Training in progress, step 200, checkpoint
Browse files- last-checkpoint/model-00001-of-00003.safetensors +1 -1
- last-checkpoint/model-00002-of-00003.safetensors +1 -1
- last-checkpoint/model-00003-of-00003.safetensors +1 -1
- last-checkpoint/optimizer.pt +2 -2
- last-checkpoint/rng_state_0.pth +3 -0
- last-checkpoint/rng_state_1.pth +3 -0
- last-checkpoint/rng_state_2.pth +3 -0
- last-checkpoint/rng_state_3.pth +3 -0
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +96 -540
- last-checkpoint/training_args.bin +1 -1
last-checkpoint/model-00001-of-00003.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4939116424
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4f1bd28175fd7513f12729e17ee3571da7edbf57f145604ce22771573d115cc5
|
| 3 |
size 4939116424
|
last-checkpoint/model-00002-of-00003.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4947390880
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b1e18b7d14aadcdd3ffd84212a90763f05677810d6606b0228ab48fc71aa8693
|
| 3 |
size 4947390880
|
last-checkpoint/model-00003-of-00003.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3590619888
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:74fed502be8e1cd05be29c5fb4cde46eadd9a078e63d9feccc111a8be0fd8b78
|
| 3 |
size 3590619888
|
last-checkpoint/optimizer.pt
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 sha256:3fd2e81881ebf33c7ad08f1ccd0211e7362bde834184d4d59f2f5bba227a0771
|
| 3 |
+
size 13688025584
|
last-checkpoint/rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7f20d155a14d34cd1bb6d04e5de90f3224906e1758821edd752a8f1a9085a2db
|
| 3 |
+
size 15024
|
last-checkpoint/rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ad18e870a176ca75a54f6620f83de92bdfd5a91302744d90bff8e5feae2fe0c5
|
| 3 |
+
size 15024
|
last-checkpoint/rng_state_2.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9009a52be47b75834407dc5e146ed5360e6f23a35bff27bab34ef6fb47df1661
|
| 3 |
+
size 15024
|
last-checkpoint/rng_state_3.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7fb494a08fd57e7c6f63f06826c872164986e81b271996be0496671f713bdcc3
|
| 3 |
+
size 15024
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9cd11d413bc67bf01de9a1a006e9e7655be307353028b25f5b3c299e5b6b7a44
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,619 +1,175 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 200,
|
| 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 |
-
"eval_loss": 2.
|
| 14 |
-
"eval_runtime":
|
| 15 |
-
"eval_samples_per_second":
|
| 16 |
-
"eval_steps_per_second":
|
| 17 |
"step": 1
|
| 18 |
},
|
| 19 |
{
|
| 20 |
-
"epoch": 0.
|
| 21 |
-
"grad_norm":
|
| 22 |
-
"learning_rate":
|
| 23 |
-
"loss": 1.
|
| 24 |
"step": 10
|
| 25 |
},
|
| 26 |
{
|
| 27 |
-
"epoch": 0.
|
| 28 |
-
"grad_norm":
|
| 29 |
-
"learning_rate":
|
| 30 |
-
"loss": 1.
|
| 31 |
"step": 20
|
| 32 |
},
|
| 33 |
{
|
| 34 |
-
"epoch": 0.
|
| 35 |
-
"grad_norm":
|
| 36 |
-
"learning_rate":
|
| 37 |
-
"loss": 1.
|
| 38 |
"step": 30
|
| 39 |
},
|
| 40 |
{
|
| 41 |
-
"epoch": 0.
|
| 42 |
-
"grad_norm":
|
| 43 |
-
"learning_rate":
|
| 44 |
-
"loss": 1.
|
| 45 |
"step": 40
|
| 46 |
},
|
| 47 |
{
|
| 48 |
-
"epoch": 0.
|
| 49 |
-
"grad_norm":
|
| 50 |
-
"learning_rate":
|
| 51 |
-
"loss":
|
| 52 |
"step": 50
|
| 53 |
},
|
| 54 |
{
|
| 55 |
-
"epoch": 0.
|
| 56 |
-
"grad_norm":
|
| 57 |
-
"learning_rate":
|
| 58 |
-
"loss":
|
| 59 |
"step": 60
|
| 60 |
},
|
| 61 |
{
|
| 62 |
-
"epoch": 0.
|
| 63 |
-
"grad_norm":
|
| 64 |
-
"learning_rate": 0.
|
| 65 |
-
"loss": 2.
|
| 66 |
"step": 70
|
| 67 |
},
|
| 68 |
{
|
| 69 |
-
"epoch": 0.
|
| 70 |
-
"grad_norm":
|
| 71 |
-
"learning_rate": 0.
|
| 72 |
-
"loss":
|
| 73 |
"step": 80
|
| 74 |
},
|
| 75 |
{
|
| 76 |
-
"epoch": 0.
|
| 77 |
-
"grad_norm":
|
| 78 |
-
"learning_rate": 0.
|
| 79 |
-
"loss": 2.
|
| 80 |
"step": 90
|
| 81 |
},
|
| 82 |
{
|
| 83 |
-
"epoch": 0.
|
| 84 |
-
"grad_norm":
|
| 85 |
-
"learning_rate": 0.
|
| 86 |
-
"loss": 2.
|
| 87 |
"step": 100
|
| 88 |
},
|
| 89 |
{
|
| 90 |
-
"epoch":
|
| 91 |
-
"grad_norm":
|
| 92 |
-
"learning_rate": 0.
|
| 93 |
-
"loss":
|
| 94 |
"step": 110
|
| 95 |
},
|
| 96 |
{
|
| 97 |
-
"epoch":
|
| 98 |
-
"grad_norm":
|
| 99 |
-
"learning_rate": 0.
|
| 100 |
-
"loss":
|
| 101 |
"step": 120
|
| 102 |
},
|
| 103 |
{
|
| 104 |
-
"epoch":
|
| 105 |
-
"grad_norm":
|
| 106 |
-
"learning_rate": 0.
|
| 107 |
-
"loss":
|
| 108 |
"step": 130
|
| 109 |
},
|
| 110 |
{
|
| 111 |
-
"epoch":
|
| 112 |
-
"grad_norm":
|
| 113 |
-
"learning_rate": 0.
|
| 114 |
-
"loss":
|
| 115 |
"step": 140
|
| 116 |
},
|
| 117 |
{
|
| 118 |
-
"epoch":
|
| 119 |
-
"grad_norm":
|
| 120 |
-
"learning_rate": 0.
|
| 121 |
-
"loss":
|
| 122 |
"step": 150
|
| 123 |
},
|
| 124 |
{
|
| 125 |
-
"epoch":
|
| 126 |
-
"grad_norm":
|
| 127 |
-
"learning_rate": 0.
|
| 128 |
-
"loss":
|
| 129 |
"step": 160
|
| 130 |
},
|
| 131 |
{
|
| 132 |
-
"epoch":
|
| 133 |
-
"grad_norm":
|
| 134 |
-
"learning_rate": 0.
|
| 135 |
-
"loss":
|
| 136 |
"step": 170
|
| 137 |
},
|
| 138 |
{
|
| 139 |
-
"epoch":
|
| 140 |
-
"grad_norm":
|
| 141 |
-
"learning_rate": 0.
|
| 142 |
-
"loss":
|
| 143 |
"step": 180
|
| 144 |
},
|
| 145 |
{
|
| 146 |
-
"epoch":
|
| 147 |
-
"grad_norm":
|
| 148 |
-
"learning_rate": 0.
|
| 149 |
-
"loss":
|
| 150 |
"step": 190
|
| 151 |
},
|
| 152 |
{
|
| 153 |
-
"epoch":
|
| 154 |
-
"grad_norm":
|
| 155 |
-
"learning_rate": 0.
|
| 156 |
-
"loss":
|
| 157 |
"step": 200
|
| 158 |
},
|
| 159 |
{
|
| 160 |
-
"epoch":
|
| 161 |
-
"eval_loss":
|
| 162 |
-
"eval_runtime":
|
| 163 |
-
"eval_samples_per_second":
|
| 164 |
-
"eval_steps_per_second": 6.
|
| 165 |
"step": 200
|
| 166 |
-
},
|
| 167 |
-
{
|
| 168 |
-
"epoch": 0.03107888116027823,
|
| 169 |
-
"grad_norm": 14.625,
|
| 170 |
-
"learning_rate": 0.0001993685735045343,
|
| 171 |
-
"loss": 3.9662,
|
| 172 |
-
"step": 210
|
| 173 |
-
},
|
| 174 |
-
{
|
| 175 |
-
"epoch": 0.03255882788219624,
|
| 176 |
-
"grad_norm": 18.0,
|
| 177 |
-
"learning_rate": 0.0001992114701314478,
|
| 178 |
-
"loss": 3.1902,
|
| 179 |
-
"step": 220
|
| 180 |
-
},
|
| 181 |
-
{
|
| 182 |
-
"epoch": 0.03403877460411425,
|
| 183 |
-
"grad_norm": 24.625,
|
| 184 |
-
"learning_rate": 0.000199037007623783,
|
| 185 |
-
"loss": 3.4792,
|
| 186 |
-
"step": 230
|
| 187 |
-
},
|
| 188 |
-
{
|
| 189 |
-
"epoch": 0.03551872132603226,
|
| 190 |
-
"grad_norm": 46.0,
|
| 191 |
-
"learning_rate": 0.00019884521650742715,
|
| 192 |
-
"loss": 3.7192,
|
| 193 |
-
"step": 240
|
| 194 |
-
},
|
| 195 |
-
{
|
| 196 |
-
"epoch": 0.036998668047950274,
|
| 197 |
-
"grad_norm": 28.0,
|
| 198 |
-
"learning_rate": 0.00019863613034027224,
|
| 199 |
-
"loss": 3.6487,
|
| 200 |
-
"step": 250
|
| 201 |
-
},
|
| 202 |
-
{
|
| 203 |
-
"epoch": 0.03847861476986828,
|
| 204 |
-
"grad_norm": 139.0,
|
| 205 |
-
"learning_rate": 0.0001984097857063434,
|
| 206 |
-
"loss": 4.3462,
|
| 207 |
-
"step": 260
|
| 208 |
-
},
|
| 209 |
-
{
|
| 210 |
-
"epoch": 0.039958561491786296,
|
| 211 |
-
"grad_norm": 13.875,
|
| 212 |
-
"learning_rate": 0.0001981662222093976,
|
| 213 |
-
"loss": 3.3132,
|
| 214 |
-
"step": 270
|
| 215 |
-
},
|
| 216 |
-
{
|
| 217 |
-
"epoch": 0.04143850821370431,
|
| 218 |
-
"grad_norm": 29.5,
|
| 219 |
-
"learning_rate": 0.00019790548246599447,
|
| 220 |
-
"loss": 3.3523,
|
| 221 |
-
"step": 280
|
| 222 |
-
},
|
| 223 |
-
{
|
| 224 |
-
"epoch": 0.04291845493562232,
|
| 225 |
-
"grad_norm": 43.75,
|
| 226 |
-
"learning_rate": 0.00019762761209803927,
|
| 227 |
-
"loss": 3.8529,
|
| 228 |
-
"step": 290
|
| 229 |
-
},
|
| 230 |
-
{
|
| 231 |
-
"epoch": 0.04439840165754033,
|
| 232 |
-
"grad_norm": 234.0,
|
| 233 |
-
"learning_rate": 0.0001973326597248006,
|
| 234 |
-
"loss": 4.7306,
|
| 235 |
-
"step": 300
|
| 236 |
-
},
|
| 237 |
-
{
|
| 238 |
-
"epoch": 0.04587834837945834,
|
| 239 |
-
"grad_norm": 17.625,
|
| 240 |
-
"learning_rate": 0.00019702067695440332,
|
| 241 |
-
"loss": 4.0088,
|
| 242 |
-
"step": 310
|
| 243 |
-
},
|
| 244 |
-
{
|
| 245 |
-
"epoch": 0.04735829510137635,
|
| 246 |
-
"grad_norm": 10.0625,
|
| 247 |
-
"learning_rate": 0.00019669171837479873,
|
| 248 |
-
"loss": 3.4104,
|
| 249 |
-
"step": 320
|
| 250 |
-
},
|
| 251 |
-
{
|
| 252 |
-
"epoch": 0.04883824182329436,
|
| 253 |
-
"grad_norm": 12.6875,
|
| 254 |
-
"learning_rate": 0.00019634584154421317,
|
| 255 |
-
"loss": 3.6337,
|
| 256 |
-
"step": 330
|
| 257 |
-
},
|
| 258 |
-
{
|
| 259 |
-
"epoch": 0.050318188545212375,
|
| 260 |
-
"grad_norm": 16.75,
|
| 261 |
-
"learning_rate": 0.00019598310698107702,
|
| 262 |
-
"loss": 3.6344,
|
| 263 |
-
"step": 340
|
| 264 |
-
},
|
| 265 |
-
{
|
| 266 |
-
"epoch": 0.05179813526713038,
|
| 267 |
-
"grad_norm": 21.625,
|
| 268 |
-
"learning_rate": 0.00019560357815343577,
|
| 269 |
-
"loss": 3.8887,
|
| 270 |
-
"step": 350
|
| 271 |
-
},
|
| 272 |
-
{
|
| 273 |
-
"epoch": 0.0532780819890484,
|
| 274 |
-
"grad_norm": 8.5625,
|
| 275 |
-
"learning_rate": 0.00019520732146784491,
|
| 276 |
-
"loss": 3.9023,
|
| 277 |
-
"step": 360
|
| 278 |
-
},
|
| 279 |
-
{
|
| 280 |
-
"epoch": 0.054758028710966404,
|
| 281 |
-
"grad_norm": 10.625,
|
| 282 |
-
"learning_rate": 0.0001947944062577507,
|
| 283 |
-
"loss": 3.7002,
|
| 284 |
-
"step": 370
|
| 285 |
-
},
|
| 286 |
-
{
|
| 287 |
-
"epoch": 0.05623797543288442,
|
| 288 |
-
"grad_norm": 34.25,
|
| 289 |
-
"learning_rate": 0.00019436490477135878,
|
| 290 |
-
"loss": 3.7505,
|
| 291 |
-
"step": 380
|
| 292 |
-
},
|
| 293 |
-
{
|
| 294 |
-
"epoch": 0.057717922154802426,
|
| 295 |
-
"grad_norm": 17.75,
|
| 296 |
-
"learning_rate": 0.00019391889215899299,
|
| 297 |
-
"loss": 3.9776,
|
| 298 |
-
"step": 390
|
| 299 |
-
},
|
| 300 |
-
{
|
| 301 |
-
"epoch": 0.05919786887672044,
|
| 302 |
-
"grad_norm": 41.25,
|
| 303 |
-
"learning_rate": 0.0001934564464599461,
|
| 304 |
-
"loss": 3.6903,
|
| 305 |
-
"step": 400
|
| 306 |
-
},
|
| 307 |
-
{
|
| 308 |
-
"epoch": 0.05919786887672044,
|
| 309 |
-
"eval_loss": 5.192676544189453,
|
| 310 |
-
"eval_runtime": 115.1721,
|
| 311 |
-
"eval_samples_per_second": 13.041,
|
| 312 |
-
"eval_steps_per_second": 6.521,
|
| 313 |
-
"step": 400
|
| 314 |
-
},
|
| 315 |
-
{
|
| 316 |
-
"epoch": 0.06067781559863845,
|
| 317 |
-
"grad_norm": 14.375,
|
| 318 |
-
"learning_rate": 0.00019297764858882514,
|
| 319 |
-
"loss": 4.2204,
|
| 320 |
-
"step": 410
|
| 321 |
-
},
|
| 322 |
-
{
|
| 323 |
-
"epoch": 0.06215776232055646,
|
| 324 |
-
"grad_norm": 17.75,
|
| 325 |
-
"learning_rate": 0.00019248258232139388,
|
| 326 |
-
"loss": 3.7817,
|
| 327 |
-
"step": 420
|
| 328 |
-
},
|
| 329 |
-
{
|
| 330 |
-
"epoch": 0.06363770904247447,
|
| 331 |
-
"grad_norm": 25.5,
|
| 332 |
-
"learning_rate": 0.00019197133427991436,
|
| 333 |
-
"loss": 3.8348,
|
| 334 |
-
"step": 430
|
| 335 |
-
},
|
| 336 |
-
{
|
| 337 |
-
"epoch": 0.06511765576439248,
|
| 338 |
-
"grad_norm": 16.375,
|
| 339 |
-
"learning_rate": 0.00019144399391799043,
|
| 340 |
-
"loss": 4.1359,
|
| 341 |
-
"step": 440
|
| 342 |
-
},
|
| 343 |
-
{
|
| 344 |
-
"epoch": 0.0665976024863105,
|
| 345 |
-
"grad_norm": 126.5,
|
| 346 |
-
"learning_rate": 0.00019090065350491626,
|
| 347 |
-
"loss": 3.8639,
|
| 348 |
-
"step": 450
|
| 349 |
-
},
|
| 350 |
-
{
|
| 351 |
-
"epoch": 0.0680775492082285,
|
| 352 |
-
"grad_norm": 10.5,
|
| 353 |
-
"learning_rate": 0.0001903414081095315,
|
| 354 |
-
"loss": 4.3344,
|
| 355 |
-
"step": 460
|
| 356 |
-
},
|
| 357 |
-
{
|
| 358 |
-
"epoch": 0.06955749593014651,
|
| 359 |
-
"grad_norm": 9.625,
|
| 360 |
-
"learning_rate": 0.00018976635558358722,
|
| 361 |
-
"loss": 3.7876,
|
| 362 |
-
"step": 470
|
| 363 |
-
},
|
| 364 |
-
{
|
| 365 |
-
"epoch": 0.07103744265206452,
|
| 366 |
-
"grad_norm": 12.75,
|
| 367 |
-
"learning_rate": 0.00018917559654462474,
|
| 368 |
-
"loss": 4.0847,
|
| 369 |
-
"step": 480
|
| 370 |
-
},
|
| 371 |
-
{
|
| 372 |
-
"epoch": 0.07251738937398254,
|
| 373 |
-
"grad_norm": 56.75,
|
| 374 |
-
"learning_rate": 0.00018856923435837022,
|
| 375 |
-
"loss": 4.2232,
|
| 376 |
-
"step": 490
|
| 377 |
-
},
|
| 378 |
-
{
|
| 379 |
-
"epoch": 0.07399733609590055,
|
| 380 |
-
"grad_norm": 49.0,
|
| 381 |
-
"learning_rate": 0.0001879473751206489,
|
| 382 |
-
"loss": 4.3389,
|
| 383 |
-
"step": 500
|
| 384 |
-
},
|
| 385 |
-
{
|
| 386 |
-
"epoch": 0.07547728281781856,
|
| 387 |
-
"grad_norm": 7.96875,
|
| 388 |
-
"learning_rate": 0.00018731012763882133,
|
| 389 |
-
"loss": 4.1522,
|
| 390 |
-
"step": 510
|
| 391 |
-
},
|
| 392 |
-
{
|
| 393 |
-
"epoch": 0.07695722953973656,
|
| 394 |
-
"grad_norm": 10.8125,
|
| 395 |
-
"learning_rate": 0.00018665760341274505,
|
| 396 |
-
"loss": 4.0533,
|
| 397 |
-
"step": 520
|
| 398 |
-
},
|
| 399 |
-
{
|
| 400 |
-
"epoch": 0.07843717626165458,
|
| 401 |
-
"grad_norm": 18.0,
|
| 402 |
-
"learning_rate": 0.00018598991661526572,
|
| 403 |
-
"loss": 4.0835,
|
| 404 |
-
"step": 530
|
| 405 |
-
},
|
| 406 |
-
{
|
| 407 |
-
"epoch": 0.07991712298357259,
|
| 408 |
-
"grad_norm": 34.5,
|
| 409 |
-
"learning_rate": 0.00018530718407223974,
|
| 410 |
-
"loss": 3.5388,
|
| 411 |
-
"step": 540
|
| 412 |
-
},
|
| 413 |
-
{
|
| 414 |
-
"epoch": 0.0813970697054906,
|
| 415 |
-
"grad_norm": 28.375,
|
| 416 |
-
"learning_rate": 0.00018460952524209355,
|
| 417 |
-
"loss": 4.2171,
|
| 418 |
-
"step": 550
|
| 419 |
-
},
|
| 420 |
-
{
|
| 421 |
-
"epoch": 0.08287701642740862,
|
| 422 |
-
"grad_norm": 13.125,
|
| 423 |
-
"learning_rate": 0.00018389706219492147,
|
| 424 |
-
"loss": 4.2511,
|
| 425 |
-
"step": 560
|
| 426 |
-
},
|
| 427 |
-
{
|
| 428 |
-
"epoch": 0.08435696314932663,
|
| 429 |
-
"grad_norm": 13.1875,
|
| 430 |
-
"learning_rate": 0.00018316991959112716,
|
| 431 |
-
"loss": 3.9025,
|
| 432 |
-
"step": 570
|
| 433 |
-
},
|
| 434 |
-
{
|
| 435 |
-
"epoch": 0.08583690987124463,
|
| 436 |
-
"grad_norm": 15.3125,
|
| 437 |
-
"learning_rate": 0.00018242822465961176,
|
| 438 |
-
"loss": 4.0034,
|
| 439 |
-
"step": 580
|
| 440 |
-
},
|
| 441 |
-
{
|
| 442 |
-
"epoch": 0.08731685659316264,
|
| 443 |
-
"grad_norm": 33.0,
|
| 444 |
-
"learning_rate": 0.00018167210717551224,
|
| 445 |
-
"loss": 4.0514,
|
| 446 |
-
"step": 590
|
| 447 |
-
},
|
| 448 |
-
{
|
| 449 |
-
"epoch": 0.08879680331508066,
|
| 450 |
-
"grad_norm": 35.0,
|
| 451 |
-
"learning_rate": 0.00018090169943749476,
|
| 452 |
-
"loss": 4.0116,
|
| 453 |
-
"step": 600
|
| 454 |
-
},
|
| 455 |
-
{
|
| 456 |
-
"epoch": 0.08879680331508066,
|
| 457 |
-
"eval_loss": 4.839527130126953,
|
| 458 |
-
"eval_runtime": 115.7002,
|
| 459 |
-
"eval_samples_per_second": 12.982,
|
| 460 |
-
"eval_steps_per_second": 6.491,
|
| 461 |
-
"step": 600
|
| 462 |
-
},
|
| 463 |
-
{
|
| 464 |
-
"epoch": 0.09027675003699867,
|
| 465 |
-
"grad_norm": 9.9375,
|
| 466 |
-
"learning_rate": 0.00018011713624460608,
|
| 467 |
-
"loss": 4.2757,
|
| 468 |
-
"step": 610
|
| 469 |
-
},
|
| 470 |
-
{
|
| 471 |
-
"epoch": 0.09175669675891668,
|
| 472 |
-
"grad_norm": 9.375,
|
| 473 |
-
"learning_rate": 0.00017931855487268782,
|
| 474 |
-
"loss": 3.9496,
|
| 475 |
-
"step": 620
|
| 476 |
-
},
|
| 477 |
-
{
|
| 478 |
-
"epoch": 0.09323664348083469,
|
| 479 |
-
"grad_norm": 17.5,
|
| 480 |
-
"learning_rate": 0.0001785060950503568,
|
| 481 |
-
"loss": 4.0227,
|
| 482 |
-
"step": 630
|
| 483 |
-
},
|
| 484 |
-
{
|
| 485 |
-
"epoch": 0.0947165902027527,
|
| 486 |
-
"grad_norm": 12.0,
|
| 487 |
-
"learning_rate": 0.00017767989893455698,
|
| 488 |
-
"loss": 4.3345,
|
| 489 |
-
"step": 640
|
| 490 |
-
},
|
| 491 |
-
{
|
| 492 |
-
"epoch": 0.09619653692467071,
|
| 493 |
-
"grad_norm": 40.75,
|
| 494 |
-
"learning_rate": 0.00017684011108568592,
|
| 495 |
-
"loss": 3.2456,
|
| 496 |
-
"step": 650
|
| 497 |
-
},
|
| 498 |
-
{
|
| 499 |
-
"epoch": 0.09767648364658872,
|
| 500 |
-
"grad_norm": 6.03125,
|
| 501 |
-
"learning_rate": 0.00017598687844230088,
|
| 502 |
-
"loss": 4.296,
|
| 503 |
-
"step": 660
|
| 504 |
-
},
|
| 505 |
-
{
|
| 506 |
-
"epoch": 0.09915643036850673,
|
| 507 |
-
"grad_norm": 10.75,
|
| 508 |
-
"learning_rate": 0.00017512035029540885,
|
| 509 |
-
"loss": 3.8307,
|
| 510 |
-
"step": 670
|
| 511 |
-
},
|
| 512 |
-
{
|
| 513 |
-
"epoch": 0.10063637709042475,
|
| 514 |
-
"grad_norm": 11.9375,
|
| 515 |
-
"learning_rate": 0.000174240678262345,
|
| 516 |
-
"loss": 3.8659,
|
| 517 |
-
"step": 680
|
| 518 |
-
},
|
| 519 |
-
{
|
| 520 |
-
"epoch": 0.10211632381234276,
|
| 521 |
-
"grad_norm": 21.75,
|
| 522 |
-
"learning_rate": 0.000173348016260244,
|
| 523 |
-
"loss": 4.0579,
|
| 524 |
-
"step": 690
|
| 525 |
-
},
|
| 526 |
-
{
|
| 527 |
-
"epoch": 0.10359627053426076,
|
| 528 |
-
"grad_norm": 29.625,
|
| 529 |
-
"learning_rate": 0.00017244252047910892,
|
| 530 |
-
"loss": 3.8463,
|
| 531 |
-
"step": 700
|
| 532 |
-
},
|
| 533 |
-
{
|
| 534 |
-
"epoch": 0.10507621725617877,
|
| 535 |
-
"grad_norm": 12.75,
|
| 536 |
-
"learning_rate": 0.00017152434935448256,
|
| 537 |
-
"loss": 4.225,
|
| 538 |
-
"step": 710
|
| 539 |
-
},
|
| 540 |
-
{
|
| 541 |
-
"epoch": 0.1065561639780968,
|
| 542 |
-
"grad_norm": 9.0625,
|
| 543 |
-
"learning_rate": 0.0001705936635397259,
|
| 544 |
-
"loss": 3.5182,
|
| 545 |
-
"step": 720
|
| 546 |
-
},
|
| 547 |
-
{
|
| 548 |
-
"epoch": 0.1080361107000148,
|
| 549 |
-
"grad_norm": 14.75,
|
| 550 |
-
"learning_rate": 0.00016965062587790823,
|
| 551 |
-
"loss": 4.0649,
|
| 552 |
-
"step": 730
|
| 553 |
-
},
|
| 554 |
-
{
|
| 555 |
-
"epoch": 0.10951605742193281,
|
| 556 |
-
"grad_norm": 19.0,
|
| 557 |
-
"learning_rate": 0.00016869540137331445,
|
| 558 |
-
"loss": 4.2849,
|
| 559 |
-
"step": 740
|
| 560 |
-
},
|
| 561 |
-
{
|
| 562 |
-
"epoch": 0.11099600414385082,
|
| 563 |
-
"grad_norm": 34.5,
|
| 564 |
-
"learning_rate": 0.00016772815716257412,
|
| 565 |
-
"loss": 3.65,
|
| 566 |
-
"step": 750
|
| 567 |
-
},
|
| 568 |
-
{
|
| 569 |
-
"epoch": 0.11247595086576884,
|
| 570 |
-
"grad_norm": 11.0,
|
| 571 |
-
"learning_rate": 0.00016674906248541726,
|
| 572 |
-
"loss": 4.1331,
|
| 573 |
-
"step": 760
|
| 574 |
-
},
|
| 575 |
-
{
|
| 576 |
-
"epoch": 0.11395589758768684,
|
| 577 |
-
"grad_norm": 38.0,
|
| 578 |
-
"learning_rate": 0.00016575828865506245,
|
| 579 |
-
"loss": 3.5679,
|
| 580 |
-
"step": 770
|
| 581 |
-
},
|
| 582 |
-
{
|
| 583 |
-
"epoch": 0.11543584430960485,
|
| 584 |
-
"grad_norm": 9.8125,
|
| 585 |
-
"learning_rate": 0.0001647560090282419,
|
| 586 |
-
"loss": 3.573,
|
| 587 |
-
"step": 780
|
| 588 |
-
},
|
| 589 |
-
{
|
| 590 |
-
"epoch": 0.11691579103152286,
|
| 591 |
-
"grad_norm": 14.0,
|
| 592 |
-
"learning_rate": 0.000163742398974869,
|
| 593 |
-
"loss": 3.9581,
|
| 594 |
-
"step": 790
|
| 595 |
-
},
|
| 596 |
-
{
|
| 597 |
-
"epoch": 0.11839573775344088,
|
| 598 |
-
"grad_norm": 20.25,
|
| 599 |
-
"learning_rate": 0.0001627176358473537,
|
| 600 |
-
"loss": 4.0812,
|
| 601 |
-
"step": 800
|
| 602 |
-
},
|
| 603 |
-
{
|
| 604 |
-
"epoch": 0.11839573775344088,
|
| 605 |
-
"eval_loss": 4.436325550079346,
|
| 606 |
-
"eval_runtime": 113.0291,
|
| 607 |
-
"eval_samples_per_second": 13.289,
|
| 608 |
-
"eval_steps_per_second": 6.644,
|
| 609 |
-
"step": 800
|
| 610 |
}
|
| 611 |
],
|
| 612 |
"logging_steps": 10,
|
| 613 |
-
"max_steps":
|
| 614 |
"num_input_tokens_seen": 0,
|
| 615 |
-
"num_train_epochs":
|
| 616 |
-
"save_steps":
|
| 617 |
"stateful_callbacks": {
|
| 618 |
"TrainerControl": {
|
| 619 |
"args": {
|
|
@@ -626,7 +182,7 @@
|
|
| 626 |
"attributes": {}
|
| 627 |
}
|
| 628 |
},
|
| 629 |
-
"total_flos": 1.
|
| 630 |
"train_batch_size": 2,
|
| 631 |
"trial_name": null,
|
| 632 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.8518518518518519,
|
| 5 |
"eval_steps": 200,
|
| 6 |
+
"global_step": 200,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
+
"epoch": 0.009259259259259259,
|
| 13 |
+
"eval_loss": 2.1662161350250244,
|
| 14 |
+
"eval_runtime": 32.9047,
|
| 15 |
+
"eval_samples_per_second": 45.617,
|
| 16 |
+
"eval_steps_per_second": 5.713,
|
| 17 |
"step": 1
|
| 18 |
},
|
| 19 |
{
|
| 20 |
+
"epoch": 0.09259259259259259,
|
| 21 |
+
"grad_norm": 2.796875,
|
| 22 |
+
"learning_rate": 6.666666666666667e-05,
|
| 23 |
+
"loss": 1.8575,
|
| 24 |
"step": 10
|
| 25 |
},
|
| 26 |
{
|
| 27 |
+
"epoch": 0.18518518518518517,
|
| 28 |
+
"grad_norm": 1.75,
|
| 29 |
+
"learning_rate": 0.00013333333333333334,
|
| 30 |
+
"loss": 1.8329,
|
| 31 |
"step": 20
|
| 32 |
},
|
| 33 |
{
|
| 34 |
+
"epoch": 0.2777777777777778,
|
| 35 |
+
"grad_norm": 2.15625,
|
| 36 |
+
"learning_rate": 0.0002,
|
| 37 |
+
"loss": 1.8697,
|
| 38 |
"step": 30
|
| 39 |
},
|
| 40 |
{
|
| 41 |
+
"epoch": 0.37037037037037035,
|
| 42 |
+
"grad_norm": 2.0,
|
| 43 |
+
"learning_rate": 0.00019984815164333163,
|
| 44 |
+
"loss": 1.9683,
|
| 45 |
"step": 40
|
| 46 |
},
|
| 47 |
{
|
| 48 |
+
"epoch": 0.46296296296296297,
|
| 49 |
+
"grad_norm": 1.3046875,
|
| 50 |
+
"learning_rate": 0.00019939306773179497,
|
| 51 |
+
"loss": 2.0113,
|
| 52 |
"step": 50
|
| 53 |
},
|
| 54 |
{
|
| 55 |
+
"epoch": 0.5555555555555556,
|
| 56 |
+
"grad_norm": 1.5703125,
|
| 57 |
+
"learning_rate": 0.00019863613034027224,
|
| 58 |
+
"loss": 2.0568,
|
| 59 |
"step": 60
|
| 60 |
},
|
| 61 |
{
|
| 62 |
+
"epoch": 0.6481481481481481,
|
| 63 |
+
"grad_norm": 1.3984375,
|
| 64 |
+
"learning_rate": 0.00019757963826274357,
|
| 65 |
+
"loss": 2.1038,
|
| 66 |
"step": 70
|
| 67 |
},
|
| 68 |
{
|
| 69 |
+
"epoch": 0.7407407407407407,
|
| 70 |
+
"grad_norm": 1.3203125,
|
| 71 |
+
"learning_rate": 0.00019622680003092503,
|
| 72 |
+
"loss": 2.1133,
|
| 73 |
"step": 80
|
| 74 |
},
|
| 75 |
{
|
| 76 |
+
"epoch": 0.8333333333333334,
|
| 77 |
+
"grad_norm": 1.421875,
|
| 78 |
+
"learning_rate": 0.00019458172417006347,
|
| 79 |
+
"loss": 2.1036,
|
| 80 |
"step": 90
|
| 81 |
},
|
| 82 |
{
|
| 83 |
+
"epoch": 0.9259259259259259,
|
| 84 |
+
"grad_norm": 1.453125,
|
| 85 |
+
"learning_rate": 0.00019264940672148018,
|
| 86 |
+
"loss": 2.1255,
|
| 87 |
"step": 100
|
| 88 |
},
|
| 89 |
{
|
| 90 |
+
"epoch": 1.0185185185185186,
|
| 91 |
+
"grad_norm": 1.3984375,
|
| 92 |
+
"learning_rate": 0.00019043571606975777,
|
| 93 |
+
"loss": 1.8837,
|
| 94 |
"step": 110
|
| 95 |
},
|
| 96 |
{
|
| 97 |
+
"epoch": 1.1111111111111112,
|
| 98 |
+
"grad_norm": 1.328125,
|
| 99 |
+
"learning_rate": 0.0001879473751206489,
|
| 100 |
+
"loss": 0.9892,
|
| 101 |
"step": 120
|
| 102 |
},
|
| 103 |
{
|
| 104 |
+
"epoch": 1.2037037037037037,
|
| 105 |
+
"grad_norm": 1.1015625,
|
| 106 |
+
"learning_rate": 0.00018519194088383273,
|
| 107 |
+
"loss": 0.9478,
|
| 108 |
"step": 130
|
| 109 |
},
|
| 110 |
{
|
| 111 |
+
"epoch": 1.2962962962962963,
|
| 112 |
+
"grad_norm": 1.21875,
|
| 113 |
+
"learning_rate": 0.0001821777815225245,
|
| 114 |
+
"loss": 0.9602,
|
| 115 |
"step": 140
|
| 116 |
},
|
| 117 |
{
|
| 118 |
+
"epoch": 1.3888888888888888,
|
| 119 |
+
"grad_norm": 1.2265625,
|
| 120 |
+
"learning_rate": 0.00017891405093963938,
|
| 121 |
+
"loss": 0.9669,
|
| 122 |
"step": 150
|
| 123 |
},
|
| 124 |
{
|
| 125 |
+
"epoch": 1.4814814814814814,
|
| 126 |
+
"grad_norm": 1.1640625,
|
| 127 |
+
"learning_rate": 0.00017541066097768963,
|
| 128 |
+
"loss": 0.9945,
|
| 129 |
"step": 160
|
| 130 |
},
|
| 131 |
{
|
| 132 |
+
"epoch": 1.574074074074074,
|
| 133 |
+
"grad_norm": 1.1875,
|
| 134 |
+
"learning_rate": 0.00017167825131684513,
|
| 135 |
+
"loss": 0.9809,
|
| 136 |
"step": 170
|
| 137 |
},
|
| 138 |
{
|
| 139 |
+
"epoch": 1.6666666666666665,
|
| 140 |
+
"grad_norm": 1.078125,
|
| 141 |
+
"learning_rate": 0.00016772815716257412,
|
| 142 |
+
"loss": 1.0197,
|
| 143 |
"step": 180
|
| 144 |
},
|
| 145 |
{
|
| 146 |
+
"epoch": 1.7592592592592593,
|
| 147 |
+
"grad_norm": 1.2109375,
|
| 148 |
+
"learning_rate": 0.00016357237482099684,
|
| 149 |
+
"loss": 1.0018,
|
| 150 |
"step": 190
|
| 151 |
},
|
| 152 |
{
|
| 153 |
+
"epoch": 1.8518518518518519,
|
| 154 |
+
"grad_norm": 1.3125,
|
| 155 |
+
"learning_rate": 0.00015922352526649803,
|
| 156 |
+
"loss": 1.0298,
|
| 157 |
"step": 200
|
| 158 |
},
|
| 159 |
{
|
| 160 |
+
"epoch": 1.8518518518518519,
|
| 161 |
+
"eval_loss": 2.0912892818450928,
|
| 162 |
+
"eval_runtime": 31.2593,
|
| 163 |
+
"eval_samples_per_second": 48.018,
|
| 164 |
+
"eval_steps_per_second": 6.014,
|
| 165 |
"step": 200
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 166 |
}
|
| 167 |
],
|
| 168 |
"logging_steps": 10,
|
| 169 |
+
"max_steps": 600,
|
| 170 |
"num_input_tokens_seen": 0,
|
| 171 |
+
"num_train_epochs": 6,
|
| 172 |
+
"save_steps": 200,
|
| 173 |
"stateful_callbacks": {
|
| 174 |
"TrainerControl": {
|
| 175 |
"args": {
|
|
|
|
| 182 |
"attributes": {}
|
| 183 |
}
|
| 184 |
},
|
| 185 |
+
"total_flos": 1.2990695522435072e+17,
|
| 186 |
"train_batch_size": 2,
|
| 187 |
"trial_name": null,
|
| 188 |
"trial_params": null
|
last-checkpoint/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 6840
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c7e4cc380bf07566f66cbd6e04a4bdc7a8bc1f51ced4f92d8dc2abee469a5015
|
| 3 |
size 6840
|