Commit
•
24ebd86
1
Parent(s):
3a50343
Added files
Browse files- config.json +30 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- trainer_state.json +360 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "UBC-NLP/MARBERT",
|
| 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": 100000
|
| 30 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8667c6d1cce7439c7e5617729c973d341c0787cd72911d1e462263bda83e1eb3
|
| 3 |
+
size 1303669859
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d8043d989d1925377fa06cef574d7e0d7ea83a8f753527412f8ea2284b7dda83
|
| 3 |
+
size 651861714
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:168f2977615e20afb1beaa2d89e12cdcb41d6587b8985716c2123b1516b7f707
|
| 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": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "do_basic_tokenize": true, "never_split": null, "special_tokens_map_file": null, "name_or_path": "UBC-NLP/MARBERT"}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,360 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 20.0,
|
| 5 |
+
"global_step": 17200,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.58,
|
| 12 |
+
"learning_rate": 4.854651162790698e-05,
|
| 13 |
+
"loss": 3.572,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 1.0,
|
| 18 |
+
"eval_loss": 3.3753416538238525,
|
| 19 |
+
"eval_runtime": 146.7285,
|
| 20 |
+
"eval_samples_per_second": 163.69,
|
| 21 |
+
"step": 860
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 1.16,
|
| 25 |
+
"learning_rate": 4.709302325581396e-05,
|
| 26 |
+
"loss": 3.4691,
|
| 27 |
+
"step": 1000
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 1.74,
|
| 31 |
+
"learning_rate": 4.563953488372093e-05,
|
| 32 |
+
"loss": 3.2751,
|
| 33 |
+
"step": 1500
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 2.0,
|
| 37 |
+
"eval_loss": 3.3520445823669434,
|
| 38 |
+
"eval_runtime": 147.0097,
|
| 39 |
+
"eval_samples_per_second": 163.377,
|
| 40 |
+
"step": 1720
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"epoch": 2.33,
|
| 44 |
+
"learning_rate": 4.418604651162791e-05,
|
| 45 |
+
"loss": 3.1479,
|
| 46 |
+
"step": 2000
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 2.91,
|
| 50 |
+
"learning_rate": 4.2732558139534885e-05,
|
| 51 |
+
"loss": 3.0201,
|
| 52 |
+
"step": 2500
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 3.0,
|
| 56 |
+
"eval_loss": 3.3326475620269775,
|
| 57 |
+
"eval_runtime": 146.9025,
|
| 58 |
+
"eval_samples_per_second": 163.496,
|
| 59 |
+
"step": 2580
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 3.49,
|
| 63 |
+
"learning_rate": 4.127906976744187e-05,
|
| 64 |
+
"loss": 2.8872,
|
| 65 |
+
"step": 3000
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 4.0,
|
| 69 |
+
"eval_loss": 3.355100154876709,
|
| 70 |
+
"eval_runtime": 146.8556,
|
| 71 |
+
"eval_samples_per_second": 163.548,
|
| 72 |
+
"step": 3440
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 4.07,
|
| 76 |
+
"learning_rate": 3.9825581395348835e-05,
|
| 77 |
+
"loss": 2.8373,
|
| 78 |
+
"step": 3500
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 4.65,
|
| 82 |
+
"learning_rate": 3.837209302325582e-05,
|
| 83 |
+
"loss": 2.6775,
|
| 84 |
+
"step": 4000
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 5.0,
|
| 88 |
+
"eval_loss": 3.35534405708313,
|
| 89 |
+
"eval_runtime": 146.787,
|
| 90 |
+
"eval_samples_per_second": 163.625,
|
| 91 |
+
"step": 4300
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 5.23,
|
| 95 |
+
"learning_rate": 3.691860465116279e-05,
|
| 96 |
+
"loss": 2.6133,
|
| 97 |
+
"step": 4500
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 5.81,
|
| 101 |
+
"learning_rate": 3.5465116279069774e-05,
|
| 102 |
+
"loss": 2.5406,
|
| 103 |
+
"step": 5000
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"epoch": 6.0,
|
| 107 |
+
"eval_loss": 3.336427927017212,
|
| 108 |
+
"eval_runtime": 146.5342,
|
| 109 |
+
"eval_samples_per_second": 163.907,
|
| 110 |
+
"step": 5160
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 6.4,
|
| 114 |
+
"learning_rate": 3.401162790697674e-05,
|
| 115 |
+
"loss": 2.4318,
|
| 116 |
+
"step": 5500
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 6.98,
|
| 120 |
+
"learning_rate": 3.2558139534883724e-05,
|
| 121 |
+
"loss": 2.4171,
|
| 122 |
+
"step": 6000
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 7.0,
|
| 126 |
+
"eval_loss": 3.332899808883667,
|
| 127 |
+
"eval_runtime": 146.7159,
|
| 128 |
+
"eval_samples_per_second": 163.704,
|
| 129 |
+
"step": 6020
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 7.56,
|
| 133 |
+
"learning_rate": 3.11046511627907e-05,
|
| 134 |
+
"loss": 2.267,
|
| 135 |
+
"step": 6500
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 8.0,
|
| 139 |
+
"eval_loss": 3.3342535495758057,
|
| 140 |
+
"eval_runtime": 146.2923,
|
| 141 |
+
"eval_samples_per_second": 164.178,
|
| 142 |
+
"step": 6880
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 8.14,
|
| 146 |
+
"learning_rate": 2.9651162790697678e-05,
|
| 147 |
+
"loss": 2.232,
|
| 148 |
+
"step": 7000
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 8.72,
|
| 152 |
+
"learning_rate": 2.8197674418604653e-05,
|
| 153 |
+
"loss": 2.1545,
|
| 154 |
+
"step": 7500
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 9.0,
|
| 158 |
+
"eval_loss": 3.3147542476654053,
|
| 159 |
+
"eval_runtime": 147.8917,
|
| 160 |
+
"eval_samples_per_second": 162.403,
|
| 161 |
+
"step": 7740
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 9.3,
|
| 165 |
+
"learning_rate": 2.674418604651163e-05,
|
| 166 |
+
"loss": 2.1127,
|
| 167 |
+
"step": 8000
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 9.88,
|
| 171 |
+
"learning_rate": 2.5290697674418607e-05,
|
| 172 |
+
"loss": 2.064,
|
| 173 |
+
"step": 8500
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 10.0,
|
| 177 |
+
"eval_loss": 3.3158812522888184,
|
| 178 |
+
"eval_runtime": 147.2862,
|
| 179 |
+
"eval_samples_per_second": 163.07,
|
| 180 |
+
"step": 8600
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 10.47,
|
| 184 |
+
"learning_rate": 2.3837209302325582e-05,
|
| 185 |
+
"loss": 1.9663,
|
| 186 |
+
"step": 9000
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 11.0,
|
| 190 |
+
"eval_loss": 3.3465089797973633,
|
| 191 |
+
"eval_runtime": 148.1203,
|
| 192 |
+
"eval_samples_per_second": 162.152,
|
| 193 |
+
"step": 9460
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 11.05,
|
| 197 |
+
"learning_rate": 2.238372093023256e-05,
|
| 198 |
+
"loss": 1.9353,
|
| 199 |
+
"step": 9500
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 11.63,
|
| 203 |
+
"learning_rate": 2.0930232558139536e-05,
|
| 204 |
+
"loss": 1.8572,
|
| 205 |
+
"step": 10000
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 12.0,
|
| 209 |
+
"eval_loss": 3.2874529361724854,
|
| 210 |
+
"eval_runtime": 147.3935,
|
| 211 |
+
"eval_samples_per_second": 162.952,
|
| 212 |
+
"step": 10320
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 12.21,
|
| 216 |
+
"learning_rate": 1.9476744186046514e-05,
|
| 217 |
+
"loss": 1.8373,
|
| 218 |
+
"step": 10500
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 12.79,
|
| 222 |
+
"learning_rate": 1.802325581395349e-05,
|
| 223 |
+
"loss": 1.7866,
|
| 224 |
+
"step": 11000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 13.0,
|
| 228 |
+
"eval_loss": 3.321674108505249,
|
| 229 |
+
"eval_runtime": 146.9637,
|
| 230 |
+
"eval_samples_per_second": 163.428,
|
| 231 |
+
"step": 11180
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 13.37,
|
| 235 |
+
"learning_rate": 1.6569767441860464e-05,
|
| 236 |
+
"loss": 1.7253,
|
| 237 |
+
"step": 11500
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 13.95,
|
| 241 |
+
"learning_rate": 1.5116279069767441e-05,
|
| 242 |
+
"loss": 1.719,
|
| 243 |
+
"step": 12000
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 14.0,
|
| 247 |
+
"eval_loss": 3.2760589122772217,
|
| 248 |
+
"eval_runtime": 145.6136,
|
| 249 |
+
"eval_samples_per_second": 164.943,
|
| 250 |
+
"step": 12040
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 14.53,
|
| 254 |
+
"learning_rate": 1.3662790697674418e-05,
|
| 255 |
+
"loss": 1.6293,
|
| 256 |
+
"step": 12500
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 15.0,
|
| 260 |
+
"eval_loss": 3.302276611328125,
|
| 261 |
+
"eval_runtime": 146.2216,
|
| 262 |
+
"eval_samples_per_second": 164.258,
|
| 263 |
+
"step": 12900
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 15.12,
|
| 267 |
+
"learning_rate": 1.2209302325581395e-05,
|
| 268 |
+
"loss": 1.6339,
|
| 269 |
+
"step": 13000
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 15.7,
|
| 273 |
+
"learning_rate": 1.0755813953488372e-05,
|
| 274 |
+
"loss": 1.5656,
|
| 275 |
+
"step": 13500
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 16.0,
|
| 279 |
+
"eval_loss": 3.2689430713653564,
|
| 280 |
+
"eval_runtime": 145.5127,
|
| 281 |
+
"eval_samples_per_second": 165.058,
|
| 282 |
+
"step": 13760
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 16.28,
|
| 286 |
+
"learning_rate": 9.302325581395349e-06,
|
| 287 |
+
"loss": 1.5503,
|
| 288 |
+
"step": 14000
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 16.86,
|
| 292 |
+
"learning_rate": 7.848837209302325e-06,
|
| 293 |
+
"loss": 1.5344,
|
| 294 |
+
"step": 14500
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 17.0,
|
| 298 |
+
"eval_loss": 3.237142562866211,
|
| 299 |
+
"eval_runtime": 146.4021,
|
| 300 |
+
"eval_samples_per_second": 164.055,
|
| 301 |
+
"step": 14620
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 17.44,
|
| 305 |
+
"learning_rate": 6.395348837209303e-06,
|
| 306 |
+
"loss": 1.4974,
|
| 307 |
+
"step": 15000
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 18.0,
|
| 311 |
+
"eval_loss": 3.209892749786377,
|
| 312 |
+
"eval_runtime": 147.2158,
|
| 313 |
+
"eval_samples_per_second": 163.148,
|
| 314 |
+
"step": 15480
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 18.02,
|
| 318 |
+
"learning_rate": 4.941860465116279e-06,
|
| 319 |
+
"loss": 1.4739,
|
| 320 |
+
"step": 15500
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 18.6,
|
| 324 |
+
"learning_rate": 3.488372093023256e-06,
|
| 325 |
+
"loss": 1.4574,
|
| 326 |
+
"step": 16000
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 19.0,
|
| 330 |
+
"eval_loss": 3.2351009845733643,
|
| 331 |
+
"eval_runtime": 146.7384,
|
| 332 |
+
"eval_samples_per_second": 163.679,
|
| 333 |
+
"step": 16340
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 19.19,
|
| 337 |
+
"learning_rate": 2.0348837209302328e-06,
|
| 338 |
+
"loss": 1.4283,
|
| 339 |
+
"step": 16500
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 19.77,
|
| 343 |
+
"learning_rate": 5.813953488372093e-07,
|
| 344 |
+
"loss": 1.4204,
|
| 345 |
+
"step": 17000
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 20.0,
|
| 349 |
+
"eval_loss": 3.2112162113189697,
|
| 350 |
+
"eval_runtime": 147.2288,
|
| 351 |
+
"eval_samples_per_second": 163.134,
|
| 352 |
+
"step": 17200
|
| 353 |
+
}
|
| 354 |
+
],
|
| 355 |
+
"max_steps": 17200,
|
| 356 |
+
"num_train_epochs": 20,
|
| 357 |
+
"total_flos": 6.8827072512e+16,
|
| 358 |
+
"trial_name": null,
|
| 359 |
+
"trial_params": null
|
| 360 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2228a7d58ab4a59c8b8432e8dee6d0f33970fcaf9a8320173aff80a4368584d3
|
| 3 |
+
size 2351
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|