End of training
Browse files- all_results.json +4 -8
- tokenizer.json +2 -16
- train_results.json +4 -4
- trainer_state.json +22 -331
all_results.json
CHANGED
|
@@ -1,11 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 3.0,
|
| 3 |
-
"
|
| 4 |
-
"
|
| 5 |
-
"
|
| 6 |
-
"
|
| 7 |
-
"train_loss": 0.3778545842638769,
|
| 8 |
-
"train_runtime": 10416.7908,
|
| 9 |
-
"train_samples_per_second": 170.423,
|
| 10 |
-
"train_steps_per_second": 2.663
|
| 11 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 3.0,
|
| 3 |
+
"train_loss": 2.612193721001137,
|
| 4 |
+
"train_runtime": 276.8012,
|
| 5 |
+
"train_samples_per_second": 196.874,
|
| 6 |
+
"train_steps_per_second": 6.156
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
}
|
tokenizer.json
CHANGED
|
@@ -1,21 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
-
"truncation":
|
| 4 |
-
|
| 5 |
-
"max_length": 128,
|
| 6 |
-
"strategy": "LongestFirst",
|
| 7 |
-
"stride": 0
|
| 8 |
-
},
|
| 9 |
-
"padding": {
|
| 10 |
-
"strategy": {
|
| 11 |
-
"Fixed": 128
|
| 12 |
-
},
|
| 13 |
-
"direction": "Right",
|
| 14 |
-
"pad_to_multiple_of": null,
|
| 15 |
-
"pad_id": 1,
|
| 16 |
-
"pad_type_id": 0,
|
| 17 |
-
"pad_token": "<pad>"
|
| 18 |
-
},
|
| 19 |
"added_tokens": [
|
| 20 |
{
|
| 21 |
"id": 0,
|
|
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
+
"truncation": null,
|
| 4 |
+
"padding": null,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
"added_tokens": [
|
| 6 |
{
|
| 7 |
"id": 0,
|
train_results.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 3.0,
|
| 3 |
-
"train_loss":
|
| 4 |
-
"train_runtime":
|
| 5 |
-
"train_samples_per_second":
|
| 6 |
-
"train_steps_per_second":
|
| 7 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 3.0,
|
| 3 |
+
"train_loss": 2.612193721001137,
|
| 4 |
+
"train_runtime": 276.8012,
|
| 5 |
+
"train_samples_per_second": 196.874,
|
| 6 |
+
"train_steps_per_second": 6.156
|
| 7 |
}
|
trainer_state.json
CHANGED
|
@@ -3,358 +3,49 @@
|
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
"epoch": 3.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
-
"epoch": 0.
|
| 13 |
-
"
|
| 14 |
-
"
|
|
|
|
| 15 |
"step": 500
|
| 16 |
},
|
| 17 |
{
|
| 18 |
-
"epoch":
|
| 19 |
-
"
|
| 20 |
-
"
|
|
|
|
| 21 |
"step": 1000
|
| 22 |
},
|
| 23 |
{
|
| 24 |
-
"epoch":
|
| 25 |
-
"
|
| 26 |
-
"
|
|
|
|
| 27 |
"step": 1500
|
| 28 |
},
|
| 29 |
-
{
|
| 30 |
-
"epoch": 0.22,
|
| 31 |
-
"learning_rate": 4.639522728091994e-05,
|
| 32 |
-
"loss": 0.7878,
|
| 33 |
-
"step": 2000
|
| 34 |
-
},
|
| 35 |
-
{
|
| 36 |
-
"epoch": 0.27,
|
| 37 |
-
"learning_rate": 4.5494034101149925e-05,
|
| 38 |
-
"loss": 0.7461,
|
| 39 |
-
"step": 2500
|
| 40 |
-
},
|
| 41 |
-
{
|
| 42 |
-
"epoch": 0.32,
|
| 43 |
-
"learning_rate": 4.459284092137991e-05,
|
| 44 |
-
"loss": 0.7083,
|
| 45 |
-
"step": 3000
|
| 46 |
-
},
|
| 47 |
-
{
|
| 48 |
-
"epoch": 0.38,
|
| 49 |
-
"learning_rate": 4.3691647741609894e-05,
|
| 50 |
-
"loss": 0.6562,
|
| 51 |
-
"step": 3500
|
| 52 |
-
},
|
| 53 |
-
{
|
| 54 |
-
"epoch": 0.43,
|
| 55 |
-
"learning_rate": 4.279045456183988e-05,
|
| 56 |
-
"loss": 0.6378,
|
| 57 |
-
"step": 4000
|
| 58 |
-
},
|
| 59 |
-
{
|
| 60 |
-
"epoch": 0.49,
|
| 61 |
-
"learning_rate": 4.188926138206986e-05,
|
| 62 |
-
"loss": 0.6112,
|
| 63 |
-
"step": 4500
|
| 64 |
-
},
|
| 65 |
-
{
|
| 66 |
-
"epoch": 0.54,
|
| 67 |
-
"learning_rate": 4.098806820229985e-05,
|
| 68 |
-
"loss": 0.5941,
|
| 69 |
-
"step": 5000
|
| 70 |
-
},
|
| 71 |
-
{
|
| 72 |
-
"epoch": 0.59,
|
| 73 |
-
"learning_rate": 4.008687502252983e-05,
|
| 74 |
-
"loss": 0.5657,
|
| 75 |
-
"step": 5500
|
| 76 |
-
},
|
| 77 |
-
{
|
| 78 |
-
"epoch": 0.65,
|
| 79 |
-
"learning_rate": 3.9185681842759816e-05,
|
| 80 |
-
"loss": 0.5425,
|
| 81 |
-
"step": 6000
|
| 82 |
-
},
|
| 83 |
-
{
|
| 84 |
-
"epoch": 0.7,
|
| 85 |
-
"learning_rate": 3.82844886629898e-05,
|
| 86 |
-
"loss": 0.5342,
|
| 87 |
-
"step": 6500
|
| 88 |
-
},
|
| 89 |
-
{
|
| 90 |
-
"epoch": 0.76,
|
| 91 |
-
"learning_rate": 3.7383295483219785e-05,
|
| 92 |
-
"loss": 0.5069,
|
| 93 |
-
"step": 7000
|
| 94 |
-
},
|
| 95 |
-
{
|
| 96 |
-
"epoch": 0.81,
|
| 97 |
-
"learning_rate": 3.648210230344977e-05,
|
| 98 |
-
"loss": 0.4833,
|
| 99 |
-
"step": 7500
|
| 100 |
-
},
|
| 101 |
-
{
|
| 102 |
-
"epoch": 0.87,
|
| 103 |
-
"learning_rate": 3.558090912367975e-05,
|
| 104 |
-
"loss": 0.4735,
|
| 105 |
-
"step": 8000
|
| 106 |
-
},
|
| 107 |
-
{
|
| 108 |
-
"epoch": 0.92,
|
| 109 |
-
"learning_rate": 3.467971594390974e-05,
|
| 110 |
-
"loss": 0.4568,
|
| 111 |
-
"step": 8500
|
| 112 |
-
},
|
| 113 |
-
{
|
| 114 |
-
"epoch": 0.97,
|
| 115 |
-
"learning_rate": 3.3778522764139723e-05,
|
| 116 |
-
"loss": 0.4392,
|
| 117 |
-
"step": 9000
|
| 118 |
-
},
|
| 119 |
-
{
|
| 120 |
-
"epoch": 1.03,
|
| 121 |
-
"learning_rate": 3.287732958436971e-05,
|
| 122 |
-
"loss": 0.3994,
|
| 123 |
-
"step": 9500
|
| 124 |
-
},
|
| 125 |
-
{
|
| 126 |
-
"epoch": 1.08,
|
| 127 |
-
"learning_rate": 3.197613640459969e-05,
|
| 128 |
-
"loss": 0.3682,
|
| 129 |
-
"step": 10000
|
| 130 |
-
},
|
| 131 |
-
{
|
| 132 |
-
"epoch": 1.14,
|
| 133 |
-
"learning_rate": 3.107494322482968e-05,
|
| 134 |
-
"loss": 0.3629,
|
| 135 |
-
"step": 10500
|
| 136 |
-
},
|
| 137 |
-
{
|
| 138 |
-
"epoch": 1.19,
|
| 139 |
-
"learning_rate": 3.017375004505966e-05,
|
| 140 |
-
"loss": 0.3455,
|
| 141 |
-
"step": 11000
|
| 142 |
-
},
|
| 143 |
-
{
|
| 144 |
-
"epoch": 1.24,
|
| 145 |
-
"learning_rate": 2.9272556865289646e-05,
|
| 146 |
-
"loss": 0.3417,
|
| 147 |
-
"step": 11500
|
| 148 |
-
},
|
| 149 |
-
{
|
| 150 |
-
"epoch": 1.3,
|
| 151 |
-
"learning_rate": 2.837136368551963e-05,
|
| 152 |
-
"loss": 0.3347,
|
| 153 |
-
"step": 12000
|
| 154 |
-
},
|
| 155 |
-
{
|
| 156 |
-
"epoch": 1.35,
|
| 157 |
-
"learning_rate": 2.7470170505749615e-05,
|
| 158 |
-
"loss": 0.3316,
|
| 159 |
-
"step": 12500
|
| 160 |
-
},
|
| 161 |
-
{
|
| 162 |
-
"epoch": 1.41,
|
| 163 |
-
"learning_rate": 2.65689773259796e-05,
|
| 164 |
-
"loss": 0.3147,
|
| 165 |
-
"step": 13000
|
| 166 |
-
},
|
| 167 |
-
{
|
| 168 |
-
"epoch": 1.46,
|
| 169 |
-
"learning_rate": 2.5667784146209584e-05,
|
| 170 |
-
"loss": 0.3236,
|
| 171 |
-
"step": 13500
|
| 172 |
-
},
|
| 173 |
-
{
|
| 174 |
-
"epoch": 1.51,
|
| 175 |
-
"learning_rate": 2.476659096643957e-05,
|
| 176 |
-
"loss": 0.3162,
|
| 177 |
-
"step": 14000
|
| 178 |
-
},
|
| 179 |
-
{
|
| 180 |
-
"epoch": 1.57,
|
| 181 |
-
"learning_rate": 2.3865397786669553e-05,
|
| 182 |
-
"loss": 0.2953,
|
| 183 |
-
"step": 14500
|
| 184 |
-
},
|
| 185 |
-
{
|
| 186 |
-
"epoch": 1.62,
|
| 187 |
-
"learning_rate": 2.2964204606899537e-05,
|
| 188 |
-
"loss": 0.3018,
|
| 189 |
-
"step": 15000
|
| 190 |
-
},
|
| 191 |
-
{
|
| 192 |
-
"epoch": 1.68,
|
| 193 |
-
"learning_rate": 2.2063011427129522e-05,
|
| 194 |
-
"loss": 0.2876,
|
| 195 |
-
"step": 15500
|
| 196 |
-
},
|
| 197 |
-
{
|
| 198 |
-
"epoch": 1.73,
|
| 199 |
-
"learning_rate": 2.1161818247359506e-05,
|
| 200 |
-
"loss": 0.2796,
|
| 201 |
-
"step": 16000
|
| 202 |
-
},
|
| 203 |
-
{
|
| 204 |
-
"epoch": 1.78,
|
| 205 |
-
"learning_rate": 2.026062506758949e-05,
|
| 206 |
-
"loss": 0.2749,
|
| 207 |
-
"step": 16500
|
| 208 |
-
},
|
| 209 |
-
{
|
| 210 |
-
"epoch": 1.84,
|
| 211 |
-
"learning_rate": 1.9359431887819472e-05,
|
| 212 |
-
"loss": 0.2718,
|
| 213 |
-
"step": 17000
|
| 214 |
-
},
|
| 215 |
-
{
|
| 216 |
-
"epoch": 1.89,
|
| 217 |
-
"learning_rate": 1.8458238708049457e-05,
|
| 218 |
-
"loss": 0.2716,
|
| 219 |
-
"step": 17500
|
| 220 |
-
},
|
| 221 |
-
{
|
| 222 |
-
"epoch": 1.95,
|
| 223 |
-
"learning_rate": 1.755704552827944e-05,
|
| 224 |
-
"loss": 0.2631,
|
| 225 |
-
"step": 18000
|
| 226 |
-
},
|
| 227 |
-
{
|
| 228 |
-
"epoch": 2.0,
|
| 229 |
-
"learning_rate": 1.6655852348509426e-05,
|
| 230 |
-
"loss": 0.2503,
|
| 231 |
-
"step": 18500
|
| 232 |
-
},
|
| 233 |
-
{
|
| 234 |
-
"epoch": 2.05,
|
| 235 |
-
"learning_rate": 1.575465916873941e-05,
|
| 236 |
-
"loss": 0.2014,
|
| 237 |
-
"step": 19000
|
| 238 |
-
},
|
| 239 |
-
{
|
| 240 |
-
"epoch": 2.11,
|
| 241 |
-
"learning_rate": 1.4853465988969395e-05,
|
| 242 |
-
"loss": 0.1991,
|
| 243 |
-
"step": 19500
|
| 244 |
-
},
|
| 245 |
-
{
|
| 246 |
-
"epoch": 2.16,
|
| 247 |
-
"learning_rate": 1.3952272809199379e-05,
|
| 248 |
-
"loss": 0.191,
|
| 249 |
-
"step": 20000
|
| 250 |
-
},
|
| 251 |
-
{
|
| 252 |
-
"epoch": 2.22,
|
| 253 |
-
"learning_rate": 1.3051079629429367e-05,
|
| 254 |
-
"loss": 0.1931,
|
| 255 |
-
"step": 20500
|
| 256 |
-
},
|
| 257 |
-
{
|
| 258 |
-
"epoch": 2.27,
|
| 259 |
-
"learning_rate": 1.214988644965935e-05,
|
| 260 |
-
"loss": 0.1887,
|
| 261 |
-
"step": 21000
|
| 262 |
-
},
|
| 263 |
-
{
|
| 264 |
-
"epoch": 2.33,
|
| 265 |
-
"learning_rate": 1.1248693269889334e-05,
|
| 266 |
-
"loss": 0.183,
|
| 267 |
-
"step": 21500
|
| 268 |
-
},
|
| 269 |
-
{
|
| 270 |
-
"epoch": 2.38,
|
| 271 |
-
"learning_rate": 1.0347500090119317e-05,
|
| 272 |
-
"loss": 0.1833,
|
| 273 |
-
"step": 22000
|
| 274 |
-
},
|
| 275 |
-
{
|
| 276 |
-
"epoch": 2.43,
|
| 277 |
-
"learning_rate": 9.446306910349303e-06,
|
| 278 |
-
"loss": 0.1779,
|
| 279 |
-
"step": 22500
|
| 280 |
-
},
|
| 281 |
-
{
|
| 282 |
-
"epoch": 2.49,
|
| 283 |
-
"learning_rate": 8.545113730579288e-06,
|
| 284 |
-
"loss": 0.1755,
|
| 285 |
-
"step": 23000
|
| 286 |
-
},
|
| 287 |
-
{
|
| 288 |
-
"epoch": 2.54,
|
| 289 |
-
"learning_rate": 7.643920550809272e-06,
|
| 290 |
-
"loss": 0.1737,
|
| 291 |
-
"step": 23500
|
| 292 |
-
},
|
| 293 |
-
{
|
| 294 |
-
"epoch": 2.6,
|
| 295 |
-
"learning_rate": 6.742727371039257e-06,
|
| 296 |
-
"loss": 0.1723,
|
| 297 |
-
"step": 24000
|
| 298 |
-
},
|
| 299 |
-
{
|
| 300 |
-
"epoch": 2.65,
|
| 301 |
-
"learning_rate": 5.84153419126924e-06,
|
| 302 |
-
"loss": 0.1648,
|
| 303 |
-
"step": 24500
|
| 304 |
-
},
|
| 305 |
-
{
|
| 306 |
-
"epoch": 2.7,
|
| 307 |
-
"learning_rate": 4.940341011499225e-06,
|
| 308 |
-
"loss": 0.1643,
|
| 309 |
-
"step": 25000
|
| 310 |
-
},
|
| 311 |
-
{
|
| 312 |
-
"epoch": 2.76,
|
| 313 |
-
"learning_rate": 4.03914783172921e-06,
|
| 314 |
-
"loss": 0.161,
|
| 315 |
-
"step": 25500
|
| 316 |
-
},
|
| 317 |
-
{
|
| 318 |
-
"epoch": 2.81,
|
| 319 |
-
"learning_rate": 3.1379546519591943e-06,
|
| 320 |
-
"loss": 0.1616,
|
| 321 |
-
"step": 26000
|
| 322 |
-
},
|
| 323 |
-
{
|
| 324 |
-
"epoch": 2.87,
|
| 325 |
-
"learning_rate": 2.2367614721891784e-06,
|
| 326 |
-
"loss": 0.1559,
|
| 327 |
-
"step": 26500
|
| 328 |
-
},
|
| 329 |
-
{
|
| 330 |
-
"epoch": 2.92,
|
| 331 |
-
"learning_rate": 1.335568292419163e-06,
|
| 332 |
-
"loss": 0.1589,
|
| 333 |
-
"step": 27000
|
| 334 |
-
},
|
| 335 |
-
{
|
| 336 |
-
"epoch": 2.97,
|
| 337 |
-
"learning_rate": 4.3437511264914753e-07,
|
| 338 |
-
"loss": 0.1537,
|
| 339 |
-
"step": 27500
|
| 340 |
-
},
|
| 341 |
{
|
| 342 |
"epoch": 3.0,
|
| 343 |
-
"step":
|
| 344 |
-
"total_flos":
|
| 345 |
-
"train_loss":
|
| 346 |
-
"train_runtime":
|
| 347 |
-
"train_samples_per_second":
|
| 348 |
-
"train_steps_per_second":
|
| 349 |
}
|
| 350 |
],
|
| 351 |
"logging_steps": 500,
|
| 352 |
-
"max_steps":
|
| 353 |
"num_input_tokens_seen": 0,
|
| 354 |
"num_train_epochs": 3,
|
| 355 |
"save_steps": 500,
|
| 356 |
-
"total_flos":
|
| 357 |
-
"train_batch_size":
|
| 358 |
"trial_name": null,
|
| 359 |
"trial_params": null
|
| 360 |
}
|
|
|
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
"epoch": 3.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 1704,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
+
"epoch": 0.88,
|
| 13 |
+
"grad_norm": 12.444563865661621,
|
| 14 |
+
"learning_rate": 3.532863849765258e-05,
|
| 15 |
+
"loss": 3.0578,
|
| 16 |
"step": 500
|
| 17 |
},
|
| 18 |
{
|
| 19 |
+
"epoch": 1.76,
|
| 20 |
+
"grad_norm": 8.964831352233887,
|
| 21 |
+
"learning_rate": 2.0657276995305167e-05,
|
| 22 |
+
"loss": 2.7481,
|
| 23 |
"step": 1000
|
| 24 |
},
|
| 25 |
{
|
| 26 |
+
"epoch": 2.64,
|
| 27 |
+
"grad_norm": 16.21776008605957,
|
| 28 |
+
"learning_rate": 5.9859154929577465e-06,
|
| 29 |
+
"loss": 2.2776,
|
| 30 |
"step": 1500
|
| 31 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 32 |
{
|
| 33 |
"epoch": 3.0,
|
| 34 |
+
"step": 1704,
|
| 35 |
+
"total_flos": 7276024173600000.0,
|
| 36 |
+
"train_loss": 2.612193721001137,
|
| 37 |
+
"train_runtime": 276.8012,
|
| 38 |
+
"train_samples_per_second": 196.874,
|
| 39 |
+
"train_steps_per_second": 6.156
|
| 40 |
}
|
| 41 |
],
|
| 42 |
"logging_steps": 500,
|
| 43 |
+
"max_steps": 1704,
|
| 44 |
"num_input_tokens_seen": 0,
|
| 45 |
"num_train_epochs": 3,
|
| 46 |
"save_steps": 500,
|
| 47 |
+
"total_flos": 7276024173600000.0,
|
| 48 |
+
"train_batch_size": 32,
|
| 49 |
"trial_name": null,
|
| 50 |
"trial_params": null
|
| 51 |
}
|