Training in progress, step 100, checkpoint
Browse files- last-checkpoint/model.safetensors +1 -1
- last-checkpoint/optimizer.pt +2 -2
- last-checkpoint/rng_state_0.pth +2 -2
- last-checkpoint/rng_state_1.pth +2 -2
- 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 +53 -327
- 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 250490408
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a6afd96f0a4efb226214a2f98fc2930b95faa7d2409bdbba1791318c01e36cad
|
| 3 |
size 250490408
|
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 sha256:9766749cabbd0fe5ad2cb84cb5b1e21a853eda9b1ed07a7c96fd6bf1b05d3c04
|
| 3 |
+
size 255265850
|
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
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0676c143653a967526628bc2f1d4644cea97dd18a780321d518070502832502d
|
| 3 |
+
size 15024
|
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
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:465d2d2aca677e6044b1b9bb8917a886a23650c3ce9b3ee9246d24ecb5324a05
|
| 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:c747745535681b443a3cae9777675e8f1d7f8e4fdcc2e923572fbc2e7ee62ede
|
| 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:d9410529b5a855657bd3a08b9e2887f922f2b19dd1ea9123054c798d54f882e1
|
| 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 sha256:3a60c7d771c1fd156acee762fba03c724cb41829a3f71df370ecd1d20b134982
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,371 +1,97 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 5 |
-
"eval_steps":
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
-
"epoch": 0.
|
| 13 |
-
"eval_loss": 3.
|
| 14 |
-
"eval_runtime":
|
| 15 |
-
"eval_samples_per_second":
|
| 16 |
-
"eval_steps_per_second": 2.
|
| 17 |
"step": 1
|
| 18 |
},
|
| 19 |
-
{
|
| 20 |
-
"epoch": 0.8333333333333334,
|
| 21 |
-
"grad_norm": 8.0625,
|
| 22 |
-
"learning_rate": 6.666666666666667e-05,
|
| 23 |
-
"loss": 6.5691,
|
| 24 |
-
"step": 10
|
| 25 |
-
},
|
| 26 |
{
|
| 27 |
"epoch": 1.6666666666666665,
|
| 28 |
-
"grad_norm": 3.
|
| 29 |
-
"learning_rate": 0.
|
| 30 |
-
"loss":
|
| 31 |
-
"step":
|
| 32 |
-
},
|
| 33 |
-
{
|
| 34 |
-
"epoch": 2.5,
|
| 35 |
-
"grad_norm": 4.375,
|
| 36 |
-
"learning_rate": 0.0002,
|
| 37 |
-
"loss": 5.5103,
|
| 38 |
-
"step": 30
|
| 39 |
},
|
| 40 |
{
|
| 41 |
"epoch": 3.3333333333333335,
|
| 42 |
-
"grad_norm":
|
| 43 |
-
"learning_rate": 0.
|
| 44 |
-
"loss": 5.
|
| 45 |
-
"step":
|
| 46 |
-
},
|
| 47 |
-
{
|
| 48 |
-
"epoch": 4.166666666666667,
|
| 49 |
-
"grad_norm": 4.1875,
|
| 50 |
-
"learning_rate": 0.00019939306773179497,
|
| 51 |
-
"loss": 5.0693,
|
| 52 |
-
"step": 50
|
| 53 |
-
},
|
| 54 |
-
{
|
| 55 |
-
"epoch": 4.166666666666667,
|
| 56 |
-
"eval_loss": 3.1816465854644775,
|
| 57 |
-
"eval_runtime": 10.8479,
|
| 58 |
-
"eval_samples_per_second": 138.368,
|
| 59 |
-
"eval_steps_per_second": 2.212,
|
| 60 |
-
"step": 50
|
| 61 |
},
|
| 62 |
{
|
| 63 |
"epoch": 5.0,
|
| 64 |
-
"grad_norm":
|
| 65 |
-
"learning_rate": 0.
|
| 66 |
-
"loss":
|
| 67 |
-
"step":
|
| 68 |
-
},
|
| 69 |
-
{
|
| 70 |
-
"epoch": 5.833333333333333,
|
| 71 |
-
"grad_norm": 4.53125,
|
| 72 |
-
"learning_rate": 0.00019757963826274357,
|
| 73 |
-
"loss": 4.671,
|
| 74 |
-
"step": 70
|
| 75 |
},
|
| 76 |
{
|
| 77 |
"epoch": 6.666666666666667,
|
| 78 |
-
"grad_norm":
|
| 79 |
-
"learning_rate": 0.
|
| 80 |
-
"loss":
|
| 81 |
-
"step":
|
| 82 |
-
},
|
| 83 |
-
{
|
| 84 |
-
"epoch": 7.5,
|
| 85 |
-
"grad_norm": 3.796875,
|
| 86 |
-
"learning_rate": 0.00019458172417006347,
|
| 87 |
-
"loss": 4.3646,
|
| 88 |
-
"step": 90
|
| 89 |
-
},
|
| 90 |
-
{
|
| 91 |
-
"epoch": 8.333333333333334,
|
| 92 |
-
"grad_norm": 3.875,
|
| 93 |
-
"learning_rate": 0.00019264940672148018,
|
| 94 |
-
"loss": 4.2165,
|
| 95 |
-
"step": 100
|
| 96 |
},
|
| 97 |
{
|
| 98 |
"epoch": 8.333333333333334,
|
| 99 |
-
"
|
| 100 |
-
"
|
| 101 |
-
"
|
| 102 |
-
"
|
| 103 |
-
"step": 100
|
| 104 |
-
},
|
| 105 |
-
{
|
| 106 |
-
"epoch": 9.166666666666666,
|
| 107 |
-
"grad_norm": 5.0625,
|
| 108 |
-
"learning_rate": 0.00019043571606975777,
|
| 109 |
-
"loss": 4.1085,
|
| 110 |
-
"step": 110
|
| 111 |
},
|
| 112 |
{
|
| 113 |
"epoch": 10.0,
|
| 114 |
-
"grad_norm":
|
| 115 |
-
"learning_rate":
|
| 116 |
-
"loss": 4.
|
| 117 |
-
"step":
|
| 118 |
-
},
|
| 119 |
-
{
|
| 120 |
-
"epoch": 10.833333333333334,
|
| 121 |
-
"grad_norm": 4.875,
|
| 122 |
-
"learning_rate": 0.00018519194088383273,
|
| 123 |
-
"loss": 3.8989,
|
| 124 |
-
"step": 130
|
| 125 |
},
|
| 126 |
{
|
| 127 |
"epoch": 11.666666666666666,
|
| 128 |
-
"grad_norm":
|
| 129 |
-
"learning_rate":
|
| 130 |
-
"loss":
|
| 131 |
-
"step":
|
| 132 |
-
},
|
| 133 |
-
{
|
| 134 |
-
"epoch": 12.5,
|
| 135 |
-
"grad_norm": 3.9375,
|
| 136 |
-
"learning_rate": 0.00017891405093963938,
|
| 137 |
-
"loss": 3.7077,
|
| 138 |
-
"step": 150
|
| 139 |
-
},
|
| 140 |
-
{
|
| 141 |
-
"epoch": 12.5,
|
| 142 |
-
"eval_loss": 3.263496160507202,
|
| 143 |
-
"eval_runtime": 10.1832,
|
| 144 |
-
"eval_samples_per_second": 147.399,
|
| 145 |
-
"eval_steps_per_second": 2.357,
|
| 146 |
-
"step": 150
|
| 147 |
},
|
| 148 |
{
|
| 149 |
"epoch": 13.333333333333334,
|
| 150 |
-
"grad_norm":
|
| 151 |
-
"learning_rate":
|
| 152 |
-
"loss":
|
| 153 |
-
"step":
|
| 154 |
-
},
|
| 155 |
-
{
|
| 156 |
-
"epoch": 14.166666666666666,
|
| 157 |
-
"grad_norm": 4.21875,
|
| 158 |
-
"learning_rate": 0.00017167825131684513,
|
| 159 |
-
"loss": 3.533,
|
| 160 |
-
"step": 170
|
| 161 |
},
|
| 162 |
{
|
| 163 |
"epoch": 15.0,
|
| 164 |
-
"grad_norm": 4.59375,
|
| 165 |
-
"learning_rate": 0.00016772815716257412,
|
| 166 |
-
"loss": 3.4567,
|
| 167 |
-
"step": 180
|
| 168 |
-
},
|
| 169 |
-
{
|
| 170 |
-
"epoch": 15.833333333333334,
|
| 171 |
-
"grad_norm": 5.125,
|
| 172 |
-
"learning_rate": 0.00016357237482099684,
|
| 173 |
-
"loss": 3.3726,
|
| 174 |
-
"step": 190
|
| 175 |
-
},
|
| 176 |
-
{
|
| 177 |
-
"epoch": 16.666666666666668,
|
| 178 |
-
"grad_norm": 4.03125,
|
| 179 |
-
"learning_rate": 0.00015922352526649803,
|
| 180 |
-
"loss": 3.3007,
|
| 181 |
-
"step": 200
|
| 182 |
-
},
|
| 183 |
-
{
|
| 184 |
-
"epoch": 16.666666666666668,
|
| 185 |
-
"eval_loss": 3.2971582412719727,
|
| 186 |
-
"eval_runtime": 10.605,
|
| 187 |
-
"eval_samples_per_second": 141.537,
|
| 188 |
-
"eval_steps_per_second": 2.263,
|
| 189 |
-
"step": 200
|
| 190 |
-
},
|
| 191 |
-
{
|
| 192 |
-
"epoch": 17.5,
|
| 193 |
-
"grad_norm": 3.984375,
|
| 194 |
-
"learning_rate": 0.00015469481581224272,
|
| 195 |
-
"loss": 3.2145,
|
| 196 |
-
"step": 210
|
| 197 |
-
},
|
| 198 |
-
{
|
| 199 |
-
"epoch": 18.333333333333332,
|
| 200 |
-
"grad_norm": 4.0,
|
| 201 |
-
"learning_rate": 0.00015000000000000001,
|
| 202 |
-
"loss": 3.1833,
|
| 203 |
-
"step": 220
|
| 204 |
-
},
|
| 205 |
-
{
|
| 206 |
-
"epoch": 19.166666666666668,
|
| 207 |
-
"grad_norm": 4.28125,
|
| 208 |
-
"learning_rate": 0.00014515333583108896,
|
| 209 |
-
"loss": 3.1072,
|
| 210 |
-
"step": 230
|
| 211 |
-
},
|
| 212 |
-
{
|
| 213 |
-
"epoch": 20.0,
|
| 214 |
-
"grad_norm": 3.328125,
|
| 215 |
-
"learning_rate": 0.00014016954246529696,
|
| 216 |
-
"loss": 3.0609,
|
| 217 |
-
"step": 240
|
| 218 |
-
},
|
| 219 |
-
{
|
| 220 |
-
"epoch": 20.833333333333332,
|
| 221 |
-
"grad_norm": 4.0,
|
| 222 |
-
"learning_rate": 0.00013506375551927547,
|
| 223 |
-
"loss": 3.0201,
|
| 224 |
-
"step": 250
|
| 225 |
-
},
|
| 226 |
-
{
|
| 227 |
-
"epoch": 20.833333333333332,
|
| 228 |
-
"eval_loss": 3.0752980709075928,
|
| 229 |
-
"eval_runtime": 10.4283,
|
| 230 |
-
"eval_samples_per_second": 143.936,
|
| 231 |
-
"eval_steps_per_second": 2.301,
|
| 232 |
-
"step": 250
|
| 233 |
-
},
|
| 234 |
-
{
|
| 235 |
-
"epoch": 21.666666666666668,
|
| 236 |
-
"grad_norm": 4.03125,
|
| 237 |
-
"learning_rate": 0.00012985148110016947,
|
| 238 |
-
"loss": 2.9827,
|
| 239 |
-
"step": 260
|
| 240 |
-
},
|
| 241 |
-
{
|
| 242 |
-
"epoch": 22.5,
|
| 243 |
-
"grad_norm": 3.953125,
|
| 244 |
-
"learning_rate": 0.00012454854871407994,
|
| 245 |
-
"loss": 2.9238,
|
| 246 |
-
"step": 270
|
| 247 |
-
},
|
| 248 |
-
{
|
| 249 |
-
"epoch": 23.333333333333332,
|
| 250 |
-
"grad_norm": 4.25,
|
| 251 |
-
"learning_rate": 0.00011917106319237386,
|
| 252 |
-
"loss": 2.8875,
|
| 253 |
-
"step": 280
|
| 254 |
-
},
|
| 255 |
-
{
|
| 256 |
-
"epoch": 24.166666666666668,
|
| 257 |
-
"grad_norm": 3.90625,
|
| 258 |
-
"learning_rate": 0.00011373535578184082,
|
| 259 |
-
"loss": 2.836,
|
| 260 |
-
"step": 290
|
| 261 |
-
},
|
| 262 |
-
{
|
| 263 |
-
"epoch": 25.0,
|
| 264 |
-
"grad_norm": 3.703125,
|
| 265 |
-
"learning_rate": 0.00010825793454723325,
|
| 266 |
-
"loss": 2.8044,
|
| 267 |
-
"step": 300
|
| 268 |
-
},
|
| 269 |
-
{
|
| 270 |
-
"epoch": 25.0,
|
| 271 |
-
"eval_loss": 3.1132636070251465,
|
| 272 |
-
"eval_runtime": 10.3535,
|
| 273 |
-
"eval_samples_per_second": 144.976,
|
| 274 |
-
"eval_steps_per_second": 2.318,
|
| 275 |
-
"step": 300
|
| 276 |
-
},
|
| 277 |
-
{
|
| 278 |
-
"epoch": 25.833333333333332,
|
| 279 |
-
"grad_norm": 3.84375,
|
| 280 |
-
"learning_rate": 0.00010275543423681621,
|
| 281 |
-
"loss": 2.7693,
|
| 282 |
-
"step": 310
|
| 283 |
-
},
|
| 284 |
-
{
|
| 285 |
-
"epoch": 26.666666666666668,
|
| 286 |
-
"grad_norm": 4.25,
|
| 287 |
-
"learning_rate": 9.724456576318381e-05,
|
| 288 |
-
"loss": 2.7404,
|
| 289 |
-
"step": 320
|
| 290 |
-
},
|
| 291 |
-
{
|
| 292 |
-
"epoch": 27.5,
|
| 293 |
"grad_norm": 3.28125,
|
| 294 |
-
"learning_rate":
|
| 295 |
-
"loss":
|
| 296 |
-
"step":
|
| 297 |
-
},
|
| 298 |
-
{
|
| 299 |
-
"epoch": 28.333333333333332,
|
| 300 |
-
"grad_norm": 3.734375,
|
| 301 |
-
"learning_rate": 8.626464421815919e-05,
|
| 302 |
-
"loss": 2.6912,
|
| 303 |
-
"step": 340
|
| 304 |
-
},
|
| 305 |
-
{
|
| 306 |
-
"epoch": 29.166666666666668,
|
| 307 |
-
"grad_norm": 3.546875,
|
| 308 |
-
"learning_rate": 8.082893680762619e-05,
|
| 309 |
-
"loss": 2.6459,
|
| 310 |
-
"step": 350
|
| 311 |
-
},
|
| 312 |
-
{
|
| 313 |
-
"epoch": 29.166666666666668,
|
| 314 |
-
"eval_loss": 3.04976749420166,
|
| 315 |
-
"eval_runtime": 10.3469,
|
| 316 |
-
"eval_samples_per_second": 145.068,
|
| 317 |
-
"eval_steps_per_second": 2.32,
|
| 318 |
-
"step": 350
|
| 319 |
-
},
|
| 320 |
-
{
|
| 321 |
-
"epoch": 30.0,
|
| 322 |
-
"grad_norm": 3.6875,
|
| 323 |
-
"learning_rate": 7.54514512859201e-05,
|
| 324 |
-
"loss": 2.6366,
|
| 325 |
-
"step": 360
|
| 326 |
-
},
|
| 327 |
-
{
|
| 328 |
-
"epoch": 30.833333333333332,
|
| 329 |
-
"grad_norm": 2.890625,
|
| 330 |
-
"learning_rate": 7.014851889983057e-05,
|
| 331 |
-
"loss": 2.6056,
|
| 332 |
-
"step": 370
|
| 333 |
-
},
|
| 334 |
-
{
|
| 335 |
-
"epoch": 31.666666666666668,
|
| 336 |
-
"grad_norm": 4.03125,
|
| 337 |
-
"learning_rate": 6.493624448072457e-05,
|
| 338 |
-
"loss": 2.5957,
|
| 339 |
-
"step": 380
|
| 340 |
-
},
|
| 341 |
-
{
|
| 342 |
-
"epoch": 32.5,
|
| 343 |
-
"grad_norm": 2.9375,
|
| 344 |
-
"learning_rate": 5.983045753470308e-05,
|
| 345 |
-
"loss": 2.5768,
|
| 346 |
-
"step": 390
|
| 347 |
-
},
|
| 348 |
-
{
|
| 349 |
-
"epoch": 33.333333333333336,
|
| 350 |
-
"grad_norm": 2.75,
|
| 351 |
-
"learning_rate": 5.484666416891109e-05,
|
| 352 |
-
"loss": 2.5792,
|
| 353 |
-
"step": 400
|
| 354 |
},
|
| 355 |
{
|
| 356 |
-
"epoch":
|
| 357 |
-
"
|
| 358 |
-
"
|
| 359 |
-
"
|
| 360 |
-
"
|
| 361 |
-
"step": 400
|
| 362 |
}
|
| 363 |
],
|
| 364 |
"logging_steps": 10,
|
| 365 |
-
"max_steps":
|
| 366 |
"num_input_tokens_seen": 0,
|
| 367 |
-
"num_train_epochs":
|
| 368 |
-
"save_steps":
|
| 369 |
"stateful_callbacks": {
|
| 370 |
"TrainerControl": {
|
| 371 |
"args": {
|
|
@@ -373,12 +99,12 @@
|
|
| 373 |
"should_evaluate": false,
|
| 374 |
"should_log": false,
|
| 375 |
"should_save": true,
|
| 376 |
-
"should_training_stop":
|
| 377 |
},
|
| 378 |
"attributes": {}
|
| 379 |
}
|
| 380 |
},
|
| 381 |
-
"total_flos":
|
| 382 |
"train_batch_size": 32,
|
| 383 |
"trial_name": null,
|
| 384 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 16.666666666666668,
|
| 5 |
+
"eval_steps": 200,
|
| 6 |
+
"global_step": 100,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
+
"epoch": 0.16666666666666666,
|
| 13 |
+
"eval_loss": 3.2664246559143066,
|
| 14 |
+
"eval_runtime": 5.1158,
|
| 15 |
+
"eval_samples_per_second": 293.406,
|
| 16 |
+
"eval_steps_per_second": 2.346,
|
| 17 |
"step": 1
|
| 18 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 19 |
{
|
| 20 |
"epoch": 1.6666666666666665,
|
| 21 |
+
"grad_norm": 3.84375,
|
| 22 |
+
"learning_rate": 0.00019863613034027224,
|
| 23 |
+
"loss": 6.2672,
|
| 24 |
+
"step": 10
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 25 |
},
|
| 26 |
{
|
| 27 |
"epoch": 3.3333333333333335,
|
| 28 |
+
"grad_norm": 3.5,
|
| 29 |
+
"learning_rate": 0.0001879473751206489,
|
| 30 |
+
"loss": 5.5486,
|
| 31 |
+
"step": 20
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 32 |
},
|
| 33 |
{
|
| 34 |
"epoch": 5.0,
|
| 35 |
+
"grad_norm": 2.71875,
|
| 36 |
+
"learning_rate": 0.00016772815716257412,
|
| 37 |
+
"loss": 5.2045,
|
| 38 |
+
"step": 30
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 39 |
},
|
| 40 |
{
|
| 41 |
"epoch": 6.666666666666667,
|
| 42 |
+
"grad_norm": 3.03125,
|
| 43 |
+
"learning_rate": 0.00014016954246529696,
|
| 44 |
+
"loss": 5.0295,
|
| 45 |
+
"step": 40
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 46 |
},
|
| 47 |
{
|
| 48 |
"epoch": 8.333333333333334,
|
| 49 |
+
"grad_norm": 4.25,
|
| 50 |
+
"learning_rate": 0.00010825793454723325,
|
| 51 |
+
"loss": 4.8139,
|
| 52 |
+
"step": 50
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 53 |
},
|
| 54 |
{
|
| 55 |
"epoch": 10.0,
|
| 56 |
+
"grad_norm": 2.921875,
|
| 57 |
+
"learning_rate": 7.54514512859201e-05,
|
| 58 |
+
"loss": 4.6461,
|
| 59 |
+
"step": 60
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 60 |
},
|
| 61 |
{
|
| 62 |
"epoch": 11.666666666666666,
|
| 63 |
+
"grad_norm": 2.34375,
|
| 64 |
+
"learning_rate": 4.530518418775733e-05,
|
| 65 |
+
"loss": 4.5564,
|
| 66 |
+
"step": 70
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 67 |
},
|
| 68 |
{
|
| 69 |
"epoch": 13.333333333333334,
|
| 70 |
+
"grad_norm": 2.265625,
|
| 71 |
+
"learning_rate": 2.1085949060360654e-05,
|
| 72 |
+
"loss": 4.4932,
|
| 73 |
+
"step": 80
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 74 |
},
|
| 75 |
{
|
| 76 |
"epoch": 15.0,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 77 |
"grad_norm": 3.28125,
|
| 78 |
+
"learning_rate": 5.418275829936537e-06,
|
| 79 |
+
"loss": 4.4706,
|
| 80 |
+
"step": 90
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 81 |
},
|
| 82 |
{
|
| 83 |
+
"epoch": 16.666666666666668,
|
| 84 |
+
"grad_norm": 1.953125,
|
| 85 |
+
"learning_rate": 0.0,
|
| 86 |
+
"loss": 4.4708,
|
| 87 |
+
"step": 100
|
|
|
|
| 88 |
}
|
| 89 |
],
|
| 90 |
"logging_steps": 10,
|
| 91 |
+
"max_steps": 100,
|
| 92 |
"num_input_tokens_seen": 0,
|
| 93 |
+
"num_train_epochs": 17,
|
| 94 |
+
"save_steps": 200,
|
| 95 |
"stateful_callbacks": {
|
| 96 |
"TrainerControl": {
|
| 97 |
"args": {
|
|
|
|
| 99 |
"should_evaluate": false,
|
| 100 |
"should_log": false,
|
| 101 |
"should_save": true,
|
| 102 |
+
"should_training_stop": true
|
| 103 |
},
|
| 104 |
"attributes": {}
|
| 105 |
}
|
| 106 |
},
|
| 107 |
+
"total_flos": 1.2971582112661504e+16,
|
| 108 |
"train_batch_size": 32,
|
| 109 |
"trial_name": null,
|
| 110 |
"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 sha256:91e32bef4fa18f7434f34b3ab9a59a991d12d4e7c7fd850b74f33c05529273df
|
| 3 |
size 6840
|