 |
+
"loss": 1.7569,
|
| 2817 |
+
"step": 234000
|
| 2818 |
+
},
|
| 2819 |
+
{
|
| 2820 |
+
"epoch": 2.45,
|
| 2821 |
+
"learning_rate": 9.157156989786678e-06,
|
| 2822 |
+
"loss": 1.7453,
|
| 2823 |
+
"step": 234500
|
| 2824 |
+
},
|
| 2825 |
+
{
|
| 2826 |
+
"epoch": 2.46,
|
| 2827 |
+
"learning_rate": 9.070072036673216e-06,
|
| 2828 |
+
"loss": 1.7449,
|
| 2829 |
+
"step": 235000
|
| 2830 |
+
},
|
| 2831 |
+
{
|
| 2832 |
+
"epoch": 2.46,
|
| 2833 |
+
"learning_rate": 8.982987083559754e-06,
|
| 2834 |
+
"loss": 1.7682,
|
| 2835 |
+
"step": 235500
|
| 2836 |
+
},
|
| 2837 |
+
{
|
| 2838 |
+
"epoch": 2.47,
|
| 2839 |
+
"learning_rate": 8.895902130446294e-06,
|
| 2840 |
+
"loss": 1.7584,
|
| 2841 |
+
"step": 236000
|
| 2842 |
+
},
|
| 2843 |
+
{
|
| 2844 |
+
"epoch": 2.47,
|
| 2845 |
+
"learning_rate": 8.808817177332832e-06,
|
| 2846 |
+
"loss": 1.7557,
|
| 2847 |
+
"step": 236500
|
| 2848 |
+
},
|
| 2849 |
+
{
|
| 2850 |
+
"epoch": 2.48,
|
| 2851 |
+
"learning_rate": 8.721732224219371e-06,
|
| 2852 |
+
"loss": 1.773,
|
| 2853 |
+
"step": 237000
|
| 2854 |
+
},
|
| 2855 |
+
{
|
| 2856 |
+
"epoch": 2.48,
|
| 2857 |
+
"learning_rate": 8.634647271105909e-06,
|
| 2858 |
+
"loss": 1.773,
|
| 2859 |
+
"step": 237500
|
| 2860 |
+
},
|
| 2861 |
+
{
|
| 2862 |
+
"epoch": 2.49,
|
| 2863 |
+
"learning_rate": 8.547562317992449e-06,
|
| 2864 |
+
"loss": 1.744,
|
| 2865 |
+
"step": 238000
|
| 2866 |
+
},
|
| 2867 |
+
{
|
| 2868 |
+
"epoch": 2.49,
|
| 2869 |
+
"learning_rate": 8.460477364878987e-06,
|
| 2870 |
+
"loss": 1.7379,
|
| 2871 |
+
"step": 238500
|
| 2872 |
+
},
|
| 2873 |
+
{
|
| 2874 |
+
"epoch": 2.5,
|
| 2875 |
+
"learning_rate": 8.373392411765526e-06,
|
| 2876 |
+
"loss": 1.7635,
|
| 2877 |
+
"step": 239000
|
| 2878 |
+
},
|
| 2879 |
+
{
|
| 2880 |
+
"epoch": 2.5,
|
| 2881 |
+
"learning_rate": 8.286307458652066e-06,
|
| 2882 |
+
"loss": 1.7585,
|
| 2883 |
+
"step": 239500
|
| 2884 |
+
},
|
| 2885 |
+
{
|
| 2886 |
+
"epoch": 2.51,
|
| 2887 |
+
"learning_rate": 8.199222505538604e-06,
|
| 2888 |
+
"loss": 1.7488,
|
| 2889 |
+
"step": 240000
|
| 2890 |
+
},
|
| 2891 |
+
{
|
| 2892 |
+
"epoch": 2.51,
|
| 2893 |
+
"learning_rate": 8.112137552425142e-06,
|
| 2894 |
+
"loss": 1.7532,
|
| 2895 |
+
"step": 240500
|
| 2896 |
+
},
|
| 2897 |
+
{
|
| 2898 |
+
"epoch": 2.52,
|
| 2899 |
+
"learning_rate": 8.025052599311681e-06,
|
| 2900 |
+
"loss": 1.758,
|
| 2901 |
+
"step": 241000
|
| 2902 |
+
},
|
| 2903 |
+
{
|
| 2904 |
+
"epoch": 2.52,
|
| 2905 |
+
"learning_rate": 7.93796764619822e-06,
|
| 2906 |
+
"loss": 1.7485,
|
| 2907 |
+
"step": 241500
|
| 2908 |
+
},
|
| 2909 |
+
{
|
| 2910 |
+
"epoch": 2.53,
|
| 2911 |
+
"learning_rate": 7.850882693084759e-06,
|
| 2912 |
+
"loss": 1.7409,
|
| 2913 |
+
"step": 242000
|
| 2914 |
+
},
|
| 2915 |
+
{
|
| 2916 |
+
"epoch": 2.53,
|
| 2917 |
+
"learning_rate": 7.763797739971297e-06,
|
| 2918 |
+
"loss": 1.7494,
|
| 2919 |
+
"step": 242500
|
| 2920 |
+
},
|
| 2921 |
+
{
|
| 2922 |
+
"epoch": 2.54,
|
| 2923 |
+
"learning_rate": 7.676712786857836e-06,
|
| 2924 |
+
"loss": 1.7264,
|
| 2925 |
+
"step": 243000
|
| 2926 |
+
},
|
| 2927 |
+
{
|
| 2928 |
+
"epoch": 2.54,
|
| 2929 |
+
"learning_rate": 7.589627833744374e-06,
|
| 2930 |
+
"loss": 1.7465,
|
| 2931 |
+
"step": 243500
|
| 2932 |
+
},
|
| 2933 |
+
{
|
| 2934 |
+
"epoch": 2.55,
|
| 2935 |
+
"learning_rate": 7.502542880630914e-06,
|
| 2936 |
+
"loss": 1.7654,
|
| 2937 |
+
"step": 244000
|
| 2938 |
+
},
|
| 2939 |
+
{
|
| 2940 |
+
"epoch": 2.56,
|
| 2941 |
+
"learning_rate": 7.415457927517452e-06,
|
| 2942 |
+
"loss": 1.7422,
|
| 2943 |
+
"step": 244500
|
| 2944 |
+
},
|
| 2945 |
+
{
|
| 2946 |
+
"epoch": 2.56,
|
| 2947 |
+
"learning_rate": 7.328372974403991e-06,
|
| 2948 |
+
"loss": 1.7418,
|
| 2949 |
+
"step": 245000
|
| 2950 |
+
},
|
| 2951 |
+
{
|
| 2952 |
+
"epoch": 2.57,
|
| 2953 |
+
"learning_rate": 7.241288021290529e-06,
|
| 2954 |
+
"loss": 1.7664,
|
| 2955 |
+
"step": 245500
|
| 2956 |
+
},
|
| 2957 |
+
{
|
| 2958 |
+
"epoch": 2.57,
|
| 2959 |
+
"learning_rate": 7.154203068177068e-06,
|
| 2960 |
+
"loss": 1.7324,
|
| 2961 |
+
"step": 246000
|
| 2962 |
+
},
|
| 2963 |
+
{
|
| 2964 |
+
"epoch": 2.58,
|
| 2965 |
+
"learning_rate": 7.067118115063607e-06,
|
| 2966 |
+
"loss": 1.7143,
|
| 2967 |
+
"step": 246500
|
| 2968 |
+
},
|
| 2969 |
+
{
|
| 2970 |
+
"epoch": 2.58,
|
| 2971 |
+
"learning_rate": 6.980033161950146e-06,
|
| 2972 |
+
"loss": 1.6917,
|
| 2973 |
+
"step": 247000
|
| 2974 |
+
},
|
| 2975 |
+
{
|
| 2976 |
+
"epoch": 2.59,
|
| 2977 |
+
"learning_rate": 6.892948208836685e-06,
|
| 2978 |
+
"loss": 1.7498,
|
| 2979 |
+
"step": 247500
|
| 2980 |
+
},
|
| 2981 |
+
{
|
| 2982 |
+
"epoch": 2.59,
|
| 2983 |
+
"learning_rate": 6.805863255723223e-06,
|
| 2984 |
+
"loss": 1.7161,
|
| 2985 |
+
"step": 248000
|
| 2986 |
+
},
|
| 2987 |
+
{
|
| 2988 |
+
"epoch": 2.6,
|
| 2989 |
+
"learning_rate": 6.718778302609763e-06,
|
| 2990 |
+
"loss": 1.7315,
|
| 2991 |
+
"step": 248500
|
| 2992 |
+
},
|
| 2993 |
+
{
|
| 2994 |
+
"epoch": 2.6,
|
| 2995 |
+
"learning_rate": 6.631693349496301e-06,
|
| 2996 |
+
"loss": 1.7591,
|
| 2997 |
+
"step": 249000
|
| 2998 |
+
},
|
| 2999 |
+
{
|
| 3000 |
+
"epoch": 2.61,
|
| 3001 |
+
"learning_rate": 6.54460839638284e-06,
|
| 3002 |
+
"loss": 1.7388,
|
| 3003 |
+
"step": 249500
|
| 3004 |
+
},
|
| 3005 |
+
{
|
| 3006 |
+
"epoch": 2.61,
|
| 3007 |
+
"learning_rate": 6.4575234432693785e-06,
|
| 3008 |
+
"loss": 1.7236,
|
| 3009 |
+
"step": 250000
|
| 3010 |
+
},
|
| 3011 |
+
{
|
| 3012 |
+
"epoch": 2.62,
|
| 3013 |
+
"learning_rate": 6.370438490155916e-06,
|
| 3014 |
+
"loss": 1.7396,
|
| 3015 |
+
"step": 250500
|
| 3016 |
+
},
|
| 3017 |
+
{
|
| 3018 |
+
"epoch": 2.62,
|
| 3019 |
+
"learning_rate": 6.283353537042457e-06,
|
| 3020 |
+
"loss": 1.7287,
|
| 3021 |
+
"step": 251000
|
| 3022 |
+
},
|
| 3023 |
+
{
|
| 3024 |
+
"epoch": 2.63,
|
| 3025 |
+
"learning_rate": 6.196268583928995e-06,
|
| 3026 |
+
"loss": 1.7231,
|
| 3027 |
+
"step": 251500
|
| 3028 |
+
},
|
| 3029 |
+
{
|
| 3030 |
+
"epoch": 2.63,
|
| 3031 |
+
"learning_rate": 6.1091836308155335e-06,
|
| 3032 |
+
"loss": 1.723,
|
| 3033 |
+
"step": 252000
|
| 3034 |
+
},
|
| 3035 |
+
{
|
| 3036 |
+
"epoch": 2.64,
|
| 3037 |
+
"learning_rate": 6.022098677702072e-06,
|
| 3038 |
+
"loss": 1.7419,
|
| 3039 |
+
"step": 252500
|
| 3040 |
+
},
|
| 3041 |
+
{
|
| 3042 |
+
"epoch": 2.64,
|
| 3043 |
+
"learning_rate": 5.935013724588611e-06,
|
| 3044 |
+
"loss": 1.7434,
|
| 3045 |
+
"step": 253000
|
| 3046 |
+
},
|
| 3047 |
+
{
|
| 3048 |
+
"epoch": 2.65,
|
| 3049 |
+
"learning_rate": 5.84792877147515e-06,
|
| 3050 |
+
"loss": 1.7221,
|
| 3051 |
+
"step": 253500
|
| 3052 |
+
},
|
| 3053 |
+
{
|
| 3054 |
+
"epoch": 2.65,
|
| 3055 |
+
"learning_rate": 5.7608438183616885e-06,
|
| 3056 |
+
"loss": 1.7131,
|
| 3057 |
+
"step": 254000
|
| 3058 |
+
},
|
| 3059 |
+
{
|
| 3060 |
+
"epoch": 2.66,
|
| 3061 |
+
"learning_rate": 5.673758865248227e-06,
|
| 3062 |
+
"loss": 1.7402,
|
| 3063 |
+
"step": 254500
|
| 3064 |
+
},
|
| 3065 |
+
{
|
| 3066 |
+
"epoch": 2.66,
|
| 3067 |
+
"learning_rate": 5.586673912134766e-06,
|
| 3068 |
+
"loss": 1.7157,
|
| 3069 |
+
"step": 255000
|
| 3070 |
+
},
|
| 3071 |
+
{
|
| 3072 |
+
"epoch": 2.67,
|
| 3073 |
+
"learning_rate": 5.499588959021305e-06,
|
| 3074 |
+
"loss": 1.7488,
|
| 3075 |
+
"step": 255500
|
| 3076 |
+
},
|
| 3077 |
+
{
|
| 3078 |
+
"epoch": 2.68,
|
| 3079 |
+
"learning_rate": 5.4125040059078434e-06,
|
| 3080 |
+
"loss": 1.7135,
|
| 3081 |
+
"step": 256000
|
| 3082 |
+
},
|
| 3083 |
+
{
|
| 3084 |
+
"epoch": 2.68,
|
| 3085 |
+
"learning_rate": 5.325419052794382e-06,
|
| 3086 |
+
"loss": 1.7125,
|
| 3087 |
+
"step": 256500
|
| 3088 |
+
},
|
| 3089 |
+
{
|
| 3090 |
+
"epoch": 2.69,
|
| 3091 |
+
"learning_rate": 5.238334099680921e-06,
|
| 3092 |
+
"loss": 1.713,
|
| 3093 |
+
"step": 257000
|
| 3094 |
+
},
|
| 3095 |
+
{
|
| 3096 |
+
"epoch": 2.69,
|
| 3097 |
+
"learning_rate": 5.15124914656746e-06,
|
| 3098 |
+
"loss": 1.7231,
|
| 3099 |
+
"step": 257500
|
| 3100 |
+
},
|
| 3101 |
+
{
|
| 3102 |
+
"epoch": 2.7,
|
| 3103 |
+
"learning_rate": 5.064164193453998e-06,
|
| 3104 |
+
"loss": 1.724,
|
| 3105 |
+
"step": 258000
|
| 3106 |
+
},
|
| 3107 |
+
{
|
| 3108 |
+
"epoch": 2.7,
|
| 3109 |
+
"learning_rate": 4.977079240340537e-06,
|
| 3110 |
+
"loss": 1.7196,
|
| 3111 |
+
"step": 258500
|
| 3112 |
+
},
|
| 3113 |
+
{
|
| 3114 |
+
"epoch": 2.71,
|
| 3115 |
+
"learning_rate": 4.889994287227076e-06,
|
| 3116 |
+
"loss": 1.7282,
|
| 3117 |
+
"step": 259000
|
| 3118 |
+
},
|
| 3119 |
+
{
|
| 3120 |
+
"epoch": 2.71,
|
| 3121 |
+
"learning_rate": 4.802909334113615e-06,
|
| 3122 |
+
"loss": 1.7245,
|
| 3123 |
+
"step": 259500
|
| 3124 |
+
},
|
| 3125 |
+
{
|
| 3126 |
+
"epoch": 2.72,
|
| 3127 |
+
"learning_rate": 4.715824381000153e-06,
|
| 3128 |
+
"loss": 1.7129,
|
| 3129 |
+
"step": 260000
|
| 3130 |
+
},
|
| 3131 |
+
{
|
| 3132 |
+
"epoch": 2.72,
|
| 3133 |
+
"learning_rate": 4.628739427886692e-06,
|
| 3134 |
+
"loss": 1.7114,
|
| 3135 |
+
"step": 260500
|
| 3136 |
+
},
|
| 3137 |
+
{
|
| 3138 |
+
"epoch": 2.73,
|
| 3139 |
+
"learning_rate": 4.541654474773231e-06,
|
| 3140 |
+
"loss": 1.72,
|
| 3141 |
+
"step": 261000
|
| 3142 |
+
},
|
| 3143 |
+
{
|
| 3144 |
+
"epoch": 2.73,
|
| 3145 |
+
"learning_rate": 4.45456952165977e-06,
|
| 3146 |
+
"loss": 1.7321,
|
| 3147 |
+
"step": 261500
|
| 3148 |
+
},
|
| 3149 |
+
{
|
| 3150 |
+
"epoch": 2.74,
|
| 3151 |
+
"learning_rate": 4.367484568546309e-06,
|
| 3152 |
+
"loss": 1.7439,
|
| 3153 |
+
"step": 262000
|
| 3154 |
+
},
|
| 3155 |
+
{
|
| 3156 |
+
"epoch": 2.74,
|
| 3157 |
+
"learning_rate": 4.280399615432847e-06,
|
| 3158 |
+
"loss": 1.6934,
|
| 3159 |
+
"step": 262500
|
| 3160 |
+
},
|
| 3161 |
+
{
|
| 3162 |
+
"epoch": 2.75,
|
| 3163 |
+
"learning_rate": 4.193314662319386e-06,
|
| 3164 |
+
"loss": 1.7236,
|
| 3165 |
+
"step": 263000
|
| 3166 |
+
},
|
| 3167 |
+
{
|
| 3168 |
+
"epoch": 2.75,
|
| 3169 |
+
"learning_rate": 4.1062297092059246e-06,
|
| 3170 |
+
"loss": 1.7333,
|
| 3171 |
+
"step": 263500
|
| 3172 |
+
},
|
| 3173 |
+
{
|
| 3174 |
+
"epoch": 2.76,
|
| 3175 |
+
"learning_rate": 4.019144756092463e-06,
|
| 3176 |
+
"loss": 1.7389,
|
| 3177 |
+
"step": 264000
|
| 3178 |
+
},
|
| 3179 |
+
{
|
| 3180 |
+
"epoch": 2.76,
|
| 3181 |
+
"learning_rate": 3.932059802979003e-06,
|
| 3182 |
+
"loss": 1.6828,
|
| 3183 |
+
"step": 264500
|
| 3184 |
+
},
|
| 3185 |
+
{
|
| 3186 |
+
"epoch": 2.77,
|
| 3187 |
+
"learning_rate": 3.844974849865541e-06,
|
| 3188 |
+
"loss": 1.7122,
|
| 3189 |
+
"step": 265000
|
| 3190 |
+
},
|
| 3191 |
+
{
|
| 3192 |
+
"epoch": 2.77,
|
| 3193 |
+
"learning_rate": 3.75788989675208e-06,
|
| 3194 |
+
"loss": 1.7356,
|
| 3195 |
+
"step": 265500
|
| 3196 |
+
},
|
| 3197 |
+
{
|
| 3198 |
+
"epoch": 2.78,
|
| 3199 |
+
"learning_rate": 3.6708049436386187e-06,
|
| 3200 |
+
"loss": 1.7251,
|
| 3201 |
+
"step": 266000
|
| 3202 |
+
},
|
| 3203 |
+
{
|
| 3204 |
+
"epoch": 2.78,
|
| 3205 |
+
"learning_rate": 3.583719990525157e-06,
|
| 3206 |
+
"loss": 1.7069,
|
| 3207 |
+
"step": 266500
|
| 3208 |
+
},
|
| 3209 |
+
{
|
| 3210 |
+
"epoch": 2.79,
|
| 3211 |
+
"learning_rate": 3.496635037411696e-06,
|
| 3212 |
+
"loss": 1.6999,
|
| 3213 |
+
"step": 267000
|
| 3214 |
+
},
|
| 3215 |
+
{
|
| 3216 |
+
"epoch": 2.8,
|
| 3217 |
+
"learning_rate": 3.4095500842982345e-06,
|
| 3218 |
+
"loss": 1.6997,
|
| 3219 |
+
"step": 267500
|
| 3220 |
+
},
|
| 3221 |
+
{
|
| 3222 |
+
"epoch": 2.8,
|
| 3223 |
+
"learning_rate": 3.3224651311847737e-06,
|
| 3224 |
+
"loss": 1.6997,
|
| 3225 |
+
"step": 268000
|
| 3226 |
+
},
|
| 3227 |
+
{
|
| 3228 |
+
"epoch": 2.81,
|
| 3229 |
+
"learning_rate": 3.2353801780713124e-06,
|
| 3230 |
+
"loss": 1.7099,
|
| 3231 |
+
"step": 268500
|
| 3232 |
+
},
|
| 3233 |
+
{
|
| 3234 |
+
"epoch": 2.81,
|
| 3235 |
+
"learning_rate": 3.1482952249578516e-06,
|
| 3236 |
+
"loss": 1.7147,
|
| 3237 |
+
"step": 269000
|
| 3238 |
+
},
|
| 3239 |
+
{
|
| 3240 |
+
"epoch": 2.82,
|
| 3241 |
+
"learning_rate": 3.06121027184439e-06,
|
| 3242 |
+
"loss": 1.7139,
|
| 3243 |
+
"step": 269500
|
| 3244 |
+
},
|
| 3245 |
+
{
|
| 3246 |
+
"epoch": 2.82,
|
| 3247 |
+
"learning_rate": 2.9741253187309286e-06,
|
| 3248 |
+
"loss": 1.7218,
|
| 3249 |
+
"step": 270000
|
| 3250 |
+
},
|
| 3251 |
+
{
|
| 3252 |
+
"epoch": 2.83,
|
| 3253 |
+
"learning_rate": 2.8870403656174674e-06,
|
| 3254 |
+
"loss": 1.7158,
|
| 3255 |
+
"step": 270500
|
| 3256 |
+
},
|
| 3257 |
+
{
|
| 3258 |
+
"epoch": 2.83,
|
| 3259 |
+
"learning_rate": 2.7999554125040057e-06,
|
| 3260 |
+
"loss": 1.6819,
|
| 3261 |
+
"step": 271000
|
| 3262 |
+
},
|
| 3263 |
+
{
|
| 3264 |
+
"epoch": 2.84,
|
| 3265 |
+
"learning_rate": 2.712870459390545e-06,
|
| 3266 |
+
"loss": 1.7058,
|
| 3267 |
+
"step": 271500
|
| 3268 |
+
},
|
| 3269 |
+
{
|
| 3270 |
+
"epoch": 2.84,
|
| 3271 |
+
"learning_rate": 2.6257855062770836e-06,
|
| 3272 |
+
"loss": 1.708,
|
| 3273 |
+
"step": 272000
|
| 3274 |
+
},
|
| 3275 |
+
{
|
| 3276 |
+
"epoch": 2.85,
|
| 3277 |
+
"learning_rate": 2.5387005531636223e-06,
|
| 3278 |
+
"loss": 1.7167,
|
| 3279 |
+
"step": 272500
|
| 3280 |
+
},
|
| 3281 |
+
{
|
| 3282 |
+
"epoch": 2.85,
|
| 3283 |
+
"learning_rate": 2.451615600050161e-06,
|
| 3284 |
+
"loss": 1.7075,
|
| 3285 |
+
"step": 273000
|
| 3286 |
+
},
|
| 3287 |
+
{
|
| 3288 |
+
"epoch": 2.86,
|
| 3289 |
+
"learning_rate": 2.3645306469367e-06,
|
| 3290 |
+
"loss": 1.7125,
|
| 3291 |
+
"step": 273500
|
| 3292 |
+
},
|
| 3293 |
+
{
|
| 3294 |
+
"epoch": 2.86,
|
| 3295 |
+
"learning_rate": 2.2774456938232386e-06,
|
| 3296 |
+
"loss": 1.7116,
|
| 3297 |
+
"step": 274000
|
| 3298 |
+
},
|
| 3299 |
+
{
|
| 3300 |
+
"epoch": 2.87,
|
| 3301 |
+
"learning_rate": 2.1903607407097773e-06,
|
| 3302 |
+
"loss": 1.6871,
|
| 3303 |
+
"step": 274500
|
| 3304 |
+
},
|
| 3305 |
+
{
|
| 3306 |
+
"epoch": 2.87,
|
| 3307 |
+
"learning_rate": 2.103275787596316e-06,
|
| 3308 |
+
"loss": 1.6659,
|
| 3309 |
+
"step": 275000
|
| 3310 |
+
},
|
| 3311 |
+
{
|
| 3312 |
+
"epoch": 2.88,
|
| 3313 |
+
"learning_rate": 2.016190834482855e-06,
|
| 3314 |
+
"loss": 1.6994,
|
| 3315 |
+
"step": 275500
|
| 3316 |
+
},
|
| 3317 |
+
{
|
| 3318 |
+
"epoch": 2.88,
|
| 3319 |
+
"learning_rate": 1.9291058813693935e-06,
|
| 3320 |
+
"loss": 1.6782,
|
| 3321 |
+
"step": 276000
|
| 3322 |
+
},
|
| 3323 |
+
{
|
| 3324 |
+
"epoch": 2.89,
|
| 3325 |
+
"learning_rate": 1.8420209282559325e-06,
|
| 3326 |
+
"loss": 1.6992,
|
| 3327 |
+
"step": 276500
|
| 3328 |
+
},
|
| 3329 |
+
{
|
| 3330 |
+
"epoch": 2.89,
|
| 3331 |
+
"learning_rate": 1.7549359751424712e-06,
|
| 3332 |
+
"loss": 1.6839,
|
| 3333 |
+
"step": 277000
|
| 3334 |
+
},
|
| 3335 |
+
{
|
| 3336 |
+
"epoch": 2.9,
|
| 3337 |
+
"learning_rate": 1.6678510220290096e-06,
|
| 3338 |
+
"loss": 1.7042,
|
| 3339 |
+
"step": 277500
|
| 3340 |
+
},
|
| 3341 |
+
{
|
| 3342 |
+
"epoch": 2.91,
|
| 3343 |
+
"learning_rate": 1.5807660689155485e-06,
|
| 3344 |
+
"loss": 1.6993,
|
| 3345 |
+
"step": 278000
|
| 3346 |
+
},
|
| 3347 |
+
{
|
| 3348 |
+
"epoch": 2.91,
|
| 3349 |
+
"learning_rate": 1.4936811158020872e-06,
|
| 3350 |
+
"loss": 1.7004,
|
| 3351 |
+
"step": 278500
|
| 3352 |
+
},
|
| 3353 |
+
{
|
| 3354 |
+
"epoch": 2.92,
|
| 3355 |
+
"learning_rate": 1.406596162688626e-06,
|
| 3356 |
+
"loss": 1.6947,
|
| 3357 |
+
"step": 279000
|
| 3358 |
+
},
|
| 3359 |
+
{
|
| 3360 |
+
"epoch": 2.92,
|
| 3361 |
+
"learning_rate": 1.319511209575165e-06,
|
| 3362 |
+
"loss": 1.7011,
|
| 3363 |
+
"step": 279500
|
| 3364 |
+
},
|
| 3365 |
+
{
|
| 3366 |
+
"epoch": 2.93,
|
| 3367 |
+
"learning_rate": 1.2324262564617035e-06,
|
| 3368 |
+
"loss": 1.6973,
|
| 3369 |
+
"step": 280000
|
| 3370 |
+
},
|
| 3371 |
+
{
|
| 3372 |
+
"epoch": 2.93,
|
| 3373 |
+
"learning_rate": 1.1453413033482422e-06,
|
| 3374 |
+
"loss": 1.6965,
|
| 3375 |
+
"step": 280500
|
| 3376 |
+
},
|
| 3377 |
+
{
|
| 3378 |
+
"epoch": 2.94,
|
| 3379 |
+
"learning_rate": 1.0582563502347812e-06,
|
| 3380 |
+
"loss": 1.687,
|
| 3381 |
+
"step": 281000
|
| 3382 |
+
},
|
| 3383 |
+
{
|
| 3384 |
+
"epoch": 2.94,
|
| 3385 |
+
"learning_rate": 9.7117139712132e-07,
|
| 3386 |
+
"loss": 1.6907,
|
| 3387 |
+
"step": 281500
|
| 3388 |
+
},
|
| 3389 |
+
{
|
| 3390 |
+
"epoch": 2.95,
|
| 3391 |
+
"learning_rate": 8.840864440078585e-07,
|
| 3392 |
+
"loss": 1.6931,
|
| 3393 |
+
"step": 282000
|
| 3394 |
+
},
|
| 3395 |
+
{
|
| 3396 |
+
"epoch": 2.95,
|
| 3397 |
+
"learning_rate": 7.970014908943974e-07,
|
| 3398 |
+
"loss": 1.7063,
|
| 3399 |
+
"step": 282500
|
| 3400 |
+
},
|
| 3401 |
+
{
|
| 3402 |
+
"epoch": 2.96,
|
| 3403 |
+
"learning_rate": 7.09916537780936e-07,
|
| 3404 |
+
"loss": 1.7135,
|
| 3405 |
+
"step": 283000
|
| 3406 |
+
},
|
| 3407 |
+
{
|
| 3408 |
+
"epoch": 2.96,
|
| 3409 |
+
"learning_rate": 6.228315846674749e-07,
|
| 3410 |
+
"loss": 1.689,
|
| 3411 |
+
"step": 283500
|
| 3412 |
+
},
|
| 3413 |
+
{
|
| 3414 |
+
"epoch": 2.97,
|
| 3415 |
+
"learning_rate": 5.357466315540136e-07,
|
| 3416 |
+
"loss": 1.6676,
|
| 3417 |
+
"step": 284000
|
| 3418 |
+
},
|
| 3419 |
+
{
|
| 3420 |
+
"epoch": 2.97,
|
| 3421 |
+
"learning_rate": 4.486616784405523e-07,
|
| 3422 |
+
"loss": 1.7108,
|
| 3423 |
+
"step": 284500
|
| 3424 |
+
},
|
| 3425 |
+
{
|
| 3426 |
+
"epoch": 2.98,
|
| 3427 |
+
"learning_rate": 3.615767253270911e-07,
|
| 3428 |
+
"loss": 1.6767,
|
| 3429 |
+
"step": 285000
|
| 3430 |
+
},
|
| 3431 |
+
{
|
| 3432 |
+
"epoch": 2.98,
|
| 3433 |
+
"learning_rate": 2.7449177221362985e-07,
|
| 3434 |
+
"loss": 1.6986,
|
| 3435 |
+
"step": 285500
|
| 3436 |
+
},
|
| 3437 |
+
{
|
| 3438 |
+
"epoch": 2.99,
|
| 3439 |
+
"learning_rate": 1.8740681910016862e-07,
|
| 3440 |
+
"loss": 1.6615,
|
| 3441 |
+
"step": 286000
|
| 3442 |
+
},
|
| 3443 |
+
{
|
| 3444 |
+
"epoch": 2.99,
|
| 3445 |
+
"learning_rate": 1.0032186598670735e-07,
|
| 3446 |
+
"loss": 1.6876,
|
| 3447 |
+
"step": 286500
|
| 3448 |
+
},
|
| 3449 |
+
{
|
| 3450 |
+
"epoch": 3.0,
|
| 3451 |
+
"learning_rate": 1.323691287324611e-08,
|
| 3452 |
+
"loss": 1.7034,
|
| 3453 |
+
"step": 287000
|
| 3454 |
+
},
|
| 3455 |
+
{
|
| 3456 |
+
"epoch": 3.0,
|
| 3457 |
+
"step": 287076,
|
| 3458 |
+
"total_flos": 4.9083067456945856e+17,
|
| 3459 |
+
"train_loss": 2.060935147813305,
|
| 3460 |
+
"train_runtime": 51665.6711,
|
| 3461 |
+
"train_samples_per_second": 44.451,
|
| 3462 |
+
"train_steps_per_second": 5.556
|
| 3463 |
+
}
|
| 3464 |
+
],
|
| 3465 |
+
"logging_steps": 500,
|
| 3466 |
+
"max_steps": 287076,
|
| 3467 |
+
"num_train_epochs": 3,
|
| 3468 |
+
"save_steps": 500,
|
| 3469 |
+
"total_flos": 4.9083067456945856e+17,
|
| 3470 |
+
"trial_name": null,
|
| 3471 |
+
"trial_params": null
|
| 3472 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:99b5ce78b785f68e7248ffd1816ea037d3b2028f0ac090be1f2f2b9c0bcdaa52
|
| 3 |
+
size 4472
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|