Upload folder using huggingface_hub
Browse files- checkpoint-1875/config.json +26 -0
- checkpoint-1875/model.safetensors +3 -0
- checkpoint-1875/optimizer.pt +3 -0
- checkpoint-1875/rng_state.pth +3 -0
- checkpoint-1875/scheduler.pt +3 -0
- checkpoint-1875/special_tokens_map.json +7 -0
- checkpoint-1875/tokenizer.json +0 -0
- checkpoint-1875/tokenizer_config.json +56 -0
- checkpoint-1875/trainer_state.json +322 -0
- checkpoint-1875/training_args.bin +3 -0
- checkpoint-1875/vocab.txt +0 -0
- config.json +26 -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-1875/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-1875/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d6fea760f8875922c3eca7badda83888a53140efdc7ee4489f34783bdf4b2af1
|
| 3 |
+
size 541317368
|
checkpoint-1875/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dd9164cdd8730f052c1f9afe82ce96d5fdde2585a51c97f665168077750333d6
|
| 3 |
+
size 1082696890
|
checkpoint-1875/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3b56f2db6ff9568123aac307e3342fb6125740e3281f1020534db5b68c80e86a
|
| 3 |
+
size 14244
|
checkpoint-1875/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b33b8e08809e71907726d3fa223f40927d644edbee82458d39aa52feebc75248
|
| 3 |
+
size 1064
|
checkpoint-1875/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-1875/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-1875/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-1875/trainer_state.json
ADDED
|
@@ -0,0 +1,322 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1875,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.08,
|
| 13 |
+
"grad_norm": 1.9789578914642334,
|
| 14 |
+
"learning_rate": 4.866666666666667e-05,
|
| 15 |
+
"loss": 0.5912,
|
| 16 |
+
"step": 50
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.16,
|
| 20 |
+
"grad_norm": 3.7243642807006836,
|
| 21 |
+
"learning_rate": 4.7333333333333336e-05,
|
| 22 |
+
"loss": 0.5039,
|
| 23 |
+
"step": 100
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.24,
|
| 27 |
+
"grad_norm": 3.1943674087524414,
|
| 28 |
+
"learning_rate": 4.600000000000001e-05,
|
| 29 |
+
"loss": 0.4657,
|
| 30 |
+
"step": 150
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.32,
|
| 34 |
+
"grad_norm": 2.474888324737549,
|
| 35 |
+
"learning_rate": 4.466666666666667e-05,
|
| 36 |
+
"loss": 0.427,
|
| 37 |
+
"step": 200
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.4,
|
| 41 |
+
"grad_norm": 1.7402023077011108,
|
| 42 |
+
"learning_rate": 4.3333333333333334e-05,
|
| 43 |
+
"loss": 0.405,
|
| 44 |
+
"step": 250
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.48,
|
| 48 |
+
"grad_norm": 3.6526741981506348,
|
| 49 |
+
"learning_rate": 4.2e-05,
|
| 50 |
+
"loss": 0.3935,
|
| 51 |
+
"step": 300
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.56,
|
| 55 |
+
"grad_norm": 4.588198661804199,
|
| 56 |
+
"learning_rate": 4.066666666666667e-05,
|
| 57 |
+
"loss": 0.3913,
|
| 58 |
+
"step": 350
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.64,
|
| 62 |
+
"grad_norm": 1.92843496799469,
|
| 63 |
+
"learning_rate": 3.933333333333333e-05,
|
| 64 |
+
"loss": 0.3842,
|
| 65 |
+
"step": 400
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.72,
|
| 69 |
+
"grad_norm": 2.492220401763916,
|
| 70 |
+
"learning_rate": 3.8e-05,
|
| 71 |
+
"loss": 0.3882,
|
| 72 |
+
"step": 450
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.8,
|
| 76 |
+
"grad_norm": 3.1379597187042236,
|
| 77 |
+
"learning_rate": 3.6666666666666666e-05,
|
| 78 |
+
"loss": 0.389,
|
| 79 |
+
"step": 500
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.88,
|
| 83 |
+
"grad_norm": 5.709914207458496,
|
| 84 |
+
"learning_rate": 3.5333333333333336e-05,
|
| 85 |
+
"loss": 0.3932,
|
| 86 |
+
"step": 550
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.96,
|
| 90 |
+
"grad_norm": 2.0878422260284424,
|
| 91 |
+
"learning_rate": 3.4000000000000007e-05,
|
| 92 |
+
"loss": 0.3686,
|
| 93 |
+
"step": 600
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 1.0,
|
| 97 |
+
"eval_accuracy": 0.8497,
|
| 98 |
+
"eval_f1": 0.8489599035272837,
|
| 99 |
+
"eval_loss": 0.33891910314559937,
|
| 100 |
+
"eval_runtime": 71.0766,
|
| 101 |
+
"eval_samples_per_second": 140.693,
|
| 102 |
+
"eval_steps_per_second": 2.209,
|
| 103 |
+
"step": 625
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"epoch": 1.04,
|
| 107 |
+
"grad_norm": 2.726353406906128,
|
| 108 |
+
"learning_rate": 3.266666666666667e-05,
|
| 109 |
+
"loss": 0.3155,
|
| 110 |
+
"step": 650
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 1.12,
|
| 114 |
+
"grad_norm": 2.56447172164917,
|
| 115 |
+
"learning_rate": 3.1333333333333334e-05,
|
| 116 |
+
"loss": 0.2846,
|
| 117 |
+
"step": 700
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 1.2,
|
| 121 |
+
"grad_norm": 3.0739433765411377,
|
| 122 |
+
"learning_rate": 3e-05,
|
| 123 |
+
"loss": 0.2666,
|
| 124 |
+
"step": 750
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 1.28,
|
| 128 |
+
"grad_norm": 3.5835840702056885,
|
| 129 |
+
"learning_rate": 2.8666666666666668e-05,
|
| 130 |
+
"loss": 0.2695,
|
| 131 |
+
"step": 800
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 1.3599999999999999,
|
| 135 |
+
"grad_norm": 4.5375142097473145,
|
| 136 |
+
"learning_rate": 2.733333333333333e-05,
|
| 137 |
+
"loss": 0.2511,
|
| 138 |
+
"step": 850
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 1.44,
|
| 142 |
+
"grad_norm": 3.7059097290039062,
|
| 143 |
+
"learning_rate": 2.6000000000000002e-05,
|
| 144 |
+
"loss": 0.2569,
|
| 145 |
+
"step": 900
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 1.52,
|
| 149 |
+
"grad_norm": 5.3880228996276855,
|
| 150 |
+
"learning_rate": 2.466666666666667e-05,
|
| 151 |
+
"loss": 0.2509,
|
| 152 |
+
"step": 950
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 1.6,
|
| 156 |
+
"grad_norm": 3.807117462158203,
|
| 157 |
+
"learning_rate": 2.3333333333333336e-05,
|
| 158 |
+
"loss": 0.2448,
|
| 159 |
+
"step": 1000
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 1.6800000000000002,
|
| 163 |
+
"grad_norm": 3.342334747314453,
|
| 164 |
+
"learning_rate": 2.2000000000000003e-05,
|
| 165 |
+
"loss": 0.2598,
|
| 166 |
+
"step": 1050
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 1.76,
|
| 170 |
+
"grad_norm": 3.763474464416504,
|
| 171 |
+
"learning_rate": 2.0666666666666666e-05,
|
| 172 |
+
"loss": 0.229,
|
| 173 |
+
"step": 1100
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 1.8399999999999999,
|
| 177 |
+
"grad_norm": 3.3964762687683105,
|
| 178 |
+
"learning_rate": 1.9333333333333333e-05,
|
| 179 |
+
"loss": 0.2441,
|
| 180 |
+
"step": 1150
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 1.92,
|
| 184 |
+
"grad_norm": 2.2125933170318604,
|
| 185 |
+
"learning_rate": 1.8e-05,
|
| 186 |
+
"loss": 0.2395,
|
| 187 |
+
"step": 1200
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 2.0,
|
| 191 |
+
"grad_norm": 3.5789754390716553,
|
| 192 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 193 |
+
"loss": 0.2272,
|
| 194 |
+
"step": 1250
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 2.0,
|
| 198 |
+
"eval_accuracy": 0.8688,
|
| 199 |
+
"eval_f1": 0.8694007565200079,
|
| 200 |
+
"eval_loss": 0.308406800031662,
|
| 201 |
+
"eval_runtime": 70.3069,
|
| 202 |
+
"eval_samples_per_second": 142.234,
|
| 203 |
+
"eval_steps_per_second": 2.233,
|
| 204 |
+
"step": 1250
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 2.08,
|
| 208 |
+
"grad_norm": 5.787478923797607,
|
| 209 |
+
"learning_rate": 1.5333333333333334e-05,
|
| 210 |
+
"loss": 0.1498,
|
| 211 |
+
"step": 1300
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 2.16,
|
| 215 |
+
"grad_norm": 3.0282957553863525,
|
| 216 |
+
"learning_rate": 1.4000000000000001e-05,
|
| 217 |
+
"loss": 0.1466,
|
| 218 |
+
"step": 1350
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 2.24,
|
| 222 |
+
"grad_norm": 3.736396551132202,
|
| 223 |
+
"learning_rate": 1.2666666666666668e-05,
|
| 224 |
+
"loss": 0.1514,
|
| 225 |
+
"step": 1400
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 2.32,
|
| 229 |
+
"grad_norm": 3.3952717781066895,
|
| 230 |
+
"learning_rate": 1.1333333333333334e-05,
|
| 231 |
+
"loss": 0.1424,
|
| 232 |
+
"step": 1450
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 2.4,
|
| 236 |
+
"grad_norm": 5.165234088897705,
|
| 237 |
+
"learning_rate": 1e-05,
|
| 238 |
+
"loss": 0.1335,
|
| 239 |
+
"step": 1500
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 2.48,
|
| 243 |
+
"grad_norm": 4.4568328857421875,
|
| 244 |
+
"learning_rate": 8.666666666666668e-06,
|
| 245 |
+
"loss": 0.1411,
|
| 246 |
+
"step": 1550
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 2.56,
|
| 250 |
+
"grad_norm": 3.4608709812164307,
|
| 251 |
+
"learning_rate": 7.333333333333334e-06,
|
| 252 |
+
"loss": 0.1412,
|
| 253 |
+
"step": 1600
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 2.64,
|
| 257 |
+
"grad_norm": 3.449420690536499,
|
| 258 |
+
"learning_rate": 6e-06,
|
| 259 |
+
"loss": 0.1439,
|
| 260 |
+
"step": 1650
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 2.7199999999999998,
|
| 264 |
+
"grad_norm": 6.220186233520508,
|
| 265 |
+
"learning_rate": 4.666666666666667e-06,
|
| 266 |
+
"loss": 0.1485,
|
| 267 |
+
"step": 1700
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 2.8,
|
| 271 |
+
"grad_norm": 4.675362586975098,
|
| 272 |
+
"learning_rate": 3.3333333333333333e-06,
|
| 273 |
+
"loss": 0.1481,
|
| 274 |
+
"step": 1750
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 2.88,
|
| 278 |
+
"grad_norm": 4.322061538696289,
|
| 279 |
+
"learning_rate": 2.0000000000000003e-06,
|
| 280 |
+
"loss": 0.1438,
|
| 281 |
+
"step": 1800
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 2.96,
|
| 285 |
+
"grad_norm": 6.561125755310059,
|
| 286 |
+
"learning_rate": 6.666666666666667e-07,
|
| 287 |
+
"loss": 0.142,
|
| 288 |
+
"step": 1850
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 3.0,
|
| 292 |
+
"eval_accuracy": 0.8715,
|
| 293 |
+
"eval_f1": 0.8737597013459082,
|
| 294 |
+
"eval_loss": 0.3732281029224396,
|
| 295 |
+
"eval_runtime": 70.8618,
|
| 296 |
+
"eval_samples_per_second": 141.12,
|
| 297 |
+
"eval_steps_per_second": 2.216,
|
| 298 |
+
"step": 1875
|
| 299 |
+
}
|
| 300 |
+
],
|
| 301 |
+
"logging_steps": 50,
|
| 302 |
+
"max_steps": 1875,
|
| 303 |
+
"num_input_tokens_seen": 0,
|
| 304 |
+
"num_train_epochs": 3,
|
| 305 |
+
"save_steps": 500,
|
| 306 |
+
"stateful_callbacks": {
|
| 307 |
+
"TrainerControl": {
|
| 308 |
+
"args": {
|
| 309 |
+
"should_epoch_stop": false,
|
| 310 |
+
"should_evaluate": false,
|
| 311 |
+
"should_log": false,
|
| 312 |
+
"should_save": true,
|
| 313 |
+
"should_training_stop": true
|
| 314 |
+
},
|
| 315 |
+
"attributes": {}
|
| 316 |
+
}
|
| 317 |
+
},
|
| 318 |
+
"total_flos": 1.589608783872e+16,
|
| 319 |
+
"train_batch_size": 64,
|
| 320 |
+
"trial_name": null,
|
| 321 |
+
"trial_params": null
|
| 322 |
+
}
|
checkpoint-1875/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c9636aa93b4557840fe95de4e6622813789b40fcc1bec040b0b76bc36285b0fb
|
| 3 |
+
size 5304
|
checkpoint-1875/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
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 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d6fea760f8875922c3eca7badda83888a53140efdc7ee4489f34783bdf4b2af1
|
| 3 |
+
size 541317368
|
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": 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 |
+
}
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|