Upload folder using huggingface_hub
Browse files- checkpoint-4500/model.safetensors +3 -0
- checkpoint-4500/optimizer.pt +3 -0
- checkpoint-4500/rng_state.pth +3 -0
- checkpoint-4500/scheduler.pt +3 -0
- checkpoint-4500/special_tokens_map.json +7 -0
- checkpoint-4500/tokenizer.json +0 -0
- checkpoint-4500/tokenizer_config.json +59 -0
- checkpoint-4500/trainer_state.json +232 -0
- checkpoint-4500/training_args.bin +3 -0
- checkpoint-4500/vocab.txt +0 -0
- checkpoint-8236/model.safetensors +3 -0
- checkpoint-8236/optimizer.pt +3 -0
- checkpoint-8236/rng_state.pth +3 -0
- checkpoint-8236/scheduler.pt +3 -0
- checkpoint-8236/special_tokens_map.json +7 -0
- checkpoint-8236/tokenizer.json +0 -0
- checkpoint-8236/tokenizer_config.json +59 -0
- checkpoint-8236/trainer_state.json +386 -0
- checkpoint-8236/training_args.bin +3 -0
- checkpoint-8236/vocab.txt +0 -0
- model.safetensors +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +59 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
checkpoint-4500/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2ad50af0d0ec81a0eee4dc85c9fa9da78a86ff99bdd689c0ce94b3bf86b5fed9
|
| 3 |
+
size 436414084
|
checkpoint-4500/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c912e248e4f70ddb896cbbb2f315e699919e3ce527bc205aeb63a25d4762d6b7
|
| 3 |
+
size 872948026
|
checkpoint-4500/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:188602f9a1816aa120ac22edd69467727e10ee46c714750b1d1bea01b54a9760
|
| 3 |
+
size 14244
|
checkpoint-4500/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bf66d38ccc4094f2631320aef1cf0c180f6441150b0a9c7a0744b208841cdeaf
|
| 3 |
+
size 1064
|
checkpoint-4500/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-4500/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-4500/tokenizer_config.json
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"1": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"4": {
|
| 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": true,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_basic_tokenize": true,
|
| 47 |
+
"do_lower_case": false,
|
| 48 |
+
"extra_special_tokens": {},
|
| 49 |
+
"full_tokenizer_file": null,
|
| 50 |
+
"mask_token": "[MASK]",
|
| 51 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 52 |
+
"never_split": null,
|
| 53 |
+
"pad_token": "[PAD]",
|
| 54 |
+
"sep_token": "[SEP]",
|
| 55 |
+
"strip_accents": null,
|
| 56 |
+
"tokenize_chinese_chars": true,
|
| 57 |
+
"tokenizer_class": "BertTokenizer",
|
| 58 |
+
"unk_token": "[UNK]"
|
| 59 |
+
}
|
checkpoint-4500/trainer_state.json
ADDED
|
@@ -0,0 +1,232 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 4500,
|
| 3 |
+
"best_metric": 0.8526874352604716,
|
| 4 |
+
"best_model_checkpoint": "./camelbert-ner-author/checkpoint-4500",
|
| 5 |
+
"epoch": 2.1855269548324427,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 4500,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.24283632831471588,
|
| 14 |
+
"grad_norm": 19.655189514160156,
|
| 15 |
+
"learning_rate": 1.8788246721709567e-05,
|
| 16 |
+
"loss": 1.3015,
|
| 17 |
+
"step": 500
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.24283632831471588,
|
| 21 |
+
"eval_accuracy": 0.7120519605484724,
|
| 22 |
+
"eval_f1_macro": 0.6183057931510966,
|
| 23 |
+
"eval_f1_micro": 0.7120519605484724,
|
| 24 |
+
"eval_loss": 0.9594210982322693,
|
| 25 |
+
"eval_precision_macro": 0.6361214235541449,
|
| 26 |
+
"eval_precision_micro": 0.7120519605484724,
|
| 27 |
+
"eval_recall_macro": 0.6773081159897201,
|
| 28 |
+
"eval_recall_micro": 0.7120519605484724,
|
| 29 |
+
"eval_runtime": 78.8319,
|
| 30 |
+
"eval_samples_per_second": 52.732,
|
| 31 |
+
"eval_steps_per_second": 3.298,
|
| 32 |
+
"step": 500
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.48567265662943176,
|
| 36 |
+
"grad_norm": 12.739048957824707,
|
| 37 |
+
"learning_rate": 1.757406508013599e-05,
|
| 38 |
+
"loss": 0.4807,
|
| 39 |
+
"step": 1000
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.48567265662943176,
|
| 43 |
+
"eval_accuracy": 0.7986528746692326,
|
| 44 |
+
"eval_f1_macro": 0.7134381815266957,
|
| 45 |
+
"eval_f1_micro": 0.7986528746692327,
|
| 46 |
+
"eval_loss": 0.685612678527832,
|
| 47 |
+
"eval_precision_macro": 0.7383782436733511,
|
| 48 |
+
"eval_precision_micro": 0.7986528746692326,
|
| 49 |
+
"eval_recall_macro": 0.7399947161579059,
|
| 50 |
+
"eval_recall_micro": 0.7986528746692326,
|
| 51 |
+
"eval_runtime": 78.5622,
|
| 52 |
+
"eval_samples_per_second": 52.913,
|
| 53 |
+
"eval_steps_per_second": 3.309,
|
| 54 |
+
"step": 1000
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 0.7285089849441476,
|
| 58 |
+
"grad_norm": 28.610925674438477,
|
| 59 |
+
"learning_rate": 1.635988343856241e-05,
|
| 60 |
+
"loss": 0.2896,
|
| 61 |
+
"step": 1500
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 0.7285089849441476,
|
| 65 |
+
"eval_accuracy": 0.8135674765455858,
|
| 66 |
+
"eval_f1_macro": 0.7371793410016984,
|
| 67 |
+
"eval_f1_micro": 0.8135674765455858,
|
| 68 |
+
"eval_loss": 0.6776726841926575,
|
| 69 |
+
"eval_precision_macro": 0.7424769213783606,
|
| 70 |
+
"eval_precision_micro": 0.8135674765455858,
|
| 71 |
+
"eval_recall_macro": 0.7767083489723529,
|
| 72 |
+
"eval_recall_micro": 0.8135674765455858,
|
| 73 |
+
"eval_runtime": 79.2486,
|
| 74 |
+
"eval_samples_per_second": 52.455,
|
| 75 |
+
"eval_steps_per_second": 3.281,
|
| 76 |
+
"step": 1500
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 0.9713453132588635,
|
| 80 |
+
"grad_norm": 3.9482295513153076,
|
| 81 |
+
"learning_rate": 1.514570179698883e-05,
|
| 82 |
+
"loss": 0.2291,
|
| 83 |
+
"step": 2000
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 0.9713453132588635,
|
| 87 |
+
"eval_accuracy": 0.8166947317777243,
|
| 88 |
+
"eval_f1_macro": 0.7624936105293934,
|
| 89 |
+
"eval_f1_micro": 0.8166947317777243,
|
| 90 |
+
"eval_loss": 0.6716341972351074,
|
| 91 |
+
"eval_precision_macro": 0.7604827616055949,
|
| 92 |
+
"eval_precision_micro": 0.8166947317777243,
|
| 93 |
+
"eval_recall_macro": 0.8180693724015187,
|
| 94 |
+
"eval_recall_micro": 0.8166947317777243,
|
| 95 |
+
"eval_runtime": 78.8286,
|
| 96 |
+
"eval_samples_per_second": 52.735,
|
| 97 |
+
"eval_steps_per_second": 3.298,
|
| 98 |
+
"step": 2000
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 1.2141816415735793,
|
| 102 |
+
"grad_norm": 0.23831093311309814,
|
| 103 |
+
"learning_rate": 1.393152015541525e-05,
|
| 104 |
+
"loss": 0.1293,
|
| 105 |
+
"step": 2500
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 1.2141816415735793,
|
| 109 |
+
"eval_accuracy": 0.8611979793120038,
|
| 110 |
+
"eval_f1_macro": 0.8086524377893386,
|
| 111 |
+
"eval_f1_micro": 0.8611979793120037,
|
| 112 |
+
"eval_loss": 0.5560595393180847,
|
| 113 |
+
"eval_precision_macro": 0.8065670541564225,
|
| 114 |
+
"eval_precision_micro": 0.8611979793120038,
|
| 115 |
+
"eval_recall_macro": 0.827913254542162,
|
| 116 |
+
"eval_recall_micro": 0.8611979793120038,
|
| 117 |
+
"eval_runtime": 79.2647,
|
| 118 |
+
"eval_samples_per_second": 52.445,
|
| 119 |
+
"eval_steps_per_second": 3.28,
|
| 120 |
+
"step": 2500
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 1.4570179698882952,
|
| 124 |
+
"grad_norm": 14.096162796020508,
|
| 125 |
+
"learning_rate": 1.2717338513841673e-05,
|
| 126 |
+
"loss": 0.0999,
|
| 127 |
+
"step": 3000
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 1.4570179698882952,
|
| 131 |
+
"eval_accuracy": 0.863122444070243,
|
| 132 |
+
"eval_f1_macro": 0.7992144552019207,
|
| 133 |
+
"eval_f1_micro": 0.863122444070243,
|
| 134 |
+
"eval_loss": 0.5559478998184204,
|
| 135 |
+
"eval_precision_macro": 0.8206342176388387,
|
| 136 |
+
"eval_precision_micro": 0.863122444070243,
|
| 137 |
+
"eval_recall_macro": 0.8136954515050157,
|
| 138 |
+
"eval_recall_micro": 0.863122444070243,
|
| 139 |
+
"eval_runtime": 78.8108,
|
| 140 |
+
"eval_samples_per_second": 52.747,
|
| 141 |
+
"eval_steps_per_second": 3.299,
|
| 142 |
+
"step": 3000
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 1.6998542982030111,
|
| 146 |
+
"grad_norm": 17.986045837402344,
|
| 147 |
+
"learning_rate": 1.1503156872268093e-05,
|
| 148 |
+
"loss": 0.0774,
|
| 149 |
+
"step": 3500
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 1.6998542982030111,
|
| 153 |
+
"eval_accuracy": 0.8874188116430118,
|
| 154 |
+
"eval_f1_macro": 0.8277841962841266,
|
| 155 |
+
"eval_f1_micro": 0.8874188116430118,
|
| 156 |
+
"eval_loss": 0.47720664739608765,
|
| 157 |
+
"eval_precision_macro": 0.8360578643228223,
|
| 158 |
+
"eval_precision_micro": 0.8874188116430118,
|
| 159 |
+
"eval_recall_macro": 0.8389572760941908,
|
| 160 |
+
"eval_recall_micro": 0.8874188116430118,
|
| 161 |
+
"eval_runtime": 79.1831,
|
| 162 |
+
"eval_samples_per_second": 52.499,
|
| 163 |
+
"eval_steps_per_second": 3.284,
|
| 164 |
+
"step": 3500
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 1.942690626517727,
|
| 168 |
+
"grad_norm": 0.42851337790489197,
|
| 169 |
+
"learning_rate": 1.0288975230694513e-05,
|
| 170 |
+
"loss": 0.0664,
|
| 171 |
+
"step": 4000
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 1.942690626517727,
|
| 175 |
+
"eval_accuracy": 0.8676930478710608,
|
| 176 |
+
"eval_f1_macro": 0.8128736306359143,
|
| 177 |
+
"eval_f1_micro": 0.8676930478710608,
|
| 178 |
+
"eval_loss": 0.6257432103157043,
|
| 179 |
+
"eval_precision_macro": 0.8270757594085362,
|
| 180 |
+
"eval_precision_micro": 0.8676930478710608,
|
| 181 |
+
"eval_recall_macro": 0.8277626111904449,
|
| 182 |
+
"eval_recall_micro": 0.8676930478710608,
|
| 183 |
+
"eval_runtime": 78.863,
|
| 184 |
+
"eval_samples_per_second": 52.712,
|
| 185 |
+
"eval_steps_per_second": 3.297,
|
| 186 |
+
"step": 4000
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 2.1855269548324427,
|
| 190 |
+
"grad_norm": 0.35300347208976746,
|
| 191 |
+
"learning_rate": 9.074793589120935e-06,
|
| 192 |
+
"loss": 0.0358,
|
| 193 |
+
"step": 4500
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 2.1855269548324427,
|
| 197 |
+
"eval_accuracy": 0.8982439259081068,
|
| 198 |
+
"eval_f1_macro": 0.8526874352604716,
|
| 199 |
+
"eval_f1_micro": 0.8982439259081068,
|
| 200 |
+
"eval_loss": 0.5168837308883667,
|
| 201 |
+
"eval_precision_macro": 0.8595883535398947,
|
| 202 |
+
"eval_precision_micro": 0.8982439259081068,
|
| 203 |
+
"eval_recall_macro": 0.8610977340509225,
|
| 204 |
+
"eval_recall_micro": 0.8982439259081068,
|
| 205 |
+
"eval_runtime": 78.7961,
|
| 206 |
+
"eval_samples_per_second": 52.756,
|
| 207 |
+
"eval_steps_per_second": 3.3,
|
| 208 |
+
"step": 4500
|
| 209 |
+
}
|
| 210 |
+
],
|
| 211 |
+
"logging_steps": 500,
|
| 212 |
+
"max_steps": 8236,
|
| 213 |
+
"num_input_tokens_seen": 0,
|
| 214 |
+
"num_train_epochs": 4,
|
| 215 |
+
"save_steps": 500,
|
| 216 |
+
"stateful_callbacks": {
|
| 217 |
+
"TrainerControl": {
|
| 218 |
+
"args": {
|
| 219 |
+
"should_epoch_stop": false,
|
| 220 |
+
"should_evaluate": false,
|
| 221 |
+
"should_log": false,
|
| 222 |
+
"should_save": true,
|
| 223 |
+
"should_training_stop": false
|
| 224 |
+
},
|
| 225 |
+
"attributes": {}
|
| 226 |
+
}
|
| 227 |
+
},
|
| 228 |
+
"total_flos": 0.0,
|
| 229 |
+
"train_batch_size": 16,
|
| 230 |
+
"trial_name": null,
|
| 231 |
+
"trial_params": null
|
| 232 |
+
}
|
checkpoint-4500/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:136b7b4293e2141f44a8b5057bed262843c60ffd9dbdb070d79796b2a20d5edc
|
| 3 |
+
size 5304
|
checkpoint-4500/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-8236/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0053eba9d6fed54b60ce94e122f93db3a0c5338da1985fa97849adb8f310203c
|
| 3 |
+
size 436414084
|
checkpoint-8236/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:545b4dc909774e97a82208a190b2cf0ce107bb00f71485351e22522dc122b939
|
| 3 |
+
size 872948026
|
checkpoint-8236/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ea2145bb230d225d0b28f40534aeceec3c6394e863d5ded18d632d85e6f76606
|
| 3 |
+
size 14244
|
checkpoint-8236/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c49c4c3f9280587c8ffc7eba095e0030369b0c09f7ff72035d62a66e48c3f2d2
|
| 3 |
+
size 1064
|
checkpoint-8236/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-8236/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-8236/tokenizer_config.json
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"1": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"4": {
|
| 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": true,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_basic_tokenize": true,
|
| 47 |
+
"do_lower_case": false,
|
| 48 |
+
"extra_special_tokens": {},
|
| 49 |
+
"full_tokenizer_file": null,
|
| 50 |
+
"mask_token": "[MASK]",
|
| 51 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 52 |
+
"never_split": null,
|
| 53 |
+
"pad_token": "[PAD]",
|
| 54 |
+
"sep_token": "[SEP]",
|
| 55 |
+
"strip_accents": null,
|
| 56 |
+
"tokenize_chinese_chars": true,
|
| 57 |
+
"tokenizer_class": "BertTokenizer",
|
| 58 |
+
"unk_token": "[UNK]"
|
| 59 |
+
}
|
checkpoint-8236/trainer_state.json
ADDED
|
@@ -0,0 +1,386 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 4500,
|
| 3 |
+
"best_metric": 0.8526874352604716,
|
| 4 |
+
"best_model_checkpoint": "./camelbert-ner-author/checkpoint-4500",
|
| 5 |
+
"epoch": 4.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 8236,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.24283632831471588,
|
| 14 |
+
"grad_norm": 19.655189514160156,
|
| 15 |
+
"learning_rate": 1.8788246721709567e-05,
|
| 16 |
+
"loss": 1.3015,
|
| 17 |
+
"step": 500
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.24283632831471588,
|
| 21 |
+
"eval_accuracy": 0.7120519605484724,
|
| 22 |
+
"eval_f1_macro": 0.6183057931510966,
|
| 23 |
+
"eval_f1_micro": 0.7120519605484724,
|
| 24 |
+
"eval_loss": 0.9594210982322693,
|
| 25 |
+
"eval_precision_macro": 0.6361214235541449,
|
| 26 |
+
"eval_precision_micro": 0.7120519605484724,
|
| 27 |
+
"eval_recall_macro": 0.6773081159897201,
|
| 28 |
+
"eval_recall_micro": 0.7120519605484724,
|
| 29 |
+
"eval_runtime": 78.8319,
|
| 30 |
+
"eval_samples_per_second": 52.732,
|
| 31 |
+
"eval_steps_per_second": 3.298,
|
| 32 |
+
"step": 500
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.48567265662943176,
|
| 36 |
+
"grad_norm": 12.739048957824707,
|
| 37 |
+
"learning_rate": 1.757406508013599e-05,
|
| 38 |
+
"loss": 0.4807,
|
| 39 |
+
"step": 1000
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.48567265662943176,
|
| 43 |
+
"eval_accuracy": 0.7986528746692326,
|
| 44 |
+
"eval_f1_macro": 0.7134381815266957,
|
| 45 |
+
"eval_f1_micro": 0.7986528746692327,
|
| 46 |
+
"eval_loss": 0.685612678527832,
|
| 47 |
+
"eval_precision_macro": 0.7383782436733511,
|
| 48 |
+
"eval_precision_micro": 0.7986528746692326,
|
| 49 |
+
"eval_recall_macro": 0.7399947161579059,
|
| 50 |
+
"eval_recall_micro": 0.7986528746692326,
|
| 51 |
+
"eval_runtime": 78.5622,
|
| 52 |
+
"eval_samples_per_second": 52.913,
|
| 53 |
+
"eval_steps_per_second": 3.309,
|
| 54 |
+
"step": 1000
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 0.7285089849441476,
|
| 58 |
+
"grad_norm": 28.610925674438477,
|
| 59 |
+
"learning_rate": 1.635988343856241e-05,
|
| 60 |
+
"loss": 0.2896,
|
| 61 |
+
"step": 1500
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 0.7285089849441476,
|
| 65 |
+
"eval_accuracy": 0.8135674765455858,
|
| 66 |
+
"eval_f1_macro": 0.7371793410016984,
|
| 67 |
+
"eval_f1_micro": 0.8135674765455858,
|
| 68 |
+
"eval_loss": 0.6776726841926575,
|
| 69 |
+
"eval_precision_macro": 0.7424769213783606,
|
| 70 |
+
"eval_precision_micro": 0.8135674765455858,
|
| 71 |
+
"eval_recall_macro": 0.7767083489723529,
|
| 72 |
+
"eval_recall_micro": 0.8135674765455858,
|
| 73 |
+
"eval_runtime": 79.2486,
|
| 74 |
+
"eval_samples_per_second": 52.455,
|
| 75 |
+
"eval_steps_per_second": 3.281,
|
| 76 |
+
"step": 1500
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 0.9713453132588635,
|
| 80 |
+
"grad_norm": 3.9482295513153076,
|
| 81 |
+
"learning_rate": 1.514570179698883e-05,
|
| 82 |
+
"loss": 0.2291,
|
| 83 |
+
"step": 2000
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 0.9713453132588635,
|
| 87 |
+
"eval_accuracy": 0.8166947317777243,
|
| 88 |
+
"eval_f1_macro": 0.7624936105293934,
|
| 89 |
+
"eval_f1_micro": 0.8166947317777243,
|
| 90 |
+
"eval_loss": 0.6716341972351074,
|
| 91 |
+
"eval_precision_macro": 0.7604827616055949,
|
| 92 |
+
"eval_precision_micro": 0.8166947317777243,
|
| 93 |
+
"eval_recall_macro": 0.8180693724015187,
|
| 94 |
+
"eval_recall_micro": 0.8166947317777243,
|
| 95 |
+
"eval_runtime": 78.8286,
|
| 96 |
+
"eval_samples_per_second": 52.735,
|
| 97 |
+
"eval_steps_per_second": 3.298,
|
| 98 |
+
"step": 2000
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 1.2141816415735793,
|
| 102 |
+
"grad_norm": 0.23831093311309814,
|
| 103 |
+
"learning_rate": 1.393152015541525e-05,
|
| 104 |
+
"loss": 0.1293,
|
| 105 |
+
"step": 2500
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 1.2141816415735793,
|
| 109 |
+
"eval_accuracy": 0.8611979793120038,
|
| 110 |
+
"eval_f1_macro": 0.8086524377893386,
|
| 111 |
+
"eval_f1_micro": 0.8611979793120037,
|
| 112 |
+
"eval_loss": 0.5560595393180847,
|
| 113 |
+
"eval_precision_macro": 0.8065670541564225,
|
| 114 |
+
"eval_precision_micro": 0.8611979793120038,
|
| 115 |
+
"eval_recall_macro": 0.827913254542162,
|
| 116 |
+
"eval_recall_micro": 0.8611979793120038,
|
| 117 |
+
"eval_runtime": 79.2647,
|
| 118 |
+
"eval_samples_per_second": 52.445,
|
| 119 |
+
"eval_steps_per_second": 3.28,
|
| 120 |
+
"step": 2500
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 1.4570179698882952,
|
| 124 |
+
"grad_norm": 14.096162796020508,
|
| 125 |
+
"learning_rate": 1.2717338513841673e-05,
|
| 126 |
+
"loss": 0.0999,
|
| 127 |
+
"step": 3000
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 1.4570179698882952,
|
| 131 |
+
"eval_accuracy": 0.863122444070243,
|
| 132 |
+
"eval_f1_macro": 0.7992144552019207,
|
| 133 |
+
"eval_f1_micro": 0.863122444070243,
|
| 134 |
+
"eval_loss": 0.5559478998184204,
|
| 135 |
+
"eval_precision_macro": 0.8206342176388387,
|
| 136 |
+
"eval_precision_micro": 0.863122444070243,
|
| 137 |
+
"eval_recall_macro": 0.8136954515050157,
|
| 138 |
+
"eval_recall_micro": 0.863122444070243,
|
| 139 |
+
"eval_runtime": 78.8108,
|
| 140 |
+
"eval_samples_per_second": 52.747,
|
| 141 |
+
"eval_steps_per_second": 3.299,
|
| 142 |
+
"step": 3000
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 1.6998542982030111,
|
| 146 |
+
"grad_norm": 17.986045837402344,
|
| 147 |
+
"learning_rate": 1.1503156872268093e-05,
|
| 148 |
+
"loss": 0.0774,
|
| 149 |
+
"step": 3500
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 1.6998542982030111,
|
| 153 |
+
"eval_accuracy": 0.8874188116430118,
|
| 154 |
+
"eval_f1_macro": 0.8277841962841266,
|
| 155 |
+
"eval_f1_micro": 0.8874188116430118,
|
| 156 |
+
"eval_loss": 0.47720664739608765,
|
| 157 |
+
"eval_precision_macro": 0.8360578643228223,
|
| 158 |
+
"eval_precision_micro": 0.8874188116430118,
|
| 159 |
+
"eval_recall_macro": 0.8389572760941908,
|
| 160 |
+
"eval_recall_micro": 0.8874188116430118,
|
| 161 |
+
"eval_runtime": 79.1831,
|
| 162 |
+
"eval_samples_per_second": 52.499,
|
| 163 |
+
"eval_steps_per_second": 3.284,
|
| 164 |
+
"step": 3500
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 1.942690626517727,
|
| 168 |
+
"grad_norm": 0.42851337790489197,
|
| 169 |
+
"learning_rate": 1.0288975230694513e-05,
|
| 170 |
+
"loss": 0.0664,
|
| 171 |
+
"step": 4000
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 1.942690626517727,
|
| 175 |
+
"eval_accuracy": 0.8676930478710608,
|
| 176 |
+
"eval_f1_macro": 0.8128736306359143,
|
| 177 |
+
"eval_f1_micro": 0.8676930478710608,
|
| 178 |
+
"eval_loss": 0.6257432103157043,
|
| 179 |
+
"eval_precision_macro": 0.8270757594085362,
|
| 180 |
+
"eval_precision_micro": 0.8676930478710608,
|
| 181 |
+
"eval_recall_macro": 0.8277626111904449,
|
| 182 |
+
"eval_recall_micro": 0.8676930478710608,
|
| 183 |
+
"eval_runtime": 78.863,
|
| 184 |
+
"eval_samples_per_second": 52.712,
|
| 185 |
+
"eval_steps_per_second": 3.297,
|
| 186 |
+
"step": 4000
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 2.1855269548324427,
|
| 190 |
+
"grad_norm": 0.35300347208976746,
|
| 191 |
+
"learning_rate": 9.074793589120935e-06,
|
| 192 |
+
"loss": 0.0358,
|
| 193 |
+
"step": 4500
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 2.1855269548324427,
|
| 197 |
+
"eval_accuracy": 0.8982439259081068,
|
| 198 |
+
"eval_f1_macro": 0.8526874352604716,
|
| 199 |
+
"eval_f1_micro": 0.8982439259081068,
|
| 200 |
+
"eval_loss": 0.5168837308883667,
|
| 201 |
+
"eval_precision_macro": 0.8595883535398947,
|
| 202 |
+
"eval_precision_micro": 0.8982439259081068,
|
| 203 |
+
"eval_recall_macro": 0.8610977340509225,
|
| 204 |
+
"eval_recall_micro": 0.8982439259081068,
|
| 205 |
+
"eval_runtime": 78.7961,
|
| 206 |
+
"eval_samples_per_second": 52.756,
|
| 207 |
+
"eval_steps_per_second": 3.3,
|
| 208 |
+
"step": 4500
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 2.4283632831471587,
|
| 212 |
+
"grad_norm": 0.004080391488969326,
|
| 213 |
+
"learning_rate": 7.860611947547354e-06,
|
| 214 |
+
"loss": 0.0257,
|
| 215 |
+
"step": 5000
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 2.4283632831471587,
|
| 219 |
+
"eval_accuracy": 0.8811643011787347,
|
| 220 |
+
"eval_f1_macro": 0.8297981700465746,
|
| 221 |
+
"eval_f1_micro": 0.8811643011787347,
|
| 222 |
+
"eval_loss": 0.5981627106666565,
|
| 223 |
+
"eval_precision_macro": 0.8386903015490977,
|
| 224 |
+
"eval_precision_micro": 0.8811643011787347,
|
| 225 |
+
"eval_recall_macro": 0.8494999643786711,
|
| 226 |
+
"eval_recall_micro": 0.8811643011787347,
|
| 227 |
+
"eval_runtime": 79.1803,
|
| 228 |
+
"eval_samples_per_second": 52.5,
|
| 229 |
+
"eval_steps_per_second": 3.284,
|
| 230 |
+
"step": 5000
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 2.6711996114618746,
|
| 234 |
+
"grad_norm": 0.025048088282346725,
|
| 235 |
+
"learning_rate": 6.646430305973774e-06,
|
| 236 |
+
"loss": 0.0341,
|
| 237 |
+
"step": 5500
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 2.6711996114618746,
|
| 241 |
+
"eval_accuracy": 0.8842915564108732,
|
| 242 |
+
"eval_f1_macro": 0.8331171832679176,
|
| 243 |
+
"eval_f1_micro": 0.8842915564108732,
|
| 244 |
+
"eval_loss": 0.5772708654403687,
|
| 245 |
+
"eval_precision_macro": 0.8494868074895356,
|
| 246 |
+
"eval_precision_micro": 0.8842915564108732,
|
| 247 |
+
"eval_recall_macro": 0.8483270001882943,
|
| 248 |
+
"eval_recall_micro": 0.8842915564108732,
|
| 249 |
+
"eval_runtime": 78.6231,
|
| 250 |
+
"eval_samples_per_second": 52.873,
|
| 251 |
+
"eval_steps_per_second": 3.307,
|
| 252 |
+
"step": 5500
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 2.9140359397765905,
|
| 256 |
+
"grad_norm": 0.02463502809405327,
|
| 257 |
+
"learning_rate": 5.432248664400195e-06,
|
| 258 |
+
"loss": 0.0189,
|
| 259 |
+
"step": 6000
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 2.9140359397765905,
|
| 263 |
+
"eval_accuracy": 0.89126774115949,
|
| 264 |
+
"eval_f1_macro": 0.8419632069460932,
|
| 265 |
+
"eval_f1_micro": 0.89126774115949,
|
| 266 |
+
"eval_loss": 0.5399471521377563,
|
| 267 |
+
"eval_precision_macro": 0.8471174550638614,
|
| 268 |
+
"eval_precision_micro": 0.89126774115949,
|
| 269 |
+
"eval_recall_macro": 0.851015220437627,
|
| 270 |
+
"eval_recall_micro": 0.89126774115949,
|
| 271 |
+
"eval_runtime": 79.0105,
|
| 272 |
+
"eval_samples_per_second": 52.613,
|
| 273 |
+
"eval_steps_per_second": 3.291,
|
| 274 |
+
"step": 6000
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 3.1568722680913064,
|
| 278 |
+
"grad_norm": 0.0073256283067166805,
|
| 279 |
+
"learning_rate": 4.2180670228266156e-06,
|
| 280 |
+
"loss": 0.0116,
|
| 281 |
+
"step": 6500
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 3.1568722680913064,
|
| 285 |
+
"eval_accuracy": 0.8931922059177291,
|
| 286 |
+
"eval_f1_macro": 0.8414264169454924,
|
| 287 |
+
"eval_f1_micro": 0.8931922059177291,
|
| 288 |
+
"eval_loss": 0.5759193301200867,
|
| 289 |
+
"eval_precision_macro": 0.8427389427262956,
|
| 290 |
+
"eval_precision_micro": 0.8931922059177291,
|
| 291 |
+
"eval_recall_macro": 0.8551472022218021,
|
| 292 |
+
"eval_recall_micro": 0.8931922059177291,
|
| 293 |
+
"eval_runtime": 78.8344,
|
| 294 |
+
"eval_samples_per_second": 52.731,
|
| 295 |
+
"eval_steps_per_second": 3.298,
|
| 296 |
+
"step": 6500
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 3.3997085964060223,
|
| 300 |
+
"grad_norm": 0.0036666509695351124,
|
| 301 |
+
"learning_rate": 3.0038853812530354e-06,
|
| 302 |
+
"loss": 0.0059,
|
| 303 |
+
"step": 7000
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 3.3997085964060223,
|
| 307 |
+
"eval_accuracy": 0.8727447678614385,
|
| 308 |
+
"eval_f1_macro": 0.8203565475839012,
|
| 309 |
+
"eval_f1_micro": 0.8727447678614385,
|
| 310 |
+
"eval_loss": 0.672887921333313,
|
| 311 |
+
"eval_precision_macro": 0.8299847158193392,
|
| 312 |
+
"eval_precision_micro": 0.8727447678614385,
|
| 313 |
+
"eval_recall_macro": 0.8322106966291821,
|
| 314 |
+
"eval_recall_micro": 0.8727447678614385,
|
| 315 |
+
"eval_runtime": 78.7849,
|
| 316 |
+
"eval_samples_per_second": 52.764,
|
| 317 |
+
"eval_steps_per_second": 3.3,
|
| 318 |
+
"step": 7000
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 3.642544924720738,
|
| 322 |
+
"grad_norm": 0.004680951591581106,
|
| 323 |
+
"learning_rate": 1.789703739679456e-06,
|
| 324 |
+
"loss": 0.0042,
|
| 325 |
+
"step": 7500
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 3.642544924720738,
|
| 329 |
+
"eval_accuracy": 0.8878999278325715,
|
| 330 |
+
"eval_f1_macro": 0.8433308117001564,
|
| 331 |
+
"eval_f1_micro": 0.8878999278325715,
|
| 332 |
+
"eval_loss": 0.5990936756134033,
|
| 333 |
+
"eval_precision_macro": 0.8472220448304009,
|
| 334 |
+
"eval_precision_micro": 0.8878999278325715,
|
| 335 |
+
"eval_recall_macro": 0.8545322401470954,
|
| 336 |
+
"eval_recall_micro": 0.8878999278325715,
|
| 337 |
+
"eval_runtime": 79.0879,
|
| 338 |
+
"eval_samples_per_second": 52.562,
|
| 339 |
+
"eval_steps_per_second": 3.287,
|
| 340 |
+
"step": 7500
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 3.885381253035454,
|
| 344 |
+
"grad_norm": 0.010031532496213913,
|
| 345 |
+
"learning_rate": 5.755220981058767e-07,
|
| 346 |
+
"loss": 0.0031,
|
| 347 |
+
"step": 8000
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 3.885381253035454,
|
| 351 |
+
"eval_accuracy": 0.8917488573490499,
|
| 352 |
+
"eval_f1_macro": 0.8426490769860735,
|
| 353 |
+
"eval_f1_micro": 0.8917488573490499,
|
| 354 |
+
"eval_loss": 0.5693513751029968,
|
| 355 |
+
"eval_precision_macro": 0.8463441328885969,
|
| 356 |
+
"eval_precision_micro": 0.8917488573490499,
|
| 357 |
+
"eval_recall_macro": 0.8543482468908278,
|
| 358 |
+
"eval_recall_micro": 0.8917488573490499,
|
| 359 |
+
"eval_runtime": 78.783,
|
| 360 |
+
"eval_samples_per_second": 52.765,
|
| 361 |
+
"eval_steps_per_second": 3.3,
|
| 362 |
+
"step": 8000
|
| 363 |
+
}
|
| 364 |
+
],
|
| 365 |
+
"logging_steps": 500,
|
| 366 |
+
"max_steps": 8236,
|
| 367 |
+
"num_input_tokens_seen": 0,
|
| 368 |
+
"num_train_epochs": 4,
|
| 369 |
+
"save_steps": 500,
|
| 370 |
+
"stateful_callbacks": {
|
| 371 |
+
"TrainerControl": {
|
| 372 |
+
"args": {
|
| 373 |
+
"should_epoch_stop": false,
|
| 374 |
+
"should_evaluate": false,
|
| 375 |
+
"should_log": false,
|
| 376 |
+
"should_save": true,
|
| 377 |
+
"should_training_stop": true
|
| 378 |
+
},
|
| 379 |
+
"attributes": {}
|
| 380 |
+
}
|
| 381 |
+
},
|
| 382 |
+
"total_flos": 0.0,
|
| 383 |
+
"train_batch_size": 16,
|
| 384 |
+
"trial_name": null,
|
| 385 |
+
"trial_params": null
|
| 386 |
+
}
|
checkpoint-8236/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:136b7b4293e2141f44a8b5057bed262843c60ffd9dbdb070d79796b2a20d5edc
|
| 3 |
+
size 5304
|
checkpoint-8236/vocab.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 sha256:2ad50af0d0ec81a0eee4dc85c9fa9da78a86ff99bdd689c0ce94b3bf86b5fed9
|
| 3 |
+
size 436414084
|
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 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"1": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"4": {
|
| 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": true,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_basic_tokenize": true,
|
| 47 |
+
"do_lower_case": false,
|
| 48 |
+
"extra_special_tokens": {},
|
| 49 |
+
"full_tokenizer_file": null,
|
| 50 |
+
"mask_token": "[MASK]",
|
| 51 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 52 |
+
"never_split": null,
|
| 53 |
+
"pad_token": "[PAD]",
|
| 54 |
+
"sep_token": "[SEP]",
|
| 55 |
+
"strip_accents": null,
|
| 56 |
+
"tokenize_chinese_chars": true,
|
| 57 |
+
"tokenizer_class": "BertTokenizer",
|
| 58 |
+
"unk_token": "[UNK]"
|
| 59 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:136b7b4293e2141f44a8b5057bed262843c60ffd9dbdb070d79796b2a20d5edc
|
| 3 |
+
size 5304
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|