Commit
•
1ce113a
1
Parent(s):
a4fe551
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_loss": 0.23661810159683228,
|
| 13 |
+
"eval_mse": 0.23661810159683228,
|
| 14 |
+
"eval_runtime": 2.3458,
|
| 15 |
+
"eval_samples_per_second": 213.15,
|
| 16 |
+
"eval_steps_per_second": 26.857,
|
| 17 |
+
"step": 406
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 1.23,
|
| 21 |
+
"learning_rate": 2.8341964112881786e-05,
|
| 22 |
+
"loss": 0.5408,
|
| 23 |
+
"step": 500
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 2.0,
|
| 27 |
+
"eval_loss": 0.174851194024086,
|
| 28 |
+
"eval_mse": 0.1748511791229248,
|
| 29 |
+
"eval_runtime": 2.4627,
|
| 30 |
+
"eval_samples_per_second": 203.028,
|
| 31 |
+
"eval_steps_per_second": 25.582,
|
| 32 |
+
"step": 812
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 2.46,
|
| 36 |
+
"learning_rate": 2.648225518159033e-05,
|
| 37 |
+
"loss": 0.1601,
|
| 38 |
+
"step": 1000
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 3.0,
|
| 42 |
+
"eval_loss": 0.16912883520126343,
|
| 43 |
+
"eval_mse": 0.16912883520126343,
|
| 44 |
+
"eval_runtime": 2.4762,
|
| 45 |
+
"eval_samples_per_second": 201.92,
|
| 46 |
+
"eval_steps_per_second": 25.442,
|
| 47 |
+
"step": 1218
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 3.69,
|
| 51 |
+
"learning_rate": 2.4622546250298872e-05,
|
| 52 |
+
"loss": 0.1051,
|
| 53 |
+
"step": 1500
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 4.0,
|
| 57 |
+
"eval_loss": 0.15406909584999084,
|
| 58 |
+
"eval_mse": 0.15406909584999084,
|
| 59 |
+
"eval_runtime": 2.4694,
|
| 60 |
+
"eval_samples_per_second": 202.478,
|
| 61 |
+
"eval_steps_per_second": 25.512,
|
| 62 |
+
"step": 1624
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 4.93,
|
| 66 |
+
"learning_rate": 2.2762837319007417e-05,
|
| 67 |
+
"loss": 0.0784,
|
| 68 |
+
"step": 2000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 5.0,
|
| 72 |
+
"eval_loss": 0.16454747319221497,
|
| 73 |
+
"eval_mse": 0.16454748809337616,
|
| 74 |
+
"eval_runtime": 2.4788,
|
| 75 |
+
"eval_samples_per_second": 201.707,
|
| 76 |
+
"eval_steps_per_second": 25.415,
|
| 77 |
+
"step": 2030
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 6.0,
|
| 81 |
+
"eval_loss": 0.13350126147270203,
|
| 82 |
+
"eval_mse": 0.13350127637386322,
|
| 83 |
+
"eval_runtime": 2.3387,
|
| 84 |
+
"eval_samples_per_second": 213.798,
|
| 85 |
+
"eval_steps_per_second": 26.939,
|
| 86 |
+
"step": 2436
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 6.16,
|
| 90 |
+
"learning_rate": 2.0903128387715962e-05,
|
| 91 |
+
"loss": 0.0615,
|
| 92 |
+
"step": 2500
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 7.0,
|
| 96 |
+
"eval_loss": 0.11380095779895782,
|
| 97 |
+
"eval_mse": 0.11380096524953842,
|
| 98 |
+
"eval_runtime": 2.4535,
|
| 99 |
+
"eval_samples_per_second": 203.787,
|
| 100 |
+
"eval_steps_per_second": 25.677,
|
| 101 |
+
"step": 2842
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 7.39,
|
| 105 |
+
"learning_rate": 1.9043419456424507e-05,
|
| 106 |
+
"loss": 0.0486,
|
| 107 |
+
"step": 3000
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 8.0,
|
| 111 |
+
"eval_loss": 0.11023622751235962,
|
| 112 |
+
"eval_mse": 0.11023622006177902,
|
| 113 |
+
"eval_runtime": 2.3622,
|
| 114 |
+
"eval_samples_per_second": 211.671,
|
| 115 |
+
"eval_steps_per_second": 26.671,
|
| 116 |
+
"step": 3248
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 8.62,
|
| 120 |
+
"learning_rate": 1.718371052513305e-05,
|
| 121 |
+
"loss": 0.04,
|
| 122 |
+
"step": 3500
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 9.0,
|
| 126 |
+
"eval_loss": 0.13071884214878082,
|
| 127 |
+
"eval_mse": 0.13071882724761963,
|
| 128 |
+
"eval_runtime": 2.3355,
|
| 129 |
+
"eval_samples_per_second": 214.09,
|
| 130 |
+
"eval_steps_per_second": 26.975,
|
| 131 |
+
"step": 3654
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 9.85,
|
| 135 |
+
"learning_rate": 1.5324001593841596e-05,
|
| 136 |
+
"loss": 0.0333,
|
| 137 |
+
"step": 4000
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 10.0,
|
| 141 |
+
"eval_loss": 0.11540825664997101,
|
| 142 |
+
"eval_mse": 0.11540825664997101,
|
| 143 |
+
"eval_runtime": 2.3363,
|
| 144 |
+
"eval_samples_per_second": 214.015,
|
| 145 |
+
"eval_steps_per_second": 26.966,
|
| 146 |
+
"step": 4060
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 11.0,
|
| 150 |
+
"eval_loss": 0.08316297829151154,
|
| 151 |
+
"eval_mse": 0.08316297829151154,
|
| 152 |
+
"eval_runtime": 2.3934,
|
| 153 |
+
"eval_samples_per_second": 208.905,
|
| 154 |
+
"eval_steps_per_second": 26.322,
|
| 155 |
+
"step": 4466
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 11.08,
|
| 159 |
+
"learning_rate": 1.346429266255014e-05,
|
| 160 |
+
"loss": 0.0303,
|
| 161 |
+
"step": 4500
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 12.0,
|
| 165 |
+
"eval_loss": 0.090473473072052,
|
| 166 |
+
"eval_mse": 0.090473473072052,
|
| 167 |
+
"eval_runtime": 2.48,
|
| 168 |
+
"eval_samples_per_second": 201.616,
|
| 169 |
+
"eval_steps_per_second": 25.404,
|
| 170 |
+
"step": 4872
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 12.32,
|
| 174 |
+
"learning_rate": 1.1604583731258682e-05,
|
| 175 |
+
"loss": 0.0243,
|
| 176 |
+
"step": 5000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 13.0,
|
| 180 |
+
"eval_loss": 0.08971528708934784,
|
| 181 |
+
"eval_mse": 0.08971529453992844,
|
| 182 |
+
"eval_runtime": 2.3125,
|
| 183 |
+
"eval_samples_per_second": 216.213,
|
| 184 |
+
"eval_steps_per_second": 27.243,
|
| 185 |
+
"step": 5278
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 13.55,
|
| 189 |
+
"learning_rate": 9.744874799967227e-06,
|
| 190 |
+
"loss": 0.0222,
|
| 191 |
+
"step": 5500
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 14.0,
|
| 195 |
+
"eval_loss": 0.08441515266895294,
|
| 196 |
+
"eval_mse": 0.08441514521837234,
|
| 197 |
+
"eval_runtime": 2.4412,
|
| 198 |
+
"eval_samples_per_second": 204.815,
|
| 199 |
+
"eval_steps_per_second": 25.807,
|
| 200 |
+
"step": 5684
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 14.78,
|
| 204 |
+
"learning_rate": 7.885165868675772e-06,
|
| 205 |
+
"loss": 0.0194,
|
| 206 |
+
"step": 6000
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 15.0,
|
| 210 |
+
"eval_loss": 0.08390124142169952,
|
| 211 |
+
"eval_mse": 0.08390124142169952,
|
| 212 |
+
"eval_runtime": 2.5105,
|
| 213 |
+
"eval_samples_per_second": 199.165,
|
| 214 |
+
"eval_steps_per_second": 25.095,
|
| 215 |
+
"step": 6090
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 16.0,
|
| 219 |
+
"eval_loss": 0.07694818079471588,
|
| 220 |
+
"eval_mse": 0.07694818079471588,
|
| 221 |
+
"eval_runtime": 2.4507,
|
| 222 |
+
"eval_samples_per_second": 204.025,
|
| 223 |
+
"eval_steps_per_second": 25.707,
|
| 224 |
+
"step": 6496
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 16.01,
|
| 228 |
+
"learning_rate": 6.025456937384317e-06,
|
| 229 |
+
"loss": 0.0173,
|
| 230 |
+
"step": 6500
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 17.0,
|
| 234 |
+
"eval_loss": 0.07610571384429932,
|
| 235 |
+
"eval_mse": 0.07610571384429932,
|
| 236 |
+
"eval_runtime": 2.3078,
|
| 237 |
+
"eval_samples_per_second": 216.656,
|
| 238 |
+
"eval_steps_per_second": 27.299,
|
| 239 |
+
"step": 6902
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 17.24,
|
| 243 |
+
"learning_rate": 4.165748006092861e-06,
|
| 244 |
+
"loss": 0.0156,
|
| 245 |
+
"step": 7000
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 18.0,
|
| 249 |
+
"eval_loss": 0.06984403729438782,
|
| 250 |
+
"eval_mse": 0.06984403729438782,
|
| 251 |
+
"eval_runtime": 2.3322,
|
| 252 |
+
"eval_samples_per_second": 214.388,
|
| 253 |
+
"eval_steps_per_second": 27.013,
|
| 254 |
+
"step": 7308
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 18.47,
|
| 258 |
+
"learning_rate": 2.306039074801405e-06,
|
| 259 |
+
"loss": 0.0138,
|
| 260 |
+
"step": 7500
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 19.0,
|
| 264 |
+
"eval_loss": 0.07631801068782806,
|
| 265 |
+
"eval_mse": 0.07631801813840866,
|
| 266 |
+
"eval_runtime": 2.4913,
|
| 267 |
+
"eval_samples_per_second": 200.701,
|
| 268 |
+
"eval_steps_per_second": 25.288,
|
| 269 |
+
"step": 7714
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 19.7,
|
| 273 |
+
"learning_rate": 4.4633014350994935e-07,
|
| 274 |
+
"loss": 0.0128,
|
| 275 |
+
"step": 8000
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 20.0,
|
| 279 |
+
"eval_loss": 0.07459883391857147,
|
| 280 |
+
"eval_mse": 0.07459883391857147,
|
| 281 |
+
"eval_runtime": 2.3857,
|
| 282 |
+
"eval_samples_per_second": 209.585,
|
| 283 |
+
"eval_steps_per_second": 26.408,
|
| 284 |
+
"step": 8120
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 20.0,
|
| 288 |
+
"step": 8120,
|
| 289 |
+
"total_flos": 8550769413547008.0,
|
| 290 |
+
"train_loss": 0.07552281259903179,
|
| 291 |
+
"train_runtime": 3008.7042,
|
| 292 |
+
"train_samples_per_second": 43.208,
|
| 293 |
+
"train_steps_per_second": 2.699
|
| 294 |
+
}
|
| 295 |
+
],
|
| 296 |
+
"max_steps": 8120,
|
| 297 |
+
"num_train_epochs": 20,
|
| 298 |
+
"total_flos": 8550769413547008.0,
|
| 299 |
+
"trial_name": null,
|
| 300 |
+
"trial_params": null
|
| 301 |
+
}
|