Nikita Moghe Moghe
commited on
Commit
•
95001ba
1
Parent(s):
8695609
First model version
Browse files- config.json +30 -0
- eval_results_mlm.txt +1 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- train_results.txt +3 -0
- trainer_state.json +322 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "bert-base-multilingual-uncased",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForMaskedLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"directionality": "bidi",
|
| 8 |
+
"gradient_checkpointing": false,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 3072,
|
| 14 |
+
"layer_norm_eps": 1e-12,
|
| 15 |
+
"max_position_embeddings": 512,
|
| 16 |
+
"model_type": "bert",
|
| 17 |
+
"num_attention_heads": 12,
|
| 18 |
+
"num_hidden_layers": 12,
|
| 19 |
+
"pad_token_id": 0,
|
| 20 |
+
"pooler_fc_size": 768,
|
| 21 |
+
"pooler_num_attention_heads": 12,
|
| 22 |
+
"pooler_num_fc_layers": 3,
|
| 23 |
+
"pooler_size_per_head": 128,
|
| 24 |
+
"pooler_type": "first_token_transform",
|
| 25 |
+
"position_embedding_type": "absolute",
|
| 26 |
+
"transformers_version": "4.2.2",
|
| 27 |
+
"type_vocab_size": 2,
|
| 28 |
+
"use_cache": true,
|
| 29 |
+
"vocab_size": 105879
|
| 30 |
+
}
|
eval_results_mlm.txt
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
perplexity = 4.088457825011212
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:382e16bfe83cea434adaae30b619995e31b20f3072812f96e13e63c66cbde932
|
| 3 |
+
size 669910510
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"bos_token": "<S>", "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "name_or_path": "bert-base-multilingual-uncased"}
|
train_results.txt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
epoch = 10.0
|
| 2 |
+
train_runtime = 15880.0798
|
| 3 |
+
train_samples_per_second = 7.871
|
trainer_state.json
ADDED
|
@@ -0,0 +1,322 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 9.999960001599936,
|
| 5 |
+
"global_step": 125000,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.2,
|
| 12 |
+
"learning_rate": 4.9e-05,
|
| 13 |
+
"loss": 2.2296,
|
| 14 |
+
"step": 2500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.4,
|
| 18 |
+
"learning_rate": 4.8e-05,
|
| 19 |
+
"loss": 2.0608,
|
| 20 |
+
"step": 5000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.6,
|
| 24 |
+
"learning_rate": 4.7e-05,
|
| 25 |
+
"loss": 1.987,
|
| 26 |
+
"step": 7500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.8,
|
| 30 |
+
"learning_rate": 4.600000000000001e-05,
|
| 31 |
+
"loss": 1.9583,
|
| 32 |
+
"step": 10000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 1.0,
|
| 36 |
+
"learning_rate": 4.5e-05,
|
| 37 |
+
"loss": 1.9038,
|
| 38 |
+
"step": 12500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 1.2,
|
| 42 |
+
"learning_rate": 4.4000000000000006e-05,
|
| 43 |
+
"loss": 1.8114,
|
| 44 |
+
"step": 15000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 1.4,
|
| 48 |
+
"learning_rate": 4.3e-05,
|
| 49 |
+
"loss": 1.8088,
|
| 50 |
+
"step": 17500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 1.6,
|
| 54 |
+
"learning_rate": 4.2e-05,
|
| 55 |
+
"loss": 1.7709,
|
| 56 |
+
"step": 20000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 1.8,
|
| 60 |
+
"learning_rate": 4.1e-05,
|
| 61 |
+
"loss": 1.7479,
|
| 62 |
+
"step": 22500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 2.0,
|
| 66 |
+
"learning_rate": 4e-05,
|
| 67 |
+
"loss": 1.7373,
|
| 68 |
+
"step": 25000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 2.2,
|
| 72 |
+
"learning_rate": 3.9000000000000006e-05,
|
| 73 |
+
"loss": 1.6358,
|
| 74 |
+
"step": 27500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 2.4,
|
| 78 |
+
"learning_rate": 3.8e-05,
|
| 79 |
+
"loss": 1.6291,
|
| 80 |
+
"step": 30000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 2.6,
|
| 84 |
+
"learning_rate": 3.7e-05,
|
| 85 |
+
"loss": 1.6265,
|
| 86 |
+
"step": 32500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 2.8,
|
| 90 |
+
"learning_rate": 3.6e-05,
|
| 91 |
+
"loss": 1.6149,
|
| 92 |
+
"step": 35000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 3.0,
|
| 96 |
+
"learning_rate": 3.5e-05,
|
| 97 |
+
"loss": 1.6124,
|
| 98 |
+
"step": 37500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 3.2,
|
| 102 |
+
"learning_rate": 3.4000000000000007e-05,
|
| 103 |
+
"loss": 1.5486,
|
| 104 |
+
"step": 40000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 3.4,
|
| 108 |
+
"learning_rate": 3.3e-05,
|
| 109 |
+
"loss": 1.5361,
|
| 110 |
+
"step": 42500
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 3.6,
|
| 114 |
+
"learning_rate": 3.2000000000000005e-05,
|
| 115 |
+
"loss": 1.52,
|
| 116 |
+
"step": 45000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 3.8,
|
| 120 |
+
"learning_rate": 3.1e-05,
|
| 121 |
+
"loss": 1.5049,
|
| 122 |
+
"step": 47500
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 4.0,
|
| 126 |
+
"learning_rate": 3e-05,
|
| 127 |
+
"loss": 1.5074,
|
| 128 |
+
"step": 50000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 4.2,
|
| 132 |
+
"learning_rate": 2.9e-05,
|
| 133 |
+
"loss": 1.4674,
|
| 134 |
+
"step": 52500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 4.4,
|
| 138 |
+
"learning_rate": 2.8000000000000003e-05,
|
| 139 |
+
"loss": 1.446,
|
| 140 |
+
"step": 55000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 4.6,
|
| 144 |
+
"learning_rate": 2.7000000000000002e-05,
|
| 145 |
+
"loss": 1.4385,
|
| 146 |
+
"step": 57500
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 4.8,
|
| 150 |
+
"learning_rate": 2.6000000000000002e-05,
|
| 151 |
+
"loss": 1.4202,
|
| 152 |
+
"step": 60000
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 5.0,
|
| 156 |
+
"learning_rate": 2.5e-05,
|
| 157 |
+
"loss": 1.3935,
|
| 158 |
+
"step": 62500
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 5.2,
|
| 162 |
+
"learning_rate": 2.4e-05,
|
| 163 |
+
"loss": 1.3593,
|
| 164 |
+
"step": 65000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 5.4,
|
| 168 |
+
"learning_rate": 2.3000000000000003e-05,
|
| 169 |
+
"loss": 1.3439,
|
| 170 |
+
"step": 67500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 5.6,
|
| 174 |
+
"learning_rate": 2.2000000000000003e-05,
|
| 175 |
+
"loss": 1.3417,
|
| 176 |
+
"step": 70000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 5.8,
|
| 180 |
+
"learning_rate": 2.1e-05,
|
| 181 |
+
"loss": 1.3306,
|
| 182 |
+
"step": 72500
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 6.0,
|
| 186 |
+
"learning_rate": 2e-05,
|
| 187 |
+
"loss": 1.3141,
|
| 188 |
+
"step": 75000
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 6.2,
|
| 192 |
+
"learning_rate": 1.9e-05,
|
| 193 |
+
"loss": 1.2657,
|
| 194 |
+
"step": 77500
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 6.4,
|
| 198 |
+
"learning_rate": 1.8e-05,
|
| 199 |
+
"loss": 1.2714,
|
| 200 |
+
"step": 80000
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 6.6,
|
| 204 |
+
"learning_rate": 1.7000000000000003e-05,
|
| 205 |
+
"loss": 1.2649,
|
| 206 |
+
"step": 82500
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 6.8,
|
| 210 |
+
"learning_rate": 1.6000000000000003e-05,
|
| 211 |
+
"loss": 1.248,
|
| 212 |
+
"step": 85000
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 7.0,
|
| 216 |
+
"learning_rate": 1.5e-05,
|
| 217 |
+
"loss": 1.2594,
|
| 218 |
+
"step": 87500
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 7.2,
|
| 222 |
+
"learning_rate": 1.4000000000000001e-05,
|
| 223 |
+
"loss": 1.2195,
|
| 224 |
+
"step": 90000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 7.4,
|
| 228 |
+
"learning_rate": 1.3000000000000001e-05,
|
| 229 |
+
"loss": 1.2105,
|
| 230 |
+
"step": 92500
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 7.6,
|
| 234 |
+
"learning_rate": 1.2e-05,
|
| 235 |
+
"loss": 1.1911,
|
| 236 |
+
"step": 95000
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 7.8,
|
| 240 |
+
"learning_rate": 1.1000000000000001e-05,
|
| 241 |
+
"loss": 1.172,
|
| 242 |
+
"step": 97500
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 8.0,
|
| 246 |
+
"learning_rate": 1e-05,
|
| 247 |
+
"loss": 1.1758,
|
| 248 |
+
"step": 100000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 8.2,
|
| 252 |
+
"learning_rate": 9e-06,
|
| 253 |
+
"loss": 1.163,
|
| 254 |
+
"step": 102500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 8.4,
|
| 258 |
+
"learning_rate": 8.000000000000001e-06,
|
| 259 |
+
"loss": 1.1555,
|
| 260 |
+
"step": 105000
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 8.6,
|
| 264 |
+
"learning_rate": 7.000000000000001e-06,
|
| 265 |
+
"loss": 1.1418,
|
| 266 |
+
"step": 107500
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 8.8,
|
| 270 |
+
"learning_rate": 6e-06,
|
| 271 |
+
"loss": 1.1162,
|
| 272 |
+
"step": 110000
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 9.0,
|
| 276 |
+
"learning_rate": 5e-06,
|
| 277 |
+
"loss": 1.1089,
|
| 278 |
+
"step": 112500
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 9.2,
|
| 282 |
+
"learning_rate": 4.000000000000001e-06,
|
| 283 |
+
"loss": 1.0745,
|
| 284 |
+
"step": 115000
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 9.4,
|
| 288 |
+
"learning_rate": 3e-06,
|
| 289 |
+
"loss": 1.1002,
|
| 290 |
+
"step": 117500
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 9.6,
|
| 294 |
+
"learning_rate": 2.0000000000000003e-06,
|
| 295 |
+
"loss": 1.0877,
|
| 296 |
+
"step": 120000
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 9.8,
|
| 300 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 301 |
+
"loss": 1.0767,
|
| 302 |
+
"step": 122500
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 10.0,
|
| 306 |
+
"learning_rate": 0.0,
|
| 307 |
+
"loss": 1.0536,
|
| 308 |
+
"step": 125000
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 10.0,
|
| 312 |
+
"step": 125000,
|
| 313 |
+
"train_runtime": 15880.0798,
|
| 314 |
+
"train_samples_per_second": 7.871
|
| 315 |
+
}
|
| 316 |
+
],
|
| 317 |
+
"max_steps": 125000,
|
| 318 |
+
"num_train_epochs": 10,
|
| 319 |
+
"total_flos": 33561297088632468,
|
| 320 |
+
"trial_name": null,
|
| 321 |
+
"trial_params": null
|
| 322 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f35e4357deb186bbab8d3e7e9da86ff3bf5e01c204827a388844f9007a4de5e6
|
| 3 |
+
size 1831
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|