Shuheng Liu
commited on
Commit
·
d22837a
1
Parent(s):
7cf3089
Uploading model
Browse files- .gitattributes +1 -0
- README.md +86 -0
- all_results.json +25 -0
- config.json +51 -0
- eval_results.json +12 -0
- predict_results.json +10 -0
- predictions.txt +0 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +15 -0
- tokenizer.json +3 -0
- tokenizer_config.json +20 -0
- train_results.json +8 -0
- trainer_state.json +757 -0
- training_args.bin +3 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,86 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
base_model: xlm-roberta-large
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
datasets:
|
| 7 |
+
- uner_all
|
| 8 |
+
metrics:
|
| 9 |
+
- precision
|
| 10 |
+
- recall
|
| 11 |
+
- f1
|
| 12 |
+
- accuracy
|
| 13 |
+
model-index:
|
| 14 |
+
- name: 3e-5lr_4bsz
|
| 15 |
+
results:
|
| 16 |
+
- task:
|
| 17 |
+
name: Token Classification
|
| 18 |
+
type: token-classification
|
| 19 |
+
dataset:
|
| 20 |
+
name: uner_all
|
| 21 |
+
type: uner_all
|
| 22 |
+
config: null
|
| 23 |
+
split: None
|
| 24 |
+
metrics:
|
| 25 |
+
- name: Precision
|
| 26 |
+
type: precision
|
| 27 |
+
value: 0.8566170026292725
|
| 28 |
+
- name: Recall
|
| 29 |
+
type: recall
|
| 30 |
+
value: 0.8522846180676665
|
| 31 |
+
- name: F1
|
| 32 |
+
type: f1
|
| 33 |
+
value: 0.8544453186467348
|
| 34 |
+
- name: Accuracy
|
| 35 |
+
type: accuracy
|
| 36 |
+
value: 0.9842612991521463
|
| 37 |
+
---
|
| 38 |
+
|
| 39 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 40 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 41 |
+
|
| 42 |
+
# 3e-5lr_4bsz
|
| 43 |
+
|
| 44 |
+
This model is a fine-tuned version of [xlm-roberta-large](https://huggingface.co/xlm-roberta-large) on the uner_all dataset.
|
| 45 |
+
It achieves the following results on the evaluation set:
|
| 46 |
+
- Loss: 0.1180
|
| 47 |
+
- Precision: 0.8566
|
| 48 |
+
- Recall: 0.8523
|
| 49 |
+
- F1: 0.8544
|
| 50 |
+
- Accuracy: 0.9843
|
| 51 |
+
|
| 52 |
+
## Model description
|
| 53 |
+
|
| 54 |
+
More information needed
|
| 55 |
+
|
| 56 |
+
## Intended uses & limitations
|
| 57 |
+
|
| 58 |
+
More information needed
|
| 59 |
+
|
| 60 |
+
## Training and evaluation data
|
| 61 |
+
|
| 62 |
+
More information needed
|
| 63 |
+
|
| 64 |
+
## Training procedure
|
| 65 |
+
|
| 66 |
+
### Training hyperparameters
|
| 67 |
+
|
| 68 |
+
The following hyperparameters were used during training:
|
| 69 |
+
- learning_rate: 3e-05
|
| 70 |
+
- train_batch_size: 4
|
| 71 |
+
- eval_batch_size: 4
|
| 72 |
+
- seed: 42
|
| 73 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 74 |
+
- lr_scheduler_type: linear
|
| 75 |
+
- num_epochs: 5.0
|
| 76 |
+
|
| 77 |
+
### Training results
|
| 78 |
+
|
| 79 |
+
|
| 80 |
+
|
| 81 |
+
### Framework versions
|
| 82 |
+
|
| 83 |
+
- Transformers 4.31.0
|
| 84 |
+
- Pytorch 1.10.1+cu113
|
| 85 |
+
- Datasets 2.14.4
|
| 86 |
+
- Tokenizers 0.13.3
|
all_results.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"eval_accuracy": 0.9842612991521463,
|
| 4 |
+
"eval_f1": 0.8544453186467348,
|
| 5 |
+
"eval_loss": 0.11804134398698807,
|
| 6 |
+
"eval_precision": 0.8566170026292725,
|
| 7 |
+
"eval_recall": 0.8522846180676665,
|
| 8 |
+
"eval_runtime": 39.8443,
|
| 9 |
+
"eval_samples": 6773,
|
| 10 |
+
"eval_samples_per_second": 169.987,
|
| 11 |
+
"eval_steps_per_second": 42.515,
|
| 12 |
+
"predict_accuracy": 0.9861662964870078,
|
| 13 |
+
"predict_f1": 0.8785117691723614,
|
| 14 |
+
"predict_loss": 0.10341698676347733,
|
| 15 |
+
"predict_precision": 0.883206106870229,
|
| 16 |
+
"predict_recall": 0.8738670694864048,
|
| 17 |
+
"predict_runtime": 45.4563,
|
| 18 |
+
"predict_samples_per_second": 170.097,
|
| 19 |
+
"predict_steps_per_second": 42.524,
|
| 20 |
+
"train_loss": 0.0358083400544193,
|
| 21 |
+
"train_runtime": 10226.935,
|
| 22 |
+
"train_samples": 48960,
|
| 23 |
+
"train_samples_per_second": 23.937,
|
| 24 |
+
"train_steps_per_second": 5.984
|
| 25 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "xlm-roberta-large",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"XLMRobertaForTokenClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"finetuning_task": "ner",
|
| 11 |
+
"hidden_act": "gelu",
|
| 12 |
+
"hidden_dropout_prob": 0.1,
|
| 13 |
+
"hidden_size": 1024,
|
| 14 |
+
"id2label": {
|
| 15 |
+
"0": "O",
|
| 16 |
+
"1": "B-PER",
|
| 17 |
+
"2": "I-PER",
|
| 18 |
+
"3": "B-ORG",
|
| 19 |
+
"4": "I-ORG",
|
| 20 |
+
"5": "B-LOC",
|
| 21 |
+
"6": "I-LOC",
|
| 22 |
+
"7": "B-OTH",
|
| 23 |
+
"8": "I-OTH"
|
| 24 |
+
},
|
| 25 |
+
"initializer_range": 0.02,
|
| 26 |
+
"intermediate_size": 4096,
|
| 27 |
+
"label2id": {
|
| 28 |
+
"B-LOC": 5,
|
| 29 |
+
"B-ORG": 3,
|
| 30 |
+
"B-OTH": 7,
|
| 31 |
+
"B-PER": 1,
|
| 32 |
+
"I-LOC": 6,
|
| 33 |
+
"I-ORG": 4,
|
| 34 |
+
"I-OTH": 8,
|
| 35 |
+
"I-PER": 2,
|
| 36 |
+
"O": 0
|
| 37 |
+
},
|
| 38 |
+
"layer_norm_eps": 1e-05,
|
| 39 |
+
"max_position_embeddings": 514,
|
| 40 |
+
"model_type": "xlm-roberta",
|
| 41 |
+
"num_attention_heads": 16,
|
| 42 |
+
"num_hidden_layers": 24,
|
| 43 |
+
"output_past": true,
|
| 44 |
+
"pad_token_id": 1,
|
| 45 |
+
"position_embedding_type": "absolute",
|
| 46 |
+
"torch_dtype": "float32",
|
| 47 |
+
"transformers_version": "4.31.0",
|
| 48 |
+
"type_vocab_size": 1,
|
| 49 |
+
"use_cache": true,
|
| 50 |
+
"vocab_size": 250002
|
| 51 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"eval_accuracy": 0.9842612991521463,
|
| 4 |
+
"eval_f1": 0.8544453186467348,
|
| 5 |
+
"eval_loss": 0.11804134398698807,
|
| 6 |
+
"eval_precision": 0.8566170026292725,
|
| 7 |
+
"eval_recall": 0.8522846180676665,
|
| 8 |
+
"eval_runtime": 39.8443,
|
| 9 |
+
"eval_samples": 6773,
|
| 10 |
+
"eval_samples_per_second": 169.987,
|
| 11 |
+
"eval_steps_per_second": 42.515
|
| 12 |
+
}
|
predict_results.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"predict_accuracy": 0.9861662964870078,
|
| 3 |
+
"predict_f1": 0.8785117691723614,
|
| 4 |
+
"predict_loss": 0.10341698676347733,
|
| 5 |
+
"predict_precision": 0.883206106870229,
|
| 6 |
+
"predict_recall": 0.8738670694864048,
|
| 7 |
+
"predict_runtime": 45.4563,
|
| 8 |
+
"predict_samples_per_second": 170.097,
|
| 9 |
+
"predict_steps_per_second": 42.524
|
| 10 |
+
}
|
predictions.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:02ebcfb73199ea1d83619dcf49fcf5cc65541ac66c9efc2ca4af04ff3324c111
|
| 3 |
+
size 2235532275
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"cls_token": "<s>",
|
| 4 |
+
"eos_token": "</s>",
|
| 5 |
+
"mask_token": {
|
| 6 |
+
"content": "<mask>",
|
| 7 |
+
"lstrip": true,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false
|
| 11 |
+
},
|
| 12 |
+
"pad_token": "<pad>",
|
| 13 |
+
"sep_token": "</s>",
|
| 14 |
+
"unk_token": "<unk>"
|
| 15 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f2c509a525eb51aebb33fb59c24ee923c1d4c1db23c3ae81fe05ccf354084f7b
|
| 3 |
+
size 17082758
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": true,
|
| 3 |
+
"bos_token": "<s>",
|
| 4 |
+
"clean_up_tokenization_spaces": true,
|
| 5 |
+
"cls_token": "<s>",
|
| 6 |
+
"eos_token": "</s>",
|
| 7 |
+
"mask_token": {
|
| 8 |
+
"__type": "AddedToken",
|
| 9 |
+
"content": "<mask>",
|
| 10 |
+
"lstrip": true,
|
| 11 |
+
"normalized": true,
|
| 12 |
+
"rstrip": false,
|
| 13 |
+
"single_word": false
|
| 14 |
+
},
|
| 15 |
+
"model_max_length": 512,
|
| 16 |
+
"pad_token": "<pad>",
|
| 17 |
+
"sep_token": "</s>",
|
| 18 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
| 19 |
+
"unk_token": "<unk>"
|
| 20 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"train_loss": 0.0358083400544193,
|
| 4 |
+
"train_runtime": 10226.935,
|
| 5 |
+
"train_samples": 48960,
|
| 6 |
+
"train_samples_per_second": 23.937,
|
| 7 |
+
"train_steps_per_second": 5.984
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,757 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 5.0,
|
| 5 |
+
"global_step": 61200,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.04,
|
| 12 |
+
"learning_rate": 2.9754901960784317e-05,
|
| 13 |
+
"loss": 0.2061,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.08,
|
| 18 |
+
"learning_rate": 2.9509803921568626e-05,
|
| 19 |
+
"loss": 0.1319,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.12,
|
| 24 |
+
"learning_rate": 2.9264705882352942e-05,
|
| 25 |
+
"loss": 0.1099,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.16,
|
| 30 |
+
"learning_rate": 2.9019607843137255e-05,
|
| 31 |
+
"loss": 0.1096,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.2,
|
| 36 |
+
"learning_rate": 2.877450980392157e-05,
|
| 37 |
+
"loss": 0.1035,
|
| 38 |
+
"step": 2500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.25,
|
| 42 |
+
"learning_rate": 2.8529411764705883e-05,
|
| 43 |
+
"loss": 0.1015,
|
| 44 |
+
"step": 3000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.29,
|
| 48 |
+
"learning_rate": 2.8284313725490196e-05,
|
| 49 |
+
"loss": 0.0842,
|
| 50 |
+
"step": 3500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.33,
|
| 54 |
+
"learning_rate": 2.8039215686274512e-05,
|
| 55 |
+
"loss": 0.0844,
|
| 56 |
+
"step": 4000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.37,
|
| 60 |
+
"learning_rate": 2.7794117647058824e-05,
|
| 61 |
+
"loss": 0.0702,
|
| 62 |
+
"step": 4500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.41,
|
| 66 |
+
"learning_rate": 2.7549019607843137e-05,
|
| 67 |
+
"loss": 0.0766,
|
| 68 |
+
"step": 5000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.45,
|
| 72 |
+
"learning_rate": 2.730392156862745e-05,
|
| 73 |
+
"loss": 0.0811,
|
| 74 |
+
"step": 5500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.49,
|
| 78 |
+
"learning_rate": 2.7058823529411766e-05,
|
| 79 |
+
"loss": 0.072,
|
| 80 |
+
"step": 6000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.53,
|
| 84 |
+
"learning_rate": 2.6813725490196082e-05,
|
| 85 |
+
"loss": 0.0667,
|
| 86 |
+
"step": 6500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.57,
|
| 90 |
+
"learning_rate": 2.656862745098039e-05,
|
| 91 |
+
"loss": 0.0753,
|
| 92 |
+
"step": 7000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.61,
|
| 96 |
+
"learning_rate": 2.6323529411764707e-05,
|
| 97 |
+
"loss": 0.0689,
|
| 98 |
+
"step": 7500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.65,
|
| 102 |
+
"learning_rate": 2.607843137254902e-05,
|
| 103 |
+
"loss": 0.0614,
|
| 104 |
+
"step": 8000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.69,
|
| 108 |
+
"learning_rate": 2.5833333333333336e-05,
|
| 109 |
+
"loss": 0.0643,
|
| 110 |
+
"step": 8500
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.74,
|
| 114 |
+
"learning_rate": 2.5588235294117648e-05,
|
| 115 |
+
"loss": 0.0687,
|
| 116 |
+
"step": 9000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.78,
|
| 120 |
+
"learning_rate": 2.534313725490196e-05,
|
| 121 |
+
"loss": 0.0674,
|
| 122 |
+
"step": 9500
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.82,
|
| 126 |
+
"learning_rate": 2.5098039215686277e-05,
|
| 127 |
+
"loss": 0.0588,
|
| 128 |
+
"step": 10000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.86,
|
| 132 |
+
"learning_rate": 2.485294117647059e-05,
|
| 133 |
+
"loss": 0.0676,
|
| 134 |
+
"step": 10500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.9,
|
| 138 |
+
"learning_rate": 2.4607843137254902e-05,
|
| 139 |
+
"loss": 0.0657,
|
| 140 |
+
"step": 11000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.94,
|
| 144 |
+
"learning_rate": 2.4362745098039215e-05,
|
| 145 |
+
"loss": 0.0595,
|
| 146 |
+
"step": 11500
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.98,
|
| 150 |
+
"learning_rate": 2.411764705882353e-05,
|
| 151 |
+
"loss": 0.0641,
|
| 152 |
+
"step": 12000
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 1.02,
|
| 156 |
+
"learning_rate": 2.3872549019607843e-05,
|
| 157 |
+
"loss": 0.0573,
|
| 158 |
+
"step": 12500
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 1.06,
|
| 162 |
+
"learning_rate": 2.3627450980392156e-05,
|
| 163 |
+
"loss": 0.0446,
|
| 164 |
+
"step": 13000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 1.1,
|
| 168 |
+
"learning_rate": 2.3382352941176472e-05,
|
| 169 |
+
"loss": 0.0403,
|
| 170 |
+
"step": 13500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 1.14,
|
| 174 |
+
"learning_rate": 2.3137254901960785e-05,
|
| 175 |
+
"loss": 0.0389,
|
| 176 |
+
"step": 14000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 1.18,
|
| 180 |
+
"learning_rate": 2.2892156862745097e-05,
|
| 181 |
+
"loss": 0.0438,
|
| 182 |
+
"step": 14500
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 1.23,
|
| 186 |
+
"learning_rate": 2.2647058823529413e-05,
|
| 187 |
+
"loss": 0.0439,
|
| 188 |
+
"step": 15000
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 1.27,
|
| 192 |
+
"learning_rate": 2.2401960784313726e-05,
|
| 193 |
+
"loss": 0.0495,
|
| 194 |
+
"step": 15500
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 1.31,
|
| 198 |
+
"learning_rate": 2.2156862745098042e-05,
|
| 199 |
+
"loss": 0.047,
|
| 200 |
+
"step": 16000
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 1.35,
|
| 204 |
+
"learning_rate": 2.191176470588235e-05,
|
| 205 |
+
"loss": 0.0501,
|
| 206 |
+
"step": 16500
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 1.39,
|
| 210 |
+
"learning_rate": 2.1666666666666667e-05,
|
| 211 |
+
"loss": 0.0517,
|
| 212 |
+
"step": 17000
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 1.43,
|
| 216 |
+
"learning_rate": 2.1421568627450983e-05,
|
| 217 |
+
"loss": 0.0452,
|
| 218 |
+
"step": 17500
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 1.47,
|
| 222 |
+
"learning_rate": 2.1176470588235296e-05,
|
| 223 |
+
"loss": 0.0459,
|
| 224 |
+
"step": 18000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 1.51,
|
| 228 |
+
"learning_rate": 2.0931372549019608e-05,
|
| 229 |
+
"loss": 0.0451,
|
| 230 |
+
"step": 18500
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 1.55,
|
| 234 |
+
"learning_rate": 2.068627450980392e-05,
|
| 235 |
+
"loss": 0.0418,
|
| 236 |
+
"step": 19000
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 1.59,
|
| 240 |
+
"learning_rate": 2.0441176470588237e-05,
|
| 241 |
+
"loss": 0.0446,
|
| 242 |
+
"step": 19500
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 1.63,
|
| 246 |
+
"learning_rate": 2.019607843137255e-05,
|
| 247 |
+
"loss": 0.0478,
|
| 248 |
+
"step": 20000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 1.67,
|
| 252 |
+
"learning_rate": 1.9950980392156862e-05,
|
| 253 |
+
"loss": 0.0387,
|
| 254 |
+
"step": 20500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 1.72,
|
| 258 |
+
"learning_rate": 1.9705882352941178e-05,
|
| 259 |
+
"loss": 0.04,
|
| 260 |
+
"step": 21000
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 1.76,
|
| 264 |
+
"learning_rate": 1.946078431372549e-05,
|
| 265 |
+
"loss": 0.048,
|
| 266 |
+
"step": 21500
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 1.8,
|
| 270 |
+
"learning_rate": 1.9215686274509803e-05,
|
| 271 |
+
"loss": 0.0382,
|
| 272 |
+
"step": 22000
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 1.84,
|
| 276 |
+
"learning_rate": 1.8970588235294116e-05,
|
| 277 |
+
"loss": 0.0402,
|
| 278 |
+
"step": 22500
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 1.88,
|
| 282 |
+
"learning_rate": 1.8725490196078432e-05,
|
| 283 |
+
"loss": 0.0409,
|
| 284 |
+
"step": 23000
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 1.92,
|
| 288 |
+
"learning_rate": 1.8480392156862748e-05,
|
| 289 |
+
"loss": 0.0403,
|
| 290 |
+
"step": 23500
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 1.96,
|
| 294 |
+
"learning_rate": 1.8235294117647057e-05,
|
| 295 |
+
"loss": 0.0577,
|
| 296 |
+
"step": 24000
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 2.0,
|
| 300 |
+
"learning_rate": 1.7990196078431373e-05,
|
| 301 |
+
"loss": 0.0434,
|
| 302 |
+
"step": 24500
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 2.04,
|
| 306 |
+
"learning_rate": 1.7745098039215686e-05,
|
| 307 |
+
"loss": 0.0304,
|
| 308 |
+
"step": 25000
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 2.08,
|
| 312 |
+
"learning_rate": 1.7500000000000002e-05,
|
| 313 |
+
"loss": 0.0227,
|
| 314 |
+
"step": 25500
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 2.12,
|
| 318 |
+
"learning_rate": 1.7254901960784314e-05,
|
| 319 |
+
"loss": 0.0307,
|
| 320 |
+
"step": 26000
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 2.17,
|
| 324 |
+
"learning_rate": 1.7009803921568627e-05,
|
| 325 |
+
"loss": 0.0266,
|
| 326 |
+
"step": 26500
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 2.21,
|
| 330 |
+
"learning_rate": 1.6764705882352943e-05,
|
| 331 |
+
"loss": 0.0319,
|
| 332 |
+
"step": 27000
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 2.25,
|
| 336 |
+
"learning_rate": 1.6519607843137256e-05,
|
| 337 |
+
"loss": 0.0324,
|
| 338 |
+
"step": 27500
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 2.29,
|
| 342 |
+
"learning_rate": 1.627450980392157e-05,
|
| 343 |
+
"loss": 0.0256,
|
| 344 |
+
"step": 28000
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 2.33,
|
| 348 |
+
"learning_rate": 1.602941176470588e-05,
|
| 349 |
+
"loss": 0.0292,
|
| 350 |
+
"step": 28500
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 2.37,
|
| 354 |
+
"learning_rate": 1.5784313725490197e-05,
|
| 355 |
+
"loss": 0.0284,
|
| 356 |
+
"step": 29000
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 2.41,
|
| 360 |
+
"learning_rate": 1.5539215686274513e-05,
|
| 361 |
+
"loss": 0.0307,
|
| 362 |
+
"step": 29500
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 2.45,
|
| 366 |
+
"learning_rate": 1.5294117647058822e-05,
|
| 367 |
+
"loss": 0.0333,
|
| 368 |
+
"step": 30000
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 2.49,
|
| 372 |
+
"learning_rate": 1.5049019607843138e-05,
|
| 373 |
+
"loss": 0.0316,
|
| 374 |
+
"step": 30500
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 2.53,
|
| 378 |
+
"learning_rate": 1.4803921568627453e-05,
|
| 379 |
+
"loss": 0.0298,
|
| 380 |
+
"step": 31000
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 2.57,
|
| 384 |
+
"learning_rate": 1.4558823529411765e-05,
|
| 385 |
+
"loss": 0.0255,
|
| 386 |
+
"step": 31500
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 2.61,
|
| 390 |
+
"learning_rate": 1.431372549019608e-05,
|
| 391 |
+
"loss": 0.0274,
|
| 392 |
+
"step": 32000
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 2.66,
|
| 396 |
+
"learning_rate": 1.4068627450980392e-05,
|
| 397 |
+
"loss": 0.0268,
|
| 398 |
+
"step": 32500
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 2.7,
|
| 402 |
+
"learning_rate": 1.3823529411764705e-05,
|
| 403 |
+
"loss": 0.0263,
|
| 404 |
+
"step": 33000
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 2.74,
|
| 408 |
+
"learning_rate": 1.357843137254902e-05,
|
| 409 |
+
"loss": 0.0208,
|
| 410 |
+
"step": 33500
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 2.78,
|
| 414 |
+
"learning_rate": 1.3333333333333333e-05,
|
| 415 |
+
"loss": 0.0272,
|
| 416 |
+
"step": 34000
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 2.82,
|
| 420 |
+
"learning_rate": 1.3088235294117648e-05,
|
| 421 |
+
"loss": 0.0245,
|
| 422 |
+
"step": 34500
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 2.86,
|
| 426 |
+
"learning_rate": 1.284313725490196e-05,
|
| 427 |
+
"loss": 0.0245,
|
| 428 |
+
"step": 35000
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 2.9,
|
| 432 |
+
"learning_rate": 1.2598039215686275e-05,
|
| 433 |
+
"loss": 0.0239,
|
| 434 |
+
"step": 35500
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 2.94,
|
| 438 |
+
"learning_rate": 1.2352941176470587e-05,
|
| 439 |
+
"loss": 0.0271,
|
| 440 |
+
"step": 36000
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 2.98,
|
| 444 |
+
"learning_rate": 1.2107843137254903e-05,
|
| 445 |
+
"loss": 0.0226,
|
| 446 |
+
"step": 36500
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 3.02,
|
| 450 |
+
"learning_rate": 1.1862745098039216e-05,
|
| 451 |
+
"loss": 0.0216,
|
| 452 |
+
"step": 37000
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 3.06,
|
| 456 |
+
"learning_rate": 1.161764705882353e-05,
|
| 457 |
+
"loss": 0.0157,
|
| 458 |
+
"step": 37500
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 3.1,
|
| 462 |
+
"learning_rate": 1.1372549019607843e-05,
|
| 463 |
+
"loss": 0.0137,
|
| 464 |
+
"step": 38000
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 3.15,
|
| 468 |
+
"learning_rate": 1.1127450980392157e-05,
|
| 469 |
+
"loss": 0.0122,
|
| 470 |
+
"step": 38500
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 3.19,
|
| 474 |
+
"learning_rate": 1.0882352941176471e-05,
|
| 475 |
+
"loss": 0.0153,
|
| 476 |
+
"step": 39000
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 3.23,
|
| 480 |
+
"learning_rate": 1.0637254901960786e-05,
|
| 481 |
+
"loss": 0.018,
|
| 482 |
+
"step": 39500
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 3.27,
|
| 486 |
+
"learning_rate": 1.0392156862745098e-05,
|
| 487 |
+
"loss": 0.018,
|
| 488 |
+
"step": 40000
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 3.31,
|
| 492 |
+
"learning_rate": 1.0147058823529413e-05,
|
| 493 |
+
"loss": 0.0169,
|
| 494 |
+
"step": 40500
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 3.35,
|
| 498 |
+
"learning_rate": 9.901960784313725e-06,
|
| 499 |
+
"loss": 0.0138,
|
| 500 |
+
"step": 41000
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 3.39,
|
| 504 |
+
"learning_rate": 9.65686274509804e-06,
|
| 505 |
+
"loss": 0.0171,
|
| 506 |
+
"step": 41500
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 3.43,
|
| 510 |
+
"learning_rate": 9.411764705882354e-06,
|
| 511 |
+
"loss": 0.0139,
|
| 512 |
+
"step": 42000
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 3.47,
|
| 516 |
+
"learning_rate": 9.166666666666668e-06,
|
| 517 |
+
"loss": 0.0123,
|
| 518 |
+
"step": 42500
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 3.51,
|
| 522 |
+
"learning_rate": 8.92156862745098e-06,
|
| 523 |
+
"loss": 0.0172,
|
| 524 |
+
"step": 43000
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 3.55,
|
| 528 |
+
"learning_rate": 8.676470588235295e-06,
|
| 529 |
+
"loss": 0.0168,
|
| 530 |
+
"step": 43500
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 3.59,
|
| 534 |
+
"learning_rate": 8.431372549019608e-06,
|
| 535 |
+
"loss": 0.0146,
|
| 536 |
+
"step": 44000
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 3.64,
|
| 540 |
+
"learning_rate": 8.18627450980392e-06,
|
| 541 |
+
"loss": 0.0155,
|
| 542 |
+
"step": 44500
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 3.68,
|
| 546 |
+
"learning_rate": 7.941176470588236e-06,
|
| 547 |
+
"loss": 0.0148,
|
| 548 |
+
"step": 45000
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 3.72,
|
| 552 |
+
"learning_rate": 7.696078431372549e-06,
|
| 553 |
+
"loss": 0.0187,
|
| 554 |
+
"step": 45500
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 3.76,
|
| 558 |
+
"learning_rate": 7.450980392156863e-06,
|
| 559 |
+
"loss": 0.0124,
|
| 560 |
+
"step": 46000
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 3.8,
|
| 564 |
+
"learning_rate": 7.205882352941177e-06,
|
| 565 |
+
"loss": 0.0119,
|
| 566 |
+
"step": 46500
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 3.84,
|
| 570 |
+
"learning_rate": 6.960784313725491e-06,
|
| 571 |
+
"loss": 0.0125,
|
| 572 |
+
"step": 47000
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 3.88,
|
| 576 |
+
"learning_rate": 6.7156862745098045e-06,
|
| 577 |
+
"loss": 0.0157,
|
| 578 |
+
"step": 47500
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 3.92,
|
| 582 |
+
"learning_rate": 6.470588235294118e-06,
|
| 583 |
+
"loss": 0.0149,
|
| 584 |
+
"step": 48000
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 3.96,
|
| 588 |
+
"learning_rate": 6.225490196078432e-06,
|
| 589 |
+
"loss": 0.0179,
|
| 590 |
+
"step": 48500
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 4.0,
|
| 594 |
+
"learning_rate": 5.980392156862746e-06,
|
| 595 |
+
"loss": 0.0142,
|
| 596 |
+
"step": 49000
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 4.04,
|
| 600 |
+
"learning_rate": 5.735294117647058e-06,
|
| 601 |
+
"loss": 0.0111,
|
| 602 |
+
"step": 49500
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 4.08,
|
| 606 |
+
"learning_rate": 5.490196078431373e-06,
|
| 607 |
+
"loss": 0.0056,
|
| 608 |
+
"step": 50000
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 4.13,
|
| 612 |
+
"learning_rate": 5.245098039215686e-06,
|
| 613 |
+
"loss": 0.0051,
|
| 614 |
+
"step": 50500
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 4.17,
|
| 618 |
+
"learning_rate": 4.9999999999999996e-06,
|
| 619 |
+
"loss": 0.0101,
|
| 620 |
+
"step": 51000
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 4.21,
|
| 624 |
+
"learning_rate": 4.754901960784314e-06,
|
| 625 |
+
"loss": 0.0069,
|
| 626 |
+
"step": 51500
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 4.25,
|
| 630 |
+
"learning_rate": 4.509803921568627e-06,
|
| 631 |
+
"loss": 0.0069,
|
| 632 |
+
"step": 52000
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 4.29,
|
| 636 |
+
"learning_rate": 4.264705882352941e-06,
|
| 637 |
+
"loss": 0.0091,
|
| 638 |
+
"step": 52500
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 4.33,
|
| 642 |
+
"learning_rate": 4.019607843137255e-06,
|
| 643 |
+
"loss": 0.0068,
|
| 644 |
+
"step": 53000
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 4.37,
|
| 648 |
+
"learning_rate": 3.7745098039215686e-06,
|
| 649 |
+
"loss": 0.0079,
|
| 650 |
+
"step": 53500
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 4.41,
|
| 654 |
+
"learning_rate": 3.5294117647058825e-06,
|
| 655 |
+
"loss": 0.0139,
|
| 656 |
+
"step": 54000
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 4.45,
|
| 660 |
+
"learning_rate": 3.2843137254901964e-06,
|
| 661 |
+
"loss": 0.0051,
|
| 662 |
+
"step": 54500
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 4.49,
|
| 666 |
+
"learning_rate": 3.03921568627451e-06,
|
| 667 |
+
"loss": 0.0104,
|
| 668 |
+
"step": 55000
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 4.53,
|
| 672 |
+
"learning_rate": 2.7941176470588237e-06,
|
| 673 |
+
"loss": 0.0068,
|
| 674 |
+
"step": 55500
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 4.58,
|
| 678 |
+
"learning_rate": 2.5490196078431376e-06,
|
| 679 |
+
"loss": 0.0102,
|
| 680 |
+
"step": 56000
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 4.62,
|
| 684 |
+
"learning_rate": 2.303921568627451e-06,
|
| 685 |
+
"loss": 0.0107,
|
| 686 |
+
"step": 56500
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 4.66,
|
| 690 |
+
"learning_rate": 2.058823529411765e-06,
|
| 691 |
+
"loss": 0.0093,
|
| 692 |
+
"step": 57000
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 4.7,
|
| 696 |
+
"learning_rate": 1.8137254901960784e-06,
|
| 697 |
+
"loss": 0.0059,
|
| 698 |
+
"step": 57500
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 4.74,
|
| 702 |
+
"learning_rate": 1.5686274509803923e-06,
|
| 703 |
+
"loss": 0.0077,
|
| 704 |
+
"step": 58000
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 4.78,
|
| 708 |
+
"learning_rate": 1.323529411764706e-06,
|
| 709 |
+
"loss": 0.0074,
|
| 710 |
+
"step": 58500
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 4.82,
|
| 714 |
+
"learning_rate": 1.0784313725490197e-06,
|
| 715 |
+
"loss": 0.0076,
|
| 716 |
+
"step": 59000
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 4.86,
|
| 720 |
+
"learning_rate": 8.333333333333333e-07,
|
| 721 |
+
"loss": 0.0062,
|
| 722 |
+
"step": 59500
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 4.9,
|
| 726 |
+
"learning_rate": 5.882352941176471e-07,
|
| 727 |
+
"loss": 0.0073,
|
| 728 |
+
"step": 60000
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 4.94,
|
| 732 |
+
"learning_rate": 3.431372549019608e-07,
|
| 733 |
+
"loss": 0.0088,
|
| 734 |
+
"step": 60500
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 4.98,
|
| 738 |
+
"learning_rate": 9.803921568627452e-08,
|
| 739 |
+
"loss": 0.0053,
|
| 740 |
+
"step": 61000
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 5.0,
|
| 744 |
+
"step": 61200,
|
| 745 |
+
"total_flos": 2.401553971865549e+16,
|
| 746 |
+
"train_loss": 0.0358083400544193,
|
| 747 |
+
"train_runtime": 10226.935,
|
| 748 |
+
"train_samples_per_second": 23.937,
|
| 749 |
+
"train_steps_per_second": 5.984
|
| 750 |
+
}
|
| 751 |
+
],
|
| 752 |
+
"max_steps": 61200,
|
| 753 |
+
"num_train_epochs": 5,
|
| 754 |
+
"total_flos": 2.401553971865549e+16,
|
| 755 |
+
"trial_name": null,
|
| 756 |
+
"trial_params": null
|
| 757 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:180fefa9e717c97a839f58553c52c456ee80140c3f4589356f021f09d2b11f4d
|
| 3 |
+
size 4015
|