Model save
Browse files- README.md +66 -0
- all_results.json +14 -0
- config.json +70 -0
- eval_results.json +9 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- special_tokens_map.json +15 -0
- tokenizer.json +0 -0
- tokenizer_config.json +15 -0
- train_results.json +8 -0
- trainer_state.json +952 -0
- training_args.bin +3 -0
- vocab.json +0 -0
README.md
ADDED
|
@@ -0,0 +1,66 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
base_model: roberta-large-mnli
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
metrics:
|
| 7 |
+
- f1
|
| 8 |
+
model-index:
|
| 9 |
+
- name: roberta-large-mnli-goodreads-bookgenres-Book_cls-5e
|
| 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 |
+
# roberta-large-mnli-goodreads-bookgenres-Book_cls-5e
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [roberta-large-mnli](https://huggingface.co/roberta-large-mnli) on an unknown dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 0.2758
|
| 21 |
+
- F1: 0.5464
|
| 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: 6e-05
|
| 41 |
+
- train_batch_size: 32
|
| 42 |
+
- eval_batch_size: 32
|
| 43 |
+
- seed: 42
|
| 44 |
+
- gradient_accumulation_steps: 4
|
| 45 |
+
- total_train_batch_size: 128
|
| 46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-10
|
| 47 |
+
- lr_scheduler_type: linear
|
| 48 |
+
- num_epochs: 5.0
|
| 49 |
+
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
| Training Loss | Epoch | Step | Validation Loss | F1 |
|
| 53 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
| 54 |
+
| 0.3096 | 1.0 | 62 | 0.2862 | 0.3707 |
|
| 55 |
+
| 0.2863 | 2.0 | 124 | 0.2804 | 0.4422 |
|
| 56 |
+
| 0.2618 | 3.0 | 186 | 0.2773 | 0.4989 |
|
| 57 |
+
| 0.2432 | 4.0 | 248 | 0.2764 | 0.5223 |
|
| 58 |
+
| 0.2241 | 5.0 | 310 | 0.2758 | 0.5464 |
|
| 59 |
+
|
| 60 |
+
|
| 61 |
+
### Framework versions
|
| 62 |
+
|
| 63 |
+
- Transformers 4.33.3
|
| 64 |
+
- Pytorch 2.2.0.dev20231001+cu121
|
| 65 |
+
- Datasets 2.14.5
|
| 66 |
+
- Tokenizers 0.13.3
|
all_results.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 20.0,
|
| 3 |
+
"eval_f1": 0.5832229580573952,
|
| 4 |
+
"eval_loss": 0.3661610186100006,
|
| 5 |
+
"eval_runtime": 2.8821,
|
| 6 |
+
"eval_samples": 989,
|
| 7 |
+
"eval_samples_per_second": 343.154,
|
| 8 |
+
"eval_steps_per_second": 10.756,
|
| 9 |
+
"train_loss": 0.14994276651451666,
|
| 10 |
+
"train_runtime": 1498.2493,
|
| 11 |
+
"train_samples": 7914,
|
| 12 |
+
"train_samples_per_second": 105.643,
|
| 13 |
+
"train_steps_per_second": 0.828
|
| 14 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "roberta-large-mnli",
|
| 3 |
+
"_num_labels": 3,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"RobertaForSequenceClassification"
|
| 6 |
+
],
|
| 7 |
+
"attention_probs_dropout_prob": 0.1,
|
| 8 |
+
"bos_token_id": 0,
|
| 9 |
+
"classifier_dropout": null,
|
| 10 |
+
"eos_token_id": 2,
|
| 11 |
+
"finetuning_task": "text-classification",
|
| 12 |
+
"hidden_act": "gelu",
|
| 13 |
+
"hidden_dropout_prob": 0.1,
|
| 14 |
+
"hidden_size": 1024,
|
| 15 |
+
"id2label": {
|
| 16 |
+
"0": "History & Politics",
|
| 17 |
+
"1": "Health & Medicine",
|
| 18 |
+
"2": "Mystery & Thriller",
|
| 19 |
+
"3": "Arts & Design",
|
| 20 |
+
"4": "Self-Help & Wellness",
|
| 21 |
+
"5": "Sports & Recreation",
|
| 22 |
+
"6": "Non-Fiction",
|
| 23 |
+
"7": "Science Fiction & Fantasy",
|
| 24 |
+
"8": "Countries & Geography",
|
| 25 |
+
"9": "Other",
|
| 26 |
+
"10": "Nature & Environment",
|
| 27 |
+
"11": "Business & Finance",
|
| 28 |
+
"12": "Romance",
|
| 29 |
+
"13": "Philosophy & Religion",
|
| 30 |
+
"14": "Literature & Fiction",
|
| 31 |
+
"15": "Science & Technology",
|
| 32 |
+
"16": "Children & Young Adult",
|
| 33 |
+
"17": "Food & Cooking"
|
| 34 |
+
},
|
| 35 |
+
"initializer_range": 0.02,
|
| 36 |
+
"intermediate_size": 4096,
|
| 37 |
+
"label2id": {
|
| 38 |
+
"Arts & Design": 3,
|
| 39 |
+
"Business & Finance": 11,
|
| 40 |
+
"Children & Young Adult": 16,
|
| 41 |
+
"Countries & Geography": 8,
|
| 42 |
+
"Food & Cooking": 17,
|
| 43 |
+
"Health & Medicine": 1,
|
| 44 |
+
"History & Politics": 0,
|
| 45 |
+
"Literature & Fiction": 14,
|
| 46 |
+
"Mystery & Thriller": 2,
|
| 47 |
+
"Nature & Environment": 10,
|
| 48 |
+
"Non-Fiction": 6,
|
| 49 |
+
"Other": 9,
|
| 50 |
+
"Philosophy & Religion": 13,
|
| 51 |
+
"Romance": 12,
|
| 52 |
+
"Science & Technology": 15,
|
| 53 |
+
"Science Fiction & Fantasy": 7,
|
| 54 |
+
"Self-Help & Wellness": 4,
|
| 55 |
+
"Sports & Recreation": 5
|
| 56 |
+
},
|
| 57 |
+
"layer_norm_eps": 1e-05,
|
| 58 |
+
"max_position_embeddings": 514,
|
| 59 |
+
"model_type": "roberta",
|
| 60 |
+
"num_attention_heads": 16,
|
| 61 |
+
"num_hidden_layers": 24,
|
| 62 |
+
"pad_token_id": 1,
|
| 63 |
+
"position_embedding_type": "absolute",
|
| 64 |
+
"problem_type": "multi_label_classification",
|
| 65 |
+
"torch_dtype": "float32",
|
| 66 |
+
"transformers_version": "4.33.3",
|
| 67 |
+
"type_vocab_size": 1,
|
| 68 |
+
"use_cache": true,
|
| 69 |
+
"vocab_size": 50265
|
| 70 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 20.0,
|
| 3 |
+
"eval_f1": 0.5832229580573952,
|
| 4 |
+
"eval_loss": 0.3661610186100006,
|
| 5 |
+
"eval_runtime": 2.8821,
|
| 6 |
+
"eval_samples": 989,
|
| 7 |
+
"eval_samples_per_second": 343.154,
|
| 8 |
+
"eval_steps_per_second": 10.756
|
| 9 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8601937cac48a5151f1d4c48445cb8b152e8e9bc875f9ee17304ea18ff02913e
|
| 3 |
+
size 1421561016
|
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
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"bos_token": "<s>",
|
| 4 |
+
"clean_up_tokenization_spaces": true,
|
| 5 |
+
"cls_token": "<s>",
|
| 6 |
+
"eos_token": "</s>",
|
| 7 |
+
"errors": "replace",
|
| 8 |
+
"mask_token": "<mask>",
|
| 9 |
+
"model_max_length": 512,
|
| 10 |
+
"pad_token": "<pad>",
|
| 11 |
+
"sep_token": "</s>",
|
| 12 |
+
"tokenizer_class": "RobertaTokenizer",
|
| 13 |
+
"trim_offsets": true,
|
| 14 |
+
"unk_token": "<unk>"
|
| 15 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 20.0,
|
| 3 |
+
"train_loss": 0.14994276651451666,
|
| 4 |
+
"train_runtime": 1498.2493,
|
| 5 |
+
"train_samples": 7914,
|
| 6 |
+
"train_samples_per_second": 105.643,
|
| 7 |
+
"train_steps_per_second": 0.828
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,952 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 20.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1240,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.16,
|
| 13 |
+
"learning_rate": 5.951612903225807e-05,
|
| 14 |
+
"loss": 0.4848,
|
| 15 |
+
"step": 10
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.32,
|
| 19 |
+
"learning_rate": 5.9032258064516134e-05,
|
| 20 |
+
"loss": 0.3412,
|
| 21 |
+
"step": 20
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.48,
|
| 25 |
+
"learning_rate": 5.854838709677419e-05,
|
| 26 |
+
"loss": 0.3195,
|
| 27 |
+
"step": 30
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.65,
|
| 31 |
+
"learning_rate": 5.806451612903226e-05,
|
| 32 |
+
"loss": 0.3107,
|
| 33 |
+
"step": 40
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.81,
|
| 37 |
+
"learning_rate": 5.7580645161290325e-05,
|
| 38 |
+
"loss": 0.3062,
|
| 39 |
+
"step": 50
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.97,
|
| 43 |
+
"learning_rate": 5.709677419354839e-05,
|
| 44 |
+
"loss": 0.3047,
|
| 45 |
+
"step": 60
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 1.0,
|
| 49 |
+
"eval_f1": 0.3600605143721634,
|
| 50 |
+
"eval_loss": 0.28778037428855896,
|
| 51 |
+
"eval_runtime": 2.9163,
|
| 52 |
+
"eval_samples_per_second": 339.124,
|
| 53 |
+
"eval_steps_per_second": 10.63,
|
| 54 |
+
"step": 62
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 1.13,
|
| 58 |
+
"learning_rate": 5.661290322580646e-05,
|
| 59 |
+
"loss": 0.2971,
|
| 60 |
+
"step": 70
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 1.29,
|
| 64 |
+
"learning_rate": 5.612903225806452e-05,
|
| 65 |
+
"loss": 0.2923,
|
| 66 |
+
"step": 80
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 1.45,
|
| 70 |
+
"learning_rate": 5.5645161290322576e-05,
|
| 71 |
+
"loss": 0.2913,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 1.61,
|
| 76 |
+
"learning_rate": 5.516129032258064e-05,
|
| 77 |
+
"loss": 0.2868,
|
| 78 |
+
"step": 100
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 1.77,
|
| 82 |
+
"learning_rate": 5.467741935483871e-05,
|
| 83 |
+
"loss": 0.2876,
|
| 84 |
+
"step": 110
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 1.94,
|
| 88 |
+
"learning_rate": 5.4193548387096774e-05,
|
| 89 |
+
"loss": 0.2809,
|
| 90 |
+
"step": 120
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 2.0,
|
| 94 |
+
"eval_f1": 0.4606093878671425,
|
| 95 |
+
"eval_loss": 0.2768673002719879,
|
| 96 |
+
"eval_runtime": 2.9476,
|
| 97 |
+
"eval_samples_per_second": 335.524,
|
| 98 |
+
"eval_steps_per_second": 10.517,
|
| 99 |
+
"step": 124
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 2.1,
|
| 103 |
+
"learning_rate": 5.370967741935484e-05,
|
| 104 |
+
"loss": 0.2685,
|
| 105 |
+
"step": 130
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 2.26,
|
| 109 |
+
"learning_rate": 5.3225806451612906e-05,
|
| 110 |
+
"loss": 0.2658,
|
| 111 |
+
"step": 140
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 2.42,
|
| 115 |
+
"learning_rate": 5.2741935483870966e-05,
|
| 116 |
+
"loss": 0.2706,
|
| 117 |
+
"step": 150
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 2.58,
|
| 121 |
+
"learning_rate": 5.225806451612903e-05,
|
| 122 |
+
"loss": 0.2613,
|
| 123 |
+
"step": 160
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 2.74,
|
| 127 |
+
"learning_rate": 5.17741935483871e-05,
|
| 128 |
+
"loss": 0.2634,
|
| 129 |
+
"step": 170
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 2.9,
|
| 133 |
+
"learning_rate": 5.1290322580645164e-05,
|
| 134 |
+
"loss": 0.2584,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 3.0,
|
| 139 |
+
"eval_f1": 0.48365306673871933,
|
| 140 |
+
"eval_loss": 0.2766420543193817,
|
| 141 |
+
"eval_runtime": 2.9111,
|
| 142 |
+
"eval_samples_per_second": 339.73,
|
| 143 |
+
"eval_steps_per_second": 10.649,
|
| 144 |
+
"step": 186
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 3.06,
|
| 148 |
+
"learning_rate": 5.080645161290323e-05,
|
| 149 |
+
"loss": 0.259,
|
| 150 |
+
"step": 190
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 3.23,
|
| 154 |
+
"learning_rate": 5.0322580645161296e-05,
|
| 155 |
+
"loss": 0.2427,
|
| 156 |
+
"step": 200
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 3.39,
|
| 160 |
+
"learning_rate": 4.9838709677419356e-05,
|
| 161 |
+
"loss": 0.2389,
|
| 162 |
+
"step": 210
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 3.55,
|
| 166 |
+
"learning_rate": 4.935483870967742e-05,
|
| 167 |
+
"loss": 0.2441,
|
| 168 |
+
"step": 220
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 3.71,
|
| 172 |
+
"learning_rate": 4.887096774193549e-05,
|
| 173 |
+
"loss": 0.2416,
|
| 174 |
+
"step": 230
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 3.87,
|
| 178 |
+
"learning_rate": 4.838709677419355e-05,
|
| 179 |
+
"loss": 0.2382,
|
| 180 |
+
"step": 240
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 4.0,
|
| 184 |
+
"eval_f1": 0.49434656849855374,
|
| 185 |
+
"eval_loss": 0.28233975172042847,
|
| 186 |
+
"eval_runtime": 2.9046,
|
| 187 |
+
"eval_samples_per_second": 340.492,
|
| 188 |
+
"eval_steps_per_second": 10.673,
|
| 189 |
+
"step": 248
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 4.03,
|
| 193 |
+
"learning_rate": 4.790322580645161e-05,
|
| 194 |
+
"loss": 0.2327,
|
| 195 |
+
"step": 250
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 4.19,
|
| 199 |
+
"learning_rate": 4.741935483870968e-05,
|
| 200 |
+
"loss": 0.2168,
|
| 201 |
+
"step": 260
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 4.35,
|
| 205 |
+
"learning_rate": 4.693548387096774e-05,
|
| 206 |
+
"loss": 0.2198,
|
| 207 |
+
"step": 270
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 4.52,
|
| 211 |
+
"learning_rate": 4.6451612903225805e-05,
|
| 212 |
+
"loss": 0.221,
|
| 213 |
+
"step": 280
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 4.68,
|
| 217 |
+
"learning_rate": 4.596774193548387e-05,
|
| 218 |
+
"loss": 0.2191,
|
| 219 |
+
"step": 290
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 4.84,
|
| 223 |
+
"learning_rate": 4.548387096774194e-05,
|
| 224 |
+
"loss": 0.2126,
|
| 225 |
+
"step": 300
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 5.0,
|
| 229 |
+
"learning_rate": 4.5e-05,
|
| 230 |
+
"loss": 0.2161,
|
| 231 |
+
"step": 310
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 5.0,
|
| 235 |
+
"eval_f1": 0.5236882322975038,
|
| 236 |
+
"eval_loss": 0.28145599365234375,
|
| 237 |
+
"eval_runtime": 2.9136,
|
| 238 |
+
"eval_samples_per_second": 339.438,
|
| 239 |
+
"eval_steps_per_second": 10.64,
|
| 240 |
+
"step": 310
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 5.16,
|
| 244 |
+
"learning_rate": 4.451612903225807e-05,
|
| 245 |
+
"loss": 0.1952,
|
| 246 |
+
"step": 320
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 5.32,
|
| 250 |
+
"learning_rate": 4.403225806451613e-05,
|
| 251 |
+
"loss": 0.1996,
|
| 252 |
+
"step": 330
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 5.48,
|
| 256 |
+
"learning_rate": 4.3548387096774194e-05,
|
| 257 |
+
"loss": 0.1921,
|
| 258 |
+
"step": 340
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 5.65,
|
| 262 |
+
"learning_rate": 4.306451612903226e-05,
|
| 263 |
+
"loss": 0.1966,
|
| 264 |
+
"step": 350
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 5.81,
|
| 268 |
+
"learning_rate": 4.2580645161290327e-05,
|
| 269 |
+
"loss": 0.2023,
|
| 270 |
+
"step": 360
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 5.97,
|
| 274 |
+
"learning_rate": 4.209677419354839e-05,
|
| 275 |
+
"loss": 0.1903,
|
| 276 |
+
"step": 370
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 6.0,
|
| 280 |
+
"eval_f1": 0.5535545023696682,
|
| 281 |
+
"eval_loss": 0.29538020491600037,
|
| 282 |
+
"eval_runtime": 2.9433,
|
| 283 |
+
"eval_samples_per_second": 336.013,
|
| 284 |
+
"eval_steps_per_second": 10.532,
|
| 285 |
+
"step": 372
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 6.13,
|
| 289 |
+
"learning_rate": 4.161290322580646e-05,
|
| 290 |
+
"loss": 0.1854,
|
| 291 |
+
"step": 380
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 6.29,
|
| 295 |
+
"learning_rate": 4.112903225806451e-05,
|
| 296 |
+
"loss": 0.1784,
|
| 297 |
+
"step": 390
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 6.45,
|
| 301 |
+
"learning_rate": 4.064516129032258e-05,
|
| 302 |
+
"loss": 0.1776,
|
| 303 |
+
"step": 400
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 6.61,
|
| 307 |
+
"learning_rate": 4.0161290322580643e-05,
|
| 308 |
+
"loss": 0.1746,
|
| 309 |
+
"step": 410
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 6.77,
|
| 313 |
+
"learning_rate": 3.967741935483871e-05,
|
| 314 |
+
"loss": 0.1762,
|
| 315 |
+
"step": 420
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 6.94,
|
| 319 |
+
"learning_rate": 3.9193548387096776e-05,
|
| 320 |
+
"loss": 0.172,
|
| 321 |
+
"step": 430
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 7.0,
|
| 325 |
+
"eval_f1": 0.5482866043613707,
|
| 326 |
+
"eval_loss": 0.29978421330451965,
|
| 327 |
+
"eval_runtime": 2.9231,
|
| 328 |
+
"eval_samples_per_second": 338.34,
|
| 329 |
+
"eval_steps_per_second": 10.605,
|
| 330 |
+
"step": 434
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 7.1,
|
| 334 |
+
"learning_rate": 3.870967741935484e-05,
|
| 335 |
+
"loss": 0.1638,
|
| 336 |
+
"step": 440
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 7.26,
|
| 340 |
+
"learning_rate": 3.82258064516129e-05,
|
| 341 |
+
"loss": 0.1628,
|
| 342 |
+
"step": 450
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 7.42,
|
| 346 |
+
"learning_rate": 3.774193548387097e-05,
|
| 347 |
+
"loss": 0.1559,
|
| 348 |
+
"step": 460
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 7.58,
|
| 352 |
+
"learning_rate": 3.725806451612903e-05,
|
| 353 |
+
"loss": 0.1574,
|
| 354 |
+
"step": 470
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 7.74,
|
| 358 |
+
"learning_rate": 3.67741935483871e-05,
|
| 359 |
+
"loss": 0.1614,
|
| 360 |
+
"step": 480
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 7.9,
|
| 364 |
+
"learning_rate": 3.6290322580645165e-05,
|
| 365 |
+
"loss": 0.1551,
|
| 366 |
+
"step": 490
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 8.0,
|
| 370 |
+
"eval_f1": 0.5663555656726611,
|
| 371 |
+
"eval_loss": 0.3146507441997528,
|
| 372 |
+
"eval_runtime": 2.9227,
|
| 373 |
+
"eval_samples_per_second": 338.382,
|
| 374 |
+
"eval_steps_per_second": 10.607,
|
| 375 |
+
"step": 496
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 8.06,
|
| 379 |
+
"learning_rate": 3.580645161290323e-05,
|
| 380 |
+
"loss": 0.1497,
|
| 381 |
+
"step": 500
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 8.23,
|
| 385 |
+
"learning_rate": 3.532258064516129e-05,
|
| 386 |
+
"loss": 0.146,
|
| 387 |
+
"step": 510
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 8.39,
|
| 391 |
+
"learning_rate": 3.483870967741936e-05,
|
| 392 |
+
"loss": 0.1426,
|
| 393 |
+
"step": 520
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 8.55,
|
| 397 |
+
"learning_rate": 3.435483870967742e-05,
|
| 398 |
+
"loss": 0.1494,
|
| 399 |
+
"step": 530
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 8.71,
|
| 403 |
+
"learning_rate": 3.387096774193549e-05,
|
| 404 |
+
"loss": 0.1405,
|
| 405 |
+
"step": 540
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 8.87,
|
| 409 |
+
"learning_rate": 3.338709677419355e-05,
|
| 410 |
+
"loss": 0.1419,
|
| 411 |
+
"step": 550
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 9.0,
|
| 415 |
+
"eval_f1": 0.5569386814200094,
|
| 416 |
+
"eval_loss": 0.3179270029067993,
|
| 417 |
+
"eval_runtime": 2.8924,
|
| 418 |
+
"eval_samples_per_second": 341.925,
|
| 419 |
+
"eval_steps_per_second": 10.718,
|
| 420 |
+
"step": 558
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 9.03,
|
| 424 |
+
"learning_rate": 3.2903225806451614e-05,
|
| 425 |
+
"loss": 0.1391,
|
| 426 |
+
"step": 560
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 9.19,
|
| 430 |
+
"learning_rate": 3.2419354838709674e-05,
|
| 431 |
+
"loss": 0.1295,
|
| 432 |
+
"step": 570
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 9.35,
|
| 436 |
+
"learning_rate": 3.193548387096774e-05,
|
| 437 |
+
"loss": 0.1269,
|
| 438 |
+
"step": 580
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 9.52,
|
| 442 |
+
"learning_rate": 3.1451612903225806e-05,
|
| 443 |
+
"loss": 0.1279,
|
| 444 |
+
"step": 590
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 9.68,
|
| 448 |
+
"learning_rate": 3.096774193548387e-05,
|
| 449 |
+
"loss": 0.1283,
|
| 450 |
+
"step": 600
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 9.84,
|
| 454 |
+
"learning_rate": 3.0483870967741935e-05,
|
| 455 |
+
"loss": 0.1266,
|
| 456 |
+
"step": 610
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 10.0,
|
| 460 |
+
"learning_rate": 3e-05,
|
| 461 |
+
"loss": 0.1291,
|
| 462 |
+
"step": 620
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 10.0,
|
| 466 |
+
"eval_f1": 0.5659516202647192,
|
| 467 |
+
"eval_loss": 0.32372668385505676,
|
| 468 |
+
"eval_runtime": 2.9143,
|
| 469 |
+
"eval_samples_per_second": 339.356,
|
| 470 |
+
"eval_steps_per_second": 10.637,
|
| 471 |
+
"step": 620
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 10.16,
|
| 475 |
+
"learning_rate": 2.9516129032258067e-05,
|
| 476 |
+
"loss": 0.1164,
|
| 477 |
+
"step": 630
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 10.32,
|
| 481 |
+
"learning_rate": 2.903225806451613e-05,
|
| 482 |
+
"loss": 0.1206,
|
| 483 |
+
"step": 640
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 10.48,
|
| 487 |
+
"learning_rate": 2.8548387096774196e-05,
|
| 488 |
+
"loss": 0.1121,
|
| 489 |
+
"step": 650
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 10.65,
|
| 493 |
+
"learning_rate": 2.806451612903226e-05,
|
| 494 |
+
"loss": 0.123,
|
| 495 |
+
"step": 660
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 10.81,
|
| 499 |
+
"learning_rate": 2.758064516129032e-05,
|
| 500 |
+
"loss": 0.1148,
|
| 501 |
+
"step": 670
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 10.97,
|
| 505 |
+
"learning_rate": 2.7096774193548387e-05,
|
| 506 |
+
"loss": 0.1166,
|
| 507 |
+
"step": 680
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 11.0,
|
| 511 |
+
"eval_f1": 0.5683084466235793,
|
| 512 |
+
"eval_loss": 0.3352525234222412,
|
| 513 |
+
"eval_runtime": 2.8947,
|
| 514 |
+
"eval_samples_per_second": 341.665,
|
| 515 |
+
"eval_steps_per_second": 10.709,
|
| 516 |
+
"step": 682
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 11.13,
|
| 520 |
+
"learning_rate": 2.6612903225806453e-05,
|
| 521 |
+
"loss": 0.1068,
|
| 522 |
+
"step": 690
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 11.29,
|
| 526 |
+
"learning_rate": 2.6129032258064516e-05,
|
| 527 |
+
"loss": 0.1109,
|
| 528 |
+
"step": 700
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 11.45,
|
| 532 |
+
"learning_rate": 2.5645161290322582e-05,
|
| 533 |
+
"loss": 0.1049,
|
| 534 |
+
"step": 710
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 11.61,
|
| 538 |
+
"learning_rate": 2.5161290322580648e-05,
|
| 539 |
+
"loss": 0.1042,
|
| 540 |
+
"step": 720
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 11.77,
|
| 544 |
+
"learning_rate": 2.467741935483871e-05,
|
| 545 |
+
"loss": 0.1111,
|
| 546 |
+
"step": 730
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 11.94,
|
| 550 |
+
"learning_rate": 2.4193548387096773e-05,
|
| 551 |
+
"loss": 0.1079,
|
| 552 |
+
"step": 740
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 12.0,
|
| 556 |
+
"eval_f1": 0.5689615996364462,
|
| 557 |
+
"eval_loss": 0.33389773964881897,
|
| 558 |
+
"eval_runtime": 2.9192,
|
| 559 |
+
"eval_samples_per_second": 338.786,
|
| 560 |
+
"eval_steps_per_second": 10.619,
|
| 561 |
+
"step": 744
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 12.1,
|
| 565 |
+
"learning_rate": 2.370967741935484e-05,
|
| 566 |
+
"loss": 0.0981,
|
| 567 |
+
"step": 750
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 12.26,
|
| 571 |
+
"learning_rate": 2.3225806451612902e-05,
|
| 572 |
+
"loss": 0.1,
|
| 573 |
+
"step": 760
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 12.42,
|
| 577 |
+
"learning_rate": 2.274193548387097e-05,
|
| 578 |
+
"loss": 0.0947,
|
| 579 |
+
"step": 770
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 12.58,
|
| 583 |
+
"learning_rate": 2.2258064516129034e-05,
|
| 584 |
+
"loss": 0.0937,
|
| 585 |
+
"step": 780
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 12.74,
|
| 589 |
+
"learning_rate": 2.1774193548387097e-05,
|
| 590 |
+
"loss": 0.0978,
|
| 591 |
+
"step": 790
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 12.9,
|
| 595 |
+
"learning_rate": 2.1290322580645163e-05,
|
| 596 |
+
"loss": 0.0988,
|
| 597 |
+
"step": 800
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 13.0,
|
| 601 |
+
"eval_f1": 0.573460769059791,
|
| 602 |
+
"eval_loss": 0.34931689500808716,
|
| 603 |
+
"eval_runtime": 2.9238,
|
| 604 |
+
"eval_samples_per_second": 338.256,
|
| 605 |
+
"eval_steps_per_second": 10.603,
|
| 606 |
+
"step": 806
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 13.06,
|
| 610 |
+
"learning_rate": 2.080645161290323e-05,
|
| 611 |
+
"loss": 0.0948,
|
| 612 |
+
"step": 810
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 13.23,
|
| 616 |
+
"learning_rate": 2.032258064516129e-05,
|
| 617 |
+
"loss": 0.0874,
|
| 618 |
+
"step": 820
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 13.39,
|
| 622 |
+
"learning_rate": 1.9838709677419355e-05,
|
| 623 |
+
"loss": 0.0894,
|
| 624 |
+
"step": 830
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 13.55,
|
| 628 |
+
"learning_rate": 1.935483870967742e-05,
|
| 629 |
+
"loss": 0.0919,
|
| 630 |
+
"step": 840
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 13.71,
|
| 634 |
+
"learning_rate": 1.8870967741935484e-05,
|
| 635 |
+
"loss": 0.0899,
|
| 636 |
+
"step": 850
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"epoch": 13.87,
|
| 640 |
+
"learning_rate": 1.838709677419355e-05,
|
| 641 |
+
"loss": 0.0926,
|
| 642 |
+
"step": 860
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"epoch": 14.0,
|
| 646 |
+
"eval_f1": 0.5807734806629834,
|
| 647 |
+
"eval_loss": 0.35069382190704346,
|
| 648 |
+
"eval_runtime": 2.9589,
|
| 649 |
+
"eval_samples_per_second": 334.248,
|
| 650 |
+
"eval_steps_per_second": 10.477,
|
| 651 |
+
"step": 868
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 14.03,
|
| 655 |
+
"learning_rate": 1.7903225806451616e-05,
|
| 656 |
+
"loss": 0.0817,
|
| 657 |
+
"step": 870
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 14.19,
|
| 661 |
+
"learning_rate": 1.741935483870968e-05,
|
| 662 |
+
"loss": 0.0826,
|
| 663 |
+
"step": 880
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 14.35,
|
| 667 |
+
"learning_rate": 1.6935483870967744e-05,
|
| 668 |
+
"loss": 0.0842,
|
| 669 |
+
"step": 890
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 14.52,
|
| 673 |
+
"learning_rate": 1.6451612903225807e-05,
|
| 674 |
+
"loss": 0.0824,
|
| 675 |
+
"step": 900
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 14.68,
|
| 679 |
+
"learning_rate": 1.596774193548387e-05,
|
| 680 |
+
"loss": 0.0822,
|
| 681 |
+
"step": 910
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 14.84,
|
| 685 |
+
"learning_rate": 1.5483870967741936e-05,
|
| 686 |
+
"loss": 0.0826,
|
| 687 |
+
"step": 920
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 15.0,
|
| 691 |
+
"learning_rate": 1.5e-05,
|
| 692 |
+
"loss": 0.0837,
|
| 693 |
+
"step": 930
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 15.0,
|
| 697 |
+
"eval_f1": 0.5837362637362637,
|
| 698 |
+
"eval_loss": 0.3567672073841095,
|
| 699 |
+
"eval_runtime": 2.915,
|
| 700 |
+
"eval_samples_per_second": 339.279,
|
| 701 |
+
"eval_steps_per_second": 10.635,
|
| 702 |
+
"step": 930
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 15.16,
|
| 706 |
+
"learning_rate": 1.4516129032258065e-05,
|
| 707 |
+
"loss": 0.0781,
|
| 708 |
+
"step": 940
|
| 709 |
+
},
|
| 710 |
+
{
|
| 711 |
+
"epoch": 15.32,
|
| 712 |
+
"learning_rate": 1.403225806451613e-05,
|
| 713 |
+
"loss": 0.0757,
|
| 714 |
+
"step": 950
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 15.48,
|
| 718 |
+
"learning_rate": 1.3548387096774194e-05,
|
| 719 |
+
"loss": 0.0766,
|
| 720 |
+
"step": 960
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 15.65,
|
| 724 |
+
"learning_rate": 1.3064516129032258e-05,
|
| 725 |
+
"loss": 0.0788,
|
| 726 |
+
"step": 970
|
| 727 |
+
},
|
| 728 |
+
{
|
| 729 |
+
"epoch": 15.81,
|
| 730 |
+
"learning_rate": 1.2580645161290324e-05,
|
| 731 |
+
"loss": 0.0764,
|
| 732 |
+
"step": 980
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 15.97,
|
| 736 |
+
"learning_rate": 1.2096774193548387e-05,
|
| 737 |
+
"loss": 0.076,
|
| 738 |
+
"step": 990
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 16.0,
|
| 742 |
+
"eval_f1": 0.5796391178436178,
|
| 743 |
+
"eval_loss": 0.3577311336994171,
|
| 744 |
+
"eval_runtime": 2.8859,
|
| 745 |
+
"eval_samples_per_second": 342.697,
|
| 746 |
+
"eval_steps_per_second": 10.742,
|
| 747 |
+
"step": 992
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 16.13,
|
| 751 |
+
"learning_rate": 1.1612903225806451e-05,
|
| 752 |
+
"loss": 0.0743,
|
| 753 |
+
"step": 1000
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 16.29,
|
| 757 |
+
"learning_rate": 1.1129032258064517e-05,
|
| 758 |
+
"loss": 0.0713,
|
| 759 |
+
"step": 1010
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 16.45,
|
| 763 |
+
"learning_rate": 1.0645161290322582e-05,
|
| 764 |
+
"loss": 0.0744,
|
| 765 |
+
"step": 1020
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 16.61,
|
| 769 |
+
"learning_rate": 1.0161290322580644e-05,
|
| 770 |
+
"loss": 0.069,
|
| 771 |
+
"step": 1030
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 16.77,
|
| 775 |
+
"learning_rate": 9.67741935483871e-06,
|
| 776 |
+
"loss": 0.0742,
|
| 777 |
+
"step": 1040
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 16.94,
|
| 781 |
+
"learning_rate": 9.193548387096775e-06,
|
| 782 |
+
"loss": 0.0718,
|
| 783 |
+
"step": 1050
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 17.0,
|
| 787 |
+
"eval_f1": 0.5815983881799865,
|
| 788 |
+
"eval_loss": 0.3607926368713379,
|
| 789 |
+
"eval_runtime": 2.9273,
|
| 790 |
+
"eval_samples_per_second": 337.857,
|
| 791 |
+
"eval_steps_per_second": 10.59,
|
| 792 |
+
"step": 1054
|
| 793 |
+
},
|
| 794 |
+
{
|
| 795 |
+
"epoch": 17.1,
|
| 796 |
+
"learning_rate": 8.70967741935484e-06,
|
| 797 |
+
"loss": 0.0704,
|
| 798 |
+
"step": 1060
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"epoch": 17.26,
|
| 802 |
+
"learning_rate": 8.225806451612904e-06,
|
| 803 |
+
"loss": 0.067,
|
| 804 |
+
"step": 1070
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 17.42,
|
| 808 |
+
"learning_rate": 7.741935483870968e-06,
|
| 809 |
+
"loss": 0.0709,
|
| 810 |
+
"step": 1080
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 17.58,
|
| 814 |
+
"learning_rate": 7.258064516129032e-06,
|
| 815 |
+
"loss": 0.0679,
|
| 816 |
+
"step": 1090
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 17.74,
|
| 820 |
+
"learning_rate": 6.774193548387097e-06,
|
| 821 |
+
"loss": 0.071,
|
| 822 |
+
"step": 1100
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 17.9,
|
| 826 |
+
"learning_rate": 6.290322580645162e-06,
|
| 827 |
+
"loss": 0.0685,
|
| 828 |
+
"step": 1110
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 18.0,
|
| 832 |
+
"eval_f1": 0.5815289438798055,
|
| 833 |
+
"eval_loss": 0.36424893140792847,
|
| 834 |
+
"eval_runtime": 2.9446,
|
| 835 |
+
"eval_samples_per_second": 335.873,
|
| 836 |
+
"eval_steps_per_second": 10.528,
|
| 837 |
+
"step": 1116
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 18.06,
|
| 841 |
+
"learning_rate": 5.8064516129032256e-06,
|
| 842 |
+
"loss": 0.0673,
|
| 843 |
+
"step": 1120
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 18.23,
|
| 847 |
+
"learning_rate": 5.322580645161291e-06,
|
| 848 |
+
"loss": 0.0666,
|
| 849 |
+
"step": 1130
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 18.39,
|
| 853 |
+
"learning_rate": 4.838709677419355e-06,
|
| 854 |
+
"loss": 0.0663,
|
| 855 |
+
"step": 1140
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 18.55,
|
| 859 |
+
"learning_rate": 4.35483870967742e-06,
|
| 860 |
+
"loss": 0.0669,
|
| 861 |
+
"step": 1150
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 18.71,
|
| 865 |
+
"learning_rate": 3.870967741935484e-06,
|
| 866 |
+
"loss": 0.0677,
|
| 867 |
+
"step": 1160
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 18.87,
|
| 871 |
+
"learning_rate": 3.3870967741935484e-06,
|
| 872 |
+
"loss": 0.0665,
|
| 873 |
+
"step": 1170
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 19.0,
|
| 877 |
+
"eval_f1": 0.5837742504409171,
|
| 878 |
+
"eval_loss": 0.36555004119873047,
|
| 879 |
+
"eval_runtime": 2.9275,
|
| 880 |
+
"eval_samples_per_second": 337.836,
|
| 881 |
+
"eval_steps_per_second": 10.589,
|
| 882 |
+
"step": 1178
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 19.03,
|
| 886 |
+
"learning_rate": 2.9032258064516128e-06,
|
| 887 |
+
"loss": 0.0656,
|
| 888 |
+
"step": 1180
|
| 889 |
+
},
|
| 890 |
+
{
|
| 891 |
+
"epoch": 19.19,
|
| 892 |
+
"learning_rate": 2.4193548387096776e-06,
|
| 893 |
+
"loss": 0.063,
|
| 894 |
+
"step": 1190
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 19.35,
|
| 898 |
+
"learning_rate": 1.935483870967742e-06,
|
| 899 |
+
"loss": 0.0628,
|
| 900 |
+
"step": 1200
|
| 901 |
+
},
|
| 902 |
+
{
|
| 903 |
+
"epoch": 19.52,
|
| 904 |
+
"learning_rate": 1.4516129032258064e-06,
|
| 905 |
+
"loss": 0.0651,
|
| 906 |
+
"step": 1210
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 19.68,
|
| 910 |
+
"learning_rate": 9.67741935483871e-07,
|
| 911 |
+
"loss": 0.0662,
|
| 912 |
+
"step": 1220
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 19.84,
|
| 916 |
+
"learning_rate": 4.838709677419355e-07,
|
| 917 |
+
"loss": 0.0636,
|
| 918 |
+
"step": 1230
|
| 919 |
+
},
|
| 920 |
+
{
|
| 921 |
+
"epoch": 20.0,
|
| 922 |
+
"learning_rate": 0.0,
|
| 923 |
+
"loss": 0.0676,
|
| 924 |
+
"step": 1240
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"epoch": 20.0,
|
| 928 |
+
"eval_f1": 0.5832229580573952,
|
| 929 |
+
"eval_loss": 0.3661610186100006,
|
| 930 |
+
"eval_runtime": 2.9338,
|
| 931 |
+
"eval_samples_per_second": 337.105,
|
| 932 |
+
"eval_steps_per_second": 10.566,
|
| 933 |
+
"step": 1240
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 20.0,
|
| 937 |
+
"step": 1240,
|
| 938 |
+
"total_flos": 2.082560024604672e+16,
|
| 939 |
+
"train_loss": 0.14994276651451666,
|
| 940 |
+
"train_runtime": 1498.2493,
|
| 941 |
+
"train_samples_per_second": 105.643,
|
| 942 |
+
"train_steps_per_second": 0.828
|
| 943 |
+
}
|
| 944 |
+
],
|
| 945 |
+
"logging_steps": 10,
|
| 946 |
+
"max_steps": 1240,
|
| 947 |
+
"num_train_epochs": 20,
|
| 948 |
+
"save_steps": 500,
|
| 949 |
+
"total_flos": 2.082560024604672e+16,
|
| 950 |
+
"trial_name": null,
|
| 951 |
+
"trial_params": null
|
| 952 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:49d4aa7ecccbe4b27163ea940d8f5d4aed0acdeee63d06ce326f947364079c53
|
| 3 |
+
size 4600
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|