Upload folder using huggingface_hub
Browse files- checkpoint-2661/config.json +26 -0
- checkpoint-2661/model.safetensors +3 -0
- checkpoint-2661/optimizer.pt +3 -0
- checkpoint-2661/rng_state.pth +3 -0
- checkpoint-2661/scheduler.pt +3 -0
- checkpoint-2661/special_tokens_map.json +7 -0
- checkpoint-2661/tokenizer.json +0 -0
- checkpoint-2661/tokenizer_config.json +56 -0
- checkpoint-2661/trainer_state.json +434 -0
- checkpoint-2661/training_args.bin +3 -0
- checkpoint-2661/vocab.txt +0 -0
- model.safetensors +1 -1
checkpoint-2661/config.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "distilbert/distilbert-base-multilingual-cased",
|
| 3 |
+
"activation": "gelu",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"DistilBertForSequenceClassification"
|
| 6 |
+
],
|
| 7 |
+
"attention_dropout": 0.1,
|
| 8 |
+
"dim": 768,
|
| 9 |
+
"dropout": 0.1,
|
| 10 |
+
"hidden_dim": 3072,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"max_position_embeddings": 512,
|
| 13 |
+
"model_type": "distilbert",
|
| 14 |
+
"n_heads": 12,
|
| 15 |
+
"n_layers": 6,
|
| 16 |
+
"output_past": true,
|
| 17 |
+
"pad_token_id": 0,
|
| 18 |
+
"problem_type": "single_label_classification",
|
| 19 |
+
"qa_dropout": 0.1,
|
| 20 |
+
"seq_classif_dropout": 0.2,
|
| 21 |
+
"sinusoidal_pos_embds": false,
|
| 22 |
+
"tie_weights_": true,
|
| 23 |
+
"torch_dtype": "float32",
|
| 24 |
+
"transformers_version": "4.48.3",
|
| 25 |
+
"vocab_size": 119547
|
| 26 |
+
}
|
checkpoint-2661/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:591c68f23e62a2e2c2186c8f31dda5212136e630664963b224e4719c47dcd4ea
|
| 3 |
+
size 541317368
|
checkpoint-2661/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6bbf46c170717591038485a90221f42c04da067bcad1172f0dfe5e9cf4786086
|
| 3 |
+
size 1082696890
|
checkpoint-2661/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:51d81d9f2c53331206efe2ce78301f609f46b42e7344d02dafa3749e588b726c
|
| 3 |
+
size 14244
|
checkpoint-2661/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:32b93fb50a5142fbdd43ea128ac5e1d93e0dbdc81a227fedc2724f289978cae5
|
| 3 |
+
size 1064
|
checkpoint-2661/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-2661/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-2661/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": false,
|
| 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-2661/trainer_state.json
ADDED
|
@@ -0,0 +1,434 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 2661,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.05636978579481398,
|
| 13 |
+
"grad_norm": 1.0439274311065674,
|
| 14 |
+
"learning_rate": 4.9060503570086435e-05,
|
| 15 |
+
"loss": 0.6368,
|
| 16 |
+
"step": 50
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.11273957158962795,
|
| 20 |
+
"grad_norm": 2.2991294860839844,
|
| 21 |
+
"learning_rate": 4.812100714017287e-05,
|
| 22 |
+
"loss": 0.5758,
|
| 23 |
+
"step": 100
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.16910935738444194,
|
| 27 |
+
"grad_norm": 1.6218173503875732,
|
| 28 |
+
"learning_rate": 4.71815107102593e-05,
|
| 29 |
+
"loss": 0.5639,
|
| 30 |
+
"step": 150
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.2254791431792559,
|
| 34 |
+
"grad_norm": 2.0030906200408936,
|
| 35 |
+
"learning_rate": 4.6242014280345734e-05,
|
| 36 |
+
"loss": 0.5421,
|
| 37 |
+
"step": 200
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.2818489289740699,
|
| 41 |
+
"grad_norm": 2.060424566268921,
|
| 42 |
+
"learning_rate": 4.530251785043217e-05,
|
| 43 |
+
"loss": 0.5377,
|
| 44 |
+
"step": 250
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.3382187147688839,
|
| 48 |
+
"grad_norm": 1.5049147605895996,
|
| 49 |
+
"learning_rate": 4.43630214205186e-05,
|
| 50 |
+
"loss": 0.5457,
|
| 51 |
+
"step": 300
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.3945885005636979,
|
| 55 |
+
"grad_norm": 2.017237663269043,
|
| 56 |
+
"learning_rate": 4.342352499060503e-05,
|
| 57 |
+
"loss": 0.5329,
|
| 58 |
+
"step": 350
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.4509582863585118,
|
| 62 |
+
"grad_norm": 1.5960201025009155,
|
| 63 |
+
"learning_rate": 4.2484028560691466e-05,
|
| 64 |
+
"loss": 0.538,
|
| 65 |
+
"step": 400
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.5073280721533259,
|
| 69 |
+
"grad_norm": 1.7139301300048828,
|
| 70 |
+
"learning_rate": 4.1544532130777905e-05,
|
| 71 |
+
"loss": 0.5141,
|
| 72 |
+
"step": 450
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.5636978579481398,
|
| 76 |
+
"grad_norm": 1.4965617656707764,
|
| 77 |
+
"learning_rate": 4.060503570086434e-05,
|
| 78 |
+
"loss": 0.5196,
|
| 79 |
+
"step": 500
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.6200676437429538,
|
| 83 |
+
"grad_norm": 1.2821619510650635,
|
| 84 |
+
"learning_rate": 3.966553927095078e-05,
|
| 85 |
+
"loss": 0.5114,
|
| 86 |
+
"step": 550
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.6764374295377678,
|
| 90 |
+
"grad_norm": 1.5799860954284668,
|
| 91 |
+
"learning_rate": 3.872604284103721e-05,
|
| 92 |
+
"loss": 0.52,
|
| 93 |
+
"step": 600
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.7328072153325818,
|
| 97 |
+
"grad_norm": 1.6334625482559204,
|
| 98 |
+
"learning_rate": 3.7786546411123644e-05,
|
| 99 |
+
"loss": 0.5093,
|
| 100 |
+
"step": 650
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.7891770011273957,
|
| 104 |
+
"grad_norm": 2.19488525390625,
|
| 105 |
+
"learning_rate": 3.6847049981210077e-05,
|
| 106 |
+
"loss": 0.503,
|
| 107 |
+
"step": 700
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.8455467869222097,
|
| 111 |
+
"grad_norm": 1.5821040868759155,
|
| 112 |
+
"learning_rate": 3.590755355129651e-05,
|
| 113 |
+
"loss": 0.4988,
|
| 114 |
+
"step": 750
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.9019165727170236,
|
| 118 |
+
"grad_norm": 2.2586898803710938,
|
| 119 |
+
"learning_rate": 3.496805712138294e-05,
|
| 120 |
+
"loss": 0.5102,
|
| 121 |
+
"step": 800
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.9582863585118376,
|
| 125 |
+
"grad_norm": 1.5365625619888306,
|
| 126 |
+
"learning_rate": 3.4028560691469375e-05,
|
| 127 |
+
"loss": 0.5047,
|
| 128 |
+
"step": 850
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 1.0,
|
| 132 |
+
"eval_accuracy": 0.744162007235822,
|
| 133 |
+
"eval_f1": 0.7656552614590059,
|
| 134 |
+
"eval_loss": 0.4819556772708893,
|
| 135 |
+
"eval_runtime": 56.9558,
|
| 136 |
+
"eval_samples_per_second": 373.676,
|
| 137 |
+
"eval_steps_per_second": 3.898,
|
| 138 |
+
"step": 887
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 1.0146561443066517,
|
| 142 |
+
"grad_norm": 1.1745824813842773,
|
| 143 |
+
"learning_rate": 3.308906426155581e-05,
|
| 144 |
+
"loss": 0.4858,
|
| 145 |
+
"step": 900
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 1.0710259301014655,
|
| 149 |
+
"grad_norm": 3.0086119174957275,
|
| 150 |
+
"learning_rate": 3.214956783164224e-05,
|
| 151 |
+
"loss": 0.4368,
|
| 152 |
+
"step": 950
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 1.1273957158962795,
|
| 156 |
+
"grad_norm": 2.154918909072876,
|
| 157 |
+
"learning_rate": 3.1210071401728674e-05,
|
| 158 |
+
"loss": 0.4373,
|
| 159 |
+
"step": 1000
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 1.1837655016910935,
|
| 163 |
+
"grad_norm": 2.587249994277954,
|
| 164 |
+
"learning_rate": 3.0270574971815107e-05,
|
| 165 |
+
"loss": 0.4275,
|
| 166 |
+
"step": 1050
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 1.2401352874859075,
|
| 170 |
+
"grad_norm": 2.3393185138702393,
|
| 171 |
+
"learning_rate": 2.933107854190154e-05,
|
| 172 |
+
"loss": 0.4351,
|
| 173 |
+
"step": 1100
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 1.2965050732807215,
|
| 177 |
+
"grad_norm": 1.727163553237915,
|
| 178 |
+
"learning_rate": 2.8391582111987973e-05,
|
| 179 |
+
"loss": 0.4457,
|
| 180 |
+
"step": 1150
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 1.3528748590755355,
|
| 184 |
+
"grad_norm": 2.3959648609161377,
|
| 185 |
+
"learning_rate": 2.745208568207441e-05,
|
| 186 |
+
"loss": 0.4291,
|
| 187 |
+
"step": 1200
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 1.4092446448703495,
|
| 191 |
+
"grad_norm": 2.1558401584625244,
|
| 192 |
+
"learning_rate": 2.6512589252160842e-05,
|
| 193 |
+
"loss": 0.4375,
|
| 194 |
+
"step": 1250
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 1.4656144306651635,
|
| 198 |
+
"grad_norm": 2.3182780742645264,
|
| 199 |
+
"learning_rate": 2.5573092822247275e-05,
|
| 200 |
+
"loss": 0.4297,
|
| 201 |
+
"step": 1300
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 1.5219842164599775,
|
| 205 |
+
"grad_norm": 2.0232203006744385,
|
| 206 |
+
"learning_rate": 2.463359639233371e-05,
|
| 207 |
+
"loss": 0.4383,
|
| 208 |
+
"step": 1350
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 1.5783540022547915,
|
| 212 |
+
"grad_norm": 1.779449224472046,
|
| 213 |
+
"learning_rate": 2.3694099962420144e-05,
|
| 214 |
+
"loss": 0.4454,
|
| 215 |
+
"step": 1400
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 1.6347237880496053,
|
| 219 |
+
"grad_norm": 2.562135696411133,
|
| 220 |
+
"learning_rate": 2.2754603532506577e-05,
|
| 221 |
+
"loss": 0.4251,
|
| 222 |
+
"step": 1450
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 1.6910935738444195,
|
| 226 |
+
"grad_norm": 2.216463327407837,
|
| 227 |
+
"learning_rate": 2.181510710259301e-05,
|
| 228 |
+
"loss": 0.4212,
|
| 229 |
+
"step": 1500
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 1.7474633596392333,
|
| 233 |
+
"grad_norm": 1.364642858505249,
|
| 234 |
+
"learning_rate": 2.0875610672679443e-05,
|
| 235 |
+
"loss": 0.4242,
|
| 236 |
+
"step": 1550
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 1.8038331454340475,
|
| 240 |
+
"grad_norm": 1.5100990533828735,
|
| 241 |
+
"learning_rate": 1.993611424276588e-05,
|
| 242 |
+
"loss": 0.4264,
|
| 243 |
+
"step": 1600
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 1.8602029312288613,
|
| 247 |
+
"grad_norm": 2.195282220840454,
|
| 248 |
+
"learning_rate": 1.8996617812852312e-05,
|
| 249 |
+
"loss": 0.4317,
|
| 250 |
+
"step": 1650
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 1.9165727170236753,
|
| 254 |
+
"grad_norm": 2.2001285552978516,
|
| 255 |
+
"learning_rate": 1.8057121382938748e-05,
|
| 256 |
+
"loss": 0.4392,
|
| 257 |
+
"step": 1700
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 1.9729425028184893,
|
| 261 |
+
"grad_norm": 2.5997512340545654,
|
| 262 |
+
"learning_rate": 1.711762495302518e-05,
|
| 263 |
+
"loss": 0.4199,
|
| 264 |
+
"step": 1750
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 2.0,
|
| 268 |
+
"eval_accuracy": 0.7526194615420758,
|
| 269 |
+
"eval_f1": 0.768051456011278,
|
| 270 |
+
"eval_loss": 0.4766261875629425,
|
| 271 |
+
"eval_runtime": 56.2574,
|
| 272 |
+
"eval_samples_per_second": 378.314,
|
| 273 |
+
"eval_steps_per_second": 3.946,
|
| 274 |
+
"step": 1774
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 2.0293122886133035,
|
| 278 |
+
"grad_norm": 2.3610382080078125,
|
| 279 |
+
"learning_rate": 1.6178128523111614e-05,
|
| 280 |
+
"loss": 0.3941,
|
| 281 |
+
"step": 1800
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 2.0856820744081173,
|
| 285 |
+
"grad_norm": 3.2270758152008057,
|
| 286 |
+
"learning_rate": 1.5238632093198047e-05,
|
| 287 |
+
"loss": 0.3712,
|
| 288 |
+
"step": 1850
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 2.142051860202931,
|
| 292 |
+
"grad_norm": 2.4744791984558105,
|
| 293 |
+
"learning_rate": 1.429913566328448e-05,
|
| 294 |
+
"loss": 0.3755,
|
| 295 |
+
"step": 1900
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 2.1984216459977453,
|
| 299 |
+
"grad_norm": 3.3841307163238525,
|
| 300 |
+
"learning_rate": 1.3359639233370913e-05,
|
| 301 |
+
"loss": 0.3645,
|
| 302 |
+
"step": 1950
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 2.254791431792559,
|
| 306 |
+
"grad_norm": 2.185528516769409,
|
| 307 |
+
"learning_rate": 1.2420142803457347e-05,
|
| 308 |
+
"loss": 0.3716,
|
| 309 |
+
"step": 2000
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 2.3111612175873733,
|
| 313 |
+
"grad_norm": 2.18782639503479,
|
| 314 |
+
"learning_rate": 1.1480646373543782e-05,
|
| 315 |
+
"loss": 0.378,
|
| 316 |
+
"step": 2050
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 2.367531003382187,
|
| 320 |
+
"grad_norm": 2.1629090309143066,
|
| 321 |
+
"learning_rate": 1.0541149943630215e-05,
|
| 322 |
+
"loss": 0.3569,
|
| 323 |
+
"step": 2100
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 2.4239007891770012,
|
| 327 |
+
"grad_norm": 3.4792726039886475,
|
| 328 |
+
"learning_rate": 9.601653513716648e-06,
|
| 329 |
+
"loss": 0.3624,
|
| 330 |
+
"step": 2150
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 2.480270574971815,
|
| 334 |
+
"grad_norm": 2.1638121604919434,
|
| 335 |
+
"learning_rate": 8.662157083803082e-06,
|
| 336 |
+
"loss": 0.3647,
|
| 337 |
+
"step": 2200
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 2.5366403607666292,
|
| 341 |
+
"grad_norm": 1.679718255996704,
|
| 342 |
+
"learning_rate": 7.722660653889515e-06,
|
| 343 |
+
"loss": 0.3636,
|
| 344 |
+
"step": 2250
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 2.593010146561443,
|
| 348 |
+
"grad_norm": 3.7099499702453613,
|
| 349 |
+
"learning_rate": 6.783164223975949e-06,
|
| 350 |
+
"loss": 0.3619,
|
| 351 |
+
"step": 2300
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 2.649379932356257,
|
| 355 |
+
"grad_norm": 3.1615912914276123,
|
| 356 |
+
"learning_rate": 5.8436677940623835e-06,
|
| 357 |
+
"loss": 0.3667,
|
| 358 |
+
"step": 2350
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 2.705749718151071,
|
| 362 |
+
"grad_norm": 2.1708598136901855,
|
| 363 |
+
"learning_rate": 4.904171364148816e-06,
|
| 364 |
+
"loss": 0.3707,
|
| 365 |
+
"step": 2400
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 2.7621195039458852,
|
| 369 |
+
"grad_norm": 1.8847932815551758,
|
| 370 |
+
"learning_rate": 3.96467493423525e-06,
|
| 371 |
+
"loss": 0.3558,
|
| 372 |
+
"step": 2450
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 2.818489289740699,
|
| 376 |
+
"grad_norm": 2.6283624172210693,
|
| 377 |
+
"learning_rate": 3.025178504321684e-06,
|
| 378 |
+
"loss": 0.3575,
|
| 379 |
+
"step": 2500
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"epoch": 2.874859075535513,
|
| 383 |
+
"grad_norm": 1.7425137758255005,
|
| 384 |
+
"learning_rate": 2.0856820744081176e-06,
|
| 385 |
+
"loss": 0.3685,
|
| 386 |
+
"step": 2550
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 2.931228861330327,
|
| 390 |
+
"grad_norm": 3.9649059772491455,
|
| 391 |
+
"learning_rate": 1.146185644494551e-06,
|
| 392 |
+
"loss": 0.374,
|
| 393 |
+
"step": 2600
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 2.987598647125141,
|
| 397 |
+
"grad_norm": 3.081310749053955,
|
| 398 |
+
"learning_rate": 2.066892145809846e-07,
|
| 399 |
+
"loss": 0.363,
|
| 400 |
+
"step": 2650
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 3.0,
|
| 404 |
+
"eval_accuracy": 0.7502701686792276,
|
| 405 |
+
"eval_f1": 0.7636622348703811,
|
| 406 |
+
"eval_loss": 0.5071986317634583,
|
| 407 |
+
"eval_runtime": 57.0998,
|
| 408 |
+
"eval_samples_per_second": 372.733,
|
| 409 |
+
"eval_steps_per_second": 3.888,
|
| 410 |
+
"step": 2661
|
| 411 |
+
}
|
| 412 |
+
],
|
| 413 |
+
"logging_steps": 50,
|
| 414 |
+
"max_steps": 2661,
|
| 415 |
+
"num_input_tokens_seen": 0,
|
| 416 |
+
"num_train_epochs": 3,
|
| 417 |
+
"save_steps": 500,
|
| 418 |
+
"stateful_callbacks": {
|
| 419 |
+
"TrainerControl": {
|
| 420 |
+
"args": {
|
| 421 |
+
"should_epoch_stop": false,
|
| 422 |
+
"should_evaluate": false,
|
| 423 |
+
"should_log": false,
|
| 424 |
+
"should_save": true,
|
| 425 |
+
"should_training_stop": true
|
| 426 |
+
},
|
| 427 |
+
"attributes": {}
|
| 428 |
+
}
|
| 429 |
+
},
|
| 430 |
+
"total_flos": 3.3829656736167936e+16,
|
| 431 |
+
"train_batch_size": 96,
|
| 432 |
+
"trial_name": null,
|
| 433 |
+
"trial_params": null
|
| 434 |
+
}
|
checkpoint-2661/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b76a7922b684c1c4953ec27b2cd8cab89ecad5c9324f5600caab8aaa80f8c94a
|
| 3 |
+
size 5304
|
checkpoint-2661/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 541317368
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:591c68f23e62a2e2c2186c8f31dda5212136e630664963b224e4719c47dcd4ea
|
| 3 |
size 541317368
|