Ubuntu
commited on
Commit
·
864fd0b
1
Parent(s):
891bbc6
added model
Browse files- config.json +30 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- trainer_state.json +273 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "models-no-git/models/v3-dev-test-all/mBERT/bert-base-multilingual-cased/",
|
| 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": "4.6.0.dev0",
|
| 27 |
+
"type_vocab_size": 2,
|
| 28 |
+
"use_cache": true,
|
| 29 |
+
"vocab_size": 119547
|
| 30 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1f1cb24b4b39c188a8bbad73d402d5285142148f179532113d21eaa87f491808
|
| 3 |
+
size 1423922915
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0125347bd1a66f381177e9f5ec58aa92d90c7c087b1f8af07495d050b35229cd
|
| 3 |
+
size 711988242
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d0e23f0c907bde1c6c1a34166ed1638acfa3db62869ffe2a6cf7d5bd6ecd3c5d
|
| 3 |
+
size 14657
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:871f15849a71622c471a8839ff81f09b66a7cc7025ca394d3f64046134ca8a65
|
| 3 |
+
size 623
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"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": false, "do_basic_tokenize": true, "never_split": null, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "truncation": true, "model_max_length": 512, "special_tokens_map_file": null, "tokenizer_file": "/home/ubuntu/.cache/huggingface/transformers/46880f3b0081fda494a4e15b05787692aa4c1e21e0ff2428ba8b14d4eda0784d.b33e51591f94f17c238ee9b1fac75b96ff2678cbaed6e108feadb3449d18dc24", "name_or_path": "bert-base-multilingual-cased"}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,273 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 5.0,
|
| 5 |
+
"global_step": 18750,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.13,
|
| 12 |
+
"learning_rate": 1.9733333333333336e-05,
|
| 13 |
+
"loss": 2.5525,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.27,
|
| 18 |
+
"learning_rate": 1.9466666666666668e-05,
|
| 19 |
+
"loss": 2.3435,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.4,
|
| 24 |
+
"learning_rate": 1.9200000000000003e-05,
|
| 25 |
+
"loss": 2.2863,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.53,
|
| 30 |
+
"learning_rate": 1.8933333333333334e-05,
|
| 31 |
+
"loss": 2.1898,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.67,
|
| 36 |
+
"learning_rate": 1.866666666666667e-05,
|
| 37 |
+
"loss": 2.1592,
|
| 38 |
+
"step": 2500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.8,
|
| 42 |
+
"learning_rate": 1.8400000000000003e-05,
|
| 43 |
+
"loss": 2.118,
|
| 44 |
+
"step": 3000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.93,
|
| 48 |
+
"learning_rate": 1.8133333333333335e-05,
|
| 49 |
+
"loss": 2.1194,
|
| 50 |
+
"step": 3500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 1.0,
|
| 54 |
+
"eval_loss": 2.167937755584717,
|
| 55 |
+
"eval_runtime": 5.4656,
|
| 56 |
+
"eval_samples_per_second": 216.811,
|
| 57 |
+
"step": 3750
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 1.07,
|
| 61 |
+
"learning_rate": 1.7866666666666666e-05,
|
| 62 |
+
"loss": 2.0226,
|
| 63 |
+
"step": 4000
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 1.2,
|
| 67 |
+
"learning_rate": 1.76e-05,
|
| 68 |
+
"loss": 1.9416,
|
| 69 |
+
"step": 4500
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 1.33,
|
| 73 |
+
"learning_rate": 1.7333333333333336e-05,
|
| 74 |
+
"loss": 1.9142,
|
| 75 |
+
"step": 5000
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 1.47,
|
| 79 |
+
"learning_rate": 1.706666666666667e-05,
|
| 80 |
+
"loss": 1.9465,
|
| 81 |
+
"step": 5500
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 1.6,
|
| 85 |
+
"learning_rate": 1.6800000000000002e-05,
|
| 86 |
+
"loss": 1.9171,
|
| 87 |
+
"step": 6000
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 1.73,
|
| 91 |
+
"learning_rate": 1.6533333333333333e-05,
|
| 92 |
+
"loss": 1.9979,
|
| 93 |
+
"step": 6500
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 1.87,
|
| 97 |
+
"learning_rate": 1.6266666666666668e-05,
|
| 98 |
+
"loss": 1.963,
|
| 99 |
+
"step": 7000
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 2.0,
|
| 103 |
+
"learning_rate": 1.6000000000000003e-05,
|
| 104 |
+
"loss": 1.8565,
|
| 105 |
+
"step": 7500
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 2.0,
|
| 109 |
+
"eval_loss": 1.9571301937103271,
|
| 110 |
+
"eval_runtime": 5.653,
|
| 111 |
+
"eval_samples_per_second": 209.624,
|
| 112 |
+
"step": 7500
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 2.13,
|
| 116 |
+
"learning_rate": 1.5733333333333334e-05,
|
| 117 |
+
"loss": 1.824,
|
| 118 |
+
"step": 8000
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"epoch": 2.27,
|
| 122 |
+
"learning_rate": 1.546666666666667e-05,
|
| 123 |
+
"loss": 1.7946,
|
| 124 |
+
"step": 8500
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 2.4,
|
| 128 |
+
"learning_rate": 1.5200000000000002e-05,
|
| 129 |
+
"loss": 1.7443,
|
| 130 |
+
"step": 9000
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 2.53,
|
| 134 |
+
"learning_rate": 1.4933333333333335e-05,
|
| 135 |
+
"loss": 1.7903,
|
| 136 |
+
"step": 9500
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 2.67,
|
| 140 |
+
"learning_rate": 1.4666666666666666e-05,
|
| 141 |
+
"loss": 1.8024,
|
| 142 |
+
"step": 10000
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 2.8,
|
| 146 |
+
"learning_rate": 1.4400000000000001e-05,
|
| 147 |
+
"loss": 1.8127,
|
| 148 |
+
"step": 10500
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 2.93,
|
| 152 |
+
"learning_rate": 1.4133333333333334e-05,
|
| 153 |
+
"loss": 1.8099,
|
| 154 |
+
"step": 11000
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 3.0,
|
| 158 |
+
"eval_loss": 1.874105453491211,
|
| 159 |
+
"eval_runtime": 5.6378,
|
| 160 |
+
"eval_samples_per_second": 210.188,
|
| 161 |
+
"step": 11250
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 3.07,
|
| 165 |
+
"learning_rate": 1.3866666666666669e-05,
|
| 166 |
+
"loss": 1.8065,
|
| 167 |
+
"step": 11500
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 3.2,
|
| 171 |
+
"learning_rate": 1.3600000000000002e-05,
|
| 172 |
+
"loss": 1.7176,
|
| 173 |
+
"step": 12000
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 3.33,
|
| 177 |
+
"learning_rate": 1.3333333333333333e-05,
|
| 178 |
+
"loss": 1.7245,
|
| 179 |
+
"step": 12500
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 3.47,
|
| 183 |
+
"learning_rate": 1.3066666666666668e-05,
|
| 184 |
+
"loss": 1.6684,
|
| 185 |
+
"step": 13000
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 3.6,
|
| 189 |
+
"learning_rate": 1.2800000000000001e-05,
|
| 190 |
+
"loss": 1.7295,
|
| 191 |
+
"step": 13500
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 3.73,
|
| 195 |
+
"learning_rate": 1.2533333333333336e-05,
|
| 196 |
+
"loss": 1.6837,
|
| 197 |
+
"step": 14000
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 3.87,
|
| 201 |
+
"learning_rate": 1.2266666666666667e-05,
|
| 202 |
+
"loss": 1.6656,
|
| 203 |
+
"step": 14500
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 4.0,
|
| 207 |
+
"learning_rate": 1.2e-05,
|
| 208 |
+
"loss": 1.6573,
|
| 209 |
+
"step": 15000
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 4.0,
|
| 213 |
+
"eval_loss": 1.8567960262298584,
|
| 214 |
+
"eval_runtime": 5.4744,
|
| 215 |
+
"eval_samples_per_second": 216.461,
|
| 216 |
+
"step": 15000
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 4.13,
|
| 220 |
+
"learning_rate": 1.1733333333333335e-05,
|
| 221 |
+
"loss": 1.5965,
|
| 222 |
+
"step": 15500
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 4.27,
|
| 226 |
+
"learning_rate": 1.1466666666666668e-05,
|
| 227 |
+
"loss": 1.6115,
|
| 228 |
+
"step": 16000
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 4.4,
|
| 232 |
+
"learning_rate": 1.1200000000000001e-05,
|
| 233 |
+
"loss": 1.5584,
|
| 234 |
+
"step": 16500
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 4.53,
|
| 238 |
+
"learning_rate": 1.0933333333333334e-05,
|
| 239 |
+
"loss": 1.587,
|
| 240 |
+
"step": 17000
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 4.67,
|
| 244 |
+
"learning_rate": 1.0666666666666667e-05,
|
| 245 |
+
"loss": 1.5693,
|
| 246 |
+
"step": 17500
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 4.8,
|
| 250 |
+
"learning_rate": 1.04e-05,
|
| 251 |
+
"loss": 1.4976,
|
| 252 |
+
"step": 18000
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 4.93,
|
| 256 |
+
"learning_rate": 1.0133333333333335e-05,
|
| 257 |
+
"loss": 1.5615,
|
| 258 |
+
"step": 18500
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 5.0,
|
| 262 |
+
"eval_loss": 1.836472988128662,
|
| 263 |
+
"eval_runtime": 5.4044,
|
| 264 |
+
"eval_samples_per_second": 219.268,
|
| 265 |
+
"step": 18750
|
| 266 |
+
}
|
| 267 |
+
],
|
| 268 |
+
"max_steps": 37500,
|
| 269 |
+
"num_train_epochs": 10,
|
| 270 |
+
"total_flos": 876612801138408.0,
|
| 271 |
+
"trial_name": null,
|
| 272 |
+
"trial_params": null
|
| 273 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1f8271d33f1eb5e9743280501355c73ff558bef8408ebe5356782a61f049a418
|
| 3 |
+
size 2415
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|