End of training
Browse files- README.md +9 -7
- config.json +1 -1
- logs/events.out.tfevents.1707056479.6b8ef76803b7.26.0 +3 -0
- model.safetensors +1 -1
- trainer_state.json +19 -915
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -1,4 +1,6 @@
|
|
| 1 |
---
|
|
|
|
|
|
|
| 2 |
tags:
|
| 3 |
- generated_from_trainer
|
| 4 |
model-index:
|
|
@@ -11,14 +13,14 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 11 |
|
| 12 |
# controlled-food-recipe-generation
|
| 13 |
|
| 14 |
-
This model
|
| 15 |
It achieves the following results on the evaluation set:
|
| 16 |
-
- eval_loss: 1.
|
| 17 |
-
- eval_runtime:
|
| 18 |
-
- eval_samples_per_second:
|
| 19 |
-
- eval_steps_per_second:
|
| 20 |
-
- epoch:
|
| 21 |
-
- step:
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
|
|
| 1 |
---
|
| 2 |
+
license: mit
|
| 3 |
+
base_model: gpt2
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
| 6 |
model-index:
|
|
|
|
| 13 |
|
| 14 |
# controlled-food-recipe-generation
|
| 15 |
|
| 16 |
+
This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
+
- eval_loss: 1.0261
|
| 19 |
+
- eval_runtime: 1432.5553
|
| 20 |
+
- eval_samples_per_second: 104.708
|
| 21 |
+
- eval_steps_per_second: 1.636
|
| 22 |
+
- epoch: 1.19
|
| 23 |
+
- step: 50000
|
| 24 |
|
| 25 |
## Model description
|
| 26 |
|
config.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "
|
| 3 |
"activation_function": "gelu_new",
|
| 4 |
"architectures": [
|
| 5 |
"GPT2LMHeadModel"
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "gpt2",
|
| 3 |
"activation_function": "gelu_new",
|
| 4 |
"architectures": [
|
| 5 |
"GPT2LMHeadModel"
|
logs/events.out.tfevents.1707056479.6b8ef76803b7.26.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a955400898c05287b5b58720427850d09aa1706c6a220d4c70d8cc3f13652102
|
| 3 |
+
size 5081
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 497918592
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:167443881e7d10287201ffedb2a2f6354b36719d8c5ceb86c2538e5de6b97c7b
|
| 3 |
size 497918592
|
trainer_state.json
CHANGED
|
@@ -1,930 +1,34 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric":
|
| 3 |
-
"best_model_checkpoint":
|
| 4 |
-
"epoch":
|
| 5 |
-
"eval_steps":
|
| 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": 1.
|
| 13 |
-
"learning_rate":
|
| 14 |
-
"loss":
|
| 15 |
-
"step":
|
| 16 |
},
|
| 17 |
{
|
| 18 |
-
"epoch": 1.
|
| 19 |
-
"eval_loss":
|
| 20 |
-
"eval_runtime":
|
| 21 |
-
"eval_samples_per_second":
|
| 22 |
-
"eval_steps_per_second":
|
| 23 |
-
"step":
|
| 24 |
-
},
|
| 25 |
-
{
|
| 26 |
-
"epoch": 2.0,
|
| 27 |
-
"learning_rate": 5e-05,
|
| 28 |
-
"loss": 78.2388,
|
| 29 |
-
"step": 2
|
| 30 |
-
},
|
| 31 |
-
{
|
| 32 |
-
"epoch": 2.0,
|
| 33 |
-
"eval_loss": 76.51811981201172,
|
| 34 |
-
"eval_runtime": 0.0201,
|
| 35 |
-
"eval_samples_per_second": 49.811,
|
| 36 |
-
"eval_steps_per_second": 49.811,
|
| 37 |
-
"step": 2
|
| 38 |
-
},
|
| 39 |
-
{
|
| 40 |
-
"epoch": 3.0,
|
| 41 |
-
"learning_rate": 5e-05,
|
| 42 |
-
"loss": 77.0195,
|
| 43 |
-
"step": 3
|
| 44 |
-
},
|
| 45 |
-
{
|
| 46 |
-
"epoch": 3.0,
|
| 47 |
-
"eval_loss": 76.51811981201172,
|
| 48 |
-
"eval_runtime": 0.0202,
|
| 49 |
-
"eval_samples_per_second": 49.475,
|
| 50 |
-
"eval_steps_per_second": 49.475,
|
| 51 |
-
"step": 3
|
| 52 |
-
},
|
| 53 |
-
{
|
| 54 |
-
"epoch": 4.0,
|
| 55 |
-
"learning_rate": 5e-05,
|
| 56 |
-
"loss": 77.6197,
|
| 57 |
-
"step": 4
|
| 58 |
-
},
|
| 59 |
-
{
|
| 60 |
-
"epoch": 4.0,
|
| 61 |
-
"eval_loss": 76.51811981201172,
|
| 62 |
-
"eval_runtime": 0.0199,
|
| 63 |
-
"eval_samples_per_second": 50.171,
|
| 64 |
-
"eval_steps_per_second": 50.171,
|
| 65 |
-
"step": 4
|
| 66 |
-
},
|
| 67 |
-
{
|
| 68 |
-
"epoch": 5.0,
|
| 69 |
-
"learning_rate": 5e-05,
|
| 70 |
-
"loss": 77.8364,
|
| 71 |
-
"step": 5
|
| 72 |
-
},
|
| 73 |
-
{
|
| 74 |
-
"epoch": 5.0,
|
| 75 |
-
"eval_loss": 76.51811981201172,
|
| 76 |
-
"eval_runtime": 0.02,
|
| 77 |
-
"eval_samples_per_second": 50.05,
|
| 78 |
-
"eval_steps_per_second": 50.05,
|
| 79 |
-
"step": 5
|
| 80 |
-
},
|
| 81 |
-
{
|
| 82 |
-
"epoch": 6.0,
|
| 83 |
-
"learning_rate": 5e-05,
|
| 84 |
-
"loss": 77.9326,
|
| 85 |
-
"step": 6
|
| 86 |
-
},
|
| 87 |
-
{
|
| 88 |
-
"epoch": 6.0,
|
| 89 |
-
"eval_loss": 76.51811981201172,
|
| 90 |
-
"eval_runtime": 0.02,
|
| 91 |
-
"eval_samples_per_second": 49.998,
|
| 92 |
-
"eval_steps_per_second": 49.998,
|
| 93 |
-
"step": 6
|
| 94 |
-
},
|
| 95 |
-
{
|
| 96 |
-
"epoch": 7.0,
|
| 97 |
-
"learning_rate": 5e-05,
|
| 98 |
-
"loss": 77.1428,
|
| 99 |
-
"step": 7
|
| 100 |
-
},
|
| 101 |
-
{
|
| 102 |
-
"epoch": 7.0,
|
| 103 |
-
"eval_loss": 76.51811981201172,
|
| 104 |
-
"eval_runtime": 0.0203,
|
| 105 |
-
"eval_samples_per_second": 49.376,
|
| 106 |
-
"eval_steps_per_second": 49.376,
|
| 107 |
-
"step": 7
|
| 108 |
-
},
|
| 109 |
-
{
|
| 110 |
-
"epoch": 8.0,
|
| 111 |
-
"learning_rate": 5e-05,
|
| 112 |
-
"loss": 77.9131,
|
| 113 |
-
"step": 8
|
| 114 |
-
},
|
| 115 |
-
{
|
| 116 |
-
"epoch": 8.0,
|
| 117 |
-
"eval_loss": 76.51811981201172,
|
| 118 |
-
"eval_runtime": 0.0197,
|
| 119 |
-
"eval_samples_per_second": 50.657,
|
| 120 |
-
"eval_steps_per_second": 50.657,
|
| 121 |
-
"step": 8
|
| 122 |
-
},
|
| 123 |
-
{
|
| 124 |
-
"epoch": 9.0,
|
| 125 |
-
"learning_rate": 4.9500000000000004e-05,
|
| 126 |
-
"loss": 77.8046,
|
| 127 |
-
"step": 9
|
| 128 |
-
},
|
| 129 |
-
{
|
| 130 |
-
"epoch": 9.0,
|
| 131 |
-
"eval_loss": 46.12736129760742,
|
| 132 |
-
"eval_runtime": 0.0203,
|
| 133 |
-
"eval_samples_per_second": 49.335,
|
| 134 |
-
"eval_steps_per_second": 49.335,
|
| 135 |
-
"step": 9
|
| 136 |
-
},
|
| 137 |
-
{
|
| 138 |
-
"epoch": 10.0,
|
| 139 |
-
"learning_rate": 4.9e-05,
|
| 140 |
-
"loss": 35.9262,
|
| 141 |
-
"step": 10
|
| 142 |
-
},
|
| 143 |
-
{
|
| 144 |
-
"epoch": 10.0,
|
| 145 |
-
"eval_loss": 42.20186233520508,
|
| 146 |
-
"eval_runtime": 0.0212,
|
| 147 |
-
"eval_samples_per_second": 47.156,
|
| 148 |
-
"eval_steps_per_second": 47.156,
|
| 149 |
-
"step": 10
|
| 150 |
-
},
|
| 151 |
-
{
|
| 152 |
-
"epoch": 11.0,
|
| 153 |
-
"learning_rate": 4.85e-05,
|
| 154 |
-
"loss": 24.7783,
|
| 155 |
-
"step": 11
|
| 156 |
-
},
|
| 157 |
-
{
|
| 158 |
-
"epoch": 11.0,
|
| 159 |
-
"eval_loss": 21.848590850830078,
|
| 160 |
-
"eval_runtime": 0.0209,
|
| 161 |
-
"eval_samples_per_second": 47.862,
|
| 162 |
-
"eval_steps_per_second": 47.862,
|
| 163 |
-
"step": 11
|
| 164 |
-
},
|
| 165 |
-
{
|
| 166 |
-
"epoch": 12.0,
|
| 167 |
-
"learning_rate": 4.8e-05,
|
| 168 |
-
"loss": 11.8436,
|
| 169 |
-
"step": 12
|
| 170 |
-
},
|
| 171 |
-
{
|
| 172 |
-
"epoch": 12.0,
|
| 173 |
-
"eval_loss": 10.201495170593262,
|
| 174 |
-
"eval_runtime": 0.0205,
|
| 175 |
-
"eval_samples_per_second": 48.692,
|
| 176 |
-
"eval_steps_per_second": 48.692,
|
| 177 |
-
"step": 12
|
| 178 |
-
},
|
| 179 |
-
{
|
| 180 |
-
"epoch": 13.0,
|
| 181 |
-
"learning_rate": 4.75e-05,
|
| 182 |
-
"loss": 8.908,
|
| 183 |
-
"step": 13
|
| 184 |
-
},
|
| 185 |
-
{
|
| 186 |
-
"epoch": 13.0,
|
| 187 |
-
"eval_loss": 11.220573425292969,
|
| 188 |
-
"eval_runtime": 0.0213,
|
| 189 |
-
"eval_samples_per_second": 46.959,
|
| 190 |
-
"eval_steps_per_second": 46.959,
|
| 191 |
-
"step": 13
|
| 192 |
-
},
|
| 193 |
-
{
|
| 194 |
-
"epoch": 14.0,
|
| 195 |
-
"learning_rate": 4.7e-05,
|
| 196 |
-
"loss": 7.022,
|
| 197 |
-
"step": 14
|
| 198 |
-
},
|
| 199 |
-
{
|
| 200 |
-
"epoch": 14.0,
|
| 201 |
-
"eval_loss": 9.170014381408691,
|
| 202 |
-
"eval_runtime": 0.0227,
|
| 203 |
-
"eval_samples_per_second": 44.006,
|
| 204 |
-
"eval_steps_per_second": 44.006,
|
| 205 |
-
"step": 14
|
| 206 |
-
},
|
| 207 |
-
{
|
| 208 |
-
"epoch": 15.0,
|
| 209 |
-
"learning_rate": 4.6500000000000005e-05,
|
| 210 |
-
"loss": 6.3525,
|
| 211 |
-
"step": 15
|
| 212 |
-
},
|
| 213 |
-
{
|
| 214 |
-
"epoch": 15.0,
|
| 215 |
-
"eval_loss": 6.997350215911865,
|
| 216 |
-
"eval_runtime": 0.0211,
|
| 217 |
-
"eval_samples_per_second": 47.457,
|
| 218 |
-
"eval_steps_per_second": 47.457,
|
| 219 |
-
"step": 15
|
| 220 |
-
},
|
| 221 |
-
{
|
| 222 |
-
"epoch": 16.0,
|
| 223 |
-
"learning_rate": 4.600000000000001e-05,
|
| 224 |
-
"loss": 5.6621,
|
| 225 |
-
"step": 16
|
| 226 |
-
},
|
| 227 |
-
{
|
| 228 |
-
"epoch": 16.0,
|
| 229 |
-
"eval_loss": 4.715316295623779,
|
| 230 |
-
"eval_runtime": 0.0208,
|
| 231 |
-
"eval_samples_per_second": 48.084,
|
| 232 |
-
"eval_steps_per_second": 48.084,
|
| 233 |
-
"step": 16
|
| 234 |
-
},
|
| 235 |
-
{
|
| 236 |
-
"epoch": 17.0,
|
| 237 |
-
"learning_rate": 5e-05,
|
| 238 |
-
"loss": 5.8038,
|
| 239 |
-
"step": 17
|
| 240 |
-
},
|
| 241 |
-
{
|
| 242 |
-
"epoch": 17.0,
|
| 243 |
-
"eval_loss": 4.024607181549072,
|
| 244 |
-
"eval_runtime": 0.0201,
|
| 245 |
-
"eval_samples_per_second": 49.72,
|
| 246 |
-
"eval_steps_per_second": 49.72,
|
| 247 |
-
"step": 17
|
| 248 |
-
},
|
| 249 |
-
{
|
| 250 |
-
"epoch": 18.0,
|
| 251 |
-
"learning_rate": 5e-05,
|
| 252 |
-
"loss": 5.6281,
|
| 253 |
-
"step": 18
|
| 254 |
-
},
|
| 255 |
-
{
|
| 256 |
-
"epoch": 18.0,
|
| 257 |
-
"eval_loss": 4.024607181549072,
|
| 258 |
-
"eval_runtime": 0.0191,
|
| 259 |
-
"eval_samples_per_second": 52.343,
|
| 260 |
-
"eval_steps_per_second": 52.343,
|
| 261 |
-
"step": 18
|
| 262 |
-
},
|
| 263 |
-
{
|
| 264 |
-
"epoch": 19.0,
|
| 265 |
-
"learning_rate": 5e-05,
|
| 266 |
-
"loss": 5.4614,
|
| 267 |
-
"step": 19
|
| 268 |
-
},
|
| 269 |
-
{
|
| 270 |
-
"epoch": 19.0,
|
| 271 |
-
"eval_loss": 4.024607181549072,
|
| 272 |
-
"eval_runtime": 0.0197,
|
| 273 |
-
"eval_samples_per_second": 50.703,
|
| 274 |
-
"eval_steps_per_second": 50.703,
|
| 275 |
-
"step": 19
|
| 276 |
-
},
|
| 277 |
-
{
|
| 278 |
-
"epoch": 20.0,
|
| 279 |
-
"learning_rate": 5e-05,
|
| 280 |
-
"loss": 5.5227,
|
| 281 |
-
"step": 20
|
| 282 |
-
},
|
| 283 |
-
{
|
| 284 |
-
"epoch": 20.0,
|
| 285 |
-
"eval_loss": 4.024607181549072,
|
| 286 |
-
"eval_runtime": 0.0208,
|
| 287 |
-
"eval_samples_per_second": 48.085,
|
| 288 |
-
"eval_steps_per_second": 48.085,
|
| 289 |
-
"step": 20
|
| 290 |
-
},
|
| 291 |
-
{
|
| 292 |
-
"epoch": 21.0,
|
| 293 |
-
"learning_rate": 4.9500000000000004e-05,
|
| 294 |
-
"loss": 5.2292,
|
| 295 |
-
"step": 21
|
| 296 |
-
},
|
| 297 |
-
{
|
| 298 |
-
"epoch": 21.0,
|
| 299 |
-
"eval_loss": 3.1571905612945557,
|
| 300 |
-
"eval_runtime": 0.02,
|
| 301 |
-
"eval_samples_per_second": 50.062,
|
| 302 |
-
"eval_steps_per_second": 50.062,
|
| 303 |
-
"step": 21
|
| 304 |
-
},
|
| 305 |
-
{
|
| 306 |
-
"epoch": 22.0,
|
| 307 |
-
"learning_rate": 4.9e-05,
|
| 308 |
-
"loss": 4.6673,
|
| 309 |
-
"step": 22
|
| 310 |
-
},
|
| 311 |
-
{
|
| 312 |
-
"epoch": 22.0,
|
| 313 |
-
"eval_loss": 2.9552078247070312,
|
| 314 |
-
"eval_runtime": 0.0218,
|
| 315 |
-
"eval_samples_per_second": 45.876,
|
| 316 |
-
"eval_steps_per_second": 45.876,
|
| 317 |
-
"step": 22
|
| 318 |
-
},
|
| 319 |
-
{
|
| 320 |
-
"epoch": 23.0,
|
| 321 |
-
"learning_rate": 4.85e-05,
|
| 322 |
-
"loss": 4.9696,
|
| 323 |
-
"step": 23
|
| 324 |
-
},
|
| 325 |
-
{
|
| 326 |
-
"epoch": 23.0,
|
| 327 |
-
"eval_loss": 2.9095003604888916,
|
| 328 |
-
"eval_runtime": 0.0216,
|
| 329 |
-
"eval_samples_per_second": 46.366,
|
| 330 |
-
"eval_steps_per_second": 46.366,
|
| 331 |
-
"step": 23
|
| 332 |
-
},
|
| 333 |
-
{
|
| 334 |
-
"epoch": 24.0,
|
| 335 |
-
"learning_rate": 4.8e-05,
|
| 336 |
-
"loss": 4.1183,
|
| 337 |
-
"step": 24
|
| 338 |
-
},
|
| 339 |
-
{
|
| 340 |
-
"epoch": 24.0,
|
| 341 |
-
"eval_loss": 2.6673200130462646,
|
| 342 |
-
"eval_runtime": 0.0208,
|
| 343 |
-
"eval_samples_per_second": 48.003,
|
| 344 |
-
"eval_steps_per_second": 48.003,
|
| 345 |
-
"step": 24
|
| 346 |
-
},
|
| 347 |
-
{
|
| 348 |
-
"epoch": 25.0,
|
| 349 |
-
"learning_rate": 4.75e-05,
|
| 350 |
-
"loss": 3.8033,
|
| 351 |
-
"step": 25
|
| 352 |
-
},
|
| 353 |
-
{
|
| 354 |
-
"epoch": 25.0,
|
| 355 |
-
"eval_loss": 2.3663747310638428,
|
| 356 |
-
"eval_runtime": 0.0208,
|
| 357 |
-
"eval_samples_per_second": 47.966,
|
| 358 |
-
"eval_steps_per_second": 47.966,
|
| 359 |
-
"step": 25
|
| 360 |
-
},
|
| 361 |
-
{
|
| 362 |
-
"epoch": 26.0,
|
| 363 |
-
"learning_rate": 4.7e-05,
|
| 364 |
-
"loss": 3.6167,
|
| 365 |
-
"step": 26
|
| 366 |
-
},
|
| 367 |
-
{
|
| 368 |
-
"epoch": 26.0,
|
| 369 |
-
"eval_loss": 2.278635025024414,
|
| 370 |
-
"eval_runtime": 0.0194,
|
| 371 |
-
"eval_samples_per_second": 51.613,
|
| 372 |
-
"eval_steps_per_second": 51.613,
|
| 373 |
-
"step": 26
|
| 374 |
-
},
|
| 375 |
-
{
|
| 376 |
-
"epoch": 27.0,
|
| 377 |
-
"learning_rate": 4.6500000000000005e-05,
|
| 378 |
-
"loss": 3.4501,
|
| 379 |
-
"step": 27
|
| 380 |
-
},
|
| 381 |
-
{
|
| 382 |
-
"epoch": 27.0,
|
| 383 |
-
"eval_loss": 2.2132723331451416,
|
| 384 |
-
"eval_runtime": 0.0197,
|
| 385 |
-
"eval_samples_per_second": 50.812,
|
| 386 |
-
"eval_steps_per_second": 50.812,
|
| 387 |
-
"step": 27
|
| 388 |
-
},
|
| 389 |
-
{
|
| 390 |
-
"epoch": 28.0,
|
| 391 |
-
"learning_rate": 4.600000000000001e-05,
|
| 392 |
-
"loss": 3.2932,
|
| 393 |
-
"step": 28
|
| 394 |
-
},
|
| 395 |
-
{
|
| 396 |
-
"epoch": 28.0,
|
| 397 |
-
"eval_loss": 2.1897881031036377,
|
| 398 |
-
"eval_runtime": 0.0192,
|
| 399 |
-
"eval_samples_per_second": 52.029,
|
| 400 |
-
"eval_steps_per_second": 52.029,
|
| 401 |
-
"step": 28
|
| 402 |
-
},
|
| 403 |
-
{
|
| 404 |
-
"epoch": 29.0,
|
| 405 |
-
"learning_rate": 4.55e-05,
|
| 406 |
-
"loss": 3.1358,
|
| 407 |
-
"step": 29
|
| 408 |
-
},
|
| 409 |
-
{
|
| 410 |
-
"epoch": 29.0,
|
| 411 |
-
"eval_loss": 2.131443738937378,
|
| 412 |
-
"eval_runtime": 0.0209,
|
| 413 |
-
"eval_samples_per_second": 47.849,
|
| 414 |
-
"eval_steps_per_second": 47.849,
|
| 415 |
-
"step": 29
|
| 416 |
-
},
|
| 417 |
-
{
|
| 418 |
-
"epoch": 30.0,
|
| 419 |
-
"learning_rate": 4.5e-05,
|
| 420 |
-
"loss": 3.1239,
|
| 421 |
-
"step": 30
|
| 422 |
-
},
|
| 423 |
-
{
|
| 424 |
-
"epoch": 30.0,
|
| 425 |
-
"eval_loss": 2.0433859825134277,
|
| 426 |
-
"eval_runtime": 0.0229,
|
| 427 |
-
"eval_samples_per_second": 43.73,
|
| 428 |
-
"eval_steps_per_second": 43.73,
|
| 429 |
-
"step": 30
|
| 430 |
-
},
|
| 431 |
-
{
|
| 432 |
-
"epoch": 31.0,
|
| 433 |
-
"learning_rate": 4.4500000000000004e-05,
|
| 434 |
-
"loss": 2.9609,
|
| 435 |
-
"step": 31
|
| 436 |
-
},
|
| 437 |
-
{
|
| 438 |
-
"epoch": 31.0,
|
| 439 |
-
"eval_loss": 1.9398747682571411,
|
| 440 |
-
"eval_runtime": 0.0205,
|
| 441 |
-
"eval_samples_per_second": 48.772,
|
| 442 |
-
"eval_steps_per_second": 48.772,
|
| 443 |
-
"step": 31
|
| 444 |
-
},
|
| 445 |
-
{
|
| 446 |
-
"epoch": 32.0,
|
| 447 |
-
"learning_rate": 4.4000000000000006e-05,
|
| 448 |
-
"loss": 2.8511,
|
| 449 |
-
"step": 32
|
| 450 |
-
},
|
| 451 |
-
{
|
| 452 |
-
"epoch": 32.0,
|
| 453 |
-
"eval_loss": 1.8651390075683594,
|
| 454 |
-
"eval_runtime": 0.0254,
|
| 455 |
-
"eval_samples_per_second": 39.429,
|
| 456 |
-
"eval_steps_per_second": 39.429,
|
| 457 |
-
"step": 32
|
| 458 |
-
},
|
| 459 |
-
{
|
| 460 |
-
"epoch": 33.0,
|
| 461 |
-
"learning_rate": 4.35e-05,
|
| 462 |
-
"loss": 2.8323,
|
| 463 |
-
"step": 33
|
| 464 |
-
},
|
| 465 |
-
{
|
| 466 |
-
"epoch": 33.0,
|
| 467 |
-
"eval_loss": 1.8202353715896606,
|
| 468 |
-
"eval_runtime": 0.0198,
|
| 469 |
-
"eval_samples_per_second": 50.491,
|
| 470 |
-
"eval_steps_per_second": 50.491,
|
| 471 |
-
"step": 33
|
| 472 |
-
},
|
| 473 |
-
{
|
| 474 |
-
"epoch": 34.0,
|
| 475 |
-
"learning_rate": 4.3e-05,
|
| 476 |
-
"loss": 2.7235,
|
| 477 |
-
"step": 34
|
| 478 |
-
},
|
| 479 |
-
{
|
| 480 |
-
"epoch": 34.0,
|
| 481 |
-
"eval_loss": 1.7782583236694336,
|
| 482 |
-
"eval_runtime": 0.0204,
|
| 483 |
-
"eval_samples_per_second": 49.011,
|
| 484 |
-
"eval_steps_per_second": 49.011,
|
| 485 |
-
"step": 34
|
| 486 |
-
},
|
| 487 |
-
{
|
| 488 |
-
"epoch": 35.0,
|
| 489 |
-
"learning_rate": 4.25e-05,
|
| 490 |
-
"loss": 2.534,
|
| 491 |
-
"step": 35
|
| 492 |
-
},
|
| 493 |
-
{
|
| 494 |
-
"epoch": 35.0,
|
| 495 |
-
"eval_loss": 1.7466678619384766,
|
| 496 |
-
"eval_runtime": 0.0204,
|
| 497 |
-
"eval_samples_per_second": 48.995,
|
| 498 |
-
"eval_steps_per_second": 48.995,
|
| 499 |
-
"step": 35
|
| 500 |
-
},
|
| 501 |
-
{
|
| 502 |
-
"epoch": 36.0,
|
| 503 |
-
"learning_rate": 4.2e-05,
|
| 504 |
-
"loss": 2.4176,
|
| 505 |
-
"step": 36
|
| 506 |
-
},
|
| 507 |
-
{
|
| 508 |
-
"epoch": 36.0,
|
| 509 |
-
"eval_loss": 1.7186834812164307,
|
| 510 |
-
"eval_runtime": 0.0197,
|
| 511 |
-
"eval_samples_per_second": 50.712,
|
| 512 |
-
"eval_steps_per_second": 50.712,
|
| 513 |
-
"step": 36
|
| 514 |
-
},
|
| 515 |
-
{
|
| 516 |
-
"epoch": 37.0,
|
| 517 |
-
"learning_rate": 4.15e-05,
|
| 518 |
-
"loss": 2.3308,
|
| 519 |
-
"step": 37
|
| 520 |
-
},
|
| 521 |
-
{
|
| 522 |
-
"epoch": 37.0,
|
| 523 |
-
"eval_loss": 1.6936513185501099,
|
| 524 |
-
"eval_runtime": 0.021,
|
| 525 |
-
"eval_samples_per_second": 47.662,
|
| 526 |
-
"eval_steps_per_second": 47.662,
|
| 527 |
-
"step": 37
|
| 528 |
-
},
|
| 529 |
-
{
|
| 530 |
-
"epoch": 38.0,
|
| 531 |
-
"learning_rate": 4.1e-05,
|
| 532 |
-
"loss": 2.2995,
|
| 533 |
-
"step": 38
|
| 534 |
-
},
|
| 535 |
-
{
|
| 536 |
-
"epoch": 38.0,
|
| 537 |
-
"eval_loss": 1.666297197341919,
|
| 538 |
-
"eval_runtime": 0.0199,
|
| 539 |
-
"eval_samples_per_second": 50.261,
|
| 540 |
-
"eval_steps_per_second": 50.261,
|
| 541 |
-
"step": 38
|
| 542 |
-
},
|
| 543 |
-
{
|
| 544 |
-
"epoch": 39.0,
|
| 545 |
-
"learning_rate": 4.05e-05,
|
| 546 |
-
"loss": 2.202,
|
| 547 |
-
"step": 39
|
| 548 |
-
},
|
| 549 |
-
{
|
| 550 |
-
"epoch": 39.0,
|
| 551 |
-
"eval_loss": 1.6525242328643799,
|
| 552 |
-
"eval_runtime": 0.0201,
|
| 553 |
-
"eval_samples_per_second": 49.718,
|
| 554 |
-
"eval_steps_per_second": 49.718,
|
| 555 |
-
"step": 39
|
| 556 |
-
},
|
| 557 |
-
{
|
| 558 |
-
"epoch": 40.0,
|
| 559 |
-
"learning_rate": 4e-05,
|
| 560 |
-
"loss": 2.1826,
|
| 561 |
-
"step": 40
|
| 562 |
-
},
|
| 563 |
-
{
|
| 564 |
-
"epoch": 40.0,
|
| 565 |
-
"eval_loss": 1.6410127878189087,
|
| 566 |
-
"eval_runtime": 0.0198,
|
| 567 |
-
"eval_samples_per_second": 50.533,
|
| 568 |
-
"eval_steps_per_second": 50.533,
|
| 569 |
-
"step": 40
|
| 570 |
-
},
|
| 571 |
-
{
|
| 572 |
-
"epoch": 41.0,
|
| 573 |
-
"learning_rate": 3.9500000000000005e-05,
|
| 574 |
-
"loss": 2.0815,
|
| 575 |
-
"step": 41
|
| 576 |
-
},
|
| 577 |
-
{
|
| 578 |
-
"epoch": 41.0,
|
| 579 |
-
"eval_loss": 1.6258727312088013,
|
| 580 |
-
"eval_runtime": 0.0204,
|
| 581 |
-
"eval_samples_per_second": 49.053,
|
| 582 |
-
"eval_steps_per_second": 49.053,
|
| 583 |
-
"step": 41
|
| 584 |
-
},
|
| 585 |
-
{
|
| 586 |
-
"epoch": 42.0,
|
| 587 |
-
"learning_rate": 3.9000000000000006e-05,
|
| 588 |
-
"loss": 2.0493,
|
| 589 |
-
"step": 42
|
| 590 |
-
},
|
| 591 |
-
{
|
| 592 |
-
"epoch": 42.0,
|
| 593 |
-
"eval_loss": 1.6132334470748901,
|
| 594 |
-
"eval_runtime": 0.0199,
|
| 595 |
-
"eval_samples_per_second": 50.174,
|
| 596 |
-
"eval_steps_per_second": 50.174,
|
| 597 |
-
"step": 42
|
| 598 |
-
},
|
| 599 |
-
{
|
| 600 |
-
"epoch": 43.0,
|
| 601 |
-
"learning_rate": 3.85e-05,
|
| 602 |
-
"loss": 1.9386,
|
| 603 |
-
"step": 43
|
| 604 |
-
},
|
| 605 |
-
{
|
| 606 |
-
"epoch": 43.0,
|
| 607 |
-
"eval_loss": 1.6055489778518677,
|
| 608 |
-
"eval_runtime": 0.0202,
|
| 609 |
-
"eval_samples_per_second": 49.408,
|
| 610 |
-
"eval_steps_per_second": 49.408,
|
| 611 |
-
"step": 43
|
| 612 |
-
},
|
| 613 |
-
{
|
| 614 |
-
"epoch": 44.0,
|
| 615 |
-
"learning_rate": 3.8e-05,
|
| 616 |
-
"loss": 1.8849,
|
| 617 |
-
"step": 44
|
| 618 |
-
},
|
| 619 |
-
{
|
| 620 |
-
"epoch": 44.0,
|
| 621 |
-
"eval_loss": 1.6034255027770996,
|
| 622 |
-
"eval_runtime": 0.0195,
|
| 623 |
-
"eval_samples_per_second": 51.165,
|
| 624 |
-
"eval_steps_per_second": 51.165,
|
| 625 |
-
"step": 44
|
| 626 |
-
},
|
| 627 |
-
{
|
| 628 |
-
"epoch": 45.0,
|
| 629 |
-
"learning_rate": 3.7500000000000003e-05,
|
| 630 |
-
"loss": 1.783,
|
| 631 |
-
"step": 45
|
| 632 |
-
},
|
| 633 |
-
{
|
| 634 |
-
"epoch": 45.0,
|
| 635 |
-
"eval_loss": 1.607292890548706,
|
| 636 |
-
"eval_runtime": 0.0198,
|
| 637 |
-
"eval_samples_per_second": 50.498,
|
| 638 |
-
"eval_steps_per_second": 50.498,
|
| 639 |
-
"step": 45
|
| 640 |
-
},
|
| 641 |
-
{
|
| 642 |
-
"epoch": 46.0,
|
| 643 |
-
"learning_rate": 3.7e-05,
|
| 644 |
-
"loss": 1.8884,
|
| 645 |
-
"step": 46
|
| 646 |
-
},
|
| 647 |
-
{
|
| 648 |
-
"epoch": 46.0,
|
| 649 |
-
"eval_loss": 1.612091302871704,
|
| 650 |
-
"eval_runtime": 0.0214,
|
| 651 |
-
"eval_samples_per_second": 46.624,
|
| 652 |
-
"eval_steps_per_second": 46.624,
|
| 653 |
-
"step": 46
|
| 654 |
-
},
|
| 655 |
-
{
|
| 656 |
-
"epoch": 47.0,
|
| 657 |
-
"learning_rate": 3.65e-05,
|
| 658 |
-
"loss": 1.7434,
|
| 659 |
-
"step": 47
|
| 660 |
-
},
|
| 661 |
-
{
|
| 662 |
-
"epoch": 47.0,
|
| 663 |
-
"eval_loss": 1.6218953132629395,
|
| 664 |
-
"eval_runtime": 0.0196,
|
| 665 |
-
"eval_samples_per_second": 51.002,
|
| 666 |
-
"eval_steps_per_second": 51.002,
|
| 667 |
-
"step": 47
|
| 668 |
-
},
|
| 669 |
-
{
|
| 670 |
-
"epoch": 48.0,
|
| 671 |
-
"learning_rate": 3.6e-05,
|
| 672 |
-
"loss": 1.6887,
|
| 673 |
-
"step": 48
|
| 674 |
-
},
|
| 675 |
-
{
|
| 676 |
-
"epoch": 48.0,
|
| 677 |
-
"eval_loss": 1.624631404876709,
|
| 678 |
-
"eval_runtime": 0.0227,
|
| 679 |
-
"eval_samples_per_second": 44.127,
|
| 680 |
-
"eval_steps_per_second": 44.127,
|
| 681 |
-
"step": 48
|
| 682 |
-
},
|
| 683 |
-
{
|
| 684 |
-
"epoch": 49.0,
|
| 685 |
-
"learning_rate": 3.55e-05,
|
| 686 |
-
"loss": 1.6335,
|
| 687 |
-
"step": 49
|
| 688 |
-
},
|
| 689 |
-
{
|
| 690 |
-
"epoch": 49.0,
|
| 691 |
-
"eval_loss": 1.6270328760147095,
|
| 692 |
-
"eval_runtime": 0.0199,
|
| 693 |
-
"eval_samples_per_second": 50.273,
|
| 694 |
-
"eval_steps_per_second": 50.273,
|
| 695 |
-
"step": 49
|
| 696 |
-
},
|
| 697 |
-
{
|
| 698 |
-
"epoch": 50.0,
|
| 699 |
-
"learning_rate": 3.5e-05,
|
| 700 |
-
"loss": 1.5708,
|
| 701 |
-
"step": 50
|
| 702 |
-
},
|
| 703 |
-
{
|
| 704 |
-
"epoch": 50.0,
|
| 705 |
-
"eval_loss": 1.621827483177185,
|
| 706 |
-
"eval_runtime": 0.02,
|
| 707 |
-
"eval_samples_per_second": 50.013,
|
| 708 |
-
"eval_steps_per_second": 50.013,
|
| 709 |
-
"step": 50
|
| 710 |
-
},
|
| 711 |
-
{
|
| 712 |
-
"epoch": 51.0,
|
| 713 |
-
"learning_rate": 3.45e-05,
|
| 714 |
-
"loss": 1.5745,
|
| 715 |
-
"step": 51
|
| 716 |
-
},
|
| 717 |
-
{
|
| 718 |
-
"epoch": 51.0,
|
| 719 |
-
"eval_loss": 1.612929344177246,
|
| 720 |
-
"eval_runtime": 0.0203,
|
| 721 |
-
"eval_samples_per_second": 49.29,
|
| 722 |
-
"eval_steps_per_second": 49.29,
|
| 723 |
-
"step": 51
|
| 724 |
-
},
|
| 725 |
-
{
|
| 726 |
-
"epoch": 52.0,
|
| 727 |
-
"learning_rate": 3.4000000000000007e-05,
|
| 728 |
-
"loss": 1.4928,
|
| 729 |
-
"step": 52
|
| 730 |
-
},
|
| 731 |
-
{
|
| 732 |
-
"epoch": 52.0,
|
| 733 |
-
"eval_loss": 1.6025854349136353,
|
| 734 |
-
"eval_runtime": 0.0204,
|
| 735 |
-
"eval_samples_per_second": 49.026,
|
| 736 |
-
"eval_steps_per_second": 49.026,
|
| 737 |
-
"step": 52
|
| 738 |
-
},
|
| 739 |
-
{
|
| 740 |
-
"epoch": 53.0,
|
| 741 |
-
"learning_rate": 3.35e-05,
|
| 742 |
-
"loss": 1.5607,
|
| 743 |
-
"step": 53
|
| 744 |
-
},
|
| 745 |
-
{
|
| 746 |
-
"epoch": 53.0,
|
| 747 |
-
"eval_loss": 1.5992611646652222,
|
| 748 |
-
"eval_runtime": 0.0198,
|
| 749 |
-
"eval_samples_per_second": 50.457,
|
| 750 |
-
"eval_steps_per_second": 50.457,
|
| 751 |
-
"step": 53
|
| 752 |
-
},
|
| 753 |
-
{
|
| 754 |
-
"epoch": 54.0,
|
| 755 |
-
"learning_rate": 3.3e-05,
|
| 756 |
-
"loss": 1.4556,
|
| 757 |
-
"step": 54
|
| 758 |
-
},
|
| 759 |
-
{
|
| 760 |
-
"epoch": 54.0,
|
| 761 |
-
"eval_loss": 1.6017229557037354,
|
| 762 |
-
"eval_runtime": 0.02,
|
| 763 |
-
"eval_samples_per_second": 49.905,
|
| 764 |
-
"eval_steps_per_second": 49.905,
|
| 765 |
-
"step": 54
|
| 766 |
-
},
|
| 767 |
-
{
|
| 768 |
-
"epoch": 55.0,
|
| 769 |
-
"learning_rate": 3.2500000000000004e-05,
|
| 770 |
-
"loss": 1.425,
|
| 771 |
-
"step": 55
|
| 772 |
-
},
|
| 773 |
-
{
|
| 774 |
-
"epoch": 55.0,
|
| 775 |
-
"eval_loss": 1.6151561737060547,
|
| 776 |
-
"eval_runtime": 0.0265,
|
| 777 |
-
"eval_samples_per_second": 37.698,
|
| 778 |
-
"eval_steps_per_second": 37.698,
|
| 779 |
-
"step": 55
|
| 780 |
-
},
|
| 781 |
-
{
|
| 782 |
-
"epoch": 56.0,
|
| 783 |
-
"learning_rate": 3.2000000000000005e-05,
|
| 784 |
-
"loss": 1.3748,
|
| 785 |
-
"step": 56
|
| 786 |
-
},
|
| 787 |
-
{
|
| 788 |
-
"epoch": 56.0,
|
| 789 |
-
"eval_loss": 1.6267999410629272,
|
| 790 |
-
"eval_runtime": 0.0201,
|
| 791 |
-
"eval_samples_per_second": 49.657,
|
| 792 |
-
"eval_steps_per_second": 49.657,
|
| 793 |
-
"step": 56
|
| 794 |
-
},
|
| 795 |
-
{
|
| 796 |
-
"epoch": 57.0,
|
| 797 |
-
"learning_rate": 3.15e-05,
|
| 798 |
-
"loss": 1.3616,
|
| 799 |
-
"step": 57
|
| 800 |
-
},
|
| 801 |
-
{
|
| 802 |
-
"epoch": 57.0,
|
| 803 |
-
"eval_loss": 1.6329103708267212,
|
| 804 |
-
"eval_runtime": 0.0198,
|
| 805 |
-
"eval_samples_per_second": 50.392,
|
| 806 |
-
"eval_steps_per_second": 50.392,
|
| 807 |
-
"step": 57
|
| 808 |
-
},
|
| 809 |
-
{
|
| 810 |
-
"epoch": 58.0,
|
| 811 |
-
"learning_rate": 3.1e-05,
|
| 812 |
-
"loss": 1.2908,
|
| 813 |
-
"step": 58
|
| 814 |
-
},
|
| 815 |
-
{
|
| 816 |
-
"epoch": 58.0,
|
| 817 |
-
"eval_loss": 1.630703330039978,
|
| 818 |
-
"eval_runtime": 0.0218,
|
| 819 |
-
"eval_samples_per_second": 45.773,
|
| 820 |
-
"eval_steps_per_second": 45.773,
|
| 821 |
-
"step": 58
|
| 822 |
-
},
|
| 823 |
-
{
|
| 824 |
-
"epoch": 59.0,
|
| 825 |
-
"learning_rate": 3.05e-05,
|
| 826 |
-
"loss": 1.228,
|
| 827 |
-
"step": 59
|
| 828 |
-
},
|
| 829 |
-
{
|
| 830 |
-
"epoch": 59.0,
|
| 831 |
-
"eval_loss": 1.6292531490325928,
|
| 832 |
-
"eval_runtime": 0.0205,
|
| 833 |
-
"eval_samples_per_second": 48.745,
|
| 834 |
-
"eval_steps_per_second": 48.745,
|
| 835 |
-
"step": 59
|
| 836 |
-
},
|
| 837 |
-
{
|
| 838 |
-
"epoch": 60.0,
|
| 839 |
-
"learning_rate": 3e-05,
|
| 840 |
-
"loss": 1.2228,
|
| 841 |
-
"step": 60
|
| 842 |
-
},
|
| 843 |
-
{
|
| 844 |
-
"epoch": 60.0,
|
| 845 |
-
"eval_loss": 1.6247613430023193,
|
| 846 |
-
"eval_runtime": 0.0205,
|
| 847 |
-
"eval_samples_per_second": 48.733,
|
| 848 |
-
"eval_steps_per_second": 48.733,
|
| 849 |
-
"step": 60
|
| 850 |
-
},
|
| 851 |
-
{
|
| 852 |
-
"epoch": 61.0,
|
| 853 |
-
"learning_rate": 2.95e-05,
|
| 854 |
-
"loss": 1.2232,
|
| 855 |
-
"step": 61
|
| 856 |
-
},
|
| 857 |
-
{
|
| 858 |
-
"epoch": 61.0,
|
| 859 |
-
"eval_loss": 1.6152808666229248,
|
| 860 |
-
"eval_runtime": 0.0297,
|
| 861 |
-
"eval_samples_per_second": 33.674,
|
| 862 |
-
"eval_steps_per_second": 33.674,
|
| 863 |
-
"step": 61
|
| 864 |
-
},
|
| 865 |
-
{
|
| 866 |
-
"epoch": 62.0,
|
| 867 |
-
"learning_rate": 2.9e-05,
|
| 868 |
-
"loss": 1.1724,
|
| 869 |
-
"step": 62
|
| 870 |
-
},
|
| 871 |
-
{
|
| 872 |
-
"epoch": 62.0,
|
| 873 |
-
"eval_loss": 1.6111640930175781,
|
| 874 |
-
"eval_runtime": 0.0208,
|
| 875 |
-
"eval_samples_per_second": 48.023,
|
| 876 |
-
"eval_steps_per_second": 48.023,
|
| 877 |
-
"step": 62
|
| 878 |
-
},
|
| 879 |
-
{
|
| 880 |
-
"epoch": 63.0,
|
| 881 |
-
"learning_rate": 2.8499999999999998e-05,
|
| 882 |
-
"loss": 1.1462,
|
| 883 |
-
"step": 63
|
| 884 |
-
},
|
| 885 |
-
{
|
| 886 |
-
"epoch": 63.0,
|
| 887 |
-
"eval_loss": 1.6092727184295654,
|
| 888 |
-
"eval_runtime": 0.0202,
|
| 889 |
-
"eval_samples_per_second": 49.616,
|
| 890 |
-
"eval_steps_per_second": 49.616,
|
| 891 |
-
"step": 63
|
| 892 |
-
},
|
| 893 |
-
{
|
| 894 |
-
"epoch": 64.0,
|
| 895 |
-
"learning_rate": 2.8000000000000003e-05,
|
| 896 |
-
"loss": 1.1083,
|
| 897 |
-
"step": 64
|
| 898 |
-
},
|
| 899 |
-
{
|
| 900 |
-
"epoch": 64.0,
|
| 901 |
-
"eval_loss": 1.6092382669448853,
|
| 902 |
-
"eval_runtime": 0.0205,
|
| 903 |
-
"eval_samples_per_second": 48.823,
|
| 904 |
-
"eval_steps_per_second": 48.823,
|
| 905 |
-
"step": 64
|
| 906 |
-
},
|
| 907 |
-
{
|
| 908 |
-
"epoch": 65.0,
|
| 909 |
-
"learning_rate": 2.7500000000000004e-05,
|
| 910 |
-
"loss": 1.0987,
|
| 911 |
-
"step": 65
|
| 912 |
-
},
|
| 913 |
-
{
|
| 914 |
-
"epoch": 65.0,
|
| 915 |
-
"eval_loss": 1.6176224946975708,
|
| 916 |
-
"eval_runtime": 0.0198,
|
| 917 |
-
"eval_samples_per_second": 50.41,
|
| 918 |
-
"eval_steps_per_second": 50.41,
|
| 919 |
-
"step": 65
|
| 920 |
}
|
| 921 |
],
|
| 922 |
-
"logging_steps":
|
| 923 |
-
"max_steps":
|
| 924 |
"num_input_tokens_seen": 0,
|
| 925 |
"num_train_epochs": 100,
|
| 926 |
-
"save_steps":
|
| 927 |
-
"total_flos":
|
| 928 |
"train_batch_size": 32,
|
| 929 |
"trial_name": null,
|
| 930 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.18517113871243,
|
| 5 |
+
"eval_steps": 50000,
|
| 6 |
+
"global_step": 50000,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
+
"epoch": 1.19,
|
| 13 |
+
"learning_rate": 4.940766331658292e-05,
|
| 14 |
+
"loss": 1.1651,
|
| 15 |
+
"step": 50000
|
| 16 |
},
|
| 17 |
{
|
| 18 |
+
"epoch": 1.19,
|
| 19 |
+
"eval_loss": 1.026120662689209,
|
| 20 |
+
"eval_runtime": 1432.5553,
|
| 21 |
+
"eval_samples_per_second": 104.708,
|
| 22 |
+
"eval_steps_per_second": 1.636,
|
| 23 |
+
"step": 50000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 24 |
}
|
| 25 |
],
|
| 26 |
+
"logging_steps": 50000,
|
| 27 |
+
"max_steps": 4218800,
|
| 28 |
"num_input_tokens_seen": 0,
|
| 29 |
"num_train_epochs": 100,
|
| 30 |
+
"save_steps": 50000,
|
| 31 |
+
"total_flos": 1.04515767631872e+17,
|
| 32 |
"train_batch_size": 32,
|
| 33 |
"trial_name": null,
|
| 34 |
"trial_params": null
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4728
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eb10217ea6ee5a53faf925ba15fc624a98562d0ed446408452fcac3eb4a1b18e
|
| 3 |
size 4728
|