Upload trainer_state.json
Browse files- trainer_state.json +434 -0
trainer_state.json
ADDED
|
@@ -0,0 +1,434 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8793088793754578,
|
| 3 |
+
"best_model_checkpoint": "models/checkpoints/checkpoint-5500",
|
| 4 |
+
"epoch": 0.4509582863585118,
|
| 5 |
+
"global_step": 5500,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.01,
|
| 12 |
+
"learning_rate": 1.998360118071499e-05,
|
| 13 |
+
"loss": 1.518,
|
| 14 |
+
"step": 100
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.02,
|
| 18 |
+
"learning_rate": 1.9967202361429978e-05,
|
| 19 |
+
"loss": 1.2325,
|
| 20 |
+
"step": 200
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.02,
|
| 24 |
+
"learning_rate": 1.9950803542144966e-05,
|
| 25 |
+
"loss": 1.1664,
|
| 26 |
+
"step": 300
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.03,
|
| 30 |
+
"learning_rate": 1.9934404722859955e-05,
|
| 31 |
+
"loss": 1.1746,
|
| 32 |
+
"step": 400
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.04,
|
| 36 |
+
"learning_rate": 1.9918005903574943e-05,
|
| 37 |
+
"loss": 1.1251,
|
| 38 |
+
"step": 500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.04,
|
| 42 |
+
"eval_loss": 0.964438259601593,
|
| 43 |
+
"eval_runtime": 267.7236,
|
| 44 |
+
"eval_samples_per_second": 255.906,
|
| 45 |
+
"eval_steps_per_second": 15.994,
|
| 46 |
+
"step": 500
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 0.05,
|
| 50 |
+
"learning_rate": 1.9901607084289934e-05,
|
| 51 |
+
"loss": 1.1041,
|
| 52 |
+
"step": 600
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.06,
|
| 56 |
+
"learning_rate": 1.988520826500492e-05,
|
| 57 |
+
"loss": 1.0817,
|
| 58 |
+
"step": 700
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.07,
|
| 62 |
+
"learning_rate": 1.986880944571991e-05,
|
| 63 |
+
"loss": 1.0594,
|
| 64 |
+
"step": 800
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 0.07,
|
| 68 |
+
"learning_rate": 1.98524106264349e-05,
|
| 69 |
+
"loss": 1.0642,
|
| 70 |
+
"step": 900
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 0.08,
|
| 74 |
+
"learning_rate": 1.9836011807149887e-05,
|
| 75 |
+
"loss": 1.0453,
|
| 76 |
+
"step": 1000
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 0.08,
|
| 80 |
+
"eval_loss": 0.9285051226615906,
|
| 81 |
+
"eval_runtime": 253.7626,
|
| 82 |
+
"eval_samples_per_second": 269.985,
|
| 83 |
+
"eval_steps_per_second": 16.874,
|
| 84 |
+
"step": 1000
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 0.09,
|
| 88 |
+
"learning_rate": 1.9819612987864875e-05,
|
| 89 |
+
"loss": 1.0486,
|
| 90 |
+
"step": 1100
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 0.1,
|
| 94 |
+
"learning_rate": 1.9803214168579864e-05,
|
| 95 |
+
"loss": 1.0549,
|
| 96 |
+
"step": 1200
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 0.11,
|
| 100 |
+
"learning_rate": 1.9786815349294852e-05,
|
| 101 |
+
"loss": 1.0639,
|
| 102 |
+
"step": 1300
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 0.11,
|
| 106 |
+
"learning_rate": 1.977041653000984e-05,
|
| 107 |
+
"loss": 1.0354,
|
| 108 |
+
"step": 1400
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.12,
|
| 112 |
+
"learning_rate": 1.9754017710724828e-05,
|
| 113 |
+
"loss": 1.0393,
|
| 114 |
+
"step": 1500
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.12,
|
| 118 |
+
"eval_loss": 0.9202534556388855,
|
| 119 |
+
"eval_runtime": 264.8239,
|
| 120 |
+
"eval_samples_per_second": 258.708,
|
| 121 |
+
"eval_steps_per_second": 16.169,
|
| 122 |
+
"step": 1500
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.13,
|
| 126 |
+
"learning_rate": 1.9737618891439817e-05,
|
| 127 |
+
"loss": 1.0381,
|
| 128 |
+
"step": 1600
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.14,
|
| 132 |
+
"learning_rate": 1.9721220072154808e-05,
|
| 133 |
+
"loss": 1.0672,
|
| 134 |
+
"step": 1700
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.15,
|
| 138 |
+
"learning_rate": 1.9704821252869793e-05,
|
| 139 |
+
"loss": 1.0335,
|
| 140 |
+
"step": 1800
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.16,
|
| 144 |
+
"learning_rate": 1.9688422433584785e-05,
|
| 145 |
+
"loss": 1.0239,
|
| 146 |
+
"step": 1900
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.16,
|
| 150 |
+
"learning_rate": 1.9672023614299773e-05,
|
| 151 |
+
"loss": 1.0012,
|
| 152 |
+
"step": 2000
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.16,
|
| 156 |
+
"eval_loss": 0.9098692536354065,
|
| 157 |
+
"eval_runtime": 264.5198,
|
| 158 |
+
"eval_samples_per_second": 259.005,
|
| 159 |
+
"eval_steps_per_second": 16.188,
|
| 160 |
+
"step": 2000
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 0.17,
|
| 164 |
+
"learning_rate": 1.965562479501476e-05,
|
| 165 |
+
"loss": 1.0146,
|
| 166 |
+
"step": 2100
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 0.18,
|
| 170 |
+
"learning_rate": 1.963922597572975e-05,
|
| 171 |
+
"loss": 1.0502,
|
| 172 |
+
"step": 2200
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 0.19,
|
| 176 |
+
"learning_rate": 1.9622827156444737e-05,
|
| 177 |
+
"loss": 1.0062,
|
| 178 |
+
"step": 2300
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.2,
|
| 182 |
+
"learning_rate": 1.9606428337159726e-05,
|
| 183 |
+
"loss": 1.0144,
|
| 184 |
+
"step": 2400
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.2,
|
| 188 |
+
"learning_rate": 1.9590029517874714e-05,
|
| 189 |
+
"loss": 0.9826,
|
| 190 |
+
"step": 2500
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 0.2,
|
| 194 |
+
"eval_loss": 0.9166184067726135,
|
| 195 |
+
"eval_runtime": 256.5893,
|
| 196 |
+
"eval_samples_per_second": 267.01,
|
| 197 |
+
"eval_steps_per_second": 16.688,
|
| 198 |
+
"step": 2500
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.21,
|
| 202 |
+
"learning_rate": 1.9573630698589702e-05,
|
| 203 |
+
"loss": 1.0269,
|
| 204 |
+
"step": 2600
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 0.22,
|
| 208 |
+
"learning_rate": 1.9557231879304694e-05,
|
| 209 |
+
"loss": 0.9898,
|
| 210 |
+
"step": 2700
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 0.23,
|
| 214 |
+
"learning_rate": 1.954083306001968e-05,
|
| 215 |
+
"loss": 1.0248,
|
| 216 |
+
"step": 2800
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 0.24,
|
| 220 |
+
"learning_rate": 1.952443424073467e-05,
|
| 221 |
+
"loss": 0.9996,
|
| 222 |
+
"step": 2900
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 0.25,
|
| 226 |
+
"learning_rate": 1.950803542144966e-05,
|
| 227 |
+
"loss": 0.9595,
|
| 228 |
+
"step": 3000
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 0.25,
|
| 232 |
+
"eval_loss": 0.9191610217094421,
|
| 233 |
+
"eval_runtime": 272.1388,
|
| 234 |
+
"eval_samples_per_second": 251.754,
|
| 235 |
+
"eval_steps_per_second": 15.735,
|
| 236 |
+
"step": 3000
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 0.25,
|
| 240 |
+
"learning_rate": 1.9491636602164647e-05,
|
| 241 |
+
"loss": 0.9873,
|
| 242 |
+
"step": 3100
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 0.26,
|
| 246 |
+
"learning_rate": 1.9475237782879635e-05,
|
| 247 |
+
"loss": 0.9667,
|
| 248 |
+
"step": 3200
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.27,
|
| 252 |
+
"learning_rate": 1.9458838963594623e-05,
|
| 253 |
+
"loss": 0.9666,
|
| 254 |
+
"step": 3300
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.28,
|
| 258 |
+
"learning_rate": 1.944244014430961e-05,
|
| 259 |
+
"loss": 1.0102,
|
| 260 |
+
"step": 3400
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 0.29,
|
| 264 |
+
"learning_rate": 1.94260413250246e-05,
|
| 265 |
+
"loss": 0.9511,
|
| 266 |
+
"step": 3500
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 0.29,
|
| 270 |
+
"eval_loss": 0.9013209342956543,
|
| 271 |
+
"eval_runtime": 267.0529,
|
| 272 |
+
"eval_samples_per_second": 256.548,
|
| 273 |
+
"eval_steps_per_second": 16.034,
|
| 274 |
+
"step": 3500
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 0.3,
|
| 278 |
+
"learning_rate": 1.9409642505739588e-05,
|
| 279 |
+
"loss": 0.9927,
|
| 280 |
+
"step": 3600
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 0.3,
|
| 284 |
+
"learning_rate": 1.9393243686454576e-05,
|
| 285 |
+
"loss": 0.9507,
|
| 286 |
+
"step": 3700
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 0.31,
|
| 290 |
+
"learning_rate": 1.9376844867169567e-05,
|
| 291 |
+
"loss": 1.0049,
|
| 292 |
+
"step": 3800
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 0.32,
|
| 296 |
+
"learning_rate": 1.9360446047884552e-05,
|
| 297 |
+
"loss": 0.9385,
|
| 298 |
+
"step": 3900
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 0.33,
|
| 302 |
+
"learning_rate": 1.9344047228599544e-05,
|
| 303 |
+
"loss": 0.9644,
|
| 304 |
+
"step": 4000
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.33,
|
| 308 |
+
"eval_loss": 0.8957135081291199,
|
| 309 |
+
"eval_runtime": 260.7988,
|
| 310 |
+
"eval_samples_per_second": 262.701,
|
| 311 |
+
"eval_steps_per_second": 16.419,
|
| 312 |
+
"step": 4000
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 0.34,
|
| 316 |
+
"learning_rate": 1.932764840931453e-05,
|
| 317 |
+
"loss": 0.9293,
|
| 318 |
+
"step": 4100
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.34,
|
| 322 |
+
"learning_rate": 1.931124959002952e-05,
|
| 323 |
+
"loss": 0.9298,
|
| 324 |
+
"step": 4200
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.35,
|
| 328 |
+
"learning_rate": 1.929485077074451e-05,
|
| 329 |
+
"loss": 0.9218,
|
| 330 |
+
"step": 4300
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 0.36,
|
| 334 |
+
"learning_rate": 1.9278451951459497e-05,
|
| 335 |
+
"loss": 0.9523,
|
| 336 |
+
"step": 4400
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 0.37,
|
| 340 |
+
"learning_rate": 1.9262053132174485e-05,
|
| 341 |
+
"loss": 0.9079,
|
| 342 |
+
"step": 4500
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 0.37,
|
| 346 |
+
"eval_loss": 0.9050074815750122,
|
| 347 |
+
"eval_runtime": 264.4439,
|
| 348 |
+
"eval_samples_per_second": 259.079,
|
| 349 |
+
"eval_steps_per_second": 16.192,
|
| 350 |
+
"step": 4500
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 0.38,
|
| 354 |
+
"learning_rate": 1.9245654312889473e-05,
|
| 355 |
+
"loss": 0.9437,
|
| 356 |
+
"step": 4600
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 0.39,
|
| 360 |
+
"learning_rate": 1.922925549360446e-05,
|
| 361 |
+
"loss": 0.9395,
|
| 362 |
+
"step": 4700
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 0.39,
|
| 366 |
+
"learning_rate": 1.921285667431945e-05,
|
| 367 |
+
"loss": 0.969,
|
| 368 |
+
"step": 4800
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 0.4,
|
| 372 |
+
"learning_rate": 1.9196457855034438e-05,
|
| 373 |
+
"loss": 0.926,
|
| 374 |
+
"step": 4900
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.41,
|
| 378 |
+
"learning_rate": 1.9180059035749426e-05,
|
| 379 |
+
"loss": 0.9178,
|
| 380 |
+
"step": 5000
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.41,
|
| 384 |
+
"eval_loss": 0.8956226706504822,
|
| 385 |
+
"eval_runtime": 259.9134,
|
| 386 |
+
"eval_samples_per_second": 263.595,
|
| 387 |
+
"eval_steps_per_second": 16.475,
|
| 388 |
+
"step": 5000
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.42,
|
| 392 |
+
"learning_rate": 1.9163660216464418e-05,
|
| 393 |
+
"loss": 0.9697,
|
| 394 |
+
"step": 5100
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.43,
|
| 398 |
+
"learning_rate": 1.9147261397179403e-05,
|
| 399 |
+
"loss": 0.9448,
|
| 400 |
+
"step": 5200
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 0.43,
|
| 404 |
+
"learning_rate": 1.9130862577894394e-05,
|
| 405 |
+
"loss": 0.9118,
|
| 406 |
+
"step": 5300
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 0.44,
|
| 410 |
+
"learning_rate": 1.911446375860938e-05,
|
| 411 |
+
"loss": 0.9321,
|
| 412 |
+
"step": 5400
|
| 413 |
+
},
|
| 414 |
+
{
|
| 415 |
+
"epoch": 0.45,
|
| 416 |
+
"learning_rate": 1.909806493932437e-05,
|
| 417 |
+
"loss": 0.9289,
|
| 418 |
+
"step": 5500
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 0.45,
|
| 422 |
+
"eval_loss": 0.8793088793754578,
|
| 423 |
+
"eval_runtime": 261.4397,
|
| 424 |
+
"eval_samples_per_second": 262.057,
|
| 425 |
+
"eval_steps_per_second": 16.379,
|
| 426 |
+
"step": 5500
|
| 427 |
+
}
|
| 428 |
+
],
|
| 429 |
+
"max_steps": 121960,
|
| 430 |
+
"num_train_epochs": 10,
|
| 431 |
+
"total_flos": 1.922426903232e+16,
|
| 432 |
+
"trial_name": null,
|
| 433 |
+
"trial_params": null
|
| 434 |
+
}
|