Commit
•
4aae324
1
Parent(s):
bd9578a
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": 0.7493506493506493,
|
| 13 |
+
"eval_f1": 0.0,
|
| 14 |
+
"eval_loss": 2.0015974044799805,
|
| 15 |
+
"eval_precision": 0.0,
|
| 16 |
+
"eval_recall": 0.0,
|
| 17 |
+
"eval_runtime": 0.0742,
|
| 18 |
+
"eval_samples_per_second": 107.752,
|
| 19 |
+
"eval_steps_per_second": 13.469,
|
| 20 |
+
"step": 7
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 1.94,
|
| 24 |
+
"eval_accuracy": 0.7506493506493507,
|
| 25 |
+
"eval_f1": 0.0,
|
| 26 |
+
"eval_loss": 1.2346057891845703,
|
| 27 |
+
"eval_precision": 0.0,
|
| 28 |
+
"eval_recall": 0.0,
|
| 29 |
+
"eval_runtime": 0.0731,
|
| 30 |
+
"eval_samples_per_second": 109.424,
|
| 31 |
+
"eval_steps_per_second": 13.678,
|
| 32 |
+
"step": 15
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 2.97,
|
| 36 |
+
"eval_accuracy": 0.7506493506493507,
|
| 37 |
+
"eval_f1": 0.0,
|
| 38 |
+
"eval_loss": 1.0348587036132812,
|
| 39 |
+
"eval_precision": 0.0,
|
| 40 |
+
"eval_recall": 0.0,
|
| 41 |
+
"eval_runtime": 0.0828,
|
| 42 |
+
"eval_samples_per_second": 96.596,
|
| 43 |
+
"eval_steps_per_second": 12.074,
|
| 44 |
+
"step": 23
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 4.0,
|
| 48 |
+
"eval_accuracy": 0.7532467532467533,
|
| 49 |
+
"eval_f1": 0.0,
|
| 50 |
+
"eval_loss": 0.8629260659217834,
|
| 51 |
+
"eval_precision": 0.0,
|
| 52 |
+
"eval_recall": 0.0,
|
| 53 |
+
"eval_runtime": 0.0723,
|
| 54 |
+
"eval_samples_per_second": 110.649,
|
| 55 |
+
"eval_steps_per_second": 13.831,
|
| 56 |
+
"step": 31
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 4.9,
|
| 60 |
+
"eval_accuracy": 0.8064935064935065,
|
| 61 |
+
"eval_f1": 0.18965517241379312,
|
| 62 |
+
"eval_loss": 0.7592337727546692,
|
| 63 |
+
"eval_precision": 0.25,
|
| 64 |
+
"eval_recall": 0.1527777777777778,
|
| 65 |
+
"eval_runtime": 0.0625,
|
| 66 |
+
"eval_samples_per_second": 128.063,
|
| 67 |
+
"eval_steps_per_second": 16.008,
|
| 68 |
+
"step": 38
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 5.94,
|
| 72 |
+
"eval_accuracy": 0.8402597402597403,
|
| 73 |
+
"eval_f1": 0.3356643356643357,
|
| 74 |
+
"eval_loss": 0.6848217248916626,
|
| 75 |
+
"eval_precision": 0.3380281690140845,
|
| 76 |
+
"eval_recall": 0.3333333333333333,
|
| 77 |
+
"eval_runtime": 0.0632,
|
| 78 |
+
"eval_samples_per_second": 126.518,
|
| 79 |
+
"eval_steps_per_second": 15.815,
|
| 80 |
+
"step": 46
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 6.97,
|
| 84 |
+
"eval_accuracy": 0.8545454545454545,
|
| 85 |
+
"eval_f1": 0.4081632653061225,
|
| 86 |
+
"eval_loss": 0.6335278153419495,
|
| 87 |
+
"eval_precision": 0.4,
|
| 88 |
+
"eval_recall": 0.4166666666666667,
|
| 89 |
+
"eval_runtime": 0.058,
|
| 90 |
+
"eval_samples_per_second": 137.846,
|
| 91 |
+
"eval_steps_per_second": 17.231,
|
| 92 |
+
"step": 54
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 8.0,
|
| 96 |
+
"eval_accuracy": 0.861038961038961,
|
| 97 |
+
"eval_f1": 0.4697986577181208,
|
| 98 |
+
"eval_loss": 0.5917361974716187,
|
| 99 |
+
"eval_precision": 0.45454545454545453,
|
| 100 |
+
"eval_recall": 0.4861111111111111,
|
| 101 |
+
"eval_runtime": 0.0572,
|
| 102 |
+
"eval_samples_per_second": 139.965,
|
| 103 |
+
"eval_steps_per_second": 17.496,
|
| 104 |
+
"step": 62
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 8.9,
|
| 108 |
+
"eval_accuracy": 0.8727272727272727,
|
| 109 |
+
"eval_f1": 0.4966442953020133,
|
| 110 |
+
"eval_loss": 0.559086799621582,
|
| 111 |
+
"eval_precision": 0.4805194805194805,
|
| 112 |
+
"eval_recall": 0.5138888888888888,
|
| 113 |
+
"eval_runtime": 0.0653,
|
| 114 |
+
"eval_samples_per_second": 122.43,
|
| 115 |
+
"eval_steps_per_second": 15.304,
|
| 116 |
+
"step": 69
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 9.94,
|
| 120 |
+
"eval_accuracy": 0.8831168831168831,
|
| 121 |
+
"eval_f1": 0.5490196078431373,
|
| 122 |
+
"eval_loss": 0.5236128568649292,
|
| 123 |
+
"eval_precision": 0.5185185185185185,
|
| 124 |
+
"eval_recall": 0.5833333333333334,
|
| 125 |
+
"eval_runtime": 0.0798,
|
| 126 |
+
"eval_samples_per_second": 100.3,
|
| 127 |
+
"eval_steps_per_second": 12.537,
|
| 128 |
+
"step": 77
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 10.97,
|
| 132 |
+
"eval_accuracy": 0.8935064935064935,
|
| 133 |
+
"eval_f1": 0.5866666666666667,
|
| 134 |
+
"eval_loss": 0.49883803725242615,
|
| 135 |
+
"eval_precision": 0.5641025641025641,
|
| 136 |
+
"eval_recall": 0.6111111111111112,
|
| 137 |
+
"eval_runtime": 0.082,
|
| 138 |
+
"eval_samples_per_second": 97.527,
|
| 139 |
+
"eval_steps_per_second": 12.191,
|
| 140 |
+
"step": 85
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 12.0,
|
| 144 |
+
"eval_accuracy": 0.8935064935064935,
|
| 145 |
+
"eval_f1": 0.5605095541401275,
|
| 146 |
+
"eval_loss": 0.4820162355899811,
|
| 147 |
+
"eval_precision": 0.5176470588235295,
|
| 148 |
+
"eval_recall": 0.6111111111111112,
|
| 149 |
+
"eval_runtime": 0.0889,
|
| 150 |
+
"eval_samples_per_second": 90.026,
|
| 151 |
+
"eval_steps_per_second": 11.253,
|
| 152 |
+
"step": 93
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 12.9,
|
| 156 |
+
"eval_accuracy": 0.8935064935064935,
|
| 157 |
+
"eval_f1": 0.576923076923077,
|
| 158 |
+
"eval_loss": 0.4691239893436432,
|
| 159 |
+
"eval_precision": 0.5357142857142857,
|
| 160 |
+
"eval_recall": 0.625,
|
| 161 |
+
"eval_runtime": 0.1004,
|
| 162 |
+
"eval_samples_per_second": 79.701,
|
| 163 |
+
"eval_steps_per_second": 9.963,
|
| 164 |
+
"step": 100
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 13.94,
|
| 168 |
+
"eval_accuracy": 0.8961038961038961,
|
| 169 |
+
"eval_f1": 0.5859872611464968,
|
| 170 |
+
"eval_loss": 0.4579147398471832,
|
| 171 |
+
"eval_precision": 0.5411764705882353,
|
| 172 |
+
"eval_recall": 0.6388888888888888,
|
| 173 |
+
"eval_runtime": 0.0904,
|
| 174 |
+
"eval_samples_per_second": 88.539,
|
| 175 |
+
"eval_steps_per_second": 11.067,
|
| 176 |
+
"step": 108
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 14.97,
|
| 180 |
+
"eval_accuracy": 0.9012987012987013,
|
| 181 |
+
"eval_f1": 0.5874999999999999,
|
| 182 |
+
"eval_loss": 0.44733989238739014,
|
| 183 |
+
"eval_precision": 0.5340909090909091,
|
| 184 |
+
"eval_recall": 0.6527777777777778,
|
| 185 |
+
"eval_runtime": 0.0796,
|
| 186 |
+
"eval_samples_per_second": 100.53,
|
| 187 |
+
"eval_steps_per_second": 12.566,
|
| 188 |
+
"step": 116
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 16.0,
|
| 192 |
+
"eval_accuracy": 0.9,
|
| 193 |
+
"eval_f1": 0.5822784810126581,
|
| 194 |
+
"eval_loss": 0.44305217266082764,
|
| 195 |
+
"eval_precision": 0.5348837209302325,
|
| 196 |
+
"eval_recall": 0.6388888888888888,
|
| 197 |
+
"eval_runtime": 0.0612,
|
| 198 |
+
"eval_samples_per_second": 130.641,
|
| 199 |
+
"eval_steps_per_second": 16.33,
|
| 200 |
+
"step": 124
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 16.9,
|
| 204 |
+
"eval_accuracy": 0.9,
|
| 205 |
+
"eval_f1": 0.5822784810126581,
|
| 206 |
+
"eval_loss": 0.442893922328949,
|
| 207 |
+
"eval_precision": 0.5348837209302325,
|
| 208 |
+
"eval_recall": 0.6388888888888888,
|
| 209 |
+
"eval_runtime": 0.0713,
|
| 210 |
+
"eval_samples_per_second": 112.198,
|
| 211 |
+
"eval_steps_per_second": 14.025,
|
| 212 |
+
"step": 131
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 17.94,
|
| 216 |
+
"eval_accuracy": 0.8987012987012987,
|
| 217 |
+
"eval_f1": 0.5732484076433121,
|
| 218 |
+
"eval_loss": 0.4412069320678711,
|
| 219 |
+
"eval_precision": 0.5294117647058824,
|
| 220 |
+
"eval_recall": 0.625,
|
| 221 |
+
"eval_runtime": 0.0835,
|
| 222 |
+
"eval_samples_per_second": 95.82,
|
| 223 |
+
"eval_steps_per_second": 11.977,
|
| 224 |
+
"step": 139
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 18.06,
|
| 228 |
+
"eval_accuracy": 0.8987012987012987,
|
| 229 |
+
"eval_f1": 0.5732484076433121,
|
| 230 |
+
"eval_loss": 0.4411640167236328,
|
| 231 |
+
"eval_precision": 0.5294117647058824,
|
| 232 |
+
"eval_recall": 0.625,
|
| 233 |
+
"eval_runtime": 0.0624,
|
| 234 |
+
"eval_samples_per_second": 128.169,
|
| 235 |
+
"eval_steps_per_second": 16.021,
|
| 236 |
+
"step": 140
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 18.06,
|
| 240 |
+
"step": 140,
|
| 241 |
+
"total_flos": 142786456035984.0,
|
| 242 |
+
"train_loss": 0.6083726610456194,
|
| 243 |
+
"train_runtime": 458.469,
|
| 244 |
+
"train_samples_per_second": 5.278,
|
| 245 |
+
"train_steps_per_second": 0.305
|
| 246 |
+
}
|
| 247 |
+
],
|
| 248 |
+
"max_steps": 140,
|
| 249 |
+
"num_train_epochs": 20,
|
| 250 |
+
"total_flos": 142786456035984.0,
|
| 251 |
+
"trial_name": null,
|
| 252 |
+
"trial_params": null
|
| 253 |
+
}
|