Ubuntu
commited on
Commit
•
7650c7a
1
Parent(s):
80850df
initial upload
Browse files- all_results.json +7 -0
- config.json +24 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- train_results.json +7 -0
- trainer_state.json +354 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
all_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"train_runtime": 30959.6058,
|
| 4 |
+
"train_samples": 88524,
|
| 5 |
+
"train_samples_per_second": 14.297,
|
| 6 |
+
"train_steps_per_second": 0.894
|
| 7 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "bert-large-uncased",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForQuestionAnswering"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"gradient_checkpointing": false,
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.1,
|
| 10 |
+
"hidden_size": 1024,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 4096,
|
| 13 |
+
"layer_norm_eps": 1e-12,
|
| 14 |
+
"max_position_embeddings": 512,
|
| 15 |
+
"model_type": "bert",
|
| 16 |
+
"num_attention_heads": 16,
|
| 17 |
+
"num_hidden_layers": 24,
|
| 18 |
+
"pad_token_id": 0,
|
| 19 |
+
"position_embedding_type": "absolute",
|
| 20 |
+
"transformers_version": "4.7.0.dev0",
|
| 21 |
+
"type_vocab_size": 2,
|
| 22 |
+
"use_cache": true,
|
| 23 |
+
"vocab_size": 30522
|
| 24 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:644e7be54f301eb4a0d4947745c2137c9d19ec1a349502923ef0e42892d4f698
|
| 3 |
+
size 1336544467
|
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.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
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, "special_tokens_map_file": null, "name_or_path": "bert-large-uncased"}
|
train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"train_runtime": 30959.6058,
|
| 4 |
+
"train_samples": 88524,
|
| 5 |
+
"train_samples_per_second": 14.297,
|
| 6 |
+
"train_steps_per_second": 0.894
|
| 7 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,354 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 5.0,
|
| 5 |
+
"global_step": 27665,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.09,
|
| 12 |
+
"learning_rate": 2.9457798662570034e-05,
|
| 13 |
+
"loss": 1.8933,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.18,
|
| 18 |
+
"learning_rate": 2.891559732514007e-05,
|
| 19 |
+
"loss": 1.2883,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.27,
|
| 24 |
+
"learning_rate": 2.83733959877101e-05,
|
| 25 |
+
"loss": 1.1257,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.36,
|
| 30 |
+
"learning_rate": 2.783119465028014e-05,
|
| 31 |
+
"loss": 1.0502,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.45,
|
| 36 |
+
"learning_rate": 2.7288993312850172e-05,
|
| 37 |
+
"loss": 1.0699,
|
| 38 |
+
"step": 2500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.54,
|
| 42 |
+
"learning_rate": 2.6746791975420206e-05,
|
| 43 |
+
"loss": 0.9881,
|
| 44 |
+
"step": 3000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.63,
|
| 48 |
+
"learning_rate": 2.6204590637990243e-05,
|
| 49 |
+
"loss": 0.9836,
|
| 50 |
+
"step": 3500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.72,
|
| 54 |
+
"learning_rate": 2.5662389300560273e-05,
|
| 55 |
+
"loss": 0.9681,
|
| 56 |
+
"step": 4000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.81,
|
| 60 |
+
"learning_rate": 2.512018796313031e-05,
|
| 61 |
+
"loss": 0.969,
|
| 62 |
+
"step": 4500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.9,
|
| 66 |
+
"learning_rate": 2.4577986625700344e-05,
|
| 67 |
+
"loss": 0.9503,
|
| 68 |
+
"step": 5000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.99,
|
| 72 |
+
"learning_rate": 2.4035785288270377e-05,
|
| 73 |
+
"loss": 0.9695,
|
| 74 |
+
"step": 5500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 1.08,
|
| 78 |
+
"learning_rate": 2.3493583950840414e-05,
|
| 79 |
+
"loss": 0.636,
|
| 80 |
+
"step": 6000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 1.17,
|
| 84 |
+
"learning_rate": 2.2951382613410445e-05,
|
| 85 |
+
"loss": 0.6444,
|
| 86 |
+
"step": 6500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 1.27,
|
| 90 |
+
"learning_rate": 2.2409181275980482e-05,
|
| 91 |
+
"loss": 0.6331,
|
| 92 |
+
"step": 7000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 1.36,
|
| 96 |
+
"learning_rate": 2.1866979938550515e-05,
|
| 97 |
+
"loss": 0.6488,
|
| 98 |
+
"step": 7500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 1.45,
|
| 102 |
+
"learning_rate": 2.132477860112055e-05,
|
| 103 |
+
"loss": 0.6312,
|
| 104 |
+
"step": 8000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 1.54,
|
| 108 |
+
"learning_rate": 2.0782577263690586e-05,
|
| 109 |
+
"loss": 0.6953,
|
| 110 |
+
"step": 8500
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 1.63,
|
| 114 |
+
"learning_rate": 2.024037592626062e-05,
|
| 115 |
+
"loss": 0.5981,
|
| 116 |
+
"step": 9000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 1.72,
|
| 120 |
+
"learning_rate": 1.9698174588830653e-05,
|
| 121 |
+
"loss": 0.6499,
|
| 122 |
+
"step": 9500
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 1.81,
|
| 126 |
+
"learning_rate": 1.9155973251400687e-05,
|
| 127 |
+
"loss": 0.6395,
|
| 128 |
+
"step": 10000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 1.9,
|
| 132 |
+
"learning_rate": 1.861377191397072e-05,
|
| 133 |
+
"loss": 0.6079,
|
| 134 |
+
"step": 10500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 1.99,
|
| 138 |
+
"learning_rate": 1.8071570576540758e-05,
|
| 139 |
+
"loss": 0.6615,
|
| 140 |
+
"step": 11000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 2.08,
|
| 144 |
+
"learning_rate": 1.752936923911079e-05,
|
| 145 |
+
"loss": 0.3813,
|
| 146 |
+
"step": 11500
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 2.17,
|
| 150 |
+
"learning_rate": 1.6987167901680825e-05,
|
| 151 |
+
"loss": 0.3715,
|
| 152 |
+
"step": 12000
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 2.26,
|
| 156 |
+
"learning_rate": 1.644496656425086e-05,
|
| 157 |
+
"loss": 0.3573,
|
| 158 |
+
"step": 12500
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 2.35,
|
| 162 |
+
"learning_rate": 1.5902765226820892e-05,
|
| 163 |
+
"loss": 0.3673,
|
| 164 |
+
"step": 13000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 2.44,
|
| 168 |
+
"learning_rate": 1.536056388939093e-05,
|
| 169 |
+
"loss": 0.3802,
|
| 170 |
+
"step": 13500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 2.53,
|
| 174 |
+
"learning_rate": 1.4818362551960961e-05,
|
| 175 |
+
"loss": 0.3911,
|
| 176 |
+
"step": 14000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 2.62,
|
| 180 |
+
"learning_rate": 1.4276161214530996e-05,
|
| 181 |
+
"loss": 0.3691,
|
| 182 |
+
"step": 14500
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 2.71,
|
| 186 |
+
"learning_rate": 1.373395987710103e-05,
|
| 187 |
+
"loss": 0.3998,
|
| 188 |
+
"step": 15000
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 2.8,
|
| 192 |
+
"learning_rate": 1.3191758539671065e-05,
|
| 193 |
+
"loss": 0.3819,
|
| 194 |
+
"step": 15500
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 2.89,
|
| 198 |
+
"learning_rate": 1.26495572022411e-05,
|
| 199 |
+
"loss": 0.3748,
|
| 200 |
+
"step": 16000
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 2.98,
|
| 204 |
+
"learning_rate": 1.2107355864811133e-05,
|
| 205 |
+
"loss": 0.391,
|
| 206 |
+
"step": 16500
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 3.07,
|
| 210 |
+
"learning_rate": 1.1565154527381168e-05,
|
| 211 |
+
"loss": 0.2517,
|
| 212 |
+
"step": 17000
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 3.16,
|
| 216 |
+
"learning_rate": 1.1022953189951202e-05,
|
| 217 |
+
"loss": 0.2038,
|
| 218 |
+
"step": 17500
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 3.25,
|
| 222 |
+
"learning_rate": 1.0480751852521237e-05,
|
| 223 |
+
"loss": 0.1975,
|
| 224 |
+
"step": 18000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 3.34,
|
| 228 |
+
"learning_rate": 9.938550515091272e-06,
|
| 229 |
+
"loss": 0.21,
|
| 230 |
+
"step": 18500
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 3.43,
|
| 234 |
+
"learning_rate": 9.396349177661304e-06,
|
| 235 |
+
"loss": 0.2048,
|
| 236 |
+
"step": 19000
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 3.52,
|
| 240 |
+
"learning_rate": 8.85414784023134e-06,
|
| 241 |
+
"loss": 0.212,
|
| 242 |
+
"step": 19500
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 3.61,
|
| 246 |
+
"learning_rate": 8.311946502801373e-06,
|
| 247 |
+
"loss": 0.2126,
|
| 248 |
+
"step": 20000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 3.71,
|
| 252 |
+
"learning_rate": 7.769745165371408e-06,
|
| 253 |
+
"loss": 0.2084,
|
| 254 |
+
"step": 20500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 3.8,
|
| 258 |
+
"learning_rate": 7.227543827941442e-06,
|
| 259 |
+
"loss": 0.2097,
|
| 260 |
+
"step": 21000
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 3.89,
|
| 264 |
+
"learning_rate": 6.685342490511477e-06,
|
| 265 |
+
"loss": 0.2295,
|
| 266 |
+
"step": 21500
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 3.98,
|
| 270 |
+
"learning_rate": 6.143141153081511e-06,
|
| 271 |
+
"loss": 0.2157,
|
| 272 |
+
"step": 22000
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 4.07,
|
| 276 |
+
"learning_rate": 5.6009398156515455e-06,
|
| 277 |
+
"loss": 0.157,
|
| 278 |
+
"step": 22500
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 4.16,
|
| 282 |
+
"learning_rate": 5.058738478221579e-06,
|
| 283 |
+
"loss": 0.0847,
|
| 284 |
+
"step": 23000
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 4.25,
|
| 288 |
+
"learning_rate": 4.516537140791614e-06,
|
| 289 |
+
"loss": 0.0945,
|
| 290 |
+
"step": 23500
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 4.34,
|
| 294 |
+
"learning_rate": 3.974335803361649e-06,
|
| 295 |
+
"loss": 0.1156,
|
| 296 |
+
"step": 24000
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 4.43,
|
| 300 |
+
"learning_rate": 3.4321344659316826e-06,
|
| 301 |
+
"loss": 0.0965,
|
| 302 |
+
"step": 24500
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 4.52,
|
| 306 |
+
"learning_rate": 2.889933128501717e-06,
|
| 307 |
+
"loss": 0.1191,
|
| 308 |
+
"step": 25000
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 4.61,
|
| 312 |
+
"learning_rate": 2.3477317910717515e-06,
|
| 313 |
+
"loss": 0.0982,
|
| 314 |
+
"step": 25500
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 4.7,
|
| 318 |
+
"learning_rate": 1.8055304536417856e-06,
|
| 319 |
+
"loss": 0.1145,
|
| 320 |
+
"step": 26000
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 4.79,
|
| 324 |
+
"learning_rate": 1.26332911621182e-06,
|
| 325 |
+
"loss": 0.0894,
|
| 326 |
+
"step": 26500
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 4.88,
|
| 330 |
+
"learning_rate": 7.211277787818543e-07,
|
| 331 |
+
"loss": 0.0939,
|
| 332 |
+
"step": 27000
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 4.97,
|
| 336 |
+
"learning_rate": 1.7892644135188868e-07,
|
| 337 |
+
"loss": 0.0916,
|
| 338 |
+
"step": 27500
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 5.0,
|
| 342 |
+
"step": 27665,
|
| 343 |
+
"total_flos": 3.407082354156503e+17,
|
| 344 |
+
"train_runtime": 30959.6058,
|
| 345 |
+
"train_samples_per_second": 14.297,
|
| 346 |
+
"train_steps_per_second": 0.894
|
| 347 |
+
}
|
| 348 |
+
],
|
| 349 |
+
"max_steps": 27665,
|
| 350 |
+
"num_train_epochs": 5,
|
| 351 |
+
"total_flos": 3.407082354156503e+17,
|
| 352 |
+
"trial_name": null,
|
| 353 |
+
"trial_params": null
|
| 354 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7c436bbfc1550370b07f82d830f333d856df2bef9ecaf86cfc8d44ee6ea1db04
|
| 3 |
+
size 2479
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|