End of training
Browse files- all_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +319 -0
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"train_loss": 0.4794288249261376,
|
| 4 |
+
"train_runtime": 6378.689,
|
| 5 |
+
"train_samples": 392702,
|
| 6 |
+
"train_samples_per_second": 123.129,
|
| 7 |
+
"train_steps_per_second": 3.848
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"train_loss": 0.4794288249261376,
|
| 4 |
+
"train_runtime": 6378.689,
|
| 5 |
+
"train_samples": 392702,
|
| 6 |
+
"train_samples_per_second": 123.129,
|
| 7 |
+
"train_steps_per_second": 3.848
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,319 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
+
"global_step": 24544,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.04,
|
| 12 |
+
"learning_rate": 4.898142112125163e-05,
|
| 13 |
+
"loss": 0.7857,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.08,
|
| 18 |
+
"learning_rate": 4.7962842242503265e-05,
|
| 19 |
+
"loss": 0.6857,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.12,
|
| 24 |
+
"learning_rate": 4.694426336375489e-05,
|
| 25 |
+
"loss": 0.6523,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.16,
|
| 30 |
+
"learning_rate": 4.592568448500652e-05,
|
| 31 |
+
"loss": 0.6259,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.2,
|
| 36 |
+
"learning_rate": 4.490710560625815e-05,
|
| 37 |
+
"loss": 0.6288,
|
| 38 |
+
"step": 2500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.24,
|
| 42 |
+
"learning_rate": 4.3888526727509784e-05,
|
| 43 |
+
"loss": 0.6145,
|
| 44 |
+
"step": 3000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.29,
|
| 48 |
+
"learning_rate": 4.286994784876141e-05,
|
| 49 |
+
"loss": 0.6104,
|
| 50 |
+
"step": 3500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.33,
|
| 54 |
+
"learning_rate": 4.185136897001304e-05,
|
| 55 |
+
"loss": 0.5997,
|
| 56 |
+
"step": 4000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.37,
|
| 60 |
+
"learning_rate": 4.0832790091264675e-05,
|
| 61 |
+
"loss": 0.5836,
|
| 62 |
+
"step": 4500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.41,
|
| 66 |
+
"learning_rate": 3.98142112125163e-05,
|
| 67 |
+
"loss": 0.5834,
|
| 68 |
+
"step": 5000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.45,
|
| 72 |
+
"learning_rate": 3.879563233376793e-05,
|
| 73 |
+
"loss": 0.5685,
|
| 74 |
+
"step": 5500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.49,
|
| 78 |
+
"learning_rate": 3.777705345501956e-05,
|
| 79 |
+
"loss": 0.567,
|
| 80 |
+
"step": 6000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.53,
|
| 84 |
+
"learning_rate": 3.675847457627119e-05,
|
| 85 |
+
"loss": 0.5703,
|
| 86 |
+
"step": 6500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.57,
|
| 90 |
+
"learning_rate": 3.5739895697522816e-05,
|
| 91 |
+
"loss": 0.5648,
|
| 92 |
+
"step": 7000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.61,
|
| 96 |
+
"learning_rate": 3.4721316818774444e-05,
|
| 97 |
+
"loss": 0.5652,
|
| 98 |
+
"step": 7500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.65,
|
| 102 |
+
"learning_rate": 3.370273794002607e-05,
|
| 103 |
+
"loss": 0.5497,
|
| 104 |
+
"step": 8000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.69,
|
| 108 |
+
"learning_rate": 3.2684159061277707e-05,
|
| 109 |
+
"loss": 0.5488,
|
| 110 |
+
"step": 8500
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.73,
|
| 114 |
+
"learning_rate": 3.1665580182529335e-05,
|
| 115 |
+
"loss": 0.5484,
|
| 116 |
+
"step": 9000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.77,
|
| 120 |
+
"learning_rate": 3.064700130378096e-05,
|
| 121 |
+
"loss": 0.54,
|
| 122 |
+
"step": 9500
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.81,
|
| 126 |
+
"learning_rate": 2.9628422425032598e-05,
|
| 127 |
+
"loss": 0.5385,
|
| 128 |
+
"step": 10000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.86,
|
| 132 |
+
"learning_rate": 2.8609843546284226e-05,
|
| 133 |
+
"loss": 0.5391,
|
| 134 |
+
"step": 10500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.9,
|
| 138 |
+
"learning_rate": 2.7591264667535854e-05,
|
| 139 |
+
"loss": 0.5348,
|
| 140 |
+
"step": 11000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.94,
|
| 144 |
+
"learning_rate": 2.6572685788787482e-05,
|
| 145 |
+
"loss": 0.534,
|
| 146 |
+
"step": 11500
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.98,
|
| 150 |
+
"learning_rate": 2.5554106910039117e-05,
|
| 151 |
+
"loss": 0.5347,
|
| 152 |
+
"step": 12000
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 1.02,
|
| 156 |
+
"learning_rate": 2.4535528031290745e-05,
|
| 157 |
+
"loss": 0.4633,
|
| 158 |
+
"step": 12500
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 1.06,
|
| 162 |
+
"learning_rate": 2.3516949152542376e-05,
|
| 163 |
+
"loss": 0.3967,
|
| 164 |
+
"step": 13000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 1.1,
|
| 168 |
+
"learning_rate": 2.2498370273794004e-05,
|
| 169 |
+
"loss": 0.3887,
|
| 170 |
+
"step": 13500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 1.14,
|
| 174 |
+
"learning_rate": 2.1479791395045636e-05,
|
| 175 |
+
"loss": 0.3927,
|
| 176 |
+
"step": 14000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 1.18,
|
| 180 |
+
"learning_rate": 2.0461212516297264e-05,
|
| 181 |
+
"loss": 0.376,
|
| 182 |
+
"step": 14500
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 1.22,
|
| 186 |
+
"learning_rate": 1.944263363754889e-05,
|
| 187 |
+
"loss": 0.3855,
|
| 188 |
+
"step": 15000
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 1.26,
|
| 192 |
+
"learning_rate": 1.842405475880052e-05,
|
| 193 |
+
"loss": 0.3765,
|
| 194 |
+
"step": 15500
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 1.3,
|
| 198 |
+
"learning_rate": 1.740547588005215e-05,
|
| 199 |
+
"loss": 0.3804,
|
| 200 |
+
"step": 16000
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 1.34,
|
| 204 |
+
"learning_rate": 1.6386897001303783e-05,
|
| 205 |
+
"loss": 0.3763,
|
| 206 |
+
"step": 16500
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 1.39,
|
| 210 |
+
"learning_rate": 1.536831812255541e-05,
|
| 211 |
+
"loss": 0.3846,
|
| 212 |
+
"step": 17000
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 1.43,
|
| 216 |
+
"learning_rate": 1.4349739243807042e-05,
|
| 217 |
+
"loss": 0.372,
|
| 218 |
+
"step": 17500
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 1.47,
|
| 222 |
+
"learning_rate": 1.333116036505867e-05,
|
| 223 |
+
"loss": 0.3704,
|
| 224 |
+
"step": 18000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 1.51,
|
| 228 |
+
"learning_rate": 1.23125814863103e-05,
|
| 229 |
+
"loss": 0.3683,
|
| 230 |
+
"step": 18500
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 1.55,
|
| 234 |
+
"learning_rate": 1.1294002607561931e-05,
|
| 235 |
+
"loss": 0.3812,
|
| 236 |
+
"step": 19000
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 1.59,
|
| 240 |
+
"learning_rate": 1.027542372881356e-05,
|
| 241 |
+
"loss": 0.3731,
|
| 242 |
+
"step": 19500
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 1.63,
|
| 246 |
+
"learning_rate": 9.25684485006519e-06,
|
| 247 |
+
"loss": 0.3745,
|
| 248 |
+
"step": 20000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 1.67,
|
| 252 |
+
"learning_rate": 8.238265971316819e-06,
|
| 253 |
+
"loss": 0.3662,
|
| 254 |
+
"step": 20500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 1.71,
|
| 258 |
+
"learning_rate": 7.219687092568449e-06,
|
| 259 |
+
"loss": 0.3588,
|
| 260 |
+
"step": 21000
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 1.75,
|
| 264 |
+
"learning_rate": 6.2011082138200785e-06,
|
| 265 |
+
"loss": 0.375,
|
| 266 |
+
"step": 21500
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 1.79,
|
| 270 |
+
"learning_rate": 5.182529335071708e-06,
|
| 271 |
+
"loss": 0.3599,
|
| 272 |
+
"step": 22000
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 1.83,
|
| 276 |
+
"learning_rate": 4.163950456323338e-06,
|
| 277 |
+
"loss": 0.3732,
|
| 278 |
+
"step": 22500
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 1.87,
|
| 282 |
+
"learning_rate": 3.1453715775749674e-06,
|
| 283 |
+
"loss": 0.3631,
|
| 284 |
+
"step": 23000
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 1.91,
|
| 288 |
+
"learning_rate": 2.126792698826597e-06,
|
| 289 |
+
"loss": 0.3546,
|
| 290 |
+
"step": 23500
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 1.96,
|
| 294 |
+
"learning_rate": 1.108213820078227e-06,
|
| 295 |
+
"loss": 0.3589,
|
| 296 |
+
"step": 24000
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 2.0,
|
| 300 |
+
"learning_rate": 8.963494132985658e-08,
|
| 301 |
+
"loss": 0.3586,
|
| 302 |
+
"step": 24500
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 2.0,
|
| 306 |
+
"step": 24544,
|
| 307 |
+
"total_flos": 5.166258268431053e+16,
|
| 308 |
+
"train_loss": 0.4794288249261376,
|
| 309 |
+
"train_runtime": 6378.689,
|
| 310 |
+
"train_samples_per_second": 123.129,
|
| 311 |
+
"train_steps_per_second": 3.848
|
| 312 |
+
}
|
| 313 |
+
],
|
| 314 |
+
"max_steps": 24544,
|
| 315 |
+
"num_train_epochs": 2,
|
| 316 |
+
"total_flos": 5.166258268431053e+16,
|
| 317 |
+
"trial_name": null,
|
| 318 |
+
"trial_params": null
|
| 319 |
+
}
|