Upload 7 files
Browse files- config.json +27 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +357 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "bert-base-uncased",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"classifier_dropout": null,
|
| 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 |
+
"position_embedding_type": "absolute",
|
| 21 |
+
"problem_type": "single_label_classification",
|
| 22 |
+
"torch_dtype": "float32",
|
| 23 |
+
"transformers_version": "4.36.2",
|
| 24 |
+
"type_vocab_size": 2,
|
| 25 |
+
"use_cache": true,
|
| 26 |
+
"vocab_size": 30522
|
| 27 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e08f75a6274266fb804455db44b0927db949590a6e777601fa67ffdc1f8501f1
|
| 3 |
+
size 437958648
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:05da5e6a371dc397e04bbfc1d708b31f7302e076f183da1f879038c66b366a91
|
| 3 |
+
size 685336698
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8097bb570d39ce19b6bc88d32f36055efa0e6f16086f1579e9c893d9c1d36b94
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7e23bcf8635536032e6f45e37f42a66a9fc38887a82eb6af464f361047f08d58
|
| 3 |
+
size 1064
|
trainer_state.json
ADDED
|
@@ -0,0 +1,357 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 1.0,
|
| 3 |
+
"best_model_checkpoint": "./en_results/checkpoint-750",
|
| 4 |
+
"epoch": 9.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1350,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 1.0,
|
| 13 |
+
"eval_accuracy": 0.9925,
|
| 14 |
+
"eval_classification_report": {
|
| 15 |
+
"accuracy": 0.9925,
|
| 16 |
+
"macro avg": {
|
| 17 |
+
"f1-score": 0.9924995781012682,
|
| 18 |
+
"precision": 0.9926108374384237,
|
| 19 |
+
"recall": 0.9924999999999999,
|
| 20 |
+
"support": 800.0
|
| 21 |
+
},
|
| 22 |
+
"neural": {
|
| 23 |
+
"f1-score": 0.9924433249370278,
|
| 24 |
+
"precision": 1.0,
|
| 25 |
+
"recall": 0.985,
|
| 26 |
+
"support": 400.0
|
| 27 |
+
},
|
| 28 |
+
"real": {
|
| 29 |
+
"f1-score": 0.9925558312655086,
|
| 30 |
+
"precision": 0.9852216748768473,
|
| 31 |
+
"recall": 1.0,
|
| 32 |
+
"support": 400.0
|
| 33 |
+
},
|
| 34 |
+
"weighted avg": {
|
| 35 |
+
"f1-score": 0.9924995781012683,
|
| 36 |
+
"precision": 0.9926108374384236,
|
| 37 |
+
"recall": 0.9925,
|
| 38 |
+
"support": 800.0
|
| 39 |
+
}
|
| 40 |
+
},
|
| 41 |
+
"eval_loss": 0.033255234360694885,
|
| 42 |
+
"eval_runtime": 5.455,
|
| 43 |
+
"eval_samples_per_second": 146.653,
|
| 44 |
+
"eval_steps_per_second": 9.166,
|
| 45 |
+
"step": 150
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 2.0,
|
| 49 |
+
"eval_accuracy": 0.99875,
|
| 50 |
+
"eval_classification_report": {
|
| 51 |
+
"accuracy": 0.99875,
|
| 52 |
+
"macro avg": {
|
| 53 |
+
"f1-score": 0.9987499980468719,
|
| 54 |
+
"precision": 0.9987531172069826,
|
| 55 |
+
"recall": 0.99875,
|
| 56 |
+
"support": 800.0
|
| 57 |
+
},
|
| 58 |
+
"neural": {
|
| 59 |
+
"f1-score": 0.9987515605493134,
|
| 60 |
+
"precision": 0.9975062344139651,
|
| 61 |
+
"recall": 1.0,
|
| 62 |
+
"support": 400.0
|
| 63 |
+
},
|
| 64 |
+
"real": {
|
| 65 |
+
"f1-score": 0.9987484355444306,
|
| 66 |
+
"precision": 1.0,
|
| 67 |
+
"recall": 0.9975,
|
| 68 |
+
"support": 400.0
|
| 69 |
+
},
|
| 70 |
+
"weighted avg": {
|
| 71 |
+
"f1-score": 0.998749998046872,
|
| 72 |
+
"precision": 0.9987531172069825,
|
| 73 |
+
"recall": 0.99875,
|
| 74 |
+
"support": 800.0
|
| 75 |
+
}
|
| 76 |
+
},
|
| 77 |
+
"eval_loss": 0.004529090132564306,
|
| 78 |
+
"eval_runtime": 17.6229,
|
| 79 |
+
"eval_samples_per_second": 45.396,
|
| 80 |
+
"eval_steps_per_second": 2.837,
|
| 81 |
+
"step": 300
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 3.0,
|
| 85 |
+
"eval_accuracy": 0.9925,
|
| 86 |
+
"eval_classification_report": {
|
| 87 |
+
"accuracy": 0.9925,
|
| 88 |
+
"macro avg": {
|
| 89 |
+
"f1-score": 0.9924995781012682,
|
| 90 |
+
"precision": 0.9926108374384237,
|
| 91 |
+
"recall": 0.9924999999999999,
|
| 92 |
+
"support": 800.0
|
| 93 |
+
},
|
| 94 |
+
"neural": {
|
| 95 |
+
"f1-score": 0.9924433249370278,
|
| 96 |
+
"precision": 1.0,
|
| 97 |
+
"recall": 0.985,
|
| 98 |
+
"support": 400.0
|
| 99 |
+
},
|
| 100 |
+
"real": {
|
| 101 |
+
"f1-score": 0.9925558312655086,
|
| 102 |
+
"precision": 0.9852216748768473,
|
| 103 |
+
"recall": 1.0,
|
| 104 |
+
"support": 400.0
|
| 105 |
+
},
|
| 106 |
+
"weighted avg": {
|
| 107 |
+
"f1-score": 0.9924995781012683,
|
| 108 |
+
"precision": 0.9926108374384236,
|
| 109 |
+
"recall": 0.9925,
|
| 110 |
+
"support": 800.0
|
| 111 |
+
}
|
| 112 |
+
},
|
| 113 |
+
"eval_loss": 0.04066295549273491,
|
| 114 |
+
"eval_runtime": 18.5855,
|
| 115 |
+
"eval_samples_per_second": 43.044,
|
| 116 |
+
"eval_steps_per_second": 2.69,
|
| 117 |
+
"step": 450
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 3.33,
|
| 121 |
+
"learning_rate": 5e-05,
|
| 122 |
+
"loss": 0.1429,
|
| 123 |
+
"step": 500
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 4.0,
|
| 127 |
+
"eval_accuracy": 0.97875,
|
| 128 |
+
"eval_classification_report": {
|
| 129 |
+
"accuracy": 0.97875,
|
| 130 |
+
"macro avg": {
|
| 131 |
+
"f1-score": 0.9787403999618578,
|
| 132 |
+
"precision": 0.9796163069544365,
|
| 133 |
+
"recall": 0.97875,
|
| 134 |
+
"support": 800.0
|
| 135 |
+
},
|
| 136 |
+
"neural": {
|
| 137 |
+
"f1-score": 0.9782886334610472,
|
| 138 |
+
"precision": 1.0,
|
| 139 |
+
"recall": 0.9575,
|
| 140 |
+
"support": 400.0
|
| 141 |
+
},
|
| 142 |
+
"real": {
|
| 143 |
+
"f1-score": 0.9791921664626683,
|
| 144 |
+
"precision": 0.9592326139088729,
|
| 145 |
+
"recall": 1.0,
|
| 146 |
+
"support": 400.0
|
| 147 |
+
},
|
| 148 |
+
"weighted avg": {
|
| 149 |
+
"f1-score": 0.9787403999618579,
|
| 150 |
+
"precision": 0.9796163069544365,
|
| 151 |
+
"recall": 0.97875,
|
| 152 |
+
"support": 800.0
|
| 153 |
+
}
|
| 154 |
+
},
|
| 155 |
+
"eval_loss": 0.14006006717681885,
|
| 156 |
+
"eval_runtime": 37.5571,
|
| 157 |
+
"eval_samples_per_second": 21.301,
|
| 158 |
+
"eval_steps_per_second": 1.331,
|
| 159 |
+
"step": 600
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 5.0,
|
| 163 |
+
"eval_accuracy": 1.0,
|
| 164 |
+
"eval_classification_report": {
|
| 165 |
+
"accuracy": 1.0,
|
| 166 |
+
"macro avg": {
|
| 167 |
+
"f1-score": 1.0,
|
| 168 |
+
"precision": 1.0,
|
| 169 |
+
"recall": 1.0,
|
| 170 |
+
"support": 800.0
|
| 171 |
+
},
|
| 172 |
+
"neural": {
|
| 173 |
+
"f1-score": 1.0,
|
| 174 |
+
"precision": 1.0,
|
| 175 |
+
"recall": 1.0,
|
| 176 |
+
"support": 400.0
|
| 177 |
+
},
|
| 178 |
+
"real": {
|
| 179 |
+
"f1-score": 1.0,
|
| 180 |
+
"precision": 1.0,
|
| 181 |
+
"recall": 1.0,
|
| 182 |
+
"support": 400.0
|
| 183 |
+
},
|
| 184 |
+
"weighted avg": {
|
| 185 |
+
"f1-score": 1.0,
|
| 186 |
+
"precision": 1.0,
|
| 187 |
+
"recall": 1.0,
|
| 188 |
+
"support": 800.0
|
| 189 |
+
}
|
| 190 |
+
},
|
| 191 |
+
"eval_loss": 0.0003298004739917815,
|
| 192 |
+
"eval_runtime": 25.2571,
|
| 193 |
+
"eval_samples_per_second": 31.674,
|
| 194 |
+
"eval_steps_per_second": 1.98,
|
| 195 |
+
"step": 750
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 6.0,
|
| 199 |
+
"eval_accuracy": 1.0,
|
| 200 |
+
"eval_classification_report": {
|
| 201 |
+
"accuracy": 1.0,
|
| 202 |
+
"macro avg": {
|
| 203 |
+
"f1-score": 1.0,
|
| 204 |
+
"precision": 1.0,
|
| 205 |
+
"recall": 1.0,
|
| 206 |
+
"support": 800.0
|
| 207 |
+
},
|
| 208 |
+
"neural": {
|
| 209 |
+
"f1-score": 1.0,
|
| 210 |
+
"precision": 1.0,
|
| 211 |
+
"recall": 1.0,
|
| 212 |
+
"support": 400.0
|
| 213 |
+
},
|
| 214 |
+
"real": {
|
| 215 |
+
"f1-score": 1.0,
|
| 216 |
+
"precision": 1.0,
|
| 217 |
+
"recall": 1.0,
|
| 218 |
+
"support": 400.0
|
| 219 |
+
},
|
| 220 |
+
"weighted avg": {
|
| 221 |
+
"f1-score": 1.0,
|
| 222 |
+
"precision": 1.0,
|
| 223 |
+
"recall": 1.0,
|
| 224 |
+
"support": 800.0
|
| 225 |
+
}
|
| 226 |
+
},
|
| 227 |
+
"eval_loss": 8.567087206756696e-05,
|
| 228 |
+
"eval_runtime": 35.7288,
|
| 229 |
+
"eval_samples_per_second": 22.391,
|
| 230 |
+
"eval_steps_per_second": 1.399,
|
| 231 |
+
"step": 900
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 6.67,
|
| 235 |
+
"learning_rate": 4.827586206896552e-05,
|
| 236 |
+
"loss": 0.0134,
|
| 237 |
+
"step": 1000
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 7.0,
|
| 241 |
+
"eval_accuracy": 1.0,
|
| 242 |
+
"eval_classification_report": {
|
| 243 |
+
"accuracy": 1.0,
|
| 244 |
+
"macro avg": {
|
| 245 |
+
"f1-score": 1.0,
|
| 246 |
+
"precision": 1.0,
|
| 247 |
+
"recall": 1.0,
|
| 248 |
+
"support": 800.0
|
| 249 |
+
},
|
| 250 |
+
"neural": {
|
| 251 |
+
"f1-score": 1.0,
|
| 252 |
+
"precision": 1.0,
|
| 253 |
+
"recall": 1.0,
|
| 254 |
+
"support": 400.0
|
| 255 |
+
},
|
| 256 |
+
"real": {
|
| 257 |
+
"f1-score": 1.0,
|
| 258 |
+
"precision": 1.0,
|
| 259 |
+
"recall": 1.0,
|
| 260 |
+
"support": 400.0
|
| 261 |
+
},
|
| 262 |
+
"weighted avg": {
|
| 263 |
+
"f1-score": 1.0,
|
| 264 |
+
"precision": 1.0,
|
| 265 |
+
"recall": 1.0,
|
| 266 |
+
"support": 800.0
|
| 267 |
+
}
|
| 268 |
+
},
|
| 269 |
+
"eval_loss": 4.2337298509664834e-05,
|
| 270 |
+
"eval_runtime": 33.2322,
|
| 271 |
+
"eval_samples_per_second": 24.073,
|
| 272 |
+
"eval_steps_per_second": 1.505,
|
| 273 |
+
"step": 1050
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 8.0,
|
| 277 |
+
"eval_accuracy": 1.0,
|
| 278 |
+
"eval_classification_report": {
|
| 279 |
+
"accuracy": 1.0,
|
| 280 |
+
"macro avg": {
|
| 281 |
+
"f1-score": 1.0,
|
| 282 |
+
"precision": 1.0,
|
| 283 |
+
"recall": 1.0,
|
| 284 |
+
"support": 800.0
|
| 285 |
+
},
|
| 286 |
+
"neural": {
|
| 287 |
+
"f1-score": 1.0,
|
| 288 |
+
"precision": 1.0,
|
| 289 |
+
"recall": 1.0,
|
| 290 |
+
"support": 400.0
|
| 291 |
+
},
|
| 292 |
+
"real": {
|
| 293 |
+
"f1-score": 1.0,
|
| 294 |
+
"precision": 1.0,
|
| 295 |
+
"recall": 1.0,
|
| 296 |
+
"support": 400.0
|
| 297 |
+
},
|
| 298 |
+
"weighted avg": {
|
| 299 |
+
"f1-score": 1.0,
|
| 300 |
+
"precision": 1.0,
|
| 301 |
+
"recall": 1.0,
|
| 302 |
+
"support": 800.0
|
| 303 |
+
}
|
| 304 |
+
},
|
| 305 |
+
"eval_loss": 2.951826354546938e-05,
|
| 306 |
+
"eval_runtime": 34.6231,
|
| 307 |
+
"eval_samples_per_second": 23.106,
|
| 308 |
+
"eval_steps_per_second": 1.444,
|
| 309 |
+
"step": 1200
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 9.0,
|
| 313 |
+
"eval_accuracy": 1.0,
|
| 314 |
+
"eval_classification_report": {
|
| 315 |
+
"accuracy": 1.0,
|
| 316 |
+
"macro avg": {
|
| 317 |
+
"f1-score": 1.0,
|
| 318 |
+
"precision": 1.0,
|
| 319 |
+
"recall": 1.0,
|
| 320 |
+
"support": 800.0
|
| 321 |
+
},
|
| 322 |
+
"neural": {
|
| 323 |
+
"f1-score": 1.0,
|
| 324 |
+
"precision": 1.0,
|
| 325 |
+
"recall": 1.0,
|
| 326 |
+
"support": 400.0
|
| 327 |
+
},
|
| 328 |
+
"real": {
|
| 329 |
+
"f1-score": 1.0,
|
| 330 |
+
"precision": 1.0,
|
| 331 |
+
"recall": 1.0,
|
| 332 |
+
"support": 400.0
|
| 333 |
+
},
|
| 334 |
+
"weighted avg": {
|
| 335 |
+
"f1-score": 1.0,
|
| 336 |
+
"precision": 1.0,
|
| 337 |
+
"recall": 1.0,
|
| 338 |
+
"support": 800.0
|
| 339 |
+
}
|
| 340 |
+
},
|
| 341 |
+
"eval_loss": 2.2726077077095397e-05,
|
| 342 |
+
"eval_runtime": 24.0892,
|
| 343 |
+
"eval_samples_per_second": 33.21,
|
| 344 |
+
"eval_steps_per_second": 2.076,
|
| 345 |
+
"step": 1350
|
| 346 |
+
}
|
| 347 |
+
],
|
| 348 |
+
"logging_steps": 500,
|
| 349 |
+
"max_steps": 15000,
|
| 350 |
+
"num_input_tokens_seen": 0,
|
| 351 |
+
"num_train_epochs": 100,
|
| 352 |
+
"save_steps": 500,
|
| 353 |
+
"total_flos": 5683198795776000.0,
|
| 354 |
+
"train_batch_size": 16,
|
| 355 |
+
"trial_name": null,
|
| 356 |
+
"trial_params": null
|
| 357 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:168411abf1a1450fc9ae01ba8bb66204b999faf69da6dddbddf31aea9d627785
|
| 3 |
+
size 4664
|