Training in progress, step 50, checkpoint
Browse files- last-checkpoint/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/rng_state_2.pth +1 -1
- last-checkpoint/rng_state_3.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +78 -560
- last-checkpoint/training_args.bin +1 -1
last-checkpoint/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1738460416
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e219b25b7e3609e604ef05ade6d200dabd377e65247e60e3e2ff5ed1c7e25fe1
|
| 3 |
size 1738460416
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3477327340
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cb5c19a9e3e14de1d661eba59716d3a9e1a9a87a5be68b944fb729f292c5937b
|
| 3 |
size 3477327340
|
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 15429
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9892a41432d4e48929c5376b8225d5373bb9afe9f14665fbcb3934dc45cb330a
|
| 3 |
size 15429
|
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 15429
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b6f3949e2b25ad05905da16bc2d58aeadc9a9f1db0b0e97a04ceb63467acff1d
|
| 3 |
size 15429
|
last-checkpoint/rng_state_2.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15429
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5c3812c5e7f13c9d32f97d83cd625428061b1c9486e869caffd453d83ac07ceb
|
| 3 |
size 15429
|
last-checkpoint/rng_state_3.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15429
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6eda756b33768639c1e1932ae00c5d43269de5705c09162bc09acdf71d3533c0
|
| 3 |
size 15429
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ac56030360eaf7d09a44b289120bcd685e39fa9a366361e9c512debf4fa01791
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,611 +2,129 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 0.
|
| 6 |
-
"eval_steps":
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
| 11 |
"log_history": [
|
| 12 |
{
|
| 13 |
-
"epoch": 0.
|
| 14 |
-
"grad_norm":
|
| 15 |
-
"learning_rate":
|
| 16 |
-
"loss":
|
| 17 |
"step": 5
|
| 18 |
},
|
| 19 |
{
|
| 20 |
-
"epoch": 0.
|
| 21 |
-
"grad_norm":
|
| 22 |
-
"learning_rate":
|
| 23 |
-
"loss":
|
| 24 |
"step": 10
|
| 25 |
},
|
| 26 |
-
{
|
| 27 |
-
"epoch": 0.01,
|
| 28 |
-
"grad_norm": 12.9375,
|
| 29 |
-
"learning_rate": 2e-05,
|
| 30 |
-
"loss": 44.1295,
|
| 31 |
-
"step": 15
|
| 32 |
-
},
|
| 33 |
-
{
|
| 34 |
-
"epoch": 0.013333333333333334,
|
| 35 |
-
"grad_norm": 9.6875,
|
| 36 |
-
"learning_rate": 2e-05,
|
| 37 |
-
"loss": 41.9134,
|
| 38 |
-
"step": 20
|
| 39 |
-
},
|
| 40 |
-
{
|
| 41 |
-
"epoch": 0.016666666666666666,
|
| 42 |
-
"grad_norm": 8.25,
|
| 43 |
-
"learning_rate": 2e-05,
|
| 44 |
-
"loss": 40.9631,
|
| 45 |
-
"step": 25
|
| 46 |
-
},
|
| 47 |
-
{
|
| 48 |
-
"epoch": 0.02,
|
| 49 |
-
"grad_norm": 7.53125,
|
| 50 |
-
"learning_rate": 2e-05,
|
| 51 |
-
"loss": 40.2396,
|
| 52 |
-
"step": 30
|
| 53 |
-
},
|
| 54 |
-
{
|
| 55 |
-
"epoch": 0.023333333333333334,
|
| 56 |
-
"grad_norm": 7.65625,
|
| 57 |
-
"learning_rate": 2e-05,
|
| 58 |
-
"loss": 39.7111,
|
| 59 |
-
"step": 35
|
| 60 |
-
},
|
| 61 |
-
{
|
| 62 |
-
"epoch": 0.02666666666666667,
|
| 63 |
-
"grad_norm": 7.375,
|
| 64 |
-
"learning_rate": 2e-05,
|
| 65 |
-
"loss": 39.2189,
|
| 66 |
-
"step": 40
|
| 67 |
-
},
|
| 68 |
-
{
|
| 69 |
-
"epoch": 0.03,
|
| 70 |
-
"grad_norm": 6.96875,
|
| 71 |
-
"learning_rate": 2e-05,
|
| 72 |
-
"loss": 38.8553,
|
| 73 |
-
"step": 45
|
| 74 |
-
},
|
| 75 |
-
{
|
| 76 |
-
"epoch": 0.03333333333333333,
|
| 77 |
-
"grad_norm": 6.78125,
|
| 78 |
-
"learning_rate": 2e-05,
|
| 79 |
-
"loss": 38.5259,
|
| 80 |
-
"step": 50
|
| 81 |
-
},
|
| 82 |
-
{
|
| 83 |
-
"epoch": 0.03666666666666667,
|
| 84 |
-
"grad_norm": 6.53125,
|
| 85 |
-
"learning_rate": 2e-05,
|
| 86 |
-
"loss": 38.059,
|
| 87 |
-
"step": 55
|
| 88 |
-
},
|
| 89 |
-
{
|
| 90 |
-
"epoch": 0.04,
|
| 91 |
-
"grad_norm": 6.78125,
|
| 92 |
-
"learning_rate": 2e-05,
|
| 93 |
-
"loss": 37.7568,
|
| 94 |
-
"step": 60
|
| 95 |
-
},
|
| 96 |
-
{
|
| 97 |
-
"epoch": 0.043333333333333335,
|
| 98 |
-
"grad_norm": 6.375,
|
| 99 |
-
"learning_rate": 2e-05,
|
| 100 |
-
"loss": 37.3479,
|
| 101 |
-
"step": 65
|
| 102 |
-
},
|
| 103 |
-
{
|
| 104 |
-
"epoch": 0.04666666666666667,
|
| 105 |
-
"grad_norm": 6.4375,
|
| 106 |
-
"learning_rate": 2e-05,
|
| 107 |
-
"loss": 37.0288,
|
| 108 |
-
"step": 70
|
| 109 |
-
},
|
| 110 |
{
|
| 111 |
"epoch": 0.05,
|
| 112 |
-
"
|
| 113 |
-
"
|
| 114 |
-
"
|
| 115 |
-
"step": 75
|
| 116 |
-
},
|
| 117 |
-
{
|
| 118 |
-
"epoch": 0.05333333333333334,
|
| 119 |
-
"grad_norm": 6.0625,
|
| 120 |
-
"learning_rate": 2e-05,
|
| 121 |
-
"loss": 36.362,
|
| 122 |
-
"step": 80
|
| 123 |
-
},
|
| 124 |
-
{
|
| 125 |
-
"epoch": 0.056666666666666664,
|
| 126 |
-
"grad_norm": 5.875,
|
| 127 |
-
"learning_rate": 2e-05,
|
| 128 |
-
"loss": 36.1666,
|
| 129 |
-
"step": 85
|
| 130 |
-
},
|
| 131 |
-
{
|
| 132 |
-
"epoch": 0.06,
|
| 133 |
-
"grad_norm": 5.9375,
|
| 134 |
-
"learning_rate": 2e-05,
|
| 135 |
-
"loss": 35.8911,
|
| 136 |
-
"step": 90
|
| 137 |
-
},
|
| 138 |
-
{
|
| 139 |
-
"epoch": 0.06333333333333334,
|
| 140 |
-
"grad_norm": 5.4375,
|
| 141 |
-
"learning_rate": 2e-05,
|
| 142 |
-
"loss": 35.6416,
|
| 143 |
-
"step": 95
|
| 144 |
-
},
|
| 145 |
-
{
|
| 146 |
-
"epoch": 0.06666666666666667,
|
| 147 |
-
"grad_norm": 5.71875,
|
| 148 |
-
"learning_rate": 2e-05,
|
| 149 |
-
"loss": 35.3982,
|
| 150 |
-
"step": 100
|
| 151 |
-
},
|
| 152 |
-
{
|
| 153 |
-
"epoch": 0.06666666666666667,
|
| 154 |
-
"eval_loss": 8.794044494628906,
|
| 155 |
-
"eval_runtime": 6.9551,
|
| 156 |
-
"eval_samples_per_second": 38.676,
|
| 157 |
"eval_steps_per_second": 1.006,
|
| 158 |
-
"step":
|
| 159 |
-
},
|
| 160 |
-
{
|
| 161 |
-
"epoch": 0.07,
|
| 162 |
-
"grad_norm": 5.5,
|
| 163 |
-
"learning_rate": 2e-05,
|
| 164 |
-
"loss": 35.1707,
|
| 165 |
-
"step": 105
|
| 166 |
-
},
|
| 167 |
-
{
|
| 168 |
-
"epoch": 0.07333333333333333,
|
| 169 |
-
"grad_norm": 5.875,
|
| 170 |
-
"learning_rate": 2e-05,
|
| 171 |
-
"loss": 34.8065,
|
| 172 |
-
"step": 110
|
| 173 |
-
},
|
| 174 |
-
{
|
| 175 |
-
"epoch": 0.07666666666666666,
|
| 176 |
-
"grad_norm": 5.09375,
|
| 177 |
-
"learning_rate": 2e-05,
|
| 178 |
-
"loss": 34.5524,
|
| 179 |
-
"step": 115
|
| 180 |
-
},
|
| 181 |
-
{
|
| 182 |
-
"epoch": 0.08,
|
| 183 |
-
"grad_norm": 5.9375,
|
| 184 |
-
"learning_rate": 2e-05,
|
| 185 |
-
"loss": 34.5738,
|
| 186 |
-
"step": 120
|
| 187 |
-
},
|
| 188 |
-
{
|
| 189 |
-
"epoch": 0.08333333333333333,
|
| 190 |
-
"grad_norm": 4.96875,
|
| 191 |
-
"learning_rate": 2e-05,
|
| 192 |
-
"loss": 34.1881,
|
| 193 |
-
"step": 125
|
| 194 |
-
},
|
| 195 |
-
{
|
| 196 |
-
"epoch": 0.08666666666666667,
|
| 197 |
-
"grad_norm": 4.9375,
|
| 198 |
-
"learning_rate": 2e-05,
|
| 199 |
-
"loss": 34.0342,
|
| 200 |
-
"step": 130
|
| 201 |
-
},
|
| 202 |
-
{
|
| 203 |
-
"epoch": 0.09,
|
| 204 |
-
"grad_norm": 4.9375,
|
| 205 |
-
"learning_rate": 2e-05,
|
| 206 |
-
"loss": 33.7996,
|
| 207 |
-
"step": 135
|
| 208 |
-
},
|
| 209 |
-
{
|
| 210 |
-
"epoch": 0.09333333333333334,
|
| 211 |
-
"grad_norm": 4.8125,
|
| 212 |
-
"learning_rate": 2e-05,
|
| 213 |
-
"loss": 33.5324,
|
| 214 |
-
"step": 140
|
| 215 |
},
|
| 216 |
{
|
| 217 |
-
"epoch": 0.
|
| 218 |
-
"grad_norm":
|
| 219 |
-
"learning_rate":
|
| 220 |
-
"loss":
|
| 221 |
-
"step":
|
| 222 |
},
|
| 223 |
{
|
| 224 |
"epoch": 0.1,
|
| 225 |
-
"grad_norm":
|
| 226 |
-
"learning_rate":
|
| 227 |
-
"loss":
|
| 228 |
-
"step":
|
| 229 |
-
},
|
| 230 |
-
{
|
| 231 |
-
"epoch": 0.10333333333333333,
|
| 232 |
-
"grad_norm": 4.78125,
|
| 233 |
-
"learning_rate": 2e-05,
|
| 234 |
-
"loss": 33.0172,
|
| 235 |
-
"step": 155
|
| 236 |
-
},
|
| 237 |
-
{
|
| 238 |
-
"epoch": 0.10666666666666667,
|
| 239 |
-
"grad_norm": 4.53125,
|
| 240 |
-
"learning_rate": 2e-05,
|
| 241 |
-
"loss": 32.9073,
|
| 242 |
-
"step": 160
|
| 243 |
-
},
|
| 244 |
-
{
|
| 245 |
-
"epoch": 0.11,
|
| 246 |
-
"grad_norm": 4.53125,
|
| 247 |
-
"learning_rate": 2e-05,
|
| 248 |
-
"loss": 32.5479,
|
| 249 |
-
"step": 165
|
| 250 |
-
},
|
| 251 |
-
{
|
| 252 |
-
"epoch": 0.11333333333333333,
|
| 253 |
-
"grad_norm": 4.46875,
|
| 254 |
-
"learning_rate": 2e-05,
|
| 255 |
-
"loss": 32.4669,
|
| 256 |
-
"step": 170
|
| 257 |
-
},
|
| 258 |
-
{
|
| 259 |
-
"epoch": 0.11666666666666667,
|
| 260 |
-
"grad_norm": 5.8125,
|
| 261 |
-
"learning_rate": 2e-05,
|
| 262 |
-
"loss": 32.4108,
|
| 263 |
-
"step": 175
|
| 264 |
-
},
|
| 265 |
-
{
|
| 266 |
-
"epoch": 0.12,
|
| 267 |
-
"grad_norm": 4.5625,
|
| 268 |
-
"learning_rate": 2e-05,
|
| 269 |
-
"loss": 32.0156,
|
| 270 |
-
"step": 180
|
| 271 |
-
},
|
| 272 |
-
{
|
| 273 |
-
"epoch": 0.12333333333333334,
|
| 274 |
-
"grad_norm": 4.34375,
|
| 275 |
-
"learning_rate": 2e-05,
|
| 276 |
-
"loss": 32.0051,
|
| 277 |
-
"step": 185
|
| 278 |
-
},
|
| 279 |
-
{
|
| 280 |
-
"epoch": 0.12666666666666668,
|
| 281 |
-
"grad_norm": 4.34375,
|
| 282 |
-
"learning_rate": 2e-05,
|
| 283 |
-
"loss": 31.8771,
|
| 284 |
-
"step": 190
|
| 285 |
-
},
|
| 286 |
-
{
|
| 287 |
-
"epoch": 0.13,
|
| 288 |
-
"grad_norm": 4.6875,
|
| 289 |
-
"learning_rate": 2e-05,
|
| 290 |
-
"loss": 31.6117,
|
| 291 |
-
"step": 195
|
| 292 |
-
},
|
| 293 |
-
{
|
| 294 |
-
"epoch": 0.13333333333333333,
|
| 295 |
-
"grad_norm": 4.3125,
|
| 296 |
-
"learning_rate": 2e-05,
|
| 297 |
-
"loss": 31.5273,
|
| 298 |
-
"step": 200
|
| 299 |
-
},
|
| 300 |
-
{
|
| 301 |
-
"epoch": 0.13333333333333333,
|
| 302 |
-
"eval_loss": 7.888162612915039,
|
| 303 |
-
"eval_runtime": 6.8793,
|
| 304 |
-
"eval_samples_per_second": 39.103,
|
| 305 |
-
"eval_steps_per_second": 1.018,
|
| 306 |
-
"step": 200
|
| 307 |
-
},
|
| 308 |
-
{
|
| 309 |
-
"epoch": 0.13666666666666666,
|
| 310 |
-
"grad_norm": 4.0625,
|
| 311 |
-
"learning_rate": 2e-05,
|
| 312 |
-
"loss": 31.3537,
|
| 313 |
-
"step": 205
|
| 314 |
-
},
|
| 315 |
-
{
|
| 316 |
-
"epoch": 0.14,
|
| 317 |
-
"grad_norm": 4.34375,
|
| 318 |
-
"learning_rate": 2e-05,
|
| 319 |
-
"loss": 31.1251,
|
| 320 |
-
"step": 210
|
| 321 |
},
|
| 322 |
{
|
| 323 |
-
"epoch": 0.
|
| 324 |
-
"
|
| 325 |
-
"
|
| 326 |
-
"
|
| 327 |
-
"
|
|
|
|
| 328 |
},
|
| 329 |
{
|
| 330 |
-
"epoch": 0.
|
| 331 |
-
"grad_norm":
|
| 332 |
-
"learning_rate":
|
| 333 |
-
"loss":
|
| 334 |
-
"step":
|
| 335 |
},
|
| 336 |
{
|
| 337 |
"epoch": 0.15,
|
| 338 |
-
"grad_norm":
|
| 339 |
-
"learning_rate":
|
| 340 |
-
"loss":
|
| 341 |
-
"step":
|
| 342 |
-
},
|
| 343 |
-
{
|
| 344 |
-
"epoch": 0.15333333333333332,
|
| 345 |
-
"grad_norm": 3.953125,
|
| 346 |
-
"learning_rate": 2e-05,
|
| 347 |
-
"loss": 30.6811,
|
| 348 |
-
"step": 230
|
| 349 |
-
},
|
| 350 |
-
{
|
| 351 |
-
"epoch": 0.15666666666666668,
|
| 352 |
-
"grad_norm": 3.609375,
|
| 353 |
-
"learning_rate": 2e-05,
|
| 354 |
-
"loss": 30.6916,
|
| 355 |
-
"step": 235
|
| 356 |
-
},
|
| 357 |
-
{
|
| 358 |
-
"epoch": 0.16,
|
| 359 |
-
"grad_norm": 4.1875,
|
| 360 |
-
"learning_rate": 2e-05,
|
| 361 |
-
"loss": 30.3585,
|
| 362 |
-
"step": 240
|
| 363 |
-
},
|
| 364 |
-
{
|
| 365 |
-
"epoch": 0.16333333333333333,
|
| 366 |
-
"grad_norm": 5.90625,
|
| 367 |
-
"learning_rate": 2e-05,
|
| 368 |
-
"loss": 30.4089,
|
| 369 |
-
"step": 245
|
| 370 |
-
},
|
| 371 |
-
{
|
| 372 |
-
"epoch": 0.16666666666666666,
|
| 373 |
-
"grad_norm": 15.3125,
|
| 374 |
-
"learning_rate": 2e-05,
|
| 375 |
-
"loss": 30.3882,
|
| 376 |
-
"step": 250
|
| 377 |
-
},
|
| 378 |
-
{
|
| 379 |
-
"epoch": 0.17,
|
| 380 |
-
"grad_norm": 8.25,
|
| 381 |
-
"learning_rate": 2e-05,
|
| 382 |
-
"loss": 30.2357,
|
| 383 |
-
"step": 255
|
| 384 |
-
},
|
| 385 |
-
{
|
| 386 |
-
"epoch": 0.17333333333333334,
|
| 387 |
-
"grad_norm": 8.875,
|
| 388 |
-
"learning_rate": 2e-05,
|
| 389 |
-
"loss": 30.2875,
|
| 390 |
-
"step": 260
|
| 391 |
-
},
|
| 392 |
-
{
|
| 393 |
-
"epoch": 0.17666666666666667,
|
| 394 |
-
"grad_norm": 21.375,
|
| 395 |
-
"learning_rate": 2e-05,
|
| 396 |
-
"loss": 30.1799,
|
| 397 |
-
"step": 265
|
| 398 |
-
},
|
| 399 |
-
{
|
| 400 |
-
"epoch": 0.18,
|
| 401 |
-
"grad_norm": 33.25,
|
| 402 |
-
"learning_rate": 2e-05,
|
| 403 |
-
"loss": 30.3195,
|
| 404 |
-
"step": 270
|
| 405 |
-
},
|
| 406 |
-
{
|
| 407 |
-
"epoch": 0.18333333333333332,
|
| 408 |
-
"grad_norm": 14.0625,
|
| 409 |
-
"learning_rate": 2e-05,
|
| 410 |
-
"loss": 30.3163,
|
| 411 |
-
"step": 275
|
| 412 |
-
},
|
| 413 |
-
{
|
| 414 |
-
"epoch": 0.18666666666666668,
|
| 415 |
-
"grad_norm": 5.25,
|
| 416 |
-
"learning_rate": 2e-05,
|
| 417 |
-
"loss": 30.2876,
|
| 418 |
-
"step": 280
|
| 419 |
-
},
|
| 420 |
-
{
|
| 421 |
-
"epoch": 0.19,
|
| 422 |
-
"grad_norm": 3.78125,
|
| 423 |
-
"learning_rate": 2e-05,
|
| 424 |
-
"loss": 30.3209,
|
| 425 |
-
"step": 285
|
| 426 |
},
|
| 427 |
{
|
| 428 |
-
"epoch": 0.
|
| 429 |
-
"
|
| 430 |
-
"
|
| 431 |
-
"
|
| 432 |
-
"
|
|
|
|
| 433 |
},
|
| 434 |
{
|
| 435 |
-
"epoch": 0.
|
| 436 |
-
"grad_norm":
|
| 437 |
-
"learning_rate":
|
| 438 |
-
"loss":
|
| 439 |
-
"step":
|
| 440 |
},
|
| 441 |
{
|
| 442 |
"epoch": 0.2,
|
| 443 |
-
"grad_norm":
|
| 444 |
-
"learning_rate":
|
| 445 |
-
"loss":
|
| 446 |
-
"step":
|
| 447 |
},
|
| 448 |
{
|
| 449 |
"epoch": 0.2,
|
| 450 |
-
"eval_loss": 7.
|
| 451 |
-
"eval_runtime": 6.
|
| 452 |
-
"eval_samples_per_second":
|
| 453 |
-
"eval_steps_per_second": 1.
|
| 454 |
-
"step":
|
| 455 |
-
},
|
| 456 |
-
{
|
| 457 |
-
"epoch": 0.20333333333333334,
|
| 458 |
-
"grad_norm": 17.375,
|
| 459 |
-
"learning_rate": 2e-05,
|
| 460 |
-
"loss": 29.8938,
|
| 461 |
-
"step": 305
|
| 462 |
-
},
|
| 463 |
-
{
|
| 464 |
-
"epoch": 0.20666666666666667,
|
| 465 |
-
"grad_norm": 24.375,
|
| 466 |
-
"learning_rate": 2e-05,
|
| 467 |
-
"loss": 29.8926,
|
| 468 |
-
"step": 310
|
| 469 |
-
},
|
| 470 |
-
{
|
| 471 |
-
"epoch": 0.21,
|
| 472 |
-
"grad_norm": 36.5,
|
| 473 |
-
"learning_rate": 2e-05,
|
| 474 |
-
"loss": 29.9906,
|
| 475 |
-
"step": 315
|
| 476 |
-
},
|
| 477 |
-
{
|
| 478 |
-
"epoch": 0.21333333333333335,
|
| 479 |
-
"grad_norm": 23.0,
|
| 480 |
-
"learning_rate": 2e-05,
|
| 481 |
-
"loss": 29.9687,
|
| 482 |
-
"step": 320
|
| 483 |
-
},
|
| 484 |
-
{
|
| 485 |
-
"epoch": 0.21666666666666667,
|
| 486 |
-
"grad_norm": 30.625,
|
| 487 |
-
"learning_rate": 2e-05,
|
| 488 |
-
"loss": 30.0537,
|
| 489 |
-
"step": 325
|
| 490 |
-
},
|
| 491 |
-
{
|
| 492 |
-
"epoch": 0.22,
|
| 493 |
-
"grad_norm": 26.0,
|
| 494 |
-
"learning_rate": 2e-05,
|
| 495 |
-
"loss": 30.3012,
|
| 496 |
-
"step": 330
|
| 497 |
-
},
|
| 498 |
-
{
|
| 499 |
-
"epoch": 0.22333333333333333,
|
| 500 |
-
"grad_norm": 24.0,
|
| 501 |
-
"learning_rate": 2e-05,
|
| 502 |
-
"loss": 29.9831,
|
| 503 |
-
"step": 335
|
| 504 |
-
},
|
| 505 |
-
{
|
| 506 |
-
"epoch": 0.22666666666666666,
|
| 507 |
-
"grad_norm": 5.53125,
|
| 508 |
-
"learning_rate": 2e-05,
|
| 509 |
-
"loss": 30.1414,
|
| 510 |
-
"step": 340
|
| 511 |
-
},
|
| 512 |
-
{
|
| 513 |
-
"epoch": 0.23,
|
| 514 |
-
"grad_norm": 8.5625,
|
| 515 |
-
"learning_rate": 2e-05,
|
| 516 |
-
"loss": 29.8688,
|
| 517 |
-
"step": 345
|
| 518 |
-
},
|
| 519 |
-
{
|
| 520 |
-
"epoch": 0.23333333333333334,
|
| 521 |
-
"grad_norm": 15.375,
|
| 522 |
-
"learning_rate": 2e-05,
|
| 523 |
-
"loss": 29.9341,
|
| 524 |
-
"step": 350
|
| 525 |
-
},
|
| 526 |
-
{
|
| 527 |
-
"epoch": 0.23666666666666666,
|
| 528 |
-
"grad_norm": 4.625,
|
| 529 |
-
"learning_rate": 2e-05,
|
| 530 |
-
"loss": 29.8085,
|
| 531 |
-
"step": 355
|
| 532 |
-
},
|
| 533 |
-
{
|
| 534 |
-
"epoch": 0.24,
|
| 535 |
-
"grad_norm": 5.0625,
|
| 536 |
-
"learning_rate": 2e-05,
|
| 537 |
-
"loss": 29.7093,
|
| 538 |
-
"step": 360
|
| 539 |
-
},
|
| 540 |
-
{
|
| 541 |
-
"epoch": 0.24333333333333335,
|
| 542 |
-
"grad_norm": 6.8125,
|
| 543 |
-
"learning_rate": 2e-05,
|
| 544 |
-
"loss": 29.6956,
|
| 545 |
-
"step": 365
|
| 546 |
},
|
| 547 |
{
|
| 548 |
-
"epoch": 0.
|
| 549 |
-
"grad_norm":
|
| 550 |
-
"learning_rate":
|
| 551 |
-
"loss":
|
| 552 |
-
"step":
|
| 553 |
},
|
| 554 |
{
|
| 555 |
"epoch": 0.25,
|
| 556 |
-
"grad_norm":
|
| 557 |
-
"learning_rate":
|
| 558 |
-
"loss":
|
| 559 |
-
"step":
|
| 560 |
-
},
|
| 561 |
-
{
|
| 562 |
-
"epoch": 0.25333333333333335,
|
| 563 |
-
"grad_norm": 9.5,
|
| 564 |
-
"learning_rate": 2e-05,
|
| 565 |
-
"loss": 29.6157,
|
| 566 |
-
"step": 380
|
| 567 |
-
},
|
| 568 |
-
{
|
| 569 |
-
"epoch": 0.25666666666666665,
|
| 570 |
-
"grad_norm": 23.5,
|
| 571 |
-
"learning_rate": 2e-05,
|
| 572 |
-
"loss": 29.6261,
|
| 573 |
-
"step": 385
|
| 574 |
-
},
|
| 575 |
-
{
|
| 576 |
-
"epoch": 0.26,
|
| 577 |
-
"grad_norm": 21.75,
|
| 578 |
-
"learning_rate": 2e-05,
|
| 579 |
-
"loss": 29.6411,
|
| 580 |
-
"step": 390
|
| 581 |
-
},
|
| 582 |
-
{
|
| 583 |
-
"epoch": 0.2633333333333333,
|
| 584 |
-
"grad_norm": 30.25,
|
| 585 |
-
"learning_rate": 2e-05,
|
| 586 |
-
"loss": 29.7162,
|
| 587 |
-
"step": 395
|
| 588 |
-
},
|
| 589 |
-
{
|
| 590 |
-
"epoch": 0.26666666666666666,
|
| 591 |
-
"grad_norm": 8.3125,
|
| 592 |
-
"learning_rate": 2e-05,
|
| 593 |
-
"loss": 29.6952,
|
| 594 |
-
"step": 400
|
| 595 |
},
|
| 596 |
{
|
| 597 |
-
"epoch": 0.
|
| 598 |
-
"eval_loss":
|
| 599 |
-
"eval_runtime": 6.
|
| 600 |
-
"eval_samples_per_second":
|
| 601 |
-
"eval_steps_per_second": 1.
|
| 602 |
-
"step":
|
| 603 |
}
|
| 604 |
],
|
| 605 |
"logging_steps": 5,
|
| 606 |
-
"max_steps":
|
| 607 |
"num_input_tokens_seen": 0,
|
| 608 |
"num_train_epochs": 9223372036854775807,
|
| 609 |
-
"save_steps":
|
| 610 |
"stateful_callbacks": {
|
| 611 |
"TrainerControl": {
|
| 612 |
"args": {
|
|
@@ -619,8 +137,8 @@
|
|
| 619 |
"attributes": {}
|
| 620 |
}
|
| 621 |
},
|
| 622 |
-
"total_flos":
|
| 623 |
-
"train_batch_size":
|
| 624 |
"trial_name": null,
|
| 625 |
"trial_params": null
|
| 626 |
}
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.25,
|
| 6 |
+
"eval_steps": 10,
|
| 7 |
+
"global_step": 50,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
| 11 |
"log_history": [
|
| 12 |
{
|
| 13 |
+
"epoch": 0.025,
|
| 14 |
+
"grad_norm": 67.5,
|
| 15 |
+
"learning_rate": 0.0004,
|
| 16 |
+
"loss": 271.8493,
|
| 17 |
"step": 5
|
| 18 |
},
|
| 19 |
{
|
| 20 |
+
"epoch": 0.05,
|
| 21 |
+
"grad_norm": 68.5,
|
| 22 |
+
"learning_rate": 0.0009000000000000001,
|
| 23 |
+
"loss": 208.6483,
|
| 24 |
"step": 10
|
| 25 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 26 |
{
|
| 27 |
"epoch": 0.05,
|
| 28 |
+
"eval_loss": 7.974327087402344,
|
| 29 |
+
"eval_runtime": 6.9602,
|
| 30 |
+
"eval_samples_per_second": 19.252,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 31 |
"eval_steps_per_second": 1.006,
|
| 32 |
+
"step": 10
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 33 |
},
|
| 34 |
{
|
| 35 |
+
"epoch": 0.075,
|
| 36 |
+
"grad_norm": 114.5,
|
| 37 |
+
"learning_rate": 0.0009989068136093873,
|
| 38 |
+
"loss": 190.7281,
|
| 39 |
+
"step": 15
|
| 40 |
},
|
| 41 |
{
|
| 42 |
"epoch": 0.1,
|
| 43 |
+
"grad_norm": 26.25,
|
| 44 |
+
"learning_rate": 0.0009944739353007343,
|
| 45 |
+
"loss": 188.7951,
|
| 46 |
+
"step": 20
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 47 |
},
|
| 48 |
{
|
| 49 |
+
"epoch": 0.1,
|
| 50 |
+
"eval_loss": 7.880503177642822,
|
| 51 |
+
"eval_runtime": 6.6198,
|
| 52 |
+
"eval_samples_per_second": 20.242,
|
| 53 |
+
"eval_steps_per_second": 1.057,
|
| 54 |
+
"step": 20
|
| 55 |
},
|
| 56 |
{
|
| 57 |
+
"epoch": 0.125,
|
| 58 |
+
"grad_norm": 23.75,
|
| 59 |
+
"learning_rate": 0.000986663298624003,
|
| 60 |
+
"loss": 186.3658,
|
| 61 |
+
"step": 25
|
| 62 |
},
|
| 63 |
{
|
| 64 |
"epoch": 0.15,
|
| 65 |
+
"grad_norm": 14.5,
|
| 66 |
+
"learning_rate": 0.0009755282581475768,
|
| 67 |
+
"loss": 185.2524,
|
| 68 |
+
"step": 30
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 69 |
},
|
| 70 |
{
|
| 71 |
+
"epoch": 0.15,
|
| 72 |
+
"eval_loss": 7.70925760269165,
|
| 73 |
+
"eval_runtime": 6.8441,
|
| 74 |
+
"eval_samples_per_second": 19.579,
|
| 75 |
+
"eval_steps_per_second": 1.023,
|
| 76 |
+
"step": 30
|
| 77 |
},
|
| 78 |
{
|
| 79 |
+
"epoch": 0.175,
|
| 80 |
+
"grad_norm": 20.75,
|
| 81 |
+
"learning_rate": 0.0009611448774886924,
|
| 82 |
+
"loss": 182.743,
|
| 83 |
+
"step": 35
|
| 84 |
},
|
| 85 |
{
|
| 86 |
"epoch": 0.2,
|
| 87 |
+
"grad_norm": 146.0,
|
| 88 |
+
"learning_rate": 0.000943611409721806,
|
| 89 |
+
"loss": 181.0595,
|
| 90 |
+
"step": 40
|
| 91 |
},
|
| 92 |
{
|
| 93 |
"epoch": 0.2,
|
| 94 |
+
"eval_loss": 7.680881023406982,
|
| 95 |
+
"eval_runtime": 6.8778,
|
| 96 |
+
"eval_samples_per_second": 19.483,
|
| 97 |
+
"eval_steps_per_second": 1.018,
|
| 98 |
+
"step": 40
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 99 |
},
|
| 100 |
{
|
| 101 |
+
"epoch": 0.225,
|
| 102 |
+
"grad_norm": 14336.0,
|
| 103 |
+
"learning_rate": 0.0009230476262104677,
|
| 104 |
+
"loss": 183.6445,
|
| 105 |
+
"step": 45
|
| 106 |
},
|
| 107 |
{
|
| 108 |
"epoch": 0.25,
|
| 109 |
+
"grad_norm": 10176.0,
|
| 110 |
+
"learning_rate": 0.0008995939984474624,
|
| 111 |
+
"loss": 192.1855,
|
| 112 |
+
"step": 50
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 113 |
},
|
| 114 |
{
|
| 115 |
+
"epoch": 0.25,
|
| 116 |
+
"eval_loss": 8.385082244873047,
|
| 117 |
+
"eval_runtime": 6.7705,
|
| 118 |
+
"eval_samples_per_second": 19.792,
|
| 119 |
+
"eval_steps_per_second": 1.034,
|
| 120 |
+
"step": 50
|
| 121 |
}
|
| 122 |
],
|
| 123 |
"logging_steps": 5,
|
| 124 |
+
"max_steps": 200,
|
| 125 |
"num_input_tokens_seen": 0,
|
| 126 |
"num_train_epochs": 9223372036854775807,
|
| 127 |
+
"save_steps": 50,
|
| 128 |
"stateful_callbacks": {
|
| 129 |
"TrainerControl": {
|
| 130 |
"args": {
|
|
|
|
| 137 |
"attributes": {}
|
| 138 |
}
|
| 139 |
},
|
| 140 |
+
"total_flos": 1.9622204484354048e+17,
|
| 141 |
+
"train_batch_size": 5,
|
| 142 |
"trial_name": null,
|
| 143 |
"trial_params": null
|
| 144 |
}
|
last-checkpoint/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5841
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:855e4e426c5eafaf63f7a009322eb06b70910e4a4bee1286781bd91f0ef7fc5c
|
| 3 |
size 5841
|