Upload folder using huggingface_hub
Browse files- checkpoint-1800/config.json +24 -0
- checkpoint-1800/model.safetensors +3 -0
- checkpoint-1800/optimizer.pt +3 -0
- checkpoint-1800/rng_state.pth +3 -0
- checkpoint-1800/scheduler.pt +3 -0
- checkpoint-1800/special_tokens_map.json +7 -0
- checkpoint-1800/tokenizer.json +0 -0
- checkpoint-1800/tokenizer_config.json +56 -0
- checkpoint-1800/trainer_state.json +367 -0
- checkpoint-1800/training_args.bin +3 -0
- checkpoint-1800/vocab.txt +0 -0
- checkpoint-1947/config.json +24 -0
- checkpoint-1947/model.safetensors +3 -0
- checkpoint-1947/optimizer.pt +3 -0
- checkpoint-1947/rng_state.pth +3 -0
- checkpoint-1947/scheduler.pt +3 -0
- checkpoint-1947/special_tokens_map.json +7 -0
- checkpoint-1947/tokenizer.json +0 -0
- checkpoint-1947/tokenizer_config.json +56 -0
- checkpoint-1947/trainer_state.json +381 -0
- checkpoint-1947/training_args.bin +3 -0
- checkpoint-1947/vocab.txt +0 -0
- config.json +24 -0
- model.safetensors +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +56 -0
- vocab.txt +0 -0
checkpoint-1800/config.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation": "gelu",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"DistilBertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.1,
|
| 7 |
+
"dim": 768,
|
| 8 |
+
"dropout": 0.1,
|
| 9 |
+
"hidden_dim": 3072,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"max_position_embeddings": 512,
|
| 12 |
+
"model_type": "distilbert",
|
| 13 |
+
"n_heads": 12,
|
| 14 |
+
"n_layers": 6,
|
| 15 |
+
"pad_token_id": 0,
|
| 16 |
+
"problem_type": "single_label_classification",
|
| 17 |
+
"qa_dropout": 0.1,
|
| 18 |
+
"seq_classif_dropout": 0.2,
|
| 19 |
+
"sinusoidal_pos_embds": false,
|
| 20 |
+
"tie_weights_": true,
|
| 21 |
+
"torch_dtype": "float32",
|
| 22 |
+
"transformers_version": "4.51.1",
|
| 23 |
+
"vocab_size": 30522
|
| 24 |
+
}
|
checkpoint-1800/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d1b50dcfadc970946e6f245aaa179b7851959c17a01d83129ac9640b17f45638
|
| 3 |
+
size 267832560
|
checkpoint-1800/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e908c412a83dad12d76427fd698ed3e59177ad14463e763d02beed55ce4826e8
|
| 3 |
+
size 535727290
|
checkpoint-1800/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:372d885561f7d262286a4d47b4b2c6b1e651dbb06b0ed245c2fea50564774c2f
|
| 3 |
+
size 14244
|
checkpoint-1800/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e98f31b801f8f0743c709eec311eeea0794fb93f53415b772e1133cd088674d2
|
| 3 |
+
size 1064
|
checkpoint-1800/special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
checkpoint-1800/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-1800/tokenizer_config.json
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[PAD]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"100": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"101": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"102": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"103": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"clean_up_tokenization_spaces": false,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_lower_case": true,
|
| 47 |
+
"extra_special_tokens": {},
|
| 48 |
+
"mask_token": "[MASK]",
|
| 49 |
+
"model_max_length": 512,
|
| 50 |
+
"pad_token": "[PAD]",
|
| 51 |
+
"sep_token": "[SEP]",
|
| 52 |
+
"strip_accents": null,
|
| 53 |
+
"tokenize_chinese_chars": true,
|
| 54 |
+
"tokenizer_class": "DistilBertTokenizer",
|
| 55 |
+
"unk_token": "[UNK]"
|
| 56 |
+
}
|
checkpoint-1800/trainer_state.json
ADDED
|
@@ -0,0 +1,367 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 2.773497688751926,
|
| 6 |
+
"eval_steps": 200,
|
| 7 |
+
"global_step": 1800,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.07704160246533127,
|
| 14 |
+
"grad_norm": 10.05362606048584,
|
| 15 |
+
"learning_rate": 1.9496661530559838e-05,
|
| 16 |
+
"loss": 0.4736,
|
| 17 |
+
"step": 50
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.15408320493066255,
|
| 21 |
+
"grad_norm": 6.351088047027588,
|
| 22 |
+
"learning_rate": 1.898305084745763e-05,
|
| 23 |
+
"loss": 0.2932,
|
| 24 |
+
"step": 100
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.23112480739599384,
|
| 28 |
+
"grad_norm": 2.3145954608917236,
|
| 29 |
+
"learning_rate": 1.846944016435542e-05,
|
| 30 |
+
"loss": 0.2252,
|
| 31 |
+
"step": 150
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.3081664098613251,
|
| 35 |
+
"grad_norm": 4.7438859939575195,
|
| 36 |
+
"learning_rate": 1.7955829481253212e-05,
|
| 37 |
+
"loss": 0.2269,
|
| 38 |
+
"step": 200
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.3081664098613251,
|
| 42 |
+
"eval_accuracy": 0.9313536444273043,
|
| 43 |
+
"eval_loss": 0.17986150085926056,
|
| 44 |
+
"eval_runtime": 23.9933,
|
| 45 |
+
"eval_samples_per_second": 108.072,
|
| 46 |
+
"eval_steps_per_second": 1.709,
|
| 47 |
+
"step": 200
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 0.3852080123266564,
|
| 51 |
+
"grad_norm": 4.632046222686768,
|
| 52 |
+
"learning_rate": 1.7442218798151004e-05,
|
| 53 |
+
"loss": 0.1725,
|
| 54 |
+
"step": 250
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 0.4622496147919877,
|
| 58 |
+
"grad_norm": 6.293688774108887,
|
| 59 |
+
"learning_rate": 1.6928608115048793e-05,
|
| 60 |
+
"loss": 0.1877,
|
| 61 |
+
"step": 300
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 0.539291217257319,
|
| 65 |
+
"grad_norm": 2.77512264251709,
|
| 66 |
+
"learning_rate": 1.6414997431946586e-05,
|
| 67 |
+
"loss": 0.1837,
|
| 68 |
+
"step": 350
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.6163328197226502,
|
| 72 |
+
"grad_norm": 4.431891441345215,
|
| 73 |
+
"learning_rate": 1.5901386748844375e-05,
|
| 74 |
+
"loss": 0.1644,
|
| 75 |
+
"step": 400
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.6163328197226502,
|
| 79 |
+
"eval_accuracy": 0.9390667180871577,
|
| 80 |
+
"eval_loss": 0.17171578109264374,
|
| 81 |
+
"eval_runtime": 24.501,
|
| 82 |
+
"eval_samples_per_second": 105.832,
|
| 83 |
+
"eval_steps_per_second": 1.673,
|
| 84 |
+
"step": 400
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 0.6933744221879815,
|
| 88 |
+
"grad_norm": 3.417551040649414,
|
| 89 |
+
"learning_rate": 1.5387776065742167e-05,
|
| 90 |
+
"loss": 0.159,
|
| 91 |
+
"step": 450
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 0.7704160246533128,
|
| 95 |
+
"grad_norm": 8.935800552368164,
|
| 96 |
+
"learning_rate": 1.487416538263996e-05,
|
| 97 |
+
"loss": 0.1613,
|
| 98 |
+
"step": 500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.847457627118644,
|
| 102 |
+
"grad_norm": 8.21597671508789,
|
| 103 |
+
"learning_rate": 1.4360554699537752e-05,
|
| 104 |
+
"loss": 0.165,
|
| 105 |
+
"step": 550
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.9244992295839753,
|
| 109 |
+
"grad_norm": 7.380743026733398,
|
| 110 |
+
"learning_rate": 1.3846944016435544e-05,
|
| 111 |
+
"loss": 0.1658,
|
| 112 |
+
"step": 600
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 0.9244992295839753,
|
| 116 |
+
"eval_accuracy": 0.9460084843810258,
|
| 117 |
+
"eval_loss": 0.14509333670139313,
|
| 118 |
+
"eval_runtime": 24.6419,
|
| 119 |
+
"eval_samples_per_second": 105.227,
|
| 120 |
+
"eval_steps_per_second": 1.664,
|
| 121 |
+
"step": 600
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 1.0015408320493067,
|
| 125 |
+
"grad_norm": 5.918083667755127,
|
| 126 |
+
"learning_rate": 1.3333333333333333e-05,
|
| 127 |
+
"loss": 0.1583,
|
| 128 |
+
"step": 650
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 1.078582434514638,
|
| 132 |
+
"grad_norm": 4.35791015625,
|
| 133 |
+
"learning_rate": 1.2819722650231126e-05,
|
| 134 |
+
"loss": 0.0942,
|
| 135 |
+
"step": 700
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 1.1556240369799693,
|
| 139 |
+
"grad_norm": 2.5846035480499268,
|
| 140 |
+
"learning_rate": 1.2306111967128918e-05,
|
| 141 |
+
"loss": 0.112,
|
| 142 |
+
"step": 750
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 1.2326656394453004,
|
| 146 |
+
"grad_norm": 4.686473846435547,
|
| 147 |
+
"learning_rate": 1.1792501284026709e-05,
|
| 148 |
+
"loss": 0.1124,
|
| 149 |
+
"step": 800
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 1.2326656394453004,
|
| 153 |
+
"eval_accuracy": 0.9533359043578866,
|
| 154 |
+
"eval_loss": 0.14733003079891205,
|
| 155 |
+
"eval_runtime": 24.7017,
|
| 156 |
+
"eval_samples_per_second": 104.972,
|
| 157 |
+
"eval_steps_per_second": 1.66,
|
| 158 |
+
"step": 800
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 1.3097072419106317,
|
| 162 |
+
"grad_norm": 4.999251842498779,
|
| 163 |
+
"learning_rate": 1.12788906009245e-05,
|
| 164 |
+
"loss": 0.0973,
|
| 165 |
+
"step": 850
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 1.386748844375963,
|
| 169 |
+
"grad_norm": 6.902672290802002,
|
| 170 |
+
"learning_rate": 1.0765279917822292e-05,
|
| 171 |
+
"loss": 0.1005,
|
| 172 |
+
"step": 900
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 1.4637904468412943,
|
| 176 |
+
"grad_norm": 0.9856418371200562,
|
| 177 |
+
"learning_rate": 1.0251669234720083e-05,
|
| 178 |
+
"loss": 0.0962,
|
| 179 |
+
"step": 950
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 1.5408320493066254,
|
| 183 |
+
"grad_norm": 7.715114593505859,
|
| 184 |
+
"learning_rate": 9.738058551617875e-06,
|
| 185 |
+
"loss": 0.082,
|
| 186 |
+
"step": 1000
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 1.5408320493066254,
|
| 190 |
+
"eval_accuracy": 0.9502506748939452,
|
| 191 |
+
"eval_loss": 0.1763252317905426,
|
| 192 |
+
"eval_runtime": 24.7441,
|
| 193 |
+
"eval_samples_per_second": 104.793,
|
| 194 |
+
"eval_steps_per_second": 1.657,
|
| 195 |
+
"step": 1000
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 1.6178736517719567,
|
| 199 |
+
"grad_norm": 5.8433380126953125,
|
| 200 |
+
"learning_rate": 9.224447868515666e-06,
|
| 201 |
+
"loss": 0.101,
|
| 202 |
+
"step": 1050
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 1.694915254237288,
|
| 206 |
+
"grad_norm": 5.463233470916748,
|
| 207 |
+
"learning_rate": 8.710837185413458e-06,
|
| 208 |
+
"loss": 0.0829,
|
| 209 |
+
"step": 1100
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 1.7719568567026194,
|
| 213 |
+
"grad_norm": 10.795263290405273,
|
| 214 |
+
"learning_rate": 8.197226502311249e-06,
|
| 215 |
+
"loss": 0.1151,
|
| 216 |
+
"step": 1150
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 1.8489984591679507,
|
| 220 |
+
"grad_norm": 10.039093971252441,
|
| 221 |
+
"learning_rate": 7.68361581920904e-06,
|
| 222 |
+
"loss": 0.0893,
|
| 223 |
+
"step": 1200
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 1.8489984591679507,
|
| 227 |
+
"eval_accuracy": 0.9541072117238719,
|
| 228 |
+
"eval_loss": 0.15539486706256866,
|
| 229 |
+
"eval_runtime": 24.6202,
|
| 230 |
+
"eval_samples_per_second": 105.32,
|
| 231 |
+
"eval_steps_per_second": 1.665,
|
| 232 |
+
"step": 1200
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 1.926040061633282,
|
| 236 |
+
"grad_norm": 3.626760721206665,
|
| 237 |
+
"learning_rate": 7.170005136106831e-06,
|
| 238 |
+
"loss": 0.0855,
|
| 239 |
+
"step": 1250
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 2.0030816640986133,
|
| 243 |
+
"grad_norm": 8.325395584106445,
|
| 244 |
+
"learning_rate": 6.6563944530046235e-06,
|
| 245 |
+
"loss": 0.0751,
|
| 246 |
+
"step": 1300
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 2.0801232665639446,
|
| 250 |
+
"grad_norm": 0.14258642494678497,
|
| 251 |
+
"learning_rate": 6.142783769902414e-06,
|
| 252 |
+
"loss": 0.0475,
|
| 253 |
+
"step": 1350
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 2.157164869029276,
|
| 257 |
+
"grad_norm": 11.120409965515137,
|
| 258 |
+
"learning_rate": 5.629173086800206e-06,
|
| 259 |
+
"loss": 0.0514,
|
| 260 |
+
"step": 1400
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 2.157164869029276,
|
| 264 |
+
"eval_accuracy": 0.9529502506748939,
|
| 265 |
+
"eval_loss": 0.1841726303100586,
|
| 266 |
+
"eval_runtime": 25.0063,
|
| 267 |
+
"eval_samples_per_second": 103.694,
|
| 268 |
+
"eval_steps_per_second": 1.64,
|
| 269 |
+
"step": 1400
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 2.2342064714946073,
|
| 273 |
+
"grad_norm": 1.1915600299835205,
|
| 274 |
+
"learning_rate": 5.115562403697998e-06,
|
| 275 |
+
"loss": 0.0485,
|
| 276 |
+
"step": 1450
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 2.3112480739599386,
|
| 280 |
+
"grad_norm": 0.05526341125369072,
|
| 281 |
+
"learning_rate": 4.601951720595789e-06,
|
| 282 |
+
"loss": 0.06,
|
| 283 |
+
"step": 1500
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 2.3882896764252695,
|
| 287 |
+
"grad_norm": 0.2091483324766159,
|
| 288 |
+
"learning_rate": 4.08834103749358e-06,
|
| 289 |
+
"loss": 0.0381,
|
| 290 |
+
"step": 1550
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 2.4653312788906008,
|
| 294 |
+
"grad_norm": 3.9713540077209473,
|
| 295 |
+
"learning_rate": 3.574730354391371e-06,
|
| 296 |
+
"loss": 0.0429,
|
| 297 |
+
"step": 1600
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 2.4653312788906008,
|
| 301 |
+
"eval_accuracy": 0.956421133821828,
|
| 302 |
+
"eval_loss": 0.18568892776966095,
|
| 303 |
+
"eval_runtime": 24.8383,
|
| 304 |
+
"eval_samples_per_second": 104.395,
|
| 305 |
+
"eval_steps_per_second": 1.651,
|
| 306 |
+
"step": 1600
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 2.542372881355932,
|
| 310 |
+
"grad_norm": 11.278206825256348,
|
| 311 |
+
"learning_rate": 3.061119671289163e-06,
|
| 312 |
+
"loss": 0.0713,
|
| 313 |
+
"step": 1650
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 2.6194144838212634,
|
| 317 |
+
"grad_norm": 0.25844085216522217,
|
| 318 |
+
"learning_rate": 2.5475089881869547e-06,
|
| 319 |
+
"loss": 0.0469,
|
| 320 |
+
"step": 1700
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 2.6964560862865947,
|
| 324 |
+
"grad_norm": 0.8902830481529236,
|
| 325 |
+
"learning_rate": 2.033898305084746e-06,
|
| 326 |
+
"loss": 0.0601,
|
| 327 |
+
"step": 1750
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 2.773497688751926,
|
| 331 |
+
"grad_norm": 3.1224634647369385,
|
| 332 |
+
"learning_rate": 1.5202876219825374e-06,
|
| 333 |
+
"loss": 0.0412,
|
| 334 |
+
"step": 1800
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 2.773497688751926,
|
| 338 |
+
"eval_accuracy": 0.9560354801388353,
|
| 339 |
+
"eval_loss": 0.17419876158237457,
|
| 340 |
+
"eval_runtime": 24.7703,
|
| 341 |
+
"eval_samples_per_second": 104.682,
|
| 342 |
+
"eval_steps_per_second": 1.655,
|
| 343 |
+
"step": 1800
|
| 344 |
+
}
|
| 345 |
+
],
|
| 346 |
+
"logging_steps": 50,
|
| 347 |
+
"max_steps": 1947,
|
| 348 |
+
"num_input_tokens_seen": 0,
|
| 349 |
+
"num_train_epochs": 3,
|
| 350 |
+
"save_steps": 200,
|
| 351 |
+
"stateful_callbacks": {
|
| 352 |
+
"TrainerControl": {
|
| 353 |
+
"args": {
|
| 354 |
+
"should_epoch_stop": false,
|
| 355 |
+
"should_evaluate": false,
|
| 356 |
+
"should_log": false,
|
| 357 |
+
"should_save": true,
|
| 358 |
+
"should_training_stop": false
|
| 359 |
+
},
|
| 360 |
+
"attributes": {}
|
| 361 |
+
}
|
| 362 |
+
},
|
| 363 |
+
"total_flos": 7623763727450112.0,
|
| 364 |
+
"train_batch_size": 32,
|
| 365 |
+
"trial_name": null,
|
| 366 |
+
"trial_params": null
|
| 367 |
+
}
|
checkpoint-1800/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:590efece3220d2015b3187be0322ce739d60183b6edb84c6c589d3e1da99e031
|
| 3 |
+
size 5240
|
checkpoint-1800/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-1947/config.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation": "gelu",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"DistilBertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.1,
|
| 7 |
+
"dim": 768,
|
| 8 |
+
"dropout": 0.1,
|
| 9 |
+
"hidden_dim": 3072,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"max_position_embeddings": 512,
|
| 12 |
+
"model_type": "distilbert",
|
| 13 |
+
"n_heads": 12,
|
| 14 |
+
"n_layers": 6,
|
| 15 |
+
"pad_token_id": 0,
|
| 16 |
+
"problem_type": "single_label_classification",
|
| 17 |
+
"qa_dropout": 0.1,
|
| 18 |
+
"seq_classif_dropout": 0.2,
|
| 19 |
+
"sinusoidal_pos_embds": false,
|
| 20 |
+
"tie_weights_": true,
|
| 21 |
+
"torch_dtype": "float32",
|
| 22 |
+
"transformers_version": "4.51.1",
|
| 23 |
+
"vocab_size": 30522
|
| 24 |
+
}
|
checkpoint-1947/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fb43262efa605f47af9fbdd580a40049def5dec51e68ebfd80791cc3ca245901
|
| 3 |
+
size 267832560
|
checkpoint-1947/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3f8f152da457677d3fe31424ea8eb2e0ec06712f3526bd75293a0a8ba9c3ffa5
|
| 3 |
+
size 535727290
|
checkpoint-1947/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8ad3421938f9c44928292ff5697c8909a9e5684b52323ad08263736739829e00
|
| 3 |
+
size 14244
|
checkpoint-1947/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:828d5e6e61118686315a961917935d65140efe9be4e45d7a22aa713bfc15f6c1
|
| 3 |
+
size 1064
|
checkpoint-1947/special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
checkpoint-1947/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-1947/tokenizer_config.json
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[PAD]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"100": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"101": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"102": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"103": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"clean_up_tokenization_spaces": false,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_lower_case": true,
|
| 47 |
+
"extra_special_tokens": {},
|
| 48 |
+
"mask_token": "[MASK]",
|
| 49 |
+
"model_max_length": 512,
|
| 50 |
+
"pad_token": "[PAD]",
|
| 51 |
+
"sep_token": "[SEP]",
|
| 52 |
+
"strip_accents": null,
|
| 53 |
+
"tokenize_chinese_chars": true,
|
| 54 |
+
"tokenizer_class": "DistilBertTokenizer",
|
| 55 |
+
"unk_token": "[UNK]"
|
| 56 |
+
}
|
checkpoint-1947/trainer_state.json
ADDED
|
@@ -0,0 +1,381 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 3.0,
|
| 6 |
+
"eval_steps": 200,
|
| 7 |
+
"global_step": 1947,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.07704160246533127,
|
| 14 |
+
"grad_norm": 10.05362606048584,
|
| 15 |
+
"learning_rate": 1.9496661530559838e-05,
|
| 16 |
+
"loss": 0.4736,
|
| 17 |
+
"step": 50
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.15408320493066255,
|
| 21 |
+
"grad_norm": 6.351088047027588,
|
| 22 |
+
"learning_rate": 1.898305084745763e-05,
|
| 23 |
+
"loss": 0.2932,
|
| 24 |
+
"step": 100
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.23112480739599384,
|
| 28 |
+
"grad_norm": 2.3145954608917236,
|
| 29 |
+
"learning_rate": 1.846944016435542e-05,
|
| 30 |
+
"loss": 0.2252,
|
| 31 |
+
"step": 150
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.3081664098613251,
|
| 35 |
+
"grad_norm": 4.7438859939575195,
|
| 36 |
+
"learning_rate": 1.7955829481253212e-05,
|
| 37 |
+
"loss": 0.2269,
|
| 38 |
+
"step": 200
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.3081664098613251,
|
| 42 |
+
"eval_accuracy": 0.9313536444273043,
|
| 43 |
+
"eval_loss": 0.17986150085926056,
|
| 44 |
+
"eval_runtime": 23.9933,
|
| 45 |
+
"eval_samples_per_second": 108.072,
|
| 46 |
+
"eval_steps_per_second": 1.709,
|
| 47 |
+
"step": 200
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 0.3852080123266564,
|
| 51 |
+
"grad_norm": 4.632046222686768,
|
| 52 |
+
"learning_rate": 1.7442218798151004e-05,
|
| 53 |
+
"loss": 0.1725,
|
| 54 |
+
"step": 250
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 0.4622496147919877,
|
| 58 |
+
"grad_norm": 6.293688774108887,
|
| 59 |
+
"learning_rate": 1.6928608115048793e-05,
|
| 60 |
+
"loss": 0.1877,
|
| 61 |
+
"step": 300
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 0.539291217257319,
|
| 65 |
+
"grad_norm": 2.77512264251709,
|
| 66 |
+
"learning_rate": 1.6414997431946586e-05,
|
| 67 |
+
"loss": 0.1837,
|
| 68 |
+
"step": 350
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.6163328197226502,
|
| 72 |
+
"grad_norm": 4.431891441345215,
|
| 73 |
+
"learning_rate": 1.5901386748844375e-05,
|
| 74 |
+
"loss": 0.1644,
|
| 75 |
+
"step": 400
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.6163328197226502,
|
| 79 |
+
"eval_accuracy": 0.9390667180871577,
|
| 80 |
+
"eval_loss": 0.17171578109264374,
|
| 81 |
+
"eval_runtime": 24.501,
|
| 82 |
+
"eval_samples_per_second": 105.832,
|
| 83 |
+
"eval_steps_per_second": 1.673,
|
| 84 |
+
"step": 400
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 0.6933744221879815,
|
| 88 |
+
"grad_norm": 3.417551040649414,
|
| 89 |
+
"learning_rate": 1.5387776065742167e-05,
|
| 90 |
+
"loss": 0.159,
|
| 91 |
+
"step": 450
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 0.7704160246533128,
|
| 95 |
+
"grad_norm": 8.935800552368164,
|
| 96 |
+
"learning_rate": 1.487416538263996e-05,
|
| 97 |
+
"loss": 0.1613,
|
| 98 |
+
"step": 500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.847457627118644,
|
| 102 |
+
"grad_norm": 8.21597671508789,
|
| 103 |
+
"learning_rate": 1.4360554699537752e-05,
|
| 104 |
+
"loss": 0.165,
|
| 105 |
+
"step": 550
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.9244992295839753,
|
| 109 |
+
"grad_norm": 7.380743026733398,
|
| 110 |
+
"learning_rate": 1.3846944016435544e-05,
|
| 111 |
+
"loss": 0.1658,
|
| 112 |
+
"step": 600
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 0.9244992295839753,
|
| 116 |
+
"eval_accuracy": 0.9460084843810258,
|
| 117 |
+
"eval_loss": 0.14509333670139313,
|
| 118 |
+
"eval_runtime": 24.6419,
|
| 119 |
+
"eval_samples_per_second": 105.227,
|
| 120 |
+
"eval_steps_per_second": 1.664,
|
| 121 |
+
"step": 600
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 1.0015408320493067,
|
| 125 |
+
"grad_norm": 5.918083667755127,
|
| 126 |
+
"learning_rate": 1.3333333333333333e-05,
|
| 127 |
+
"loss": 0.1583,
|
| 128 |
+
"step": 650
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 1.078582434514638,
|
| 132 |
+
"grad_norm": 4.35791015625,
|
| 133 |
+
"learning_rate": 1.2819722650231126e-05,
|
| 134 |
+
"loss": 0.0942,
|
| 135 |
+
"step": 700
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 1.1556240369799693,
|
| 139 |
+
"grad_norm": 2.5846035480499268,
|
| 140 |
+
"learning_rate": 1.2306111967128918e-05,
|
| 141 |
+
"loss": 0.112,
|
| 142 |
+
"step": 750
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 1.2326656394453004,
|
| 146 |
+
"grad_norm": 4.686473846435547,
|
| 147 |
+
"learning_rate": 1.1792501284026709e-05,
|
| 148 |
+
"loss": 0.1124,
|
| 149 |
+
"step": 800
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 1.2326656394453004,
|
| 153 |
+
"eval_accuracy": 0.9533359043578866,
|
| 154 |
+
"eval_loss": 0.14733003079891205,
|
| 155 |
+
"eval_runtime": 24.7017,
|
| 156 |
+
"eval_samples_per_second": 104.972,
|
| 157 |
+
"eval_steps_per_second": 1.66,
|
| 158 |
+
"step": 800
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 1.3097072419106317,
|
| 162 |
+
"grad_norm": 4.999251842498779,
|
| 163 |
+
"learning_rate": 1.12788906009245e-05,
|
| 164 |
+
"loss": 0.0973,
|
| 165 |
+
"step": 850
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 1.386748844375963,
|
| 169 |
+
"grad_norm": 6.902672290802002,
|
| 170 |
+
"learning_rate": 1.0765279917822292e-05,
|
| 171 |
+
"loss": 0.1005,
|
| 172 |
+
"step": 900
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 1.4637904468412943,
|
| 176 |
+
"grad_norm": 0.9856418371200562,
|
| 177 |
+
"learning_rate": 1.0251669234720083e-05,
|
| 178 |
+
"loss": 0.0962,
|
| 179 |
+
"step": 950
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 1.5408320493066254,
|
| 183 |
+
"grad_norm": 7.715114593505859,
|
| 184 |
+
"learning_rate": 9.738058551617875e-06,
|
| 185 |
+
"loss": 0.082,
|
| 186 |
+
"step": 1000
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 1.5408320493066254,
|
| 190 |
+
"eval_accuracy": 0.9502506748939452,
|
| 191 |
+
"eval_loss": 0.1763252317905426,
|
| 192 |
+
"eval_runtime": 24.7441,
|
| 193 |
+
"eval_samples_per_second": 104.793,
|
| 194 |
+
"eval_steps_per_second": 1.657,
|
| 195 |
+
"step": 1000
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 1.6178736517719567,
|
| 199 |
+
"grad_norm": 5.8433380126953125,
|
| 200 |
+
"learning_rate": 9.224447868515666e-06,
|
| 201 |
+
"loss": 0.101,
|
| 202 |
+
"step": 1050
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 1.694915254237288,
|
| 206 |
+
"grad_norm": 5.463233470916748,
|
| 207 |
+
"learning_rate": 8.710837185413458e-06,
|
| 208 |
+
"loss": 0.0829,
|
| 209 |
+
"step": 1100
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 1.7719568567026194,
|
| 213 |
+
"grad_norm": 10.795263290405273,
|
| 214 |
+
"learning_rate": 8.197226502311249e-06,
|
| 215 |
+
"loss": 0.1151,
|
| 216 |
+
"step": 1150
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 1.8489984591679507,
|
| 220 |
+
"grad_norm": 10.039093971252441,
|
| 221 |
+
"learning_rate": 7.68361581920904e-06,
|
| 222 |
+
"loss": 0.0893,
|
| 223 |
+
"step": 1200
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 1.8489984591679507,
|
| 227 |
+
"eval_accuracy": 0.9541072117238719,
|
| 228 |
+
"eval_loss": 0.15539486706256866,
|
| 229 |
+
"eval_runtime": 24.6202,
|
| 230 |
+
"eval_samples_per_second": 105.32,
|
| 231 |
+
"eval_steps_per_second": 1.665,
|
| 232 |
+
"step": 1200
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 1.926040061633282,
|
| 236 |
+
"grad_norm": 3.626760721206665,
|
| 237 |
+
"learning_rate": 7.170005136106831e-06,
|
| 238 |
+
"loss": 0.0855,
|
| 239 |
+
"step": 1250
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 2.0030816640986133,
|
| 243 |
+
"grad_norm": 8.325395584106445,
|
| 244 |
+
"learning_rate": 6.6563944530046235e-06,
|
| 245 |
+
"loss": 0.0751,
|
| 246 |
+
"step": 1300
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 2.0801232665639446,
|
| 250 |
+
"grad_norm": 0.14258642494678497,
|
| 251 |
+
"learning_rate": 6.142783769902414e-06,
|
| 252 |
+
"loss": 0.0475,
|
| 253 |
+
"step": 1350
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 2.157164869029276,
|
| 257 |
+
"grad_norm": 11.120409965515137,
|
| 258 |
+
"learning_rate": 5.629173086800206e-06,
|
| 259 |
+
"loss": 0.0514,
|
| 260 |
+
"step": 1400
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 2.157164869029276,
|
| 264 |
+
"eval_accuracy": 0.9529502506748939,
|
| 265 |
+
"eval_loss": 0.1841726303100586,
|
| 266 |
+
"eval_runtime": 25.0063,
|
| 267 |
+
"eval_samples_per_second": 103.694,
|
| 268 |
+
"eval_steps_per_second": 1.64,
|
| 269 |
+
"step": 1400
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 2.2342064714946073,
|
| 273 |
+
"grad_norm": 1.1915600299835205,
|
| 274 |
+
"learning_rate": 5.115562403697998e-06,
|
| 275 |
+
"loss": 0.0485,
|
| 276 |
+
"step": 1450
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 2.3112480739599386,
|
| 280 |
+
"grad_norm": 0.05526341125369072,
|
| 281 |
+
"learning_rate": 4.601951720595789e-06,
|
| 282 |
+
"loss": 0.06,
|
| 283 |
+
"step": 1500
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 2.3882896764252695,
|
| 287 |
+
"grad_norm": 0.2091483324766159,
|
| 288 |
+
"learning_rate": 4.08834103749358e-06,
|
| 289 |
+
"loss": 0.0381,
|
| 290 |
+
"step": 1550
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 2.4653312788906008,
|
| 294 |
+
"grad_norm": 3.9713540077209473,
|
| 295 |
+
"learning_rate": 3.574730354391371e-06,
|
| 296 |
+
"loss": 0.0429,
|
| 297 |
+
"step": 1600
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 2.4653312788906008,
|
| 301 |
+
"eval_accuracy": 0.956421133821828,
|
| 302 |
+
"eval_loss": 0.18568892776966095,
|
| 303 |
+
"eval_runtime": 24.8383,
|
| 304 |
+
"eval_samples_per_second": 104.395,
|
| 305 |
+
"eval_steps_per_second": 1.651,
|
| 306 |
+
"step": 1600
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 2.542372881355932,
|
| 310 |
+
"grad_norm": 11.278206825256348,
|
| 311 |
+
"learning_rate": 3.061119671289163e-06,
|
| 312 |
+
"loss": 0.0713,
|
| 313 |
+
"step": 1650
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 2.6194144838212634,
|
| 317 |
+
"grad_norm": 0.25844085216522217,
|
| 318 |
+
"learning_rate": 2.5475089881869547e-06,
|
| 319 |
+
"loss": 0.0469,
|
| 320 |
+
"step": 1700
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 2.6964560862865947,
|
| 324 |
+
"grad_norm": 0.8902830481529236,
|
| 325 |
+
"learning_rate": 2.033898305084746e-06,
|
| 326 |
+
"loss": 0.0601,
|
| 327 |
+
"step": 1750
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 2.773497688751926,
|
| 331 |
+
"grad_norm": 3.1224634647369385,
|
| 332 |
+
"learning_rate": 1.5202876219825374e-06,
|
| 333 |
+
"loss": 0.0412,
|
| 334 |
+
"step": 1800
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 2.773497688751926,
|
| 338 |
+
"eval_accuracy": 0.9560354801388353,
|
| 339 |
+
"eval_loss": 0.17419876158237457,
|
| 340 |
+
"eval_runtime": 24.7703,
|
| 341 |
+
"eval_samples_per_second": 104.682,
|
| 342 |
+
"eval_steps_per_second": 1.655,
|
| 343 |
+
"step": 1800
|
| 344 |
+
},
|
| 345 |
+
{
|
| 346 |
+
"epoch": 2.8505392912172574,
|
| 347 |
+
"grad_norm": 1.5328270196914673,
|
| 348 |
+
"learning_rate": 1.0066769388803288e-06,
|
| 349 |
+
"loss": 0.0394,
|
| 350 |
+
"step": 1850
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 2.9275808936825887,
|
| 354 |
+
"grad_norm": 0.493228018283844,
|
| 355 |
+
"learning_rate": 4.930662557781202e-07,
|
| 356 |
+
"loss": 0.0542,
|
| 357 |
+
"step": 1900
|
| 358 |
+
}
|
| 359 |
+
],
|
| 360 |
+
"logging_steps": 50,
|
| 361 |
+
"max_steps": 1947,
|
| 362 |
+
"num_input_tokens_seen": 0,
|
| 363 |
+
"num_train_epochs": 3,
|
| 364 |
+
"save_steps": 200,
|
| 365 |
+
"stateful_callbacks": {
|
| 366 |
+
"TrainerControl": {
|
| 367 |
+
"args": {
|
| 368 |
+
"should_epoch_stop": false,
|
| 369 |
+
"should_evaluate": false,
|
| 370 |
+
"should_log": false,
|
| 371 |
+
"should_save": true,
|
| 372 |
+
"should_training_stop": true
|
| 373 |
+
},
|
| 374 |
+
"attributes": {}
|
| 375 |
+
}
|
| 376 |
+
},
|
| 377 |
+
"total_flos": 8243711153160192.0,
|
| 378 |
+
"train_batch_size": 32,
|
| 379 |
+
"trial_name": null,
|
| 380 |
+
"trial_params": null
|
| 381 |
+
}
|
checkpoint-1947/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:590efece3220d2015b3187be0322ce739d60183b6edb84c6c589d3e1da99e031
|
| 3 |
+
size 5240
|
checkpoint-1947/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
config.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation": "gelu",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"DistilBertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.1,
|
| 7 |
+
"dim": 768,
|
| 8 |
+
"dropout": 0.1,
|
| 9 |
+
"hidden_dim": 3072,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"max_position_embeddings": 512,
|
| 12 |
+
"model_type": "distilbert",
|
| 13 |
+
"n_heads": 12,
|
| 14 |
+
"n_layers": 6,
|
| 15 |
+
"pad_token_id": 0,
|
| 16 |
+
"problem_type": "single_label_classification",
|
| 17 |
+
"qa_dropout": 0.1,
|
| 18 |
+
"seq_classif_dropout": 0.2,
|
| 19 |
+
"sinusoidal_pos_embds": false,
|
| 20 |
+
"tie_weights_": true,
|
| 21 |
+
"torch_dtype": "float32",
|
| 22 |
+
"transformers_version": "4.51.1",
|
| 23 |
+
"vocab_size": 30522
|
| 24 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fb43262efa605f47af9fbdd580a40049def5dec51e68ebfd80791cc3ca245901
|
| 3 |
+
size 267832560
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[PAD]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"100": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"101": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"102": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"103": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"clean_up_tokenization_spaces": false,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_lower_case": true,
|
| 47 |
+
"extra_special_tokens": {},
|
| 48 |
+
"mask_token": "[MASK]",
|
| 49 |
+
"model_max_length": 512,
|
| 50 |
+
"pad_token": "[PAD]",
|
| 51 |
+
"sep_token": "[SEP]",
|
| 52 |
+
"strip_accents": null,
|
| 53 |
+
"tokenize_chinese_chars": true,
|
| 54 |
+
"tokenizer_class": "DistilBertTokenizer",
|
| 55 |
+
"unk_token": "[UNK]"
|
| 56 |
+
}
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|