Upload 10 files
Browse files- config.json +28 -0
- label_mappings.json +11 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- special_tokens_map.json +51 -0
- tokenizer.json +0 -0
- tokenizer_config.json +58 -0
- trainer_state.json +472 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"RobertaForSequenceClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"bos_token_id": 0,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"eos_token_id": 2,
|
| 9 |
+
"gradient_checkpointing": false,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout_prob": 0.1,
|
| 12 |
+
"hidden_size": 768,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 3072,
|
| 15 |
+
"layer_norm_eps": 1e-12,
|
| 16 |
+
"max_position_embeddings": 514,
|
| 17 |
+
"model_type": "roberta",
|
| 18 |
+
"num_attention_heads": 12,
|
| 19 |
+
"num_hidden_layers": 12,
|
| 20 |
+
"pad_token_id": 1,
|
| 21 |
+
"position_embedding_type": "absolute",
|
| 22 |
+
"problem_type": "single_label_classification",
|
| 23 |
+
"torch_dtype": "bfloat16",
|
| 24 |
+
"transformers_version": "4.53.3",
|
| 25 |
+
"type_vocab_size": 1,
|
| 26 |
+
"use_cache": true,
|
| 27 |
+
"vocab_size": 52000
|
| 28 |
+
}
|
label_mappings.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"label_to_id": {
|
| 3 |
+
"0": 0,
|
| 4 |
+
"1": 1
|
| 5 |
+
},
|
| 6 |
+
"id_to_label": {
|
| 7 |
+
"0": 0,
|
| 8 |
+
"1": 1
|
| 9 |
+
},
|
| 10 |
+
"num_labels": 2
|
| 11 |
+
}
|
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 sha256:765858bc8d2b85435aba93a0212b2c498e194ab3fe38b431942387f4986acf27
|
| 3 |
+
size 251983588
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "<s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "<mask>",
|
| 25 |
+
"lstrip": true,
|
| 26 |
+
"normalized": true,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "<pad>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": true,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "</s>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": true,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "<unk>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": true,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"4": {
|
| 37 |
+
"content": "<mask>",
|
| 38 |
+
"lstrip": true,
|
| 39 |
+
"normalized": true,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
}
|
| 44 |
+
},
|
| 45 |
+
"bos_token": "<s>",
|
| 46 |
+
"clean_up_tokenization_spaces": false,
|
| 47 |
+
"cls_token": "<s>",
|
| 48 |
+
"eos_token": "</s>",
|
| 49 |
+
"errors": "replace",
|
| 50 |
+
"extra_special_tokens": {},
|
| 51 |
+
"mask_token": "<mask>",
|
| 52 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 53 |
+
"pad_token": "<pad>",
|
| 54 |
+
"sep_token": "</s>",
|
| 55 |
+
"tokenizer_class": "RobertaTokenizer",
|
| 56 |
+
"trim_offsets": true,
|
| 57 |
+
"unk_token": "<unk>"
|
| 58 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,472 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 344,
|
| 3 |
+
"best_metric": 0.8545918367346939,
|
| 4 |
+
"best_model_checkpoint": "../results\\checkpoint-344",
|
| 5 |
+
"epoch": 6.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 516,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.11627906976744186,
|
| 14 |
+
"grad_norm": 3.748704671859741,
|
| 15 |
+
"learning_rate": 1.2000000000000002e-06,
|
| 16 |
+
"loss": 0.7308,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.23255813953488372,
|
| 21 |
+
"grad_norm": 4.270473957061768,
|
| 22 |
+
"learning_rate": 2.5333333333333338e-06,
|
| 23 |
+
"loss": 0.711,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.3488372093023256,
|
| 28 |
+
"grad_norm": 3.427567481994629,
|
| 29 |
+
"learning_rate": 3.866666666666667e-06,
|
| 30 |
+
"loss": 0.6948,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.46511627906976744,
|
| 35 |
+
"grad_norm": 2.623924732208252,
|
| 36 |
+
"learning_rate": 5.2e-06,
|
| 37 |
+
"loss": 0.6786,
|
| 38 |
+
"step": 40
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.5813953488372093,
|
| 42 |
+
"grad_norm": 3.8385608196258545,
|
| 43 |
+
"learning_rate": 6.533333333333334e-06,
|
| 44 |
+
"loss": 0.6393,
|
| 45 |
+
"step": 50
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.6976744186046512,
|
| 49 |
+
"grad_norm": 6.035278797149658,
|
| 50 |
+
"learning_rate": 7.866666666666667e-06,
|
| 51 |
+
"loss": 0.6001,
|
| 52 |
+
"step": 60
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.813953488372093,
|
| 56 |
+
"grad_norm": 12.787239074707031,
|
| 57 |
+
"learning_rate": 9.200000000000002e-06,
|
| 58 |
+
"loss": 0.5629,
|
| 59 |
+
"step": 70
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.9302325581395349,
|
| 63 |
+
"grad_norm": 5.702328681945801,
|
| 64 |
+
"learning_rate": 1.0533333333333333e-05,
|
| 65 |
+
"loss": 0.5313,
|
| 66 |
+
"step": 80
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 1.0,
|
| 70 |
+
"eval_accuracy": 0.7,
|
| 71 |
+
"eval_f1": 0.7009200572480064,
|
| 72 |
+
"eval_loss": 0.5837136507034302,
|
| 73 |
+
"eval_precision": 0.7089869281045751,
|
| 74 |
+
"eval_recall": 0.7,
|
| 75 |
+
"eval_runtime": 41.9795,
|
| 76 |
+
"eval_samples_per_second": 1.667,
|
| 77 |
+
"eval_steps_per_second": 0.071,
|
| 78 |
+
"step": 86
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 1.0465116279069768,
|
| 82 |
+
"grad_norm": 9.588857650756836,
|
| 83 |
+
"learning_rate": 1.186666666666667e-05,
|
| 84 |
+
"loss": 0.5636,
|
| 85 |
+
"step": 90
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 1.1627906976744187,
|
| 89 |
+
"grad_norm": 11.674090385437012,
|
| 90 |
+
"learning_rate": 1.3200000000000002e-05,
|
| 91 |
+
"loss": 0.5236,
|
| 92 |
+
"step": 100
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 1.2790697674418605,
|
| 96 |
+
"grad_norm": 6.487068176269531,
|
| 97 |
+
"learning_rate": 1.4533333333333335e-05,
|
| 98 |
+
"loss": 0.4575,
|
| 99 |
+
"step": 110
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 1.3953488372093024,
|
| 103 |
+
"grad_norm": 7.364016532897949,
|
| 104 |
+
"learning_rate": 1.586666666666667e-05,
|
| 105 |
+
"loss": 0.436,
|
| 106 |
+
"step": 120
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 1.5116279069767442,
|
| 110 |
+
"grad_norm": 3.313822031021118,
|
| 111 |
+
"learning_rate": 1.72e-05,
|
| 112 |
+
"loss": 0.4582,
|
| 113 |
+
"step": 130
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 1.627906976744186,
|
| 117 |
+
"grad_norm": 9.990741729736328,
|
| 118 |
+
"learning_rate": 1.8533333333333334e-05,
|
| 119 |
+
"loss": 0.4913,
|
| 120 |
+
"step": 140
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 1.744186046511628,
|
| 124 |
+
"grad_norm": 3.886936664581299,
|
| 125 |
+
"learning_rate": 1.9866666666666667e-05,
|
| 126 |
+
"loss": 0.4572,
|
| 127 |
+
"step": 150
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 1.8604651162790697,
|
| 131 |
+
"grad_norm": 20.496986389160156,
|
| 132 |
+
"learning_rate": 1.9601769911504427e-05,
|
| 133 |
+
"loss": 0.4328,
|
| 134 |
+
"step": 160
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 1.9767441860465116,
|
| 138 |
+
"grad_norm": 4.413027286529541,
|
| 139 |
+
"learning_rate": 1.915929203539823e-05,
|
| 140 |
+
"loss": 0.4989,
|
| 141 |
+
"step": 170
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 2.0,
|
| 145 |
+
"eval_accuracy": 0.7,
|
| 146 |
+
"eval_f1": 0.6979758740543855,
|
| 147 |
+
"eval_loss": 0.5208796858787537,
|
| 148 |
+
"eval_precision": 0.7318027210884354,
|
| 149 |
+
"eval_recall": 0.7,
|
| 150 |
+
"eval_runtime": 40.632,
|
| 151 |
+
"eval_samples_per_second": 1.723,
|
| 152 |
+
"eval_steps_per_second": 0.074,
|
| 153 |
+
"step": 172
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 2.0930232558139537,
|
| 157 |
+
"grad_norm": 4.327018737792969,
|
| 158 |
+
"learning_rate": 1.8716814159292035e-05,
|
| 159 |
+
"loss": 0.4098,
|
| 160 |
+
"step": 180
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 2.2093023255813953,
|
| 164 |
+
"grad_norm": 3.8148539066314697,
|
| 165 |
+
"learning_rate": 1.8274336283185843e-05,
|
| 166 |
+
"loss": 0.4117,
|
| 167 |
+
"step": 190
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 2.3255813953488373,
|
| 171 |
+
"grad_norm": 10.718646049499512,
|
| 172 |
+
"learning_rate": 1.7831858407079646e-05,
|
| 173 |
+
"loss": 0.4328,
|
| 174 |
+
"step": 200
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 2.441860465116279,
|
| 178 |
+
"grad_norm": 4.208929538726807,
|
| 179 |
+
"learning_rate": 1.7389380530973454e-05,
|
| 180 |
+
"loss": 0.3792,
|
| 181 |
+
"step": 210
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 2.558139534883721,
|
| 185 |
+
"grad_norm": 7.7923479080200195,
|
| 186 |
+
"learning_rate": 1.6946902654867258e-05,
|
| 187 |
+
"loss": 0.3999,
|
| 188 |
+
"step": 220
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 2.6744186046511627,
|
| 192 |
+
"grad_norm": 4.283344745635986,
|
| 193 |
+
"learning_rate": 1.6504424778761065e-05,
|
| 194 |
+
"loss": 0.3568,
|
| 195 |
+
"step": 230
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 2.7906976744186047,
|
| 199 |
+
"grad_norm": 5.532216548919678,
|
| 200 |
+
"learning_rate": 1.606194690265487e-05,
|
| 201 |
+
"loss": 0.4055,
|
| 202 |
+
"step": 240
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 2.9069767441860463,
|
| 206 |
+
"grad_norm": 3.663770914077759,
|
| 207 |
+
"learning_rate": 1.5619469026548676e-05,
|
| 208 |
+
"loss": 0.3422,
|
| 209 |
+
"step": 250
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 3.0,
|
| 213 |
+
"eval_accuracy": 0.7571428571428571,
|
| 214 |
+
"eval_f1": 0.7574933003504432,
|
| 215 |
+
"eval_loss": 0.4062376022338867,
|
| 216 |
+
"eval_precision": 0.7581531954887218,
|
| 217 |
+
"eval_recall": 0.7571428571428571,
|
| 218 |
+
"eval_runtime": 39.0639,
|
| 219 |
+
"eval_samples_per_second": 1.792,
|
| 220 |
+
"eval_steps_per_second": 0.077,
|
| 221 |
+
"step": 258
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 3.0232558139534884,
|
| 225 |
+
"grad_norm": 4.565627098083496,
|
| 226 |
+
"learning_rate": 1.517699115044248e-05,
|
| 227 |
+
"loss": 0.3082,
|
| 228 |
+
"step": 260
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 3.13953488372093,
|
| 232 |
+
"grad_norm": 14.768342971801758,
|
| 233 |
+
"learning_rate": 1.4734513274336284e-05,
|
| 234 |
+
"loss": 0.3585,
|
| 235 |
+
"step": 270
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 3.255813953488372,
|
| 239 |
+
"grad_norm": 6.304065704345703,
|
| 240 |
+
"learning_rate": 1.429203539823009e-05,
|
| 241 |
+
"loss": 0.3781,
|
| 242 |
+
"step": 280
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 3.3720930232558137,
|
| 246 |
+
"grad_norm": 8.55212688446045,
|
| 247 |
+
"learning_rate": 1.3849557522123895e-05,
|
| 248 |
+
"loss": 0.3061,
|
| 249 |
+
"step": 290
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 3.488372093023256,
|
| 253 |
+
"grad_norm": 10.989974975585938,
|
| 254 |
+
"learning_rate": 1.34070796460177e-05,
|
| 255 |
+
"loss": 0.3507,
|
| 256 |
+
"step": 300
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 3.604651162790698,
|
| 260 |
+
"grad_norm": 8.045317649841309,
|
| 261 |
+
"learning_rate": 1.2964601769911504e-05,
|
| 262 |
+
"loss": 0.3536,
|
| 263 |
+
"step": 310
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 3.7209302325581395,
|
| 267 |
+
"grad_norm": 4.802742958068848,
|
| 268 |
+
"learning_rate": 1.2522123893805312e-05,
|
| 269 |
+
"loss": 0.3107,
|
| 270 |
+
"step": 320
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 3.8372093023255816,
|
| 274 |
+
"grad_norm": 2.4994394779205322,
|
| 275 |
+
"learning_rate": 1.2079646017699115e-05,
|
| 276 |
+
"loss": 0.3118,
|
| 277 |
+
"step": 330
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 3.953488372093023,
|
| 281 |
+
"grad_norm": 7.95784854888916,
|
| 282 |
+
"learning_rate": 1.1637168141592921e-05,
|
| 283 |
+
"loss": 0.305,
|
| 284 |
+
"step": 340
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 4.0,
|
| 288 |
+
"eval_accuracy": 0.8571428571428571,
|
| 289 |
+
"eval_f1": 0.8545918367346939,
|
| 290 |
+
"eval_loss": 0.34065258502960205,
|
| 291 |
+
"eval_precision": 0.8655238095238094,
|
| 292 |
+
"eval_recall": 0.8571428571428571,
|
| 293 |
+
"eval_runtime": 39.7031,
|
| 294 |
+
"eval_samples_per_second": 1.763,
|
| 295 |
+
"eval_steps_per_second": 0.076,
|
| 296 |
+
"step": 344
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 4.069767441860465,
|
| 300 |
+
"grad_norm": 8.617964744567871,
|
| 301 |
+
"learning_rate": 1.1194690265486727e-05,
|
| 302 |
+
"loss": 0.3376,
|
| 303 |
+
"step": 350
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 4.186046511627907,
|
| 307 |
+
"grad_norm": 13.136701583862305,
|
| 308 |
+
"learning_rate": 1.0752212389380532e-05,
|
| 309 |
+
"loss": 0.3829,
|
| 310 |
+
"step": 360
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 4.3023255813953485,
|
| 314 |
+
"grad_norm": 3.352994203567505,
|
| 315 |
+
"learning_rate": 1.0309734513274336e-05,
|
| 316 |
+
"loss": 0.3315,
|
| 317 |
+
"step": 370
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 4.4186046511627906,
|
| 321 |
+
"grad_norm": 4.276778697967529,
|
| 322 |
+
"learning_rate": 9.867256637168142e-06,
|
| 323 |
+
"loss": 0.2992,
|
| 324 |
+
"step": 380
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 4.534883720930233,
|
| 328 |
+
"grad_norm": 4.883634090423584,
|
| 329 |
+
"learning_rate": 9.424778761061947e-06,
|
| 330 |
+
"loss": 0.2683,
|
| 331 |
+
"step": 390
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 4.651162790697675,
|
| 335 |
+
"grad_norm": 7.341738700866699,
|
| 336 |
+
"learning_rate": 8.982300884955753e-06,
|
| 337 |
+
"loss": 0.262,
|
| 338 |
+
"step": 400
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 4.767441860465116,
|
| 342 |
+
"grad_norm": 8.630583763122559,
|
| 343 |
+
"learning_rate": 8.539823008849558e-06,
|
| 344 |
+
"loss": 0.2658,
|
| 345 |
+
"step": 410
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 4.883720930232558,
|
| 349 |
+
"grad_norm": 11.391676902770996,
|
| 350 |
+
"learning_rate": 8.097345132743364e-06,
|
| 351 |
+
"loss": 0.3288,
|
| 352 |
+
"step": 420
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 5.0,
|
| 356 |
+
"grad_norm": 44.6805419921875,
|
| 357 |
+
"learning_rate": 7.654867256637168e-06,
|
| 358 |
+
"loss": 0.314,
|
| 359 |
+
"step": 430
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 5.0,
|
| 363 |
+
"eval_accuracy": 0.7714285714285715,
|
| 364 |
+
"eval_f1": 0.7714285714285715,
|
| 365 |
+
"eval_loss": 0.43682464957237244,
|
| 366 |
+
"eval_precision": 0.7714285714285715,
|
| 367 |
+
"eval_recall": 0.7714285714285715,
|
| 368 |
+
"eval_runtime": 38.7605,
|
| 369 |
+
"eval_samples_per_second": 1.806,
|
| 370 |
+
"eval_steps_per_second": 0.077,
|
| 371 |
+
"step": 430
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 5.116279069767442,
|
| 375 |
+
"grad_norm": 3.780876398086548,
|
| 376 |
+
"learning_rate": 7.212389380530974e-06,
|
| 377 |
+
"loss": 0.3121,
|
| 378 |
+
"step": 440
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 5.232558139534884,
|
| 382 |
+
"grad_norm": 4.6331000328063965,
|
| 383 |
+
"learning_rate": 6.76991150442478e-06,
|
| 384 |
+
"loss": 0.3032,
|
| 385 |
+
"step": 450
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 5.348837209302325,
|
| 389 |
+
"grad_norm": 3.838736057281494,
|
| 390 |
+
"learning_rate": 6.3274336283185845e-06,
|
| 391 |
+
"loss": 0.1971,
|
| 392 |
+
"step": 460
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 5.465116279069767,
|
| 396 |
+
"grad_norm": 7.0051469802856445,
|
| 397 |
+
"learning_rate": 5.88495575221239e-06,
|
| 398 |
+
"loss": 0.2727,
|
| 399 |
+
"step": 470
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 5.5813953488372094,
|
| 403 |
+
"grad_norm": 6.933923721313477,
|
| 404 |
+
"learning_rate": 5.442477876106195e-06,
|
| 405 |
+
"loss": 0.2669,
|
| 406 |
+
"step": 480
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 5.6976744186046515,
|
| 410 |
+
"grad_norm": 4.192832946777344,
|
| 411 |
+
"learning_rate": 5e-06,
|
| 412 |
+
"loss": 0.2535,
|
| 413 |
+
"step": 490
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 5.813953488372093,
|
| 417 |
+
"grad_norm": 4.221975803375244,
|
| 418 |
+
"learning_rate": 4.557522123893805e-06,
|
| 419 |
+
"loss": 0.2963,
|
| 420 |
+
"step": 500
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 5.930232558139535,
|
| 424 |
+
"grad_norm": 7.972716331481934,
|
| 425 |
+
"learning_rate": 4.115044247787611e-06,
|
| 426 |
+
"loss": 0.2709,
|
| 427 |
+
"step": 510
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"epoch": 6.0,
|
| 431 |
+
"eval_accuracy": 0.8142857142857143,
|
| 432 |
+
"eval_f1": 0.814553700267986,
|
| 433 |
+
"eval_loss": 0.3767072856426239,
|
| 434 |
+
"eval_precision": 0.8151550751879698,
|
| 435 |
+
"eval_recall": 0.8142857142857143,
|
| 436 |
+
"eval_runtime": 40.2015,
|
| 437 |
+
"eval_samples_per_second": 1.741,
|
| 438 |
+
"eval_steps_per_second": 0.075,
|
| 439 |
+
"step": 516
|
| 440 |
+
}
|
| 441 |
+
],
|
| 442 |
+
"logging_steps": 10,
|
| 443 |
+
"max_steps": 602,
|
| 444 |
+
"num_input_tokens_seen": 0,
|
| 445 |
+
"num_train_epochs": 7,
|
| 446 |
+
"save_steps": 500,
|
| 447 |
+
"stateful_callbacks": {
|
| 448 |
+
"EarlyStoppingCallback": {
|
| 449 |
+
"args": {
|
| 450 |
+
"early_stopping_patience": 2,
|
| 451 |
+
"early_stopping_threshold": 0.0
|
| 452 |
+
},
|
| 453 |
+
"attributes": {
|
| 454 |
+
"early_stopping_patience_counter": 2
|
| 455 |
+
}
|
| 456 |
+
},
|
| 457 |
+
"TrainerControl": {
|
| 458 |
+
"args": {
|
| 459 |
+
"should_epoch_stop": false,
|
| 460 |
+
"should_evaluate": false,
|
| 461 |
+
"should_log": false,
|
| 462 |
+
"should_save": true,
|
| 463 |
+
"should_training_stop": true
|
| 464 |
+
},
|
| 465 |
+
"attributes": {}
|
| 466 |
+
}
|
| 467 |
+
},
|
| 468 |
+
"total_flos": 4137555984396360.0,
|
| 469 |
+
"train_batch_size": 32,
|
| 470 |
+
"trial_name": null,
|
| 471 |
+
"trial_params": null
|
| 472 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cb5061143adc12fc81a253248f802d4776e5e609c983ee6538cb8492632e8444
|
| 3 |
+
size 5304
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|