Commit
·
5187cba
1
Parent(s):
ec9d271
Upload trainer_state.json with huggingface_hub
Browse files- trainer_state.json +301 -0
trainer_state.json
ADDED
|
@@ -0,0 +1,301 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 19.999384615384617,
|
| 5 |
+
"global_step": 8120,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 1.0,
|
| 12 |
+
"eval_accuracy": 0.9440000057220459,
|
| 13 |
+
"eval_loss": 0.185967355966568,
|
| 14 |
+
"eval_runtime": 3.2155,
|
| 15 |
+
"eval_samples_per_second": 155.495,
|
| 16 |
+
"eval_steps_per_second": 19.592,
|
| 17 |
+
"step": 406
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 1.23,
|
| 21 |
+
"learning_rate": 2.2079363472639895e-05,
|
| 22 |
+
"loss": 0.3271,
|
| 23 |
+
"step": 500
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 2.0,
|
| 27 |
+
"eval_accuracy": 0.9599999785423279,
|
| 28 |
+
"eval_loss": 0.1548820436000824,
|
| 29 |
+
"eval_runtime": 3.2405,
|
| 30 |
+
"eval_samples_per_second": 154.299,
|
| 31 |
+
"eval_steps_per_second": 19.442,
|
| 32 |
+
"step": 812
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 2.46,
|
| 36 |
+
"learning_rate": 2.0630586341889244e-05,
|
| 37 |
+
"loss": 0.1813,
|
| 38 |
+
"step": 1000
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 3.0,
|
| 42 |
+
"eval_accuracy": 0.9520000219345093,
|
| 43 |
+
"eval_loss": 0.18529100716114044,
|
| 44 |
+
"eval_runtime": 3.2782,
|
| 45 |
+
"eval_samples_per_second": 152.524,
|
| 46 |
+
"eval_steps_per_second": 19.218,
|
| 47 |
+
"step": 1218
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 3.69,
|
| 51 |
+
"learning_rate": 1.9181809211138593e-05,
|
| 52 |
+
"loss": 0.1331,
|
| 53 |
+
"step": 1500
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 4.0,
|
| 57 |
+
"eval_accuracy": 0.9580000042915344,
|
| 58 |
+
"eval_loss": 0.21402151882648468,
|
| 59 |
+
"eval_runtime": 3.387,
|
| 60 |
+
"eval_samples_per_second": 147.622,
|
| 61 |
+
"eval_steps_per_second": 18.6,
|
| 62 |
+
"step": 1624
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 4.93,
|
| 66 |
+
"learning_rate": 1.7733032080387945e-05,
|
| 67 |
+
"loss": 0.09,
|
| 68 |
+
"step": 2000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 5.0,
|
| 72 |
+
"eval_accuracy": 0.9520000219345093,
|
| 73 |
+
"eval_loss": 0.21573218703269958,
|
| 74 |
+
"eval_runtime": 3.3463,
|
| 75 |
+
"eval_samples_per_second": 149.417,
|
| 76 |
+
"eval_steps_per_second": 18.827,
|
| 77 |
+
"step": 2030
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 6.0,
|
| 81 |
+
"eval_accuracy": 0.9639999866485596,
|
| 82 |
+
"eval_loss": 0.19065596163272858,
|
| 83 |
+
"eval_runtime": 3.2501,
|
| 84 |
+
"eval_samples_per_second": 153.842,
|
| 85 |
+
"eval_steps_per_second": 19.384,
|
| 86 |
+
"step": 2436
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 6.16,
|
| 90 |
+
"learning_rate": 1.6284254949637297e-05,
|
| 91 |
+
"loss": 0.0675,
|
| 92 |
+
"step": 2500
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 7.0,
|
| 96 |
+
"eval_accuracy": 0.9459999799728394,
|
| 97 |
+
"eval_loss": 0.3131004273891449,
|
| 98 |
+
"eval_runtime": 3.2761,
|
| 99 |
+
"eval_samples_per_second": 152.622,
|
| 100 |
+
"eval_steps_per_second": 19.23,
|
| 101 |
+
"step": 2842
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 7.39,
|
| 105 |
+
"learning_rate": 1.4835477818886648e-05,
|
| 106 |
+
"loss": 0.0497,
|
| 107 |
+
"step": 3000
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 8.0,
|
| 111 |
+
"eval_accuracy": 0.9440000057220459,
|
| 112 |
+
"eval_loss": 0.3736623525619507,
|
| 113 |
+
"eval_runtime": 3.2136,
|
| 114 |
+
"eval_samples_per_second": 155.587,
|
| 115 |
+
"eval_steps_per_second": 19.604,
|
| 116 |
+
"step": 3248
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 8.62,
|
| 120 |
+
"learning_rate": 1.3386700688135999e-05,
|
| 121 |
+
"loss": 0.0423,
|
| 122 |
+
"step": 3500
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 9.0,
|
| 126 |
+
"eval_accuracy": 0.9520000219345093,
|
| 127 |
+
"eval_loss": 0.31935977935791016,
|
| 128 |
+
"eval_runtime": 3.2821,
|
| 129 |
+
"eval_samples_per_second": 152.343,
|
| 130 |
+
"eval_steps_per_second": 19.195,
|
| 131 |
+
"step": 3654
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 9.85,
|
| 135 |
+
"learning_rate": 1.193792355738535e-05,
|
| 136 |
+
"loss": 0.0332,
|
| 137 |
+
"step": 4000
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 10.0,
|
| 141 |
+
"eval_accuracy": 0.9580000042915344,
|
| 142 |
+
"eval_loss": 0.3113400340080261,
|
| 143 |
+
"eval_runtime": 3.3622,
|
| 144 |
+
"eval_samples_per_second": 148.714,
|
| 145 |
+
"eval_steps_per_second": 18.738,
|
| 146 |
+
"step": 4060
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 11.0,
|
| 150 |
+
"eval_accuracy": 0.9620000123977661,
|
| 151 |
+
"eval_loss": 0.29622161388397217,
|
| 152 |
+
"eval_runtime": 3.2804,
|
| 153 |
+
"eval_samples_per_second": 152.418,
|
| 154 |
+
"eval_steps_per_second": 19.205,
|
| 155 |
+
"step": 4466
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 11.08,
|
| 159 |
+
"learning_rate": 1.04891464266347e-05,
|
| 160 |
+
"loss": 0.0218,
|
| 161 |
+
"step": 4500
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 12.0,
|
| 165 |
+
"eval_accuracy": 0.9580000042915344,
|
| 166 |
+
"eval_loss": 0.337551087141037,
|
| 167 |
+
"eval_runtime": 3.3285,
|
| 168 |
+
"eval_samples_per_second": 150.217,
|
| 169 |
+
"eval_steps_per_second": 18.927,
|
| 170 |
+
"step": 4872
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 12.32,
|
| 174 |
+
"learning_rate": 9.04036929588405e-06,
|
| 175 |
+
"loss": 0.0207,
|
| 176 |
+
"step": 5000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 13.0,
|
| 180 |
+
"eval_accuracy": 0.9620000123977661,
|
| 181 |
+
"eval_loss": 0.338717520236969,
|
| 182 |
+
"eval_runtime": 3.1749,
|
| 183 |
+
"eval_samples_per_second": 157.484,
|
| 184 |
+
"eval_steps_per_second": 19.843,
|
| 185 |
+
"step": 5278
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 13.55,
|
| 189 |
+
"learning_rate": 7.5915921651334015e-06,
|
| 190 |
+
"loss": 0.0157,
|
| 191 |
+
"step": 5500
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 14.0,
|
| 195 |
+
"eval_accuracy": 0.9559999704360962,
|
| 196 |
+
"eval_loss": 0.3549070358276367,
|
| 197 |
+
"eval_runtime": 3.2845,
|
| 198 |
+
"eval_samples_per_second": 152.231,
|
| 199 |
+
"eval_steps_per_second": 19.181,
|
| 200 |
+
"step": 5684
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 14.78,
|
| 204 |
+
"learning_rate": 6.142815034382753e-06,
|
| 205 |
+
"loss": 0.0101,
|
| 206 |
+
"step": 6000
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 15.0,
|
| 210 |
+
"eval_accuracy": 0.9620000123977661,
|
| 211 |
+
"eval_loss": 0.3411114811897278,
|
| 212 |
+
"eval_runtime": 3.247,
|
| 213 |
+
"eval_samples_per_second": 153.988,
|
| 214 |
+
"eval_steps_per_second": 19.402,
|
| 215 |
+
"step": 6090
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 16.0,
|
| 219 |
+
"eval_accuracy": 0.9580000042915344,
|
| 220 |
+
"eval_loss": 0.40595561265945435,
|
| 221 |
+
"eval_runtime": 3.2347,
|
| 222 |
+
"eval_samples_per_second": 154.576,
|
| 223 |
+
"eval_steps_per_second": 19.477,
|
| 224 |
+
"step": 6496
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 16.01,
|
| 228 |
+
"learning_rate": 4.694037903632104e-06,
|
| 229 |
+
"loss": 0.0112,
|
| 230 |
+
"step": 6500
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 17.0,
|
| 234 |
+
"eval_accuracy": 0.9620000123977661,
|
| 235 |
+
"eval_loss": 0.3584845960140228,
|
| 236 |
+
"eval_runtime": 3.4061,
|
| 237 |
+
"eval_samples_per_second": 146.793,
|
| 238 |
+
"eval_steps_per_second": 18.496,
|
| 239 |
+
"step": 6902
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 17.24,
|
| 243 |
+
"learning_rate": 3.245260772881454e-06,
|
| 244 |
+
"loss": 0.0058,
|
| 245 |
+
"step": 7000
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 18.0,
|
| 249 |
+
"eval_accuracy": 0.9620000123977661,
|
| 250 |
+
"eval_loss": 0.3812974989414215,
|
| 251 |
+
"eval_runtime": 3.194,
|
| 252 |
+
"eval_samples_per_second": 156.545,
|
| 253 |
+
"eval_steps_per_second": 19.725,
|
| 254 |
+
"step": 7308
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 18.47,
|
| 258 |
+
"learning_rate": 1.796483642130805e-06,
|
| 259 |
+
"loss": 0.0043,
|
| 260 |
+
"step": 7500
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 19.0,
|
| 264 |
+
"eval_accuracy": 0.9660000205039978,
|
| 265 |
+
"eval_loss": 0.3624423146247864,
|
| 266 |
+
"eval_runtime": 3.2008,
|
| 267 |
+
"eval_samples_per_second": 156.209,
|
| 268 |
+
"eval_steps_per_second": 19.682,
|
| 269 |
+
"step": 7714
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 19.7,
|
| 273 |
+
"learning_rate": 3.477065113801558e-07,
|
| 274 |
+
"loss": 0.0019,
|
| 275 |
+
"step": 8000
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 20.0,
|
| 279 |
+
"eval_accuracy": 0.9660000205039978,
|
| 280 |
+
"eval_loss": 0.3639107644557953,
|
| 281 |
+
"eval_runtime": 3.2121,
|
| 282 |
+
"eval_samples_per_second": 155.662,
|
| 283 |
+
"eval_steps_per_second": 19.613,
|
| 284 |
+
"step": 8120
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 20.0,
|
| 288 |
+
"step": 8120,
|
| 289 |
+
"total_flos": 8550999537666048.0,
|
| 290 |
+
"train_loss": 0.06258585786290943,
|
| 291 |
+
"train_runtime": 5261.4565,
|
| 292 |
+
"train_samples_per_second": 24.708,
|
| 293 |
+
"train_steps_per_second": 1.543
|
| 294 |
+
}
|
| 295 |
+
],
|
| 296 |
+
"max_steps": 8120,
|
| 297 |
+
"num_train_epochs": 20,
|
| 298 |
+
"total_flos": 8550999537666048.0,
|
| 299 |
+
"trial_name": null,
|
| 300 |
+
"trial_params": null
|
| 301 |
+
}
|