Upload 6 files
Browse files- config.json +32 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +13 -0
- trainer_state.json +331 -0
- vocab.txt +0 -0
config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "hfl/chinese-macbert-base",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForMaskedLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"directionality": "bidi",
|
| 9 |
+
"gradient_checkpointing": false,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout_prob": 0.1,
|
| 12 |
+
"hidden_size": 768,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 3072,
|
| 15 |
+
"layer_norm_eps": 1e-12,
|
| 16 |
+
"max_position_embeddings": 512,
|
| 17 |
+
"model_type": "bert",
|
| 18 |
+
"num_attention_heads": 12,
|
| 19 |
+
"num_hidden_layers": 12,
|
| 20 |
+
"pad_token_id": 0,
|
| 21 |
+
"pooler_fc_size": 768,
|
| 22 |
+
"pooler_num_attention_heads": 12,
|
| 23 |
+
"pooler_num_fc_layers": 3,
|
| 24 |
+
"pooler_size_per_head": 128,
|
| 25 |
+
"pooler_type": "first_token_transform",
|
| 26 |
+
"position_embedding_type": "absolute",
|
| 27 |
+
"torch_dtype": "float32",
|
| 28 |
+
"transformers_version": "4.24.0.dev0",
|
| 29 |
+
"type_vocab_size": 2,
|
| 30 |
+
"use_cache": true,
|
| 31 |
+
"vocab_size": 21128
|
| 32 |
+
}
|
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 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"do_lower_case": true,
|
| 4 |
+
"mask_token": "[MASK]",
|
| 5 |
+
"name_or_path": "hfl/chinese-macbert-base",
|
| 6 |
+
"pad_token": "[PAD]",
|
| 7 |
+
"sep_token": "[SEP]",
|
| 8 |
+
"special_tokens_map_file": "/export/data/yida/huggingface_cache/models--hfl--chinese-macbert-base/snapshots/a986e004d2a7f2a1c2f5a3edef4e20604a974ed1/special_tokens_map.json",
|
| 9 |
+
"strip_accents": null,
|
| 10 |
+
"tokenize_chinese_chars": true,
|
| 11 |
+
"tokenizer_class": "BertTokenizer",
|
| 12 |
+
"unk_token": "[UNK]"
|
| 13 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,331 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 100.0,
|
| 5 |
+
"global_step": 25800,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 1.94,
|
| 12 |
+
"learning_rate": 4.903294573643411e-05,
|
| 13 |
+
"loss": 0.981,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 3.88,
|
| 18 |
+
"learning_rate": 4.8063953488372096e-05,
|
| 19 |
+
"loss": 0.7307,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 5.81,
|
| 24 |
+
"learning_rate": 4.709496124031008e-05,
|
| 25 |
+
"loss": 0.6521,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 7.75,
|
| 30 |
+
"learning_rate": 4.612596899224806e-05,
|
| 31 |
+
"loss": 0.5851,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 9.69,
|
| 36 |
+
"learning_rate": 4.515697674418605e-05,
|
| 37 |
+
"loss": 0.5504,
|
| 38 |
+
"step": 2500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 11.63,
|
| 42 |
+
"learning_rate": 4.418798449612404e-05,
|
| 43 |
+
"loss": 0.5169,
|
| 44 |
+
"step": 3000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 13.57,
|
| 48 |
+
"learning_rate": 4.321899224806202e-05,
|
| 49 |
+
"loss": 0.4854,
|
| 50 |
+
"step": 3500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 15.5,
|
| 54 |
+
"learning_rate": 4.2250000000000004e-05,
|
| 55 |
+
"loss": 0.4565,
|
| 56 |
+
"step": 4000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 17.44,
|
| 60 |
+
"learning_rate": 4.128100775193799e-05,
|
| 61 |
+
"loss": 0.4407,
|
| 62 |
+
"step": 4500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 19.38,
|
| 66 |
+
"learning_rate": 4.031201550387597e-05,
|
| 67 |
+
"loss": 0.4256,
|
| 68 |
+
"step": 5000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 21.32,
|
| 72 |
+
"learning_rate": 3.9343023255813954e-05,
|
| 73 |
+
"loss": 0.4087,
|
| 74 |
+
"step": 5500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 23.26,
|
| 78 |
+
"learning_rate": 3.837403100775194e-05,
|
| 79 |
+
"loss": 0.3882,
|
| 80 |
+
"step": 6000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 25.19,
|
| 84 |
+
"learning_rate": 3.740697674418605e-05,
|
| 85 |
+
"loss": 0.3757,
|
| 86 |
+
"step": 6500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 27.13,
|
| 90 |
+
"learning_rate": 3.643798449612403e-05,
|
| 91 |
+
"loss": 0.3613,
|
| 92 |
+
"step": 7000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 29.07,
|
| 96 |
+
"learning_rate": 3.5468992248062015e-05,
|
| 97 |
+
"loss": 0.3477,
|
| 98 |
+
"step": 7500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 31.01,
|
| 102 |
+
"learning_rate": 3.45e-05,
|
| 103 |
+
"loss": 0.3302,
|
| 104 |
+
"step": 8000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 32.95,
|
| 108 |
+
"learning_rate": 3.353100775193799e-05,
|
| 109 |
+
"loss": 0.3222,
|
| 110 |
+
"step": 8500
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 34.88,
|
| 114 |
+
"learning_rate": 3.256201550387597e-05,
|
| 115 |
+
"loss": 0.3118,
|
| 116 |
+
"step": 9000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 36.82,
|
| 120 |
+
"learning_rate": 3.1594961240310076e-05,
|
| 121 |
+
"loss": 0.3015,
|
| 122 |
+
"step": 9500
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 38.76,
|
| 126 |
+
"learning_rate": 3.062596899224806e-05,
|
| 127 |
+
"loss": 0.2976,
|
| 128 |
+
"step": 10000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 40.7,
|
| 132 |
+
"learning_rate": 2.965697674418605e-05,
|
| 133 |
+
"loss": 0.2893,
|
| 134 |
+
"step": 10500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 42.64,
|
| 138 |
+
"learning_rate": 2.8687984496124033e-05,
|
| 139 |
+
"loss": 0.2786,
|
| 140 |
+
"step": 11000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 44.57,
|
| 144 |
+
"learning_rate": 2.7718992248062013e-05,
|
| 145 |
+
"loss": 0.2696,
|
| 146 |
+
"step": 11500
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 46.51,
|
| 150 |
+
"learning_rate": 2.6750000000000003e-05,
|
| 151 |
+
"loss": 0.2646,
|
| 152 |
+
"step": 12000
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 48.45,
|
| 156 |
+
"learning_rate": 2.5781007751937987e-05,
|
| 157 |
+
"loss": 0.2588,
|
| 158 |
+
"step": 12500
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 50.39,
|
| 162 |
+
"learning_rate": 2.481201550387597e-05,
|
| 163 |
+
"loss": 0.2484,
|
| 164 |
+
"step": 13000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 52.33,
|
| 168 |
+
"learning_rate": 2.384496124031008e-05,
|
| 169 |
+
"loss": 0.251,
|
| 170 |
+
"step": 13500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 54.26,
|
| 174 |
+
"learning_rate": 2.287596899224806e-05,
|
| 175 |
+
"loss": 0.2415,
|
| 176 |
+
"step": 14000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 56.2,
|
| 180 |
+
"learning_rate": 2.1906976744186047e-05,
|
| 181 |
+
"loss": 0.2297,
|
| 182 |
+
"step": 14500
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 58.14,
|
| 186 |
+
"learning_rate": 2.0937984496124034e-05,
|
| 187 |
+
"loss": 0.2255,
|
| 188 |
+
"step": 15000
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 60.08,
|
| 192 |
+
"learning_rate": 1.997093023255814e-05,
|
| 193 |
+
"loss": 0.2217,
|
| 194 |
+
"step": 15500
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 62.02,
|
| 198 |
+
"learning_rate": 1.9001937984496125e-05,
|
| 199 |
+
"loss": 0.2172,
|
| 200 |
+
"step": 16000
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 63.95,
|
| 204 |
+
"learning_rate": 1.8032945736434108e-05,
|
| 205 |
+
"loss": 0.2149,
|
| 206 |
+
"step": 16500
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 65.89,
|
| 210 |
+
"learning_rate": 1.7063953488372095e-05,
|
| 211 |
+
"loss": 0.2102,
|
| 212 |
+
"step": 17000
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 67.83,
|
| 216 |
+
"learning_rate": 1.6096899224806202e-05,
|
| 217 |
+
"loss": 0.2059,
|
| 218 |
+
"step": 17500
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 69.77,
|
| 222 |
+
"learning_rate": 1.5127906976744186e-05,
|
| 223 |
+
"loss": 0.2011,
|
| 224 |
+
"step": 18000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 71.71,
|
| 228 |
+
"learning_rate": 1.415891472868217e-05,
|
| 229 |
+
"loss": 0.1939,
|
| 230 |
+
"step": 18500
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 73.64,
|
| 234 |
+
"learning_rate": 1.3189922480620156e-05,
|
| 235 |
+
"loss": 0.1919,
|
| 236 |
+
"step": 19000
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 75.58,
|
| 240 |
+
"learning_rate": 1.2224806201550389e-05,
|
| 241 |
+
"loss": 0.1903,
|
| 242 |
+
"step": 19500
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 77.52,
|
| 246 |
+
"learning_rate": 1.1257751937984498e-05,
|
| 247 |
+
"loss": 0.1862,
|
| 248 |
+
"step": 20000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 79.46,
|
| 252 |
+
"learning_rate": 1.0288759689922481e-05,
|
| 253 |
+
"loss": 0.1833,
|
| 254 |
+
"step": 20500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 81.4,
|
| 258 |
+
"learning_rate": 9.319767441860464e-06,
|
| 259 |
+
"loss": 0.1811,
|
| 260 |
+
"step": 21000
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 83.33,
|
| 264 |
+
"learning_rate": 8.350775193798451e-06,
|
| 265 |
+
"loss": 0.1778,
|
| 266 |
+
"step": 21500
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 85.27,
|
| 270 |
+
"learning_rate": 7.381782945736435e-06,
|
| 271 |
+
"loss": 0.1749,
|
| 272 |
+
"step": 22000
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 87.21,
|
| 276 |
+
"learning_rate": 6.412790697674419e-06,
|
| 277 |
+
"loss": 0.1727,
|
| 278 |
+
"step": 22500
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 89.15,
|
| 282 |
+
"learning_rate": 5.443798449612403e-06,
|
| 283 |
+
"loss": 0.1666,
|
| 284 |
+
"step": 23000
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 91.09,
|
| 288 |
+
"learning_rate": 4.4748062015503875e-06,
|
| 289 |
+
"loss": 0.1707,
|
| 290 |
+
"step": 23500
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 93.02,
|
| 294 |
+
"learning_rate": 3.5077519379844964e-06,
|
| 295 |
+
"loss": 0.1687,
|
| 296 |
+
"step": 24000
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 94.96,
|
| 300 |
+
"learning_rate": 2.538759689922481e-06,
|
| 301 |
+
"loss": 0.1668,
|
| 302 |
+
"step": 24500
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 96.9,
|
| 306 |
+
"learning_rate": 1.5697674418604653e-06,
|
| 307 |
+
"loss": 0.1644,
|
| 308 |
+
"step": 25000
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 98.84,
|
| 312 |
+
"learning_rate": 6.007751937984496e-07,
|
| 313 |
+
"loss": 0.1636,
|
| 314 |
+
"step": 25500
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 100.0,
|
| 318 |
+
"step": 25800,
|
| 319 |
+
"total_flos": 1.18478524985856e+17,
|
| 320 |
+
"train_loss": 0.3071320072440214,
|
| 321 |
+
"train_runtime": 5938.5496,
|
| 322 |
+
"train_samples_per_second": 277.239,
|
| 323 |
+
"train_steps_per_second": 4.344
|
| 324 |
+
}
|
| 325 |
+
],
|
| 326 |
+
"max_steps": 25800,
|
| 327 |
+
"num_train_epochs": 100,
|
| 328 |
+
"total_flos": 1.18478524985856e+17,
|
| 329 |
+
"trial_name": null,
|
| 330 |
+
"trial_params": null
|
| 331 |
+
}
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|