Upload 17 files
Browse files- config.json +2 -5
- latest +1 -1
- rng_state_0.pth +2 -2
- rng_state_1.pth +2 -2
- rng_state_2.pth +2 -2
- rng_state_3.pth +2 -2
- rng_state_4.pth +2 -2
- rng_state_5.pth +2 -2
- rng_state_6.pth +2 -2
- trainer_state.json +126 -336
- training_args.bin +2 -2
config.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "/dev/shm/CodeLlama-7b-Instruct",
|
| 3 |
"architectures": [
|
| 4 |
"LlamaForCausalLM"
|
| 5 |
],
|
|
@@ -18,10 +18,7 @@
|
|
| 18 |
"num_key_value_heads": 32,
|
| 19 |
"pretraining_tp": 1,
|
| 20 |
"rms_norm_eps": 1e-05,
|
| 21 |
-
"rope_scaling":
|
| 22 |
-
"factor": 1.0,
|
| 23 |
-
"type": "linear"
|
| 24 |
-
},
|
| 25 |
"rope_theta": 1000000,
|
| 26 |
"tie_word_embeddings": false,
|
| 27 |
"torch_dtype": "float16",
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "/dev/shm/daoguang/CodeLlama-7b-Instruct",
|
| 3 |
"architectures": [
|
| 4 |
"LlamaForCausalLM"
|
| 5 |
],
|
|
|
|
| 18 |
"num_key_value_heads": 32,
|
| 19 |
"pretraining_tp": 1,
|
| 20 |
"rms_norm_eps": 1e-05,
|
| 21 |
+
"rope_scaling": null,
|
|
|
|
|
|
|
|
|
|
| 22 |
"rope_theta": 1000000,
|
| 23 |
"tie_word_embeddings": false,
|
| 24 |
"torch_dtype": "float16",
|
latest
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
|
|
|
|
| 1 |
+
global_step80
|
rng_state_0.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3ede3a41c76eab8d5a1109b390a56df16ebb33aa97144d7374657806fe7680ec
|
| 3 |
+
size 15728
|
rng_state_1.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5e5a3f71bd916448b335fc12b81ee46376136a8b88160f46dc05a2c519f7dc69
|
| 3 |
+
size 15728
|
rng_state_2.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1498f85638b156d84ed9814b2ee749b87a840b1cebc2023ed62f199cdf2db62a
|
| 3 |
+
size 15728
|
rng_state_3.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5c7e82267f597a2bf81008683b4aea5c1841ac18b6f7d3817788768df2bd57ca
|
| 3 |
+
size 15728
|
rng_state_4.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:881e950a2ccd0819e0af6ba6c8686e05169bc934182acceb756ddbcc66ba79d5
|
| 3 |
+
size 15728
|
rng_state_5.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:da7d85a882a0a197e2b4aadcdeca8bd3ab751aff35caf44543574dadb7638446
|
| 3 |
+
size 15728
|
rng_state_6.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0ccc34bb3651a068b5415059e67db3f95a4450f8a810669e910ccbd146669019
|
| 3 |
+
size 15728
|
trainer_state.json
CHANGED
|
@@ -1,471 +1,261 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 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 |
-
"learning_rate":
|
| 14 |
-
"loss": 0.
|
| 15 |
"step": 2
|
| 16 |
},
|
| 17 |
{
|
| 18 |
-
"epoch": 0.
|
| 19 |
-
"learning_rate":
|
| 20 |
-
"loss": 0.
|
| 21 |
"step": 4
|
| 22 |
},
|
| 23 |
{
|
| 24 |
-
"epoch": 0.
|
| 25 |
-
"learning_rate":
|
| 26 |
-
"loss": 0.
|
| 27 |
"step": 6
|
| 28 |
},
|
| 29 |
{
|
| 30 |
-
"epoch": 0.
|
| 31 |
-
"learning_rate":
|
| 32 |
-
"loss": 0.
|
| 33 |
"step": 8
|
| 34 |
},
|
| 35 |
{
|
| 36 |
-
"epoch": 0.
|
| 37 |
-
"learning_rate":
|
| 38 |
-
"loss": 0.
|
| 39 |
"step": 10
|
| 40 |
},
|
| 41 |
{
|
| 42 |
-
"epoch": 0.
|
| 43 |
-
"learning_rate":
|
| 44 |
-
"loss": 0.
|
| 45 |
"step": 12
|
| 46 |
},
|
| 47 |
{
|
| 48 |
-
"epoch": 0.
|
| 49 |
-
"learning_rate":
|
| 50 |
-
"loss": 0.
|
| 51 |
"step": 14
|
| 52 |
},
|
| 53 |
{
|
| 54 |
-
"epoch": 0.
|
| 55 |
-
"learning_rate":
|
| 56 |
-
"loss": 0.
|
| 57 |
"step": 16
|
| 58 |
},
|
| 59 |
{
|
| 60 |
-
"epoch":
|
| 61 |
-
"learning_rate":
|
| 62 |
-
"loss": 0.
|
| 63 |
"step": 18
|
| 64 |
},
|
| 65 |
{
|
| 66 |
-
"epoch":
|
| 67 |
-
"learning_rate":
|
| 68 |
-
"loss": 0.
|
| 69 |
"step": 20
|
| 70 |
},
|
| 71 |
{
|
| 72 |
-
"epoch":
|
| 73 |
-
"learning_rate":
|
| 74 |
-
"loss": 0.
|
| 75 |
"step": 22
|
| 76 |
},
|
| 77 |
{
|
| 78 |
-
"epoch":
|
| 79 |
-
"learning_rate":
|
| 80 |
-
"loss": 0.
|
| 81 |
"step": 24
|
| 82 |
},
|
| 83 |
{
|
| 84 |
-
"epoch":
|
| 85 |
-
"learning_rate":
|
| 86 |
-
"loss": 0.
|
| 87 |
"step": 26
|
| 88 |
},
|
| 89 |
{
|
| 90 |
-
"epoch":
|
| 91 |
-
"learning_rate":
|
| 92 |
-
"loss": 0.
|
| 93 |
"step": 28
|
| 94 |
},
|
| 95 |
{
|
| 96 |
-
"epoch":
|
| 97 |
-
"learning_rate":
|
| 98 |
-
"loss": 0.
|
| 99 |
"step": 30
|
| 100 |
},
|
| 101 |
{
|
| 102 |
-
"epoch":
|
| 103 |
-
"learning_rate":
|
| 104 |
-
"loss": 0.
|
| 105 |
"step": 32
|
| 106 |
},
|
| 107 |
{
|
| 108 |
-
"epoch":
|
| 109 |
-
"learning_rate":
|
| 110 |
-
"loss": 0.
|
| 111 |
"step": 34
|
| 112 |
},
|
| 113 |
{
|
| 114 |
-
"epoch":
|
| 115 |
-
"learning_rate":
|
| 116 |
-
"loss": 0.
|
| 117 |
"step": 36
|
| 118 |
},
|
| 119 |
{
|
| 120 |
-
"epoch":
|
| 121 |
-
"learning_rate":
|
| 122 |
-
"loss": 0.
|
| 123 |
"step": 38
|
| 124 |
},
|
| 125 |
{
|
| 126 |
-
"epoch":
|
| 127 |
-
"learning_rate":
|
| 128 |
-
"loss": 0.
|
| 129 |
"step": 40
|
| 130 |
},
|
| 131 |
{
|
| 132 |
-
"epoch":
|
| 133 |
-
"learning_rate":
|
| 134 |
-
"loss": 0.
|
| 135 |
"step": 42
|
| 136 |
},
|
| 137 |
{
|
| 138 |
-
"epoch":
|
| 139 |
-
"learning_rate":
|
| 140 |
-
"loss": 0.
|
| 141 |
"step": 44
|
| 142 |
},
|
| 143 |
{
|
| 144 |
-
"epoch":
|
| 145 |
-
"learning_rate":
|
| 146 |
-
"loss": 0.
|
| 147 |
"step": 46
|
| 148 |
},
|
| 149 |
{
|
| 150 |
-
"epoch":
|
| 151 |
-
"learning_rate":
|
| 152 |
-
"loss": 0.
|
| 153 |
"step": 48
|
| 154 |
},
|
| 155 |
{
|
| 156 |
-
"epoch":
|
| 157 |
-
"learning_rate":
|
| 158 |
-
"loss": 0.
|
| 159 |
"step": 50
|
| 160 |
},
|
| 161 |
{
|
| 162 |
-
"epoch": 1
|
| 163 |
-
"learning_rate":
|
| 164 |
-
"loss": 0.
|
| 165 |
"step": 52
|
| 166 |
},
|
| 167 |
{
|
| 168 |
-
"epoch":
|
| 169 |
-
"learning_rate":
|
| 170 |
-
"loss": 0.
|
| 171 |
"step": 54
|
| 172 |
},
|
| 173 |
{
|
| 174 |
-
"epoch":
|
| 175 |
-
"learning_rate":
|
| 176 |
-
"loss": 0.
|
| 177 |
"step": 56
|
| 178 |
},
|
| 179 |
{
|
| 180 |
-
"epoch":
|
| 181 |
-
"learning_rate":
|
| 182 |
-
"loss": 0.
|
| 183 |
"step": 58
|
| 184 |
},
|
| 185 |
{
|
| 186 |
-
"epoch":
|
| 187 |
-
"learning_rate":
|
| 188 |
-
"loss": 0.
|
| 189 |
"step": 60
|
| 190 |
},
|
| 191 |
{
|
| 192 |
-
"epoch":
|
| 193 |
-
"learning_rate":
|
| 194 |
-
"loss": 0.
|
| 195 |
"step": 62
|
| 196 |
},
|
| 197 |
{
|
| 198 |
-
"epoch":
|
| 199 |
-
"learning_rate":
|
| 200 |
-
"loss": 0.
|
| 201 |
"step": 64
|
| 202 |
},
|
| 203 |
{
|
| 204 |
-
"epoch":
|
| 205 |
-
"learning_rate":
|
| 206 |
-
"loss": 0.
|
| 207 |
"step": 66
|
| 208 |
},
|
| 209 |
{
|
| 210 |
-
"epoch":
|
| 211 |
-
"learning_rate":
|
| 212 |
-
"loss": 0.
|
| 213 |
"step": 68
|
| 214 |
},
|
| 215 |
{
|
| 216 |
-
"epoch":
|
| 217 |
-
"learning_rate":
|
| 218 |
-
"loss": 0.
|
| 219 |
"step": 70
|
| 220 |
},
|
| 221 |
{
|
| 222 |
-
"epoch":
|
| 223 |
-
"learning_rate":
|
| 224 |
-
"loss": 0.
|
| 225 |
"step": 72
|
| 226 |
},
|
| 227 |
{
|
| 228 |
-
"epoch":
|
| 229 |
-
"learning_rate":
|
| 230 |
-
"loss": 0.
|
| 231 |
"step": 74
|
| 232 |
},
|
| 233 |
{
|
| 234 |
-
"epoch":
|
| 235 |
-
"learning_rate":
|
| 236 |
-
"loss": 0.
|
| 237 |
"step": 76
|
| 238 |
},
|
| 239 |
{
|
| 240 |
-
"epoch":
|
| 241 |
-
"learning_rate":
|
| 242 |
-
"loss": 0.
|
| 243 |
"step": 78
|
| 244 |
},
|
| 245 |
{
|
| 246 |
-
"epoch":
|
| 247 |
-
"learning_rate":
|
| 248 |
-
"loss": 0.
|
| 249 |
"step": 80
|
| 250 |
-
},
|
| 251 |
-
{
|
| 252 |
-
"epoch": 2.11,
|
| 253 |
-
"learning_rate": 3.0332490768593675e-05,
|
| 254 |
-
"loss": 0.1188,
|
| 255 |
-
"step": 82
|
| 256 |
-
},
|
| 257 |
-
{
|
| 258 |
-
"epoch": 2.16,
|
| 259 |
-
"learning_rate": 2.952201335830275e-05,
|
| 260 |
-
"loss": 0.1067,
|
| 261 |
-
"step": 84
|
| 262 |
-
},
|
| 263 |
-
{
|
| 264 |
-
"epoch": 2.21,
|
| 265 |
-
"learning_rate": 2.870659119279605e-05,
|
| 266 |
-
"loss": 0.1131,
|
| 267 |
-
"step": 86
|
| 268 |
-
},
|
| 269 |
-
{
|
| 270 |
-
"epoch": 2.26,
|
| 271 |
-
"learning_rate": 2.788711592423966e-05,
|
| 272 |
-
"loss": 0.1308,
|
| 273 |
-
"step": 88
|
| 274 |
-
},
|
| 275 |
-
{
|
| 276 |
-
"epoch": 2.32,
|
| 277 |
-
"learning_rate": 2.7064483636808313e-05,
|
| 278 |
-
"loss": 0.1236,
|
| 279 |
-
"step": 90
|
| 280 |
-
},
|
| 281 |
-
{
|
| 282 |
-
"epoch": 2.37,
|
| 283 |
-
"learning_rate": 2.623959386683056e-05,
|
| 284 |
-
"loss": 0.1079,
|
| 285 |
-
"step": 92
|
| 286 |
-
},
|
| 287 |
-
{
|
| 288 |
-
"epoch": 2.42,
|
| 289 |
-
"learning_rate": 2.5413348619158967e-05,
|
| 290 |
-
"loss": 0.1102,
|
| 291 |
-
"step": 94
|
| 292 |
-
},
|
| 293 |
-
{
|
| 294 |
-
"epoch": 2.47,
|
| 295 |
-
"learning_rate": 2.458665138084104e-05,
|
| 296 |
-
"loss": 0.1218,
|
| 297 |
-
"step": 96
|
| 298 |
-
},
|
| 299 |
-
{
|
| 300 |
-
"epoch": 2.52,
|
| 301 |
-
"learning_rate": 2.3760406133169443e-05,
|
| 302 |
-
"loss": 0.1148,
|
| 303 |
-
"step": 98
|
| 304 |
-
},
|
| 305 |
-
{
|
| 306 |
-
"epoch": 2.57,
|
| 307 |
-
"learning_rate": 2.2935516363191693e-05,
|
| 308 |
-
"loss": 0.1109,
|
| 309 |
-
"step": 100
|
| 310 |
-
},
|
| 311 |
-
{
|
| 312 |
-
"epoch": 2.62,
|
| 313 |
-
"learning_rate": 2.2112884075760347e-05,
|
| 314 |
-
"loss": 0.1088,
|
| 315 |
-
"step": 102
|
| 316 |
-
},
|
| 317 |
-
{
|
| 318 |
-
"epoch": 2.68,
|
| 319 |
-
"learning_rate": 2.1293408807203947e-05,
|
| 320 |
-
"loss": 0.1109,
|
| 321 |
-
"step": 104
|
| 322 |
-
},
|
| 323 |
-
{
|
| 324 |
-
"epoch": 2.73,
|
| 325 |
-
"learning_rate": 2.047798664169726e-05,
|
| 326 |
-
"loss": 0.0939,
|
| 327 |
-
"step": 106
|
| 328 |
-
},
|
| 329 |
-
{
|
| 330 |
-
"epoch": 2.78,
|
| 331 |
-
"learning_rate": 1.9667509231406334e-05,
|
| 332 |
-
"loss": 0.1179,
|
| 333 |
-
"step": 108
|
| 334 |
-
},
|
| 335 |
-
{
|
| 336 |
-
"epoch": 2.83,
|
| 337 |
-
"learning_rate": 1.8862862821480025e-05,
|
| 338 |
-
"loss": 0.095,
|
| 339 |
-
"step": 110
|
| 340 |
-
},
|
| 341 |
-
{
|
| 342 |
-
"epoch": 2.88,
|
| 343 |
-
"learning_rate": 1.806492728095389e-05,
|
| 344 |
-
"loss": 0.115,
|
| 345 |
-
"step": 112
|
| 346 |
-
},
|
| 347 |
-
{
|
| 348 |
-
"epoch": 2.93,
|
| 349 |
-
"learning_rate": 1.7274575140626318e-05,
|
| 350 |
-
"loss": 0.1219,
|
| 351 |
-
"step": 114
|
| 352 |
-
},
|
| 353 |
-
{
|
| 354 |
-
"epoch": 2.98,
|
| 355 |
-
"learning_rate": 1.6492670638958924e-05,
|
| 356 |
-
"loss": 0.1153,
|
| 357 |
-
"step": 116
|
| 358 |
-
},
|
| 359 |
-
{
|
| 360 |
-
"epoch": 3.04,
|
| 361 |
-
"learning_rate": 1.5720068777044476e-05,
|
| 362 |
-
"loss": 0.0693,
|
| 363 |
-
"step": 118
|
| 364 |
-
},
|
| 365 |
-
{
|
| 366 |
-
"epoch": 3.09,
|
| 367 |
-
"learning_rate": 1.495761438367577e-05,
|
| 368 |
-
"loss": 0.0535,
|
| 369 |
-
"step": 120
|
| 370 |
-
},
|
| 371 |
-
{
|
| 372 |
-
"epoch": 3.14,
|
| 373 |
-
"learning_rate": 1.4206141191537682e-05,
|
| 374 |
-
"loss": 0.0452,
|
| 375 |
-
"step": 122
|
| 376 |
-
},
|
| 377 |
-
{
|
| 378 |
-
"epoch": 3.19,
|
| 379 |
-
"learning_rate": 1.346647092553281e-05,
|
| 380 |
-
"loss": 0.0444,
|
| 381 |
-
"step": 124
|
| 382 |
-
},
|
| 383 |
-
{
|
| 384 |
-
"epoch": 3.24,
|
| 385 |
-
"learning_rate": 1.2739412404237306e-05,
|
| 386 |
-
"loss": 0.0364,
|
| 387 |
-
"step": 126
|
| 388 |
-
},
|
| 389 |
-
{
|
| 390 |
-
"epoch": 3.29,
|
| 391 |
-
"learning_rate": 1.202576065546963e-05,
|
| 392 |
-
"loss": 0.0591,
|
| 393 |
-
"step": 128
|
| 394 |
-
},
|
| 395 |
-
{
|
| 396 |
-
"epoch": 3.34,
|
| 397 |
-
"learning_rate": 1.1326296046939333e-05,
|
| 398 |
-
"loss": 0.0466,
|
| 399 |
-
"step": 130
|
| 400 |
-
},
|
| 401 |
-
{
|
| 402 |
-
"epoch": 3.4,
|
| 403 |
-
"learning_rate": 1.064178343292641e-05,
|
| 404 |
-
"loss": 0.0558,
|
| 405 |
-
"step": 132
|
| 406 |
-
},
|
| 407 |
-
{
|
| 408 |
-
"epoch": 3.45,
|
| 409 |
-
"learning_rate": 9.972971317924374e-06,
|
| 410 |
-
"loss": 0.0533,
|
| 411 |
-
"step": 134
|
| 412 |
-
},
|
| 413 |
-
{
|
| 414 |
-
"epoch": 3.5,
|
| 415 |
-
"learning_rate": 9.320591038161574e-06,
|
| 416 |
-
"loss": 0.0549,
|
| 417 |
-
"step": 136
|
| 418 |
-
},
|
| 419 |
-
{
|
| 420 |
-
"epoch": 3.55,
|
| 421 |
-
"learning_rate": 8.685355961895784e-06,
|
| 422 |
-
"loss": 0.0446,
|
| 423 |
-
"step": 138
|
| 424 |
-
},
|
| 425 |
-
{
|
| 426 |
-
"epoch": 3.6,
|
| 427 |
-
"learning_rate": 8.067960709356478e-06,
|
| 428 |
-
"loss": 0.0622,
|
| 429 |
-
"step": 140
|
| 430 |
-
},
|
| 431 |
-
{
|
| 432 |
-
"epoch": 3.65,
|
| 433 |
-
"learning_rate": 7.469080393187786e-06,
|
| 434 |
-
"loss": 0.0494,
|
| 435 |
-
"step": 142
|
| 436 |
-
},
|
| 437 |
-
{
|
| 438 |
-
"epoch": 3.7,
|
| 439 |
-
"learning_rate": 6.889369880222776e-06,
|
| 440 |
-
"loss": 0.0391,
|
| 441 |
-
"step": 144
|
| 442 |
-
},
|
| 443 |
-
{
|
| 444 |
-
"epoch": 3.76,
|
| 445 |
-
"learning_rate": 6.329463075396161e-06,
|
| 446 |
-
"loss": 0.0399,
|
| 447 |
-
"step": 146
|
| 448 |
-
},
|
| 449 |
-
{
|
| 450 |
-
"epoch": 3.81,
|
| 451 |
-
"learning_rate": 5.78997222857853e-06,
|
| 452 |
-
"loss": 0.0509,
|
| 453 |
-
"step": 148
|
| 454 |
-
},
|
| 455 |
-
{
|
| 456 |
-
"epoch": 3.86,
|
| 457 |
-
"learning_rate": 5.271487265090163e-06,
|
| 458 |
-
"loss": 0.0451,
|
| 459 |
-
"step": 150
|
| 460 |
}
|
| 461 |
],
|
| 462 |
"logging_steps": 2,
|
| 463 |
-
"max_steps":
|
| 464 |
"num_input_tokens_seen": 0,
|
| 465 |
"num_train_epochs": 5,
|
| 466 |
-
"save_steps":
|
| 467 |
-
"total_flos":
|
| 468 |
-
"train_batch_size":
|
| 469 |
"trial_name": null,
|
| 470 |
"trial_params": null
|
| 471 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 4.776119402985074,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 80,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
+
"epoch": 0.12,
|
| 13 |
+
"learning_rate": 5e-05,
|
| 14 |
+
"loss": 0.8672,
|
| 15 |
"step": 2
|
| 16 |
},
|
| 17 |
{
|
| 18 |
+
"epoch": 0.24,
|
| 19 |
+
"learning_rate": 5e-05,
|
| 20 |
+
"loss": 0.8051,
|
| 21 |
"step": 4
|
| 22 |
},
|
| 23 |
{
|
| 24 |
+
"epoch": 0.36,
|
| 25 |
+
"learning_rate": 5e-05,
|
| 26 |
+
"loss": 0.6955,
|
| 27 |
"step": 6
|
| 28 |
},
|
| 29 |
{
|
| 30 |
+
"epoch": 0.48,
|
| 31 |
+
"learning_rate": 5e-05,
|
| 32 |
+
"loss": 0.6879,
|
| 33 |
"step": 8
|
| 34 |
},
|
| 35 |
{
|
| 36 |
+
"epoch": 0.6,
|
| 37 |
+
"learning_rate": 5e-05,
|
| 38 |
+
"loss": 0.6785,
|
| 39 |
"step": 10
|
| 40 |
},
|
| 41 |
{
|
| 42 |
+
"epoch": 0.72,
|
| 43 |
+
"learning_rate": 5e-05,
|
| 44 |
+
"loss": 0.6584,
|
| 45 |
"step": 12
|
| 46 |
},
|
| 47 |
{
|
| 48 |
+
"epoch": 0.84,
|
| 49 |
+
"learning_rate": 5e-05,
|
| 50 |
+
"loss": 0.646,
|
| 51 |
"step": 14
|
| 52 |
},
|
| 53 |
{
|
| 54 |
+
"epoch": 0.96,
|
| 55 |
+
"learning_rate": 5e-05,
|
| 56 |
+
"loss": 0.6585,
|
| 57 |
"step": 16
|
| 58 |
},
|
| 59 |
{
|
| 60 |
+
"epoch": 1.07,
|
| 61 |
+
"learning_rate": 5e-05,
|
| 62 |
+
"loss": 0.5556,
|
| 63 |
"step": 18
|
| 64 |
},
|
| 65 |
{
|
| 66 |
+
"epoch": 1.19,
|
| 67 |
+
"learning_rate": 5e-05,
|
| 68 |
+
"loss": 0.4459,
|
| 69 |
"step": 20
|
| 70 |
},
|
| 71 |
{
|
| 72 |
+
"epoch": 1.31,
|
| 73 |
+
"learning_rate": 5e-05,
|
| 74 |
+
"loss": 0.4237,
|
| 75 |
"step": 22
|
| 76 |
},
|
| 77 |
{
|
| 78 |
+
"epoch": 1.43,
|
| 79 |
+
"learning_rate": 5e-05,
|
| 80 |
+
"loss": 0.4039,
|
| 81 |
"step": 24
|
| 82 |
},
|
| 83 |
{
|
| 84 |
+
"epoch": 1.55,
|
| 85 |
+
"learning_rate": 5e-05,
|
| 86 |
+
"loss": 0.3943,
|
| 87 |
"step": 26
|
| 88 |
},
|
| 89 |
{
|
| 90 |
+
"epoch": 1.67,
|
| 91 |
+
"learning_rate": 5e-05,
|
| 92 |
+
"loss": 0.3858,
|
| 93 |
"step": 28
|
| 94 |
},
|
| 95 |
{
|
| 96 |
+
"epoch": 1.79,
|
| 97 |
+
"learning_rate": 5e-05,
|
| 98 |
+
"loss": 0.402,
|
| 99 |
"step": 30
|
| 100 |
},
|
| 101 |
{
|
| 102 |
+
"epoch": 1.91,
|
| 103 |
+
"learning_rate": 5e-05,
|
| 104 |
+
"loss": 0.4071,
|
| 105 |
"step": 32
|
| 106 |
},
|
| 107 |
{
|
| 108 |
+
"epoch": 2.03,
|
| 109 |
+
"learning_rate": 5e-05,
|
| 110 |
+
"loss": 0.3372,
|
| 111 |
"step": 34
|
| 112 |
},
|
| 113 |
{
|
| 114 |
+
"epoch": 2.15,
|
| 115 |
+
"learning_rate": 5e-05,
|
| 116 |
+
"loss": 0.2406,
|
| 117 |
"step": 36
|
| 118 |
},
|
| 119 |
{
|
| 120 |
+
"epoch": 2.27,
|
| 121 |
+
"learning_rate": 5e-05,
|
| 122 |
+
"loss": 0.1945,
|
| 123 |
"step": 38
|
| 124 |
},
|
| 125 |
{
|
| 126 |
+
"epoch": 2.39,
|
| 127 |
+
"learning_rate": 5e-05,
|
| 128 |
+
"loss": 0.1935,
|
| 129 |
"step": 40
|
| 130 |
},
|
| 131 |
{
|
| 132 |
+
"epoch": 2.51,
|
| 133 |
+
"learning_rate": 5e-05,
|
| 134 |
+
"loss": 0.1866,
|
| 135 |
"step": 42
|
| 136 |
},
|
| 137 |
{
|
| 138 |
+
"epoch": 2.63,
|
| 139 |
+
"learning_rate": 5e-05,
|
| 140 |
+
"loss": 0.1739,
|
| 141 |
"step": 44
|
| 142 |
},
|
| 143 |
{
|
| 144 |
+
"epoch": 2.75,
|
| 145 |
+
"learning_rate": 5e-05,
|
| 146 |
+
"loss": 0.1708,
|
| 147 |
"step": 46
|
| 148 |
},
|
| 149 |
{
|
| 150 |
+
"epoch": 2.87,
|
| 151 |
+
"learning_rate": 5e-05,
|
| 152 |
+
"loss": 0.1808,
|
| 153 |
"step": 48
|
| 154 |
},
|
| 155 |
{
|
| 156 |
+
"epoch": 2.99,
|
| 157 |
+
"learning_rate": 5e-05,
|
| 158 |
+
"loss": 0.1847,
|
| 159 |
"step": 50
|
| 160 |
},
|
| 161 |
{
|
| 162 |
+
"epoch": 3.1,
|
| 163 |
+
"learning_rate": 5e-05,
|
| 164 |
+
"loss": 0.1019,
|
| 165 |
"step": 52
|
| 166 |
},
|
| 167 |
{
|
| 168 |
+
"epoch": 3.22,
|
| 169 |
+
"learning_rate": 5e-05,
|
| 170 |
+
"loss": 0.0741,
|
| 171 |
"step": 54
|
| 172 |
},
|
| 173 |
{
|
| 174 |
+
"epoch": 3.34,
|
| 175 |
+
"learning_rate": 5e-05,
|
| 176 |
+
"loss": 0.073,
|
| 177 |
"step": 56
|
| 178 |
},
|
| 179 |
{
|
| 180 |
+
"epoch": 3.46,
|
| 181 |
+
"learning_rate": 5e-05,
|
| 182 |
+
"loss": 0.0748,
|
| 183 |
"step": 58
|
| 184 |
},
|
| 185 |
{
|
| 186 |
+
"epoch": 3.58,
|
| 187 |
+
"learning_rate": 5e-05,
|
| 188 |
+
"loss": 0.07,
|
| 189 |
"step": 60
|
| 190 |
},
|
| 191 |
{
|
| 192 |
+
"epoch": 3.7,
|
| 193 |
+
"learning_rate": 5e-05,
|
| 194 |
+
"loss": 0.0692,
|
| 195 |
"step": 62
|
| 196 |
},
|
| 197 |
{
|
| 198 |
+
"epoch": 3.82,
|
| 199 |
+
"learning_rate": 5e-05,
|
| 200 |
+
"loss": 0.079,
|
| 201 |
"step": 64
|
| 202 |
},
|
| 203 |
{
|
| 204 |
+
"epoch": 3.94,
|
| 205 |
+
"learning_rate": 5e-05,
|
| 206 |
+
"loss": 0.0835,
|
| 207 |
"step": 66
|
| 208 |
},
|
| 209 |
{
|
| 210 |
+
"epoch": 4.06,
|
| 211 |
+
"learning_rate": 5e-05,
|
| 212 |
+
"loss": 0.0533,
|
| 213 |
"step": 68
|
| 214 |
},
|
| 215 |
{
|
| 216 |
+
"epoch": 4.18,
|
| 217 |
+
"learning_rate": 5e-05,
|
| 218 |
+
"loss": 0.0356,
|
| 219 |
"step": 70
|
| 220 |
},
|
| 221 |
{
|
| 222 |
+
"epoch": 4.3,
|
| 223 |
+
"learning_rate": 5e-05,
|
| 224 |
+
"loss": 0.0326,
|
| 225 |
"step": 72
|
| 226 |
},
|
| 227 |
{
|
| 228 |
+
"epoch": 4.42,
|
| 229 |
+
"learning_rate": 5e-05,
|
| 230 |
+
"loss": 0.0417,
|
| 231 |
"step": 74
|
| 232 |
},
|
| 233 |
{
|
| 234 |
+
"epoch": 4.54,
|
| 235 |
+
"learning_rate": 5e-05,
|
| 236 |
+
"loss": 0.0352,
|
| 237 |
"step": 76
|
| 238 |
},
|
| 239 |
{
|
| 240 |
+
"epoch": 4.66,
|
| 241 |
+
"learning_rate": 5e-05,
|
| 242 |
+
"loss": 0.042,
|
| 243 |
"step": 78
|
| 244 |
},
|
| 245 |
{
|
| 246 |
+
"epoch": 4.78,
|
| 247 |
+
"learning_rate": 5e-05,
|
| 248 |
+
"loss": 0.0359,
|
| 249 |
"step": 80
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 250 |
}
|
| 251 |
],
|
| 252 |
"logging_steps": 2,
|
| 253 |
+
"max_steps": 80,
|
| 254 |
"num_input_tokens_seen": 0,
|
| 255 |
"num_train_epochs": 5,
|
| 256 |
+
"save_steps": 20,
|
| 257 |
+
"total_flos": 58433383956480.0,
|
| 258 |
+
"train_batch_size": 8,
|
| 259 |
"trial_name": null,
|
| 260 |
"trial_params": null
|
| 261 |
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:307a17178835f4dc291457cc32d36551ee702b49bbfcb565831d619d7743c969
|
| 3 |
+
size 7224
|