Training in progress, step 25, checkpoint
Browse files- last-checkpoint/adapter_config.json +5 -3
- last-checkpoint/adapter_model.safetensors +1 -1
- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/rng_state_0.pth +1 -1
- last-checkpoint/rng_state_1.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +88 -271
- last-checkpoint/training_args.bin +2 -2
last-checkpoint/adapter_config.json
CHANGED
|
@@ -20,10 +20,12 @@
|
|
| 20 |
"rank_pattern": {},
|
| 21 |
"revision": null,
|
| 22 |
"target_modules": [
|
| 23 |
-
"
|
| 24 |
-
"down_proj",
|
| 25 |
"o_proj",
|
| 26 |
-
"
|
|
|
|
|
|
|
|
|
|
| 27 |
],
|
| 28 |
"task_type": "CAUSAL_LM",
|
| 29 |
"use_dora": false,
|
|
|
|
| 20 |
"rank_pattern": {},
|
| 21 |
"revision": null,
|
| 22 |
"target_modules": [
|
| 23 |
+
"qkv_proj",
|
|
|
|
| 24 |
"o_proj",
|
| 25 |
+
"v_proj",
|
| 26 |
+
"q_proj",
|
| 27 |
+
"gate_up_proj",
|
| 28 |
+
"down_proj"
|
| 29 |
],
|
| 30 |
"task_type": "CAUSAL_LM",
|
| 31 |
"use_dora": false,
|
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 116744
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4fed3a1af013c2f1ffea05423e3d954d625f76227a66765d63ef9fcf839c9118
|
| 3 |
size 116744
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 243310
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aab980519daf7fb45ae3422fc203e3059108e016bd76025feee28fcbff3cfcdd
|
| 3 |
size 243310
|
last-checkpoint/rng_state_0.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14512
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5becd69b928f760cbad8d38057cc5adccf0f9da02cc5e9a3fcde2020e3171777
|
| 3 |
size 14512
|
last-checkpoint/rng_state_1.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14512
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:97853ccc6263aab55e6cbb8496f1e99b9abe2985c3208a54a97fa0b4b3fd6113
|
| 3 |
size 14512
|
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:f37b2aa490ccb1598b01e14cda36e9081f7ce646deab4d3c2d03de0d2169a755
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,386 +1,203 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 10.
|
| 3 |
-
"best_model_checkpoint": "miner_id_24/checkpoint-
|
| 4 |
"epoch": 0.0655307994757536,
|
| 5 |
"eval_steps": 25,
|
| 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 |
-
"grad_norm": 0.
|
| 14 |
"learning_rate": 5e-05,
|
| 15 |
-
"loss": 10.
|
| 16 |
"step": 1
|
| 17 |
},
|
| 18 |
{
|
| 19 |
-
"epoch": 0.
|
| 20 |
-
"eval_loss": 10.
|
| 21 |
-
"eval_runtime":
|
| 22 |
-
"eval_samples_per_second":
|
| 23 |
-
"eval_steps_per_second":
|
| 24 |
"step": 1
|
| 25 |
},
|
| 26 |
{
|
| 27 |
-
"epoch": 0.
|
| 28 |
-
"grad_norm": 0.
|
| 29 |
"learning_rate": 0.0001,
|
| 30 |
-
"loss": 10.
|
| 31 |
"step": 2
|
| 32 |
},
|
| 33 |
{
|
| 34 |
-
"epoch": 0.
|
| 35 |
-
"grad_norm": 0.
|
| 36 |
"learning_rate": 9.989294616193017e-05,
|
| 37 |
-
"loss": 10.
|
| 38 |
"step": 3
|
| 39 |
},
|
| 40 |
{
|
| 41 |
-
"epoch": 0.
|
| 42 |
-
"grad_norm": 0.
|
| 43 |
"learning_rate": 9.957224306869053e-05,
|
| 44 |
-
"loss": 10.
|
| 45 |
"step": 4
|
| 46 |
},
|
| 47 |
{
|
| 48 |
-
"epoch": 0.
|
| 49 |
-
"grad_norm": 0.
|
| 50 |
"learning_rate": 9.903926402016153e-05,
|
| 51 |
-
"loss": 10.
|
| 52 |
"step": 5
|
| 53 |
},
|
| 54 |
{
|
| 55 |
-
"epoch": 0.
|
| 56 |
-
"grad_norm": 0.
|
| 57 |
"learning_rate": 9.829629131445342e-05,
|
| 58 |
-
"loss": 10.
|
| 59 |
"step": 6
|
| 60 |
},
|
| 61 |
{
|
| 62 |
-
"epoch": 0.
|
| 63 |
-
"grad_norm": 0.
|
| 64 |
"learning_rate": 9.73465064747553e-05,
|
| 65 |
-
"loss": 10.
|
| 66 |
"step": 7
|
| 67 |
},
|
| 68 |
{
|
| 69 |
-
"epoch": 0.
|
| 70 |
-
"grad_norm": 0.
|
| 71 |
"learning_rate": 9.619397662556435e-05,
|
| 72 |
-
"loss": 10.
|
| 73 |
"step": 8
|
| 74 |
},
|
| 75 |
{
|
| 76 |
-
"epoch": 0.
|
| 77 |
-
"grad_norm": 0.
|
| 78 |
"learning_rate": 9.484363707663442e-05,
|
| 79 |
-
"loss": 10.
|
| 80 |
"step": 9
|
| 81 |
},
|
| 82 |
{
|
| 83 |
-
"epoch": 0.
|
| 84 |
-
"grad_norm": 0.
|
| 85 |
"learning_rate": 9.330127018922194e-05,
|
| 86 |
-
"loss": 10.
|
| 87 |
"step": 10
|
| 88 |
},
|
| 89 |
{
|
| 90 |
-
"epoch": 0.
|
| 91 |
-
"grad_norm": 0.
|
| 92 |
"learning_rate": 9.157348061512727e-05,
|
| 93 |
-
"loss": 10.
|
| 94 |
"step": 11
|
| 95 |
},
|
| 96 |
{
|
| 97 |
-
"epoch": 0.
|
| 98 |
-
"grad_norm": 0.
|
| 99 |
"learning_rate": 8.966766701456177e-05,
|
| 100 |
-
"loss": 10.
|
| 101 |
"step": 12
|
| 102 |
},
|
| 103 |
{
|
| 104 |
-
"epoch": 0.
|
| 105 |
-
"grad_norm": 0.
|
| 106 |
"learning_rate": 8.759199037394887e-05,
|
| 107 |
-
"loss": 10.
|
| 108 |
"step": 13
|
| 109 |
},
|
| 110 |
{
|
| 111 |
-
"epoch": 0.
|
| 112 |
-
"grad_norm": 0.
|
| 113 |
"learning_rate": 8.535533905932738e-05,
|
| 114 |
-
"loss": 10.
|
| 115 |
"step": 14
|
| 116 |
},
|
| 117 |
{
|
| 118 |
-
"epoch": 0.
|
| 119 |
-
"grad_norm": 0.
|
| 120 |
"learning_rate": 8.296729075500344e-05,
|
| 121 |
-
"loss": 10.
|
| 122 |
"step": 15
|
| 123 |
},
|
| 124 |
{
|
| 125 |
-
"epoch": 0.
|
| 126 |
-
"grad_norm": 0.
|
| 127 |
"learning_rate": 8.043807145043604e-05,
|
| 128 |
-
"loss": 10.
|
| 129 |
"step": 16
|
| 130 |
},
|
| 131 |
{
|
| 132 |
-
"epoch": 0.
|
| 133 |
-
"grad_norm": 0.
|
| 134 |
"learning_rate": 7.777851165098012e-05,
|
| 135 |
-
"loss": 10.
|
| 136 |
"step": 17
|
| 137 |
},
|
| 138 |
{
|
| 139 |
-
"epoch": 0.
|
| 140 |
-
"grad_norm": 0.
|
| 141 |
"learning_rate": 7.500000000000001e-05,
|
| 142 |
-
"loss": 10.
|
| 143 |
"step": 18
|
| 144 |
},
|
| 145 |
{
|
| 146 |
-
"epoch": 0.
|
| 147 |
-
"grad_norm": 0.
|
| 148 |
"learning_rate": 7.211443451095007e-05,
|
| 149 |
-
"loss": 10.
|
| 150 |
"step": 19
|
| 151 |
},
|
| 152 |
{
|
| 153 |
-
"epoch": 0.
|
| 154 |
-
"grad_norm": 0.
|
| 155 |
"learning_rate": 6.91341716182545e-05,
|
| 156 |
-
"loss": 10.
|
| 157 |
"step": 20
|
| 158 |
},
|
| 159 |
{
|
| 160 |
-
"epoch": 0.
|
| 161 |
-
"grad_norm": 0.
|
| 162 |
"learning_rate": 6.607197326515808e-05,
|
| 163 |
-
"loss": 10.
|
| 164 |
"step": 21
|
| 165 |
},
|
| 166 |
{
|
| 167 |
-
"epoch": 0.
|
| 168 |
-
"grad_norm": 0.
|
| 169 |
"learning_rate": 6.294095225512603e-05,
|
| 170 |
-
"loss": 10.
|
| 171 |
"step": 22
|
| 172 |
},
|
| 173 |
{
|
| 174 |
-
"epoch": 0.
|
| 175 |
-
"grad_norm": 0.
|
| 176 |
"learning_rate": 5.9754516100806423e-05,
|
| 177 |
-
"loss": 10.
|
| 178 |
"step": 23
|
| 179 |
},
|
| 180 |
{
|
| 181 |
-
"epoch": 0.
|
| 182 |
-
"grad_norm": 0.
|
| 183 |
"learning_rate": 5.6526309611002594e-05,
|
| 184 |
-
"loss": 10.
|
| 185 |
"step": 24
|
| 186 |
},
|
| 187 |
{
|
| 188 |
-
"epoch": 0.
|
| 189 |
-
"grad_norm": 0.
|
| 190 |
"learning_rate": 5.327015646150716e-05,
|
| 191 |
"loss": 10.3763,
|
| 192 |
"step": 25
|
| 193 |
},
|
| 194 |
-
{
|
| 195 |
-
"epoch": 0.0327653997378768,
|
| 196 |
-
"eval_loss": 10.368788719177246,
|
| 197 |
-
"eval_runtime": 7.1928,
|
| 198 |
-
"eval_samples_per_second": 357.442,
|
| 199 |
-
"eval_steps_per_second": 89.395,
|
| 200 |
-
"step": 25
|
| 201 |
-
},
|
| 202 |
-
{
|
| 203 |
-
"epoch": 0.03407601572739188,
|
| 204 |
-
"grad_norm": 0.14859028160572052,
|
| 205 |
-
"learning_rate": 5e-05,
|
| 206 |
-
"loss": 10.3677,
|
| 207 |
-
"step": 26
|
| 208 |
-
},
|
| 209 |
-
{
|
| 210 |
-
"epoch": 0.035386631716906945,
|
| 211 |
-
"grad_norm": 0.14715676009655,
|
| 212 |
-
"learning_rate": 4.6729843538492847e-05,
|
| 213 |
-
"loss": 10.3674,
|
| 214 |
-
"step": 27
|
| 215 |
-
},
|
| 216 |
-
{
|
| 217 |
-
"epoch": 0.03669724770642202,
|
| 218 |
-
"grad_norm": 0.1489713191986084,
|
| 219 |
-
"learning_rate": 4.347369038899744e-05,
|
| 220 |
-
"loss": 10.369,
|
| 221 |
-
"step": 28
|
| 222 |
-
},
|
| 223 |
-
{
|
| 224 |
-
"epoch": 0.03800786369593709,
|
| 225 |
-
"grad_norm": 0.15279723703861237,
|
| 226 |
-
"learning_rate": 4.0245483899193595e-05,
|
| 227 |
-
"loss": 10.3671,
|
| 228 |
-
"step": 29
|
| 229 |
-
},
|
| 230 |
-
{
|
| 231 |
-
"epoch": 0.039318479685452164,
|
| 232 |
-
"grad_norm": 0.14576803147792816,
|
| 233 |
-
"learning_rate": 3.705904774487396e-05,
|
| 234 |
-
"loss": 10.3687,
|
| 235 |
-
"step": 30
|
| 236 |
-
},
|
| 237 |
-
{
|
| 238 |
-
"epoch": 0.04062909567496723,
|
| 239 |
-
"grad_norm": 0.1643356829881668,
|
| 240 |
-
"learning_rate": 3.392802673484193e-05,
|
| 241 |
-
"loss": 10.3666,
|
| 242 |
-
"step": 31
|
| 243 |
-
},
|
| 244 |
-
{
|
| 245 |
-
"epoch": 0.04193971166448231,
|
| 246 |
-
"grad_norm": 0.15099547803401947,
|
| 247 |
-
"learning_rate": 3.086582838174551e-05,
|
| 248 |
-
"loss": 10.3666,
|
| 249 |
-
"step": 32
|
| 250 |
-
},
|
| 251 |
-
{
|
| 252 |
-
"epoch": 0.04325032765399738,
|
| 253 |
-
"grad_norm": 0.1730622947216034,
|
| 254 |
-
"learning_rate": 2.7885565489049946e-05,
|
| 255 |
-
"loss": 10.3648,
|
| 256 |
-
"step": 33
|
| 257 |
-
},
|
| 258 |
-
{
|
| 259 |
-
"epoch": 0.04456094364351245,
|
| 260 |
-
"grad_norm": 0.15695245563983917,
|
| 261 |
-
"learning_rate": 2.500000000000001e-05,
|
| 262 |
-
"loss": 10.366,
|
| 263 |
-
"step": 34
|
| 264 |
-
},
|
| 265 |
-
{
|
| 266 |
-
"epoch": 0.045871559633027525,
|
| 267 |
-
"grad_norm": 0.1533222794532776,
|
| 268 |
-
"learning_rate": 2.2221488349019903e-05,
|
| 269 |
-
"loss": 10.3665,
|
| 270 |
-
"step": 35
|
| 271 |
-
},
|
| 272 |
-
{
|
| 273 |
-
"epoch": 0.047182175622542594,
|
| 274 |
-
"grad_norm": 0.1350749284029007,
|
| 275 |
-
"learning_rate": 1.9561928549563968e-05,
|
| 276 |
-
"loss": 10.366,
|
| 277 |
-
"step": 36
|
| 278 |
-
},
|
| 279 |
-
{
|
| 280 |
-
"epoch": 0.04849279161205767,
|
| 281 |
-
"grad_norm": 0.1510956883430481,
|
| 282 |
-
"learning_rate": 1.703270924499656e-05,
|
| 283 |
-
"loss": 10.3639,
|
| 284 |
-
"step": 37
|
| 285 |
-
},
|
| 286 |
-
{
|
| 287 |
-
"epoch": 0.04980340760157274,
|
| 288 |
-
"grad_norm": 0.15642888844013214,
|
| 289 |
-
"learning_rate": 1.4644660940672627e-05,
|
| 290 |
-
"loss": 10.3667,
|
| 291 |
-
"step": 38
|
| 292 |
-
},
|
| 293 |
-
{
|
| 294 |
-
"epoch": 0.05111402359108781,
|
| 295 |
-
"grad_norm": 0.17887574434280396,
|
| 296 |
-
"learning_rate": 1.2408009626051137e-05,
|
| 297 |
-
"loss": 10.3621,
|
| 298 |
-
"step": 39
|
| 299 |
-
},
|
| 300 |
-
{
|
| 301 |
-
"epoch": 0.05242463958060288,
|
| 302 |
-
"grad_norm": 0.17263266444206238,
|
| 303 |
-
"learning_rate": 1.0332332985438248e-05,
|
| 304 |
-
"loss": 10.3623,
|
| 305 |
-
"step": 40
|
| 306 |
-
},
|
| 307 |
-
{
|
| 308 |
-
"epoch": 0.053735255570117955,
|
| 309 |
-
"grad_norm": 0.15901875495910645,
|
| 310 |
-
"learning_rate": 8.426519384872733e-06,
|
| 311 |
-
"loss": 10.3657,
|
| 312 |
-
"step": 41
|
| 313 |
-
},
|
| 314 |
-
{
|
| 315 |
-
"epoch": 0.05504587155963303,
|
| 316 |
-
"grad_norm": 0.1725824922323227,
|
| 317 |
-
"learning_rate": 6.698729810778065e-06,
|
| 318 |
-
"loss": 10.3687,
|
| 319 |
-
"step": 42
|
| 320 |
-
},
|
| 321 |
-
{
|
| 322 |
-
"epoch": 0.0563564875491481,
|
| 323 |
-
"grad_norm": 0.17225879430770874,
|
| 324 |
-
"learning_rate": 5.156362923365588e-06,
|
| 325 |
-
"loss": 10.3635,
|
| 326 |
-
"step": 43
|
| 327 |
-
},
|
| 328 |
-
{
|
| 329 |
-
"epoch": 0.057667103538663174,
|
| 330 |
-
"grad_norm": 0.19542855024337769,
|
| 331 |
-
"learning_rate": 3.8060233744356633e-06,
|
| 332 |
-
"loss": 10.3608,
|
| 333 |
-
"step": 44
|
| 334 |
-
},
|
| 335 |
-
{
|
| 336 |
-
"epoch": 0.05897771952817824,
|
| 337 |
-
"grad_norm": 0.16884516179561615,
|
| 338 |
-
"learning_rate": 2.653493525244721e-06,
|
| 339 |
-
"loss": 10.3693,
|
| 340 |
-
"step": 45
|
| 341 |
-
},
|
| 342 |
-
{
|
| 343 |
-
"epoch": 0.06028833551769332,
|
| 344 |
-
"grad_norm": 0.19233977794647217,
|
| 345 |
-
"learning_rate": 1.70370868554659e-06,
|
| 346 |
-
"loss": 10.3623,
|
| 347 |
-
"step": 46
|
| 348 |
-
},
|
| 349 |
-
{
|
| 350 |
-
"epoch": 0.061598951507208385,
|
| 351 |
-
"grad_norm": 0.204484760761261,
|
| 352 |
-
"learning_rate": 9.607359798384785e-07,
|
| 353 |
-
"loss": 10.3616,
|
| 354 |
-
"step": 47
|
| 355 |
-
},
|
| 356 |
-
{
|
| 357 |
-
"epoch": 0.06290956749672345,
|
| 358 |
-
"grad_norm": 0.23938828706741333,
|
| 359 |
-
"learning_rate": 4.277569313094809e-07,
|
| 360 |
-
"loss": 10.3619,
|
| 361 |
-
"step": 48
|
| 362 |
-
},
|
| 363 |
-
{
|
| 364 |
-
"epoch": 0.06422018348623854,
|
| 365 |
-
"grad_norm": 0.2926636338233948,
|
| 366 |
-
"learning_rate": 1.0705383806982606e-07,
|
| 367 |
-
"loss": 10.364,
|
| 368 |
-
"step": 49
|
| 369 |
-
},
|
| 370 |
{
|
| 371 |
"epoch": 0.0655307994757536,
|
| 372 |
-
"
|
| 373 |
-
"
|
| 374 |
-
"
|
| 375 |
-
"
|
| 376 |
-
|
| 377 |
-
{
|
| 378 |
-
"epoch": 0.0655307994757536,
|
| 379 |
-
"eval_loss": 10.364721298217773,
|
| 380 |
-
"eval_runtime": 7.1814,
|
| 381 |
-
"eval_samples_per_second": 358.006,
|
| 382 |
-
"eval_steps_per_second": 89.536,
|
| 383 |
-
"step": 50
|
| 384 |
}
|
| 385 |
],
|
| 386 |
"logging_steps": 1,
|
|
@@ -404,7 +221,7 @@
|
|
| 404 |
"should_evaluate": false,
|
| 405 |
"should_log": false,
|
| 406 |
"should_save": true,
|
| 407 |
-
"should_training_stop":
|
| 408 |
},
|
| 409 |
"attributes": {}
|
| 410 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 10.368563652038574,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-25",
|
| 4 |
"epoch": 0.0655307994757536,
|
| 5 |
"eval_steps": 25,
|
| 6 |
+
"global_step": 25,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
+
"epoch": 0.002621231979030144,
|
| 13 |
+
"grad_norm": 0.0983472689986229,
|
| 14 |
"learning_rate": 5e-05,
|
| 15 |
+
"loss": 10.3797,
|
| 16 |
"step": 1
|
| 17 |
},
|
| 18 |
{
|
| 19 |
+
"epoch": 0.002621231979030144,
|
| 20 |
+
"eval_loss": 10.380081176757812,
|
| 21 |
+
"eval_runtime": 8.9595,
|
| 22 |
+
"eval_samples_per_second": 286.959,
|
| 23 |
+
"eval_steps_per_second": 143.535,
|
| 24 |
"step": 1
|
| 25 |
},
|
| 26 |
{
|
| 27 |
+
"epoch": 0.005242463958060288,
|
| 28 |
+
"grad_norm": 0.09700549393892288,
|
| 29 |
"learning_rate": 0.0001,
|
| 30 |
+
"loss": 10.3796,
|
| 31 |
"step": 2
|
| 32 |
},
|
| 33 |
{
|
| 34 |
+
"epoch": 0.007863695937090432,
|
| 35 |
+
"grad_norm": 0.09336814284324646,
|
| 36 |
"learning_rate": 9.989294616193017e-05,
|
| 37 |
+
"loss": 10.3799,
|
| 38 |
"step": 3
|
| 39 |
},
|
| 40 |
{
|
| 41 |
+
"epoch": 0.010484927916120577,
|
| 42 |
+
"grad_norm": 0.09867435693740845,
|
| 43 |
"learning_rate": 9.957224306869053e-05,
|
| 44 |
+
"loss": 10.3801,
|
| 45 |
"step": 4
|
| 46 |
},
|
| 47 |
{
|
| 48 |
+
"epoch": 0.01310615989515072,
|
| 49 |
+
"grad_norm": 0.09715370833873749,
|
| 50 |
"learning_rate": 9.903926402016153e-05,
|
| 51 |
+
"loss": 10.3797,
|
| 52 |
"step": 5
|
| 53 |
},
|
| 54 |
{
|
| 55 |
+
"epoch": 0.015727391874180863,
|
| 56 |
+
"grad_norm": 0.10556021332740784,
|
| 57 |
"learning_rate": 9.829629131445342e-05,
|
| 58 |
+
"loss": 10.3784,
|
| 59 |
"step": 6
|
| 60 |
},
|
| 61 |
{
|
| 62 |
+
"epoch": 0.01834862385321101,
|
| 63 |
+
"grad_norm": 0.10574877262115479,
|
| 64 |
"learning_rate": 9.73465064747553e-05,
|
| 65 |
+
"loss": 10.3773,
|
| 66 |
"step": 7
|
| 67 |
},
|
| 68 |
{
|
| 69 |
+
"epoch": 0.020969855832241154,
|
| 70 |
+
"grad_norm": 0.10671475529670715,
|
| 71 |
"learning_rate": 9.619397662556435e-05,
|
| 72 |
+
"loss": 10.3762,
|
| 73 |
"step": 8
|
| 74 |
},
|
| 75 |
{
|
| 76 |
+
"epoch": 0.023591087811271297,
|
| 77 |
+
"grad_norm": 0.10671234875917435,
|
| 78 |
"learning_rate": 9.484363707663442e-05,
|
| 79 |
+
"loss": 10.3758,
|
| 80 |
"step": 9
|
| 81 |
},
|
| 82 |
{
|
| 83 |
+
"epoch": 0.02621231979030144,
|
| 84 |
+
"grad_norm": 0.11303173005580902,
|
| 85 |
"learning_rate": 9.330127018922194e-05,
|
| 86 |
+
"loss": 10.3748,
|
| 87 |
"step": 10
|
| 88 |
},
|
| 89 |
{
|
| 90 |
+
"epoch": 0.028833551769331587,
|
| 91 |
+
"grad_norm": 0.10760895162820816,
|
| 92 |
"learning_rate": 9.157348061512727e-05,
|
| 93 |
+
"loss": 10.3747,
|
| 94 |
"step": 11
|
| 95 |
},
|
| 96 |
{
|
| 97 |
+
"epoch": 0.03145478374836173,
|
| 98 |
+
"grad_norm": 0.10080239921808243,
|
| 99 |
"learning_rate": 8.966766701456177e-05,
|
| 100 |
+
"loss": 10.3732,
|
| 101 |
"step": 12
|
| 102 |
},
|
| 103 |
{
|
| 104 |
+
"epoch": 0.03407601572739188,
|
| 105 |
+
"grad_norm": 0.1232990175485611,
|
| 106 |
"learning_rate": 8.759199037394887e-05,
|
| 107 |
+
"loss": 10.3735,
|
| 108 |
"step": 13
|
| 109 |
},
|
| 110 |
{
|
| 111 |
+
"epoch": 0.03669724770642202,
|
| 112 |
+
"grad_norm": 0.13050110638141632,
|
| 113 |
"learning_rate": 8.535533905932738e-05,
|
| 114 |
+
"loss": 10.3727,
|
| 115 |
"step": 14
|
| 116 |
},
|
| 117 |
{
|
| 118 |
+
"epoch": 0.039318479685452164,
|
| 119 |
+
"grad_norm": 0.12770453095436096,
|
| 120 |
"learning_rate": 8.296729075500344e-05,
|
| 121 |
+
"loss": 10.3726,
|
| 122 |
"step": 15
|
| 123 |
},
|
| 124 |
{
|
| 125 |
+
"epoch": 0.04193971166448231,
|
| 126 |
+
"grad_norm": 0.12612299621105194,
|
| 127 |
"learning_rate": 8.043807145043604e-05,
|
| 128 |
+
"loss": 10.3723,
|
| 129 |
"step": 16
|
| 130 |
},
|
| 131 |
{
|
| 132 |
+
"epoch": 0.04456094364351245,
|
| 133 |
+
"grad_norm": 0.12636294960975647,
|
| 134 |
"learning_rate": 7.777851165098012e-05,
|
| 135 |
+
"loss": 10.3726,
|
| 136 |
"step": 17
|
| 137 |
},
|
| 138 |
{
|
| 139 |
+
"epoch": 0.047182175622542594,
|
| 140 |
+
"grad_norm": 0.1317187249660492,
|
| 141 |
"learning_rate": 7.500000000000001e-05,
|
| 142 |
+
"loss": 10.3704,
|
| 143 |
"step": 18
|
| 144 |
},
|
| 145 |
{
|
| 146 |
+
"epoch": 0.04980340760157274,
|
| 147 |
+
"grad_norm": 0.13668107986450195,
|
| 148 |
"learning_rate": 7.211443451095007e-05,
|
| 149 |
+
"loss": 10.3773,
|
| 150 |
"step": 19
|
| 151 |
},
|
| 152 |
{
|
| 153 |
+
"epoch": 0.05242463958060288,
|
| 154 |
+
"grad_norm": 0.14118903875350952,
|
| 155 |
"learning_rate": 6.91341716182545e-05,
|
| 156 |
+
"loss": 10.3728,
|
| 157 |
"step": 20
|
| 158 |
},
|
| 159 |
{
|
| 160 |
+
"epoch": 0.05504587155963303,
|
| 161 |
+
"grad_norm": 0.16648933291435242,
|
| 162 |
"learning_rate": 6.607197326515808e-05,
|
| 163 |
+
"loss": 10.3702,
|
| 164 |
"step": 21
|
| 165 |
},
|
| 166 |
{
|
| 167 |
+
"epoch": 0.057667103538663174,
|
| 168 |
+
"grad_norm": 0.1857651323080063,
|
| 169 |
"learning_rate": 6.294095225512603e-05,
|
| 170 |
+
"loss": 10.368,
|
| 171 |
"step": 22
|
| 172 |
},
|
| 173 |
{
|
| 174 |
+
"epoch": 0.06028833551769332,
|
| 175 |
+
"grad_norm": 0.21679675579071045,
|
| 176 |
"learning_rate": 5.9754516100806423e-05,
|
| 177 |
+
"loss": 10.3668,
|
| 178 |
"step": 23
|
| 179 |
},
|
| 180 |
{
|
| 181 |
+
"epoch": 0.06290956749672345,
|
| 182 |
+
"grad_norm": 0.26074954867362976,
|
| 183 |
"learning_rate": 5.6526309611002594e-05,
|
| 184 |
+
"loss": 10.3705,
|
| 185 |
"step": 24
|
| 186 |
},
|
| 187 |
{
|
| 188 |
+
"epoch": 0.0655307994757536,
|
| 189 |
+
"grad_norm": 0.32028478384017944,
|
| 190 |
"learning_rate": 5.327015646150716e-05,
|
| 191 |
"loss": 10.3763,
|
| 192 |
"step": 25
|
| 193 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 194 |
{
|
| 195 |
"epoch": 0.0655307994757536,
|
| 196 |
+
"eval_loss": 10.368563652038574,
|
| 197 |
+
"eval_runtime": 8.8771,
|
| 198 |
+
"eval_samples_per_second": 289.621,
|
| 199 |
+
"eval_steps_per_second": 144.867,
|
| 200 |
+
"step": 25
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 201 |
}
|
| 202 |
],
|
| 203 |
"logging_steps": 1,
|
|
|
|
| 221 |
"should_evaluate": false,
|
| 222 |
"should_log": false,
|
| 223 |
"should_save": true,
|
| 224 |
+
"should_training_stop": false
|
| 225 |
},
|
| 226 |
"attributes": {}
|
| 227 |
}
|
last-checkpoint/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:dbc8ad6344141c65c086264a78841e7f4627d66d48aed40b5efe95944405944b
|
| 3 |
+
size 6840
|