All Dunn!!!
Browse files- all_results.json +7 -0
- train_results.json +7 -0
- trainer_state.json +397 -0
all_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"train_loss": 0.6093255166633234,
|
| 4 |
+
"train_runtime": 257236.9869,
|
| 5 |
+
"train_samples_per_second": 0.052,
|
| 6 |
+
"train_steps_per_second": 0.007
|
| 7 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"train_loss": 0.6093255166633234,
|
| 4 |
+
"train_runtime": 257236.9869,
|
| 5 |
+
"train_samples_per_second": 0.052,
|
| 6 |
+
"train_steps_per_second": 0.007
|
| 7 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,397 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
+
"global_step": 1682,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.0,
|
| 12 |
+
"learning_rate": 4.9970273483947685e-05,
|
| 13 |
+
"loss": 9.5696,
|
| 14 |
+
"step": 1
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.03,
|
| 18 |
+
"learning_rate": 4.913793103448276e-05,
|
| 19 |
+
"loss": 2.0231,
|
| 20 |
+
"step": 29
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.07,
|
| 24 |
+
"learning_rate": 4.827586206896552e-05,
|
| 25 |
+
"loss": 1.2689,
|
| 26 |
+
"step": 58
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.1,
|
| 30 |
+
"learning_rate": 4.741379310344828e-05,
|
| 31 |
+
"loss": 1.1252,
|
| 32 |
+
"step": 87
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.14,
|
| 36 |
+
"learning_rate": 4.655172413793104e-05,
|
| 37 |
+
"loss": 1.0745,
|
| 38 |
+
"step": 116
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.17,
|
| 42 |
+
"learning_rate": 4.5689655172413794e-05,
|
| 43 |
+
"loss": 1.1696,
|
| 44 |
+
"step": 145
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.21,
|
| 48 |
+
"learning_rate": 4.482758620689655e-05,
|
| 49 |
+
"loss": 1.0006,
|
| 50 |
+
"step": 174
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.24,
|
| 54 |
+
"learning_rate": 4.396551724137931e-05,
|
| 55 |
+
"loss": 1.0273,
|
| 56 |
+
"step": 203
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.28,
|
| 60 |
+
"learning_rate": 4.3103448275862066e-05,
|
| 61 |
+
"loss": 1.1105,
|
| 62 |
+
"step": 232
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.31,
|
| 66 |
+
"learning_rate": 4.224137931034483e-05,
|
| 67 |
+
"loss": 1.2629,
|
| 68 |
+
"step": 261
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.34,
|
| 72 |
+
"learning_rate": 4.1379310344827587e-05,
|
| 73 |
+
"loss": 0.9306,
|
| 74 |
+
"step": 290
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.38,
|
| 78 |
+
"learning_rate": 4.0517241379310344e-05,
|
| 79 |
+
"loss": 0.9233,
|
| 80 |
+
"step": 319
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.41,
|
| 84 |
+
"learning_rate": 3.965517241379311e-05,
|
| 85 |
+
"loss": 0.9108,
|
| 86 |
+
"step": 348
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.45,
|
| 90 |
+
"learning_rate": 3.8793103448275865e-05,
|
| 91 |
+
"loss": 0.9462,
|
| 92 |
+
"step": 377
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.48,
|
| 96 |
+
"learning_rate": 3.793103448275862e-05,
|
| 97 |
+
"loss": 0.9254,
|
| 98 |
+
"step": 406
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.52,
|
| 102 |
+
"learning_rate": 3.7068965517241385e-05,
|
| 103 |
+
"loss": 0.7106,
|
| 104 |
+
"step": 435
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.55,
|
| 108 |
+
"learning_rate": 3.620689655172414e-05,
|
| 109 |
+
"loss": 0.7342,
|
| 110 |
+
"step": 464
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.59,
|
| 114 |
+
"learning_rate": 3.53448275862069e-05,
|
| 115 |
+
"loss": 0.7573,
|
| 116 |
+
"step": 493
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.62,
|
| 120 |
+
"learning_rate": 3.4482758620689657e-05,
|
| 121 |
+
"loss": 0.7451,
|
| 122 |
+
"step": 522
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.66,
|
| 126 |
+
"learning_rate": 3.3620689655172414e-05,
|
| 127 |
+
"loss": 0.714,
|
| 128 |
+
"step": 551
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.69,
|
| 132 |
+
"learning_rate": 3.275862068965517e-05,
|
| 133 |
+
"loss": 0.8191,
|
| 134 |
+
"step": 580
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.72,
|
| 138 |
+
"learning_rate": 3.1896551724137935e-05,
|
| 139 |
+
"loss": 0.6586,
|
| 140 |
+
"step": 609
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.76,
|
| 144 |
+
"learning_rate": 3.103448275862069e-05,
|
| 145 |
+
"loss": 0.7097,
|
| 146 |
+
"step": 638
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.79,
|
| 150 |
+
"learning_rate": 3.017241379310345e-05,
|
| 151 |
+
"loss": 0.6619,
|
| 152 |
+
"step": 667
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.83,
|
| 156 |
+
"learning_rate": 2.9310344827586206e-05,
|
| 157 |
+
"loss": 0.7002,
|
| 158 |
+
"step": 696
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.86,
|
| 162 |
+
"learning_rate": 2.844827586206897e-05,
|
| 163 |
+
"loss": 0.6465,
|
| 164 |
+
"step": 725
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.9,
|
| 168 |
+
"learning_rate": 2.7586206896551727e-05,
|
| 169 |
+
"loss": 0.7087,
|
| 170 |
+
"step": 754
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.93,
|
| 174 |
+
"learning_rate": 2.672413793103448e-05,
|
| 175 |
+
"loss": 0.5199,
|
| 176 |
+
"step": 783
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.97,
|
| 180 |
+
"learning_rate": 2.5862068965517244e-05,
|
| 181 |
+
"loss": 0.5276,
|
| 182 |
+
"step": 812
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 1.0,
|
| 186 |
+
"learning_rate": 2.5e-05,
|
| 187 |
+
"loss": 0.486,
|
| 188 |
+
"step": 841
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 1.0,
|
| 192 |
+
"eval_cer": 0.042814229249011855,
|
| 193 |
+
"eval_loss": 0.5168413519859314,
|
| 194 |
+
"eval_runtime": 53945.1969,
|
| 195 |
+
"eval_samples_per_second": 0.031,
|
| 196 |
+
"eval_steps_per_second": 0.004,
|
| 197 |
+
"step": 841
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 1.03,
|
| 201 |
+
"learning_rate": 2.413793103448276e-05,
|
| 202 |
+
"loss": 0.4464,
|
| 203 |
+
"step": 870
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 1.07,
|
| 207 |
+
"learning_rate": 2.327586206896552e-05,
|
| 208 |
+
"loss": 0.4375,
|
| 209 |
+
"step": 899
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 1.1,
|
| 213 |
+
"learning_rate": 2.2413793103448276e-05,
|
| 214 |
+
"loss": 0.411,
|
| 215 |
+
"step": 928
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 1.14,
|
| 219 |
+
"learning_rate": 2.1551724137931033e-05,
|
| 220 |
+
"loss": 0.4487,
|
| 221 |
+
"step": 957
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 1.17,
|
| 225 |
+
"learning_rate": 2.0689655172413793e-05,
|
| 226 |
+
"loss": 0.388,
|
| 227 |
+
"step": 986
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 1.21,
|
| 231 |
+
"learning_rate": 1.9827586206896554e-05,
|
| 232 |
+
"loss": 0.4448,
|
| 233 |
+
"step": 1015
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 1.24,
|
| 237 |
+
"learning_rate": 1.896551724137931e-05,
|
| 238 |
+
"loss": 0.5106,
|
| 239 |
+
"step": 1044
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 1.28,
|
| 243 |
+
"learning_rate": 1.810344827586207e-05,
|
| 244 |
+
"loss": 0.3352,
|
| 245 |
+
"step": 1073
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 1.31,
|
| 249 |
+
"learning_rate": 1.7241379310344828e-05,
|
| 250 |
+
"loss": 0.3674,
|
| 251 |
+
"step": 1102
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 1.34,
|
| 255 |
+
"learning_rate": 1.6379310344827585e-05,
|
| 256 |
+
"loss": 0.3654,
|
| 257 |
+
"step": 1131
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 1.38,
|
| 261 |
+
"learning_rate": 1.5517241379310346e-05,
|
| 262 |
+
"loss": 0.3391,
|
| 263 |
+
"step": 1160
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 1.41,
|
| 267 |
+
"learning_rate": 1.4655172413793103e-05,
|
| 268 |
+
"loss": 0.3538,
|
| 269 |
+
"step": 1189
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 1.45,
|
| 273 |
+
"learning_rate": 1.3793103448275863e-05,
|
| 274 |
+
"loss": 0.3327,
|
| 275 |
+
"step": 1218
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 1.48,
|
| 279 |
+
"learning_rate": 1.2931034482758622e-05,
|
| 280 |
+
"loss": 0.2937,
|
| 281 |
+
"step": 1247
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 1.52,
|
| 285 |
+
"learning_rate": 1.206896551724138e-05,
|
| 286 |
+
"loss": 0.3375,
|
| 287 |
+
"step": 1276
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 1.55,
|
| 291 |
+
"learning_rate": 1.1206896551724138e-05,
|
| 292 |
+
"loss": 0.3083,
|
| 293 |
+
"step": 1305
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 1.59,
|
| 297 |
+
"learning_rate": 1.0344827586206897e-05,
|
| 298 |
+
"loss": 0.2782,
|
| 299 |
+
"step": 1334
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 1.62,
|
| 303 |
+
"learning_rate": 9.482758620689655e-06,
|
| 304 |
+
"loss": 0.2708,
|
| 305 |
+
"step": 1363
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 1.66,
|
| 309 |
+
"learning_rate": 8.620689655172414e-06,
|
| 310 |
+
"loss": 0.2553,
|
| 311 |
+
"step": 1392
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 1.69,
|
| 315 |
+
"learning_rate": 7.758620689655173e-06,
|
| 316 |
+
"loss": 0.2646,
|
| 317 |
+
"step": 1421
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 1.72,
|
| 321 |
+
"learning_rate": 6.896551724137932e-06,
|
| 322 |
+
"loss": 0.2812,
|
| 323 |
+
"step": 1450
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 1.76,
|
| 327 |
+
"learning_rate": 6.03448275862069e-06,
|
| 328 |
+
"loss": 0.243,
|
| 329 |
+
"step": 1479
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 1.79,
|
| 333 |
+
"learning_rate": 5.172413793103448e-06,
|
| 334 |
+
"loss": 0.2263,
|
| 335 |
+
"step": 1508
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 1.83,
|
| 339 |
+
"learning_rate": 4.310344827586207e-06,
|
| 340 |
+
"loss": 0.2212,
|
| 341 |
+
"step": 1537
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 1.86,
|
| 345 |
+
"learning_rate": 3.448275862068966e-06,
|
| 346 |
+
"loss": 0.2268,
|
| 347 |
+
"step": 1566
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 1.9,
|
| 351 |
+
"learning_rate": 2.586206896551724e-06,
|
| 352 |
+
"loss": 0.2148,
|
| 353 |
+
"step": 1595
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 1.93,
|
| 357 |
+
"learning_rate": 1.724137931034483e-06,
|
| 358 |
+
"loss": 0.2399,
|
| 359 |
+
"step": 1624
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 1.97,
|
| 363 |
+
"learning_rate": 8.620689655172415e-07,
|
| 364 |
+
"loss": 0.2214,
|
| 365 |
+
"step": 1653
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 2.0,
|
| 369 |
+
"learning_rate": 0.0,
|
| 370 |
+
"loss": 0.2187,
|
| 371 |
+
"step": 1682
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 2.0,
|
| 375 |
+
"eval_cer": 0.0036363636363636364,
|
| 376 |
+
"eval_loss": 0.24321582913398743,
|
| 377 |
+
"eval_runtime": 55499.6966,
|
| 378 |
+
"eval_samples_per_second": 0.03,
|
| 379 |
+
"eval_steps_per_second": 0.004,
|
| 380 |
+
"step": 1682
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 2.0,
|
| 384 |
+
"step": 1682,
|
| 385 |
+
"total_flos": 1.9906356553640313e+19,
|
| 386 |
+
"train_loss": 0.6093255166633234,
|
| 387 |
+
"train_runtime": 257236.9869,
|
| 388 |
+
"train_samples_per_second": 0.052,
|
| 389 |
+
"train_steps_per_second": 0.007
|
| 390 |
+
}
|
| 391 |
+
],
|
| 392 |
+
"max_steps": 1682,
|
| 393 |
+
"num_train_epochs": 2,
|
| 394 |
+
"total_flos": 1.9906356553640313e+19,
|
| 395 |
+
"trial_name": null,
|
| 396 |
+
"trial_params": null
|
| 397 |
+
}
|