Commit
•
d604e21
1
Parent(s):
7a87043
Upload trainer_state.json with huggingface_hub
Browse files- trainer_state.json +253 -0
trainer_state.json
ADDED
|
@@ -0,0 +1,253 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 18.06451612903226,
|
| 5 |
+
"global_step": 140,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.9,
|
| 12 |
+
"eval_accuracy": 0.7258883248730964,
|
| 13 |
+
"eval_f1": 0.0,
|
| 14 |
+
"eval_loss": 1.5211623907089233,
|
| 15 |
+
"eval_precision": 0.0,
|
| 16 |
+
"eval_recall": 0.0,
|
| 17 |
+
"eval_runtime": 0.0934,
|
| 18 |
+
"eval_samples_per_second": 85.695,
|
| 19 |
+
"eval_steps_per_second": 10.712,
|
| 20 |
+
"step": 7
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 1.94,
|
| 24 |
+
"eval_accuracy": 0.7326565143824028,
|
| 25 |
+
"eval_f1": 0.0,
|
| 26 |
+
"eval_loss": 1.0808664560317993,
|
| 27 |
+
"eval_precision": 0.0,
|
| 28 |
+
"eval_recall": 0.0,
|
| 29 |
+
"eval_runtime": 0.075,
|
| 30 |
+
"eval_samples_per_second": 106.603,
|
| 31 |
+
"eval_steps_per_second": 13.325,
|
| 32 |
+
"step": 15
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 2.97,
|
| 36 |
+
"eval_accuracy": 0.7681895093062606,
|
| 37 |
+
"eval_f1": 0.17142857142857143,
|
| 38 |
+
"eval_loss": 0.902431309223175,
|
| 39 |
+
"eval_precision": 0.2,
|
| 40 |
+
"eval_recall": 0.15,
|
| 41 |
+
"eval_runtime": 0.0865,
|
| 42 |
+
"eval_samples_per_second": 92.481,
|
| 43 |
+
"eval_steps_per_second": 11.56,
|
| 44 |
+
"step": 23
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 4.0,
|
| 48 |
+
"eval_accuracy": 0.7969543147208121,
|
| 49 |
+
"eval_f1": 0.2518518518518518,
|
| 50 |
+
"eval_loss": 0.7922185063362122,
|
| 51 |
+
"eval_precision": 0.22666666666666666,
|
| 52 |
+
"eval_recall": 0.2833333333333333,
|
| 53 |
+
"eval_runtime": 0.0722,
|
| 54 |
+
"eval_samples_per_second": 110.797,
|
| 55 |
+
"eval_steps_per_second": 13.85,
|
| 56 |
+
"step": 31
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 4.9,
|
| 60 |
+
"eval_accuracy": 0.8155668358714044,
|
| 61 |
+
"eval_f1": 0.32876712328767127,
|
| 62 |
+
"eval_loss": 0.7233745455741882,
|
| 63 |
+
"eval_precision": 0.27906976744186046,
|
| 64 |
+
"eval_recall": 0.4,
|
| 65 |
+
"eval_runtime": 0.0672,
|
| 66 |
+
"eval_samples_per_second": 118.965,
|
| 67 |
+
"eval_steps_per_second": 14.871,
|
| 68 |
+
"step": 38
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 5.94,
|
| 72 |
+
"eval_accuracy": 0.8358714043993232,
|
| 73 |
+
"eval_f1": 0.4305555555555556,
|
| 74 |
+
"eval_loss": 0.6560729146003723,
|
| 75 |
+
"eval_precision": 0.36904761904761907,
|
| 76 |
+
"eval_recall": 0.5166666666666667,
|
| 77 |
+
"eval_runtime": 0.0878,
|
| 78 |
+
"eval_samples_per_second": 91.083,
|
| 79 |
+
"eval_steps_per_second": 11.385,
|
| 80 |
+
"step": 46
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 6.97,
|
| 84 |
+
"eval_accuracy": 0.8443316412859561,
|
| 85 |
+
"eval_f1": 0.4347826086956522,
|
| 86 |
+
"eval_loss": 0.626990795135498,
|
| 87 |
+
"eval_precision": 0.38461538461538464,
|
| 88 |
+
"eval_recall": 0.5,
|
| 89 |
+
"eval_runtime": 0.0846,
|
| 90 |
+
"eval_samples_per_second": 94.599,
|
| 91 |
+
"eval_steps_per_second": 11.825,
|
| 92 |
+
"step": 54
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 8.0,
|
| 96 |
+
"eval_accuracy": 0.8494077834179357,
|
| 97 |
+
"eval_f1": 0.48951048951048953,
|
| 98 |
+
"eval_loss": 0.5750179886817932,
|
| 99 |
+
"eval_precision": 0.42168674698795183,
|
| 100 |
+
"eval_recall": 0.5833333333333334,
|
| 101 |
+
"eval_runtime": 0.0711,
|
| 102 |
+
"eval_samples_per_second": 112.546,
|
| 103 |
+
"eval_steps_per_second": 14.068,
|
| 104 |
+
"step": 62
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 8.9,
|
| 108 |
+
"eval_accuracy": 0.8595600676818951,
|
| 109 |
+
"eval_f1": 0.5109489051094891,
|
| 110 |
+
"eval_loss": 0.5483719110488892,
|
| 111 |
+
"eval_precision": 0.45454545454545453,
|
| 112 |
+
"eval_recall": 0.5833333333333334,
|
| 113 |
+
"eval_runtime": 0.104,
|
| 114 |
+
"eval_samples_per_second": 76.947,
|
| 115 |
+
"eval_steps_per_second": 9.618,
|
| 116 |
+
"step": 69
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 9.94,
|
| 120 |
+
"eval_accuracy": 0.8629441624365483,
|
| 121 |
+
"eval_f1": 0.5285714285714286,
|
| 122 |
+
"eval_loss": 0.5253370404243469,
|
| 123 |
+
"eval_precision": 0.4625,
|
| 124 |
+
"eval_recall": 0.6166666666666667,
|
| 125 |
+
"eval_runtime": 0.0872,
|
| 126 |
+
"eval_samples_per_second": 91.721,
|
| 127 |
+
"eval_steps_per_second": 11.465,
|
| 128 |
+
"step": 77
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 10.97,
|
| 132 |
+
"eval_accuracy": 0.868020304568528,
|
| 133 |
+
"eval_f1": 0.5179856115107914,
|
| 134 |
+
"eval_loss": 0.5097917914390564,
|
| 135 |
+
"eval_precision": 0.45569620253164556,
|
| 136 |
+
"eval_recall": 0.6,
|
| 137 |
+
"eval_runtime": 0.0862,
|
| 138 |
+
"eval_samples_per_second": 92.832,
|
| 139 |
+
"eval_steps_per_second": 11.604,
|
| 140 |
+
"step": 85
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 12.0,
|
| 144 |
+
"eval_accuracy": 0.8781725888324873,
|
| 145 |
+
"eval_f1": 0.5547445255474452,
|
| 146 |
+
"eval_loss": 0.49227389693260193,
|
| 147 |
+
"eval_precision": 0.4935064935064935,
|
| 148 |
+
"eval_recall": 0.6333333333333333,
|
| 149 |
+
"eval_runtime": 0.0683,
|
| 150 |
+
"eval_samples_per_second": 117.18,
|
| 151 |
+
"eval_steps_per_second": 14.647,
|
| 152 |
+
"step": 93
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 12.9,
|
| 156 |
+
"eval_accuracy": 0.868020304568528,
|
| 157 |
+
"eval_f1": 0.5294117647058824,
|
| 158 |
+
"eval_loss": 0.49868977069854736,
|
| 159 |
+
"eval_precision": 0.47368421052631576,
|
| 160 |
+
"eval_recall": 0.6,
|
| 161 |
+
"eval_runtime": 0.0863,
|
| 162 |
+
"eval_samples_per_second": 92.658,
|
| 163 |
+
"eval_steps_per_second": 11.582,
|
| 164 |
+
"step": 100
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 13.94,
|
| 168 |
+
"eval_accuracy": 0.871404399323181,
|
| 169 |
+
"eval_f1": 0.5652173913043479,
|
| 170 |
+
"eval_loss": 0.5003769397735596,
|
| 171 |
+
"eval_precision": 0.5,
|
| 172 |
+
"eval_recall": 0.65,
|
| 173 |
+
"eval_runtime": 0.0861,
|
| 174 |
+
"eval_samples_per_second": 92.934,
|
| 175 |
+
"eval_steps_per_second": 11.617,
|
| 176 |
+
"step": 108
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 14.97,
|
| 180 |
+
"eval_accuracy": 0.8815566835871405,
|
| 181 |
+
"eval_f1": 0.5588235294117647,
|
| 182 |
+
"eval_loss": 0.48066699504852295,
|
| 183 |
+
"eval_precision": 0.5,
|
| 184 |
+
"eval_recall": 0.6333333333333333,
|
| 185 |
+
"eval_runtime": 0.073,
|
| 186 |
+
"eval_samples_per_second": 109.637,
|
| 187 |
+
"eval_steps_per_second": 13.705,
|
| 188 |
+
"step": 116
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 16.0,
|
| 192 |
+
"eval_accuracy": 0.8798646362098139,
|
| 193 |
+
"eval_f1": 0.5481481481481482,
|
| 194 |
+
"eval_loss": 0.48719707131385803,
|
| 195 |
+
"eval_precision": 0.49333333333333335,
|
| 196 |
+
"eval_recall": 0.6166666666666667,
|
| 197 |
+
"eval_runtime": 0.0729,
|
| 198 |
+
"eval_samples_per_second": 109.707,
|
| 199 |
+
"eval_steps_per_second": 13.713,
|
| 200 |
+
"step": 124
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 16.9,
|
| 204 |
+
"eval_accuracy": 0.8866328257191202,
|
| 205 |
+
"eval_f1": 0.6029411764705882,
|
| 206 |
+
"eval_loss": 0.48052239418029785,
|
| 207 |
+
"eval_precision": 0.5394736842105263,
|
| 208 |
+
"eval_recall": 0.6833333333333333,
|
| 209 |
+
"eval_runtime": 0.0836,
|
| 210 |
+
"eval_samples_per_second": 95.684,
|
| 211 |
+
"eval_steps_per_second": 11.96,
|
| 212 |
+
"step": 131
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 17.94,
|
| 216 |
+
"eval_accuracy": 0.8866328257191202,
|
| 217 |
+
"eval_f1": 0.5882352941176471,
|
| 218 |
+
"eval_loss": 0.48192963004112244,
|
| 219 |
+
"eval_precision": 0.5263157894736842,
|
| 220 |
+
"eval_recall": 0.6666666666666666,
|
| 221 |
+
"eval_runtime": 0.0874,
|
| 222 |
+
"eval_samples_per_second": 91.531,
|
| 223 |
+
"eval_steps_per_second": 11.441,
|
| 224 |
+
"step": 139
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 18.06,
|
| 228 |
+
"eval_accuracy": 0.8866328257191202,
|
| 229 |
+
"eval_f1": 0.5882352941176471,
|
| 230 |
+
"eval_loss": 0.48198172450065613,
|
| 231 |
+
"eval_precision": 0.5263157894736842,
|
| 232 |
+
"eval_recall": 0.6666666666666666,
|
| 233 |
+
"eval_runtime": 0.0703,
|
| 234 |
+
"eval_samples_per_second": 113.867,
|
| 235 |
+
"eval_steps_per_second": 14.233,
|
| 236 |
+
"step": 140
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 18.06,
|
| 240 |
+
"step": 140,
|
| 241 |
+
"total_flos": 142825785914880.0,
|
| 242 |
+
"train_loss": 0.5361384800502232,
|
| 243 |
+
"train_runtime": 994.5385,
|
| 244 |
+
"train_samples_per_second": 2.433,
|
| 245 |
+
"train_steps_per_second": 0.141
|
| 246 |
+
}
|
| 247 |
+
],
|
| 248 |
+
"max_steps": 140,
|
| 249 |
+
"num_train_epochs": 20,
|
| 250 |
+
"total_flos": 142825785914880.0,
|
| 251 |
+
"trial_name": null,
|
| 252 |
+
"trial_params": null
|
| 253 |
+
}
|