Upload my model
Browse files- README.md +64 -0
- config.json +32 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- special_tokens_map.json +15 -0
- tokenizer.json +0 -0
- tokenizer_config.json +57 -0
- trainer_state.json +439 -0
- training_args.bin +3 -0
- vocab.json +0 -0
README.md
ADDED
|
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
base_model: roberta-large
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
metrics:
|
| 7 |
+
- accuracy
|
| 8 |
+
model-index:
|
| 9 |
+
- name: example
|
| 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 |
+
# example
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [roberta-large](https://huggingface.co/roberta-large) on an unknown dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 0.3193
|
| 21 |
+
- Accuracy: 0.9259
|
| 22 |
+
- 0 To 0: 115
|
| 23 |
+
- 0 To 1: 10
|
| 24 |
+
- 1 To 0: 8
|
| 25 |
+
- 1 To 1: 110
|
| 26 |
+
|
| 27 |
+
## Model description
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Intended uses & limitations
|
| 32 |
+
|
| 33 |
+
More information needed
|
| 34 |
+
|
| 35 |
+
## Training and evaluation data
|
| 36 |
+
|
| 37 |
+
More information needed
|
| 38 |
+
|
| 39 |
+
## Training procedure
|
| 40 |
+
|
| 41 |
+
### Training hyperparameters
|
| 42 |
+
|
| 43 |
+
The following hyperparameters were used during training:
|
| 44 |
+
- learning_rate: 1e-05
|
| 45 |
+
- train_batch_size: 16
|
| 46 |
+
- eval_batch_size: 16
|
| 47 |
+
- seed: 42
|
| 48 |
+
- gradient_accumulation_steps: 5
|
| 49 |
+
- total_train_batch_size: 80
|
| 50 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 51 |
+
- lr_scheduler_type: linear
|
| 52 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 53 |
+
- num_epochs: 15
|
| 54 |
+
|
| 55 |
+
### Training results
|
| 56 |
+
|
| 57 |
+
|
| 58 |
+
|
| 59 |
+
### Framework versions
|
| 60 |
+
|
| 61 |
+
- Transformers 4.41.2
|
| 62 |
+
- Pytorch 2.3.1
|
| 63 |
+
- Datasets 2.20.0
|
| 64 |
+
- Tokenizers 0.19.1
|
config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "roberta-large",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"RobertaForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout_prob": 0.1,
|
| 12 |
+
"hidden_size": 1024,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 4096,
|
| 15 |
+
"label2id": {
|
| 16 |
+
"0": 0,
|
| 17 |
+
"1": 1
|
| 18 |
+
},
|
| 19 |
+
"layer_norm_eps": 1e-05,
|
| 20 |
+
"max_position_embeddings": 514,
|
| 21 |
+
"model_type": "roberta",
|
| 22 |
+
"num_attention_heads": 16,
|
| 23 |
+
"num_hidden_layers": 24,
|
| 24 |
+
"pad_token_id": 1,
|
| 25 |
+
"position_embedding_type": "absolute",
|
| 26 |
+
"problem_type": "single_label_classification",
|
| 27 |
+
"torch_dtype": "float32",
|
| 28 |
+
"transformers_version": "4.41.2",
|
| 29 |
+
"type_vocab_size": 1,
|
| 30 |
+
"use_cache": true,
|
| 31 |
+
"vocab_size": 50265
|
| 32 |
+
}
|
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 sha256:48d1ffaeb2e61298d25f52e7b508461862d06d247dda5d3b775f97f530cb21b1
|
| 3 |
+
size 1421495416
|
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 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<s>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "<pad>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": true,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "</s>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": true,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"3": {
|
| 29 |
+
"content": "<unk>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": true,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"50264": {
|
| 37 |
+
"content": "<mask>",
|
| 38 |
+
"lstrip": true,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
}
|
| 44 |
+
},
|
| 45 |
+
"bos_token": "<s>",
|
| 46 |
+
"clean_up_tokenization_spaces": true,
|
| 47 |
+
"cls_token": "<s>",
|
| 48 |
+
"eos_token": "</s>",
|
| 49 |
+
"errors": "replace",
|
| 50 |
+
"mask_token": "<mask>",
|
| 51 |
+
"model_max_length": 512,
|
| 52 |
+
"pad_token": "<pad>",
|
| 53 |
+
"sep_token": "</s>",
|
| 54 |
+
"tokenizer_class": "RobertaTokenizer",
|
| 55 |
+
"trim_offsets": true,
|
| 56 |
+
"unk_token": "<unk>"
|
| 57 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,439 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 14.646464646464647,
|
| 5 |
+
"eval_steps": 20,
|
| 6 |
+
"global_step": 580,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.25252525252525254,
|
| 13 |
+
"grad_norm": 13.126054763793945,
|
| 14 |
+
"learning_rate": 1.6949152542372882e-06,
|
| 15 |
+
"loss": 0.8683,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.5050505050505051,
|
| 20 |
+
"grad_norm": 17.31291961669922,
|
| 21 |
+
"learning_rate": 3.3898305084745763e-06,
|
| 22 |
+
"loss": 0.7248,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.7575757575757576,
|
| 27 |
+
"grad_norm": 8.053046226501465,
|
| 28 |
+
"learning_rate": 5.084745762711865e-06,
|
| 29 |
+
"loss": 0.6134,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 1.0101010101010102,
|
| 34 |
+
"grad_norm": 9.220598220825195,
|
| 35 |
+
"learning_rate": 6.779661016949153e-06,
|
| 36 |
+
"loss": 0.5526,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 1.2626262626262625,
|
| 41 |
+
"grad_norm": 27.968978881835938,
|
| 42 |
+
"learning_rate": 8.47457627118644e-06,
|
| 43 |
+
"loss": 0.4393,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 1.5151515151515151,
|
| 48 |
+
"grad_norm": 5.585519313812256,
|
| 49 |
+
"learning_rate": 9.980988593155894e-06,
|
| 50 |
+
"loss": 0.34,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 1.7676767676767677,
|
| 55 |
+
"grad_norm": 4.464208602905273,
|
| 56 |
+
"learning_rate": 9.790874524714829e-06,
|
| 57 |
+
"loss": 0.3483,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 2.0202020202020203,
|
| 62 |
+
"grad_norm": 11.554718017578125,
|
| 63 |
+
"learning_rate": 9.600760456273765e-06,
|
| 64 |
+
"loss": 0.3142,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 2.2727272727272725,
|
| 69 |
+
"grad_norm": 6.658814907073975,
|
| 70 |
+
"learning_rate": 9.4106463878327e-06,
|
| 71 |
+
"loss": 0.2071,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 2.525252525252525,
|
| 76 |
+
"grad_norm": 6.011457443237305,
|
| 77 |
+
"learning_rate": 9.220532319391637e-06,
|
| 78 |
+
"loss": 0.2287,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 2.7777777777777777,
|
| 83 |
+
"grad_norm": 9.19509220123291,
|
| 84 |
+
"learning_rate": 9.030418250950572e-06,
|
| 85 |
+
"loss": 0.2189,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 3.0303030303030303,
|
| 90 |
+
"grad_norm": 4.081284523010254,
|
| 91 |
+
"learning_rate": 8.840304182509506e-06,
|
| 92 |
+
"loss": 0.1807,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 3.282828282828283,
|
| 97 |
+
"grad_norm": 4.492301940917969,
|
| 98 |
+
"learning_rate": 8.650190114068441e-06,
|
| 99 |
+
"loss": 0.1727,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 3.5353535353535355,
|
| 104 |
+
"grad_norm": 5.772425174713135,
|
| 105 |
+
"learning_rate": 8.460076045627376e-06,
|
| 106 |
+
"loss": 0.128,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 3.787878787878788,
|
| 111 |
+
"grad_norm": 24.84961700439453,
|
| 112 |
+
"learning_rate": 8.269961977186313e-06,
|
| 113 |
+
"loss": 0.1993,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 4.040404040404041,
|
| 118 |
+
"grad_norm": 2.998711585998535,
|
| 119 |
+
"learning_rate": 8.079847908745247e-06,
|
| 120 |
+
"loss": 0.1502,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 4.292929292929293,
|
| 125 |
+
"grad_norm": 6.577826499938965,
|
| 126 |
+
"learning_rate": 7.889733840304184e-06,
|
| 127 |
+
"loss": 0.1225,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 4.545454545454545,
|
| 132 |
+
"grad_norm": 8.288976669311523,
|
| 133 |
+
"learning_rate": 7.699619771863119e-06,
|
| 134 |
+
"loss": 0.1113,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 4.797979797979798,
|
| 139 |
+
"grad_norm": 8.804610252380371,
|
| 140 |
+
"learning_rate": 7.509505703422054e-06,
|
| 141 |
+
"loss": 0.1692,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 5.05050505050505,
|
| 146 |
+
"grad_norm": 5.5263752937316895,
|
| 147 |
+
"learning_rate": 7.319391634980989e-06,
|
| 148 |
+
"loss": 0.1364,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 5.303030303030303,
|
| 153 |
+
"grad_norm": 3.2428457736968994,
|
| 154 |
+
"learning_rate": 7.129277566539925e-06,
|
| 155 |
+
"loss": 0.0863,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 5.555555555555555,
|
| 160 |
+
"grad_norm": 6.467748165130615,
|
| 161 |
+
"learning_rate": 6.93916349809886e-06,
|
| 162 |
+
"loss": 0.1099,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 5.808080808080808,
|
| 167 |
+
"grad_norm": 8.438054084777832,
|
| 168 |
+
"learning_rate": 6.749049429657795e-06,
|
| 169 |
+
"loss": 0.1037,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 6.0606060606060606,
|
| 174 |
+
"grad_norm": 2.7920687198638916,
|
| 175 |
+
"learning_rate": 6.55893536121673e-06,
|
| 176 |
+
"loss": 0.1054,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 6.313131313131313,
|
| 181 |
+
"grad_norm": 14.06596565246582,
|
| 182 |
+
"learning_rate": 6.368821292775666e-06,
|
| 183 |
+
"loss": 0.0708,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 6.565656565656566,
|
| 188 |
+
"grad_norm": 3.4552762508392334,
|
| 189 |
+
"learning_rate": 6.1787072243346015e-06,
|
| 190 |
+
"loss": 0.0963,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 6.818181818181818,
|
| 195 |
+
"grad_norm": 4.3161234855651855,
|
| 196 |
+
"learning_rate": 5.988593155893536e-06,
|
| 197 |
+
"loss": 0.1237,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 7.070707070707071,
|
| 202 |
+
"grad_norm": 3.9048163890838623,
|
| 203 |
+
"learning_rate": 5.798479087452472e-06,
|
| 204 |
+
"loss": 0.0868,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 7.3232323232323235,
|
| 209 |
+
"grad_norm": 8.73560905456543,
|
| 210 |
+
"learning_rate": 5.608365019011407e-06,
|
| 211 |
+
"loss": 0.0681,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 7.575757575757576,
|
| 216 |
+
"grad_norm": 3.1624324321746826,
|
| 217 |
+
"learning_rate": 5.418250950570343e-06,
|
| 218 |
+
"loss": 0.0912,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 7.828282828282829,
|
| 223 |
+
"grad_norm": 3.010721206665039,
|
| 224 |
+
"learning_rate": 5.228136882129278e-06,
|
| 225 |
+
"loss": 0.0618,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 8.080808080808081,
|
| 230 |
+
"grad_norm": 2.488093137741089,
|
| 231 |
+
"learning_rate": 5.038022813688214e-06,
|
| 232 |
+
"loss": 0.0484,
|
| 233 |
+
"step": 320
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 8.333333333333334,
|
| 237 |
+
"grad_norm": 44.87844467163086,
|
| 238 |
+
"learning_rate": 4.847908745247149e-06,
|
| 239 |
+
"loss": 0.0665,
|
| 240 |
+
"step": 330
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 8.585858585858587,
|
| 244 |
+
"grad_norm": 5.052587032318115,
|
| 245 |
+
"learning_rate": 4.657794676806084e-06,
|
| 246 |
+
"loss": 0.0643,
|
| 247 |
+
"step": 340
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 8.83838383838384,
|
| 251 |
+
"grad_norm": 1.7123836278915405,
|
| 252 |
+
"learning_rate": 4.467680608365019e-06,
|
| 253 |
+
"loss": 0.0575,
|
| 254 |
+
"step": 350
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 9.090909090909092,
|
| 258 |
+
"grad_norm": 1.540806770324707,
|
| 259 |
+
"learning_rate": 4.277566539923955e-06,
|
| 260 |
+
"loss": 0.0669,
|
| 261 |
+
"step": 360
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 9.343434343434343,
|
| 265 |
+
"grad_norm": 6.937175750732422,
|
| 266 |
+
"learning_rate": 4.08745247148289e-06,
|
| 267 |
+
"loss": 0.0502,
|
| 268 |
+
"step": 370
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 9.595959595959595,
|
| 272 |
+
"grad_norm": 1.7217215299606323,
|
| 273 |
+
"learning_rate": 3.897338403041825e-06,
|
| 274 |
+
"loss": 0.0586,
|
| 275 |
+
"step": 380
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 9.848484848484848,
|
| 279 |
+
"grad_norm": 2.884972095489502,
|
| 280 |
+
"learning_rate": 3.707224334600761e-06,
|
| 281 |
+
"loss": 0.0691,
|
| 282 |
+
"step": 390
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 10.1010101010101,
|
| 286 |
+
"grad_norm": 3.5889267921447754,
|
| 287 |
+
"learning_rate": 3.517110266159696e-06,
|
| 288 |
+
"loss": 0.0717,
|
| 289 |
+
"step": 400
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 10.353535353535353,
|
| 293 |
+
"grad_norm": 3.033485174179077,
|
| 294 |
+
"learning_rate": 3.3269961977186314e-06,
|
| 295 |
+
"loss": 0.0491,
|
| 296 |
+
"step": 410
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 10.606060606060606,
|
| 300 |
+
"grad_norm": 1.5832382440567017,
|
| 301 |
+
"learning_rate": 3.136882129277567e-06,
|
| 302 |
+
"loss": 0.0457,
|
| 303 |
+
"step": 420
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 10.858585858585858,
|
| 307 |
+
"grad_norm": 0.04450301453471184,
|
| 308 |
+
"learning_rate": 2.9467680608365023e-06,
|
| 309 |
+
"loss": 0.0687,
|
| 310 |
+
"step": 430
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 11.11111111111111,
|
| 314 |
+
"grad_norm": 4.540256977081299,
|
| 315 |
+
"learning_rate": 2.756653992395438e-06,
|
| 316 |
+
"loss": 0.0593,
|
| 317 |
+
"step": 440
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 11.363636363636363,
|
| 321 |
+
"grad_norm": 4.446552753448486,
|
| 322 |
+
"learning_rate": 2.5665399239543728e-06,
|
| 323 |
+
"loss": 0.0404,
|
| 324 |
+
"step": 450
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 11.616161616161616,
|
| 328 |
+
"grad_norm": 1.007643222808838,
|
| 329 |
+
"learning_rate": 2.3764258555133084e-06,
|
| 330 |
+
"loss": 0.0402,
|
| 331 |
+
"step": 460
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 11.868686868686869,
|
| 335 |
+
"grad_norm": 0.96592116355896,
|
| 336 |
+
"learning_rate": 2.1863117870722437e-06,
|
| 337 |
+
"loss": 0.0448,
|
| 338 |
+
"step": 470
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 12.121212121212121,
|
| 342 |
+
"grad_norm": 6.914277076721191,
|
| 343 |
+
"learning_rate": 1.996197718631179e-06,
|
| 344 |
+
"loss": 0.0536,
|
| 345 |
+
"step": 480
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 12.373737373737374,
|
| 349 |
+
"grad_norm": 4.67967414855957,
|
| 350 |
+
"learning_rate": 1.8060836501901142e-06,
|
| 351 |
+
"loss": 0.0487,
|
| 352 |
+
"step": 490
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 12.626262626262626,
|
| 356 |
+
"grad_norm": 2.039752721786499,
|
| 357 |
+
"learning_rate": 1.6159695817490494e-06,
|
| 358 |
+
"loss": 0.0468,
|
| 359 |
+
"step": 500
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 12.878787878787879,
|
| 363 |
+
"grad_norm": 7.157741546630859,
|
| 364 |
+
"learning_rate": 1.4258555133079848e-06,
|
| 365 |
+
"loss": 0.0317,
|
| 366 |
+
"step": 510
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 13.131313131313131,
|
| 370 |
+
"grad_norm": 4.240894317626953,
|
| 371 |
+
"learning_rate": 1.2357414448669203e-06,
|
| 372 |
+
"loss": 0.0424,
|
| 373 |
+
"step": 520
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 13.383838383838384,
|
| 377 |
+
"grad_norm": 1.8747172355651855,
|
| 378 |
+
"learning_rate": 1.0456273764258558e-06,
|
| 379 |
+
"loss": 0.0396,
|
| 380 |
+
"step": 530
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 13.636363636363637,
|
| 384 |
+
"grad_norm": 1.3047974109649658,
|
| 385 |
+
"learning_rate": 8.555133079847909e-07,
|
| 386 |
+
"loss": 0.0403,
|
| 387 |
+
"step": 540
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 13.88888888888889,
|
| 391 |
+
"grad_norm": 1.6948643922805786,
|
| 392 |
+
"learning_rate": 6.653992395437263e-07,
|
| 393 |
+
"loss": 0.0372,
|
| 394 |
+
"step": 550
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 14.141414141414142,
|
| 398 |
+
"grad_norm": 3.19494891166687,
|
| 399 |
+
"learning_rate": 4.752851711026616e-07,
|
| 400 |
+
"loss": 0.0422,
|
| 401 |
+
"step": 560
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 14.393939393939394,
|
| 405 |
+
"grad_norm": 0.13894398510456085,
|
| 406 |
+
"learning_rate": 2.85171102661597e-07,
|
| 407 |
+
"loss": 0.0292,
|
| 408 |
+
"step": 570
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 14.646464646464647,
|
| 412 |
+
"grad_norm": 0.04802278056740761,
|
| 413 |
+
"learning_rate": 9.505703422053233e-08,
|
| 414 |
+
"loss": 0.0377,
|
| 415 |
+
"step": 580
|
| 416 |
+
}
|
| 417 |
+
],
|
| 418 |
+
"logging_steps": 10,
|
| 419 |
+
"max_steps": 585,
|
| 420 |
+
"num_input_tokens_seen": 0,
|
| 421 |
+
"num_train_epochs": 15,
|
| 422 |
+
"save_steps": 20,
|
| 423 |
+
"stateful_callbacks": {
|
| 424 |
+
"TrainerControl": {
|
| 425 |
+
"args": {
|
| 426 |
+
"should_epoch_stop": false,
|
| 427 |
+
"should_evaluate": false,
|
| 428 |
+
"should_log": false,
|
| 429 |
+
"should_save": true,
|
| 430 |
+
"should_training_stop": false
|
| 431 |
+
},
|
| 432 |
+
"attributes": {}
|
| 433 |
+
}
|
| 434 |
+
},
|
| 435 |
+
"total_flos": 1.5658543749477888e+16,
|
| 436 |
+
"train_batch_size": 16,
|
| 437 |
+
"trial_name": null,
|
| 438 |
+
"trial_params": null
|
| 439 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4d70baba1b2f1be3023e89841ed429af172d45e87f548b1a00a0170e44cb8faa
|
| 3 |
+
size 5112
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|