End of training
Browse files- README.md +16 -2
- all_results.json +9 -9
- eval_results.json +5 -5
- log_history.json +574 -574
- train_results.json +4 -4
- trainer_state.json +575 -575
README.md
CHANGED
|
@@ -1,6 +1,7 @@
|
|
| 1 |
---
|
| 2 |
library_name: transformers
|
| 3 |
tags:
|
|
|
|
| 4 |
- generated_from_trainer
|
| 5 |
datasets:
|
| 6 |
- voxceleb
|
|
@@ -8,7 +9,20 @@ metrics:
|
|
| 8 |
- accuracy
|
| 9 |
model-index:
|
| 10 |
- name: xvector-voxceleb1
|
| 11 |
-
results:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12 |
---
|
| 13 |
|
| 14 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -16,7 +30,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 16 |
|
| 17 |
# xvector-voxceleb1
|
| 18 |
|
| 19 |
-
This model is a fine-tuned version of [](https://huggingface.co/) on the voxceleb dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
- Loss: 0.2981
|
| 22 |
- Accuracy: 0.9405
|
|
|
|
| 1 |
---
|
| 2 |
library_name: transformers
|
| 3 |
tags:
|
| 4 |
+
- audio-classification
|
| 5 |
- generated_from_trainer
|
| 6 |
datasets:
|
| 7 |
- voxceleb
|
|
|
|
| 9 |
- accuracy
|
| 10 |
model-index:
|
| 11 |
- name: xvector-voxceleb1
|
| 12 |
+
results:
|
| 13 |
+
- task:
|
| 14 |
+
name: Audio Classification
|
| 15 |
+
type: audio-classification
|
| 16 |
+
dataset:
|
| 17 |
+
name: confit/voxceleb
|
| 18 |
+
type: voxceleb
|
| 19 |
+
config: verification
|
| 20 |
+
split: train
|
| 21 |
+
args: verification
|
| 22 |
+
metrics:
|
| 23 |
+
- name: Accuracy
|
| 24 |
+
type: accuracy
|
| 25 |
+
value: 0.9405314497140935
|
| 26 |
---
|
| 27 |
|
| 28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 30 |
|
| 31 |
# xvector-voxceleb1
|
| 32 |
|
| 33 |
+
This model is a fine-tuned version of [](https://huggingface.co/) on the confit/voxceleb dataset.
|
| 34 |
It achieves the following results on the evaluation set:
|
| 35 |
- Loss: 0.2981
|
| 36 |
- Accuracy: 0.9405
|
all_results.json
CHANGED
|
@@ -1,13 +1,13 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 10.0,
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss": 0.
|
| 5 |
-
"eval_runtime":
|
| 6 |
-
"eval_samples_per_second":
|
| 7 |
-
"eval_steps_per_second":
|
| 8 |
"total_flos": 1.96318398191328e+18,
|
| 9 |
-
"train_loss": 2.
|
| 10 |
-
"train_runtime":
|
| 11 |
-
"train_samples_per_second":
|
| 12 |
-
"train_steps_per_second": 0.
|
| 13 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 10.0,
|
| 3 |
+
"eval_accuracy": 0.9405314497140935,
|
| 4 |
+
"eval_loss": 0.29811325669288635,
|
| 5 |
+
"eval_runtime": 45.8572,
|
| 6 |
+
"eval_samples_per_second": 324.159,
|
| 7 |
+
"eval_steps_per_second": 324.159,
|
| 8 |
"total_flos": 1.96318398191328e+18,
|
| 9 |
+
"train_loss": 2.122584131525306,
|
| 10 |
+
"train_runtime": 50832.5393,
|
| 11 |
+
"train_samples_per_second": 26.317,
|
| 12 |
+
"train_steps_per_second": 0.103
|
| 13 |
}
|
eval_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 10.0,
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss": 0.
|
| 5 |
-
"eval_runtime":
|
| 6 |
-
"eval_samples_per_second":
|
| 7 |
-
"eval_steps_per_second":
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 10.0,
|
| 3 |
+
"eval_accuracy": 0.9405314497140935,
|
| 4 |
+
"eval_loss": 0.29811325669288635,
|
| 5 |
+
"eval_runtime": 45.8572,
|
| 6 |
+
"eval_samples_per_second": 324.159,
|
| 7 |
+
"eval_steps_per_second": 324.159
|
| 8 |
}
|
log_history.json
CHANGED
|
@@ -1,1927 +1,1927 @@
|
|
| 1 |
[
|
| 2 |
{
|
| 3 |
-
"loss": 7.
|
| 4 |
-
"grad_norm": 4.
|
| 5 |
"learning_rate": 3.824091778202677e-05,
|
| 6 |
"epoch": 0.03824091778202677,
|
| 7 |
"step": 20
|
| 8 |
},
|
| 9 |
{
|
| 10 |
-
"loss": 7.
|
| 11 |
-
"grad_norm": 4.
|
| 12 |
"learning_rate": 7.648183556405354e-05,
|
| 13 |
"epoch": 0.07648183556405354,
|
| 14 |
"step": 40
|
| 15 |
},
|
| 16 |
{
|
| 17 |
-
"loss": 7.
|
| 18 |
-
"grad_norm": 3.
|
| 19 |
"learning_rate": 0.0001147227533460803,
|
| 20 |
"epoch": 0.1147227533460803,
|
| 21 |
"step": 60
|
| 22 |
},
|
| 23 |
{
|
| 24 |
-
"loss": 6.
|
| 25 |
-
"grad_norm": 3.
|
| 26 |
"learning_rate": 0.00015296367112810707,
|
| 27 |
"epoch": 0.15296367112810708,
|
| 28 |
"step": 80
|
| 29 |
},
|
| 30 |
{
|
| 31 |
-
"loss": 6.
|
| 32 |
-
"grad_norm": 2.
|
| 33 |
"learning_rate": 0.00019120458891013384,
|
| 34 |
"epoch": 0.19120458891013384,
|
| 35 |
"step": 100
|
| 36 |
},
|
| 37 |
{
|
| 38 |
-
"loss": 6.
|
| 39 |
-
"grad_norm": 2.
|
| 40 |
"learning_rate": 0.0002294455066921606,
|
| 41 |
"epoch": 0.2294455066921606,
|
| 42 |
"step": 120
|
| 43 |
},
|
| 44 |
{
|
| 45 |
-
"loss": 6.
|
| 46 |
-
"grad_norm":
|
| 47 |
"learning_rate": 0.0002676864244741874,
|
| 48 |
"epoch": 0.2676864244741874,
|
| 49 |
"step": 140
|
| 50 |
},
|
| 51 |
{
|
| 52 |
-
"loss": 6.
|
| 53 |
-
"grad_norm": 1.
|
| 54 |
"learning_rate": 0.00030592734225621415,
|
| 55 |
"epoch": 0.30592734225621415,
|
| 56 |
"step": 160
|
| 57 |
},
|
| 58 |
{
|
| 59 |
-
"loss": 6.
|
| 60 |
-
"grad_norm": 1.
|
| 61 |
"learning_rate": 0.00034416826003824094,
|
| 62 |
"epoch": 0.3441682600382409,
|
| 63 |
"step": 180
|
| 64 |
},
|
| 65 |
{
|
| 66 |
-
"loss": 6.
|
| 67 |
-
"grad_norm": 1.
|
| 68 |
"learning_rate": 0.0003824091778202677,
|
| 69 |
"epoch": 0.3824091778202677,
|
| 70 |
"step": 200
|
| 71 |
},
|
| 72 |
{
|
| 73 |
-
"loss": 5.
|
| 74 |
-
"grad_norm": 1.
|
| 75 |
"learning_rate": 0.0004206500956022944,
|
| 76 |
"epoch": 0.42065009560229444,
|
| 77 |
"step": 220
|
| 78 |
},
|
| 79 |
{
|
| 80 |
-
"loss": 5.
|
| 81 |
-
"grad_norm": 1.
|
| 82 |
"learning_rate": 0.0004588910133843212,
|
| 83 |
"epoch": 0.4588910133843212,
|
| 84 |
"step": 240
|
| 85 |
},
|
| 86 |
{
|
| 87 |
-
"loss": 5.
|
| 88 |
-
"grad_norm": 1.
|
| 89 |
"learning_rate": 0.0004971319311663481,
|
| 90 |
"epoch": 0.497131931166348,
|
| 91 |
"step": 260
|
| 92 |
},
|
| 93 |
{
|
| 94 |
-
"loss": 5.
|
| 95 |
-
"grad_norm": 1.
|
| 96 |
"learning_rate": 0.0005353728489483748,
|
| 97 |
"epoch": 0.5353728489483748,
|
| 98 |
"step": 280
|
| 99 |
},
|
| 100 |
{
|
| 101 |
-
"loss": 5.
|
| 102 |
-
"grad_norm": 1.
|
| 103 |
"learning_rate": 0.0005736137667304016,
|
| 104 |
"epoch": 0.5736137667304015,
|
| 105 |
"step": 300
|
| 106 |
},
|
| 107 |
{
|
| 108 |
-
"loss": 5.
|
| 109 |
-
"grad_norm": 1.
|
| 110 |
"learning_rate": 0.0006118546845124283,
|
| 111 |
"epoch": 0.6118546845124283,
|
| 112 |
"step": 320
|
| 113 |
},
|
| 114 |
{
|
| 115 |
-
"loss": 5.
|
| 116 |
-
"grad_norm": 1.
|
| 117 |
"learning_rate": 0.000650095602294455,
|
| 118 |
"epoch": 0.6500956022944551,
|
| 119 |
"step": 340
|
| 120 |
},
|
| 121 |
{
|
| 122 |
-
"loss": 5.
|
| 123 |
-
"grad_norm": 1.
|
| 124 |
"learning_rate": 0.0006883365200764819,
|
| 125 |
"epoch": 0.6883365200764818,
|
| 126 |
"step": 360
|
| 127 |
},
|
| 128 |
{
|
| 129 |
-
"loss": 5.
|
| 130 |
-
"grad_norm": 1.
|
| 131 |
"learning_rate": 0.0007265774378585086,
|
| 132 |
"epoch": 0.7265774378585086,
|
| 133 |
"step": 380
|
| 134 |
},
|
| 135 |
{
|
| 136 |
-
"loss": 5.
|
| 137 |
-
"grad_norm": 1.
|
| 138 |
"learning_rate": 0.0007648183556405354,
|
| 139 |
"epoch": 0.7648183556405354,
|
| 140 |
"step": 400
|
| 141 |
},
|
| 142 |
{
|
| 143 |
-
"loss": 5.
|
| 144 |
-
"grad_norm": 1.
|
| 145 |
"learning_rate": 0.0008030592734225621,
|
| 146 |
"epoch": 0.8030592734225621,
|
| 147 |
"step": 420
|
| 148 |
},
|
| 149 |
{
|
| 150 |
-
"loss": 4.
|
| 151 |
-
"grad_norm": 1.
|
| 152 |
"learning_rate": 0.0008413001912045888,
|
| 153 |
"epoch": 0.8413001912045889,
|
| 154 |
"step": 440
|
| 155 |
},
|
| 156 |
{
|
| 157 |
-
"loss": 4.
|
| 158 |
-
"grad_norm": 1.
|
| 159 |
"learning_rate": 0.0008795411089866157,
|
| 160 |
"epoch": 0.8795411089866156,
|
| 161 |
"step": 460
|
| 162 |
},
|
| 163 |
{
|
| 164 |
-
"loss": 4.
|
| 165 |
-
"grad_norm": 1.
|
| 166 |
"learning_rate": 0.0009177820267686424,
|
| 167 |
"epoch": 0.9177820267686424,
|
| 168 |
"step": 480
|
| 169 |
},
|
| 170 |
{
|
| 171 |
-
"loss": 4.
|
| 172 |
-
"grad_norm": 1.
|
| 173 |
"learning_rate": 0.0009560229445506692,
|
| 174 |
"epoch": 0.9560229445506692,
|
| 175 |
"step": 500
|
| 176 |
},
|
| 177 |
{
|
| 178 |
-
"loss": 4.
|
| 179 |
-
"grad_norm": 1.
|
| 180 |
"learning_rate": 0.0009942638623326961,
|
| 181 |
"epoch": 0.994263862332696,
|
| 182 |
"step": 520
|
| 183 |
},
|
| 184 |
{
|
| 185 |
-
"eval_loss": 4.
|
| 186 |
-
"eval_accuracy": 0.
|
| 187 |
-
"eval_runtime":
|
| 188 |
-
"eval_samples_per_second":
|
| 189 |
-
"eval_steps_per_second":
|
| 190 |
"epoch": 1.0,
|
| 191 |
"step": 523
|
| 192 |
},
|
| 193 |
{
|
| 194 |
-
"loss": 4.
|
| 195 |
-
"grad_norm": 1.
|
| 196 |
"learning_rate": 0.0009963883577650309,
|
| 197 |
"epoch": 1.0325047801147227,
|
| 198 |
"step": 540
|
| 199 |
},
|
| 200 |
{
|
| 201 |
-
"loss": 4.
|
| 202 |
-
"grad_norm": 1.
|
| 203 |
"learning_rate": 0.0009921393669003612,
|
| 204 |
"epoch": 1.0707456978967496,
|
| 205 |
"step": 560
|
| 206 |
},
|
| 207 |
{
|
| 208 |
-
"loss": 4.
|
| 209 |
-
"grad_norm": 1.
|
| 210 |
"learning_rate": 0.0009878903760356915,
|
| 211 |
"epoch": 1.1089866156787762,
|
| 212 |
"step": 580
|
| 213 |
},
|
| 214 |
{
|
| 215 |
-
"loss": 4.
|
| 216 |
-
"grad_norm": 1.
|
| 217 |
"learning_rate": 0.0009836413851710218,
|
| 218 |
"epoch": 1.147227533460803,
|
| 219 |
"step": 600
|
| 220 |
},
|
| 221 |
{
|
| 222 |
-
"loss": 4.
|
| 223 |
-
"grad_norm": 1.
|
| 224 |
"learning_rate": 0.0009793923943063523,
|
| 225 |
"epoch": 1.1854684512428297,
|
| 226 |
"step": 620
|
| 227 |
},
|
| 228 |
{
|
| 229 |
-
"loss": 4.
|
| 230 |
-
"grad_norm": 1.
|
| 231 |
"learning_rate": 0.0009751434034416827,
|
| 232 |
"epoch": 1.2237093690248566,
|
| 233 |
"step": 640
|
| 234 |
},
|
| 235 |
{
|
| 236 |
-
"loss": 4.
|
| 237 |
-
"grad_norm": 1.
|
| 238 |
"learning_rate": 0.000970894412577013,
|
| 239 |
"epoch": 1.2619502868068833,
|
| 240 |
"step": 660
|
| 241 |
},
|
| 242 |
{
|
| 243 |
-
"loss": 4.
|
| 244 |
-
"grad_norm": 1.
|
| 245 |
"learning_rate": 0.0009666454217123433,
|
| 246 |
"epoch": 1.3001912045889101,
|
| 247 |
"step": 680
|
| 248 |
},
|
| 249 |
{
|
| 250 |
-
"loss": 4.
|
| 251 |
-
"grad_norm": 1.
|
| 252 |
"learning_rate": 0.0009623964308476737,
|
| 253 |
"epoch": 1.338432122370937,
|
| 254 |
"step": 700
|
| 255 |
},
|
| 256 |
{
|
| 257 |
-
"loss":
|
| 258 |
-
"grad_norm": 1.
|
| 259 |
"learning_rate": 0.000958147439983004,
|
| 260 |
"epoch": 1.3766730401529637,
|
| 261 |
"step": 720
|
| 262 |
},
|
| 263 |
{
|
| 264 |
-
"loss": 3.
|
| 265 |
-
"grad_norm": 1.
|
| 266 |
"learning_rate": 0.0009538984491183344,
|
| 267 |
"epoch": 1.4149139579349903,
|
| 268 |
"step": 740
|
| 269 |
},
|
| 270 |
{
|
| 271 |
-
"loss": 3.
|
| 272 |
-
"grad_norm": 1.
|
| 273 |
"learning_rate": 0.0009496494582536647,
|
| 274 |
"epoch": 1.4531548757170172,
|
| 275 |
"step": 760
|
| 276 |
},
|
| 277 |
{
|
| 278 |
-
"loss": 3.
|
| 279 |
-
"grad_norm": 1.
|
| 280 |
"learning_rate": 0.0009454004673889951,
|
| 281 |
"epoch": 1.491395793499044,
|
| 282 |
"step": 780
|
| 283 |
},
|
| 284 |
{
|
| 285 |
-
"loss": 3.
|
| 286 |
-
"grad_norm": 1.
|
| 287 |
"learning_rate": 0.0009411514765243255,
|
| 288 |
"epoch": 1.5296367112810707,
|
| 289 |
"step": 800
|
| 290 |
},
|
| 291 |
{
|
| 292 |
-
"loss": 3.
|
| 293 |
-
"grad_norm": 1.
|
| 294 |
"learning_rate": 0.0009369024856596558,
|
| 295 |
"epoch": 1.5678776290630974,
|
| 296 |
"step": 820
|
| 297 |
},
|
| 298 |
{
|
| 299 |
-
"loss": 3.
|
| 300 |
-
"grad_norm": 1.
|
| 301 |
"learning_rate": 0.0009326534947949862,
|
| 302 |
"epoch": 1.6061185468451242,
|
| 303 |
"step": 840
|
| 304 |
},
|
| 305 |
{
|
| 306 |
-
"loss": 3.
|
| 307 |
-
"grad_norm": 1.
|
| 308 |
"learning_rate": 0.0009284045039303166,
|
| 309 |
"epoch": 1.644359464627151,
|
| 310 |
"step": 860
|
| 311 |
},
|
| 312 |
{
|
| 313 |
-
"loss": 3.
|
| 314 |
-
"grad_norm": 1.
|
| 315 |
"learning_rate": 0.0009241555130656469,
|
| 316 |
"epoch": 1.682600382409178,
|
| 317 |
"step": 880
|
| 318 |
},
|
| 319 |
{
|
| 320 |
-
"loss": 3.
|
| 321 |
-
"grad_norm": 1.
|
| 322 |
"learning_rate": 0.0009199065222009773,
|
| 323 |
"epoch": 1.7208413001912046,
|
| 324 |
"step": 900
|
| 325 |
},
|
| 326 |
{
|
| 327 |
-
"loss": 3.
|
| 328 |
-
"grad_norm": 1.
|
| 329 |
"learning_rate": 0.0009156575313363077,
|
| 330 |
"epoch": 1.7590822179732313,
|
| 331 |
"step": 920
|
| 332 |
},
|
| 333 |
{
|
| 334 |
-
"loss": 3.
|
| 335 |
-
"grad_norm": 1.
|
| 336 |
"learning_rate": 0.000911408540471638,
|
| 337 |
"epoch": 1.7973231357552581,
|
| 338 |
"step": 940
|
| 339 |
},
|
| 340 |
{
|
| 341 |
-
"loss": 3.
|
| 342 |
-
"grad_norm": 1.
|
| 343 |
"learning_rate": 0.0009071595496069684,
|
| 344 |
"epoch": 1.835564053537285,
|
| 345 |
"step": 960
|
| 346 |
},
|
| 347 |
{
|
| 348 |
-
"loss": 3.
|
| 349 |
-
"grad_norm": 1.
|
| 350 |
"learning_rate": 0.0009029105587422988,
|
| 351 |
"epoch": 1.8738049713193117,
|
| 352 |
"step": 980
|
| 353 |
},
|
| 354 |
{
|
| 355 |
-
"loss": 3.
|
| 356 |
-
"grad_norm": 1.
|
| 357 |
"learning_rate": 0.0008986615678776291,
|
| 358 |
"epoch": 1.9120458891013383,
|
| 359 |
"step": 1000
|
| 360 |
},
|
| 361 |
{
|
| 362 |
-
"loss": 3.
|
| 363 |
-
"grad_norm": 1.
|
| 364 |
"learning_rate": 0.0008944125770129595,
|
| 365 |
"epoch": 1.9502868068833652,
|
| 366 |
"step": 1020
|
| 367 |
},
|
| 368 |
{
|
| 369 |
-
"loss": 3.
|
| 370 |
-
"grad_norm": 1.
|
| 371 |
"learning_rate": 0.0008901635861482899,
|
| 372 |
"epoch": 1.988527724665392,
|
| 373 |
"step": 1040
|
| 374 |
},
|
| 375 |
{
|
| 376 |
-
"eval_loss": 2.
|
| 377 |
-
"eval_accuracy": 0.
|
| 378 |
-
"eval_runtime":
|
| 379 |
-
"eval_samples_per_second":
|
| 380 |
-
"eval_steps_per_second":
|
| 381 |
"epoch": 2.0,
|
| 382 |
"step": 1046
|
| 383 |
},
|
| 384 |
{
|
| 385 |
-
"loss": 3.
|
| 386 |
-
"grad_norm": 1.
|
| 387 |
"learning_rate": 0.0008859145952836202,
|
| 388 |
"epoch": 2.026768642447419,
|
| 389 |
"step": 1060
|
| 390 |
},
|
| 391 |
{
|
| 392 |
-
"loss": 3.
|
| 393 |
-
"grad_norm": 1.
|
| 394 |
"learning_rate": 0.0008816656044189504,
|
| 395 |
"epoch": 2.0650095602294454,
|
| 396 |
"step": 1080
|
| 397 |
},
|
| 398 |
{
|
| 399 |
-
"loss": 3.
|
| 400 |
-
"grad_norm": 1.
|
| 401 |
"learning_rate": 0.000877416613554281,
|
| 402 |
"epoch": 2.1032504780114722,
|
| 403 |
"step": 1100
|
| 404 |
},
|
| 405 |
{
|
| 406 |
-
"loss": 2.
|
| 407 |
-
"grad_norm": 1.
|
| 408 |
"learning_rate": 0.0008731676226896112,
|
| 409 |
"epoch": 2.141491395793499,
|
| 410 |
"step": 1120
|
| 411 |
},
|
| 412 |
{
|
| 413 |
-
"loss": 2.
|
| 414 |
-
"grad_norm": 1.
|
| 415 |
"learning_rate": 0.0008689186318249415,
|
| 416 |
"epoch": 2.179732313575526,
|
| 417 |
"step": 1140
|
| 418 |
},
|
| 419 |
{
|
| 420 |
-
"loss": 2.
|
| 421 |
-
"grad_norm": 1.
|
| 422 |
"learning_rate": 0.000864669640960272,
|
| 423 |
"epoch": 2.2179732313575524,
|
| 424 |
"step": 1160
|
| 425 |
},
|
| 426 |
{
|
| 427 |
-
"loss": 2.
|
| 428 |
-
"grad_norm": 1.
|
| 429 |
"learning_rate": 0.0008604206500956023,
|
| 430 |
"epoch": 2.2562141491395793,
|
| 431 |
"step": 1180
|
| 432 |
},
|
| 433 |
{
|
| 434 |
-
"loss": 2.
|
| 435 |
-
"grad_norm": 1.
|
| 436 |
"learning_rate": 0.0008561716592309326,
|
| 437 |
"epoch": 2.294455066921606,
|
| 438 |
"step": 1200
|
| 439 |
},
|
| 440 |
{
|
| 441 |
-
"loss": 2.
|
| 442 |
-
"grad_norm": 1.
|
| 443 |
"learning_rate": 0.000851922668366263,
|
| 444 |
"epoch": 2.332695984703633,
|
| 445 |
"step": 1220
|
| 446 |
},
|
| 447 |
{
|
| 448 |
-
"loss": 2.
|
| 449 |
-
"grad_norm": 1.
|
| 450 |
"learning_rate": 0.0008476736775015934,
|
| 451 |
"epoch": 2.3709369024856595,
|
| 452 |
"step": 1240
|
| 453 |
},
|
| 454 |
{
|
| 455 |
-
"loss": 2.
|
| 456 |
-
"grad_norm": 1.
|
| 457 |
"learning_rate": 0.0008434246866369237,
|
| 458 |
"epoch": 2.4091778202676863,
|
| 459 |
"step": 1260
|
| 460 |
},
|
| 461 |
{
|
| 462 |
-
"loss": 2.
|
| 463 |
-
"grad_norm": 1.
|
| 464 |
"learning_rate": 0.0008391756957722541,
|
| 465 |
"epoch": 2.447418738049713,
|
| 466 |
"step": 1280
|
| 467 |
},
|
| 468 |
{
|
| 469 |
-
"loss": 2.
|
| 470 |
-
"grad_norm": 1.
|
| 471 |
"learning_rate": 0.0008349267049075845,
|
| 472 |
"epoch": 2.48565965583174,
|
| 473 |
"step": 1300
|
| 474 |
},
|
| 475 |
{
|
| 476 |
-
"loss": 2.
|
| 477 |
-
"grad_norm": 1.
|
| 478 |
"learning_rate": 0.0008306777140429148,
|
| 479 |
"epoch": 2.5239005736137665,
|
| 480 |
"step": 1320
|
| 481 |
},
|
| 482 |
{
|
| 483 |
-
"loss": 2.
|
| 484 |
-
"grad_norm": 1.
|
| 485 |
"learning_rate": 0.0008264287231782451,
|
| 486 |
"epoch": 2.5621414913957934,
|
| 487 |
"step": 1340
|
| 488 |
},
|
| 489 |
{
|
| 490 |
-
"loss": 2.
|
| 491 |
-
"grad_norm": 1.
|
| 492 |
"learning_rate": 0.0008221797323135756,
|
| 493 |
"epoch": 2.6003824091778203,
|
| 494 |
"step": 1360
|
| 495 |
},
|
| 496 |
{
|
| 497 |
-
"loss": 2.
|
| 498 |
-
"grad_norm": 1.
|
| 499 |
"learning_rate": 0.0008179307414489059,
|
| 500 |
"epoch": 2.638623326959847,
|
| 501 |
"step": 1380
|
| 502 |
},
|
| 503 |
{
|
| 504 |
-
"loss": 2.
|
| 505 |
-
"grad_norm": 1.
|
| 506 |
"learning_rate": 0.0008136817505842362,
|
| 507 |
"epoch": 2.676864244741874,
|
| 508 |
"step": 1400
|
| 509 |
},
|
| 510 |
{
|
| 511 |
-
"loss": 2.
|
| 512 |
-
"grad_norm": 1.
|
| 513 |
"learning_rate": 0.0008094327597195667,
|
| 514 |
"epoch": 2.7151051625239004,
|
| 515 |
"step": 1420
|
| 516 |
},
|
| 517 |
{
|
| 518 |
-
"loss": 2.
|
| 519 |
-
"grad_norm": 1.
|
| 520 |
"learning_rate": 0.000805183768854897,
|
| 521 |
"epoch": 2.7533460803059273,
|
| 522 |
"step": 1440
|
| 523 |
},
|
| 524 |
{
|
| 525 |
-
"loss": 2.
|
| 526 |
-
"grad_norm": 1.
|
| 527 |
"learning_rate": 0.0008009347779902273,
|
| 528 |
"epoch": 2.791586998087954,
|
| 529 |
"step": 1460
|
| 530 |
},
|
| 531 |
{
|
| 532 |
-
"loss": 2.
|
| 533 |
-
"grad_norm": 1.
|
| 534 |
"learning_rate": 0.0007966857871255578,
|
| 535 |
"epoch": 2.8298279158699806,
|
| 536 |
"step": 1480
|
| 537 |
},
|
| 538 |
{
|
| 539 |
-
"loss": 2.
|
| 540 |
-
"grad_norm": 1.
|
| 541 |
"learning_rate": 0.000792436796260888,
|
| 542 |
"epoch": 2.8680688336520075,
|
| 543 |
"step": 1500
|
| 544 |
},
|
| 545 |
{
|
| 546 |
-
"loss": 2.
|
| 547 |
-
"grad_norm": 1.
|
| 548 |
"learning_rate": 0.0007881878053962183,
|
| 549 |
"epoch": 2.9063097514340344,
|
| 550 |
"step": 1520
|
| 551 |
},
|
| 552 |
{
|
| 553 |
-
"loss": 2.
|
| 554 |
-
"grad_norm": 1.
|
| 555 |
"learning_rate": 0.0007839388145315488,
|
| 556 |
"epoch": 2.9445506692160612,
|
| 557 |
"step": 1540
|
| 558 |
},
|
| 559 |
{
|
| 560 |
-
"loss": 2.
|
| 561 |
-
"grad_norm": 1.
|
| 562 |
"learning_rate": 0.0007796898236668791,
|
| 563 |
"epoch": 2.982791586998088,
|
| 564 |
"step": 1560
|
| 565 |
},
|
| 566 |
{
|
| 567 |
-
"eval_loss": 1.
|
| 568 |
-
"eval_accuracy": 0.
|
| 569 |
-
"eval_runtime":
|
| 570 |
-
"eval_samples_per_second":
|
| 571 |
-
"eval_steps_per_second":
|
| 572 |
"epoch": 3.0,
|
| 573 |
"step": 1569
|
| 574 |
},
|
| 575 |
{
|
| 576 |
-
"loss": 2.
|
| 577 |
-
"grad_norm": 1.
|
| 578 |
"learning_rate": 0.0007754408328022094,
|
| 579 |
"epoch": 3.0210325047801145,
|
| 580 |
"step": 1580
|
| 581 |
},
|
| 582 |
{
|
| 583 |
-
"loss": 2.
|
| 584 |
-
"grad_norm": 1.
|
| 585 |
"learning_rate": 0.0007711918419375399,
|
| 586 |
"epoch": 3.0592734225621414,
|
| 587 |
"step": 1600
|
| 588 |
},
|
| 589 |
{
|
| 590 |
-
"loss": 2.
|
| 591 |
-
"grad_norm": 1.
|
| 592 |
"learning_rate": 0.0007669428510728702,
|
| 593 |
"epoch": 3.0975143403441683,
|
| 594 |
"step": 1620
|
| 595 |
},
|
| 596 |
{
|
| 597 |
-
"loss": 2.
|
| 598 |
-
"grad_norm": 1.
|
| 599 |
"learning_rate": 0.0007626938602082005,
|
| 600 |
"epoch": 3.135755258126195,
|
| 601 |
"step": 1640
|
| 602 |
},
|
| 603 |
{
|
| 604 |
-
"loss": 2.
|
| 605 |
-
"grad_norm": 1.
|
| 606 |
"learning_rate": 0.0007584448693435309,
|
| 607 |
"epoch": 3.173996175908222,
|
| 608 |
"step": 1660
|
| 609 |
},
|
| 610 |
{
|
| 611 |
-
"loss": 2.
|
| 612 |
-
"grad_norm": 1.
|
| 613 |
"learning_rate": 0.0007541958784788613,
|
| 614 |
"epoch": 3.2122370936902485,
|
| 615 |
"step": 1680
|
| 616 |
},
|
| 617 |
{
|
| 618 |
-
"loss": 2.
|
| 619 |
-
"grad_norm": 1.
|
| 620 |
"learning_rate": 0.0007499468876141916,
|
| 621 |
"epoch": 3.2504780114722753,
|
| 622 |
"step": 1700
|
| 623 |
},
|
| 624 |
{
|
| 625 |
-
"loss": 2.
|
| 626 |
-
"grad_norm": 1.
|
| 627 |
"learning_rate": 0.000745697896749522,
|
| 628 |
"epoch": 3.288718929254302,
|
| 629 |
"step": 1720
|
| 630 |
},
|
| 631 |
{
|
| 632 |
-
"loss": 2.
|
| 633 |
-
"grad_norm": 1.
|
| 634 |
"learning_rate": 0.0007414489058848524,
|
| 635 |
"epoch": 3.3269598470363286,
|
| 636 |
"step": 1740
|
| 637 |
},
|
| 638 |
{
|
| 639 |
-
"loss": 2.
|
| 640 |
-
"grad_norm": 1.
|
| 641 |
"learning_rate": 0.0007371999150201827,
|
| 642 |
"epoch": 3.3652007648183555,
|
| 643 |
"step": 1760
|
| 644 |
},
|
| 645 |
{
|
| 646 |
-
"loss": 2.
|
| 647 |
-
"grad_norm": 1.
|
| 648 |
"learning_rate": 0.0007329509241555131,
|
| 649 |
"epoch": 3.4034416826003824,
|
| 650 |
"step": 1780
|
| 651 |
},
|
| 652 |
{
|
| 653 |
-
"loss": 2.
|
| 654 |
-
"grad_norm": 1.
|
| 655 |
"learning_rate": 0.0007287019332908435,
|
| 656 |
"epoch": 3.4416826003824093,
|
| 657 |
"step": 1800
|
| 658 |
},
|
| 659 |
{
|
| 660 |
-
"loss": 2.
|
| 661 |
-
"grad_norm": 1.
|
| 662 |
"learning_rate": 0.0007244529424261738,
|
| 663 |
"epoch": 3.479923518164436,
|
| 664 |
"step": 1820
|
| 665 |
},
|
| 666 |
{
|
| 667 |
-
"loss": 2.
|
| 668 |
-
"grad_norm": 1.
|
| 669 |
"learning_rate": 0.0007202039515615042,
|
| 670 |
"epoch": 3.5181644359464626,
|
| 671 |
"step": 1840
|
| 672 |
},
|
| 673 |
{
|
| 674 |
-
"loss": 2.
|
| 675 |
-
"grad_norm": 1.
|
| 676 |
"learning_rate": 0.0007159549606968346,
|
| 677 |
"epoch": 3.5564053537284894,
|
| 678 |
"step": 1860
|
| 679 |
},
|
| 680 |
{
|
| 681 |
-
"loss": 2.
|
| 682 |
-
"grad_norm": 1.
|
| 683 |
"learning_rate": 0.0007117059698321649,
|
| 684 |
"epoch": 3.5946462715105163,
|
| 685 |
"step": 1880
|
| 686 |
},
|
| 687 |
{
|
| 688 |
-
"loss": 2.
|
| 689 |
-
"grad_norm": 1.
|
| 690 |
"learning_rate": 0.0007074569789674953,
|
| 691 |
"epoch": 3.632887189292543,
|
| 692 |
"step": 1900
|
| 693 |
},
|
| 694 |
{
|
| 695 |
-
"loss": 2.
|
| 696 |
-
"grad_norm": 1.
|
| 697 |
"learning_rate": 0.0007032079881028257,
|
| 698 |
"epoch": 3.67112810707457,
|
| 699 |
"step": 1920
|
| 700 |
},
|
| 701 |
{
|
| 702 |
-
"loss":
|
| 703 |
-
"grad_norm": 1.
|
| 704 |
"learning_rate": 0.0006989589972381559,
|
| 705 |
"epoch": 3.7093690248565965,
|
| 706 |
"step": 1940
|
| 707 |
},
|
| 708 |
{
|
| 709 |
-
"loss": 1.
|
| 710 |
-
"grad_norm": 1.
|
| 711 |
"learning_rate": 0.0006947100063734863,
|
| 712 |
"epoch": 3.7476099426386233,
|
| 713 |
"step": 1960
|
| 714 |
},
|
| 715 |
{
|
| 716 |
-
"loss": 2.
|
| 717 |
-
"grad_norm": 1.
|
| 718 |
"learning_rate": 0.0006904610155088166,
|
| 719 |
"epoch": 3.78585086042065,
|
| 720 |
"step": 1980
|
| 721 |
},
|
| 722 |
{
|
| 723 |
-
"loss": 1.
|
| 724 |
-
"grad_norm": 1.
|
| 725 |
"learning_rate": 0.000686212024644147,
|
| 726 |
"epoch": 3.8240917782026767,
|
| 727 |
"step": 2000
|
| 728 |
},
|
| 729 |
{
|
| 730 |
-
"loss": 1.
|
| 731 |
-
"grad_norm": 1.
|
| 732 |
"learning_rate": 0.0006819630337794774,
|
| 733 |
"epoch": 3.8623326959847035,
|
| 734 |
"step": 2020
|
| 735 |
},
|
| 736 |
{
|
| 737 |
-
"loss": 1.
|
| 738 |
-
"grad_norm": 1.
|
| 739 |
"learning_rate": 0.0006777140429148077,
|
| 740 |
"epoch": 3.9005736137667304,
|
| 741 |
"step": 2040
|
| 742 |
},
|
| 743 |
{
|
| 744 |
-
"loss": 1.
|
| 745 |
-
"grad_norm": 1.
|
| 746 |
"learning_rate": 0.0006734650520501381,
|
| 747 |
"epoch": 3.9388145315487573,
|
| 748 |
"step": 2060
|
| 749 |
},
|
| 750 |
{
|
| 751 |
-
"loss": 1.
|
| 752 |
-
"grad_norm": 1.
|
| 753 |
"learning_rate": 0.0006692160611854685,
|
| 754 |
"epoch": 3.977055449330784,
|
| 755 |
"step": 2080
|
| 756 |
},
|
| 757 |
{
|
| 758 |
-
"eval_loss": 0.
|
| 759 |
-
"eval_accuracy": 0.
|
| 760 |
-
"eval_runtime":
|
| 761 |
-
"eval_samples_per_second":
|
| 762 |
-
"eval_steps_per_second":
|
| 763 |
"epoch": 4.0,
|
| 764 |
"step": 2092
|
| 765 |
},
|
| 766 |
{
|
| 767 |
-
"loss": 1.
|
| 768 |
-
"grad_norm": 1.
|
| 769 |
"learning_rate": 0.0006649670703207988,
|
| 770 |
"epoch": 4.015296367112811,
|
| 771 |
"step": 2100
|
| 772 |
},
|
| 773 |
{
|
| 774 |
-
"loss": 1.
|
| 775 |
-
"grad_norm": 1.
|
| 776 |
"learning_rate": 0.0006607180794561292,
|
| 777 |
"epoch": 4.053537284894838,
|
| 778 |
"step": 2120
|
| 779 |
},
|
| 780 |
{
|
| 781 |
-
"loss": 1.
|
| 782 |
-
"grad_norm": 1.
|
| 783 |
"learning_rate": 0.0006564690885914596,
|
| 784 |
"epoch": 4.091778202676864,
|
| 785 |
"step": 2140
|
| 786 |
},
|
| 787 |
{
|
| 788 |
-
"loss": 1.
|
| 789 |
-
"grad_norm": 1.
|
| 790 |
"learning_rate": 0.0006522200977267899,
|
| 791 |
"epoch": 4.130019120458891,
|
| 792 |
"step": 2160
|
| 793 |
},
|
| 794 |
{
|
| 795 |
-
"loss": 1.
|
| 796 |
-
"grad_norm": 1.
|
| 797 |
"learning_rate": 0.0006479711068621203,
|
| 798 |
"epoch": 4.168260038240918,
|
| 799 |
"step": 2180
|
| 800 |
},
|
| 801 |
{
|
| 802 |
-
"loss": 1.
|
| 803 |
-
"grad_norm": 1.
|
| 804 |
"learning_rate": 0.0006437221159974506,
|
| 805 |
"epoch": 4.2065009560229445,
|
| 806 |
"step": 2200
|
| 807 |
},
|
| 808 |
{
|
| 809 |
-
"loss": 1.
|
| 810 |
-
"grad_norm": 1.
|
| 811 |
"learning_rate": 0.000639473125132781,
|
| 812 |
"epoch": 4.244741873804971,
|
| 813 |
"step": 2220
|
| 814 |
},
|
| 815 |
{
|
| 816 |
-
"loss": 1.
|
| 817 |
-
"grad_norm": 1.
|
| 818 |
"learning_rate": 0.0006352241342681113,
|
| 819 |
"epoch": 4.282982791586998,
|
| 820 |
"step": 2240
|
| 821 |
},
|
| 822 |
{
|
| 823 |
-
"loss": 1.
|
| 824 |
-
"grad_norm": 1.
|
| 825 |
"learning_rate": 0.0006309751434034417,
|
| 826 |
"epoch": 4.321223709369025,
|
| 827 |
"step": 2260
|
| 828 |
},
|
| 829 |
{
|
| 830 |
-
"loss": 1.
|
| 831 |
-
"grad_norm": 1.
|
| 832 |
"learning_rate": 0.0006267261525387721,
|
| 833 |
"epoch": 4.359464627151052,
|
| 834 |
"step": 2280
|
| 835 |
},
|
| 836 |
{
|
| 837 |
-
"loss": 1.
|
| 838 |
-
"grad_norm": 1.
|
| 839 |
"learning_rate": 0.0006224771616741024,
|
| 840 |
"epoch": 4.397705544933078,
|
| 841 |
"step": 2300
|
| 842 |
},
|
| 843 |
{
|
| 844 |
-
"loss": 1.
|
| 845 |
-
"grad_norm": 1.
|
| 846 |
"learning_rate": 0.0006182281708094328,
|
| 847 |
"epoch": 4.435946462715105,
|
| 848 |
"step": 2320
|
| 849 |
},
|
| 850 |
{
|
| 851 |
-
"loss": 1.
|
| 852 |
-
"grad_norm": 1.
|
| 853 |
"learning_rate": 0.0006139791799447631,
|
| 854 |
"epoch": 4.474187380497132,
|
| 855 |
"step": 2340
|
| 856 |
},
|
| 857 |
{
|
| 858 |
-
"loss": 1.
|
| 859 |
-
"grad_norm": 1.
|
| 860 |
"learning_rate": 0.0006097301890800934,
|
| 861 |
"epoch": 4.512428298279159,
|
| 862 |
"step": 2360
|
| 863 |
},
|
| 864 |
{
|
| 865 |
-
"loss": 1.
|
| 866 |
-
"grad_norm": 1.
|
| 867 |
"learning_rate": 0.0006054811982154238,
|
| 868 |
"epoch": 4.550669216061186,
|
| 869 |
"step": 2380
|
| 870 |
},
|
| 871 |
{
|
| 872 |
-
"loss": 1.
|
| 873 |
-
"grad_norm": 1.
|
| 874 |
"learning_rate": 0.0006012322073507542,
|
| 875 |
"epoch": 4.588910133843212,
|
| 876 |
"step": 2400
|
| 877 |
},
|
| 878 |
{
|
| 879 |
-
"loss": 1.
|
| 880 |
-
"grad_norm": 1.
|
| 881 |
"learning_rate": 0.0005969832164860845,
|
| 882 |
"epoch": 4.627151051625239,
|
| 883 |
"step": 2420
|
| 884 |
},
|
| 885 |
{
|
| 886 |
-
"loss": 1.
|
| 887 |
-
"grad_norm": 1.
|
| 888 |
"learning_rate": 0.0005927342256214149,
|
| 889 |
"epoch": 4.665391969407266,
|
| 890 |
"step": 2440
|
| 891 |
},
|
| 892 |
{
|
| 893 |
-
"loss": 1.
|
| 894 |
-
"grad_norm": 1.
|
| 895 |
"learning_rate": 0.0005884852347567453,
|
| 896 |
"epoch": 4.7036328871892925,
|
| 897 |
"step": 2460
|
| 898 |
},
|
| 899 |
{
|
| 900 |
-
"loss": 1.
|
| 901 |
-
"grad_norm": 1.
|
| 902 |
"learning_rate": 0.0005842362438920756,
|
| 903 |
"epoch": 4.741873804971319,
|
| 904 |
"step": 2480
|
| 905 |
},
|
| 906 |
{
|
| 907 |
-
"loss": 1.
|
| 908 |
-
"grad_norm": 1.
|
| 909 |
"learning_rate": 0.000579987253027406,
|
| 910 |
"epoch": 4.780114722753346,
|
| 911 |
"step": 2500
|
| 912 |
},
|
| 913 |
{
|
| 914 |
-
"loss": 1.
|
| 915 |
-
"grad_norm": 1.
|
| 916 |
"learning_rate": 0.0005757382621627364,
|
| 917 |
"epoch": 4.818355640535373,
|
| 918 |
"step": 2520
|
| 919 |
},
|
| 920 |
{
|
| 921 |
-
"loss": 1.
|
| 922 |
-
"grad_norm": 1.
|
| 923 |
"learning_rate": 0.0005714892712980667,
|
| 924 |
"epoch": 4.8565965583174,
|
| 925 |
"step": 2540
|
| 926 |
},
|
| 927 |
{
|
| 928 |
-
"loss": 1.
|
| 929 |
-
"grad_norm": 1.
|
| 930 |
"learning_rate": 0.000567240280433397,
|
| 931 |
"epoch": 4.894837476099426,
|
| 932 |
"step": 2560
|
| 933 |
},
|
| 934 |
{
|
| 935 |
-
"loss": 1.
|
| 936 |
-
"grad_norm": 1.
|
| 937 |
"learning_rate": 0.0005629912895687275,
|
| 938 |
"epoch": 4.933078393881453,
|
| 939 |
"step": 2580
|
| 940 |
},
|
| 941 |
{
|
| 942 |
-
"loss": 1.
|
| 943 |
-
"grad_norm": 1.
|
| 944 |
"learning_rate": 0.0005587422987040578,
|
| 945 |
"epoch": 4.97131931166348,
|
| 946 |
"step": 2600
|
| 947 |
},
|
| 948 |
{
|
| 949 |
-
"eval_loss": 0.
|
| 950 |
-
"eval_accuracy": 0.
|
| 951 |
-
"eval_runtime":
|
| 952 |
-
"eval_samples_per_second":
|
| 953 |
-
"eval_steps_per_second":
|
| 954 |
"epoch": 5.0,
|
| 955 |
"step": 2615
|
| 956 |
},
|
| 957 |
{
|
| 958 |
-
"loss": 1.
|
| 959 |
-
"grad_norm": 1.
|
| 960 |
"learning_rate": 0.0005544933078393881,
|
| 961 |
"epoch": 5.009560229445507,
|
| 962 |
"step": 2620
|
| 963 |
},
|
| 964 |
{
|
| 965 |
-
"loss": 1.
|
| 966 |
-
"grad_norm": 1.
|
| 967 |
"learning_rate": 0.0005502443169747186,
|
| 968 |
"epoch": 5.047801147227533,
|
| 969 |
"step": 2640
|
| 970 |
},
|
| 971 |
{
|
| 972 |
-
"loss": 1.
|
| 973 |
-
"grad_norm": 1.
|
| 974 |
"learning_rate": 0.0005459953261100489,
|
| 975 |
"epoch": 5.08604206500956,
|
| 976 |
"step": 2660
|
| 977 |
},
|
| 978 |
{
|
| 979 |
-
"loss": 1.
|
| 980 |
-
"grad_norm": 1.
|
| 981 |
"learning_rate": 0.0005417463352453792,
|
| 982 |
"epoch": 5.124282982791587,
|
| 983 |
"step": 2680
|
| 984 |
},
|
| 985 |
{
|
| 986 |
-
"loss": 1.
|
| 987 |
-
"grad_norm": 1.
|
| 988 |
"learning_rate": 0.0005374973443807097,
|
| 989 |
"epoch": 5.162523900573614,
|
| 990 |
"step": 2700
|
| 991 |
},
|
| 992 |
{
|
| 993 |
-
"loss": 1.
|
| 994 |
-
"grad_norm": 1.
|
| 995 |
"learning_rate": 0.00053324835351604,
|
| 996 |
"epoch": 5.2007648183556405,
|
| 997 |
"step": 2720
|
| 998 |
},
|
| 999 |
{
|
| 1000 |
-
"loss": 1.
|
| 1001 |
-
"grad_norm": 1.
|
| 1002 |
"learning_rate": 0.0005289993626513702,
|
| 1003 |
"epoch": 5.239005736137667,
|
| 1004 |
"step": 2740
|
| 1005 |
},
|
| 1006 |
{
|
| 1007 |
-
"loss": 1.
|
| 1008 |
-
"grad_norm": 1.
|
| 1009 |
"learning_rate": 0.0005247503717867008,
|
| 1010 |
"epoch": 5.277246653919694,
|
| 1011 |
"step": 2760
|
| 1012 |
},
|
| 1013 |
{
|
| 1014 |
-
"loss": 1.
|
| 1015 |
-
"grad_norm": 1.
|
| 1016 |
"learning_rate": 0.000520501380922031,
|
| 1017 |
"epoch": 5.315487571701721,
|
| 1018 |
"step": 2780
|
| 1019 |
},
|
| 1020 |
{
|
| 1021 |
-
"loss": 1.
|
| 1022 |
-
"grad_norm": 1.
|
| 1023 |
"learning_rate": 0.0005162523900573613,
|
| 1024 |
"epoch": 5.353728489483748,
|
| 1025 |
"step": 2800
|
| 1026 |
},
|
| 1027 |
{
|
| 1028 |
-
"loss": 1.
|
| 1029 |
-
"grad_norm": 1.
|
| 1030 |
"learning_rate": 0.0005120033991926918,
|
| 1031 |
"epoch": 5.3919694072657744,
|
| 1032 |
"step": 2820
|
| 1033 |
},
|
| 1034 |
{
|
| 1035 |
-
"loss": 1.
|
| 1036 |
-
"grad_norm": 1.
|
| 1037 |
"learning_rate": 0.0005077544083280221,
|
| 1038 |
"epoch": 5.430210325047801,
|
| 1039 |
"step": 2840
|
| 1040 |
},
|
| 1041 |
{
|
| 1042 |
-
"loss": 1.
|
| 1043 |
-
"grad_norm": 1.
|
| 1044 |
"learning_rate": 0.0005035054174633524,
|
| 1045 |
"epoch": 5.468451242829828,
|
| 1046 |
"step": 2860
|
| 1047 |
},
|
| 1048 |
{
|
| 1049 |
-
"loss": 1.
|
| 1050 |
-
"grad_norm": 1.
|
| 1051 |
"learning_rate": 0.0004992564265986828,
|
| 1052 |
"epoch": 5.506692160611855,
|
| 1053 |
"step": 2880
|
| 1054 |
},
|
| 1055 |
{
|
| 1056 |
-
"loss": 1.
|
| 1057 |
-
"grad_norm": 1.
|
| 1058 |
"learning_rate": 0.0004950074357340132,
|
| 1059 |
"epoch": 5.544933078393882,
|
| 1060 |
"step": 2900
|
| 1061 |
},
|
| 1062 |
{
|
| 1063 |
-
"loss": 1.
|
| 1064 |
-
"grad_norm": 1.
|
| 1065 |
"learning_rate": 0.0004907584448693436,
|
| 1066 |
"epoch": 5.583173996175908,
|
| 1067 |
"step": 2920
|
| 1068 |
},
|
| 1069 |
{
|
| 1070 |
-
"loss": 1.
|
| 1071 |
-
"grad_norm": 1.
|
| 1072 |
"learning_rate": 0.0004865094540046739,
|
| 1073 |
"epoch": 5.621414913957935,
|
| 1074 |
"step": 2940
|
| 1075 |
},
|
| 1076 |
{
|
| 1077 |
-
"loss": 1.
|
| 1078 |
-
"grad_norm": 1.
|
| 1079 |
"learning_rate": 0.00048226046314000425,
|
| 1080 |
"epoch": 5.659655831739962,
|
| 1081 |
"step": 2960
|
| 1082 |
},
|
| 1083 |
{
|
| 1084 |
-
"loss": 1.
|
| 1085 |
-
"grad_norm": 1.
|
| 1086 |
"learning_rate": 0.0004780114722753346,
|
| 1087 |
"epoch": 5.6978967495219885,
|
| 1088 |
"step": 2980
|
| 1089 |
},
|
| 1090 |
{
|
| 1091 |
-
"loss": 1.
|
| 1092 |
-
"grad_norm": 1.
|
| 1093 |
"learning_rate": 0.000473762481410665,
|
| 1094 |
"epoch": 5.736137667304015,
|
| 1095 |
"step": 3000
|
| 1096 |
},
|
| 1097 |
{
|
| 1098 |
-
"loss": 1.
|
| 1099 |
-
"grad_norm": 1.
|
| 1100 |
"learning_rate": 0.00046951349054599533,
|
| 1101 |
"epoch": 5.774378585086042,
|
| 1102 |
"step": 3020
|
| 1103 |
},
|
| 1104 |
{
|
| 1105 |
-
"loss": 1.
|
| 1106 |
-
"grad_norm": 1.
|
| 1107 |
"learning_rate": 0.0004652644996813257,
|
| 1108 |
"epoch": 5.812619502868069,
|
| 1109 |
"step": 3040
|
| 1110 |
},
|
| 1111 |
{
|
| 1112 |
-
"loss": 1.
|
| 1113 |
-
"grad_norm": 1.
|
| 1114 |
"learning_rate": 0.0004610155088166561,
|
| 1115 |
"epoch": 5.850860420650095,
|
| 1116 |
"step": 3060
|
| 1117 |
},
|
| 1118 |
{
|
| 1119 |
-
"loss": 1.
|
| 1120 |
-
"grad_norm": 1.
|
| 1121 |
"learning_rate": 0.0004567665179519864,
|
| 1122 |
"epoch": 5.8891013384321225,
|
| 1123 |
"step": 3080
|
| 1124 |
},
|
| 1125 |
{
|
| 1126 |
-
"loss": 1.
|
| 1127 |
-
"grad_norm": 1.
|
| 1128 |
"learning_rate": 0.00045251752708731676,
|
| 1129 |
"epoch": 5.927342256214149,
|
| 1130 |
"step": 3100
|
| 1131 |
},
|
| 1132 |
{
|
| 1133 |
-
"loss": 1.
|
| 1134 |
-
"grad_norm": 1.
|
| 1135 |
"learning_rate": 0.0004482685362226471,
|
| 1136 |
"epoch": 5.965583173996176,
|
| 1137 |
"step": 3120
|
| 1138 |
},
|
| 1139 |
{
|
| 1140 |
-
"eval_loss": 0.
|
| 1141 |
-
"eval_accuracy": 0.
|
| 1142 |
-
"eval_runtime":
|
| 1143 |
-
"eval_samples_per_second":
|
| 1144 |
-
"eval_steps_per_second":
|
| 1145 |
"epoch": 6.0,
|
| 1146 |
"step": 3138
|
| 1147 |
},
|
| 1148 |
{
|
| 1149 |
-
"loss": 1.
|
| 1150 |
-
"grad_norm": 1.
|
| 1151 |
"learning_rate": 0.0004440195453579775,
|
| 1152 |
"epoch": 6.003824091778203,
|
| 1153 |
"step": 3140
|
| 1154 |
},
|
| 1155 |
{
|
| 1156 |
-
"loss": 1.
|
| 1157 |
-
"grad_norm": 1.
|
| 1158 |
"learning_rate": 0.00043977055449330785,
|
| 1159 |
"epoch": 6.042065009560229,
|
| 1160 |
"step": 3160
|
| 1161 |
},
|
| 1162 |
{
|
| 1163 |
-
"loss": 1.
|
| 1164 |
-
"grad_norm": 1.
|
| 1165 |
"learning_rate": 0.0004355215636286382,
|
| 1166 |
"epoch": 6.080305927342256,
|
| 1167 |
"step": 3180
|
| 1168 |
},
|
| 1169 |
{
|
| 1170 |
-
"loss": 1.
|
| 1171 |
-
"grad_norm": 1.
|
| 1172 |
"learning_rate": 0.0004312725727639686,
|
| 1173 |
"epoch": 6.118546845124283,
|
| 1174 |
"step": 3200
|
| 1175 |
},
|
| 1176 |
{
|
| 1177 |
-
"loss": 1.
|
| 1178 |
-
"grad_norm": 1.
|
| 1179 |
"learning_rate": 0.0004270235818992989,
|
| 1180 |
"epoch": 6.15678776290631,
|
| 1181 |
"step": 3220
|
| 1182 |
},
|
| 1183 |
{
|
| 1184 |
-
"loss": 1.
|
| 1185 |
-
"grad_norm": 1.
|
| 1186 |
"learning_rate": 0.0004227745910346293,
|
| 1187 |
"epoch": 6.195028680688337,
|
| 1188 |
"step": 3240
|
| 1189 |
},
|
| 1190 |
{
|
| 1191 |
-
"loss": 1.
|
| 1192 |
-
"grad_norm": 1.
|
| 1193 |
"learning_rate": 0.0004185256001699597,
|
| 1194 |
"epoch": 6.233269598470363,
|
| 1195 |
"step": 3260
|
| 1196 |
},
|
| 1197 |
{
|
| 1198 |
-
"loss": 1.
|
| 1199 |
-
"grad_norm": 1.
|
| 1200 |
"learning_rate": 0.00041427660930528997,
|
| 1201 |
"epoch": 6.27151051625239,
|
| 1202 |
"step": 3280
|
| 1203 |
},
|
| 1204 |
{
|
| 1205 |
-
"loss": 1.
|
| 1206 |
-
"grad_norm": 1.
|
| 1207 |
"learning_rate": 0.00041002761844062037,
|
| 1208 |
"epoch": 6.309751434034417,
|
| 1209 |
"step": 3300
|
| 1210 |
},
|
| 1211 |
{
|
| 1212 |
-
"loss": 1.
|
| 1213 |
-
"grad_norm": 1.
|
| 1214 |
"learning_rate": 0.00040577862757595076,
|
| 1215 |
"epoch": 6.347992351816444,
|
| 1216 |
"step": 3320
|
| 1217 |
},
|
| 1218 |
{
|
| 1219 |
-
"loss": 1.
|
| 1220 |
-
"grad_norm": 1.
|
| 1221 |
"learning_rate": 0.00040152963671128105,
|
| 1222 |
"epoch": 6.3862332695984705,
|
| 1223 |
"step": 3340
|
| 1224 |
},
|
| 1225 |
{
|
| 1226 |
-
"loss": 1.
|
| 1227 |
-
"grad_norm": 1.
|
| 1228 |
"learning_rate": 0.00039728064584661145,
|
| 1229 |
"epoch": 6.424474187380497,
|
| 1230 |
"step": 3360
|
| 1231 |
},
|
| 1232 |
{
|
| 1233 |
-
"loss": 1.
|
| 1234 |
-
"grad_norm": 1.
|
| 1235 |
"learning_rate": 0.0003930316549819418,
|
| 1236 |
"epoch": 6.462715105162524,
|
| 1237 |
"step": 3380
|
| 1238 |
},
|
| 1239 |
{
|
| 1240 |
-
"loss": 1.
|
| 1241 |
-
"grad_norm": 1.
|
| 1242 |
"learning_rate": 0.00038878266411727214,
|
| 1243 |
"epoch": 6.500956022944551,
|
| 1244 |
"step": 3400
|
| 1245 |
},
|
| 1246 |
{
|
| 1247 |
-
"loss": 1.
|
| 1248 |
-
"grad_norm": 1.
|
| 1249 |
"learning_rate": 0.00038453367325260254,
|
| 1250 |
"epoch": 6.539196940726577,
|
| 1251 |
"step": 3420
|
| 1252 |
},
|
| 1253 |
{
|
| 1254 |
-
"loss": 1.
|
| 1255 |
-
"grad_norm": 1.
|
| 1256 |
"learning_rate": 0.0003802846823879329,
|
| 1257 |
"epoch": 6.577437858508604,
|
| 1258 |
"step": 3440
|
| 1259 |
},
|
| 1260 |
{
|
| 1261 |
-
"loss": 1.
|
| 1262 |
-
"grad_norm": 1.
|
| 1263 |
"learning_rate": 0.0003760356915232632,
|
| 1264 |
"epoch": 6.615678776290631,
|
| 1265 |
"step": 3460
|
| 1266 |
},
|
| 1267 |
{
|
| 1268 |
-
"loss": 1.
|
| 1269 |
-
"grad_norm": 1.
|
| 1270 |
"learning_rate": 0.0003717867006585936,
|
| 1271 |
"epoch": 6.653919694072657,
|
| 1272 |
"step": 3480
|
| 1273 |
},
|
| 1274 |
{
|
| 1275 |
-
"loss": 1.
|
| 1276 |
-
"grad_norm": 1.
|
| 1277 |
"learning_rate": 0.0003675377097939239,
|
| 1278 |
"epoch": 6.692160611854685,
|
| 1279 |
"step": 3500
|
| 1280 |
},
|
| 1281 |
{
|
| 1282 |
-
"loss": 1.
|
| 1283 |
-
"grad_norm": 1.
|
| 1284 |
"learning_rate": 0.0003632887189292543,
|
| 1285 |
"epoch": 6.730401529636711,
|
| 1286 |
"step": 3520
|
| 1287 |
},
|
| 1288 |
{
|
| 1289 |
-
"loss": 1.
|
| 1290 |
-
"grad_norm": 1.
|
| 1291 |
"learning_rate": 0.00035903972806458466,
|
| 1292 |
"epoch": 6.768642447418738,
|
| 1293 |
"step": 3540
|
| 1294 |
},
|
| 1295 |
{
|
| 1296 |
-
"loss": 1.
|
| 1297 |
-
"grad_norm": 1.
|
| 1298 |
"learning_rate": 0.000354790737199915,
|
| 1299 |
"epoch": 6.806883365200765,
|
| 1300 |
"step": 3560
|
| 1301 |
},
|
| 1302 |
{
|
| 1303 |
-
"loss": 1.
|
| 1304 |
-
"grad_norm": 1.
|
| 1305 |
"learning_rate": 0.0003505417463352454,
|
| 1306 |
"epoch": 6.845124282982791,
|
| 1307 |
"step": 3580
|
| 1308 |
},
|
| 1309 |
{
|
| 1310 |
-
"loss": 1.
|
| 1311 |
-
"grad_norm": 1.
|
| 1312 |
"learning_rate": 0.00034629275547057574,
|
| 1313 |
"epoch": 6.8833652007648185,
|
| 1314 |
"step": 3600
|
| 1315 |
},
|
| 1316 |
{
|
| 1317 |
-
"loss": 1.
|
| 1318 |
-
"grad_norm": 1.
|
| 1319 |
"learning_rate": 0.0003420437646059061,
|
| 1320 |
"epoch": 6.921606118546845,
|
| 1321 |
"step": 3620
|
| 1322 |
},
|
| 1323 |
{
|
| 1324 |
"loss": 1.0912,
|
| 1325 |
-
"grad_norm": 1.
|
| 1326 |
"learning_rate": 0.0003377947737412365,
|
| 1327 |
"epoch": 6.959847036328872,
|
| 1328 |
"step": 3640
|
| 1329 |
},
|
| 1330 |
{
|
| 1331 |
-
"loss": 1.
|
| 1332 |
-
"grad_norm": 1.
|
| 1333 |
"learning_rate": 0.00033354578287656683,
|
| 1334 |
"epoch": 6.998087954110899,
|
| 1335 |
"step": 3660
|
| 1336 |
},
|
| 1337 |
{
|
| 1338 |
-
"eval_loss": 0.
|
| 1339 |
-
"eval_accuracy": 0.
|
| 1340 |
-
"eval_runtime":
|
| 1341 |
-
"eval_samples_per_second":
|
| 1342 |
-
"eval_steps_per_second":
|
| 1343 |
"epoch": 7.0,
|
| 1344 |
"step": 3661
|
| 1345 |
},
|
| 1346 |
{
|
| 1347 |
-
"loss": 1.
|
| 1348 |
-
"grad_norm": 1.
|
| 1349 |
"learning_rate": 0.0003292967920118972,
|
| 1350 |
"epoch": 7.036328871892925,
|
| 1351 |
"step": 3680
|
| 1352 |
},
|
| 1353 |
{
|
| 1354 |
-
"loss": 1.
|
| 1355 |
-
"grad_norm": 1.
|
| 1356 |
"learning_rate": 0.0003250478011472275,
|
| 1357 |
"epoch": 7.074569789674952,
|
| 1358 |
"step": 3700
|
| 1359 |
},
|
| 1360 |
{
|
| 1361 |
-
"loss": 1.
|
| 1362 |
-
"grad_norm": 1.
|
| 1363 |
"learning_rate": 0.0003207988102825579,
|
| 1364 |
"epoch": 7.112810707456979,
|
| 1365 |
"step": 3720
|
| 1366 |
},
|
| 1367 |
{
|
| 1368 |
-
"loss": 1.
|
| 1369 |
-
"grad_norm": 1.
|
| 1370 |
"learning_rate": 0.00031654981941788826,
|
| 1371 |
"epoch": 7.151051625239006,
|
| 1372 |
"step": 3740
|
| 1373 |
},
|
| 1374 |
{
|
| 1375 |
-
"loss": 1.
|
| 1376 |
-
"grad_norm": 1.
|
| 1377 |
"learning_rate": 0.0003123008285532186,
|
| 1378 |
"epoch": 7.189292543021033,
|
| 1379 |
"step": 3760
|
| 1380 |
},
|
| 1381 |
{
|
| 1382 |
-
"loss": 1.
|
| 1383 |
-
"grad_norm": 1.
|
| 1384 |
"learning_rate": 0.000308051837688549,
|
| 1385 |
"epoch": 7.227533460803059,
|
| 1386 |
"step": 3780
|
| 1387 |
},
|
| 1388 |
{
|
| 1389 |
-
"loss": 1.
|
| 1390 |
-
"grad_norm": 1.
|
| 1391 |
"learning_rate": 0.00030380284682387935,
|
| 1392 |
"epoch": 7.265774378585086,
|
| 1393 |
"step": 3800
|
| 1394 |
},
|
| 1395 |
{
|
| 1396 |
-
"loss": 0.
|
| 1397 |
-
"grad_norm": 1.
|
| 1398 |
"learning_rate": 0.0002995538559592097,
|
| 1399 |
"epoch": 7.304015296367113,
|
| 1400 |
"step": 3820
|
| 1401 |
},
|
| 1402 |
{
|
| 1403 |
-
"loss": 1.
|
| 1404 |
-
"grad_norm": 1.
|
| 1405 |
"learning_rate": 0.0002953048650945401,
|
| 1406 |
"epoch": 7.342256214149139,
|
| 1407 |
"step": 3840
|
| 1408 |
},
|
| 1409 |
{
|
| 1410 |
-
"loss": 0.
|
| 1411 |
-
"grad_norm": 1.
|
| 1412 |
"learning_rate": 0.0002910558742298704,
|
| 1413 |
"epoch": 7.3804971319311665,
|
| 1414 |
"step": 3860
|
| 1415 |
},
|
| 1416 |
{
|
| 1417 |
-
"loss": 0.
|
| 1418 |
-
"grad_norm": 1.
|
| 1419 |
"learning_rate": 0.0002868068833652008,
|
| 1420 |
"epoch": 7.418738049713193,
|
| 1421 |
"step": 3880
|
| 1422 |
},
|
| 1423 |
{
|
| 1424 |
-
"loss": 0.
|
| 1425 |
-
"grad_norm": 1.
|
| 1426 |
"learning_rate": 0.0002825578925005312,
|
| 1427 |
"epoch": 7.45697896749522,
|
| 1428 |
"step": 3900
|
| 1429 |
},
|
| 1430 |
{
|
| 1431 |
-
"loss":
|
| 1432 |
-
"grad_norm": 1.
|
| 1433 |
"learning_rate": 0.00027830890163586146,
|
| 1434 |
"epoch": 7.495219885277247,
|
| 1435 |
"step": 3920
|
| 1436 |
},
|
| 1437 |
{
|
| 1438 |
-
"loss": 0.
|
| 1439 |
-
"grad_norm": 1.
|
| 1440 |
"learning_rate": 0.00027405991077119186,
|
| 1441 |
"epoch": 7.533460803059273,
|
| 1442 |
"step": 3940
|
| 1443 |
},
|
| 1444 |
{
|
| 1445 |
-
"loss": 0.
|
| 1446 |
-
"grad_norm": 1.
|
| 1447 |
"learning_rate": 0.00026981091990652226,
|
| 1448 |
"epoch": 7.5717017208413,
|
| 1449 |
"step": 3960
|
| 1450 |
},
|
| 1451 |
{
|
| 1452 |
-
"loss": 0.
|
| 1453 |
-
"grad_norm": 1.
|
| 1454 |
"learning_rate": 0.00026556192904185255,
|
| 1455 |
"epoch": 7.609942638623327,
|
| 1456 |
"step": 3980
|
| 1457 |
},
|
| 1458 |
{
|
| 1459 |
-
"loss": 0.
|
| 1460 |
-
"grad_norm": 1.
|
| 1461 |
"learning_rate": 0.00026131293817718295,
|
| 1462 |
"epoch": 7.648183556405353,
|
| 1463 |
"step": 4000
|
| 1464 |
},
|
| 1465 |
{
|
| 1466 |
-
"loss": 0.
|
| 1467 |
-
"grad_norm": 1.
|
| 1468 |
"learning_rate": 0.00025706394731251324,
|
| 1469 |
"epoch": 7.686424474187381,
|
| 1470 |
"step": 4020
|
| 1471 |
},
|
| 1472 |
{
|
| 1473 |
-
"loss": 0.
|
| 1474 |
-
"grad_norm": 1.
|
| 1475 |
"learning_rate": 0.00025281495644784364,
|
| 1476 |
"epoch": 7.724665391969407,
|
| 1477 |
"step": 4040
|
| 1478 |
},
|
| 1479 |
{
|
| 1480 |
-
"loss": 0.
|
| 1481 |
-
"grad_norm": 1.
|
| 1482 |
"learning_rate": 0.00024856596558317403,
|
| 1483 |
"epoch": 7.762906309751434,
|
| 1484 |
"step": 4060
|
| 1485 |
},
|
| 1486 |
{
|
| 1487 |
-
"loss": 0.
|
| 1488 |
-
"grad_norm": 1.
|
| 1489 |
"learning_rate": 0.0002443169747185044,
|
| 1490 |
"epoch": 7.801147227533461,
|
| 1491 |
"step": 4080
|
| 1492 |
},
|
| 1493 |
{
|
| 1494 |
-
"loss": 0.
|
| 1495 |
-
"grad_norm": 1.
|
| 1496 |
"learning_rate": 0.00024006798385383472,
|
| 1497 |
"epoch": 7.839388145315487,
|
| 1498 |
"step": 4100
|
| 1499 |
},
|
| 1500 |
{
|
| 1501 |
-
"loss": 0.
|
| 1502 |
-
"grad_norm": 1.
|
| 1503 |
"learning_rate": 0.00023581899298916507,
|
| 1504 |
"epoch": 7.8776290630975145,
|
| 1505 |
"step": 4120
|
| 1506 |
},
|
| 1507 |
{
|
| 1508 |
-
"loss": 0.
|
| 1509 |
-
"grad_norm": 1.
|
| 1510 |
"learning_rate": 0.00023157000212449544,
|
| 1511 |
"epoch": 7.915869980879541,
|
| 1512 |
"step": 4140
|
| 1513 |
},
|
| 1514 |
{
|
| 1515 |
-
"loss": 0.
|
| 1516 |
-
"grad_norm": 1.
|
| 1517 |
"learning_rate": 0.00022732101125982578,
|
| 1518 |
"epoch": 7.954110898661568,
|
| 1519 |
"step": 4160
|
| 1520 |
},
|
| 1521 |
{
|
| 1522 |
-
"loss": 0.
|
| 1523 |
-
"grad_norm": 1.
|
| 1524 |
"learning_rate": 0.00022307202039515615,
|
| 1525 |
"epoch": 7.992351816443595,
|
| 1526 |
"step": 4180
|
| 1527 |
},
|
| 1528 |
{
|
| 1529 |
-
"eval_loss": 0.
|
| 1530 |
-
"eval_accuracy": 0.
|
| 1531 |
-
"eval_runtime":
|
| 1532 |
-
"eval_samples_per_second":
|
| 1533 |
-
"eval_steps_per_second":
|
| 1534 |
"epoch": 8.0,
|
| 1535 |
"step": 4184
|
| 1536 |
},
|
| 1537 |
{
|
| 1538 |
-
"loss": 0.
|
| 1539 |
-
"grad_norm": 1.
|
| 1540 |
"learning_rate": 0.00021882302953048652,
|
| 1541 |
"epoch": 8.030592734225621,
|
| 1542 |
"step": 4200
|
| 1543 |
},
|
| 1544 |
{
|
| 1545 |
-
"loss": 0.
|
| 1546 |
-
"grad_norm": 1.
|
| 1547 |
"learning_rate": 0.00021457403866581687,
|
| 1548 |
"epoch": 8.068833652007648,
|
| 1549 |
"step": 4220
|
| 1550 |
},
|
| 1551 |
{
|
| 1552 |
-
"loss": 0.
|
| 1553 |
-
"grad_norm": 1.
|
| 1554 |
"learning_rate": 0.0002103250478011472,
|
| 1555 |
"epoch": 8.107074569789676,
|
| 1556 |
"step": 4240
|
| 1557 |
},
|
| 1558 |
{
|
| 1559 |
-
"loss": 0.
|
| 1560 |
-
"grad_norm": 1.
|
| 1561 |
"learning_rate": 0.0002060760569364776,
|
| 1562 |
"epoch": 8.145315487571702,
|
| 1563 |
"step": 4260
|
| 1564 |
},
|
| 1565 |
{
|
| 1566 |
-
"loss": 0.
|
| 1567 |
-
"grad_norm": 1.
|
| 1568 |
"learning_rate": 0.00020182706607180795,
|
| 1569 |
"epoch": 8.183556405353729,
|
| 1570 |
"step": 4280
|
| 1571 |
},
|
| 1572 |
{
|
| 1573 |
-
"loss": 0.
|
| 1574 |
-
"grad_norm": 1.
|
| 1575 |
"learning_rate": 0.0001975780752071383,
|
| 1576 |
"epoch": 8.221797323135755,
|
| 1577 |
"step": 4300
|
| 1578 |
},
|
| 1579 |
{
|
| 1580 |
-
"loss": 0.
|
| 1581 |
-
"grad_norm": 1.
|
| 1582 |
"learning_rate": 0.00019332908434246867,
|
| 1583 |
"epoch": 8.260038240917781,
|
| 1584 |
"step": 4320
|
| 1585 |
},
|
| 1586 |
{
|
| 1587 |
-
"loss": 0.
|
| 1588 |
-
"grad_norm": 1.
|
| 1589 |
"learning_rate": 0.00018908009347779904,
|
| 1590 |
"epoch": 8.29827915869981,
|
| 1591 |
"step": 4340
|
| 1592 |
},
|
| 1593 |
{
|
| 1594 |
-
"loss": 0.
|
| 1595 |
-
"grad_norm": 1.
|
| 1596 |
"learning_rate": 0.00018483110261312938,
|
| 1597 |
"epoch": 8.336520076481836,
|
| 1598 |
"step": 4360
|
| 1599 |
},
|
| 1600 |
{
|
| 1601 |
-
"loss": 0.
|
| 1602 |
-
"grad_norm": 1.
|
| 1603 |
"learning_rate": 0.00018058211174845973,
|
| 1604 |
"epoch": 8.374760994263863,
|
| 1605 |
"step": 4380
|
| 1606 |
},
|
| 1607 |
{
|
| 1608 |
-
"loss": 0.
|
| 1609 |
-
"grad_norm": 1.
|
| 1610 |
"learning_rate": 0.0001763331208837901,
|
| 1611 |
"epoch": 8.413001912045889,
|
| 1612 |
"step": 4400
|
| 1613 |
},
|
| 1614 |
{
|
| 1615 |
-
"loss": 0.
|
| 1616 |
-
"grad_norm": 1.
|
| 1617 |
"learning_rate": 0.00017208413001912047,
|
| 1618 |
"epoch": 8.451242829827915,
|
| 1619 |
"step": 4420
|
| 1620 |
},
|
| 1621 |
{
|
| 1622 |
-
"loss": 0.
|
| 1623 |
-
"grad_norm": 1.
|
| 1624 |
"learning_rate": 0.00016783513915445082,
|
| 1625 |
"epoch": 8.489483747609942,
|
| 1626 |
"step": 4440
|
| 1627 |
},
|
| 1628 |
{
|
| 1629 |
-
"loss": 0.
|
| 1630 |
-
"grad_norm": 1.
|
| 1631 |
"learning_rate": 0.00016358614828978119,
|
| 1632 |
"epoch": 8.52772466539197,
|
| 1633 |
"step": 4460
|
| 1634 |
},
|
| 1635 |
{
|
| 1636 |
-
"loss": 0.
|
| 1637 |
-
"grad_norm": 1.
|
| 1638 |
"learning_rate": 0.00015933715742511153,
|
| 1639 |
"epoch": 8.565965583173996,
|
| 1640 |
"step": 4480
|
| 1641 |
},
|
| 1642 |
{
|
| 1643 |
-
"loss": 0.
|
| 1644 |
-
"grad_norm": 1.
|
| 1645 |
"learning_rate": 0.0001550881665604419,
|
| 1646 |
"epoch": 8.604206500956023,
|
| 1647 |
"step": 4500
|
| 1648 |
},
|
| 1649 |
{
|
| 1650 |
-
"loss": 0.
|
| 1651 |
-
"grad_norm": 1.
|
| 1652 |
"learning_rate": 0.00015083917569577227,
|
| 1653 |
"epoch": 8.64244741873805,
|
| 1654 |
"step": 4520
|
| 1655 |
},
|
| 1656 |
{
|
| 1657 |
-
"loss": 0.
|
| 1658 |
-
"grad_norm": 1.
|
| 1659 |
"learning_rate": 0.00014659018483110262,
|
| 1660 |
"epoch": 8.680688336520076,
|
| 1661 |
"step": 4540
|
| 1662 |
},
|
| 1663 |
{
|
| 1664 |
-
"loss": 0.
|
| 1665 |
-
"grad_norm": 1.
|
| 1666 |
"learning_rate": 0.00014234119396643296,
|
| 1667 |
"epoch": 8.718929254302104,
|
| 1668 |
"step": 4560
|
| 1669 |
},
|
| 1670 |
{
|
| 1671 |
-
"loss": 0.
|
| 1672 |
-
"grad_norm": 1.
|
| 1673 |
"learning_rate": 0.00013809220310176336,
|
| 1674 |
"epoch": 8.75717017208413,
|
| 1675 |
"step": 4580
|
| 1676 |
},
|
| 1677 |
{
|
| 1678 |
-
"loss": 0.
|
| 1679 |
-
"grad_norm": 1.
|
| 1680 |
"learning_rate": 0.0001338432122370937,
|
| 1681 |
"epoch": 8.795411089866157,
|
| 1682 |
"step": 4600
|
| 1683 |
},
|
| 1684 |
{
|
| 1685 |
-
"loss": 0.
|
| 1686 |
-
"grad_norm": 1.
|
| 1687 |
"learning_rate": 0.00012959422137242405,
|
| 1688 |
"epoch": 8.833652007648183,
|
| 1689 |
"step": 4620
|
| 1690 |
},
|
| 1691 |
{
|
| 1692 |
-
"loss": 0.
|
| 1693 |
-
"grad_norm": 1.
|
| 1694 |
"learning_rate": 0.0001253452305077544,
|
| 1695 |
"epoch": 8.87189292543021,
|
| 1696 |
"step": 4640
|
| 1697 |
},
|
| 1698 |
{
|
| 1699 |
-
"loss": 0.
|
| 1700 |
-
"grad_norm": 1.
|
| 1701 |
"learning_rate": 0.00012109623964308478,
|
| 1702 |
"epoch": 8.910133843212238,
|
| 1703 |
"step": 4660
|
| 1704 |
},
|
| 1705 |
{
|
| 1706 |
-
"loss": 0.
|
| 1707 |
-
"grad_norm": 1.
|
| 1708 |
"learning_rate": 0.00011684724877841513,
|
| 1709 |
"epoch": 8.948374760994264,
|
| 1710 |
"step": 4680
|
| 1711 |
},
|
| 1712 |
{
|
| 1713 |
-
"loss": 0.
|
| 1714 |
-
"grad_norm": 1.
|
| 1715 |
"learning_rate": 0.00011259825791374549,
|
| 1716 |
"epoch": 8.98661567877629,
|
| 1717 |
"step": 4700
|
| 1718 |
},
|
| 1719 |
{
|
| 1720 |
-
"eval_loss": 0.
|
| 1721 |
"eval_accuracy": 0.9352842246888665,
|
| 1722 |
-
"eval_runtime":
|
| 1723 |
-
"eval_samples_per_second":
|
| 1724 |
-
"eval_steps_per_second":
|
| 1725 |
"epoch": 9.0,
|
| 1726 |
"step": 4707
|
| 1727 |
},
|
| 1728 |
{
|
| 1729 |
-
"loss": 0.
|
| 1730 |
-
"grad_norm": 1.
|
| 1731 |
"learning_rate": 0.00010834926704907585,
|
| 1732 |
"epoch": 9.024856596558317,
|
| 1733 |
"step": 4720
|
| 1734 |
},
|
| 1735 |
{
|
| 1736 |
-
"loss": 0.
|
| 1737 |
-
"grad_norm": 1.
|
| 1738 |
"learning_rate": 0.0001041002761844062,
|
| 1739 |
"epoch": 9.063097514340344,
|
| 1740 |
"step": 4740
|
| 1741 |
},
|
| 1742 |
{
|
| 1743 |
-
"loss": 0.
|
| 1744 |
-
"grad_norm": 1.
|
| 1745 |
"learning_rate": 9.985128531973658e-05,
|
| 1746 |
"epoch": 9.101338432122372,
|
| 1747 |
"step": 4760
|
| 1748 |
},
|
| 1749 |
{
|
| 1750 |
-
"loss": 0.
|
| 1751 |
-
"grad_norm": 1.
|
| 1752 |
"learning_rate": 9.560229445506692e-05,
|
| 1753 |
"epoch": 9.139579349904398,
|
| 1754 |
"step": 4780
|
| 1755 |
},
|
| 1756 |
{
|
| 1757 |
-
"loss": 0.
|
| 1758 |
-
"grad_norm": 1.
|
| 1759 |
"learning_rate": 9.135330359039729e-05,
|
| 1760 |
"epoch": 9.177820267686425,
|
| 1761 |
"step": 4800
|
| 1762 |
},
|
| 1763 |
{
|
| 1764 |
-
"loss": 0.
|
| 1765 |
-
"grad_norm": 1.
|
| 1766 |
"learning_rate": 8.710431272572764e-05,
|
| 1767 |
"epoch": 9.216061185468451,
|
| 1768 |
"step": 4820
|
| 1769 |
},
|
| 1770 |
{
|
| 1771 |
-
"loss": 0.
|
| 1772 |
-
"grad_norm": 1.
|
| 1773 |
"learning_rate": 8.2855321861058e-05,
|
| 1774 |
"epoch": 9.254302103250478,
|
| 1775 |
"step": 4840
|
| 1776 |
},
|
| 1777 |
{
|
| 1778 |
-
"loss": 0.
|
| 1779 |
-
"grad_norm": 1.
|
| 1780 |
"learning_rate": 7.860633099638836e-05,
|
| 1781 |
"epoch": 9.292543021032504,
|
| 1782 |
"step": 4860
|
| 1783 |
},
|
| 1784 |
{
|
| 1785 |
-
"loss": 0.
|
| 1786 |
-
"grad_norm": 1.
|
| 1787 |
"learning_rate": 7.435734013171871e-05,
|
| 1788 |
"epoch": 9.330783938814532,
|
| 1789 |
"step": 4880
|
| 1790 |
},
|
| 1791 |
{
|
| 1792 |
-
"loss": 0.
|
| 1793 |
-
"grad_norm": 1.
|
| 1794 |
"learning_rate": 7.010834926704908e-05,
|
| 1795 |
"epoch": 9.369024856596559,
|
| 1796 |
"step": 4900
|
| 1797 |
},
|
| 1798 |
{
|
| 1799 |
-
"loss": 0.
|
| 1800 |
-
"grad_norm": 1.
|
| 1801 |
"learning_rate": 6.585935840237942e-05,
|
| 1802 |
"epoch": 9.407265774378585,
|
| 1803 |
"step": 4920
|
| 1804 |
},
|
| 1805 |
{
|
| 1806 |
-
"loss": 0.
|
| 1807 |
-
"grad_norm": 1.
|
| 1808 |
"learning_rate": 6.16103675377098e-05,
|
| 1809 |
"epoch": 9.445506692160611,
|
| 1810 |
"step": 4940
|
| 1811 |
},
|
| 1812 |
{
|
| 1813 |
-
"loss": 0.
|
| 1814 |
-
"grad_norm": 1.
|
| 1815 |
"learning_rate": 5.736137667304015e-05,
|
| 1816 |
"epoch": 9.483747609942638,
|
| 1817 |
"step": 4960
|
| 1818 |
},
|
| 1819 |
{
|
| 1820 |
-
"loss": 0.
|
| 1821 |
-
"grad_norm": 1.
|
| 1822 |
"learning_rate": 5.311238580837052e-05,
|
| 1823 |
"epoch": 9.521988527724666,
|
| 1824 |
"step": 4980
|
| 1825 |
},
|
| 1826 |
{
|
| 1827 |
-
"loss": 0.
|
| 1828 |
-
"grad_norm": 1.
|
| 1829 |
"learning_rate": 4.8863394943700874e-05,
|
| 1830 |
"epoch": 9.560229445506693,
|
| 1831 |
"step": 5000
|
| 1832 |
},
|
| 1833 |
{
|
| 1834 |
-
"loss": 0.
|
| 1835 |
-
"grad_norm": 1.
|
| 1836 |
"learning_rate": 4.461440407903123e-05,
|
| 1837 |
"epoch": 9.598470363288719,
|
| 1838 |
"step": 5020
|
| 1839 |
},
|
| 1840 |
{
|
| 1841 |
-
"loss": 0.
|
| 1842 |
-
"grad_norm": 1.
|
| 1843 |
"learning_rate": 4.036541321436159e-05,
|
| 1844 |
"epoch": 9.636711281070745,
|
| 1845 |
"step": 5040
|
| 1846 |
},
|
| 1847 |
{
|
| 1848 |
-
"loss": 0.
|
| 1849 |
-
"grad_norm": 1.
|
| 1850 |
"learning_rate": 3.6116422349691954e-05,
|
| 1851 |
"epoch": 9.674952198852772,
|
| 1852 |
"step": 5060
|
| 1853 |
},
|
| 1854 |
{
|
| 1855 |
-
"loss": 0.
|
| 1856 |
-
"grad_norm": 1.
|
| 1857 |
"learning_rate": 3.186743148502231e-05,
|
| 1858 |
"epoch": 9.7131931166348,
|
| 1859 |
"step": 5080
|
| 1860 |
},
|
| 1861 |
{
|
| 1862 |
-
"loss": 0.
|
| 1863 |
-
"grad_norm": 1.
|
| 1864 |
"learning_rate": 2.7618440620352666e-05,
|
| 1865 |
"epoch": 9.751434034416826,
|
| 1866 |
"step": 5100
|
| 1867 |
},
|
| 1868 |
{
|
| 1869 |
-
"loss": 0.
|
| 1870 |
-
"grad_norm": 1.
|
| 1871 |
"learning_rate": 2.3369449755683023e-05,
|
| 1872 |
"epoch": 9.789674952198853,
|
| 1873 |
"step": 5120
|
| 1874 |
},
|
| 1875 |
{
|
| 1876 |
-
"loss": 0.
|
| 1877 |
-
"grad_norm": 1.
|
| 1878 |
"learning_rate": 1.9120458891013384e-05,
|
| 1879 |
"epoch": 9.82791586998088,
|
| 1880 |
"step": 5140
|
| 1881 |
},
|
| 1882 |
{
|
| 1883 |
-
"loss": 0.
|
| 1884 |
-
"grad_norm": 1.
|
| 1885 |
"learning_rate": 1.4871468026343743e-05,
|
| 1886 |
"epoch": 9.866156787762906,
|
| 1887 |
"step": 5160
|
| 1888 |
},
|
| 1889 |
{
|
| 1890 |
-
"loss": 0.
|
| 1891 |
-
"grad_norm": 1.
|
| 1892 |
"learning_rate": 1.0622477161674103e-05,
|
| 1893 |
"epoch": 9.904397705544934,
|
| 1894 |
"step": 5180
|
| 1895 |
},
|
| 1896 |
{
|
| 1897 |
-
"loss": 0.
|
| 1898 |
-
"grad_norm": 1.
|
| 1899 |
"learning_rate": 6.373486297004461e-06,
|
| 1900 |
"epoch": 9.94263862332696,
|
| 1901 |
"step": 5200
|
| 1902 |
},
|
| 1903 |
{
|
| 1904 |
-
"loss": 0.
|
| 1905 |
-
"grad_norm": 1.
|
| 1906 |
"learning_rate": 2.1244954323348204e-06,
|
| 1907 |
"epoch": 9.980879541108987,
|
| 1908 |
"step": 5220
|
| 1909 |
},
|
| 1910 |
{
|
| 1911 |
-
"eval_loss": 0.
|
| 1912 |
-
"eval_accuracy": 0.
|
| 1913 |
-
"eval_runtime":
|
| 1914 |
-
"eval_samples_per_second":
|
| 1915 |
-
"eval_steps_per_second":
|
| 1916 |
"epoch": 10.0,
|
| 1917 |
"step": 5230
|
| 1918 |
},
|
| 1919 |
{
|
| 1920 |
-
"train_runtime":
|
| 1921 |
-
"train_samples_per_second":
|
| 1922 |
-
"train_steps_per_second": 0.
|
| 1923 |
"total_flos": 1.96318398191328e+18,
|
| 1924 |
-
"train_loss": 2.
|
| 1925 |
"epoch": 10.0,
|
| 1926 |
"step": 5230
|
| 1927 |
}
|
|
|
|
| 1 |
[
|
| 2 |
{
|
| 3 |
+
"loss": 7.1455,
|
| 4 |
+
"grad_norm": 4.702692031860352,
|
| 5 |
"learning_rate": 3.824091778202677e-05,
|
| 6 |
"epoch": 0.03824091778202677,
|
| 7 |
"step": 20
|
| 8 |
},
|
| 9 |
{
|
| 10 |
+
"loss": 7.116,
|
| 11 |
+
"grad_norm": 4.504467487335205,
|
| 12 |
"learning_rate": 7.648183556405354e-05,
|
| 13 |
"epoch": 0.07648183556405354,
|
| 14 |
"step": 40
|
| 15 |
},
|
| 16 |
{
|
| 17 |
+
"loss": 7.0566,
|
| 18 |
+
"grad_norm": 3.964728832244873,
|
| 19 |
"learning_rate": 0.0001147227533460803,
|
| 20 |
"epoch": 0.1147227533460803,
|
| 21 |
"step": 60
|
| 22 |
},
|
| 23 |
{
|
| 24 |
+
"loss": 6.972,
|
| 25 |
+
"grad_norm": 3.199570417404175,
|
| 26 |
"learning_rate": 0.00015296367112810707,
|
| 27 |
"epoch": 0.15296367112810708,
|
| 28 |
"step": 80
|
| 29 |
},
|
| 30 |
{
|
| 31 |
+
"loss": 6.8778,
|
| 32 |
+
"grad_norm": 2.6367344856262207,
|
| 33 |
"learning_rate": 0.00019120458891013384,
|
| 34 |
"epoch": 0.19120458891013384,
|
| 35 |
"step": 100
|
| 36 |
},
|
| 37 |
{
|
| 38 |
+
"loss": 6.733,
|
| 39 |
+
"grad_norm": 2.1930582523345947,
|
| 40 |
"learning_rate": 0.0002294455066921606,
|
| 41 |
"epoch": 0.2294455066921606,
|
| 42 |
"step": 120
|
| 43 |
},
|
| 44 |
{
|
| 45 |
+
"loss": 6.5814,
|
| 46 |
+
"grad_norm": 1.9982482194900513,
|
| 47 |
"learning_rate": 0.0002676864244741874,
|
| 48 |
"epoch": 0.2676864244741874,
|
| 49 |
"step": 140
|
| 50 |
},
|
| 51 |
{
|
| 52 |
+
"loss": 6.4206,
|
| 53 |
+
"grad_norm": 1.8051823377609253,
|
| 54 |
"learning_rate": 0.00030592734225621415,
|
| 55 |
"epoch": 0.30592734225621415,
|
| 56 |
"step": 160
|
| 57 |
},
|
| 58 |
{
|
| 59 |
+
"loss": 6.2424,
|
| 60 |
+
"grad_norm": 1.757859706878662,
|
| 61 |
"learning_rate": 0.00034416826003824094,
|
| 62 |
"epoch": 0.3441682600382409,
|
| 63 |
"step": 180
|
| 64 |
},
|
| 65 |
{
|
| 66 |
+
"loss": 6.0657,
|
| 67 |
+
"grad_norm": 1.7747690677642822,
|
| 68 |
"learning_rate": 0.0003824091778202677,
|
| 69 |
"epoch": 0.3824091778202677,
|
| 70 |
"step": 200
|
| 71 |
},
|
| 72 |
{
|
| 73 |
+
"loss": 5.9722,
|
| 74 |
+
"grad_norm": 1.7719988822937012,
|
| 75 |
"learning_rate": 0.0004206500956022944,
|
| 76 |
"epoch": 0.42065009560229444,
|
| 77 |
"step": 220
|
| 78 |
},
|
| 79 |
{
|
| 80 |
+
"loss": 5.814,
|
| 81 |
+
"grad_norm": 1.934911847114563,
|
| 82 |
"learning_rate": 0.0004588910133843212,
|
| 83 |
"epoch": 0.4588910133843212,
|
| 84 |
"step": 240
|
| 85 |
},
|
| 86 |
{
|
| 87 |
+
"loss": 5.6998,
|
| 88 |
+
"grad_norm": 1.793244481086731,
|
| 89 |
"learning_rate": 0.0004971319311663481,
|
| 90 |
"epoch": 0.497131931166348,
|
| 91 |
"step": 260
|
| 92 |
},
|
| 93 |
{
|
| 94 |
+
"loss": 5.6115,
|
| 95 |
+
"grad_norm": 1.7790417671203613,
|
| 96 |
"learning_rate": 0.0005353728489483748,
|
| 97 |
"epoch": 0.5353728489483748,
|
| 98 |
"step": 280
|
| 99 |
},
|
| 100 |
{
|
| 101 |
+
"loss": 5.5236,
|
| 102 |
+
"grad_norm": 1.8355106115341187,
|
| 103 |
"learning_rate": 0.0005736137667304016,
|
| 104 |
"epoch": 0.5736137667304015,
|
| 105 |
"step": 300
|
| 106 |
},
|
| 107 |
{
|
| 108 |
+
"loss": 5.3894,
|
| 109 |
+
"grad_norm": 1.7114174365997314,
|
| 110 |
"learning_rate": 0.0006118546845124283,
|
| 111 |
"epoch": 0.6118546845124283,
|
| 112 |
"step": 320
|
| 113 |
},
|
| 114 |
{
|
| 115 |
+
"loss": 5.3336,
|
| 116 |
+
"grad_norm": 1.877690315246582,
|
| 117 |
"learning_rate": 0.000650095602294455,
|
| 118 |
"epoch": 0.6500956022944551,
|
| 119 |
"step": 340
|
| 120 |
},
|
| 121 |
{
|
| 122 |
+
"loss": 5.2577,
|
| 123 |
+
"grad_norm": 1.8771674633026123,
|
| 124 |
"learning_rate": 0.0006883365200764819,
|
| 125 |
"epoch": 0.6883365200764818,
|
| 126 |
"step": 360
|
| 127 |
},
|
| 128 |
{
|
| 129 |
+
"loss": 5.1333,
|
| 130 |
+
"grad_norm": 1.9654275178909302,
|
| 131 |
"learning_rate": 0.0007265774378585086,
|
| 132 |
"epoch": 0.7265774378585086,
|
| 133 |
"step": 380
|
| 134 |
},
|
| 135 |
{
|
| 136 |
+
"loss": 5.0882,
|
| 137 |
+
"grad_norm": 1.9327517747879028,
|
| 138 |
"learning_rate": 0.0007648183556405354,
|
| 139 |
"epoch": 0.7648183556405354,
|
| 140 |
"step": 400
|
| 141 |
},
|
| 142 |
{
|
| 143 |
+
"loss": 5.0404,
|
| 144 |
+
"grad_norm": 1.8918468952178955,
|
| 145 |
"learning_rate": 0.0008030592734225621,
|
| 146 |
"epoch": 0.8030592734225621,
|
| 147 |
"step": 420
|
| 148 |
},
|
| 149 |
{
|
| 150 |
+
"loss": 4.9524,
|
| 151 |
+
"grad_norm": 1.8536239862442017,
|
| 152 |
"learning_rate": 0.0008413001912045888,
|
| 153 |
"epoch": 0.8413001912045889,
|
| 154 |
"step": 440
|
| 155 |
},
|
| 156 |
{
|
| 157 |
+
"loss": 4.8673,
|
| 158 |
+
"grad_norm": 1.8849778175354004,
|
| 159 |
"learning_rate": 0.0008795411089866157,
|
| 160 |
"epoch": 0.8795411089866156,
|
| 161 |
"step": 460
|
| 162 |
},
|
| 163 |
{
|
| 164 |
+
"loss": 4.8456,
|
| 165 |
+
"grad_norm": 1.8270999193191528,
|
| 166 |
"learning_rate": 0.0009177820267686424,
|
| 167 |
"epoch": 0.9177820267686424,
|
| 168 |
"step": 480
|
| 169 |
},
|
| 170 |
{
|
| 171 |
+
"loss": 4.7748,
|
| 172 |
+
"grad_norm": 1.8521556854248047,
|
| 173 |
"learning_rate": 0.0009560229445506692,
|
| 174 |
"epoch": 0.9560229445506692,
|
| 175 |
"step": 500
|
| 176 |
},
|
| 177 |
{
|
| 178 |
+
"loss": 4.6869,
|
| 179 |
+
"grad_norm": 1.9331077337265015,
|
| 180 |
"learning_rate": 0.0009942638623326961,
|
| 181 |
"epoch": 0.994263862332696,
|
| 182 |
"step": 520
|
| 183 |
},
|
| 184 |
{
|
| 185 |
+
"eval_loss": 4.119868278503418,
|
| 186 |
+
"eval_accuracy": 0.19596367305751766,
|
| 187 |
+
"eval_runtime": 539.7217,
|
| 188 |
+
"eval_samples_per_second": 27.542,
|
| 189 |
+
"eval_steps_per_second": 27.542,
|
| 190 |
"epoch": 1.0,
|
| 191 |
"step": 523
|
| 192 |
},
|
| 193 |
{
|
| 194 |
+
"loss": 4.5805,
|
| 195 |
+
"grad_norm": 1.7894033193588257,
|
| 196 |
"learning_rate": 0.0009963883577650309,
|
| 197 |
"epoch": 1.0325047801147227,
|
| 198 |
"step": 540
|
| 199 |
},
|
| 200 |
{
|
| 201 |
+
"loss": 4.5223,
|
| 202 |
+
"grad_norm": 1.9136412143707275,
|
| 203 |
"learning_rate": 0.0009921393669003612,
|
| 204 |
"epoch": 1.0707456978967496,
|
| 205 |
"step": 560
|
| 206 |
},
|
| 207 |
{
|
| 208 |
+
"loss": 4.4213,
|
| 209 |
+
"grad_norm": 1.8342599868774414,
|
| 210 |
"learning_rate": 0.0009878903760356915,
|
| 211 |
"epoch": 1.1089866156787762,
|
| 212 |
"step": 580
|
| 213 |
},
|
| 214 |
{
|
| 215 |
+
"loss": 4.409,
|
| 216 |
+
"grad_norm": 1.7360094785690308,
|
| 217 |
"learning_rate": 0.0009836413851710218,
|
| 218 |
"epoch": 1.147227533460803,
|
| 219 |
"step": 600
|
| 220 |
},
|
| 221 |
{
|
| 222 |
+
"loss": 4.3382,
|
| 223 |
+
"grad_norm": 1.8302013874053955,
|
| 224 |
"learning_rate": 0.0009793923943063523,
|
| 225 |
"epoch": 1.1854684512428297,
|
| 226 |
"step": 620
|
| 227 |
},
|
| 228 |
{
|
| 229 |
+
"loss": 4.2381,
|
| 230 |
+
"grad_norm": 1.847433090209961,
|
| 231 |
"learning_rate": 0.0009751434034416827,
|
| 232 |
"epoch": 1.2237093690248566,
|
| 233 |
"step": 640
|
| 234 |
},
|
| 235 |
{
|
| 236 |
+
"loss": 4.1802,
|
| 237 |
+
"grad_norm": 1.866734504699707,
|
| 238 |
"learning_rate": 0.000970894412577013,
|
| 239 |
"epoch": 1.2619502868068833,
|
| 240 |
"step": 660
|
| 241 |
},
|
| 242 |
{
|
| 243 |
+
"loss": 4.1404,
|
| 244 |
+
"grad_norm": 1.9123674631118774,
|
| 245 |
"learning_rate": 0.0009666454217123433,
|
| 246 |
"epoch": 1.3001912045889101,
|
| 247 |
"step": 680
|
| 248 |
},
|
| 249 |
{
|
| 250 |
+
"loss": 4.059,
|
| 251 |
+
"grad_norm": 1.8355252742767334,
|
| 252 |
"learning_rate": 0.0009623964308476737,
|
| 253 |
"epoch": 1.338432122370937,
|
| 254 |
"step": 700
|
| 255 |
},
|
| 256 |
{
|
| 257 |
+
"loss": 4.0086,
|
| 258 |
+
"grad_norm": 1.7890186309814453,
|
| 259 |
"learning_rate": 0.000958147439983004,
|
| 260 |
"epoch": 1.3766730401529637,
|
| 261 |
"step": 720
|
| 262 |
},
|
| 263 |
{
|
| 264 |
+
"loss": 3.9641,
|
| 265 |
+
"grad_norm": 1.847299337387085,
|
| 266 |
"learning_rate": 0.0009538984491183344,
|
| 267 |
"epoch": 1.4149139579349903,
|
| 268 |
"step": 740
|
| 269 |
},
|
| 270 |
{
|
| 271 |
+
"loss": 3.9291,
|
| 272 |
+
"grad_norm": 1.8219211101531982,
|
| 273 |
"learning_rate": 0.0009496494582536647,
|
| 274 |
"epoch": 1.4531548757170172,
|
| 275 |
"step": 760
|
| 276 |
},
|
| 277 |
{
|
| 278 |
+
"loss": 3.8577,
|
| 279 |
+
"grad_norm": 1.8026444911956787,
|
| 280 |
"learning_rate": 0.0009454004673889951,
|
| 281 |
"epoch": 1.491395793499044,
|
| 282 |
"step": 780
|
| 283 |
},
|
| 284 |
{
|
| 285 |
+
"loss": 3.8234,
|
| 286 |
+
"grad_norm": 1.7959771156311035,
|
| 287 |
"learning_rate": 0.0009411514765243255,
|
| 288 |
"epoch": 1.5296367112810707,
|
| 289 |
"step": 800
|
| 290 |
},
|
| 291 |
{
|
| 292 |
+
"loss": 3.7132,
|
| 293 |
+
"grad_norm": 1.7638428211212158,
|
| 294 |
"learning_rate": 0.0009369024856596558,
|
| 295 |
"epoch": 1.5678776290630974,
|
| 296 |
"step": 820
|
| 297 |
},
|
| 298 |
{
|
| 299 |
+
"loss": 3.7057,
|
| 300 |
+
"grad_norm": 1.8295230865478516,
|
| 301 |
"learning_rate": 0.0009326534947949862,
|
| 302 |
"epoch": 1.6061185468451242,
|
| 303 |
"step": 840
|
| 304 |
},
|
| 305 |
{
|
| 306 |
+
"loss": 3.6656,
|
| 307 |
+
"grad_norm": 1.8669532537460327,
|
| 308 |
"learning_rate": 0.0009284045039303166,
|
| 309 |
"epoch": 1.644359464627151,
|
| 310 |
"step": 860
|
| 311 |
},
|
| 312 |
{
|
| 313 |
+
"loss": 3.591,
|
| 314 |
+
"grad_norm": 1.8251906633377075,
|
| 315 |
"learning_rate": 0.0009241555130656469,
|
| 316 |
"epoch": 1.682600382409178,
|
| 317 |
"step": 880
|
| 318 |
},
|
| 319 |
{
|
| 320 |
+
"loss": 3.5281,
|
| 321 |
+
"grad_norm": 1.825548529624939,
|
| 322 |
"learning_rate": 0.0009199065222009773,
|
| 323 |
"epoch": 1.7208413001912046,
|
| 324 |
"step": 900
|
| 325 |
},
|
| 326 |
{
|
| 327 |
+
"loss": 3.4841,
|
| 328 |
+
"grad_norm": 1.7811344861984253,
|
| 329 |
"learning_rate": 0.0009156575313363077,
|
| 330 |
"epoch": 1.7590822179732313,
|
| 331 |
"step": 920
|
| 332 |
},
|
| 333 |
{
|
| 334 |
+
"loss": 3.4707,
|
| 335 |
+
"grad_norm": 1.823803186416626,
|
| 336 |
"learning_rate": 0.000911408540471638,
|
| 337 |
"epoch": 1.7973231357552581,
|
| 338 |
"step": 940
|
| 339 |
},
|
| 340 |
{
|
| 341 |
+
"loss": 3.4532,
|
| 342 |
+
"grad_norm": 1.872054100036621,
|
| 343 |
"learning_rate": 0.0009071595496069684,
|
| 344 |
"epoch": 1.835564053537285,
|
| 345 |
"step": 960
|
| 346 |
},
|
| 347 |
{
|
| 348 |
+
"loss": 3.4224,
|
| 349 |
+
"grad_norm": 1.7651457786560059,
|
| 350 |
"learning_rate": 0.0009029105587422988,
|
| 351 |
"epoch": 1.8738049713193117,
|
| 352 |
"step": 980
|
| 353 |
},
|
| 354 |
{
|
| 355 |
+
"loss": 3.3199,
|
| 356 |
+
"grad_norm": 1.7336605787277222,
|
| 357 |
"learning_rate": 0.0008986615678776291,
|
| 358 |
"epoch": 1.9120458891013383,
|
| 359 |
"step": 1000
|
| 360 |
},
|
| 361 |
{
|
| 362 |
+
"loss": 3.2814,
|
| 363 |
+
"grad_norm": 1.8058604001998901,
|
| 364 |
"learning_rate": 0.0008944125770129595,
|
| 365 |
"epoch": 1.9502868068833652,
|
| 366 |
"step": 1020
|
| 367 |
},
|
| 368 |
{
|
| 369 |
+
"loss": 3.2423,
|
| 370 |
+
"grad_norm": 1.9400501251220703,
|
| 371 |
"learning_rate": 0.0008901635861482899,
|
| 372 |
"epoch": 1.988527724665392,
|
| 373 |
"step": 1040
|
| 374 |
},
|
| 375 |
{
|
| 376 |
+
"eval_loss": 2.282437801361084,
|
| 377 |
+
"eval_accuracy": 0.5047426841574167,
|
| 378 |
+
"eval_runtime": 710.9931,
|
| 379 |
+
"eval_samples_per_second": 20.907,
|
| 380 |
+
"eval_steps_per_second": 20.907,
|
| 381 |
"epoch": 2.0,
|
| 382 |
"step": 1046
|
| 383 |
},
|
| 384 |
{
|
| 385 |
+
"loss": 3.1858,
|
| 386 |
+
"grad_norm": 1.7496325969696045,
|
| 387 |
"learning_rate": 0.0008859145952836202,
|
| 388 |
"epoch": 2.026768642447419,
|
| 389 |
"step": 1060
|
| 390 |
},
|
| 391 |
{
|
| 392 |
+
"loss": 3.0482,
|
| 393 |
+
"grad_norm": 1.7203223705291748,
|
| 394 |
"learning_rate": 0.0008816656044189504,
|
| 395 |
"epoch": 2.0650095602294454,
|
| 396 |
"step": 1080
|
| 397 |
},
|
| 398 |
{
|
| 399 |
+
"loss": 3.0764,
|
| 400 |
+
"grad_norm": 1.6859164237976074,
|
| 401 |
"learning_rate": 0.000877416613554281,
|
| 402 |
"epoch": 2.1032504780114722,
|
| 403 |
"step": 1100
|
| 404 |
},
|
| 405 |
{
|
| 406 |
+
"loss": 2.9918,
|
| 407 |
+
"grad_norm": 1.887332558631897,
|
| 408 |
"learning_rate": 0.0008731676226896112,
|
| 409 |
"epoch": 2.141491395793499,
|
| 410 |
"step": 1120
|
| 411 |
},
|
| 412 |
{
|
| 413 |
+
"loss": 2.9791,
|
| 414 |
+
"grad_norm": 1.7712619304656982,
|
| 415 |
"learning_rate": 0.0008689186318249415,
|
| 416 |
"epoch": 2.179732313575526,
|
| 417 |
"step": 1140
|
| 418 |
},
|
| 419 |
{
|
| 420 |
+
"loss": 2.9064,
|
| 421 |
+
"grad_norm": 1.8518322706222534,
|
| 422 |
"learning_rate": 0.000864669640960272,
|
| 423 |
"epoch": 2.2179732313575524,
|
| 424 |
"step": 1160
|
| 425 |
},
|
| 426 |
{
|
| 427 |
+
"loss": 2.9346,
|
| 428 |
+
"grad_norm": 1.8636976480484009,
|
| 429 |
"learning_rate": 0.0008604206500956023,
|
| 430 |
"epoch": 2.2562141491395793,
|
| 431 |
"step": 1180
|
| 432 |
},
|
| 433 |
{
|
| 434 |
+
"loss": 2.9154,
|
| 435 |
+
"grad_norm": 1.8007034063339233,
|
| 436 |
"learning_rate": 0.0008561716592309326,
|
| 437 |
"epoch": 2.294455066921606,
|
| 438 |
"step": 1200
|
| 439 |
},
|
| 440 |
{
|
| 441 |
+
"loss": 2.8311,
|
| 442 |
+
"grad_norm": 1.8480207920074463,
|
| 443 |
"learning_rate": 0.000851922668366263,
|
| 444 |
"epoch": 2.332695984703633,
|
| 445 |
"step": 1220
|
| 446 |
},
|
| 447 |
{
|
| 448 |
+
"loss": 2.843,
|
| 449 |
+
"grad_norm": 1.8463302850723267,
|
| 450 |
"learning_rate": 0.0008476736775015934,
|
| 451 |
"epoch": 2.3709369024856595,
|
| 452 |
"step": 1240
|
| 453 |
},
|
| 454 |
{
|
| 455 |
+
"loss": 2.8704,
|
| 456 |
+
"grad_norm": 1.8563566207885742,
|
| 457 |
"learning_rate": 0.0008434246866369237,
|
| 458 |
"epoch": 2.4091778202676863,
|
| 459 |
"step": 1260
|
| 460 |
},
|
| 461 |
{
|
| 462 |
+
"loss": 2.7794,
|
| 463 |
+
"grad_norm": 1.8388174772262573,
|
| 464 |
"learning_rate": 0.0008391756957722541,
|
| 465 |
"epoch": 2.447418738049713,
|
| 466 |
"step": 1280
|
| 467 |
},
|
| 468 |
{
|
| 469 |
+
"loss": 2.7776,
|
| 470 |
+
"grad_norm": 1.787711262702942,
|
| 471 |
"learning_rate": 0.0008349267049075845,
|
| 472 |
"epoch": 2.48565965583174,
|
| 473 |
"step": 1300
|
| 474 |
},
|
| 475 |
{
|
| 476 |
+
"loss": 2.7288,
|
| 477 |
+
"grad_norm": 1.6573237180709839,
|
| 478 |
"learning_rate": 0.0008306777140429148,
|
| 479 |
"epoch": 2.5239005736137665,
|
| 480 |
"step": 1320
|
| 481 |
},
|
| 482 |
{
|
| 483 |
+
"loss": 2.6598,
|
| 484 |
+
"grad_norm": 1.8304985761642456,
|
| 485 |
"learning_rate": 0.0008264287231782451,
|
| 486 |
"epoch": 2.5621414913957934,
|
| 487 |
"step": 1340
|
| 488 |
},
|
| 489 |
{
|
| 490 |
+
"loss": 2.6842,
|
| 491 |
+
"grad_norm": 1.769439458847046,
|
| 492 |
"learning_rate": 0.0008221797323135756,
|
| 493 |
"epoch": 2.6003824091778203,
|
| 494 |
"step": 1360
|
| 495 |
},
|
| 496 |
{
|
| 497 |
+
"loss": 2.5974,
|
| 498 |
+
"grad_norm": 1.7404167652130127,
|
| 499 |
"learning_rate": 0.0008179307414489059,
|
| 500 |
"epoch": 2.638623326959847,
|
| 501 |
"step": 1380
|
| 502 |
},
|
| 503 |
{
|
| 504 |
+
"loss": 2.6557,
|
| 505 |
+
"grad_norm": 1.7064534425735474,
|
| 506 |
"learning_rate": 0.0008136817505842362,
|
| 507 |
"epoch": 2.676864244741874,
|
| 508 |
"step": 1400
|
| 509 |
},
|
| 510 |
{
|
| 511 |
+
"loss": 2.5701,
|
| 512 |
+
"grad_norm": 1.784652590751648,
|
| 513 |
"learning_rate": 0.0008094327597195667,
|
| 514 |
"epoch": 2.7151051625239004,
|
| 515 |
"step": 1420
|
| 516 |
},
|
| 517 |
{
|
| 518 |
+
"loss": 2.5879,
|
| 519 |
+
"grad_norm": 1.730402946472168,
|
| 520 |
"learning_rate": 0.000805183768854897,
|
| 521 |
"epoch": 2.7533460803059273,
|
| 522 |
"step": 1440
|
| 523 |
},
|
| 524 |
{
|
| 525 |
+
"loss": 2.5413,
|
| 526 |
+
"grad_norm": 1.803881049156189,
|
| 527 |
"learning_rate": 0.0008009347779902273,
|
| 528 |
"epoch": 2.791586998087954,
|
| 529 |
"step": 1460
|
| 530 |
},
|
| 531 |
{
|
| 532 |
+
"loss": 2.4823,
|
| 533 |
+
"grad_norm": 1.7114533185958862,
|
| 534 |
"learning_rate": 0.0007966857871255578,
|
| 535 |
"epoch": 2.8298279158699806,
|
| 536 |
"step": 1480
|
| 537 |
},
|
| 538 |
{
|
| 539 |
+
"loss": 2.4236,
|
| 540 |
+
"grad_norm": 1.7487016916275024,
|
| 541 |
"learning_rate": 0.000792436796260888,
|
| 542 |
"epoch": 2.8680688336520075,
|
| 543 |
"step": 1500
|
| 544 |
},
|
| 545 |
{
|
| 546 |
+
"loss": 2.4762,
|
| 547 |
+
"grad_norm": 1.7806780338287354,
|
| 548 |
"learning_rate": 0.0007881878053962183,
|
| 549 |
"epoch": 2.9063097514340344,
|
| 550 |
"step": 1520
|
| 551 |
},
|
| 552 |
{
|
| 553 |
+
"loss": 2.4221,
|
| 554 |
+
"grad_norm": 1.851486086845398,
|
| 555 |
"learning_rate": 0.0007839388145315488,
|
| 556 |
"epoch": 2.9445506692160612,
|
| 557 |
"step": 1540
|
| 558 |
},
|
| 559 |
{
|
| 560 |
+
"loss": 2.4164,
|
| 561 |
+
"grad_norm": 1.779451608657837,
|
| 562 |
"learning_rate": 0.0007796898236668791,
|
| 563 |
"epoch": 2.982791586998088,
|
| 564 |
"step": 1560
|
| 565 |
},
|
| 566 |
{
|
| 567 |
+
"eval_loss": 1.4862462282180786,
|
| 568 |
+
"eval_accuracy": 0.6816010763538514,
|
| 569 |
+
"eval_runtime": 715.5989,
|
| 570 |
+
"eval_samples_per_second": 20.773,
|
| 571 |
+
"eval_steps_per_second": 20.773,
|
| 572 |
"epoch": 3.0,
|
| 573 |
"step": 1569
|
| 574 |
},
|
| 575 |
{
|
| 576 |
+
"loss": 2.3348,
|
| 577 |
+
"grad_norm": 1.7617199420928955,
|
| 578 |
"learning_rate": 0.0007754408328022094,
|
| 579 |
"epoch": 3.0210325047801145,
|
| 580 |
"step": 1580
|
| 581 |
},
|
| 582 |
{
|
| 583 |
+
"loss": 2.3196,
|
| 584 |
+
"grad_norm": 1.7850340604782104,
|
| 585 |
"learning_rate": 0.0007711918419375399,
|
| 586 |
"epoch": 3.0592734225621414,
|
| 587 |
"step": 1600
|
| 588 |
},
|
| 589 |
{
|
| 590 |
+
"loss": 2.2991,
|
| 591 |
+
"grad_norm": 1.828715205192566,
|
| 592 |
"learning_rate": 0.0007669428510728702,
|
| 593 |
"epoch": 3.0975143403441683,
|
| 594 |
"step": 1620
|
| 595 |
},
|
| 596 |
{
|
| 597 |
+
"loss": 2.2354,
|
| 598 |
+
"grad_norm": 1.7825413942337036,
|
| 599 |
"learning_rate": 0.0007626938602082005,
|
| 600 |
"epoch": 3.135755258126195,
|
| 601 |
"step": 1640
|
| 602 |
},
|
| 603 |
{
|
| 604 |
+
"loss": 2.221,
|
| 605 |
+
"grad_norm": 1.8411946296691895,
|
| 606 |
"learning_rate": 0.0007584448693435309,
|
| 607 |
"epoch": 3.173996175908222,
|
| 608 |
"step": 1660
|
| 609 |
},
|
| 610 |
{
|
| 611 |
+
"loss": 2.1939,
|
| 612 |
+
"grad_norm": 1.8236651420593262,
|
| 613 |
"learning_rate": 0.0007541958784788613,
|
| 614 |
"epoch": 3.2122370936902485,
|
| 615 |
"step": 1680
|
| 616 |
},
|
| 617 |
{
|
| 618 |
+
"loss": 2.211,
|
| 619 |
+
"grad_norm": 1.8275988101959229,
|
| 620 |
"learning_rate": 0.0007499468876141916,
|
| 621 |
"epoch": 3.2504780114722753,
|
| 622 |
"step": 1700
|
| 623 |
},
|
| 624 |
{
|
| 625 |
+
"loss": 2.1454,
|
| 626 |
+
"grad_norm": 1.7743233442306519,
|
| 627 |
"learning_rate": 0.000745697896749522,
|
| 628 |
"epoch": 3.288718929254302,
|
| 629 |
"step": 1720
|
| 630 |
},
|
| 631 |
{
|
| 632 |
+
"loss": 2.1258,
|
| 633 |
+
"grad_norm": 1.7873393297195435,
|
| 634 |
"learning_rate": 0.0007414489058848524,
|
| 635 |
"epoch": 3.3269598470363286,
|
| 636 |
"step": 1740
|
| 637 |
},
|
| 638 |
{
|
| 639 |
+
"loss": 2.1101,
|
| 640 |
+
"grad_norm": 1.8012022972106934,
|
| 641 |
"learning_rate": 0.0007371999150201827,
|
| 642 |
"epoch": 3.3652007648183555,
|
| 643 |
"step": 1760
|
| 644 |
},
|
| 645 |
{
|
| 646 |
+
"loss": 2.1246,
|
| 647 |
+
"grad_norm": 1.8000600337982178,
|
| 648 |
"learning_rate": 0.0007329509241555131,
|
| 649 |
"epoch": 3.4034416826003824,
|
| 650 |
"step": 1780
|
| 651 |
},
|
| 652 |
{
|
| 653 |
+
"loss": 2.1244,
|
| 654 |
+
"grad_norm": 1.7723950147628784,
|
| 655 |
"learning_rate": 0.0007287019332908435,
|
| 656 |
"epoch": 3.4416826003824093,
|
| 657 |
"step": 1800
|
| 658 |
},
|
| 659 |
{
|
| 660 |
+
"loss": 2.1099,
|
| 661 |
+
"grad_norm": 1.8095979690551758,
|
| 662 |
"learning_rate": 0.0007244529424261738,
|
| 663 |
"epoch": 3.479923518164436,
|
| 664 |
"step": 1820
|
| 665 |
},
|
| 666 |
{
|
| 667 |
+
"loss": 2.0703,
|
| 668 |
+
"grad_norm": 1.8022161722183228,
|
| 669 |
"learning_rate": 0.0007202039515615042,
|
| 670 |
"epoch": 3.5181644359464626,
|
| 671 |
"step": 1840
|
| 672 |
},
|
| 673 |
{
|
| 674 |
+
"loss": 2.0937,
|
| 675 |
+
"grad_norm": 1.7775332927703857,
|
| 676 |
"learning_rate": 0.0007159549606968346,
|
| 677 |
"epoch": 3.5564053537284894,
|
| 678 |
"step": 1860
|
| 679 |
},
|
| 680 |
{
|
| 681 |
+
"loss": 2.0305,
|
| 682 |
+
"grad_norm": 1.829291820526123,
|
| 683 |
"learning_rate": 0.0007117059698321649,
|
| 684 |
"epoch": 3.5946462715105163,
|
| 685 |
"step": 1880
|
| 686 |
},
|
| 687 |
{
|
| 688 |
+
"loss": 2.0528,
|
| 689 |
+
"grad_norm": 1.731218934059143,
|
| 690 |
"learning_rate": 0.0007074569789674953,
|
| 691 |
"epoch": 3.632887189292543,
|
| 692 |
"step": 1900
|
| 693 |
},
|
| 694 |
{
|
| 695 |
+
"loss": 2.0311,
|
| 696 |
+
"grad_norm": 1.9170475006103516,
|
| 697 |
"learning_rate": 0.0007032079881028257,
|
| 698 |
"epoch": 3.67112810707457,
|
| 699 |
"step": 1920
|
| 700 |
},
|
| 701 |
{
|
| 702 |
+
"loss": 2.006,
|
| 703 |
+
"grad_norm": 1.6934610605239868,
|
| 704 |
"learning_rate": 0.0006989589972381559,
|
| 705 |
"epoch": 3.7093690248565965,
|
| 706 |
"step": 1940
|
| 707 |
},
|
| 708 |
{
|
| 709 |
+
"loss": 1.9627,
|
| 710 |
+
"grad_norm": 1.792523741722107,
|
| 711 |
"learning_rate": 0.0006947100063734863,
|
| 712 |
"epoch": 3.7476099426386233,
|
| 713 |
"step": 1960
|
| 714 |
},
|
| 715 |
{
|
| 716 |
+
"loss": 2.0141,
|
| 717 |
+
"grad_norm": 1.7618036270141602,
|
| 718 |
"learning_rate": 0.0006904610155088166,
|
| 719 |
"epoch": 3.78585086042065,
|
| 720 |
"step": 1980
|
| 721 |
},
|
| 722 |
{
|
| 723 |
+
"loss": 1.9489,
|
| 724 |
+
"grad_norm": 1.7026081085205078,
|
| 725 |
"learning_rate": 0.000686212024644147,
|
| 726 |
"epoch": 3.8240917782026767,
|
| 727 |
"step": 2000
|
| 728 |
},
|
| 729 |
{
|
| 730 |
+
"loss": 1.965,
|
| 731 |
+
"grad_norm": 1.7117011547088623,
|
| 732 |
"learning_rate": 0.0006819630337794774,
|
| 733 |
"epoch": 3.8623326959847035,
|
| 734 |
"step": 2020
|
| 735 |
},
|
| 736 |
{
|
| 737 |
+
"loss": 1.9188,
|
| 738 |
+
"grad_norm": 1.7798806428909302,
|
| 739 |
"learning_rate": 0.0006777140429148077,
|
| 740 |
"epoch": 3.9005736137667304,
|
| 741 |
"step": 2040
|
| 742 |
},
|
| 743 |
{
|
| 744 |
+
"loss": 1.9044,
|
| 745 |
+
"grad_norm": 1.7349345684051514,
|
| 746 |
"learning_rate": 0.0006734650520501381,
|
| 747 |
"epoch": 3.9388145315487573,
|
| 748 |
"step": 2060
|
| 749 |
},
|
| 750 |
{
|
| 751 |
+
"loss": 1.8625,
|
| 752 |
+
"grad_norm": 1.8268795013427734,
|
| 753 |
"learning_rate": 0.0006692160611854685,
|
| 754 |
"epoch": 3.977055449330784,
|
| 755 |
"step": 2080
|
| 756 |
},
|
| 757 |
{
|
| 758 |
+
"eval_loss": 0.9794349670410156,
|
| 759 |
+
"eval_accuracy": 0.7917255297679112,
|
| 760 |
+
"eval_runtime": 689.4289,
|
| 761 |
+
"eval_samples_per_second": 21.561,
|
| 762 |
+
"eval_steps_per_second": 21.561,
|
| 763 |
"epoch": 4.0,
|
| 764 |
"step": 2092
|
| 765 |
},
|
| 766 |
{
|
| 767 |
+
"loss": 1.8294,
|
| 768 |
+
"grad_norm": 1.6992357969284058,
|
| 769 |
"learning_rate": 0.0006649670703207988,
|
| 770 |
"epoch": 4.015296367112811,
|
| 771 |
"step": 2100
|
| 772 |
},
|
| 773 |
{
|
| 774 |
+
"loss": 1.7572,
|
| 775 |
+
"grad_norm": 1.6715435981750488,
|
| 776 |
"learning_rate": 0.0006607180794561292,
|
| 777 |
"epoch": 4.053537284894838,
|
| 778 |
"step": 2120
|
| 779 |
},
|
| 780 |
{
|
| 781 |
+
"loss": 1.7502,
|
| 782 |
+
"grad_norm": 1.7837462425231934,
|
| 783 |
"learning_rate": 0.0006564690885914596,
|
| 784 |
"epoch": 4.091778202676864,
|
| 785 |
"step": 2140
|
| 786 |
},
|
| 787 |
{
|
| 788 |
+
"loss": 1.733,
|
| 789 |
+
"grad_norm": 1.7979024648666382,
|
| 790 |
"learning_rate": 0.0006522200977267899,
|
| 791 |
"epoch": 4.130019120458891,
|
| 792 |
"step": 2160
|
| 793 |
},
|
| 794 |
{
|
| 795 |
+
"loss": 1.7437,
|
| 796 |
+
"grad_norm": 1.6781351566314697,
|
| 797 |
"learning_rate": 0.0006479711068621203,
|
| 798 |
"epoch": 4.168260038240918,
|
| 799 |
"step": 2180
|
| 800 |
},
|
| 801 |
{
|
| 802 |
+
"loss": 1.7702,
|
| 803 |
+
"grad_norm": 1.7719937562942505,
|
| 804 |
"learning_rate": 0.0006437221159974506,
|
| 805 |
"epoch": 4.2065009560229445,
|
| 806 |
"step": 2200
|
| 807 |
},
|
| 808 |
{
|
| 809 |
+
"loss": 1.7546,
|
| 810 |
+
"grad_norm": 1.7680734395980835,
|
| 811 |
"learning_rate": 0.000639473125132781,
|
| 812 |
"epoch": 4.244741873804971,
|
| 813 |
"step": 2220
|
| 814 |
},
|
| 815 |
{
|
| 816 |
+
"loss": 1.6716,
|
| 817 |
+
"grad_norm": 1.7028470039367676,
|
| 818 |
"learning_rate": 0.0006352241342681113,
|
| 819 |
"epoch": 4.282982791586998,
|
| 820 |
"step": 2240
|
| 821 |
},
|
| 822 |
{
|
| 823 |
+
"loss": 1.7316,
|
| 824 |
+
"grad_norm": 1.764496922492981,
|
| 825 |
"learning_rate": 0.0006309751434034417,
|
| 826 |
"epoch": 4.321223709369025,
|
| 827 |
"step": 2260
|
| 828 |
},
|
| 829 |
{
|
| 830 |
+
"loss": 1.6865,
|
| 831 |
+
"grad_norm": 1.7339156866073608,
|
| 832 |
"learning_rate": 0.0006267261525387721,
|
| 833 |
"epoch": 4.359464627151052,
|
| 834 |
"step": 2280
|
| 835 |
},
|
| 836 |
{
|
| 837 |
+
"loss": 1.6711,
|
| 838 |
+
"grad_norm": 1.6657025814056396,
|
| 839 |
"learning_rate": 0.0006224771616741024,
|
| 840 |
"epoch": 4.397705544933078,
|
| 841 |
"step": 2300
|
| 842 |
},
|
| 843 |
{
|
| 844 |
+
"loss": 1.7128,
|
| 845 |
+
"grad_norm": 1.8127187490463257,
|
| 846 |
"learning_rate": 0.0006182281708094328,
|
| 847 |
"epoch": 4.435946462715105,
|
| 848 |
"step": 2320
|
| 849 |
},
|
| 850 |
{
|
| 851 |
+
"loss": 1.6676,
|
| 852 |
+
"grad_norm": 1.720580816268921,
|
| 853 |
"learning_rate": 0.0006139791799447631,
|
| 854 |
"epoch": 4.474187380497132,
|
| 855 |
"step": 2340
|
| 856 |
},
|
| 857 |
{
|
| 858 |
+
"loss": 1.6651,
|
| 859 |
+
"grad_norm": 1.7044484615325928,
|
| 860 |
"learning_rate": 0.0006097301890800934,
|
| 861 |
"epoch": 4.512428298279159,
|
| 862 |
"step": 2360
|
| 863 |
},
|
| 864 |
{
|
| 865 |
+
"loss": 1.6743,
|
| 866 |
+
"grad_norm": 1.824859857559204,
|
| 867 |
"learning_rate": 0.0006054811982154238,
|
| 868 |
"epoch": 4.550669216061186,
|
| 869 |
"step": 2380
|
| 870 |
},
|
| 871 |
{
|
| 872 |
+
"loss": 1.6765,
|
| 873 |
+
"grad_norm": 1.847652554512024,
|
| 874 |
"learning_rate": 0.0006012322073507542,
|
| 875 |
"epoch": 4.588910133843212,
|
| 876 |
"step": 2400
|
| 877 |
},
|
| 878 |
{
|
| 879 |
+
"loss": 1.6257,
|
| 880 |
+
"grad_norm": 1.6747491359710693,
|
| 881 |
"learning_rate": 0.0005969832164860845,
|
| 882 |
"epoch": 4.627151051625239,
|
| 883 |
"step": 2420
|
| 884 |
},
|
| 885 |
{
|
| 886 |
+
"loss": 1.6515,
|
| 887 |
+
"grad_norm": 1.7143758535385132,
|
| 888 |
"learning_rate": 0.0005927342256214149,
|
| 889 |
"epoch": 4.665391969407266,
|
| 890 |
"step": 2440
|
| 891 |
},
|
| 892 |
{
|
| 893 |
+
"loss": 1.6384,
|
| 894 |
+
"grad_norm": 1.7966911792755127,
|
| 895 |
"learning_rate": 0.0005884852347567453,
|
| 896 |
"epoch": 4.7036328871892925,
|
| 897 |
"step": 2460
|
| 898 |
},
|
| 899 |
{
|
| 900 |
+
"loss": 1.5939,
|
| 901 |
+
"grad_norm": 1.6942733526229858,
|
| 902 |
"learning_rate": 0.0005842362438920756,
|
| 903 |
"epoch": 4.741873804971319,
|
| 904 |
"step": 2480
|
| 905 |
},
|
| 906 |
{
|
| 907 |
+
"loss": 1.5908,
|
| 908 |
+
"grad_norm": 1.7530827522277832,
|
| 909 |
"learning_rate": 0.000579987253027406,
|
| 910 |
"epoch": 4.780114722753346,
|
| 911 |
"step": 2500
|
| 912 |
},
|
| 913 |
{
|
| 914 |
+
"loss": 1.5586,
|
| 915 |
+
"grad_norm": 1.845311164855957,
|
| 916 |
"learning_rate": 0.0005757382621627364,
|
| 917 |
"epoch": 4.818355640535373,
|
| 918 |
"step": 2520
|
| 919 |
},
|
| 920 |
{
|
| 921 |
+
"loss": 1.5561,
|
| 922 |
+
"grad_norm": 1.7648016214370728,
|
| 923 |
"learning_rate": 0.0005714892712980667,
|
| 924 |
"epoch": 4.8565965583174,
|
| 925 |
"step": 2540
|
| 926 |
},
|
| 927 |
{
|
| 928 |
+
"loss": 1.5641,
|
| 929 |
+
"grad_norm": 1.6392900943756104,
|
| 930 |
"learning_rate": 0.000567240280433397,
|
| 931 |
"epoch": 4.894837476099426,
|
| 932 |
"step": 2560
|
| 933 |
},
|
| 934 |
{
|
| 935 |
+
"loss": 1.5443,
|
| 936 |
+
"grad_norm": 1.6668881177902222,
|
| 937 |
"learning_rate": 0.0005629912895687275,
|
| 938 |
"epoch": 4.933078393881453,
|
| 939 |
"step": 2580
|
| 940 |
},
|
| 941 |
{
|
| 942 |
+
"loss": 1.5637,
|
| 943 |
+
"grad_norm": 1.8424748182296753,
|
| 944 |
"learning_rate": 0.0005587422987040578,
|
| 945 |
"epoch": 4.97131931166348,
|
| 946 |
"step": 2600
|
| 947 |
},
|
| 948 |
{
|
| 949 |
+
"eval_loss": 0.7047534584999084,
|
| 950 |
+
"eval_accuracy": 0.8490413723511604,
|
| 951 |
+
"eval_runtime": 7835.8179,
|
| 952 |
+
"eval_samples_per_second": 1.897,
|
| 953 |
+
"eval_steps_per_second": 1.897,
|
| 954 |
"epoch": 5.0,
|
| 955 |
"step": 2615
|
| 956 |
},
|
| 957 |
{
|
| 958 |
+
"loss": 1.4799,
|
| 959 |
+
"grad_norm": 1.8417068719863892,
|
| 960 |
"learning_rate": 0.0005544933078393881,
|
| 961 |
"epoch": 5.009560229445507,
|
| 962 |
"step": 2620
|
| 963 |
},
|
| 964 |
{
|
| 965 |
+
"loss": 1.4184,
|
| 966 |
+
"grad_norm": 1.6466395854949951,
|
| 967 |
"learning_rate": 0.0005502443169747186,
|
| 968 |
"epoch": 5.047801147227533,
|
| 969 |
"step": 2640
|
| 970 |
},
|
| 971 |
{
|
| 972 |
+
"loss": 1.4507,
|
| 973 |
+
"grad_norm": 1.7499247789382935,
|
| 974 |
"learning_rate": 0.0005459953261100489,
|
| 975 |
"epoch": 5.08604206500956,
|
| 976 |
"step": 2660
|
| 977 |
},
|
| 978 |
{
|
| 979 |
+
"loss": 1.405,
|
| 980 |
+
"grad_norm": 1.7968547344207764,
|
| 981 |
"learning_rate": 0.0005417463352453792,
|
| 982 |
"epoch": 5.124282982791587,
|
| 983 |
"step": 2680
|
| 984 |
},
|
| 985 |
{
|
| 986 |
+
"loss": 1.4362,
|
| 987 |
+
"grad_norm": 1.7950819730758667,
|
| 988 |
"learning_rate": 0.0005374973443807097,
|
| 989 |
"epoch": 5.162523900573614,
|
| 990 |
"step": 2700
|
| 991 |
},
|
| 992 |
{
|
| 993 |
+
"loss": 1.4238,
|
| 994 |
+
"grad_norm": 1.745133399963379,
|
| 995 |
"learning_rate": 0.00053324835351604,
|
| 996 |
"epoch": 5.2007648183556405,
|
| 997 |
"step": 2720
|
| 998 |
},
|
| 999 |
{
|
| 1000 |
+
"loss": 1.4025,
|
| 1001 |
+
"grad_norm": 1.7767413854599,
|
| 1002 |
"learning_rate": 0.0005289993626513702,
|
| 1003 |
"epoch": 5.239005736137667,
|
| 1004 |
"step": 2740
|
| 1005 |
},
|
| 1006 |
{
|
| 1007 |
+
"loss": 1.4144,
|
| 1008 |
+
"grad_norm": 1.7297043800354004,
|
| 1009 |
"learning_rate": 0.0005247503717867008,
|
| 1010 |
"epoch": 5.277246653919694,
|
| 1011 |
"step": 2760
|
| 1012 |
},
|
| 1013 |
{
|
| 1014 |
+
"loss": 1.4071,
|
| 1015 |
+
"grad_norm": 1.8174902200698853,
|
| 1016 |
"learning_rate": 0.000520501380922031,
|
| 1017 |
"epoch": 5.315487571701721,
|
| 1018 |
"step": 2780
|
| 1019 |
},
|
| 1020 |
{
|
| 1021 |
+
"loss": 1.4022,
|
| 1022 |
+
"grad_norm": 1.6889333724975586,
|
| 1023 |
"learning_rate": 0.0005162523900573613,
|
| 1024 |
"epoch": 5.353728489483748,
|
| 1025 |
"step": 2800
|
| 1026 |
},
|
| 1027 |
{
|
| 1028 |
+
"loss": 1.3479,
|
| 1029 |
+
"grad_norm": 1.6331517696380615,
|
| 1030 |
"learning_rate": 0.0005120033991926918,
|
| 1031 |
"epoch": 5.3919694072657744,
|
| 1032 |
"step": 2820
|
| 1033 |
},
|
| 1034 |
{
|
| 1035 |
+
"loss": 1.362,
|
| 1036 |
+
"grad_norm": 1.8916860818862915,
|
| 1037 |
"learning_rate": 0.0005077544083280221,
|
| 1038 |
"epoch": 5.430210325047801,
|
| 1039 |
"step": 2840
|
| 1040 |
},
|
| 1041 |
{
|
| 1042 |
+
"loss": 1.3613,
|
| 1043 |
+
"grad_norm": 1.706222653388977,
|
| 1044 |
"learning_rate": 0.0005035054174633524,
|
| 1045 |
"epoch": 5.468451242829828,
|
| 1046 |
"step": 2860
|
| 1047 |
},
|
| 1048 |
{
|
| 1049 |
+
"loss": 1.3883,
|
| 1050 |
+
"grad_norm": 1.6761025190353394,
|
| 1051 |
"learning_rate": 0.0004992564265986828,
|
| 1052 |
"epoch": 5.506692160611855,
|
| 1053 |
"step": 2880
|
| 1054 |
},
|
| 1055 |
{
|
| 1056 |
+
"loss": 1.3432,
|
| 1057 |
+
"grad_norm": 1.632095217704773,
|
| 1058 |
"learning_rate": 0.0004950074357340132,
|
| 1059 |
"epoch": 5.544933078393882,
|
| 1060 |
"step": 2900
|
| 1061 |
},
|
| 1062 |
{
|
| 1063 |
+
"loss": 1.3417,
|
| 1064 |
+
"grad_norm": 1.6419159173965454,
|
| 1065 |
"learning_rate": 0.0004907584448693436,
|
| 1066 |
"epoch": 5.583173996175908,
|
| 1067 |
"step": 2920
|
| 1068 |
},
|
| 1069 |
{
|
| 1070 |
+
"loss": 1.341,
|
| 1071 |
+
"grad_norm": 1.8355722427368164,
|
| 1072 |
"learning_rate": 0.0004865094540046739,
|
| 1073 |
"epoch": 5.621414913957935,
|
| 1074 |
"step": 2940
|
| 1075 |
},
|
| 1076 |
{
|
| 1077 |
+
"loss": 1.339,
|
| 1078 |
+
"grad_norm": 1.6611793041229248,
|
| 1079 |
"learning_rate": 0.00048226046314000425,
|
| 1080 |
"epoch": 5.659655831739962,
|
| 1081 |
"step": 2960
|
| 1082 |
},
|
| 1083 |
{
|
| 1084 |
+
"loss": 1.3183,
|
| 1085 |
+
"grad_norm": 1.7696843147277832,
|
| 1086 |
"learning_rate": 0.0004780114722753346,
|
| 1087 |
"epoch": 5.6978967495219885,
|
| 1088 |
"step": 2980
|
| 1089 |
},
|
| 1090 |
{
|
| 1091 |
+
"loss": 1.3365,
|
| 1092 |
+
"grad_norm": 1.6689785718917847,
|
| 1093 |
"learning_rate": 0.000473762481410665,
|
| 1094 |
"epoch": 5.736137667304015,
|
| 1095 |
"step": 3000
|
| 1096 |
},
|
| 1097 |
{
|
| 1098 |
+
"loss": 1.2966,
|
| 1099 |
+
"grad_norm": 1.6962292194366455,
|
| 1100 |
"learning_rate": 0.00046951349054599533,
|
| 1101 |
"epoch": 5.774378585086042,
|
| 1102 |
"step": 3020
|
| 1103 |
},
|
| 1104 |
{
|
| 1105 |
+
"loss": 1.274,
|
| 1106 |
+
"grad_norm": 1.7446441650390625,
|
| 1107 |
"learning_rate": 0.0004652644996813257,
|
| 1108 |
"epoch": 5.812619502868069,
|
| 1109 |
"step": 3040
|
| 1110 |
},
|
| 1111 |
{
|
| 1112 |
+
"loss": 1.3145,
|
| 1113 |
+
"grad_norm": 1.7083852291107178,
|
| 1114 |
"learning_rate": 0.0004610155088166561,
|
| 1115 |
"epoch": 5.850860420650095,
|
| 1116 |
"step": 3060
|
| 1117 |
},
|
| 1118 |
{
|
| 1119 |
+
"loss": 1.2944,
|
| 1120 |
+
"grad_norm": 1.6674286127090454,
|
| 1121 |
"learning_rate": 0.0004567665179519864,
|
| 1122 |
"epoch": 5.8891013384321225,
|
| 1123 |
"step": 3080
|
| 1124 |
},
|
| 1125 |
{
|
| 1126 |
+
"loss": 1.2772,
|
| 1127 |
+
"grad_norm": 1.5787798166275024,
|
| 1128 |
"learning_rate": 0.00045251752708731676,
|
| 1129 |
"epoch": 5.927342256214149,
|
| 1130 |
"step": 3100
|
| 1131 |
},
|
| 1132 |
{
|
| 1133 |
+
"loss": 1.265,
|
| 1134 |
+
"grad_norm": 1.6089515686035156,
|
| 1135 |
"learning_rate": 0.0004482685362226471,
|
| 1136 |
"epoch": 5.965583173996176,
|
| 1137 |
"step": 3120
|
| 1138 |
},
|
| 1139 |
{
|
| 1140 |
+
"eval_loss": 0.5389042496681213,
|
| 1141 |
+
"eval_accuracy": 0.886242852337706,
|
| 1142 |
+
"eval_runtime": 383.2829,
|
| 1143 |
+
"eval_samples_per_second": 38.783,
|
| 1144 |
+
"eval_steps_per_second": 38.783,
|
| 1145 |
"epoch": 6.0,
|
| 1146 |
"step": 3138
|
| 1147 |
},
|
| 1148 |
{
|
| 1149 |
+
"loss": 1.2601,
|
| 1150 |
+
"grad_norm": 1.5683554410934448,
|
| 1151 |
"learning_rate": 0.0004440195453579775,
|
| 1152 |
"epoch": 6.003824091778203,
|
| 1153 |
"step": 3140
|
| 1154 |
},
|
| 1155 |
{
|
| 1156 |
+
"loss": 1.2067,
|
| 1157 |
+
"grad_norm": 1.6791157722473145,
|
| 1158 |
"learning_rate": 0.00043977055449330785,
|
| 1159 |
"epoch": 6.042065009560229,
|
| 1160 |
"step": 3160
|
| 1161 |
},
|
| 1162 |
{
|
| 1163 |
+
"loss": 1.1818,
|
| 1164 |
+
"grad_norm": 1.5930650234222412,
|
| 1165 |
"learning_rate": 0.0004355215636286382,
|
| 1166 |
"epoch": 6.080305927342256,
|
| 1167 |
"step": 3180
|
| 1168 |
},
|
| 1169 |
{
|
| 1170 |
+
"loss": 1.1871,
|
| 1171 |
+
"grad_norm": 1.7136551141738892,
|
| 1172 |
"learning_rate": 0.0004312725727639686,
|
| 1173 |
"epoch": 6.118546845124283,
|
| 1174 |
"step": 3200
|
| 1175 |
},
|
| 1176 |
{
|
| 1177 |
+
"loss": 1.1851,
|
| 1178 |
+
"grad_norm": 1.6400994062423706,
|
| 1179 |
"learning_rate": 0.0004270235818992989,
|
| 1180 |
"epoch": 6.15678776290631,
|
| 1181 |
"step": 3220
|
| 1182 |
},
|
| 1183 |
{
|
| 1184 |
+
"loss": 1.1798,
|
| 1185 |
+
"grad_norm": 1.722548246383667,
|
| 1186 |
"learning_rate": 0.0004227745910346293,
|
| 1187 |
"epoch": 6.195028680688337,
|
| 1188 |
"step": 3240
|
| 1189 |
},
|
| 1190 |
{
|
| 1191 |
+
"loss": 1.1516,
|
| 1192 |
+
"grad_norm": 1.600697636604309,
|
| 1193 |
"learning_rate": 0.0004185256001699597,
|
| 1194 |
"epoch": 6.233269598470363,
|
| 1195 |
"step": 3260
|
| 1196 |
},
|
| 1197 |
{
|
| 1198 |
+
"loss": 1.176,
|
| 1199 |
+
"grad_norm": 1.6722103357315063,
|
| 1200 |
"learning_rate": 0.00041427660930528997,
|
| 1201 |
"epoch": 6.27151051625239,
|
| 1202 |
"step": 3280
|
| 1203 |
},
|
| 1204 |
{
|
| 1205 |
+
"loss": 1.1625,
|
| 1206 |
+
"grad_norm": 1.5297291278839111,
|
| 1207 |
"learning_rate": 0.00041002761844062037,
|
| 1208 |
"epoch": 6.309751434034417,
|
| 1209 |
"step": 3300
|
| 1210 |
},
|
| 1211 |
{
|
| 1212 |
+
"loss": 1.1744,
|
| 1213 |
+
"grad_norm": 1.6687546968460083,
|
| 1214 |
"learning_rate": 0.00040577862757595076,
|
| 1215 |
"epoch": 6.347992351816444,
|
| 1216 |
"step": 3320
|
| 1217 |
},
|
| 1218 |
{
|
| 1219 |
+
"loss": 1.1408,
|
| 1220 |
+
"grad_norm": 1.6758590936660767,
|
| 1221 |
"learning_rate": 0.00040152963671128105,
|
| 1222 |
"epoch": 6.3862332695984705,
|
| 1223 |
"step": 3340
|
| 1224 |
},
|
| 1225 |
{
|
| 1226 |
+
"loss": 1.1458,
|
| 1227 |
+
"grad_norm": 1.7506797313690186,
|
| 1228 |
"learning_rate": 0.00039728064584661145,
|
| 1229 |
"epoch": 6.424474187380497,
|
| 1230 |
"step": 3360
|
| 1231 |
},
|
| 1232 |
{
|
| 1233 |
+
"loss": 1.1579,
|
| 1234 |
+
"grad_norm": 1.7690140008926392,
|
| 1235 |
"learning_rate": 0.0003930316549819418,
|
| 1236 |
"epoch": 6.462715105162524,
|
| 1237 |
"step": 3380
|
| 1238 |
},
|
| 1239 |
{
|
| 1240 |
+
"loss": 1.1444,
|
| 1241 |
+
"grad_norm": 1.7732901573181152,
|
| 1242 |
"learning_rate": 0.00038878266411727214,
|
| 1243 |
"epoch": 6.500956022944551,
|
| 1244 |
"step": 3400
|
| 1245 |
},
|
| 1246 |
{
|
| 1247 |
+
"loss": 1.1431,
|
| 1248 |
+
"grad_norm": 1.7551547288894653,
|
| 1249 |
"learning_rate": 0.00038453367325260254,
|
| 1250 |
"epoch": 6.539196940726577,
|
| 1251 |
"step": 3420
|
| 1252 |
},
|
| 1253 |
{
|
| 1254 |
+
"loss": 1.1293,
|
| 1255 |
+
"grad_norm": 1.6275290250778198,
|
| 1256 |
"learning_rate": 0.0003802846823879329,
|
| 1257 |
"epoch": 6.577437858508604,
|
| 1258 |
"step": 3440
|
| 1259 |
},
|
| 1260 |
{
|
| 1261 |
+
"loss": 1.1418,
|
| 1262 |
+
"grad_norm": 1.769103765487671,
|
| 1263 |
"learning_rate": 0.0003760356915232632,
|
| 1264 |
"epoch": 6.615678776290631,
|
| 1265 |
"step": 3460
|
| 1266 |
},
|
| 1267 |
{
|
| 1268 |
+
"loss": 1.1305,
|
| 1269 |
+
"grad_norm": 1.7487330436706543,
|
| 1270 |
"learning_rate": 0.0003717867006585936,
|
| 1271 |
"epoch": 6.653919694072657,
|
| 1272 |
"step": 3480
|
| 1273 |
},
|
| 1274 |
{
|
| 1275 |
+
"loss": 1.0805,
|
| 1276 |
+
"grad_norm": 1.698512315750122,
|
| 1277 |
"learning_rate": 0.0003675377097939239,
|
| 1278 |
"epoch": 6.692160611854685,
|
| 1279 |
"step": 3500
|
| 1280 |
},
|
| 1281 |
{
|
| 1282 |
+
"loss": 1.0907,
|
| 1283 |
+
"grad_norm": 1.6636496782302856,
|
| 1284 |
"learning_rate": 0.0003632887189292543,
|
| 1285 |
"epoch": 6.730401529636711,
|
| 1286 |
"step": 3520
|
| 1287 |
},
|
| 1288 |
{
|
| 1289 |
+
"loss": 1.1399,
|
| 1290 |
+
"grad_norm": 1.577497959136963,
|
| 1291 |
"learning_rate": 0.00035903972806458466,
|
| 1292 |
"epoch": 6.768642447418738,
|
| 1293 |
"step": 3540
|
| 1294 |
},
|
| 1295 |
{
|
| 1296 |
+
"loss": 1.1206,
|
| 1297 |
+
"grad_norm": 1.7101361751556396,
|
| 1298 |
"learning_rate": 0.000354790737199915,
|
| 1299 |
"epoch": 6.806883365200765,
|
| 1300 |
"step": 3560
|
| 1301 |
},
|
| 1302 |
{
|
| 1303 |
+
"loss": 1.103,
|
| 1304 |
+
"grad_norm": 1.6473299264907837,
|
| 1305 |
"learning_rate": 0.0003505417463352454,
|
| 1306 |
"epoch": 6.845124282982791,
|
| 1307 |
"step": 3580
|
| 1308 |
},
|
| 1309 |
{
|
| 1310 |
+
"loss": 1.1088,
|
| 1311 |
+
"grad_norm": 1.6744282245635986,
|
| 1312 |
"learning_rate": 0.00034629275547057574,
|
| 1313 |
"epoch": 6.8833652007648185,
|
| 1314 |
"step": 3600
|
| 1315 |
},
|
| 1316 |
{
|
| 1317 |
+
"loss": 1.0857,
|
| 1318 |
+
"grad_norm": 1.67130708694458,
|
| 1319 |
"learning_rate": 0.0003420437646059061,
|
| 1320 |
"epoch": 6.921606118546845,
|
| 1321 |
"step": 3620
|
| 1322 |
},
|
| 1323 |
{
|
| 1324 |
"loss": 1.0912,
|
| 1325 |
+
"grad_norm": 1.6932523250579834,
|
| 1326 |
"learning_rate": 0.0003377947737412365,
|
| 1327 |
"epoch": 6.959847036328872,
|
| 1328 |
"step": 3640
|
| 1329 |
},
|
| 1330 |
{
|
| 1331 |
+
"loss": 1.0888,
|
| 1332 |
+
"grad_norm": 1.6580239534378052,
|
| 1333 |
"learning_rate": 0.00033354578287656683,
|
| 1334 |
"epoch": 6.998087954110899,
|
| 1335 |
"step": 3660
|
| 1336 |
},
|
| 1337 |
{
|
| 1338 |
+
"eval_loss": 0.4364229142665863,
|
| 1339 |
+
"eval_accuracy": 0.9101244534140599,
|
| 1340 |
+
"eval_runtime": 605.3795,
|
| 1341 |
+
"eval_samples_per_second": 24.555,
|
| 1342 |
+
"eval_steps_per_second": 24.555,
|
| 1343 |
"epoch": 7.0,
|
| 1344 |
"step": 3661
|
| 1345 |
},
|
| 1346 |
{
|
| 1347 |
+
"loss": 1.0123,
|
| 1348 |
+
"grad_norm": 1.5949829816818237,
|
| 1349 |
"learning_rate": 0.0003292967920118972,
|
| 1350 |
"epoch": 7.036328871892925,
|
| 1351 |
"step": 3680
|
| 1352 |
},
|
| 1353 |
{
|
| 1354 |
+
"loss": 1.0552,
|
| 1355 |
+
"grad_norm": 1.8134639263153076,
|
| 1356 |
"learning_rate": 0.0003250478011472275,
|
| 1357 |
"epoch": 7.074569789674952,
|
| 1358 |
"step": 3700
|
| 1359 |
},
|
| 1360 |
{
|
| 1361 |
+
"loss": 1.0142,
|
| 1362 |
+
"grad_norm": 1.6394524574279785,
|
| 1363 |
"learning_rate": 0.0003207988102825579,
|
| 1364 |
"epoch": 7.112810707456979,
|
| 1365 |
"step": 3720
|
| 1366 |
},
|
| 1367 |
{
|
| 1368 |
+
"loss": 1.0096,
|
| 1369 |
+
"grad_norm": 1.6918762922286987,
|
| 1370 |
"learning_rate": 0.00031654981941788826,
|
| 1371 |
"epoch": 7.151051625239006,
|
| 1372 |
"step": 3740
|
| 1373 |
},
|
| 1374 |
{
|
| 1375 |
+
"loss": 1.0203,
|
| 1376 |
+
"grad_norm": 1.673691987991333,
|
| 1377 |
"learning_rate": 0.0003123008285532186,
|
| 1378 |
"epoch": 7.189292543021033,
|
| 1379 |
"step": 3760
|
| 1380 |
},
|
| 1381 |
{
|
| 1382 |
+
"loss": 1.049,
|
| 1383 |
+
"grad_norm": 1.5526095628738403,
|
| 1384 |
"learning_rate": 0.000308051837688549,
|
| 1385 |
"epoch": 7.227533460803059,
|
| 1386 |
"step": 3780
|
| 1387 |
},
|
| 1388 |
{
|
| 1389 |
+
"loss": 1.0247,
|
| 1390 |
+
"grad_norm": 1.638197660446167,
|
| 1391 |
"learning_rate": 0.00030380284682387935,
|
| 1392 |
"epoch": 7.265774378585086,
|
| 1393 |
"step": 3800
|
| 1394 |
},
|
| 1395 |
{
|
| 1396 |
+
"loss": 0.9841,
|
| 1397 |
+
"grad_norm": 1.6690630912780762,
|
| 1398 |
"learning_rate": 0.0002995538559592097,
|
| 1399 |
"epoch": 7.304015296367113,
|
| 1400 |
"step": 3820
|
| 1401 |
},
|
| 1402 |
{
|
| 1403 |
+
"loss": 1.018,
|
| 1404 |
+
"grad_norm": 1.645591139793396,
|
| 1405 |
"learning_rate": 0.0002953048650945401,
|
| 1406 |
"epoch": 7.342256214149139,
|
| 1407 |
"step": 3840
|
| 1408 |
},
|
| 1409 |
{
|
| 1410 |
+
"loss": 0.9818,
|
| 1411 |
+
"grad_norm": 1.676079273223877,
|
| 1412 |
"learning_rate": 0.0002910558742298704,
|
| 1413 |
"epoch": 7.3804971319311665,
|
| 1414 |
"step": 3860
|
| 1415 |
},
|
| 1416 |
{
|
| 1417 |
+
"loss": 0.9795,
|
| 1418 |
+
"grad_norm": 1.6065680980682373,
|
| 1419 |
"learning_rate": 0.0002868068833652008,
|
| 1420 |
"epoch": 7.418738049713193,
|
| 1421 |
"step": 3880
|
| 1422 |
},
|
| 1423 |
{
|
| 1424 |
+
"loss": 0.9588,
|
| 1425 |
+
"grad_norm": 1.683929443359375,
|
| 1426 |
"learning_rate": 0.0002825578925005312,
|
| 1427 |
"epoch": 7.45697896749522,
|
| 1428 |
"step": 3900
|
| 1429 |
},
|
| 1430 |
{
|
| 1431 |
+
"loss": 1.0081,
|
| 1432 |
+
"grad_norm": 1.6200690269470215,
|
| 1433 |
"learning_rate": 0.00027830890163586146,
|
| 1434 |
"epoch": 7.495219885277247,
|
| 1435 |
"step": 3920
|
| 1436 |
},
|
| 1437 |
{
|
| 1438 |
+
"loss": 0.9822,
|
| 1439 |
+
"grad_norm": 1.7147966623306274,
|
| 1440 |
"learning_rate": 0.00027405991077119186,
|
| 1441 |
"epoch": 7.533460803059273,
|
| 1442 |
"step": 3940
|
| 1443 |
},
|
| 1444 |
{
|
| 1445 |
+
"loss": 0.988,
|
| 1446 |
+
"grad_norm": 1.7224268913269043,
|
| 1447 |
"learning_rate": 0.00026981091990652226,
|
| 1448 |
"epoch": 7.5717017208413,
|
| 1449 |
"step": 3960
|
| 1450 |
},
|
| 1451 |
{
|
| 1452 |
+
"loss": 0.9562,
|
| 1453 |
+
"grad_norm": 1.7145981788635254,
|
| 1454 |
"learning_rate": 0.00026556192904185255,
|
| 1455 |
"epoch": 7.609942638623327,
|
| 1456 |
"step": 3980
|
| 1457 |
},
|
| 1458 |
{
|
| 1459 |
+
"loss": 0.9644,
|
| 1460 |
+
"grad_norm": 1.8020603656768799,
|
| 1461 |
"learning_rate": 0.00026131293817718295,
|
| 1462 |
"epoch": 7.648183556405353,
|
| 1463 |
"step": 4000
|
| 1464 |
},
|
| 1465 |
{
|
| 1466 |
+
"loss": 0.9648,
|
| 1467 |
+
"grad_norm": 1.7413355112075806,
|
| 1468 |
"learning_rate": 0.00025706394731251324,
|
| 1469 |
"epoch": 7.686424474187381,
|
| 1470 |
"step": 4020
|
| 1471 |
},
|
| 1472 |
{
|
| 1473 |
+
"loss": 0.9244,
|
| 1474 |
+
"grad_norm": 1.6813682317733765,
|
| 1475 |
"learning_rate": 0.00025281495644784364,
|
| 1476 |
"epoch": 7.724665391969407,
|
| 1477 |
"step": 4040
|
| 1478 |
},
|
| 1479 |
{
|
| 1480 |
+
"loss": 0.9217,
|
| 1481 |
+
"grad_norm": 1.747910737991333,
|
| 1482 |
"learning_rate": 0.00024856596558317403,
|
| 1483 |
"epoch": 7.762906309751434,
|
| 1484 |
"step": 4060
|
| 1485 |
},
|
| 1486 |
{
|
| 1487 |
+
"loss": 0.9628,
|
| 1488 |
+
"grad_norm": 1.6242161989212036,
|
| 1489 |
"learning_rate": 0.0002443169747185044,
|
| 1490 |
"epoch": 7.801147227533461,
|
| 1491 |
"step": 4080
|
| 1492 |
},
|
| 1493 |
{
|
| 1494 |
+
"loss": 0.979,
|
| 1495 |
+
"grad_norm": 1.5416340827941895,
|
| 1496 |
"learning_rate": 0.00024006798385383472,
|
| 1497 |
"epoch": 7.839388145315487,
|
| 1498 |
"step": 4100
|
| 1499 |
},
|
| 1500 |
{
|
| 1501 |
+
"loss": 0.9528,
|
| 1502 |
+
"grad_norm": 1.7438323497772217,
|
| 1503 |
"learning_rate": 0.00023581899298916507,
|
| 1504 |
"epoch": 7.8776290630975145,
|
| 1505 |
"step": 4120
|
| 1506 |
},
|
| 1507 |
{
|
| 1508 |
+
"loss": 0.91,
|
| 1509 |
+
"grad_norm": 1.6303768157958984,
|
| 1510 |
"learning_rate": 0.00023157000212449544,
|
| 1511 |
"epoch": 7.915869980879541,
|
| 1512 |
"step": 4140
|
| 1513 |
},
|
| 1514 |
{
|
| 1515 |
+
"loss": 0.9346,
|
| 1516 |
+
"grad_norm": 1.586729884147644,
|
| 1517 |
"learning_rate": 0.00022732101125982578,
|
| 1518 |
"epoch": 7.954110898661568,
|
| 1519 |
"step": 4160
|
| 1520 |
},
|
| 1521 |
{
|
| 1522 |
+
"loss": 0.9296,
|
| 1523 |
+
"grad_norm": 1.771173357963562,
|
| 1524 |
"learning_rate": 0.00022307202039515615,
|
| 1525 |
"epoch": 7.992351816443595,
|
| 1526 |
"step": 4180
|
| 1527 |
},
|
| 1528 |
{
|
| 1529 |
+
"eval_loss": 0.36169418692588806,
|
| 1530 |
+
"eval_accuracy": 0.9264715775311133,
|
| 1531 |
+
"eval_runtime": 57.1398,
|
| 1532 |
+
"eval_samples_per_second": 260.152,
|
| 1533 |
+
"eval_steps_per_second": 260.152,
|
| 1534 |
"epoch": 8.0,
|
| 1535 |
"step": 4184
|
| 1536 |
},
|
| 1537 |
{
|
| 1538 |
+
"loss": 0.9005,
|
| 1539 |
+
"grad_norm": 1.5647226572036743,
|
| 1540 |
"learning_rate": 0.00021882302953048652,
|
| 1541 |
"epoch": 8.030592734225621,
|
| 1542 |
"step": 4200
|
| 1543 |
},
|
| 1544 |
{
|
| 1545 |
+
"loss": 0.8696,
|
| 1546 |
+
"grad_norm": 1.6461886167526245,
|
| 1547 |
"learning_rate": 0.00021457403866581687,
|
| 1548 |
"epoch": 8.068833652007648,
|
| 1549 |
"step": 4220
|
| 1550 |
},
|
| 1551 |
{
|
| 1552 |
+
"loss": 0.8782,
|
| 1553 |
+
"grad_norm": 1.5358296632766724,
|
| 1554 |
"learning_rate": 0.0002103250478011472,
|
| 1555 |
"epoch": 8.107074569789676,
|
| 1556 |
"step": 4240
|
| 1557 |
},
|
| 1558 |
{
|
| 1559 |
+
"loss": 0.8483,
|
| 1560 |
+
"grad_norm": 1.6051462888717651,
|
| 1561 |
"learning_rate": 0.0002060760569364776,
|
| 1562 |
"epoch": 8.145315487571702,
|
| 1563 |
"step": 4260
|
| 1564 |
},
|
| 1565 |
{
|
| 1566 |
+
"loss": 0.8817,
|
| 1567 |
+
"grad_norm": 1.7184685468673706,
|
| 1568 |
"learning_rate": 0.00020182706607180795,
|
| 1569 |
"epoch": 8.183556405353729,
|
| 1570 |
"step": 4280
|
| 1571 |
},
|
| 1572 |
{
|
| 1573 |
+
"loss": 0.8603,
|
| 1574 |
+
"grad_norm": 1.6134257316589355,
|
| 1575 |
"learning_rate": 0.0001975780752071383,
|
| 1576 |
"epoch": 8.221797323135755,
|
| 1577 |
"step": 4300
|
| 1578 |
},
|
| 1579 |
{
|
| 1580 |
+
"loss": 0.8654,
|
| 1581 |
+
"grad_norm": 1.5783709287643433,
|
| 1582 |
"learning_rate": 0.00019332908434246867,
|
| 1583 |
"epoch": 8.260038240917781,
|
| 1584 |
"step": 4320
|
| 1585 |
},
|
| 1586 |
{
|
| 1587 |
+
"loss": 0.8554,
|
| 1588 |
+
"grad_norm": 1.4778318405151367,
|
| 1589 |
"learning_rate": 0.00018908009347779904,
|
| 1590 |
"epoch": 8.29827915869981,
|
| 1591 |
"step": 4340
|
| 1592 |
},
|
| 1593 |
{
|
| 1594 |
+
"loss": 0.8974,
|
| 1595 |
+
"grad_norm": 1.8124628067016602,
|
| 1596 |
"learning_rate": 0.00018483110261312938,
|
| 1597 |
"epoch": 8.336520076481836,
|
| 1598 |
"step": 4360
|
| 1599 |
},
|
| 1600 |
{
|
| 1601 |
+
"loss": 0.8716,
|
| 1602 |
+
"grad_norm": 1.7594116926193237,
|
| 1603 |
"learning_rate": 0.00018058211174845973,
|
| 1604 |
"epoch": 8.374760994263863,
|
| 1605 |
"step": 4380
|
| 1606 |
},
|
| 1607 |
{
|
| 1608 |
+
"loss": 0.8525,
|
| 1609 |
+
"grad_norm": 1.7039234638214111,
|
| 1610 |
"learning_rate": 0.0001763331208837901,
|
| 1611 |
"epoch": 8.413001912045889,
|
| 1612 |
"step": 4400
|
| 1613 |
},
|
| 1614 |
{
|
| 1615 |
+
"loss": 0.8663,
|
| 1616 |
+
"grad_norm": 1.6325209140777588,
|
| 1617 |
"learning_rate": 0.00017208413001912047,
|
| 1618 |
"epoch": 8.451242829827915,
|
| 1619 |
"step": 4420
|
| 1620 |
},
|
| 1621 |
{
|
| 1622 |
+
"loss": 0.8629,
|
| 1623 |
+
"grad_norm": 1.6818372011184692,
|
| 1624 |
"learning_rate": 0.00016783513915445082,
|
| 1625 |
"epoch": 8.489483747609942,
|
| 1626 |
"step": 4440
|
| 1627 |
},
|
| 1628 |
{
|
| 1629 |
+
"loss": 0.8718,
|
| 1630 |
+
"grad_norm": 1.5809085369110107,
|
| 1631 |
"learning_rate": 0.00016358614828978119,
|
| 1632 |
"epoch": 8.52772466539197,
|
| 1633 |
"step": 4460
|
| 1634 |
},
|
| 1635 |
{
|
| 1636 |
+
"loss": 0.8527,
|
| 1637 |
+
"grad_norm": 1.5711621046066284,
|
| 1638 |
"learning_rate": 0.00015933715742511153,
|
| 1639 |
"epoch": 8.565965583173996,
|
| 1640 |
"step": 4480
|
| 1641 |
},
|
| 1642 |
{
|
| 1643 |
+
"loss": 0.8589,
|
| 1644 |
+
"grad_norm": 1.5462543964385986,
|
| 1645 |
"learning_rate": 0.0001550881665604419,
|
| 1646 |
"epoch": 8.604206500956023,
|
| 1647 |
"step": 4500
|
| 1648 |
},
|
| 1649 |
{
|
| 1650 |
+
"loss": 0.8649,
|
| 1651 |
+
"grad_norm": 1.6341811418533325,
|
| 1652 |
"learning_rate": 0.00015083917569577227,
|
| 1653 |
"epoch": 8.64244741873805,
|
| 1654 |
"step": 4520
|
| 1655 |
},
|
| 1656 |
{
|
| 1657 |
+
"loss": 0.8192,
|
| 1658 |
+
"grad_norm": 1.5172038078308105,
|
| 1659 |
"learning_rate": 0.00014659018483110262,
|
| 1660 |
"epoch": 8.680688336520076,
|
| 1661 |
"step": 4540
|
| 1662 |
},
|
| 1663 |
{
|
| 1664 |
+
"loss": 0.8436,
|
| 1665 |
+
"grad_norm": 1.4799879789352417,
|
| 1666 |
"learning_rate": 0.00014234119396643296,
|
| 1667 |
"epoch": 8.718929254302104,
|
| 1668 |
"step": 4560
|
| 1669 |
},
|
| 1670 |
{
|
| 1671 |
+
"loss": 0.8292,
|
| 1672 |
+
"grad_norm": 1.547850251197815,
|
| 1673 |
"learning_rate": 0.00013809220310176336,
|
| 1674 |
"epoch": 8.75717017208413,
|
| 1675 |
"step": 4580
|
| 1676 |
},
|
| 1677 |
{
|
| 1678 |
+
"loss": 0.8527,
|
| 1679 |
+
"grad_norm": 1.8095018863677979,
|
| 1680 |
"learning_rate": 0.0001338432122370937,
|
| 1681 |
"epoch": 8.795411089866157,
|
| 1682 |
"step": 4600
|
| 1683 |
},
|
| 1684 |
{
|
| 1685 |
+
"loss": 0.8358,
|
| 1686 |
+
"grad_norm": 1.5578687191009521,
|
| 1687 |
"learning_rate": 0.00012959422137242405,
|
| 1688 |
"epoch": 8.833652007648183,
|
| 1689 |
"step": 4620
|
| 1690 |
},
|
| 1691 |
{
|
| 1692 |
+
"loss": 0.822,
|
| 1693 |
+
"grad_norm": 1.7008335590362549,
|
| 1694 |
"learning_rate": 0.0001253452305077544,
|
| 1695 |
"epoch": 8.87189292543021,
|
| 1696 |
"step": 4640
|
| 1697 |
},
|
| 1698 |
{
|
| 1699 |
+
"loss": 0.8352,
|
| 1700 |
+
"grad_norm": 1.6717548370361328,
|
| 1701 |
"learning_rate": 0.00012109623964308478,
|
| 1702 |
"epoch": 8.910133843212238,
|
| 1703 |
"step": 4660
|
| 1704 |
},
|
| 1705 |
{
|
| 1706 |
+
"loss": 0.826,
|
| 1707 |
+
"grad_norm": 1.729179859161377,
|
| 1708 |
"learning_rate": 0.00011684724877841513,
|
| 1709 |
"epoch": 8.948374760994264,
|
| 1710 |
"step": 4680
|
| 1711 |
},
|
| 1712 |
{
|
| 1713 |
+
"loss": 0.8066,
|
| 1714 |
+
"grad_norm": 1.6358789205551147,
|
| 1715 |
"learning_rate": 0.00011259825791374549,
|
| 1716 |
"epoch": 8.98661567877629,
|
| 1717 |
"step": 4700
|
| 1718 |
},
|
| 1719 |
{
|
| 1720 |
+
"eval_loss": 0.3206591010093689,
|
| 1721 |
"eval_accuracy": 0.9352842246888665,
|
| 1722 |
+
"eval_runtime": 381.3245,
|
| 1723 |
+
"eval_samples_per_second": 38.983,
|
| 1724 |
+
"eval_steps_per_second": 38.983,
|
| 1725 |
"epoch": 9.0,
|
| 1726 |
"step": 4707
|
| 1727 |
},
|
| 1728 |
{
|
| 1729 |
+
"loss": 0.8019,
|
| 1730 |
+
"grad_norm": 1.5783698558807373,
|
| 1731 |
"learning_rate": 0.00010834926704907585,
|
| 1732 |
"epoch": 9.024856596558317,
|
| 1733 |
"step": 4720
|
| 1734 |
},
|
| 1735 |
{
|
| 1736 |
+
"loss": 0.7702,
|
| 1737 |
+
"grad_norm": 1.5668120384216309,
|
| 1738 |
"learning_rate": 0.0001041002761844062,
|
| 1739 |
"epoch": 9.063097514340344,
|
| 1740 |
"step": 4740
|
| 1741 |
},
|
| 1742 |
{
|
| 1743 |
+
"loss": 0.7934,
|
| 1744 |
+
"grad_norm": 1.624084234237671,
|
| 1745 |
"learning_rate": 9.985128531973658e-05,
|
| 1746 |
"epoch": 9.101338432122372,
|
| 1747 |
"step": 4760
|
| 1748 |
},
|
| 1749 |
{
|
| 1750 |
+
"loss": 0.7863,
|
| 1751 |
+
"grad_norm": 1.5410951375961304,
|
| 1752 |
"learning_rate": 9.560229445506692e-05,
|
| 1753 |
"epoch": 9.139579349904398,
|
| 1754 |
"step": 4780
|
| 1755 |
},
|
| 1756 |
{
|
| 1757 |
+
"loss": 0.7894,
|
| 1758 |
+
"grad_norm": 1.663845419883728,
|
| 1759 |
"learning_rate": 9.135330359039729e-05,
|
| 1760 |
"epoch": 9.177820267686425,
|
| 1761 |
"step": 4800
|
| 1762 |
},
|
| 1763 |
{
|
| 1764 |
+
"loss": 0.739,
|
| 1765 |
+
"grad_norm": 1.5939579010009766,
|
| 1766 |
"learning_rate": 8.710431272572764e-05,
|
| 1767 |
"epoch": 9.216061185468451,
|
| 1768 |
"step": 4820
|
| 1769 |
},
|
| 1770 |
{
|
| 1771 |
+
"loss": 0.7808,
|
| 1772 |
+
"grad_norm": 1.5545909404754639,
|
| 1773 |
"learning_rate": 8.2855321861058e-05,
|
| 1774 |
"epoch": 9.254302103250478,
|
| 1775 |
"step": 4840
|
| 1776 |
},
|
| 1777 |
{
|
| 1778 |
+
"loss": 0.7761,
|
| 1779 |
+
"grad_norm": 1.665999412536621,
|
| 1780 |
"learning_rate": 7.860633099638836e-05,
|
| 1781 |
"epoch": 9.292543021032504,
|
| 1782 |
"step": 4860
|
| 1783 |
},
|
| 1784 |
{
|
| 1785 |
+
"loss": 0.7876,
|
| 1786 |
+
"grad_norm": 1.6480567455291748,
|
| 1787 |
"learning_rate": 7.435734013171871e-05,
|
| 1788 |
"epoch": 9.330783938814532,
|
| 1789 |
"step": 4880
|
| 1790 |
},
|
| 1791 |
{
|
| 1792 |
+
"loss": 0.767,
|
| 1793 |
+
"grad_norm": 1.5779589414596558,
|
| 1794 |
"learning_rate": 7.010834926704908e-05,
|
| 1795 |
"epoch": 9.369024856596559,
|
| 1796 |
"step": 4900
|
| 1797 |
},
|
| 1798 |
{
|
| 1799 |
+
"loss": 0.783,
|
| 1800 |
+
"grad_norm": 1.6985348463058472,
|
| 1801 |
"learning_rate": 6.585935840237942e-05,
|
| 1802 |
"epoch": 9.407265774378585,
|
| 1803 |
"step": 4920
|
| 1804 |
},
|
| 1805 |
{
|
| 1806 |
+
"loss": 0.756,
|
| 1807 |
+
"grad_norm": 1.5563093423843384,
|
| 1808 |
"learning_rate": 6.16103675377098e-05,
|
| 1809 |
"epoch": 9.445506692160611,
|
| 1810 |
"step": 4940
|
| 1811 |
},
|
| 1812 |
{
|
| 1813 |
+
"loss": 0.7682,
|
| 1814 |
+
"grad_norm": 1.6173079013824463,
|
| 1815 |
"learning_rate": 5.736137667304015e-05,
|
| 1816 |
"epoch": 9.483747609942638,
|
| 1817 |
"step": 4960
|
| 1818 |
},
|
| 1819 |
{
|
| 1820 |
+
"loss": 0.7632,
|
| 1821 |
+
"grad_norm": 1.5880271196365356,
|
| 1822 |
"learning_rate": 5.311238580837052e-05,
|
| 1823 |
"epoch": 9.521988527724666,
|
| 1824 |
"step": 4980
|
| 1825 |
},
|
| 1826 |
{
|
| 1827 |
+
"loss": 0.7602,
|
| 1828 |
+
"grad_norm": 1.6329987049102783,
|
| 1829 |
"learning_rate": 4.8863394943700874e-05,
|
| 1830 |
"epoch": 9.560229445506693,
|
| 1831 |
"step": 5000
|
| 1832 |
},
|
| 1833 |
{
|
| 1834 |
+
"loss": 0.7595,
|
| 1835 |
+
"grad_norm": 1.442744255065918,
|
| 1836 |
"learning_rate": 4.461440407903123e-05,
|
| 1837 |
"epoch": 9.598470363288719,
|
| 1838 |
"step": 5020
|
| 1839 |
},
|
| 1840 |
{
|
| 1841 |
+
"loss": 0.7621,
|
| 1842 |
+
"grad_norm": 1.5359572172164917,
|
| 1843 |
"learning_rate": 4.036541321436159e-05,
|
| 1844 |
"epoch": 9.636711281070745,
|
| 1845 |
"step": 5040
|
| 1846 |
},
|
| 1847 |
{
|
| 1848 |
+
"loss": 0.7717,
|
| 1849 |
+
"grad_norm": 1.6465296745300293,
|
| 1850 |
"learning_rate": 3.6116422349691954e-05,
|
| 1851 |
"epoch": 9.674952198852772,
|
| 1852 |
"step": 5060
|
| 1853 |
},
|
| 1854 |
{
|
| 1855 |
+
"loss": 0.73,
|
| 1856 |
+
"grad_norm": 1.6590745449066162,
|
| 1857 |
"learning_rate": 3.186743148502231e-05,
|
| 1858 |
"epoch": 9.7131931166348,
|
| 1859 |
"step": 5080
|
| 1860 |
},
|
| 1861 |
{
|
| 1862 |
+
"loss": 0.7486,
|
| 1863 |
+
"grad_norm": 1.5176348686218262,
|
| 1864 |
"learning_rate": 2.7618440620352666e-05,
|
| 1865 |
"epoch": 9.751434034416826,
|
| 1866 |
"step": 5100
|
| 1867 |
},
|
| 1868 |
{
|
| 1869 |
+
"loss": 0.7766,
|
| 1870 |
+
"grad_norm": 1.7158029079437256,
|
| 1871 |
"learning_rate": 2.3369449755683023e-05,
|
| 1872 |
"epoch": 9.789674952198853,
|
| 1873 |
"step": 5120
|
| 1874 |
},
|
| 1875 |
{
|
| 1876 |
+
"loss": 0.7159,
|
| 1877 |
+
"grad_norm": 1.6565515995025635,
|
| 1878 |
"learning_rate": 1.9120458891013384e-05,
|
| 1879 |
"epoch": 9.82791586998088,
|
| 1880 |
"step": 5140
|
| 1881 |
},
|
| 1882 |
{
|
| 1883 |
+
"loss": 0.7304,
|
| 1884 |
+
"grad_norm": 1.4815343618392944,
|
| 1885 |
"learning_rate": 1.4871468026343743e-05,
|
| 1886 |
"epoch": 9.866156787762906,
|
| 1887 |
"step": 5160
|
| 1888 |
},
|
| 1889 |
{
|
| 1890 |
+
"loss": 0.744,
|
| 1891 |
+
"grad_norm": 1.6041672229766846,
|
| 1892 |
"learning_rate": 1.0622477161674103e-05,
|
| 1893 |
"epoch": 9.904397705544934,
|
| 1894 |
"step": 5180
|
| 1895 |
},
|
| 1896 |
{
|
| 1897 |
+
"loss": 0.7562,
|
| 1898 |
+
"grad_norm": 1.6224092245101929,
|
| 1899 |
"learning_rate": 6.373486297004461e-06,
|
| 1900 |
"epoch": 9.94263862332696,
|
| 1901 |
"step": 5200
|
| 1902 |
},
|
| 1903 |
{
|
| 1904 |
+
"loss": 0.7675,
|
| 1905 |
+
"grad_norm": 1.5392311811447144,
|
| 1906 |
"learning_rate": 2.1244954323348204e-06,
|
| 1907 |
"epoch": 9.980879541108987,
|
| 1908 |
"step": 5220
|
| 1909 |
},
|
| 1910 |
{
|
| 1911 |
+
"eval_loss": 0.29811325669288635,
|
| 1912 |
+
"eval_accuracy": 0.9405314497140935,
|
| 1913 |
+
"eval_runtime": 464.2204,
|
| 1914 |
+
"eval_samples_per_second": 32.021,
|
| 1915 |
+
"eval_steps_per_second": 32.021,
|
| 1916 |
"epoch": 10.0,
|
| 1917 |
"step": 5230
|
| 1918 |
},
|
| 1919 |
{
|
| 1920 |
+
"train_runtime": 50832.5393,
|
| 1921 |
+
"train_samples_per_second": 26.317,
|
| 1922 |
+
"train_steps_per_second": 0.103,
|
| 1923 |
"total_flos": 1.96318398191328e+18,
|
| 1924 |
+
"train_loss": 2.122584131525306,
|
| 1925 |
"epoch": 10.0,
|
| 1926 |
"step": 5230
|
| 1927 |
}
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 10.0,
|
| 3 |
"total_flos": 1.96318398191328e+18,
|
| 4 |
-
"train_loss": 2.
|
| 5 |
-
"train_runtime":
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second": 0.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 10.0,
|
| 3 |
"total_flos": 1.96318398191328e+18,
|
| 4 |
+
"train_loss": 2.122584131525306,
|
| 5 |
+
"train_runtime": 50832.5393,
|
| 6 |
+
"train_samples_per_second": 26.317,
|
| 7 |
+
"train_steps_per_second": 0.103
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
"best_model_checkpoint": "/mnt/data4_HDD_14TB/yang/voxceleb-checkpoints/xvector/voxceleb1/finetune/ce-len3-bs256-lr1e-3/checkpoint-5230",
|
| 4 |
"epoch": 10.0,
|
| 5 |
"eval_steps": 500,
|
|
@@ -10,1929 +10,1929 @@
|
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.03824091778202677,
|
| 13 |
-
"grad_norm": 4.
|
| 14 |
"learning_rate": 3.824091778202677e-05,
|
| 15 |
-
"loss": 7.
|
| 16 |
"step": 20
|
| 17 |
},
|
| 18 |
{
|
| 19 |
"epoch": 0.07648183556405354,
|
| 20 |
-
"grad_norm": 4.
|
| 21 |
"learning_rate": 7.648183556405354e-05,
|
| 22 |
-
"loss": 7.
|
| 23 |
"step": 40
|
| 24 |
},
|
| 25 |
{
|
| 26 |
"epoch": 0.1147227533460803,
|
| 27 |
-
"grad_norm": 3.
|
| 28 |
"learning_rate": 0.0001147227533460803,
|
| 29 |
-
"loss": 7.
|
| 30 |
"step": 60
|
| 31 |
},
|
| 32 |
{
|
| 33 |
"epoch": 0.15296367112810708,
|
| 34 |
-
"grad_norm": 3.
|
| 35 |
"learning_rate": 0.00015296367112810707,
|
| 36 |
-
"loss": 6.
|
| 37 |
"step": 80
|
| 38 |
},
|
| 39 |
{
|
| 40 |
"epoch": 0.19120458891013384,
|
| 41 |
-
"grad_norm": 2.
|
| 42 |
"learning_rate": 0.00019120458891013384,
|
| 43 |
-
"loss": 6.
|
| 44 |
"step": 100
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 0.2294455066921606,
|
| 48 |
-
"grad_norm": 2.
|
| 49 |
"learning_rate": 0.0002294455066921606,
|
| 50 |
-
"loss": 6.
|
| 51 |
"step": 120
|
| 52 |
},
|
| 53 |
{
|
| 54 |
"epoch": 0.2676864244741874,
|
| 55 |
-
"grad_norm":
|
| 56 |
"learning_rate": 0.0002676864244741874,
|
| 57 |
-
"loss": 6.
|
| 58 |
"step": 140
|
| 59 |
},
|
| 60 |
{
|
| 61 |
"epoch": 0.30592734225621415,
|
| 62 |
-
"grad_norm": 1.
|
| 63 |
"learning_rate": 0.00030592734225621415,
|
| 64 |
-
"loss": 6.
|
| 65 |
"step": 160
|
| 66 |
},
|
| 67 |
{
|
| 68 |
"epoch": 0.3441682600382409,
|
| 69 |
-
"grad_norm": 1.
|
| 70 |
"learning_rate": 0.00034416826003824094,
|
| 71 |
-
"loss": 6.
|
| 72 |
"step": 180
|
| 73 |
},
|
| 74 |
{
|
| 75 |
"epoch": 0.3824091778202677,
|
| 76 |
-
"grad_norm": 1.
|
| 77 |
"learning_rate": 0.0003824091778202677,
|
| 78 |
-
"loss": 6.
|
| 79 |
"step": 200
|
| 80 |
},
|
| 81 |
{
|
| 82 |
"epoch": 0.42065009560229444,
|
| 83 |
-
"grad_norm": 1.
|
| 84 |
"learning_rate": 0.0004206500956022944,
|
| 85 |
-
"loss": 5.
|
| 86 |
"step": 220
|
| 87 |
},
|
| 88 |
{
|
| 89 |
"epoch": 0.4588910133843212,
|
| 90 |
-
"grad_norm": 1.
|
| 91 |
"learning_rate": 0.0004588910133843212,
|
| 92 |
-
"loss": 5.
|
| 93 |
"step": 240
|
| 94 |
},
|
| 95 |
{
|
| 96 |
"epoch": 0.497131931166348,
|
| 97 |
-
"grad_norm": 1.
|
| 98 |
"learning_rate": 0.0004971319311663481,
|
| 99 |
-
"loss": 5.
|
| 100 |
"step": 260
|
| 101 |
},
|
| 102 |
{
|
| 103 |
"epoch": 0.5353728489483748,
|
| 104 |
-
"grad_norm": 1.
|
| 105 |
"learning_rate": 0.0005353728489483748,
|
| 106 |
-
"loss": 5.
|
| 107 |
"step": 280
|
| 108 |
},
|
| 109 |
{
|
| 110 |
"epoch": 0.5736137667304015,
|
| 111 |
-
"grad_norm": 1.
|
| 112 |
"learning_rate": 0.0005736137667304016,
|
| 113 |
-
"loss": 5.
|
| 114 |
"step": 300
|
| 115 |
},
|
| 116 |
{
|
| 117 |
"epoch": 0.6118546845124283,
|
| 118 |
-
"grad_norm": 1.
|
| 119 |
"learning_rate": 0.0006118546845124283,
|
| 120 |
-
"loss": 5.
|
| 121 |
"step": 320
|
| 122 |
},
|
| 123 |
{
|
| 124 |
"epoch": 0.6500956022944551,
|
| 125 |
-
"grad_norm": 1.
|
| 126 |
"learning_rate": 0.000650095602294455,
|
| 127 |
-
"loss": 5.
|
| 128 |
"step": 340
|
| 129 |
},
|
| 130 |
{
|
| 131 |
"epoch": 0.6883365200764818,
|
| 132 |
-
"grad_norm": 1.
|
| 133 |
"learning_rate": 0.0006883365200764819,
|
| 134 |
-
"loss": 5.
|
| 135 |
"step": 360
|
| 136 |
},
|
| 137 |
{
|
| 138 |
"epoch": 0.7265774378585086,
|
| 139 |
-
"grad_norm": 1.
|
| 140 |
"learning_rate": 0.0007265774378585086,
|
| 141 |
-
"loss": 5.
|
| 142 |
"step": 380
|
| 143 |
},
|
| 144 |
{
|
| 145 |
"epoch": 0.7648183556405354,
|
| 146 |
-
"grad_norm": 1.
|
| 147 |
"learning_rate": 0.0007648183556405354,
|
| 148 |
-
"loss": 5.
|
| 149 |
"step": 400
|
| 150 |
},
|
| 151 |
{
|
| 152 |
"epoch": 0.8030592734225621,
|
| 153 |
-
"grad_norm": 1.
|
| 154 |
"learning_rate": 0.0008030592734225621,
|
| 155 |
-
"loss": 5.
|
| 156 |
"step": 420
|
| 157 |
},
|
| 158 |
{
|
| 159 |
"epoch": 0.8413001912045889,
|
| 160 |
-
"grad_norm": 1.
|
| 161 |
"learning_rate": 0.0008413001912045888,
|
| 162 |
-
"loss": 4.
|
| 163 |
"step": 440
|
| 164 |
},
|
| 165 |
{
|
| 166 |
"epoch": 0.8795411089866156,
|
| 167 |
-
"grad_norm": 1.
|
| 168 |
"learning_rate": 0.0008795411089866157,
|
| 169 |
-
"loss": 4.
|
| 170 |
"step": 460
|
| 171 |
},
|
| 172 |
{
|
| 173 |
"epoch": 0.9177820267686424,
|
| 174 |
-
"grad_norm": 1.
|
| 175 |
"learning_rate": 0.0009177820267686424,
|
| 176 |
-
"loss": 4.
|
| 177 |
"step": 480
|
| 178 |
},
|
| 179 |
{
|
| 180 |
"epoch": 0.9560229445506692,
|
| 181 |
-
"grad_norm": 1.
|
| 182 |
"learning_rate": 0.0009560229445506692,
|
| 183 |
-
"loss": 4.
|
| 184 |
"step": 500
|
| 185 |
},
|
| 186 |
{
|
| 187 |
"epoch": 0.994263862332696,
|
| 188 |
-
"grad_norm": 1.
|
| 189 |
"learning_rate": 0.0009942638623326961,
|
| 190 |
-
"loss": 4.
|
| 191 |
"step": 520
|
| 192 |
},
|
| 193 |
{
|
| 194 |
"epoch": 1.0,
|
| 195 |
-
"eval_accuracy": 0.
|
| 196 |
-
"eval_loss": 4.
|
| 197 |
-
"eval_runtime":
|
| 198 |
-
"eval_samples_per_second":
|
| 199 |
-
"eval_steps_per_second":
|
| 200 |
"step": 523
|
| 201 |
},
|
| 202 |
{
|
| 203 |
"epoch": 1.0325047801147227,
|
| 204 |
-
"grad_norm": 1.
|
| 205 |
"learning_rate": 0.0009963883577650309,
|
| 206 |
-
"loss": 4.
|
| 207 |
"step": 540
|
| 208 |
},
|
| 209 |
{
|
| 210 |
"epoch": 1.0707456978967496,
|
| 211 |
-
"grad_norm": 1.
|
| 212 |
"learning_rate": 0.0009921393669003612,
|
| 213 |
-
"loss": 4.
|
| 214 |
"step": 560
|
| 215 |
},
|
| 216 |
{
|
| 217 |
"epoch": 1.1089866156787762,
|
| 218 |
-
"grad_norm": 1.
|
| 219 |
"learning_rate": 0.0009878903760356915,
|
| 220 |
-
"loss": 4.
|
| 221 |
"step": 580
|
| 222 |
},
|
| 223 |
{
|
| 224 |
"epoch": 1.147227533460803,
|
| 225 |
-
"grad_norm": 1.
|
| 226 |
"learning_rate": 0.0009836413851710218,
|
| 227 |
-
"loss": 4.
|
| 228 |
"step": 600
|
| 229 |
},
|
| 230 |
{
|
| 231 |
"epoch": 1.1854684512428297,
|
| 232 |
-
"grad_norm": 1.
|
| 233 |
"learning_rate": 0.0009793923943063523,
|
| 234 |
-
"loss": 4.
|
| 235 |
"step": 620
|
| 236 |
},
|
| 237 |
{
|
| 238 |
"epoch": 1.2237093690248566,
|
| 239 |
-
"grad_norm": 1.
|
| 240 |
"learning_rate": 0.0009751434034416827,
|
| 241 |
-
"loss": 4.
|
| 242 |
"step": 640
|
| 243 |
},
|
| 244 |
{
|
| 245 |
"epoch": 1.2619502868068833,
|
| 246 |
-
"grad_norm": 1.
|
| 247 |
"learning_rate": 0.000970894412577013,
|
| 248 |
-
"loss": 4.
|
| 249 |
"step": 660
|
| 250 |
},
|
| 251 |
{
|
| 252 |
"epoch": 1.3001912045889101,
|
| 253 |
-
"grad_norm": 1.
|
| 254 |
"learning_rate": 0.0009666454217123433,
|
| 255 |
-
"loss": 4.
|
| 256 |
"step": 680
|
| 257 |
},
|
| 258 |
{
|
| 259 |
"epoch": 1.338432122370937,
|
| 260 |
-
"grad_norm": 1.
|
| 261 |
"learning_rate": 0.0009623964308476737,
|
| 262 |
-
"loss": 4.
|
| 263 |
"step": 700
|
| 264 |
},
|
| 265 |
{
|
| 266 |
"epoch": 1.3766730401529637,
|
| 267 |
-
"grad_norm": 1.
|
| 268 |
"learning_rate": 0.000958147439983004,
|
| 269 |
-
"loss":
|
| 270 |
"step": 720
|
| 271 |
},
|
| 272 |
{
|
| 273 |
"epoch": 1.4149139579349903,
|
| 274 |
-
"grad_norm": 1.
|
| 275 |
"learning_rate": 0.0009538984491183344,
|
| 276 |
-
"loss": 3.
|
| 277 |
"step": 740
|
| 278 |
},
|
| 279 |
{
|
| 280 |
"epoch": 1.4531548757170172,
|
| 281 |
-
"grad_norm": 1.
|
| 282 |
"learning_rate": 0.0009496494582536647,
|
| 283 |
-
"loss": 3.
|
| 284 |
"step": 760
|
| 285 |
},
|
| 286 |
{
|
| 287 |
"epoch": 1.491395793499044,
|
| 288 |
-
"grad_norm": 1.
|
| 289 |
"learning_rate": 0.0009454004673889951,
|
| 290 |
-
"loss": 3.
|
| 291 |
"step": 780
|
| 292 |
},
|
| 293 |
{
|
| 294 |
"epoch": 1.5296367112810707,
|
| 295 |
-
"grad_norm": 1.
|
| 296 |
"learning_rate": 0.0009411514765243255,
|
| 297 |
-
"loss": 3.
|
| 298 |
"step": 800
|
| 299 |
},
|
| 300 |
{
|
| 301 |
"epoch": 1.5678776290630974,
|
| 302 |
-
"grad_norm": 1.
|
| 303 |
"learning_rate": 0.0009369024856596558,
|
| 304 |
-
"loss": 3.
|
| 305 |
"step": 820
|
| 306 |
},
|
| 307 |
{
|
| 308 |
"epoch": 1.6061185468451242,
|
| 309 |
-
"grad_norm": 1.
|
| 310 |
"learning_rate": 0.0009326534947949862,
|
| 311 |
-
"loss": 3.
|
| 312 |
"step": 840
|
| 313 |
},
|
| 314 |
{
|
| 315 |
"epoch": 1.644359464627151,
|
| 316 |
-
"grad_norm": 1.
|
| 317 |
"learning_rate": 0.0009284045039303166,
|
| 318 |
-
"loss": 3.
|
| 319 |
"step": 860
|
| 320 |
},
|
| 321 |
{
|
| 322 |
"epoch": 1.682600382409178,
|
| 323 |
-
"grad_norm": 1.
|
| 324 |
"learning_rate": 0.0009241555130656469,
|
| 325 |
-
"loss": 3.
|
| 326 |
"step": 880
|
| 327 |
},
|
| 328 |
{
|
| 329 |
"epoch": 1.7208413001912046,
|
| 330 |
-
"grad_norm": 1.
|
| 331 |
"learning_rate": 0.0009199065222009773,
|
| 332 |
-
"loss": 3.
|
| 333 |
"step": 900
|
| 334 |
},
|
| 335 |
{
|
| 336 |
"epoch": 1.7590822179732313,
|
| 337 |
-
"grad_norm": 1.
|
| 338 |
"learning_rate": 0.0009156575313363077,
|
| 339 |
-
"loss": 3.
|
| 340 |
"step": 920
|
| 341 |
},
|
| 342 |
{
|
| 343 |
"epoch": 1.7973231357552581,
|
| 344 |
-
"grad_norm": 1.
|
| 345 |
"learning_rate": 0.000911408540471638,
|
| 346 |
-
"loss": 3.
|
| 347 |
"step": 940
|
| 348 |
},
|
| 349 |
{
|
| 350 |
"epoch": 1.835564053537285,
|
| 351 |
-
"grad_norm": 1.
|
| 352 |
"learning_rate": 0.0009071595496069684,
|
| 353 |
-
"loss": 3.
|
| 354 |
"step": 960
|
| 355 |
},
|
| 356 |
{
|
| 357 |
"epoch": 1.8738049713193117,
|
| 358 |
-
"grad_norm": 1.
|
| 359 |
"learning_rate": 0.0009029105587422988,
|
| 360 |
-
"loss": 3.
|
| 361 |
"step": 980
|
| 362 |
},
|
| 363 |
{
|
| 364 |
"epoch": 1.9120458891013383,
|
| 365 |
-
"grad_norm": 1.
|
| 366 |
"learning_rate": 0.0008986615678776291,
|
| 367 |
-
"loss": 3.
|
| 368 |
"step": 1000
|
| 369 |
},
|
| 370 |
{
|
| 371 |
"epoch": 1.9502868068833652,
|
| 372 |
-
"grad_norm": 1.
|
| 373 |
"learning_rate": 0.0008944125770129595,
|
| 374 |
-
"loss": 3.
|
| 375 |
"step": 1020
|
| 376 |
},
|
| 377 |
{
|
| 378 |
"epoch": 1.988527724665392,
|
| 379 |
-
"grad_norm": 1.
|
| 380 |
"learning_rate": 0.0008901635861482899,
|
| 381 |
-
"loss": 3.
|
| 382 |
"step": 1040
|
| 383 |
},
|
| 384 |
{
|
| 385 |
"epoch": 2.0,
|
| 386 |
-
"eval_accuracy": 0.
|
| 387 |
-
"eval_loss": 2.
|
| 388 |
-
"eval_runtime":
|
| 389 |
-
"eval_samples_per_second":
|
| 390 |
-
"eval_steps_per_second":
|
| 391 |
"step": 1046
|
| 392 |
},
|
| 393 |
{
|
| 394 |
"epoch": 2.026768642447419,
|
| 395 |
-
"grad_norm": 1.
|
| 396 |
"learning_rate": 0.0008859145952836202,
|
| 397 |
-
"loss": 3.
|
| 398 |
"step": 1060
|
| 399 |
},
|
| 400 |
{
|
| 401 |
"epoch": 2.0650095602294454,
|
| 402 |
-
"grad_norm": 1.
|
| 403 |
"learning_rate": 0.0008816656044189504,
|
| 404 |
-
"loss": 3.
|
| 405 |
"step": 1080
|
| 406 |
},
|
| 407 |
{
|
| 408 |
"epoch": 2.1032504780114722,
|
| 409 |
-
"grad_norm": 1.
|
| 410 |
"learning_rate": 0.000877416613554281,
|
| 411 |
-
"loss": 3.
|
| 412 |
"step": 1100
|
| 413 |
},
|
| 414 |
{
|
| 415 |
"epoch": 2.141491395793499,
|
| 416 |
-
"grad_norm": 1.
|
| 417 |
"learning_rate": 0.0008731676226896112,
|
| 418 |
-
"loss": 2.
|
| 419 |
"step": 1120
|
| 420 |
},
|
| 421 |
{
|
| 422 |
"epoch": 2.179732313575526,
|
| 423 |
-
"grad_norm": 1.
|
| 424 |
"learning_rate": 0.0008689186318249415,
|
| 425 |
-
"loss": 2.
|
| 426 |
"step": 1140
|
| 427 |
},
|
| 428 |
{
|
| 429 |
"epoch": 2.2179732313575524,
|
| 430 |
-
"grad_norm": 1.
|
| 431 |
"learning_rate": 0.000864669640960272,
|
| 432 |
-
"loss": 2.
|
| 433 |
"step": 1160
|
| 434 |
},
|
| 435 |
{
|
| 436 |
"epoch": 2.2562141491395793,
|
| 437 |
-
"grad_norm": 1.
|
| 438 |
"learning_rate": 0.0008604206500956023,
|
| 439 |
-
"loss": 2.
|
| 440 |
"step": 1180
|
| 441 |
},
|
| 442 |
{
|
| 443 |
"epoch": 2.294455066921606,
|
| 444 |
-
"grad_norm": 1.
|
| 445 |
"learning_rate": 0.0008561716592309326,
|
| 446 |
-
"loss": 2.
|
| 447 |
"step": 1200
|
| 448 |
},
|
| 449 |
{
|
| 450 |
"epoch": 2.332695984703633,
|
| 451 |
-
"grad_norm": 1.
|
| 452 |
"learning_rate": 0.000851922668366263,
|
| 453 |
-
"loss": 2.
|
| 454 |
"step": 1220
|
| 455 |
},
|
| 456 |
{
|
| 457 |
"epoch": 2.3709369024856595,
|
| 458 |
-
"grad_norm": 1.
|
| 459 |
"learning_rate": 0.0008476736775015934,
|
| 460 |
-
"loss": 2.
|
| 461 |
"step": 1240
|
| 462 |
},
|
| 463 |
{
|
| 464 |
"epoch": 2.4091778202676863,
|
| 465 |
-
"grad_norm": 1.
|
| 466 |
"learning_rate": 0.0008434246866369237,
|
| 467 |
-
"loss": 2.
|
| 468 |
"step": 1260
|
| 469 |
},
|
| 470 |
{
|
| 471 |
"epoch": 2.447418738049713,
|
| 472 |
-
"grad_norm": 1.
|
| 473 |
"learning_rate": 0.0008391756957722541,
|
| 474 |
-
"loss": 2.
|
| 475 |
"step": 1280
|
| 476 |
},
|
| 477 |
{
|
| 478 |
"epoch": 2.48565965583174,
|
| 479 |
-
"grad_norm": 1.
|
| 480 |
"learning_rate": 0.0008349267049075845,
|
| 481 |
-
"loss": 2.
|
| 482 |
"step": 1300
|
| 483 |
},
|
| 484 |
{
|
| 485 |
"epoch": 2.5239005736137665,
|
| 486 |
-
"grad_norm": 1.
|
| 487 |
"learning_rate": 0.0008306777140429148,
|
| 488 |
-
"loss": 2.
|
| 489 |
"step": 1320
|
| 490 |
},
|
| 491 |
{
|
| 492 |
"epoch": 2.5621414913957934,
|
| 493 |
-
"grad_norm": 1.
|
| 494 |
"learning_rate": 0.0008264287231782451,
|
| 495 |
-
"loss": 2.
|
| 496 |
"step": 1340
|
| 497 |
},
|
| 498 |
{
|
| 499 |
"epoch": 2.6003824091778203,
|
| 500 |
-
"grad_norm": 1.
|
| 501 |
"learning_rate": 0.0008221797323135756,
|
| 502 |
-
"loss": 2.
|
| 503 |
"step": 1360
|
| 504 |
},
|
| 505 |
{
|
| 506 |
"epoch": 2.638623326959847,
|
| 507 |
-
"grad_norm": 1.
|
| 508 |
"learning_rate": 0.0008179307414489059,
|
| 509 |
-
"loss": 2.
|
| 510 |
"step": 1380
|
| 511 |
},
|
| 512 |
{
|
| 513 |
"epoch": 2.676864244741874,
|
| 514 |
-
"grad_norm": 1.
|
| 515 |
"learning_rate": 0.0008136817505842362,
|
| 516 |
-
"loss": 2.
|
| 517 |
"step": 1400
|
| 518 |
},
|
| 519 |
{
|
| 520 |
"epoch": 2.7151051625239004,
|
| 521 |
-
"grad_norm": 1.
|
| 522 |
"learning_rate": 0.0008094327597195667,
|
| 523 |
-
"loss": 2.
|
| 524 |
"step": 1420
|
| 525 |
},
|
| 526 |
{
|
| 527 |
"epoch": 2.7533460803059273,
|
| 528 |
-
"grad_norm": 1.
|
| 529 |
"learning_rate": 0.000805183768854897,
|
| 530 |
-
"loss": 2.
|
| 531 |
"step": 1440
|
| 532 |
},
|
| 533 |
{
|
| 534 |
"epoch": 2.791586998087954,
|
| 535 |
-
"grad_norm": 1.
|
| 536 |
"learning_rate": 0.0008009347779902273,
|
| 537 |
-
"loss": 2.
|
| 538 |
"step": 1460
|
| 539 |
},
|
| 540 |
{
|
| 541 |
"epoch": 2.8298279158699806,
|
| 542 |
-
"grad_norm": 1.
|
| 543 |
"learning_rate": 0.0007966857871255578,
|
| 544 |
-
"loss": 2.
|
| 545 |
"step": 1480
|
| 546 |
},
|
| 547 |
{
|
| 548 |
"epoch": 2.8680688336520075,
|
| 549 |
-
"grad_norm": 1.
|
| 550 |
"learning_rate": 0.000792436796260888,
|
| 551 |
-
"loss": 2.
|
| 552 |
"step": 1500
|
| 553 |
},
|
| 554 |
{
|
| 555 |
"epoch": 2.9063097514340344,
|
| 556 |
-
"grad_norm": 1.
|
| 557 |
"learning_rate": 0.0007881878053962183,
|
| 558 |
-
"loss": 2.
|
| 559 |
"step": 1520
|
| 560 |
},
|
| 561 |
{
|
| 562 |
"epoch": 2.9445506692160612,
|
| 563 |
-
"grad_norm": 1.
|
| 564 |
"learning_rate": 0.0007839388145315488,
|
| 565 |
-
"loss": 2.
|
| 566 |
"step": 1540
|
| 567 |
},
|
| 568 |
{
|
| 569 |
"epoch": 2.982791586998088,
|
| 570 |
-
"grad_norm": 1.
|
| 571 |
"learning_rate": 0.0007796898236668791,
|
| 572 |
-
"loss": 2.
|
| 573 |
"step": 1560
|
| 574 |
},
|
| 575 |
{
|
| 576 |
"epoch": 3.0,
|
| 577 |
-
"eval_accuracy": 0.
|
| 578 |
-
"eval_loss": 1.
|
| 579 |
-
"eval_runtime":
|
| 580 |
-
"eval_samples_per_second":
|
| 581 |
-
"eval_steps_per_second":
|
| 582 |
"step": 1569
|
| 583 |
},
|
| 584 |
{
|
| 585 |
"epoch": 3.0210325047801145,
|
| 586 |
-
"grad_norm": 1.
|
| 587 |
"learning_rate": 0.0007754408328022094,
|
| 588 |
-
"loss": 2.
|
| 589 |
"step": 1580
|
| 590 |
},
|
| 591 |
{
|
| 592 |
"epoch": 3.0592734225621414,
|
| 593 |
-
"grad_norm": 1.
|
| 594 |
"learning_rate": 0.0007711918419375399,
|
| 595 |
-
"loss": 2.
|
| 596 |
"step": 1600
|
| 597 |
},
|
| 598 |
{
|
| 599 |
"epoch": 3.0975143403441683,
|
| 600 |
-
"grad_norm": 1.
|
| 601 |
"learning_rate": 0.0007669428510728702,
|
| 602 |
-
"loss": 2.
|
| 603 |
"step": 1620
|
| 604 |
},
|
| 605 |
{
|
| 606 |
"epoch": 3.135755258126195,
|
| 607 |
-
"grad_norm": 1.
|
| 608 |
"learning_rate": 0.0007626938602082005,
|
| 609 |
-
"loss": 2.
|
| 610 |
"step": 1640
|
| 611 |
},
|
| 612 |
{
|
| 613 |
"epoch": 3.173996175908222,
|
| 614 |
-
"grad_norm": 1.
|
| 615 |
"learning_rate": 0.0007584448693435309,
|
| 616 |
-
"loss": 2.
|
| 617 |
"step": 1660
|
| 618 |
},
|
| 619 |
{
|
| 620 |
"epoch": 3.2122370936902485,
|
| 621 |
-
"grad_norm": 1.
|
| 622 |
"learning_rate": 0.0007541958784788613,
|
| 623 |
-
"loss": 2.
|
| 624 |
"step": 1680
|
| 625 |
},
|
| 626 |
{
|
| 627 |
"epoch": 3.2504780114722753,
|
| 628 |
-
"grad_norm": 1.
|
| 629 |
"learning_rate": 0.0007499468876141916,
|
| 630 |
-
"loss": 2.
|
| 631 |
"step": 1700
|
| 632 |
},
|
| 633 |
{
|
| 634 |
"epoch": 3.288718929254302,
|
| 635 |
-
"grad_norm": 1.
|
| 636 |
"learning_rate": 0.000745697896749522,
|
| 637 |
-
"loss": 2.
|
| 638 |
"step": 1720
|
| 639 |
},
|
| 640 |
{
|
| 641 |
"epoch": 3.3269598470363286,
|
| 642 |
-
"grad_norm": 1.
|
| 643 |
"learning_rate": 0.0007414489058848524,
|
| 644 |
-
"loss": 2.
|
| 645 |
"step": 1740
|
| 646 |
},
|
| 647 |
{
|
| 648 |
"epoch": 3.3652007648183555,
|
| 649 |
-
"grad_norm": 1.
|
| 650 |
"learning_rate": 0.0007371999150201827,
|
| 651 |
-
"loss": 2.
|
| 652 |
"step": 1760
|
| 653 |
},
|
| 654 |
{
|
| 655 |
"epoch": 3.4034416826003824,
|
| 656 |
-
"grad_norm": 1.
|
| 657 |
"learning_rate": 0.0007329509241555131,
|
| 658 |
-
"loss": 2.
|
| 659 |
"step": 1780
|
| 660 |
},
|
| 661 |
{
|
| 662 |
"epoch": 3.4416826003824093,
|
| 663 |
-
"grad_norm": 1.
|
| 664 |
"learning_rate": 0.0007287019332908435,
|
| 665 |
-
"loss": 2.
|
| 666 |
"step": 1800
|
| 667 |
},
|
| 668 |
{
|
| 669 |
"epoch": 3.479923518164436,
|
| 670 |
-
"grad_norm": 1.
|
| 671 |
"learning_rate": 0.0007244529424261738,
|
| 672 |
-
"loss": 2.
|
| 673 |
"step": 1820
|
| 674 |
},
|
| 675 |
{
|
| 676 |
"epoch": 3.5181644359464626,
|
| 677 |
-
"grad_norm": 1.
|
| 678 |
"learning_rate": 0.0007202039515615042,
|
| 679 |
-
"loss": 2.
|
| 680 |
"step": 1840
|
| 681 |
},
|
| 682 |
{
|
| 683 |
"epoch": 3.5564053537284894,
|
| 684 |
-
"grad_norm": 1.
|
| 685 |
"learning_rate": 0.0007159549606968346,
|
| 686 |
-
"loss": 2.
|
| 687 |
"step": 1860
|
| 688 |
},
|
| 689 |
{
|
| 690 |
"epoch": 3.5946462715105163,
|
| 691 |
-
"grad_norm": 1.
|
| 692 |
"learning_rate": 0.0007117059698321649,
|
| 693 |
-
"loss": 2.
|
| 694 |
"step": 1880
|
| 695 |
},
|
| 696 |
{
|
| 697 |
"epoch": 3.632887189292543,
|
| 698 |
-
"grad_norm": 1.
|
| 699 |
"learning_rate": 0.0007074569789674953,
|
| 700 |
-
"loss": 2.
|
| 701 |
"step": 1900
|
| 702 |
},
|
| 703 |
{
|
| 704 |
"epoch": 3.67112810707457,
|
| 705 |
-
"grad_norm": 1.
|
| 706 |
"learning_rate": 0.0007032079881028257,
|
| 707 |
-
"loss": 2.
|
| 708 |
"step": 1920
|
| 709 |
},
|
| 710 |
{
|
| 711 |
"epoch": 3.7093690248565965,
|
| 712 |
-
"grad_norm": 1.
|
| 713 |
"learning_rate": 0.0006989589972381559,
|
| 714 |
-
"loss":
|
| 715 |
"step": 1940
|
| 716 |
},
|
| 717 |
{
|
| 718 |
"epoch": 3.7476099426386233,
|
| 719 |
-
"grad_norm": 1.
|
| 720 |
"learning_rate": 0.0006947100063734863,
|
| 721 |
-
"loss": 1.
|
| 722 |
"step": 1960
|
| 723 |
},
|
| 724 |
{
|
| 725 |
"epoch": 3.78585086042065,
|
| 726 |
-
"grad_norm": 1.
|
| 727 |
"learning_rate": 0.0006904610155088166,
|
| 728 |
-
"loss": 2.
|
| 729 |
"step": 1980
|
| 730 |
},
|
| 731 |
{
|
| 732 |
"epoch": 3.8240917782026767,
|
| 733 |
-
"grad_norm": 1.
|
| 734 |
"learning_rate": 0.000686212024644147,
|
| 735 |
-
"loss": 1.
|
| 736 |
"step": 2000
|
| 737 |
},
|
| 738 |
{
|
| 739 |
"epoch": 3.8623326959847035,
|
| 740 |
-
"grad_norm": 1.
|
| 741 |
"learning_rate": 0.0006819630337794774,
|
| 742 |
-
"loss": 1.
|
| 743 |
"step": 2020
|
| 744 |
},
|
| 745 |
{
|
| 746 |
"epoch": 3.9005736137667304,
|
| 747 |
-
"grad_norm": 1.
|
| 748 |
"learning_rate": 0.0006777140429148077,
|
| 749 |
-
"loss": 1.
|
| 750 |
"step": 2040
|
| 751 |
},
|
| 752 |
{
|
| 753 |
"epoch": 3.9388145315487573,
|
| 754 |
-
"grad_norm": 1.
|
| 755 |
"learning_rate": 0.0006734650520501381,
|
| 756 |
-
"loss": 1.
|
| 757 |
"step": 2060
|
| 758 |
},
|
| 759 |
{
|
| 760 |
"epoch": 3.977055449330784,
|
| 761 |
-
"grad_norm": 1.
|
| 762 |
"learning_rate": 0.0006692160611854685,
|
| 763 |
-
"loss": 1.
|
| 764 |
"step": 2080
|
| 765 |
},
|
| 766 |
{
|
| 767 |
"epoch": 4.0,
|
| 768 |
-
"eval_accuracy": 0.
|
| 769 |
-
"eval_loss": 0.
|
| 770 |
-
"eval_runtime":
|
| 771 |
-
"eval_samples_per_second":
|
| 772 |
-
"eval_steps_per_second":
|
| 773 |
"step": 2092
|
| 774 |
},
|
| 775 |
{
|
| 776 |
"epoch": 4.015296367112811,
|
| 777 |
-
"grad_norm": 1.
|
| 778 |
"learning_rate": 0.0006649670703207988,
|
| 779 |
-
"loss": 1.
|
| 780 |
"step": 2100
|
| 781 |
},
|
| 782 |
{
|
| 783 |
"epoch": 4.053537284894838,
|
| 784 |
-
"grad_norm": 1.
|
| 785 |
"learning_rate": 0.0006607180794561292,
|
| 786 |
-
"loss": 1.
|
| 787 |
"step": 2120
|
| 788 |
},
|
| 789 |
{
|
| 790 |
"epoch": 4.091778202676864,
|
| 791 |
-
"grad_norm": 1.
|
| 792 |
"learning_rate": 0.0006564690885914596,
|
| 793 |
-
"loss": 1.
|
| 794 |
"step": 2140
|
| 795 |
},
|
| 796 |
{
|
| 797 |
"epoch": 4.130019120458891,
|
| 798 |
-
"grad_norm": 1.
|
| 799 |
"learning_rate": 0.0006522200977267899,
|
| 800 |
-
"loss": 1.
|
| 801 |
"step": 2160
|
| 802 |
},
|
| 803 |
{
|
| 804 |
"epoch": 4.168260038240918,
|
| 805 |
-
"grad_norm": 1.
|
| 806 |
"learning_rate": 0.0006479711068621203,
|
| 807 |
-
"loss": 1.
|
| 808 |
"step": 2180
|
| 809 |
},
|
| 810 |
{
|
| 811 |
"epoch": 4.2065009560229445,
|
| 812 |
-
"grad_norm": 1.
|
| 813 |
"learning_rate": 0.0006437221159974506,
|
| 814 |
-
"loss": 1.
|
| 815 |
"step": 2200
|
| 816 |
},
|
| 817 |
{
|
| 818 |
"epoch": 4.244741873804971,
|
| 819 |
-
"grad_norm": 1.
|
| 820 |
"learning_rate": 0.000639473125132781,
|
| 821 |
-
"loss": 1.
|
| 822 |
"step": 2220
|
| 823 |
},
|
| 824 |
{
|
| 825 |
"epoch": 4.282982791586998,
|
| 826 |
-
"grad_norm": 1.
|
| 827 |
"learning_rate": 0.0006352241342681113,
|
| 828 |
-
"loss": 1.
|
| 829 |
"step": 2240
|
| 830 |
},
|
| 831 |
{
|
| 832 |
"epoch": 4.321223709369025,
|
| 833 |
-
"grad_norm": 1.
|
| 834 |
"learning_rate": 0.0006309751434034417,
|
| 835 |
-
"loss": 1.
|
| 836 |
"step": 2260
|
| 837 |
},
|
| 838 |
{
|
| 839 |
"epoch": 4.359464627151052,
|
| 840 |
-
"grad_norm": 1.
|
| 841 |
"learning_rate": 0.0006267261525387721,
|
| 842 |
-
"loss": 1.
|
| 843 |
"step": 2280
|
| 844 |
},
|
| 845 |
{
|
| 846 |
"epoch": 4.397705544933078,
|
| 847 |
-
"grad_norm": 1.
|
| 848 |
"learning_rate": 0.0006224771616741024,
|
| 849 |
-
"loss": 1.
|
| 850 |
"step": 2300
|
| 851 |
},
|
| 852 |
{
|
| 853 |
"epoch": 4.435946462715105,
|
| 854 |
-
"grad_norm": 1.
|
| 855 |
"learning_rate": 0.0006182281708094328,
|
| 856 |
-
"loss": 1.
|
| 857 |
"step": 2320
|
| 858 |
},
|
| 859 |
{
|
| 860 |
"epoch": 4.474187380497132,
|
| 861 |
-
"grad_norm": 1.
|
| 862 |
"learning_rate": 0.0006139791799447631,
|
| 863 |
-
"loss": 1.
|
| 864 |
"step": 2340
|
| 865 |
},
|
| 866 |
{
|
| 867 |
"epoch": 4.512428298279159,
|
| 868 |
-
"grad_norm": 1.
|
| 869 |
"learning_rate": 0.0006097301890800934,
|
| 870 |
-
"loss": 1.
|
| 871 |
"step": 2360
|
| 872 |
},
|
| 873 |
{
|
| 874 |
"epoch": 4.550669216061186,
|
| 875 |
-
"grad_norm": 1.
|
| 876 |
"learning_rate": 0.0006054811982154238,
|
| 877 |
-
"loss": 1.
|
| 878 |
"step": 2380
|
| 879 |
},
|
| 880 |
{
|
| 881 |
"epoch": 4.588910133843212,
|
| 882 |
-
"grad_norm": 1.
|
| 883 |
"learning_rate": 0.0006012322073507542,
|
| 884 |
-
"loss": 1.
|
| 885 |
"step": 2400
|
| 886 |
},
|
| 887 |
{
|
| 888 |
"epoch": 4.627151051625239,
|
| 889 |
-
"grad_norm": 1.
|
| 890 |
"learning_rate": 0.0005969832164860845,
|
| 891 |
-
"loss": 1.
|
| 892 |
"step": 2420
|
| 893 |
},
|
| 894 |
{
|
| 895 |
"epoch": 4.665391969407266,
|
| 896 |
-
"grad_norm": 1.
|
| 897 |
"learning_rate": 0.0005927342256214149,
|
| 898 |
-
"loss": 1.
|
| 899 |
"step": 2440
|
| 900 |
},
|
| 901 |
{
|
| 902 |
"epoch": 4.7036328871892925,
|
| 903 |
-
"grad_norm": 1.
|
| 904 |
"learning_rate": 0.0005884852347567453,
|
| 905 |
-
"loss": 1.
|
| 906 |
"step": 2460
|
| 907 |
},
|
| 908 |
{
|
| 909 |
"epoch": 4.741873804971319,
|
| 910 |
-
"grad_norm": 1.
|
| 911 |
"learning_rate": 0.0005842362438920756,
|
| 912 |
-
"loss": 1.
|
| 913 |
"step": 2480
|
| 914 |
},
|
| 915 |
{
|
| 916 |
"epoch": 4.780114722753346,
|
| 917 |
-
"grad_norm": 1.
|
| 918 |
"learning_rate": 0.000579987253027406,
|
| 919 |
-
"loss": 1.
|
| 920 |
"step": 2500
|
| 921 |
},
|
| 922 |
{
|
| 923 |
"epoch": 4.818355640535373,
|
| 924 |
-
"grad_norm": 1.
|
| 925 |
"learning_rate": 0.0005757382621627364,
|
| 926 |
-
"loss": 1.
|
| 927 |
"step": 2520
|
| 928 |
},
|
| 929 |
{
|
| 930 |
"epoch": 4.8565965583174,
|
| 931 |
-
"grad_norm": 1.
|
| 932 |
"learning_rate": 0.0005714892712980667,
|
| 933 |
-
"loss": 1.
|
| 934 |
"step": 2540
|
| 935 |
},
|
| 936 |
{
|
| 937 |
"epoch": 4.894837476099426,
|
| 938 |
-
"grad_norm": 1.
|
| 939 |
"learning_rate": 0.000567240280433397,
|
| 940 |
-
"loss": 1.
|
| 941 |
"step": 2560
|
| 942 |
},
|
| 943 |
{
|
| 944 |
"epoch": 4.933078393881453,
|
| 945 |
-
"grad_norm": 1.
|
| 946 |
"learning_rate": 0.0005629912895687275,
|
| 947 |
-
"loss": 1.
|
| 948 |
"step": 2580
|
| 949 |
},
|
| 950 |
{
|
| 951 |
"epoch": 4.97131931166348,
|
| 952 |
-
"grad_norm": 1.
|
| 953 |
"learning_rate": 0.0005587422987040578,
|
| 954 |
-
"loss": 1.
|
| 955 |
"step": 2600
|
| 956 |
},
|
| 957 |
{
|
| 958 |
"epoch": 5.0,
|
| 959 |
-
"eval_accuracy": 0.
|
| 960 |
-
"eval_loss": 0.
|
| 961 |
-
"eval_runtime":
|
| 962 |
-
"eval_samples_per_second":
|
| 963 |
-
"eval_steps_per_second":
|
| 964 |
"step": 2615
|
| 965 |
},
|
| 966 |
{
|
| 967 |
"epoch": 5.009560229445507,
|
| 968 |
-
"grad_norm": 1.
|
| 969 |
"learning_rate": 0.0005544933078393881,
|
| 970 |
-
"loss": 1.
|
| 971 |
"step": 2620
|
| 972 |
},
|
| 973 |
{
|
| 974 |
"epoch": 5.047801147227533,
|
| 975 |
-
"grad_norm": 1.
|
| 976 |
"learning_rate": 0.0005502443169747186,
|
| 977 |
-
"loss": 1.
|
| 978 |
"step": 2640
|
| 979 |
},
|
| 980 |
{
|
| 981 |
"epoch": 5.08604206500956,
|
| 982 |
-
"grad_norm": 1.
|
| 983 |
"learning_rate": 0.0005459953261100489,
|
| 984 |
-
"loss": 1.
|
| 985 |
"step": 2660
|
| 986 |
},
|
| 987 |
{
|
| 988 |
"epoch": 5.124282982791587,
|
| 989 |
-
"grad_norm": 1.
|
| 990 |
"learning_rate": 0.0005417463352453792,
|
| 991 |
-
"loss": 1.
|
| 992 |
"step": 2680
|
| 993 |
},
|
| 994 |
{
|
| 995 |
"epoch": 5.162523900573614,
|
| 996 |
-
"grad_norm": 1.
|
| 997 |
"learning_rate": 0.0005374973443807097,
|
| 998 |
-
"loss": 1.
|
| 999 |
"step": 2700
|
| 1000 |
},
|
| 1001 |
{
|
| 1002 |
"epoch": 5.2007648183556405,
|
| 1003 |
-
"grad_norm": 1.
|
| 1004 |
"learning_rate": 0.00053324835351604,
|
| 1005 |
-
"loss": 1.
|
| 1006 |
"step": 2720
|
| 1007 |
},
|
| 1008 |
{
|
| 1009 |
"epoch": 5.239005736137667,
|
| 1010 |
-
"grad_norm": 1.
|
| 1011 |
"learning_rate": 0.0005289993626513702,
|
| 1012 |
-
"loss": 1.
|
| 1013 |
"step": 2740
|
| 1014 |
},
|
| 1015 |
{
|
| 1016 |
"epoch": 5.277246653919694,
|
| 1017 |
-
"grad_norm": 1.
|
| 1018 |
"learning_rate": 0.0005247503717867008,
|
| 1019 |
-
"loss": 1.
|
| 1020 |
"step": 2760
|
| 1021 |
},
|
| 1022 |
{
|
| 1023 |
"epoch": 5.315487571701721,
|
| 1024 |
-
"grad_norm": 1.
|
| 1025 |
"learning_rate": 0.000520501380922031,
|
| 1026 |
-
"loss": 1.
|
| 1027 |
"step": 2780
|
| 1028 |
},
|
| 1029 |
{
|
| 1030 |
"epoch": 5.353728489483748,
|
| 1031 |
-
"grad_norm": 1.
|
| 1032 |
"learning_rate": 0.0005162523900573613,
|
| 1033 |
-
"loss": 1.
|
| 1034 |
"step": 2800
|
| 1035 |
},
|
| 1036 |
{
|
| 1037 |
"epoch": 5.3919694072657744,
|
| 1038 |
-
"grad_norm": 1.
|
| 1039 |
"learning_rate": 0.0005120033991926918,
|
| 1040 |
-
"loss": 1.
|
| 1041 |
"step": 2820
|
| 1042 |
},
|
| 1043 |
{
|
| 1044 |
"epoch": 5.430210325047801,
|
| 1045 |
-
"grad_norm": 1.
|
| 1046 |
"learning_rate": 0.0005077544083280221,
|
| 1047 |
-
"loss": 1.
|
| 1048 |
"step": 2840
|
| 1049 |
},
|
| 1050 |
{
|
| 1051 |
"epoch": 5.468451242829828,
|
| 1052 |
-
"grad_norm": 1.
|
| 1053 |
"learning_rate": 0.0005035054174633524,
|
| 1054 |
-
"loss": 1.
|
| 1055 |
"step": 2860
|
| 1056 |
},
|
| 1057 |
{
|
| 1058 |
"epoch": 5.506692160611855,
|
| 1059 |
-
"grad_norm": 1.
|
| 1060 |
"learning_rate": 0.0004992564265986828,
|
| 1061 |
-
"loss": 1.
|
| 1062 |
"step": 2880
|
| 1063 |
},
|
| 1064 |
{
|
| 1065 |
"epoch": 5.544933078393882,
|
| 1066 |
-
"grad_norm": 1.
|
| 1067 |
"learning_rate": 0.0004950074357340132,
|
| 1068 |
-
"loss": 1.
|
| 1069 |
"step": 2900
|
| 1070 |
},
|
| 1071 |
{
|
| 1072 |
"epoch": 5.583173996175908,
|
| 1073 |
-
"grad_norm": 1.
|
| 1074 |
"learning_rate": 0.0004907584448693436,
|
| 1075 |
-
"loss": 1.
|
| 1076 |
"step": 2920
|
| 1077 |
},
|
| 1078 |
{
|
| 1079 |
"epoch": 5.621414913957935,
|
| 1080 |
-
"grad_norm": 1.
|
| 1081 |
"learning_rate": 0.0004865094540046739,
|
| 1082 |
-
"loss": 1.
|
| 1083 |
"step": 2940
|
| 1084 |
},
|
| 1085 |
{
|
| 1086 |
"epoch": 5.659655831739962,
|
| 1087 |
-
"grad_norm": 1.
|
| 1088 |
"learning_rate": 0.00048226046314000425,
|
| 1089 |
-
"loss": 1.
|
| 1090 |
"step": 2960
|
| 1091 |
},
|
| 1092 |
{
|
| 1093 |
"epoch": 5.6978967495219885,
|
| 1094 |
-
"grad_norm": 1.
|
| 1095 |
"learning_rate": 0.0004780114722753346,
|
| 1096 |
-
"loss": 1.
|
| 1097 |
"step": 2980
|
| 1098 |
},
|
| 1099 |
{
|
| 1100 |
"epoch": 5.736137667304015,
|
| 1101 |
-
"grad_norm": 1.
|
| 1102 |
"learning_rate": 0.000473762481410665,
|
| 1103 |
-
"loss": 1.
|
| 1104 |
"step": 3000
|
| 1105 |
},
|
| 1106 |
{
|
| 1107 |
"epoch": 5.774378585086042,
|
| 1108 |
-
"grad_norm": 1.
|
| 1109 |
"learning_rate": 0.00046951349054599533,
|
| 1110 |
-
"loss": 1.
|
| 1111 |
"step": 3020
|
| 1112 |
},
|
| 1113 |
{
|
| 1114 |
"epoch": 5.812619502868069,
|
| 1115 |
-
"grad_norm": 1.
|
| 1116 |
"learning_rate": 0.0004652644996813257,
|
| 1117 |
-
"loss": 1.
|
| 1118 |
"step": 3040
|
| 1119 |
},
|
| 1120 |
{
|
| 1121 |
"epoch": 5.850860420650095,
|
| 1122 |
-
"grad_norm": 1.
|
| 1123 |
"learning_rate": 0.0004610155088166561,
|
| 1124 |
-
"loss": 1.
|
| 1125 |
"step": 3060
|
| 1126 |
},
|
| 1127 |
{
|
| 1128 |
"epoch": 5.8891013384321225,
|
| 1129 |
-
"grad_norm": 1.
|
| 1130 |
"learning_rate": 0.0004567665179519864,
|
| 1131 |
-
"loss": 1.
|
| 1132 |
"step": 3080
|
| 1133 |
},
|
| 1134 |
{
|
| 1135 |
"epoch": 5.927342256214149,
|
| 1136 |
-
"grad_norm": 1.
|
| 1137 |
"learning_rate": 0.00045251752708731676,
|
| 1138 |
-
"loss": 1.
|
| 1139 |
"step": 3100
|
| 1140 |
},
|
| 1141 |
{
|
| 1142 |
"epoch": 5.965583173996176,
|
| 1143 |
-
"grad_norm": 1.
|
| 1144 |
"learning_rate": 0.0004482685362226471,
|
| 1145 |
-
"loss": 1.
|
| 1146 |
"step": 3120
|
| 1147 |
},
|
| 1148 |
{
|
| 1149 |
"epoch": 6.0,
|
| 1150 |
-
"eval_accuracy": 0.
|
| 1151 |
-
"eval_loss": 0.
|
| 1152 |
-
"eval_runtime":
|
| 1153 |
-
"eval_samples_per_second":
|
| 1154 |
-
"eval_steps_per_second":
|
| 1155 |
"step": 3138
|
| 1156 |
},
|
| 1157 |
{
|
| 1158 |
"epoch": 6.003824091778203,
|
| 1159 |
-
"grad_norm": 1.
|
| 1160 |
"learning_rate": 0.0004440195453579775,
|
| 1161 |
-
"loss": 1.
|
| 1162 |
"step": 3140
|
| 1163 |
},
|
| 1164 |
{
|
| 1165 |
"epoch": 6.042065009560229,
|
| 1166 |
-
"grad_norm": 1.
|
| 1167 |
"learning_rate": 0.00043977055449330785,
|
| 1168 |
-
"loss": 1.
|
| 1169 |
"step": 3160
|
| 1170 |
},
|
| 1171 |
{
|
| 1172 |
"epoch": 6.080305927342256,
|
| 1173 |
-
"grad_norm": 1.
|
| 1174 |
"learning_rate": 0.0004355215636286382,
|
| 1175 |
-
"loss": 1.
|
| 1176 |
"step": 3180
|
| 1177 |
},
|
| 1178 |
{
|
| 1179 |
"epoch": 6.118546845124283,
|
| 1180 |
-
"grad_norm": 1.
|
| 1181 |
"learning_rate": 0.0004312725727639686,
|
| 1182 |
-
"loss": 1.
|
| 1183 |
"step": 3200
|
| 1184 |
},
|
| 1185 |
{
|
| 1186 |
"epoch": 6.15678776290631,
|
| 1187 |
-
"grad_norm": 1.
|
| 1188 |
"learning_rate": 0.0004270235818992989,
|
| 1189 |
-
"loss": 1.
|
| 1190 |
"step": 3220
|
| 1191 |
},
|
| 1192 |
{
|
| 1193 |
"epoch": 6.195028680688337,
|
| 1194 |
-
"grad_norm": 1.
|
| 1195 |
"learning_rate": 0.0004227745910346293,
|
| 1196 |
-
"loss": 1.
|
| 1197 |
"step": 3240
|
| 1198 |
},
|
| 1199 |
{
|
| 1200 |
"epoch": 6.233269598470363,
|
| 1201 |
-
"grad_norm": 1.
|
| 1202 |
"learning_rate": 0.0004185256001699597,
|
| 1203 |
-
"loss": 1.
|
| 1204 |
"step": 3260
|
| 1205 |
},
|
| 1206 |
{
|
| 1207 |
"epoch": 6.27151051625239,
|
| 1208 |
-
"grad_norm": 1.
|
| 1209 |
"learning_rate": 0.00041427660930528997,
|
| 1210 |
-
"loss": 1.
|
| 1211 |
"step": 3280
|
| 1212 |
},
|
| 1213 |
{
|
| 1214 |
"epoch": 6.309751434034417,
|
| 1215 |
-
"grad_norm": 1.
|
| 1216 |
"learning_rate": 0.00041002761844062037,
|
| 1217 |
-
"loss": 1.
|
| 1218 |
"step": 3300
|
| 1219 |
},
|
| 1220 |
{
|
| 1221 |
"epoch": 6.347992351816444,
|
| 1222 |
-
"grad_norm": 1.
|
| 1223 |
"learning_rate": 0.00040577862757595076,
|
| 1224 |
-
"loss": 1.
|
| 1225 |
"step": 3320
|
| 1226 |
},
|
| 1227 |
{
|
| 1228 |
"epoch": 6.3862332695984705,
|
| 1229 |
-
"grad_norm": 1.
|
| 1230 |
"learning_rate": 0.00040152963671128105,
|
| 1231 |
-
"loss": 1.
|
| 1232 |
"step": 3340
|
| 1233 |
},
|
| 1234 |
{
|
| 1235 |
"epoch": 6.424474187380497,
|
| 1236 |
-
"grad_norm": 1.
|
| 1237 |
"learning_rate": 0.00039728064584661145,
|
| 1238 |
-
"loss": 1.
|
| 1239 |
"step": 3360
|
| 1240 |
},
|
| 1241 |
{
|
| 1242 |
"epoch": 6.462715105162524,
|
| 1243 |
-
"grad_norm": 1.
|
| 1244 |
"learning_rate": 0.0003930316549819418,
|
| 1245 |
-
"loss": 1.
|
| 1246 |
"step": 3380
|
| 1247 |
},
|
| 1248 |
{
|
| 1249 |
"epoch": 6.500956022944551,
|
| 1250 |
-
"grad_norm": 1.
|
| 1251 |
"learning_rate": 0.00038878266411727214,
|
| 1252 |
-
"loss": 1.
|
| 1253 |
"step": 3400
|
| 1254 |
},
|
| 1255 |
{
|
| 1256 |
"epoch": 6.539196940726577,
|
| 1257 |
-
"grad_norm": 1.
|
| 1258 |
"learning_rate": 0.00038453367325260254,
|
| 1259 |
-
"loss": 1.
|
| 1260 |
"step": 3420
|
| 1261 |
},
|
| 1262 |
{
|
| 1263 |
"epoch": 6.577437858508604,
|
| 1264 |
-
"grad_norm": 1.
|
| 1265 |
"learning_rate": 0.0003802846823879329,
|
| 1266 |
-
"loss": 1.
|
| 1267 |
"step": 3440
|
| 1268 |
},
|
| 1269 |
{
|
| 1270 |
"epoch": 6.615678776290631,
|
| 1271 |
-
"grad_norm": 1.
|
| 1272 |
"learning_rate": 0.0003760356915232632,
|
| 1273 |
-
"loss": 1.
|
| 1274 |
"step": 3460
|
| 1275 |
},
|
| 1276 |
{
|
| 1277 |
"epoch": 6.653919694072657,
|
| 1278 |
-
"grad_norm": 1.
|
| 1279 |
"learning_rate": 0.0003717867006585936,
|
| 1280 |
-
"loss": 1.
|
| 1281 |
"step": 3480
|
| 1282 |
},
|
| 1283 |
{
|
| 1284 |
"epoch": 6.692160611854685,
|
| 1285 |
-
"grad_norm": 1.
|
| 1286 |
"learning_rate": 0.0003675377097939239,
|
| 1287 |
-
"loss": 1.
|
| 1288 |
"step": 3500
|
| 1289 |
},
|
| 1290 |
{
|
| 1291 |
"epoch": 6.730401529636711,
|
| 1292 |
-
"grad_norm": 1.
|
| 1293 |
"learning_rate": 0.0003632887189292543,
|
| 1294 |
-
"loss": 1.
|
| 1295 |
"step": 3520
|
| 1296 |
},
|
| 1297 |
{
|
| 1298 |
"epoch": 6.768642447418738,
|
| 1299 |
-
"grad_norm": 1.
|
| 1300 |
"learning_rate": 0.00035903972806458466,
|
| 1301 |
-
"loss": 1.
|
| 1302 |
"step": 3540
|
| 1303 |
},
|
| 1304 |
{
|
| 1305 |
"epoch": 6.806883365200765,
|
| 1306 |
-
"grad_norm": 1.
|
| 1307 |
"learning_rate": 0.000354790737199915,
|
| 1308 |
-
"loss": 1.
|
| 1309 |
"step": 3560
|
| 1310 |
},
|
| 1311 |
{
|
| 1312 |
"epoch": 6.845124282982791,
|
| 1313 |
-
"grad_norm": 1.
|
| 1314 |
"learning_rate": 0.0003505417463352454,
|
| 1315 |
-
"loss": 1.
|
| 1316 |
"step": 3580
|
| 1317 |
},
|
| 1318 |
{
|
| 1319 |
"epoch": 6.8833652007648185,
|
| 1320 |
-
"grad_norm": 1.
|
| 1321 |
"learning_rate": 0.00034629275547057574,
|
| 1322 |
-
"loss": 1.
|
| 1323 |
"step": 3600
|
| 1324 |
},
|
| 1325 |
{
|
| 1326 |
"epoch": 6.921606118546845,
|
| 1327 |
-
"grad_norm": 1.
|
| 1328 |
"learning_rate": 0.0003420437646059061,
|
| 1329 |
-
"loss": 1.
|
| 1330 |
"step": 3620
|
| 1331 |
},
|
| 1332 |
{
|
| 1333 |
"epoch": 6.959847036328872,
|
| 1334 |
-
"grad_norm": 1.
|
| 1335 |
"learning_rate": 0.0003377947737412365,
|
| 1336 |
"loss": 1.0912,
|
| 1337 |
"step": 3640
|
| 1338 |
},
|
| 1339 |
{
|
| 1340 |
"epoch": 6.998087954110899,
|
| 1341 |
-
"grad_norm": 1.
|
| 1342 |
"learning_rate": 0.00033354578287656683,
|
| 1343 |
-
"loss": 1.
|
| 1344 |
"step": 3660
|
| 1345 |
},
|
| 1346 |
{
|
| 1347 |
"epoch": 7.0,
|
| 1348 |
-
"eval_accuracy": 0.
|
| 1349 |
-
"eval_loss": 0.
|
| 1350 |
-
"eval_runtime":
|
| 1351 |
-
"eval_samples_per_second":
|
| 1352 |
-
"eval_steps_per_second":
|
| 1353 |
"step": 3661
|
| 1354 |
},
|
| 1355 |
{
|
| 1356 |
"epoch": 7.036328871892925,
|
| 1357 |
-
"grad_norm": 1.
|
| 1358 |
"learning_rate": 0.0003292967920118972,
|
| 1359 |
-
"loss": 1.
|
| 1360 |
"step": 3680
|
| 1361 |
},
|
| 1362 |
{
|
| 1363 |
"epoch": 7.074569789674952,
|
| 1364 |
-
"grad_norm": 1.
|
| 1365 |
"learning_rate": 0.0003250478011472275,
|
| 1366 |
-
"loss": 1.
|
| 1367 |
"step": 3700
|
| 1368 |
},
|
| 1369 |
{
|
| 1370 |
"epoch": 7.112810707456979,
|
| 1371 |
-
"grad_norm": 1.
|
| 1372 |
"learning_rate": 0.0003207988102825579,
|
| 1373 |
-
"loss": 1.
|
| 1374 |
"step": 3720
|
| 1375 |
},
|
| 1376 |
{
|
| 1377 |
"epoch": 7.151051625239006,
|
| 1378 |
-
"grad_norm": 1.
|
| 1379 |
"learning_rate": 0.00031654981941788826,
|
| 1380 |
-
"loss": 1.
|
| 1381 |
"step": 3740
|
| 1382 |
},
|
| 1383 |
{
|
| 1384 |
"epoch": 7.189292543021033,
|
| 1385 |
-
"grad_norm": 1.
|
| 1386 |
"learning_rate": 0.0003123008285532186,
|
| 1387 |
-
"loss": 1.
|
| 1388 |
"step": 3760
|
| 1389 |
},
|
| 1390 |
{
|
| 1391 |
"epoch": 7.227533460803059,
|
| 1392 |
-
"grad_norm": 1.
|
| 1393 |
"learning_rate": 0.000308051837688549,
|
| 1394 |
-
"loss": 1.
|
| 1395 |
"step": 3780
|
| 1396 |
},
|
| 1397 |
{
|
| 1398 |
"epoch": 7.265774378585086,
|
| 1399 |
-
"grad_norm": 1.
|
| 1400 |
"learning_rate": 0.00030380284682387935,
|
| 1401 |
-
"loss": 1.
|
| 1402 |
"step": 3800
|
| 1403 |
},
|
| 1404 |
{
|
| 1405 |
"epoch": 7.304015296367113,
|
| 1406 |
-
"grad_norm": 1.
|
| 1407 |
"learning_rate": 0.0002995538559592097,
|
| 1408 |
-
"loss": 0.
|
| 1409 |
"step": 3820
|
| 1410 |
},
|
| 1411 |
{
|
| 1412 |
"epoch": 7.342256214149139,
|
| 1413 |
-
"grad_norm": 1.
|
| 1414 |
"learning_rate": 0.0002953048650945401,
|
| 1415 |
-
"loss": 1.
|
| 1416 |
"step": 3840
|
| 1417 |
},
|
| 1418 |
{
|
| 1419 |
"epoch": 7.3804971319311665,
|
| 1420 |
-
"grad_norm": 1.
|
| 1421 |
"learning_rate": 0.0002910558742298704,
|
| 1422 |
-
"loss": 0.
|
| 1423 |
"step": 3860
|
| 1424 |
},
|
| 1425 |
{
|
| 1426 |
"epoch": 7.418738049713193,
|
| 1427 |
-
"grad_norm": 1.
|
| 1428 |
"learning_rate": 0.0002868068833652008,
|
| 1429 |
-
"loss": 0.
|
| 1430 |
"step": 3880
|
| 1431 |
},
|
| 1432 |
{
|
| 1433 |
"epoch": 7.45697896749522,
|
| 1434 |
-
"grad_norm": 1.
|
| 1435 |
"learning_rate": 0.0002825578925005312,
|
| 1436 |
-
"loss": 0.
|
| 1437 |
"step": 3900
|
| 1438 |
},
|
| 1439 |
{
|
| 1440 |
"epoch": 7.495219885277247,
|
| 1441 |
-
"grad_norm": 1.
|
| 1442 |
"learning_rate": 0.00027830890163586146,
|
| 1443 |
-
"loss":
|
| 1444 |
"step": 3920
|
| 1445 |
},
|
| 1446 |
{
|
| 1447 |
"epoch": 7.533460803059273,
|
| 1448 |
-
"grad_norm": 1.
|
| 1449 |
"learning_rate": 0.00027405991077119186,
|
| 1450 |
-
"loss": 0.
|
| 1451 |
"step": 3940
|
| 1452 |
},
|
| 1453 |
{
|
| 1454 |
"epoch": 7.5717017208413,
|
| 1455 |
-
"grad_norm": 1.
|
| 1456 |
"learning_rate": 0.00026981091990652226,
|
| 1457 |
-
"loss": 0.
|
| 1458 |
"step": 3960
|
| 1459 |
},
|
| 1460 |
{
|
| 1461 |
"epoch": 7.609942638623327,
|
| 1462 |
-
"grad_norm": 1.
|
| 1463 |
"learning_rate": 0.00026556192904185255,
|
| 1464 |
-
"loss": 0.
|
| 1465 |
"step": 3980
|
| 1466 |
},
|
| 1467 |
{
|
| 1468 |
"epoch": 7.648183556405353,
|
| 1469 |
-
"grad_norm": 1.
|
| 1470 |
"learning_rate": 0.00026131293817718295,
|
| 1471 |
-
"loss": 0.
|
| 1472 |
"step": 4000
|
| 1473 |
},
|
| 1474 |
{
|
| 1475 |
"epoch": 7.686424474187381,
|
| 1476 |
-
"grad_norm": 1.
|
| 1477 |
"learning_rate": 0.00025706394731251324,
|
| 1478 |
-
"loss": 0.
|
| 1479 |
"step": 4020
|
| 1480 |
},
|
| 1481 |
{
|
| 1482 |
"epoch": 7.724665391969407,
|
| 1483 |
-
"grad_norm": 1.
|
| 1484 |
"learning_rate": 0.00025281495644784364,
|
| 1485 |
-
"loss": 0.
|
| 1486 |
"step": 4040
|
| 1487 |
},
|
| 1488 |
{
|
| 1489 |
"epoch": 7.762906309751434,
|
| 1490 |
-
"grad_norm": 1.
|
| 1491 |
"learning_rate": 0.00024856596558317403,
|
| 1492 |
-
"loss": 0.
|
| 1493 |
"step": 4060
|
| 1494 |
},
|
| 1495 |
{
|
| 1496 |
"epoch": 7.801147227533461,
|
| 1497 |
-
"grad_norm": 1.
|
| 1498 |
"learning_rate": 0.0002443169747185044,
|
| 1499 |
-
"loss": 0.
|
| 1500 |
"step": 4080
|
| 1501 |
},
|
| 1502 |
{
|
| 1503 |
"epoch": 7.839388145315487,
|
| 1504 |
-
"grad_norm": 1.
|
| 1505 |
"learning_rate": 0.00024006798385383472,
|
| 1506 |
-
"loss": 0.
|
| 1507 |
"step": 4100
|
| 1508 |
},
|
| 1509 |
{
|
| 1510 |
"epoch": 7.8776290630975145,
|
| 1511 |
-
"grad_norm": 1.
|
| 1512 |
"learning_rate": 0.00023581899298916507,
|
| 1513 |
-
"loss": 0.
|
| 1514 |
"step": 4120
|
| 1515 |
},
|
| 1516 |
{
|
| 1517 |
"epoch": 7.915869980879541,
|
| 1518 |
-
"grad_norm": 1.
|
| 1519 |
"learning_rate": 0.00023157000212449544,
|
| 1520 |
-
"loss": 0.
|
| 1521 |
"step": 4140
|
| 1522 |
},
|
| 1523 |
{
|
| 1524 |
"epoch": 7.954110898661568,
|
| 1525 |
-
"grad_norm": 1.
|
| 1526 |
"learning_rate": 0.00022732101125982578,
|
| 1527 |
-
"loss": 0.
|
| 1528 |
"step": 4160
|
| 1529 |
},
|
| 1530 |
{
|
| 1531 |
"epoch": 7.992351816443595,
|
| 1532 |
-
"grad_norm": 1.
|
| 1533 |
"learning_rate": 0.00022307202039515615,
|
| 1534 |
-
"loss": 0.
|
| 1535 |
"step": 4180
|
| 1536 |
},
|
| 1537 |
{
|
| 1538 |
"epoch": 8.0,
|
| 1539 |
-
"eval_accuracy": 0.
|
| 1540 |
-
"eval_loss": 0.
|
| 1541 |
-
"eval_runtime":
|
| 1542 |
-
"eval_samples_per_second":
|
| 1543 |
-
"eval_steps_per_second":
|
| 1544 |
"step": 4184
|
| 1545 |
},
|
| 1546 |
{
|
| 1547 |
"epoch": 8.030592734225621,
|
| 1548 |
-
"grad_norm": 1.
|
| 1549 |
"learning_rate": 0.00021882302953048652,
|
| 1550 |
-
"loss": 0.
|
| 1551 |
"step": 4200
|
| 1552 |
},
|
| 1553 |
{
|
| 1554 |
"epoch": 8.068833652007648,
|
| 1555 |
-
"grad_norm": 1.
|
| 1556 |
"learning_rate": 0.00021457403866581687,
|
| 1557 |
-
"loss": 0.
|
| 1558 |
"step": 4220
|
| 1559 |
},
|
| 1560 |
{
|
| 1561 |
"epoch": 8.107074569789676,
|
| 1562 |
-
"grad_norm": 1.
|
| 1563 |
"learning_rate": 0.0002103250478011472,
|
| 1564 |
-
"loss": 0.
|
| 1565 |
"step": 4240
|
| 1566 |
},
|
| 1567 |
{
|
| 1568 |
"epoch": 8.145315487571702,
|
| 1569 |
-
"grad_norm": 1.
|
| 1570 |
"learning_rate": 0.0002060760569364776,
|
| 1571 |
-
"loss": 0.
|
| 1572 |
"step": 4260
|
| 1573 |
},
|
| 1574 |
{
|
| 1575 |
"epoch": 8.183556405353729,
|
| 1576 |
-
"grad_norm": 1.
|
| 1577 |
"learning_rate": 0.00020182706607180795,
|
| 1578 |
-
"loss": 0.
|
| 1579 |
"step": 4280
|
| 1580 |
},
|
| 1581 |
{
|
| 1582 |
"epoch": 8.221797323135755,
|
| 1583 |
-
"grad_norm": 1.
|
| 1584 |
"learning_rate": 0.0001975780752071383,
|
| 1585 |
-
"loss": 0.
|
| 1586 |
"step": 4300
|
| 1587 |
},
|
| 1588 |
{
|
| 1589 |
"epoch": 8.260038240917781,
|
| 1590 |
-
"grad_norm": 1.
|
| 1591 |
"learning_rate": 0.00019332908434246867,
|
| 1592 |
-
"loss": 0.
|
| 1593 |
"step": 4320
|
| 1594 |
},
|
| 1595 |
{
|
| 1596 |
"epoch": 8.29827915869981,
|
| 1597 |
-
"grad_norm": 1.
|
| 1598 |
"learning_rate": 0.00018908009347779904,
|
| 1599 |
-
"loss": 0.
|
| 1600 |
"step": 4340
|
| 1601 |
},
|
| 1602 |
{
|
| 1603 |
"epoch": 8.336520076481836,
|
| 1604 |
-
"grad_norm": 1.
|
| 1605 |
"learning_rate": 0.00018483110261312938,
|
| 1606 |
-
"loss": 0.
|
| 1607 |
"step": 4360
|
| 1608 |
},
|
| 1609 |
{
|
| 1610 |
"epoch": 8.374760994263863,
|
| 1611 |
-
"grad_norm": 1.
|
| 1612 |
"learning_rate": 0.00018058211174845973,
|
| 1613 |
-
"loss": 0.
|
| 1614 |
"step": 4380
|
| 1615 |
},
|
| 1616 |
{
|
| 1617 |
"epoch": 8.413001912045889,
|
| 1618 |
-
"grad_norm": 1.
|
| 1619 |
"learning_rate": 0.0001763331208837901,
|
| 1620 |
-
"loss": 0.
|
| 1621 |
"step": 4400
|
| 1622 |
},
|
| 1623 |
{
|
| 1624 |
"epoch": 8.451242829827915,
|
| 1625 |
-
"grad_norm": 1.
|
| 1626 |
"learning_rate": 0.00017208413001912047,
|
| 1627 |
-
"loss": 0.
|
| 1628 |
"step": 4420
|
| 1629 |
},
|
| 1630 |
{
|
| 1631 |
"epoch": 8.489483747609942,
|
| 1632 |
-
"grad_norm": 1.
|
| 1633 |
"learning_rate": 0.00016783513915445082,
|
| 1634 |
-
"loss": 0.
|
| 1635 |
"step": 4440
|
| 1636 |
},
|
| 1637 |
{
|
| 1638 |
"epoch": 8.52772466539197,
|
| 1639 |
-
"grad_norm": 1.
|
| 1640 |
"learning_rate": 0.00016358614828978119,
|
| 1641 |
-
"loss": 0.
|
| 1642 |
"step": 4460
|
| 1643 |
},
|
| 1644 |
{
|
| 1645 |
"epoch": 8.565965583173996,
|
| 1646 |
-
"grad_norm": 1.
|
| 1647 |
"learning_rate": 0.00015933715742511153,
|
| 1648 |
-
"loss": 0.
|
| 1649 |
"step": 4480
|
| 1650 |
},
|
| 1651 |
{
|
| 1652 |
"epoch": 8.604206500956023,
|
| 1653 |
-
"grad_norm": 1.
|
| 1654 |
"learning_rate": 0.0001550881665604419,
|
| 1655 |
-
"loss": 0.
|
| 1656 |
"step": 4500
|
| 1657 |
},
|
| 1658 |
{
|
| 1659 |
"epoch": 8.64244741873805,
|
| 1660 |
-
"grad_norm": 1.
|
| 1661 |
"learning_rate": 0.00015083917569577227,
|
| 1662 |
-
"loss": 0.
|
| 1663 |
"step": 4520
|
| 1664 |
},
|
| 1665 |
{
|
| 1666 |
"epoch": 8.680688336520076,
|
| 1667 |
-
"grad_norm": 1.
|
| 1668 |
"learning_rate": 0.00014659018483110262,
|
| 1669 |
-
"loss": 0.
|
| 1670 |
"step": 4540
|
| 1671 |
},
|
| 1672 |
{
|
| 1673 |
"epoch": 8.718929254302104,
|
| 1674 |
-
"grad_norm": 1.
|
| 1675 |
"learning_rate": 0.00014234119396643296,
|
| 1676 |
-
"loss": 0.
|
| 1677 |
"step": 4560
|
| 1678 |
},
|
| 1679 |
{
|
| 1680 |
"epoch": 8.75717017208413,
|
| 1681 |
-
"grad_norm": 1.
|
| 1682 |
"learning_rate": 0.00013809220310176336,
|
| 1683 |
-
"loss": 0.
|
| 1684 |
"step": 4580
|
| 1685 |
},
|
| 1686 |
{
|
| 1687 |
"epoch": 8.795411089866157,
|
| 1688 |
-
"grad_norm": 1.
|
| 1689 |
"learning_rate": 0.0001338432122370937,
|
| 1690 |
-
"loss": 0.
|
| 1691 |
"step": 4600
|
| 1692 |
},
|
| 1693 |
{
|
| 1694 |
"epoch": 8.833652007648183,
|
| 1695 |
-
"grad_norm": 1.
|
| 1696 |
"learning_rate": 0.00012959422137242405,
|
| 1697 |
-
"loss": 0.
|
| 1698 |
"step": 4620
|
| 1699 |
},
|
| 1700 |
{
|
| 1701 |
"epoch": 8.87189292543021,
|
| 1702 |
-
"grad_norm": 1.
|
| 1703 |
"learning_rate": 0.0001253452305077544,
|
| 1704 |
-
"loss": 0.
|
| 1705 |
"step": 4640
|
| 1706 |
},
|
| 1707 |
{
|
| 1708 |
"epoch": 8.910133843212238,
|
| 1709 |
-
"grad_norm": 1.
|
| 1710 |
"learning_rate": 0.00012109623964308478,
|
| 1711 |
-
"loss": 0.
|
| 1712 |
"step": 4660
|
| 1713 |
},
|
| 1714 |
{
|
| 1715 |
"epoch": 8.948374760994264,
|
| 1716 |
-
"grad_norm": 1.
|
| 1717 |
"learning_rate": 0.00011684724877841513,
|
| 1718 |
-
"loss": 0.
|
| 1719 |
"step": 4680
|
| 1720 |
},
|
| 1721 |
{
|
| 1722 |
"epoch": 8.98661567877629,
|
| 1723 |
-
"grad_norm": 1.
|
| 1724 |
"learning_rate": 0.00011259825791374549,
|
| 1725 |
-
"loss": 0.
|
| 1726 |
"step": 4700
|
| 1727 |
},
|
| 1728 |
{
|
| 1729 |
"epoch": 9.0,
|
| 1730 |
"eval_accuracy": 0.9352842246888665,
|
| 1731 |
-
"eval_loss": 0.
|
| 1732 |
-
"eval_runtime":
|
| 1733 |
-
"eval_samples_per_second":
|
| 1734 |
-
"eval_steps_per_second":
|
| 1735 |
"step": 4707
|
| 1736 |
},
|
| 1737 |
{
|
| 1738 |
"epoch": 9.024856596558317,
|
| 1739 |
-
"grad_norm": 1.
|
| 1740 |
"learning_rate": 0.00010834926704907585,
|
| 1741 |
-
"loss": 0.
|
| 1742 |
"step": 4720
|
| 1743 |
},
|
| 1744 |
{
|
| 1745 |
"epoch": 9.063097514340344,
|
| 1746 |
-
"grad_norm": 1.
|
| 1747 |
"learning_rate": 0.0001041002761844062,
|
| 1748 |
-
"loss": 0.
|
| 1749 |
"step": 4740
|
| 1750 |
},
|
| 1751 |
{
|
| 1752 |
"epoch": 9.101338432122372,
|
| 1753 |
-
"grad_norm": 1.
|
| 1754 |
"learning_rate": 9.985128531973658e-05,
|
| 1755 |
-
"loss": 0.
|
| 1756 |
"step": 4760
|
| 1757 |
},
|
| 1758 |
{
|
| 1759 |
"epoch": 9.139579349904398,
|
| 1760 |
-
"grad_norm": 1.
|
| 1761 |
"learning_rate": 9.560229445506692e-05,
|
| 1762 |
-
"loss": 0.
|
| 1763 |
"step": 4780
|
| 1764 |
},
|
| 1765 |
{
|
| 1766 |
"epoch": 9.177820267686425,
|
| 1767 |
-
"grad_norm": 1.
|
| 1768 |
"learning_rate": 9.135330359039729e-05,
|
| 1769 |
-
"loss": 0.
|
| 1770 |
"step": 4800
|
| 1771 |
},
|
| 1772 |
{
|
| 1773 |
"epoch": 9.216061185468451,
|
| 1774 |
-
"grad_norm": 1.
|
| 1775 |
"learning_rate": 8.710431272572764e-05,
|
| 1776 |
-
"loss": 0.
|
| 1777 |
"step": 4820
|
| 1778 |
},
|
| 1779 |
{
|
| 1780 |
"epoch": 9.254302103250478,
|
| 1781 |
-
"grad_norm": 1.
|
| 1782 |
"learning_rate": 8.2855321861058e-05,
|
| 1783 |
-
"loss": 0.
|
| 1784 |
"step": 4840
|
| 1785 |
},
|
| 1786 |
{
|
| 1787 |
"epoch": 9.292543021032504,
|
| 1788 |
-
"grad_norm": 1.
|
| 1789 |
"learning_rate": 7.860633099638836e-05,
|
| 1790 |
-
"loss": 0.
|
| 1791 |
"step": 4860
|
| 1792 |
},
|
| 1793 |
{
|
| 1794 |
"epoch": 9.330783938814532,
|
| 1795 |
-
"grad_norm": 1.
|
| 1796 |
"learning_rate": 7.435734013171871e-05,
|
| 1797 |
-
"loss": 0.
|
| 1798 |
"step": 4880
|
| 1799 |
},
|
| 1800 |
{
|
| 1801 |
"epoch": 9.369024856596559,
|
| 1802 |
-
"grad_norm": 1.
|
| 1803 |
"learning_rate": 7.010834926704908e-05,
|
| 1804 |
-
"loss": 0.
|
| 1805 |
"step": 4900
|
| 1806 |
},
|
| 1807 |
{
|
| 1808 |
"epoch": 9.407265774378585,
|
| 1809 |
-
"grad_norm": 1.
|
| 1810 |
"learning_rate": 6.585935840237942e-05,
|
| 1811 |
-
"loss": 0.
|
| 1812 |
"step": 4920
|
| 1813 |
},
|
| 1814 |
{
|
| 1815 |
"epoch": 9.445506692160611,
|
| 1816 |
-
"grad_norm": 1.
|
| 1817 |
"learning_rate": 6.16103675377098e-05,
|
| 1818 |
-
"loss": 0.
|
| 1819 |
"step": 4940
|
| 1820 |
},
|
| 1821 |
{
|
| 1822 |
"epoch": 9.483747609942638,
|
| 1823 |
-
"grad_norm": 1.
|
| 1824 |
"learning_rate": 5.736137667304015e-05,
|
| 1825 |
-
"loss": 0.
|
| 1826 |
"step": 4960
|
| 1827 |
},
|
| 1828 |
{
|
| 1829 |
"epoch": 9.521988527724666,
|
| 1830 |
-
"grad_norm": 1.
|
| 1831 |
"learning_rate": 5.311238580837052e-05,
|
| 1832 |
-
"loss": 0.
|
| 1833 |
"step": 4980
|
| 1834 |
},
|
| 1835 |
{
|
| 1836 |
"epoch": 9.560229445506693,
|
| 1837 |
-
"grad_norm": 1.
|
| 1838 |
"learning_rate": 4.8863394943700874e-05,
|
| 1839 |
-
"loss": 0.
|
| 1840 |
"step": 5000
|
| 1841 |
},
|
| 1842 |
{
|
| 1843 |
"epoch": 9.598470363288719,
|
| 1844 |
-
"grad_norm": 1.
|
| 1845 |
"learning_rate": 4.461440407903123e-05,
|
| 1846 |
-
"loss": 0.
|
| 1847 |
"step": 5020
|
| 1848 |
},
|
| 1849 |
{
|
| 1850 |
"epoch": 9.636711281070745,
|
| 1851 |
-
"grad_norm": 1.
|
| 1852 |
"learning_rate": 4.036541321436159e-05,
|
| 1853 |
-
"loss": 0.
|
| 1854 |
"step": 5040
|
| 1855 |
},
|
| 1856 |
{
|
| 1857 |
"epoch": 9.674952198852772,
|
| 1858 |
-
"grad_norm": 1.
|
| 1859 |
"learning_rate": 3.6116422349691954e-05,
|
| 1860 |
-
"loss": 0.
|
| 1861 |
"step": 5060
|
| 1862 |
},
|
| 1863 |
{
|
| 1864 |
"epoch": 9.7131931166348,
|
| 1865 |
-
"grad_norm": 1.
|
| 1866 |
"learning_rate": 3.186743148502231e-05,
|
| 1867 |
-
"loss": 0.
|
| 1868 |
"step": 5080
|
| 1869 |
},
|
| 1870 |
{
|
| 1871 |
"epoch": 9.751434034416826,
|
| 1872 |
-
"grad_norm": 1.
|
| 1873 |
"learning_rate": 2.7618440620352666e-05,
|
| 1874 |
-
"loss": 0.
|
| 1875 |
"step": 5100
|
| 1876 |
},
|
| 1877 |
{
|
| 1878 |
"epoch": 9.789674952198853,
|
| 1879 |
-
"grad_norm": 1.
|
| 1880 |
"learning_rate": 2.3369449755683023e-05,
|
| 1881 |
-
"loss": 0.
|
| 1882 |
"step": 5120
|
| 1883 |
},
|
| 1884 |
{
|
| 1885 |
"epoch": 9.82791586998088,
|
| 1886 |
-
"grad_norm": 1.
|
| 1887 |
"learning_rate": 1.9120458891013384e-05,
|
| 1888 |
-
"loss": 0.
|
| 1889 |
"step": 5140
|
| 1890 |
},
|
| 1891 |
{
|
| 1892 |
"epoch": 9.866156787762906,
|
| 1893 |
-
"grad_norm": 1.
|
| 1894 |
"learning_rate": 1.4871468026343743e-05,
|
| 1895 |
-
"loss": 0.
|
| 1896 |
"step": 5160
|
| 1897 |
},
|
| 1898 |
{
|
| 1899 |
"epoch": 9.904397705544934,
|
| 1900 |
-
"grad_norm": 1.
|
| 1901 |
"learning_rate": 1.0622477161674103e-05,
|
| 1902 |
-
"loss": 0.
|
| 1903 |
"step": 5180
|
| 1904 |
},
|
| 1905 |
{
|
| 1906 |
"epoch": 9.94263862332696,
|
| 1907 |
-
"grad_norm": 1.
|
| 1908 |
"learning_rate": 6.373486297004461e-06,
|
| 1909 |
-
"loss": 0.
|
| 1910 |
"step": 5200
|
| 1911 |
},
|
| 1912 |
{
|
| 1913 |
"epoch": 9.980879541108987,
|
| 1914 |
-
"grad_norm": 1.
|
| 1915 |
"learning_rate": 2.1244954323348204e-06,
|
| 1916 |
-
"loss": 0.
|
| 1917 |
"step": 5220
|
| 1918 |
},
|
| 1919 |
{
|
| 1920 |
"epoch": 10.0,
|
| 1921 |
-
"eval_accuracy": 0.
|
| 1922 |
-
"eval_loss": 0.
|
| 1923 |
-
"eval_runtime":
|
| 1924 |
-
"eval_samples_per_second":
|
| 1925 |
-
"eval_steps_per_second":
|
| 1926 |
"step": 5230
|
| 1927 |
},
|
| 1928 |
{
|
| 1929 |
"epoch": 10.0,
|
| 1930 |
"step": 5230,
|
| 1931 |
"total_flos": 1.96318398191328e+18,
|
| 1932 |
-
"train_loss": 2.
|
| 1933 |
-
"train_runtime":
|
| 1934 |
-
"train_samples_per_second":
|
| 1935 |
-
"train_steps_per_second": 0.
|
| 1936 |
}
|
| 1937 |
],
|
| 1938 |
"logging_steps": 20,
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.9405314497140935,
|
| 3 |
"best_model_checkpoint": "/mnt/data4_HDD_14TB/yang/voxceleb-checkpoints/xvector/voxceleb1/finetune/ce-len3-bs256-lr1e-3/checkpoint-5230",
|
| 4 |
"epoch": 10.0,
|
| 5 |
"eval_steps": 500,
|
|
|
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.03824091778202677,
|
| 13 |
+
"grad_norm": 4.702692031860352,
|
| 14 |
"learning_rate": 3.824091778202677e-05,
|
| 15 |
+
"loss": 7.1455,
|
| 16 |
"step": 20
|
| 17 |
},
|
| 18 |
{
|
| 19 |
"epoch": 0.07648183556405354,
|
| 20 |
+
"grad_norm": 4.504467487335205,
|
| 21 |
"learning_rate": 7.648183556405354e-05,
|
| 22 |
+
"loss": 7.116,
|
| 23 |
"step": 40
|
| 24 |
},
|
| 25 |
{
|
| 26 |
"epoch": 0.1147227533460803,
|
| 27 |
+
"grad_norm": 3.964728832244873,
|
| 28 |
"learning_rate": 0.0001147227533460803,
|
| 29 |
+
"loss": 7.0566,
|
| 30 |
"step": 60
|
| 31 |
},
|
| 32 |
{
|
| 33 |
"epoch": 0.15296367112810708,
|
| 34 |
+
"grad_norm": 3.199570417404175,
|
| 35 |
"learning_rate": 0.00015296367112810707,
|
| 36 |
+
"loss": 6.972,
|
| 37 |
"step": 80
|
| 38 |
},
|
| 39 |
{
|
| 40 |
"epoch": 0.19120458891013384,
|
| 41 |
+
"grad_norm": 2.6367344856262207,
|
| 42 |
"learning_rate": 0.00019120458891013384,
|
| 43 |
+
"loss": 6.8778,
|
| 44 |
"step": 100
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 0.2294455066921606,
|
| 48 |
+
"grad_norm": 2.1930582523345947,
|
| 49 |
"learning_rate": 0.0002294455066921606,
|
| 50 |
+
"loss": 6.733,
|
| 51 |
"step": 120
|
| 52 |
},
|
| 53 |
{
|
| 54 |
"epoch": 0.2676864244741874,
|
| 55 |
+
"grad_norm": 1.9982482194900513,
|
| 56 |
"learning_rate": 0.0002676864244741874,
|
| 57 |
+
"loss": 6.5814,
|
| 58 |
"step": 140
|
| 59 |
},
|
| 60 |
{
|
| 61 |
"epoch": 0.30592734225621415,
|
| 62 |
+
"grad_norm": 1.8051823377609253,
|
| 63 |
"learning_rate": 0.00030592734225621415,
|
| 64 |
+
"loss": 6.4206,
|
| 65 |
"step": 160
|
| 66 |
},
|
| 67 |
{
|
| 68 |
"epoch": 0.3441682600382409,
|
| 69 |
+
"grad_norm": 1.757859706878662,
|
| 70 |
"learning_rate": 0.00034416826003824094,
|
| 71 |
+
"loss": 6.2424,
|
| 72 |
"step": 180
|
| 73 |
},
|
| 74 |
{
|
| 75 |
"epoch": 0.3824091778202677,
|
| 76 |
+
"grad_norm": 1.7747690677642822,
|
| 77 |
"learning_rate": 0.0003824091778202677,
|
| 78 |
+
"loss": 6.0657,
|
| 79 |
"step": 200
|
| 80 |
},
|
| 81 |
{
|
| 82 |
"epoch": 0.42065009560229444,
|
| 83 |
+
"grad_norm": 1.7719988822937012,
|
| 84 |
"learning_rate": 0.0004206500956022944,
|
| 85 |
+
"loss": 5.9722,
|
| 86 |
"step": 220
|
| 87 |
},
|
| 88 |
{
|
| 89 |
"epoch": 0.4588910133843212,
|
| 90 |
+
"grad_norm": 1.934911847114563,
|
| 91 |
"learning_rate": 0.0004588910133843212,
|
| 92 |
+
"loss": 5.814,
|
| 93 |
"step": 240
|
| 94 |
},
|
| 95 |
{
|
| 96 |
"epoch": 0.497131931166348,
|
| 97 |
+
"grad_norm": 1.793244481086731,
|
| 98 |
"learning_rate": 0.0004971319311663481,
|
| 99 |
+
"loss": 5.6998,
|
| 100 |
"step": 260
|
| 101 |
},
|
| 102 |
{
|
| 103 |
"epoch": 0.5353728489483748,
|
| 104 |
+
"grad_norm": 1.7790417671203613,
|
| 105 |
"learning_rate": 0.0005353728489483748,
|
| 106 |
+
"loss": 5.6115,
|
| 107 |
"step": 280
|
| 108 |
},
|
| 109 |
{
|
| 110 |
"epoch": 0.5736137667304015,
|
| 111 |
+
"grad_norm": 1.8355106115341187,
|
| 112 |
"learning_rate": 0.0005736137667304016,
|
| 113 |
+
"loss": 5.5236,
|
| 114 |
"step": 300
|
| 115 |
},
|
| 116 |
{
|
| 117 |
"epoch": 0.6118546845124283,
|
| 118 |
+
"grad_norm": 1.7114174365997314,
|
| 119 |
"learning_rate": 0.0006118546845124283,
|
| 120 |
+
"loss": 5.3894,
|
| 121 |
"step": 320
|
| 122 |
},
|
| 123 |
{
|
| 124 |
"epoch": 0.6500956022944551,
|
| 125 |
+
"grad_norm": 1.877690315246582,
|
| 126 |
"learning_rate": 0.000650095602294455,
|
| 127 |
+
"loss": 5.3336,
|
| 128 |
"step": 340
|
| 129 |
},
|
| 130 |
{
|
| 131 |
"epoch": 0.6883365200764818,
|
| 132 |
+
"grad_norm": 1.8771674633026123,
|
| 133 |
"learning_rate": 0.0006883365200764819,
|
| 134 |
+
"loss": 5.2577,
|
| 135 |
"step": 360
|
| 136 |
},
|
| 137 |
{
|
| 138 |
"epoch": 0.7265774378585086,
|
| 139 |
+
"grad_norm": 1.9654275178909302,
|
| 140 |
"learning_rate": 0.0007265774378585086,
|
| 141 |
+
"loss": 5.1333,
|
| 142 |
"step": 380
|
| 143 |
},
|
| 144 |
{
|
| 145 |
"epoch": 0.7648183556405354,
|
| 146 |
+
"grad_norm": 1.9327517747879028,
|
| 147 |
"learning_rate": 0.0007648183556405354,
|
| 148 |
+
"loss": 5.0882,
|
| 149 |
"step": 400
|
| 150 |
},
|
| 151 |
{
|
| 152 |
"epoch": 0.8030592734225621,
|
| 153 |
+
"grad_norm": 1.8918468952178955,
|
| 154 |
"learning_rate": 0.0008030592734225621,
|
| 155 |
+
"loss": 5.0404,
|
| 156 |
"step": 420
|
| 157 |
},
|
| 158 |
{
|
| 159 |
"epoch": 0.8413001912045889,
|
| 160 |
+
"grad_norm": 1.8536239862442017,
|
| 161 |
"learning_rate": 0.0008413001912045888,
|
| 162 |
+
"loss": 4.9524,
|
| 163 |
"step": 440
|
| 164 |
},
|
| 165 |
{
|
| 166 |
"epoch": 0.8795411089866156,
|
| 167 |
+
"grad_norm": 1.8849778175354004,
|
| 168 |
"learning_rate": 0.0008795411089866157,
|
| 169 |
+
"loss": 4.8673,
|
| 170 |
"step": 460
|
| 171 |
},
|
| 172 |
{
|
| 173 |
"epoch": 0.9177820267686424,
|
| 174 |
+
"grad_norm": 1.8270999193191528,
|
| 175 |
"learning_rate": 0.0009177820267686424,
|
| 176 |
+
"loss": 4.8456,
|
| 177 |
"step": 480
|
| 178 |
},
|
| 179 |
{
|
| 180 |
"epoch": 0.9560229445506692,
|
| 181 |
+
"grad_norm": 1.8521556854248047,
|
| 182 |
"learning_rate": 0.0009560229445506692,
|
| 183 |
+
"loss": 4.7748,
|
| 184 |
"step": 500
|
| 185 |
},
|
| 186 |
{
|
| 187 |
"epoch": 0.994263862332696,
|
| 188 |
+
"grad_norm": 1.9331077337265015,
|
| 189 |
"learning_rate": 0.0009942638623326961,
|
| 190 |
+
"loss": 4.6869,
|
| 191 |
"step": 520
|
| 192 |
},
|
| 193 |
{
|
| 194 |
"epoch": 1.0,
|
| 195 |
+
"eval_accuracy": 0.19596367305751766,
|
| 196 |
+
"eval_loss": 4.119868278503418,
|
| 197 |
+
"eval_runtime": 539.7217,
|
| 198 |
+
"eval_samples_per_second": 27.542,
|
| 199 |
+
"eval_steps_per_second": 27.542,
|
| 200 |
"step": 523
|
| 201 |
},
|
| 202 |
{
|
| 203 |
"epoch": 1.0325047801147227,
|
| 204 |
+
"grad_norm": 1.7894033193588257,
|
| 205 |
"learning_rate": 0.0009963883577650309,
|
| 206 |
+
"loss": 4.5805,
|
| 207 |
"step": 540
|
| 208 |
},
|
| 209 |
{
|
| 210 |
"epoch": 1.0707456978967496,
|
| 211 |
+
"grad_norm": 1.9136412143707275,
|
| 212 |
"learning_rate": 0.0009921393669003612,
|
| 213 |
+
"loss": 4.5223,
|
| 214 |
"step": 560
|
| 215 |
},
|
| 216 |
{
|
| 217 |
"epoch": 1.1089866156787762,
|
| 218 |
+
"grad_norm": 1.8342599868774414,
|
| 219 |
"learning_rate": 0.0009878903760356915,
|
| 220 |
+
"loss": 4.4213,
|
| 221 |
"step": 580
|
| 222 |
},
|
| 223 |
{
|
| 224 |
"epoch": 1.147227533460803,
|
| 225 |
+
"grad_norm": 1.7360094785690308,
|
| 226 |
"learning_rate": 0.0009836413851710218,
|
| 227 |
+
"loss": 4.409,
|
| 228 |
"step": 600
|
| 229 |
},
|
| 230 |
{
|
| 231 |
"epoch": 1.1854684512428297,
|
| 232 |
+
"grad_norm": 1.8302013874053955,
|
| 233 |
"learning_rate": 0.0009793923943063523,
|
| 234 |
+
"loss": 4.3382,
|
| 235 |
"step": 620
|
| 236 |
},
|
| 237 |
{
|
| 238 |
"epoch": 1.2237093690248566,
|
| 239 |
+
"grad_norm": 1.847433090209961,
|
| 240 |
"learning_rate": 0.0009751434034416827,
|
| 241 |
+
"loss": 4.2381,
|
| 242 |
"step": 640
|
| 243 |
},
|
| 244 |
{
|
| 245 |
"epoch": 1.2619502868068833,
|
| 246 |
+
"grad_norm": 1.866734504699707,
|
| 247 |
"learning_rate": 0.000970894412577013,
|
| 248 |
+
"loss": 4.1802,
|
| 249 |
"step": 660
|
| 250 |
},
|
| 251 |
{
|
| 252 |
"epoch": 1.3001912045889101,
|
| 253 |
+
"grad_norm": 1.9123674631118774,
|
| 254 |
"learning_rate": 0.0009666454217123433,
|
| 255 |
+
"loss": 4.1404,
|
| 256 |
"step": 680
|
| 257 |
},
|
| 258 |
{
|
| 259 |
"epoch": 1.338432122370937,
|
| 260 |
+
"grad_norm": 1.8355252742767334,
|
| 261 |
"learning_rate": 0.0009623964308476737,
|
| 262 |
+
"loss": 4.059,
|
| 263 |
"step": 700
|
| 264 |
},
|
| 265 |
{
|
| 266 |
"epoch": 1.3766730401529637,
|
| 267 |
+
"grad_norm": 1.7890186309814453,
|
| 268 |
"learning_rate": 0.000958147439983004,
|
| 269 |
+
"loss": 4.0086,
|
| 270 |
"step": 720
|
| 271 |
},
|
| 272 |
{
|
| 273 |
"epoch": 1.4149139579349903,
|
| 274 |
+
"grad_norm": 1.847299337387085,
|
| 275 |
"learning_rate": 0.0009538984491183344,
|
| 276 |
+
"loss": 3.9641,
|
| 277 |
"step": 740
|
| 278 |
},
|
| 279 |
{
|
| 280 |
"epoch": 1.4531548757170172,
|
| 281 |
+
"grad_norm": 1.8219211101531982,
|
| 282 |
"learning_rate": 0.0009496494582536647,
|
| 283 |
+
"loss": 3.9291,
|
| 284 |
"step": 760
|
| 285 |
},
|
| 286 |
{
|
| 287 |
"epoch": 1.491395793499044,
|
| 288 |
+
"grad_norm": 1.8026444911956787,
|
| 289 |
"learning_rate": 0.0009454004673889951,
|
| 290 |
+
"loss": 3.8577,
|
| 291 |
"step": 780
|
| 292 |
},
|
| 293 |
{
|
| 294 |
"epoch": 1.5296367112810707,
|
| 295 |
+
"grad_norm": 1.7959771156311035,
|
| 296 |
"learning_rate": 0.0009411514765243255,
|
| 297 |
+
"loss": 3.8234,
|
| 298 |
"step": 800
|
| 299 |
},
|
| 300 |
{
|
| 301 |
"epoch": 1.5678776290630974,
|
| 302 |
+
"grad_norm": 1.7638428211212158,
|
| 303 |
"learning_rate": 0.0009369024856596558,
|
| 304 |
+
"loss": 3.7132,
|
| 305 |
"step": 820
|
| 306 |
},
|
| 307 |
{
|
| 308 |
"epoch": 1.6061185468451242,
|
| 309 |
+
"grad_norm": 1.8295230865478516,
|
| 310 |
"learning_rate": 0.0009326534947949862,
|
| 311 |
+
"loss": 3.7057,
|
| 312 |
"step": 840
|
| 313 |
},
|
| 314 |
{
|
| 315 |
"epoch": 1.644359464627151,
|
| 316 |
+
"grad_norm": 1.8669532537460327,
|
| 317 |
"learning_rate": 0.0009284045039303166,
|
| 318 |
+
"loss": 3.6656,
|
| 319 |
"step": 860
|
| 320 |
},
|
| 321 |
{
|
| 322 |
"epoch": 1.682600382409178,
|
| 323 |
+
"grad_norm": 1.8251906633377075,
|
| 324 |
"learning_rate": 0.0009241555130656469,
|
| 325 |
+
"loss": 3.591,
|
| 326 |
"step": 880
|
| 327 |
},
|
| 328 |
{
|
| 329 |
"epoch": 1.7208413001912046,
|
| 330 |
+
"grad_norm": 1.825548529624939,
|
| 331 |
"learning_rate": 0.0009199065222009773,
|
| 332 |
+
"loss": 3.5281,
|
| 333 |
"step": 900
|
| 334 |
},
|
| 335 |
{
|
| 336 |
"epoch": 1.7590822179732313,
|
| 337 |
+
"grad_norm": 1.7811344861984253,
|
| 338 |
"learning_rate": 0.0009156575313363077,
|
| 339 |
+
"loss": 3.4841,
|
| 340 |
"step": 920
|
| 341 |
},
|
| 342 |
{
|
| 343 |
"epoch": 1.7973231357552581,
|
| 344 |
+
"grad_norm": 1.823803186416626,
|
| 345 |
"learning_rate": 0.000911408540471638,
|
| 346 |
+
"loss": 3.4707,
|
| 347 |
"step": 940
|
| 348 |
},
|
| 349 |
{
|
| 350 |
"epoch": 1.835564053537285,
|
| 351 |
+
"grad_norm": 1.872054100036621,
|
| 352 |
"learning_rate": 0.0009071595496069684,
|
| 353 |
+
"loss": 3.4532,
|
| 354 |
"step": 960
|
| 355 |
},
|
| 356 |
{
|
| 357 |
"epoch": 1.8738049713193117,
|
| 358 |
+
"grad_norm": 1.7651457786560059,
|
| 359 |
"learning_rate": 0.0009029105587422988,
|
| 360 |
+
"loss": 3.4224,
|
| 361 |
"step": 980
|
| 362 |
},
|
| 363 |
{
|
| 364 |
"epoch": 1.9120458891013383,
|
| 365 |
+
"grad_norm": 1.7336605787277222,
|
| 366 |
"learning_rate": 0.0008986615678776291,
|
| 367 |
+
"loss": 3.3199,
|
| 368 |
"step": 1000
|
| 369 |
},
|
| 370 |
{
|
| 371 |
"epoch": 1.9502868068833652,
|
| 372 |
+
"grad_norm": 1.8058604001998901,
|
| 373 |
"learning_rate": 0.0008944125770129595,
|
| 374 |
+
"loss": 3.2814,
|
| 375 |
"step": 1020
|
| 376 |
},
|
| 377 |
{
|
| 378 |
"epoch": 1.988527724665392,
|
| 379 |
+
"grad_norm": 1.9400501251220703,
|
| 380 |
"learning_rate": 0.0008901635861482899,
|
| 381 |
+
"loss": 3.2423,
|
| 382 |
"step": 1040
|
| 383 |
},
|
| 384 |
{
|
| 385 |
"epoch": 2.0,
|
| 386 |
+
"eval_accuracy": 0.5047426841574167,
|
| 387 |
+
"eval_loss": 2.282437801361084,
|
| 388 |
+
"eval_runtime": 710.9931,
|
| 389 |
+
"eval_samples_per_second": 20.907,
|
| 390 |
+
"eval_steps_per_second": 20.907,
|
| 391 |
"step": 1046
|
| 392 |
},
|
| 393 |
{
|
| 394 |
"epoch": 2.026768642447419,
|
| 395 |
+
"grad_norm": 1.7496325969696045,
|
| 396 |
"learning_rate": 0.0008859145952836202,
|
| 397 |
+
"loss": 3.1858,
|
| 398 |
"step": 1060
|
| 399 |
},
|
| 400 |
{
|
| 401 |
"epoch": 2.0650095602294454,
|
| 402 |
+
"grad_norm": 1.7203223705291748,
|
| 403 |
"learning_rate": 0.0008816656044189504,
|
| 404 |
+
"loss": 3.0482,
|
| 405 |
"step": 1080
|
| 406 |
},
|
| 407 |
{
|
| 408 |
"epoch": 2.1032504780114722,
|
| 409 |
+
"grad_norm": 1.6859164237976074,
|
| 410 |
"learning_rate": 0.000877416613554281,
|
| 411 |
+
"loss": 3.0764,
|
| 412 |
"step": 1100
|
| 413 |
},
|
| 414 |
{
|
| 415 |
"epoch": 2.141491395793499,
|
| 416 |
+
"grad_norm": 1.887332558631897,
|
| 417 |
"learning_rate": 0.0008731676226896112,
|
| 418 |
+
"loss": 2.9918,
|
| 419 |
"step": 1120
|
| 420 |
},
|
| 421 |
{
|
| 422 |
"epoch": 2.179732313575526,
|
| 423 |
+
"grad_norm": 1.7712619304656982,
|
| 424 |
"learning_rate": 0.0008689186318249415,
|
| 425 |
+
"loss": 2.9791,
|
| 426 |
"step": 1140
|
| 427 |
},
|
| 428 |
{
|
| 429 |
"epoch": 2.2179732313575524,
|
| 430 |
+
"grad_norm": 1.8518322706222534,
|
| 431 |
"learning_rate": 0.000864669640960272,
|
| 432 |
+
"loss": 2.9064,
|
| 433 |
"step": 1160
|
| 434 |
},
|
| 435 |
{
|
| 436 |
"epoch": 2.2562141491395793,
|
| 437 |
+
"grad_norm": 1.8636976480484009,
|
| 438 |
"learning_rate": 0.0008604206500956023,
|
| 439 |
+
"loss": 2.9346,
|
| 440 |
"step": 1180
|
| 441 |
},
|
| 442 |
{
|
| 443 |
"epoch": 2.294455066921606,
|
| 444 |
+
"grad_norm": 1.8007034063339233,
|
| 445 |
"learning_rate": 0.0008561716592309326,
|
| 446 |
+
"loss": 2.9154,
|
| 447 |
"step": 1200
|
| 448 |
},
|
| 449 |
{
|
| 450 |
"epoch": 2.332695984703633,
|
| 451 |
+
"grad_norm": 1.8480207920074463,
|
| 452 |
"learning_rate": 0.000851922668366263,
|
| 453 |
+
"loss": 2.8311,
|
| 454 |
"step": 1220
|
| 455 |
},
|
| 456 |
{
|
| 457 |
"epoch": 2.3709369024856595,
|
| 458 |
+
"grad_norm": 1.8463302850723267,
|
| 459 |
"learning_rate": 0.0008476736775015934,
|
| 460 |
+
"loss": 2.843,
|
| 461 |
"step": 1240
|
| 462 |
},
|
| 463 |
{
|
| 464 |
"epoch": 2.4091778202676863,
|
| 465 |
+
"grad_norm": 1.8563566207885742,
|
| 466 |
"learning_rate": 0.0008434246866369237,
|
| 467 |
+
"loss": 2.8704,
|
| 468 |
"step": 1260
|
| 469 |
},
|
| 470 |
{
|
| 471 |
"epoch": 2.447418738049713,
|
| 472 |
+
"grad_norm": 1.8388174772262573,
|
| 473 |
"learning_rate": 0.0008391756957722541,
|
| 474 |
+
"loss": 2.7794,
|
| 475 |
"step": 1280
|
| 476 |
},
|
| 477 |
{
|
| 478 |
"epoch": 2.48565965583174,
|
| 479 |
+
"grad_norm": 1.787711262702942,
|
| 480 |
"learning_rate": 0.0008349267049075845,
|
| 481 |
+
"loss": 2.7776,
|
| 482 |
"step": 1300
|
| 483 |
},
|
| 484 |
{
|
| 485 |
"epoch": 2.5239005736137665,
|
| 486 |
+
"grad_norm": 1.6573237180709839,
|
| 487 |
"learning_rate": 0.0008306777140429148,
|
| 488 |
+
"loss": 2.7288,
|
| 489 |
"step": 1320
|
| 490 |
},
|
| 491 |
{
|
| 492 |
"epoch": 2.5621414913957934,
|
| 493 |
+
"grad_norm": 1.8304985761642456,
|
| 494 |
"learning_rate": 0.0008264287231782451,
|
| 495 |
+
"loss": 2.6598,
|
| 496 |
"step": 1340
|
| 497 |
},
|
| 498 |
{
|
| 499 |
"epoch": 2.6003824091778203,
|
| 500 |
+
"grad_norm": 1.769439458847046,
|
| 501 |
"learning_rate": 0.0008221797323135756,
|
| 502 |
+
"loss": 2.6842,
|
| 503 |
"step": 1360
|
| 504 |
},
|
| 505 |
{
|
| 506 |
"epoch": 2.638623326959847,
|
| 507 |
+
"grad_norm": 1.7404167652130127,
|
| 508 |
"learning_rate": 0.0008179307414489059,
|
| 509 |
+
"loss": 2.5974,
|
| 510 |
"step": 1380
|
| 511 |
},
|
| 512 |
{
|
| 513 |
"epoch": 2.676864244741874,
|
| 514 |
+
"grad_norm": 1.7064534425735474,
|
| 515 |
"learning_rate": 0.0008136817505842362,
|
| 516 |
+
"loss": 2.6557,
|
| 517 |
"step": 1400
|
| 518 |
},
|
| 519 |
{
|
| 520 |
"epoch": 2.7151051625239004,
|
| 521 |
+
"grad_norm": 1.784652590751648,
|
| 522 |
"learning_rate": 0.0008094327597195667,
|
| 523 |
+
"loss": 2.5701,
|
| 524 |
"step": 1420
|
| 525 |
},
|
| 526 |
{
|
| 527 |
"epoch": 2.7533460803059273,
|
| 528 |
+
"grad_norm": 1.730402946472168,
|
| 529 |
"learning_rate": 0.000805183768854897,
|
| 530 |
+
"loss": 2.5879,
|
| 531 |
"step": 1440
|
| 532 |
},
|
| 533 |
{
|
| 534 |
"epoch": 2.791586998087954,
|
| 535 |
+
"grad_norm": 1.803881049156189,
|
| 536 |
"learning_rate": 0.0008009347779902273,
|
| 537 |
+
"loss": 2.5413,
|
| 538 |
"step": 1460
|
| 539 |
},
|
| 540 |
{
|
| 541 |
"epoch": 2.8298279158699806,
|
| 542 |
+
"grad_norm": 1.7114533185958862,
|
| 543 |
"learning_rate": 0.0007966857871255578,
|
| 544 |
+
"loss": 2.4823,
|
| 545 |
"step": 1480
|
| 546 |
},
|
| 547 |
{
|
| 548 |
"epoch": 2.8680688336520075,
|
| 549 |
+
"grad_norm": 1.7487016916275024,
|
| 550 |
"learning_rate": 0.000792436796260888,
|
| 551 |
+
"loss": 2.4236,
|
| 552 |
"step": 1500
|
| 553 |
},
|
| 554 |
{
|
| 555 |
"epoch": 2.9063097514340344,
|
| 556 |
+
"grad_norm": 1.7806780338287354,
|
| 557 |
"learning_rate": 0.0007881878053962183,
|
| 558 |
+
"loss": 2.4762,
|
| 559 |
"step": 1520
|
| 560 |
},
|
| 561 |
{
|
| 562 |
"epoch": 2.9445506692160612,
|
| 563 |
+
"grad_norm": 1.851486086845398,
|
| 564 |
"learning_rate": 0.0007839388145315488,
|
| 565 |
+
"loss": 2.4221,
|
| 566 |
"step": 1540
|
| 567 |
},
|
| 568 |
{
|
| 569 |
"epoch": 2.982791586998088,
|
| 570 |
+
"grad_norm": 1.779451608657837,
|
| 571 |
"learning_rate": 0.0007796898236668791,
|
| 572 |
+
"loss": 2.4164,
|
| 573 |
"step": 1560
|
| 574 |
},
|
| 575 |
{
|
| 576 |
"epoch": 3.0,
|
| 577 |
+
"eval_accuracy": 0.6816010763538514,
|
| 578 |
+
"eval_loss": 1.4862462282180786,
|
| 579 |
+
"eval_runtime": 715.5989,
|
| 580 |
+
"eval_samples_per_second": 20.773,
|
| 581 |
+
"eval_steps_per_second": 20.773,
|
| 582 |
"step": 1569
|
| 583 |
},
|
| 584 |
{
|
| 585 |
"epoch": 3.0210325047801145,
|
| 586 |
+
"grad_norm": 1.7617199420928955,
|
| 587 |
"learning_rate": 0.0007754408328022094,
|
| 588 |
+
"loss": 2.3348,
|
| 589 |
"step": 1580
|
| 590 |
},
|
| 591 |
{
|
| 592 |
"epoch": 3.0592734225621414,
|
| 593 |
+
"grad_norm": 1.7850340604782104,
|
| 594 |
"learning_rate": 0.0007711918419375399,
|
| 595 |
+
"loss": 2.3196,
|
| 596 |
"step": 1600
|
| 597 |
},
|
| 598 |
{
|
| 599 |
"epoch": 3.0975143403441683,
|
| 600 |
+
"grad_norm": 1.828715205192566,
|
| 601 |
"learning_rate": 0.0007669428510728702,
|
| 602 |
+
"loss": 2.2991,
|
| 603 |
"step": 1620
|
| 604 |
},
|
| 605 |
{
|
| 606 |
"epoch": 3.135755258126195,
|
| 607 |
+
"grad_norm": 1.7825413942337036,
|
| 608 |
"learning_rate": 0.0007626938602082005,
|
| 609 |
+
"loss": 2.2354,
|
| 610 |
"step": 1640
|
| 611 |
},
|
| 612 |
{
|
| 613 |
"epoch": 3.173996175908222,
|
| 614 |
+
"grad_norm": 1.8411946296691895,
|
| 615 |
"learning_rate": 0.0007584448693435309,
|
| 616 |
+
"loss": 2.221,
|
| 617 |
"step": 1660
|
| 618 |
},
|
| 619 |
{
|
| 620 |
"epoch": 3.2122370936902485,
|
| 621 |
+
"grad_norm": 1.8236651420593262,
|
| 622 |
"learning_rate": 0.0007541958784788613,
|
| 623 |
+
"loss": 2.1939,
|
| 624 |
"step": 1680
|
| 625 |
},
|
| 626 |
{
|
| 627 |
"epoch": 3.2504780114722753,
|
| 628 |
+
"grad_norm": 1.8275988101959229,
|
| 629 |
"learning_rate": 0.0007499468876141916,
|
| 630 |
+
"loss": 2.211,
|
| 631 |
"step": 1700
|
| 632 |
},
|
| 633 |
{
|
| 634 |
"epoch": 3.288718929254302,
|
| 635 |
+
"grad_norm": 1.7743233442306519,
|
| 636 |
"learning_rate": 0.000745697896749522,
|
| 637 |
+
"loss": 2.1454,
|
| 638 |
"step": 1720
|
| 639 |
},
|
| 640 |
{
|
| 641 |
"epoch": 3.3269598470363286,
|
| 642 |
+
"grad_norm": 1.7873393297195435,
|
| 643 |
"learning_rate": 0.0007414489058848524,
|
| 644 |
+
"loss": 2.1258,
|
| 645 |
"step": 1740
|
| 646 |
},
|
| 647 |
{
|
| 648 |
"epoch": 3.3652007648183555,
|
| 649 |
+
"grad_norm": 1.8012022972106934,
|
| 650 |
"learning_rate": 0.0007371999150201827,
|
| 651 |
+
"loss": 2.1101,
|
| 652 |
"step": 1760
|
| 653 |
},
|
| 654 |
{
|
| 655 |
"epoch": 3.4034416826003824,
|
| 656 |
+
"grad_norm": 1.8000600337982178,
|
| 657 |
"learning_rate": 0.0007329509241555131,
|
| 658 |
+
"loss": 2.1246,
|
| 659 |
"step": 1780
|
| 660 |
},
|
| 661 |
{
|
| 662 |
"epoch": 3.4416826003824093,
|
| 663 |
+
"grad_norm": 1.7723950147628784,
|
| 664 |
"learning_rate": 0.0007287019332908435,
|
| 665 |
+
"loss": 2.1244,
|
| 666 |
"step": 1800
|
| 667 |
},
|
| 668 |
{
|
| 669 |
"epoch": 3.479923518164436,
|
| 670 |
+
"grad_norm": 1.8095979690551758,
|
| 671 |
"learning_rate": 0.0007244529424261738,
|
| 672 |
+
"loss": 2.1099,
|
| 673 |
"step": 1820
|
| 674 |
},
|
| 675 |
{
|
| 676 |
"epoch": 3.5181644359464626,
|
| 677 |
+
"grad_norm": 1.8022161722183228,
|
| 678 |
"learning_rate": 0.0007202039515615042,
|
| 679 |
+
"loss": 2.0703,
|
| 680 |
"step": 1840
|
| 681 |
},
|
| 682 |
{
|
| 683 |
"epoch": 3.5564053537284894,
|
| 684 |
+
"grad_norm": 1.7775332927703857,
|
| 685 |
"learning_rate": 0.0007159549606968346,
|
| 686 |
+
"loss": 2.0937,
|
| 687 |
"step": 1860
|
| 688 |
},
|
| 689 |
{
|
| 690 |
"epoch": 3.5946462715105163,
|
| 691 |
+
"grad_norm": 1.829291820526123,
|
| 692 |
"learning_rate": 0.0007117059698321649,
|
| 693 |
+
"loss": 2.0305,
|
| 694 |
"step": 1880
|
| 695 |
},
|
| 696 |
{
|
| 697 |
"epoch": 3.632887189292543,
|
| 698 |
+
"grad_norm": 1.731218934059143,
|
| 699 |
"learning_rate": 0.0007074569789674953,
|
| 700 |
+
"loss": 2.0528,
|
| 701 |
"step": 1900
|
| 702 |
},
|
| 703 |
{
|
| 704 |
"epoch": 3.67112810707457,
|
| 705 |
+
"grad_norm": 1.9170475006103516,
|
| 706 |
"learning_rate": 0.0007032079881028257,
|
| 707 |
+
"loss": 2.0311,
|
| 708 |
"step": 1920
|
| 709 |
},
|
| 710 |
{
|
| 711 |
"epoch": 3.7093690248565965,
|
| 712 |
+
"grad_norm": 1.6934610605239868,
|
| 713 |
"learning_rate": 0.0006989589972381559,
|
| 714 |
+
"loss": 2.006,
|
| 715 |
"step": 1940
|
| 716 |
},
|
| 717 |
{
|
| 718 |
"epoch": 3.7476099426386233,
|
| 719 |
+
"grad_norm": 1.792523741722107,
|
| 720 |
"learning_rate": 0.0006947100063734863,
|
| 721 |
+
"loss": 1.9627,
|
| 722 |
"step": 1960
|
| 723 |
},
|
| 724 |
{
|
| 725 |
"epoch": 3.78585086042065,
|
| 726 |
+
"grad_norm": 1.7618036270141602,
|
| 727 |
"learning_rate": 0.0006904610155088166,
|
| 728 |
+
"loss": 2.0141,
|
| 729 |
"step": 1980
|
| 730 |
},
|
| 731 |
{
|
| 732 |
"epoch": 3.8240917782026767,
|
| 733 |
+
"grad_norm": 1.7026081085205078,
|
| 734 |
"learning_rate": 0.000686212024644147,
|
| 735 |
+
"loss": 1.9489,
|
| 736 |
"step": 2000
|
| 737 |
},
|
| 738 |
{
|
| 739 |
"epoch": 3.8623326959847035,
|
| 740 |
+
"grad_norm": 1.7117011547088623,
|
| 741 |
"learning_rate": 0.0006819630337794774,
|
| 742 |
+
"loss": 1.965,
|
| 743 |
"step": 2020
|
| 744 |
},
|
| 745 |
{
|
| 746 |
"epoch": 3.9005736137667304,
|
| 747 |
+
"grad_norm": 1.7798806428909302,
|
| 748 |
"learning_rate": 0.0006777140429148077,
|
| 749 |
+
"loss": 1.9188,
|
| 750 |
"step": 2040
|
| 751 |
},
|
| 752 |
{
|
| 753 |
"epoch": 3.9388145315487573,
|
| 754 |
+
"grad_norm": 1.7349345684051514,
|
| 755 |
"learning_rate": 0.0006734650520501381,
|
| 756 |
+
"loss": 1.9044,
|
| 757 |
"step": 2060
|
| 758 |
},
|
| 759 |
{
|
| 760 |
"epoch": 3.977055449330784,
|
| 761 |
+
"grad_norm": 1.8268795013427734,
|
| 762 |
"learning_rate": 0.0006692160611854685,
|
| 763 |
+
"loss": 1.8625,
|
| 764 |
"step": 2080
|
| 765 |
},
|
| 766 |
{
|
| 767 |
"epoch": 4.0,
|
| 768 |
+
"eval_accuracy": 0.7917255297679112,
|
| 769 |
+
"eval_loss": 0.9794349670410156,
|
| 770 |
+
"eval_runtime": 689.4289,
|
| 771 |
+
"eval_samples_per_second": 21.561,
|
| 772 |
+
"eval_steps_per_second": 21.561,
|
| 773 |
"step": 2092
|
| 774 |
},
|
| 775 |
{
|
| 776 |
"epoch": 4.015296367112811,
|
| 777 |
+
"grad_norm": 1.6992357969284058,
|
| 778 |
"learning_rate": 0.0006649670703207988,
|
| 779 |
+
"loss": 1.8294,
|
| 780 |
"step": 2100
|
| 781 |
},
|
| 782 |
{
|
| 783 |
"epoch": 4.053537284894838,
|
| 784 |
+
"grad_norm": 1.6715435981750488,
|
| 785 |
"learning_rate": 0.0006607180794561292,
|
| 786 |
+
"loss": 1.7572,
|
| 787 |
"step": 2120
|
| 788 |
},
|
| 789 |
{
|
| 790 |
"epoch": 4.091778202676864,
|
| 791 |
+
"grad_norm": 1.7837462425231934,
|
| 792 |
"learning_rate": 0.0006564690885914596,
|
| 793 |
+
"loss": 1.7502,
|
| 794 |
"step": 2140
|
| 795 |
},
|
| 796 |
{
|
| 797 |
"epoch": 4.130019120458891,
|
| 798 |
+
"grad_norm": 1.7979024648666382,
|
| 799 |
"learning_rate": 0.0006522200977267899,
|
| 800 |
+
"loss": 1.733,
|
| 801 |
"step": 2160
|
| 802 |
},
|
| 803 |
{
|
| 804 |
"epoch": 4.168260038240918,
|
| 805 |
+
"grad_norm": 1.6781351566314697,
|
| 806 |
"learning_rate": 0.0006479711068621203,
|
| 807 |
+
"loss": 1.7437,
|
| 808 |
"step": 2180
|
| 809 |
},
|
| 810 |
{
|
| 811 |
"epoch": 4.2065009560229445,
|
| 812 |
+
"grad_norm": 1.7719937562942505,
|
| 813 |
"learning_rate": 0.0006437221159974506,
|
| 814 |
+
"loss": 1.7702,
|
| 815 |
"step": 2200
|
| 816 |
},
|
| 817 |
{
|
| 818 |
"epoch": 4.244741873804971,
|
| 819 |
+
"grad_norm": 1.7680734395980835,
|
| 820 |
"learning_rate": 0.000639473125132781,
|
| 821 |
+
"loss": 1.7546,
|
| 822 |
"step": 2220
|
| 823 |
},
|
| 824 |
{
|
| 825 |
"epoch": 4.282982791586998,
|
| 826 |
+
"grad_norm": 1.7028470039367676,
|
| 827 |
"learning_rate": 0.0006352241342681113,
|
| 828 |
+
"loss": 1.6716,
|
| 829 |
"step": 2240
|
| 830 |
},
|
| 831 |
{
|
| 832 |
"epoch": 4.321223709369025,
|
| 833 |
+
"grad_norm": 1.764496922492981,
|
| 834 |
"learning_rate": 0.0006309751434034417,
|
| 835 |
+
"loss": 1.7316,
|
| 836 |
"step": 2260
|
| 837 |
},
|
| 838 |
{
|
| 839 |
"epoch": 4.359464627151052,
|
| 840 |
+
"grad_norm": 1.7339156866073608,
|
| 841 |
"learning_rate": 0.0006267261525387721,
|
| 842 |
+
"loss": 1.6865,
|
| 843 |
"step": 2280
|
| 844 |
},
|
| 845 |
{
|
| 846 |
"epoch": 4.397705544933078,
|
| 847 |
+
"grad_norm": 1.6657025814056396,
|
| 848 |
"learning_rate": 0.0006224771616741024,
|
| 849 |
+
"loss": 1.6711,
|
| 850 |
"step": 2300
|
| 851 |
},
|
| 852 |
{
|
| 853 |
"epoch": 4.435946462715105,
|
| 854 |
+
"grad_norm": 1.8127187490463257,
|
| 855 |
"learning_rate": 0.0006182281708094328,
|
| 856 |
+
"loss": 1.7128,
|
| 857 |
"step": 2320
|
| 858 |
},
|
| 859 |
{
|
| 860 |
"epoch": 4.474187380497132,
|
| 861 |
+
"grad_norm": 1.720580816268921,
|
| 862 |
"learning_rate": 0.0006139791799447631,
|
| 863 |
+
"loss": 1.6676,
|
| 864 |
"step": 2340
|
| 865 |
},
|
| 866 |
{
|
| 867 |
"epoch": 4.512428298279159,
|
| 868 |
+
"grad_norm": 1.7044484615325928,
|
| 869 |
"learning_rate": 0.0006097301890800934,
|
| 870 |
+
"loss": 1.6651,
|
| 871 |
"step": 2360
|
| 872 |
},
|
| 873 |
{
|
| 874 |
"epoch": 4.550669216061186,
|
| 875 |
+
"grad_norm": 1.824859857559204,
|
| 876 |
"learning_rate": 0.0006054811982154238,
|
| 877 |
+
"loss": 1.6743,
|
| 878 |
"step": 2380
|
| 879 |
},
|
| 880 |
{
|
| 881 |
"epoch": 4.588910133843212,
|
| 882 |
+
"grad_norm": 1.847652554512024,
|
| 883 |
"learning_rate": 0.0006012322073507542,
|
| 884 |
+
"loss": 1.6765,
|
| 885 |
"step": 2400
|
| 886 |
},
|
| 887 |
{
|
| 888 |
"epoch": 4.627151051625239,
|
| 889 |
+
"grad_norm": 1.6747491359710693,
|
| 890 |
"learning_rate": 0.0005969832164860845,
|
| 891 |
+
"loss": 1.6257,
|
| 892 |
"step": 2420
|
| 893 |
},
|
| 894 |
{
|
| 895 |
"epoch": 4.665391969407266,
|
| 896 |
+
"grad_norm": 1.7143758535385132,
|
| 897 |
"learning_rate": 0.0005927342256214149,
|
| 898 |
+
"loss": 1.6515,
|
| 899 |
"step": 2440
|
| 900 |
},
|
| 901 |
{
|
| 902 |
"epoch": 4.7036328871892925,
|
| 903 |
+
"grad_norm": 1.7966911792755127,
|
| 904 |
"learning_rate": 0.0005884852347567453,
|
| 905 |
+
"loss": 1.6384,
|
| 906 |
"step": 2460
|
| 907 |
},
|
| 908 |
{
|
| 909 |
"epoch": 4.741873804971319,
|
| 910 |
+
"grad_norm": 1.6942733526229858,
|
| 911 |
"learning_rate": 0.0005842362438920756,
|
| 912 |
+
"loss": 1.5939,
|
| 913 |
"step": 2480
|
| 914 |
},
|
| 915 |
{
|
| 916 |
"epoch": 4.780114722753346,
|
| 917 |
+
"grad_norm": 1.7530827522277832,
|
| 918 |
"learning_rate": 0.000579987253027406,
|
| 919 |
+
"loss": 1.5908,
|
| 920 |
"step": 2500
|
| 921 |
},
|
| 922 |
{
|
| 923 |
"epoch": 4.818355640535373,
|
| 924 |
+
"grad_norm": 1.845311164855957,
|
| 925 |
"learning_rate": 0.0005757382621627364,
|
| 926 |
+
"loss": 1.5586,
|
| 927 |
"step": 2520
|
| 928 |
},
|
| 929 |
{
|
| 930 |
"epoch": 4.8565965583174,
|
| 931 |
+
"grad_norm": 1.7648016214370728,
|
| 932 |
"learning_rate": 0.0005714892712980667,
|
| 933 |
+
"loss": 1.5561,
|
| 934 |
"step": 2540
|
| 935 |
},
|
| 936 |
{
|
| 937 |
"epoch": 4.894837476099426,
|
| 938 |
+
"grad_norm": 1.6392900943756104,
|
| 939 |
"learning_rate": 0.000567240280433397,
|
| 940 |
+
"loss": 1.5641,
|
| 941 |
"step": 2560
|
| 942 |
},
|
| 943 |
{
|
| 944 |
"epoch": 4.933078393881453,
|
| 945 |
+
"grad_norm": 1.6668881177902222,
|
| 946 |
"learning_rate": 0.0005629912895687275,
|
| 947 |
+
"loss": 1.5443,
|
| 948 |
"step": 2580
|
| 949 |
},
|
| 950 |
{
|
| 951 |
"epoch": 4.97131931166348,
|
| 952 |
+
"grad_norm": 1.8424748182296753,
|
| 953 |
"learning_rate": 0.0005587422987040578,
|
| 954 |
+
"loss": 1.5637,
|
| 955 |
"step": 2600
|
| 956 |
},
|
| 957 |
{
|
| 958 |
"epoch": 5.0,
|
| 959 |
+
"eval_accuracy": 0.8490413723511604,
|
| 960 |
+
"eval_loss": 0.7047534584999084,
|
| 961 |
+
"eval_runtime": 7835.8179,
|
| 962 |
+
"eval_samples_per_second": 1.897,
|
| 963 |
+
"eval_steps_per_second": 1.897,
|
| 964 |
"step": 2615
|
| 965 |
},
|
| 966 |
{
|
| 967 |
"epoch": 5.009560229445507,
|
| 968 |
+
"grad_norm": 1.8417068719863892,
|
| 969 |
"learning_rate": 0.0005544933078393881,
|
| 970 |
+
"loss": 1.4799,
|
| 971 |
"step": 2620
|
| 972 |
},
|
| 973 |
{
|
| 974 |
"epoch": 5.047801147227533,
|
| 975 |
+
"grad_norm": 1.6466395854949951,
|
| 976 |
"learning_rate": 0.0005502443169747186,
|
| 977 |
+
"loss": 1.4184,
|
| 978 |
"step": 2640
|
| 979 |
},
|
| 980 |
{
|
| 981 |
"epoch": 5.08604206500956,
|
| 982 |
+
"grad_norm": 1.7499247789382935,
|
| 983 |
"learning_rate": 0.0005459953261100489,
|
| 984 |
+
"loss": 1.4507,
|
| 985 |
"step": 2660
|
| 986 |
},
|
| 987 |
{
|
| 988 |
"epoch": 5.124282982791587,
|
| 989 |
+
"grad_norm": 1.7968547344207764,
|
| 990 |
"learning_rate": 0.0005417463352453792,
|
| 991 |
+
"loss": 1.405,
|
| 992 |
"step": 2680
|
| 993 |
},
|
| 994 |
{
|
| 995 |
"epoch": 5.162523900573614,
|
| 996 |
+
"grad_norm": 1.7950819730758667,
|
| 997 |
"learning_rate": 0.0005374973443807097,
|
| 998 |
+
"loss": 1.4362,
|
| 999 |
"step": 2700
|
| 1000 |
},
|
| 1001 |
{
|
| 1002 |
"epoch": 5.2007648183556405,
|
| 1003 |
+
"grad_norm": 1.745133399963379,
|
| 1004 |
"learning_rate": 0.00053324835351604,
|
| 1005 |
+
"loss": 1.4238,
|
| 1006 |
"step": 2720
|
| 1007 |
},
|
| 1008 |
{
|
| 1009 |
"epoch": 5.239005736137667,
|
| 1010 |
+
"grad_norm": 1.7767413854599,
|
| 1011 |
"learning_rate": 0.0005289993626513702,
|
| 1012 |
+
"loss": 1.4025,
|
| 1013 |
"step": 2740
|
| 1014 |
},
|
| 1015 |
{
|
| 1016 |
"epoch": 5.277246653919694,
|
| 1017 |
+
"grad_norm": 1.7297043800354004,
|
| 1018 |
"learning_rate": 0.0005247503717867008,
|
| 1019 |
+
"loss": 1.4144,
|
| 1020 |
"step": 2760
|
| 1021 |
},
|
| 1022 |
{
|
| 1023 |
"epoch": 5.315487571701721,
|
| 1024 |
+
"grad_norm": 1.8174902200698853,
|
| 1025 |
"learning_rate": 0.000520501380922031,
|
| 1026 |
+
"loss": 1.4071,
|
| 1027 |
"step": 2780
|
| 1028 |
},
|
| 1029 |
{
|
| 1030 |
"epoch": 5.353728489483748,
|
| 1031 |
+
"grad_norm": 1.6889333724975586,
|
| 1032 |
"learning_rate": 0.0005162523900573613,
|
| 1033 |
+
"loss": 1.4022,
|
| 1034 |
"step": 2800
|
| 1035 |
},
|
| 1036 |
{
|
| 1037 |
"epoch": 5.3919694072657744,
|
| 1038 |
+
"grad_norm": 1.6331517696380615,
|
| 1039 |
"learning_rate": 0.0005120033991926918,
|
| 1040 |
+
"loss": 1.3479,
|
| 1041 |
"step": 2820
|
| 1042 |
},
|
| 1043 |
{
|
| 1044 |
"epoch": 5.430210325047801,
|
| 1045 |
+
"grad_norm": 1.8916860818862915,
|
| 1046 |
"learning_rate": 0.0005077544083280221,
|
| 1047 |
+
"loss": 1.362,
|
| 1048 |
"step": 2840
|
| 1049 |
},
|
| 1050 |
{
|
| 1051 |
"epoch": 5.468451242829828,
|
| 1052 |
+
"grad_norm": 1.706222653388977,
|
| 1053 |
"learning_rate": 0.0005035054174633524,
|
| 1054 |
+
"loss": 1.3613,
|
| 1055 |
"step": 2860
|
| 1056 |
},
|
| 1057 |
{
|
| 1058 |
"epoch": 5.506692160611855,
|
| 1059 |
+
"grad_norm": 1.6761025190353394,
|
| 1060 |
"learning_rate": 0.0004992564265986828,
|
| 1061 |
+
"loss": 1.3883,
|
| 1062 |
"step": 2880
|
| 1063 |
},
|
| 1064 |
{
|
| 1065 |
"epoch": 5.544933078393882,
|
| 1066 |
+
"grad_norm": 1.632095217704773,
|
| 1067 |
"learning_rate": 0.0004950074357340132,
|
| 1068 |
+
"loss": 1.3432,
|
| 1069 |
"step": 2900
|
| 1070 |
},
|
| 1071 |
{
|
| 1072 |
"epoch": 5.583173996175908,
|
| 1073 |
+
"grad_norm": 1.6419159173965454,
|
| 1074 |
"learning_rate": 0.0004907584448693436,
|
| 1075 |
+
"loss": 1.3417,
|
| 1076 |
"step": 2920
|
| 1077 |
},
|
| 1078 |
{
|
| 1079 |
"epoch": 5.621414913957935,
|
| 1080 |
+
"grad_norm": 1.8355722427368164,
|
| 1081 |
"learning_rate": 0.0004865094540046739,
|
| 1082 |
+
"loss": 1.341,
|
| 1083 |
"step": 2940
|
| 1084 |
},
|
| 1085 |
{
|
| 1086 |
"epoch": 5.659655831739962,
|
| 1087 |
+
"grad_norm": 1.6611793041229248,
|
| 1088 |
"learning_rate": 0.00048226046314000425,
|
| 1089 |
+
"loss": 1.339,
|
| 1090 |
"step": 2960
|
| 1091 |
},
|
| 1092 |
{
|
| 1093 |
"epoch": 5.6978967495219885,
|
| 1094 |
+
"grad_norm": 1.7696843147277832,
|
| 1095 |
"learning_rate": 0.0004780114722753346,
|
| 1096 |
+
"loss": 1.3183,
|
| 1097 |
"step": 2980
|
| 1098 |
},
|
| 1099 |
{
|
| 1100 |
"epoch": 5.736137667304015,
|
| 1101 |
+
"grad_norm": 1.6689785718917847,
|
| 1102 |
"learning_rate": 0.000473762481410665,
|
| 1103 |
+
"loss": 1.3365,
|
| 1104 |
"step": 3000
|
| 1105 |
},
|
| 1106 |
{
|
| 1107 |
"epoch": 5.774378585086042,
|
| 1108 |
+
"grad_norm": 1.6962292194366455,
|
| 1109 |
"learning_rate": 0.00046951349054599533,
|
| 1110 |
+
"loss": 1.2966,
|
| 1111 |
"step": 3020
|
| 1112 |
},
|
| 1113 |
{
|
| 1114 |
"epoch": 5.812619502868069,
|
| 1115 |
+
"grad_norm": 1.7446441650390625,
|
| 1116 |
"learning_rate": 0.0004652644996813257,
|
| 1117 |
+
"loss": 1.274,
|
| 1118 |
"step": 3040
|
| 1119 |
},
|
| 1120 |
{
|
| 1121 |
"epoch": 5.850860420650095,
|
| 1122 |
+
"grad_norm": 1.7083852291107178,
|
| 1123 |
"learning_rate": 0.0004610155088166561,
|
| 1124 |
+
"loss": 1.3145,
|
| 1125 |
"step": 3060
|
| 1126 |
},
|
| 1127 |
{
|
| 1128 |
"epoch": 5.8891013384321225,
|
| 1129 |
+
"grad_norm": 1.6674286127090454,
|
| 1130 |
"learning_rate": 0.0004567665179519864,
|
| 1131 |
+
"loss": 1.2944,
|
| 1132 |
"step": 3080
|
| 1133 |
},
|
| 1134 |
{
|
| 1135 |
"epoch": 5.927342256214149,
|
| 1136 |
+
"grad_norm": 1.5787798166275024,
|
| 1137 |
"learning_rate": 0.00045251752708731676,
|
| 1138 |
+
"loss": 1.2772,
|
| 1139 |
"step": 3100
|
| 1140 |
},
|
| 1141 |
{
|
| 1142 |
"epoch": 5.965583173996176,
|
| 1143 |
+
"grad_norm": 1.6089515686035156,
|
| 1144 |
"learning_rate": 0.0004482685362226471,
|
| 1145 |
+
"loss": 1.265,
|
| 1146 |
"step": 3120
|
| 1147 |
},
|
| 1148 |
{
|
| 1149 |
"epoch": 6.0,
|
| 1150 |
+
"eval_accuracy": 0.886242852337706,
|
| 1151 |
+
"eval_loss": 0.5389042496681213,
|
| 1152 |
+
"eval_runtime": 383.2829,
|
| 1153 |
+
"eval_samples_per_second": 38.783,
|
| 1154 |
+
"eval_steps_per_second": 38.783,
|
| 1155 |
"step": 3138
|
| 1156 |
},
|
| 1157 |
{
|
| 1158 |
"epoch": 6.003824091778203,
|
| 1159 |
+
"grad_norm": 1.5683554410934448,
|
| 1160 |
"learning_rate": 0.0004440195453579775,
|
| 1161 |
+
"loss": 1.2601,
|
| 1162 |
"step": 3140
|
| 1163 |
},
|
| 1164 |
{
|
| 1165 |
"epoch": 6.042065009560229,
|
| 1166 |
+
"grad_norm": 1.6791157722473145,
|
| 1167 |
"learning_rate": 0.00043977055449330785,
|
| 1168 |
+
"loss": 1.2067,
|
| 1169 |
"step": 3160
|
| 1170 |
},
|
| 1171 |
{
|
| 1172 |
"epoch": 6.080305927342256,
|
| 1173 |
+
"grad_norm": 1.5930650234222412,
|
| 1174 |
"learning_rate": 0.0004355215636286382,
|
| 1175 |
+
"loss": 1.1818,
|
| 1176 |
"step": 3180
|
| 1177 |
},
|
| 1178 |
{
|
| 1179 |
"epoch": 6.118546845124283,
|
| 1180 |
+
"grad_norm": 1.7136551141738892,
|
| 1181 |
"learning_rate": 0.0004312725727639686,
|
| 1182 |
+
"loss": 1.1871,
|
| 1183 |
"step": 3200
|
| 1184 |
},
|
| 1185 |
{
|
| 1186 |
"epoch": 6.15678776290631,
|
| 1187 |
+
"grad_norm": 1.6400994062423706,
|
| 1188 |
"learning_rate": 0.0004270235818992989,
|
| 1189 |
+
"loss": 1.1851,
|
| 1190 |
"step": 3220
|
| 1191 |
},
|
| 1192 |
{
|
| 1193 |
"epoch": 6.195028680688337,
|
| 1194 |
+
"grad_norm": 1.722548246383667,
|
| 1195 |
"learning_rate": 0.0004227745910346293,
|
| 1196 |
+
"loss": 1.1798,
|
| 1197 |
"step": 3240
|
| 1198 |
},
|
| 1199 |
{
|
| 1200 |
"epoch": 6.233269598470363,
|
| 1201 |
+
"grad_norm": 1.600697636604309,
|
| 1202 |
"learning_rate": 0.0004185256001699597,
|
| 1203 |
+
"loss": 1.1516,
|
| 1204 |
"step": 3260
|
| 1205 |
},
|
| 1206 |
{
|
| 1207 |
"epoch": 6.27151051625239,
|
| 1208 |
+
"grad_norm": 1.6722103357315063,
|
| 1209 |
"learning_rate": 0.00041427660930528997,
|
| 1210 |
+
"loss": 1.176,
|
| 1211 |
"step": 3280
|
| 1212 |
},
|
| 1213 |
{
|
| 1214 |
"epoch": 6.309751434034417,
|
| 1215 |
+
"grad_norm": 1.5297291278839111,
|
| 1216 |
"learning_rate": 0.00041002761844062037,
|
| 1217 |
+
"loss": 1.1625,
|
| 1218 |
"step": 3300
|
| 1219 |
},
|
| 1220 |
{
|
| 1221 |
"epoch": 6.347992351816444,
|
| 1222 |
+
"grad_norm": 1.6687546968460083,
|
| 1223 |
"learning_rate": 0.00040577862757595076,
|
| 1224 |
+
"loss": 1.1744,
|
| 1225 |
"step": 3320
|
| 1226 |
},
|
| 1227 |
{
|
| 1228 |
"epoch": 6.3862332695984705,
|
| 1229 |
+
"grad_norm": 1.6758590936660767,
|
| 1230 |
"learning_rate": 0.00040152963671128105,
|
| 1231 |
+
"loss": 1.1408,
|
| 1232 |
"step": 3340
|
| 1233 |
},
|
| 1234 |
{
|
| 1235 |
"epoch": 6.424474187380497,
|
| 1236 |
+
"grad_norm": 1.7506797313690186,
|
| 1237 |
"learning_rate": 0.00039728064584661145,
|
| 1238 |
+
"loss": 1.1458,
|
| 1239 |
"step": 3360
|
| 1240 |
},
|
| 1241 |
{
|
| 1242 |
"epoch": 6.462715105162524,
|
| 1243 |
+
"grad_norm": 1.7690140008926392,
|
| 1244 |
"learning_rate": 0.0003930316549819418,
|
| 1245 |
+
"loss": 1.1579,
|
| 1246 |
"step": 3380
|
| 1247 |
},
|
| 1248 |
{
|
| 1249 |
"epoch": 6.500956022944551,
|
| 1250 |
+
"grad_norm": 1.7732901573181152,
|
| 1251 |
"learning_rate": 0.00038878266411727214,
|
| 1252 |
+
"loss": 1.1444,
|
| 1253 |
"step": 3400
|
| 1254 |
},
|
| 1255 |
{
|
| 1256 |
"epoch": 6.539196940726577,
|
| 1257 |
+
"grad_norm": 1.7551547288894653,
|
| 1258 |
"learning_rate": 0.00038453367325260254,
|
| 1259 |
+
"loss": 1.1431,
|
| 1260 |
"step": 3420
|
| 1261 |
},
|
| 1262 |
{
|
| 1263 |
"epoch": 6.577437858508604,
|
| 1264 |
+
"grad_norm": 1.6275290250778198,
|
| 1265 |
"learning_rate": 0.0003802846823879329,
|
| 1266 |
+
"loss": 1.1293,
|
| 1267 |
"step": 3440
|
| 1268 |
},
|
| 1269 |
{
|
| 1270 |
"epoch": 6.615678776290631,
|
| 1271 |
+
"grad_norm": 1.769103765487671,
|
| 1272 |
"learning_rate": 0.0003760356915232632,
|
| 1273 |
+
"loss": 1.1418,
|
| 1274 |
"step": 3460
|
| 1275 |
},
|
| 1276 |
{
|
| 1277 |
"epoch": 6.653919694072657,
|
| 1278 |
+
"grad_norm": 1.7487330436706543,
|
| 1279 |
"learning_rate": 0.0003717867006585936,
|
| 1280 |
+
"loss": 1.1305,
|
| 1281 |
"step": 3480
|
| 1282 |
},
|
| 1283 |
{
|
| 1284 |
"epoch": 6.692160611854685,
|
| 1285 |
+
"grad_norm": 1.698512315750122,
|
| 1286 |
"learning_rate": 0.0003675377097939239,
|
| 1287 |
+
"loss": 1.0805,
|
| 1288 |
"step": 3500
|
| 1289 |
},
|
| 1290 |
{
|
| 1291 |
"epoch": 6.730401529636711,
|
| 1292 |
+
"grad_norm": 1.6636496782302856,
|
| 1293 |
"learning_rate": 0.0003632887189292543,
|
| 1294 |
+
"loss": 1.0907,
|
| 1295 |
"step": 3520
|
| 1296 |
},
|
| 1297 |
{
|
| 1298 |
"epoch": 6.768642447418738,
|
| 1299 |
+
"grad_norm": 1.577497959136963,
|
| 1300 |
"learning_rate": 0.00035903972806458466,
|
| 1301 |
+
"loss": 1.1399,
|
| 1302 |
"step": 3540
|
| 1303 |
},
|
| 1304 |
{
|
| 1305 |
"epoch": 6.806883365200765,
|
| 1306 |
+
"grad_norm": 1.7101361751556396,
|
| 1307 |
"learning_rate": 0.000354790737199915,
|
| 1308 |
+
"loss": 1.1206,
|
| 1309 |
"step": 3560
|
| 1310 |
},
|
| 1311 |
{
|
| 1312 |
"epoch": 6.845124282982791,
|
| 1313 |
+
"grad_norm": 1.6473299264907837,
|
| 1314 |
"learning_rate": 0.0003505417463352454,
|
| 1315 |
+
"loss": 1.103,
|
| 1316 |
"step": 3580
|
| 1317 |
},
|
| 1318 |
{
|
| 1319 |
"epoch": 6.8833652007648185,
|
| 1320 |
+
"grad_norm": 1.6744282245635986,
|
| 1321 |
"learning_rate": 0.00034629275547057574,
|
| 1322 |
+
"loss": 1.1088,
|
| 1323 |
"step": 3600
|
| 1324 |
},
|
| 1325 |
{
|
| 1326 |
"epoch": 6.921606118546845,
|
| 1327 |
+
"grad_norm": 1.67130708694458,
|
| 1328 |
"learning_rate": 0.0003420437646059061,
|
| 1329 |
+
"loss": 1.0857,
|
| 1330 |
"step": 3620
|
| 1331 |
},
|
| 1332 |
{
|
| 1333 |
"epoch": 6.959847036328872,
|
| 1334 |
+
"grad_norm": 1.6932523250579834,
|
| 1335 |
"learning_rate": 0.0003377947737412365,
|
| 1336 |
"loss": 1.0912,
|
| 1337 |
"step": 3640
|
| 1338 |
},
|
| 1339 |
{
|
| 1340 |
"epoch": 6.998087954110899,
|
| 1341 |
+
"grad_norm": 1.6580239534378052,
|
| 1342 |
"learning_rate": 0.00033354578287656683,
|
| 1343 |
+
"loss": 1.0888,
|
| 1344 |
"step": 3660
|
| 1345 |
},
|
| 1346 |
{
|
| 1347 |
"epoch": 7.0,
|
| 1348 |
+
"eval_accuracy": 0.9101244534140599,
|
| 1349 |
+
"eval_loss": 0.4364229142665863,
|
| 1350 |
+
"eval_runtime": 605.3795,
|
| 1351 |
+
"eval_samples_per_second": 24.555,
|
| 1352 |
+
"eval_steps_per_second": 24.555,
|
| 1353 |
"step": 3661
|
| 1354 |
},
|
| 1355 |
{
|
| 1356 |
"epoch": 7.036328871892925,
|
| 1357 |
+
"grad_norm": 1.5949829816818237,
|
| 1358 |
"learning_rate": 0.0003292967920118972,
|
| 1359 |
+
"loss": 1.0123,
|
| 1360 |
"step": 3680
|
| 1361 |
},
|
| 1362 |
{
|
| 1363 |
"epoch": 7.074569789674952,
|
| 1364 |
+
"grad_norm": 1.8134639263153076,
|
| 1365 |
"learning_rate": 0.0003250478011472275,
|
| 1366 |
+
"loss": 1.0552,
|
| 1367 |
"step": 3700
|
| 1368 |
},
|
| 1369 |
{
|
| 1370 |
"epoch": 7.112810707456979,
|
| 1371 |
+
"grad_norm": 1.6394524574279785,
|
| 1372 |
"learning_rate": 0.0003207988102825579,
|
| 1373 |
+
"loss": 1.0142,
|
| 1374 |
"step": 3720
|
| 1375 |
},
|
| 1376 |
{
|
| 1377 |
"epoch": 7.151051625239006,
|
| 1378 |
+
"grad_norm": 1.6918762922286987,
|
| 1379 |
"learning_rate": 0.00031654981941788826,
|
| 1380 |
+
"loss": 1.0096,
|
| 1381 |
"step": 3740
|
| 1382 |
},
|
| 1383 |
{
|
| 1384 |
"epoch": 7.189292543021033,
|
| 1385 |
+
"grad_norm": 1.673691987991333,
|
| 1386 |
"learning_rate": 0.0003123008285532186,
|
| 1387 |
+
"loss": 1.0203,
|
| 1388 |
"step": 3760
|
| 1389 |
},
|
| 1390 |
{
|
| 1391 |
"epoch": 7.227533460803059,
|
| 1392 |
+
"grad_norm": 1.5526095628738403,
|
| 1393 |
"learning_rate": 0.000308051837688549,
|
| 1394 |
+
"loss": 1.049,
|
| 1395 |
"step": 3780
|
| 1396 |
},
|
| 1397 |
{
|
| 1398 |
"epoch": 7.265774378585086,
|
| 1399 |
+
"grad_norm": 1.638197660446167,
|
| 1400 |
"learning_rate": 0.00030380284682387935,
|
| 1401 |
+
"loss": 1.0247,
|
| 1402 |
"step": 3800
|
| 1403 |
},
|
| 1404 |
{
|
| 1405 |
"epoch": 7.304015296367113,
|
| 1406 |
+
"grad_norm": 1.6690630912780762,
|
| 1407 |
"learning_rate": 0.0002995538559592097,
|
| 1408 |
+
"loss": 0.9841,
|
| 1409 |
"step": 3820
|
| 1410 |
},
|
| 1411 |
{
|
| 1412 |
"epoch": 7.342256214149139,
|
| 1413 |
+
"grad_norm": 1.645591139793396,
|
| 1414 |
"learning_rate": 0.0002953048650945401,
|
| 1415 |
+
"loss": 1.018,
|
| 1416 |
"step": 3840
|
| 1417 |
},
|
| 1418 |
{
|
| 1419 |
"epoch": 7.3804971319311665,
|
| 1420 |
+
"grad_norm": 1.676079273223877,
|
| 1421 |
"learning_rate": 0.0002910558742298704,
|
| 1422 |
+
"loss": 0.9818,
|
| 1423 |
"step": 3860
|
| 1424 |
},
|
| 1425 |
{
|
| 1426 |
"epoch": 7.418738049713193,
|
| 1427 |
+
"grad_norm": 1.6065680980682373,
|
| 1428 |
"learning_rate": 0.0002868068833652008,
|
| 1429 |
+
"loss": 0.9795,
|
| 1430 |
"step": 3880
|
| 1431 |
},
|
| 1432 |
{
|
| 1433 |
"epoch": 7.45697896749522,
|
| 1434 |
+
"grad_norm": 1.683929443359375,
|
| 1435 |
"learning_rate": 0.0002825578925005312,
|
| 1436 |
+
"loss": 0.9588,
|
| 1437 |
"step": 3900
|
| 1438 |
},
|
| 1439 |
{
|
| 1440 |
"epoch": 7.495219885277247,
|
| 1441 |
+
"grad_norm": 1.6200690269470215,
|
| 1442 |
"learning_rate": 0.00027830890163586146,
|
| 1443 |
+
"loss": 1.0081,
|
| 1444 |
"step": 3920
|
| 1445 |
},
|
| 1446 |
{
|
| 1447 |
"epoch": 7.533460803059273,
|
| 1448 |
+
"grad_norm": 1.7147966623306274,
|
| 1449 |
"learning_rate": 0.00027405991077119186,
|
| 1450 |
+
"loss": 0.9822,
|
| 1451 |
"step": 3940
|
| 1452 |
},
|
| 1453 |
{
|
| 1454 |
"epoch": 7.5717017208413,
|
| 1455 |
+
"grad_norm": 1.7224268913269043,
|
| 1456 |
"learning_rate": 0.00026981091990652226,
|
| 1457 |
+
"loss": 0.988,
|
| 1458 |
"step": 3960
|
| 1459 |
},
|
| 1460 |
{
|
| 1461 |
"epoch": 7.609942638623327,
|
| 1462 |
+
"grad_norm": 1.7145981788635254,
|
| 1463 |
"learning_rate": 0.00026556192904185255,
|
| 1464 |
+
"loss": 0.9562,
|
| 1465 |
"step": 3980
|
| 1466 |
},
|
| 1467 |
{
|
| 1468 |
"epoch": 7.648183556405353,
|
| 1469 |
+
"grad_norm": 1.8020603656768799,
|
| 1470 |
"learning_rate": 0.00026131293817718295,
|
| 1471 |
+
"loss": 0.9644,
|
| 1472 |
"step": 4000
|
| 1473 |
},
|
| 1474 |
{
|
| 1475 |
"epoch": 7.686424474187381,
|
| 1476 |
+
"grad_norm": 1.7413355112075806,
|
| 1477 |
"learning_rate": 0.00025706394731251324,
|
| 1478 |
+
"loss": 0.9648,
|
| 1479 |
"step": 4020
|
| 1480 |
},
|
| 1481 |
{
|
| 1482 |
"epoch": 7.724665391969407,
|
| 1483 |
+
"grad_norm": 1.6813682317733765,
|
| 1484 |
"learning_rate": 0.00025281495644784364,
|
| 1485 |
+
"loss": 0.9244,
|
| 1486 |
"step": 4040
|
| 1487 |
},
|
| 1488 |
{
|
| 1489 |
"epoch": 7.762906309751434,
|
| 1490 |
+
"grad_norm": 1.747910737991333,
|
| 1491 |
"learning_rate": 0.00024856596558317403,
|
| 1492 |
+
"loss": 0.9217,
|
| 1493 |
"step": 4060
|
| 1494 |
},
|
| 1495 |
{
|
| 1496 |
"epoch": 7.801147227533461,
|
| 1497 |
+
"grad_norm": 1.6242161989212036,
|
| 1498 |
"learning_rate": 0.0002443169747185044,
|
| 1499 |
+
"loss": 0.9628,
|
| 1500 |
"step": 4080
|
| 1501 |
},
|
| 1502 |
{
|
| 1503 |
"epoch": 7.839388145315487,
|
| 1504 |
+
"grad_norm": 1.5416340827941895,
|
| 1505 |
"learning_rate": 0.00024006798385383472,
|
| 1506 |
+
"loss": 0.979,
|
| 1507 |
"step": 4100
|
| 1508 |
},
|
| 1509 |
{
|
| 1510 |
"epoch": 7.8776290630975145,
|
| 1511 |
+
"grad_norm": 1.7438323497772217,
|
| 1512 |
"learning_rate": 0.00023581899298916507,
|
| 1513 |
+
"loss": 0.9528,
|
| 1514 |
"step": 4120
|
| 1515 |
},
|
| 1516 |
{
|
| 1517 |
"epoch": 7.915869980879541,
|
| 1518 |
+
"grad_norm": 1.6303768157958984,
|
| 1519 |
"learning_rate": 0.00023157000212449544,
|
| 1520 |
+
"loss": 0.91,
|
| 1521 |
"step": 4140
|
| 1522 |
},
|
| 1523 |
{
|
| 1524 |
"epoch": 7.954110898661568,
|
| 1525 |
+
"grad_norm": 1.586729884147644,
|
| 1526 |
"learning_rate": 0.00022732101125982578,
|
| 1527 |
+
"loss": 0.9346,
|
| 1528 |
"step": 4160
|
| 1529 |
},
|
| 1530 |
{
|
| 1531 |
"epoch": 7.992351816443595,
|
| 1532 |
+
"grad_norm": 1.771173357963562,
|
| 1533 |
"learning_rate": 0.00022307202039515615,
|
| 1534 |
+
"loss": 0.9296,
|
| 1535 |
"step": 4180
|
| 1536 |
},
|
| 1537 |
{
|
| 1538 |
"epoch": 8.0,
|
| 1539 |
+
"eval_accuracy": 0.9264715775311133,
|
| 1540 |
+
"eval_loss": 0.36169418692588806,
|
| 1541 |
+
"eval_runtime": 57.1398,
|
| 1542 |
+
"eval_samples_per_second": 260.152,
|
| 1543 |
+
"eval_steps_per_second": 260.152,
|
| 1544 |
"step": 4184
|
| 1545 |
},
|
| 1546 |
{
|
| 1547 |
"epoch": 8.030592734225621,
|
| 1548 |
+
"grad_norm": 1.5647226572036743,
|
| 1549 |
"learning_rate": 0.00021882302953048652,
|
| 1550 |
+
"loss": 0.9005,
|
| 1551 |
"step": 4200
|
| 1552 |
},
|
| 1553 |
{
|
| 1554 |
"epoch": 8.068833652007648,
|
| 1555 |
+
"grad_norm": 1.6461886167526245,
|
| 1556 |
"learning_rate": 0.00021457403866581687,
|
| 1557 |
+
"loss": 0.8696,
|
| 1558 |
"step": 4220
|
| 1559 |
},
|
| 1560 |
{
|
| 1561 |
"epoch": 8.107074569789676,
|
| 1562 |
+
"grad_norm": 1.5358296632766724,
|
| 1563 |
"learning_rate": 0.0002103250478011472,
|
| 1564 |
+
"loss": 0.8782,
|
| 1565 |
"step": 4240
|
| 1566 |
},
|
| 1567 |
{
|
| 1568 |
"epoch": 8.145315487571702,
|
| 1569 |
+
"grad_norm": 1.6051462888717651,
|
| 1570 |
"learning_rate": 0.0002060760569364776,
|
| 1571 |
+
"loss": 0.8483,
|
| 1572 |
"step": 4260
|
| 1573 |
},
|
| 1574 |
{
|
| 1575 |
"epoch": 8.183556405353729,
|
| 1576 |
+
"grad_norm": 1.7184685468673706,
|
| 1577 |
"learning_rate": 0.00020182706607180795,
|
| 1578 |
+
"loss": 0.8817,
|
| 1579 |
"step": 4280
|
| 1580 |
},
|
| 1581 |
{
|
| 1582 |
"epoch": 8.221797323135755,
|
| 1583 |
+
"grad_norm": 1.6134257316589355,
|
| 1584 |
"learning_rate": 0.0001975780752071383,
|
| 1585 |
+
"loss": 0.8603,
|
| 1586 |
"step": 4300
|
| 1587 |
},
|
| 1588 |
{
|
| 1589 |
"epoch": 8.260038240917781,
|
| 1590 |
+
"grad_norm": 1.5783709287643433,
|
| 1591 |
"learning_rate": 0.00019332908434246867,
|
| 1592 |
+
"loss": 0.8654,
|
| 1593 |
"step": 4320
|
| 1594 |
},
|
| 1595 |
{
|
| 1596 |
"epoch": 8.29827915869981,
|
| 1597 |
+
"grad_norm": 1.4778318405151367,
|
| 1598 |
"learning_rate": 0.00018908009347779904,
|
| 1599 |
+
"loss": 0.8554,
|
| 1600 |
"step": 4340
|
| 1601 |
},
|
| 1602 |
{
|
| 1603 |
"epoch": 8.336520076481836,
|
| 1604 |
+
"grad_norm": 1.8124628067016602,
|
| 1605 |
"learning_rate": 0.00018483110261312938,
|
| 1606 |
+
"loss": 0.8974,
|
| 1607 |
"step": 4360
|
| 1608 |
},
|
| 1609 |
{
|
| 1610 |
"epoch": 8.374760994263863,
|
| 1611 |
+
"grad_norm": 1.7594116926193237,
|
| 1612 |
"learning_rate": 0.00018058211174845973,
|
| 1613 |
+
"loss": 0.8716,
|
| 1614 |
"step": 4380
|
| 1615 |
},
|
| 1616 |
{
|
| 1617 |
"epoch": 8.413001912045889,
|
| 1618 |
+
"grad_norm": 1.7039234638214111,
|
| 1619 |
"learning_rate": 0.0001763331208837901,
|
| 1620 |
+
"loss": 0.8525,
|
| 1621 |
"step": 4400
|
| 1622 |
},
|
| 1623 |
{
|
| 1624 |
"epoch": 8.451242829827915,
|
| 1625 |
+
"grad_norm": 1.6325209140777588,
|
| 1626 |
"learning_rate": 0.00017208413001912047,
|
| 1627 |
+
"loss": 0.8663,
|
| 1628 |
"step": 4420
|
| 1629 |
},
|
| 1630 |
{
|
| 1631 |
"epoch": 8.489483747609942,
|
| 1632 |
+
"grad_norm": 1.6818372011184692,
|
| 1633 |
"learning_rate": 0.00016783513915445082,
|
| 1634 |
+
"loss": 0.8629,
|
| 1635 |
"step": 4440
|
| 1636 |
},
|
| 1637 |
{
|
| 1638 |
"epoch": 8.52772466539197,
|
| 1639 |
+
"grad_norm": 1.5809085369110107,
|
| 1640 |
"learning_rate": 0.00016358614828978119,
|
| 1641 |
+
"loss": 0.8718,
|
| 1642 |
"step": 4460
|
| 1643 |
},
|
| 1644 |
{
|
| 1645 |
"epoch": 8.565965583173996,
|
| 1646 |
+
"grad_norm": 1.5711621046066284,
|
| 1647 |
"learning_rate": 0.00015933715742511153,
|
| 1648 |
+
"loss": 0.8527,
|
| 1649 |
"step": 4480
|
| 1650 |
},
|
| 1651 |
{
|
| 1652 |
"epoch": 8.604206500956023,
|
| 1653 |
+
"grad_norm": 1.5462543964385986,
|
| 1654 |
"learning_rate": 0.0001550881665604419,
|
| 1655 |
+
"loss": 0.8589,
|
| 1656 |
"step": 4500
|
| 1657 |
},
|
| 1658 |
{
|
| 1659 |
"epoch": 8.64244741873805,
|
| 1660 |
+
"grad_norm": 1.6341811418533325,
|
| 1661 |
"learning_rate": 0.00015083917569577227,
|
| 1662 |
+
"loss": 0.8649,
|
| 1663 |
"step": 4520
|
| 1664 |
},
|
| 1665 |
{
|
| 1666 |
"epoch": 8.680688336520076,
|
| 1667 |
+
"grad_norm": 1.5172038078308105,
|
| 1668 |
"learning_rate": 0.00014659018483110262,
|
| 1669 |
+
"loss": 0.8192,
|
| 1670 |
"step": 4540
|
| 1671 |
},
|
| 1672 |
{
|
| 1673 |
"epoch": 8.718929254302104,
|
| 1674 |
+
"grad_norm": 1.4799879789352417,
|
| 1675 |
"learning_rate": 0.00014234119396643296,
|
| 1676 |
+
"loss": 0.8436,
|
| 1677 |
"step": 4560
|
| 1678 |
},
|
| 1679 |
{
|
| 1680 |
"epoch": 8.75717017208413,
|
| 1681 |
+
"grad_norm": 1.547850251197815,
|
| 1682 |
"learning_rate": 0.00013809220310176336,
|
| 1683 |
+
"loss": 0.8292,
|
| 1684 |
"step": 4580
|
| 1685 |
},
|
| 1686 |
{
|
| 1687 |
"epoch": 8.795411089866157,
|
| 1688 |
+
"grad_norm": 1.8095018863677979,
|
| 1689 |
"learning_rate": 0.0001338432122370937,
|
| 1690 |
+
"loss": 0.8527,
|
| 1691 |
"step": 4600
|
| 1692 |
},
|
| 1693 |
{
|
| 1694 |
"epoch": 8.833652007648183,
|
| 1695 |
+
"grad_norm": 1.5578687191009521,
|
| 1696 |
"learning_rate": 0.00012959422137242405,
|
| 1697 |
+
"loss": 0.8358,
|
| 1698 |
"step": 4620
|
| 1699 |
},
|
| 1700 |
{
|
| 1701 |
"epoch": 8.87189292543021,
|
| 1702 |
+
"grad_norm": 1.7008335590362549,
|
| 1703 |
"learning_rate": 0.0001253452305077544,
|
| 1704 |
+
"loss": 0.822,
|
| 1705 |
"step": 4640
|
| 1706 |
},
|
| 1707 |
{
|
| 1708 |
"epoch": 8.910133843212238,
|
| 1709 |
+
"grad_norm": 1.6717548370361328,
|
| 1710 |
"learning_rate": 0.00012109623964308478,
|
| 1711 |
+
"loss": 0.8352,
|
| 1712 |
"step": 4660
|
| 1713 |
},
|
| 1714 |
{
|
| 1715 |
"epoch": 8.948374760994264,
|
| 1716 |
+
"grad_norm": 1.729179859161377,
|
| 1717 |
"learning_rate": 0.00011684724877841513,
|
| 1718 |
+
"loss": 0.826,
|
| 1719 |
"step": 4680
|
| 1720 |
},
|
| 1721 |
{
|
| 1722 |
"epoch": 8.98661567877629,
|
| 1723 |
+
"grad_norm": 1.6358789205551147,
|
| 1724 |
"learning_rate": 0.00011259825791374549,
|
| 1725 |
+
"loss": 0.8066,
|
| 1726 |
"step": 4700
|
| 1727 |
},
|
| 1728 |
{
|
| 1729 |
"epoch": 9.0,
|
| 1730 |
"eval_accuracy": 0.9352842246888665,
|
| 1731 |
+
"eval_loss": 0.3206591010093689,
|
| 1732 |
+
"eval_runtime": 381.3245,
|
| 1733 |
+
"eval_samples_per_second": 38.983,
|
| 1734 |
+
"eval_steps_per_second": 38.983,
|
| 1735 |
"step": 4707
|
| 1736 |
},
|
| 1737 |
{
|
| 1738 |
"epoch": 9.024856596558317,
|
| 1739 |
+
"grad_norm": 1.5783698558807373,
|
| 1740 |
"learning_rate": 0.00010834926704907585,
|
| 1741 |
+
"loss": 0.8019,
|
| 1742 |
"step": 4720
|
| 1743 |
},
|
| 1744 |
{
|
| 1745 |
"epoch": 9.063097514340344,
|
| 1746 |
+
"grad_norm": 1.5668120384216309,
|
| 1747 |
"learning_rate": 0.0001041002761844062,
|
| 1748 |
+
"loss": 0.7702,
|
| 1749 |
"step": 4740
|
| 1750 |
},
|
| 1751 |
{
|
| 1752 |
"epoch": 9.101338432122372,
|
| 1753 |
+
"grad_norm": 1.624084234237671,
|
| 1754 |
"learning_rate": 9.985128531973658e-05,
|
| 1755 |
+
"loss": 0.7934,
|
| 1756 |
"step": 4760
|
| 1757 |
},
|
| 1758 |
{
|
| 1759 |
"epoch": 9.139579349904398,
|
| 1760 |
+
"grad_norm": 1.5410951375961304,
|
| 1761 |
"learning_rate": 9.560229445506692e-05,
|
| 1762 |
+
"loss": 0.7863,
|
| 1763 |
"step": 4780
|
| 1764 |
},
|
| 1765 |
{
|
| 1766 |
"epoch": 9.177820267686425,
|
| 1767 |
+
"grad_norm": 1.663845419883728,
|
| 1768 |
"learning_rate": 9.135330359039729e-05,
|
| 1769 |
+
"loss": 0.7894,
|
| 1770 |
"step": 4800
|
| 1771 |
},
|
| 1772 |
{
|
| 1773 |
"epoch": 9.216061185468451,
|
| 1774 |
+
"grad_norm": 1.5939579010009766,
|
| 1775 |
"learning_rate": 8.710431272572764e-05,
|
| 1776 |
+
"loss": 0.739,
|
| 1777 |
"step": 4820
|
| 1778 |
},
|
| 1779 |
{
|
| 1780 |
"epoch": 9.254302103250478,
|
| 1781 |
+
"grad_norm": 1.5545909404754639,
|
| 1782 |
"learning_rate": 8.2855321861058e-05,
|
| 1783 |
+
"loss": 0.7808,
|
| 1784 |
"step": 4840
|
| 1785 |
},
|
| 1786 |
{
|
| 1787 |
"epoch": 9.292543021032504,
|
| 1788 |
+
"grad_norm": 1.665999412536621,
|
| 1789 |
"learning_rate": 7.860633099638836e-05,
|
| 1790 |
+
"loss": 0.7761,
|
| 1791 |
"step": 4860
|
| 1792 |
},
|
| 1793 |
{
|
| 1794 |
"epoch": 9.330783938814532,
|
| 1795 |
+
"grad_norm": 1.6480567455291748,
|
| 1796 |
"learning_rate": 7.435734013171871e-05,
|
| 1797 |
+
"loss": 0.7876,
|
| 1798 |
"step": 4880
|
| 1799 |
},
|
| 1800 |
{
|
| 1801 |
"epoch": 9.369024856596559,
|
| 1802 |
+
"grad_norm": 1.5779589414596558,
|
| 1803 |
"learning_rate": 7.010834926704908e-05,
|
| 1804 |
+
"loss": 0.767,
|
| 1805 |
"step": 4900
|
| 1806 |
},
|
| 1807 |
{
|
| 1808 |
"epoch": 9.407265774378585,
|
| 1809 |
+
"grad_norm": 1.6985348463058472,
|
| 1810 |
"learning_rate": 6.585935840237942e-05,
|
| 1811 |
+
"loss": 0.783,
|
| 1812 |
"step": 4920
|
| 1813 |
},
|
| 1814 |
{
|
| 1815 |
"epoch": 9.445506692160611,
|
| 1816 |
+
"grad_norm": 1.5563093423843384,
|
| 1817 |
"learning_rate": 6.16103675377098e-05,
|
| 1818 |
+
"loss": 0.756,
|
| 1819 |
"step": 4940
|
| 1820 |
},
|
| 1821 |
{
|
| 1822 |
"epoch": 9.483747609942638,
|
| 1823 |
+
"grad_norm": 1.6173079013824463,
|
| 1824 |
"learning_rate": 5.736137667304015e-05,
|
| 1825 |
+
"loss": 0.7682,
|
| 1826 |
"step": 4960
|
| 1827 |
},
|
| 1828 |
{
|
| 1829 |
"epoch": 9.521988527724666,
|
| 1830 |
+
"grad_norm": 1.5880271196365356,
|
| 1831 |
"learning_rate": 5.311238580837052e-05,
|
| 1832 |
+
"loss": 0.7632,
|
| 1833 |
"step": 4980
|
| 1834 |
},
|
| 1835 |
{
|
| 1836 |
"epoch": 9.560229445506693,
|
| 1837 |
+
"grad_norm": 1.6329987049102783,
|
| 1838 |
"learning_rate": 4.8863394943700874e-05,
|
| 1839 |
+
"loss": 0.7602,
|
| 1840 |
"step": 5000
|
| 1841 |
},
|
| 1842 |
{
|
| 1843 |
"epoch": 9.598470363288719,
|
| 1844 |
+
"grad_norm": 1.442744255065918,
|
| 1845 |
"learning_rate": 4.461440407903123e-05,
|
| 1846 |
+
"loss": 0.7595,
|
| 1847 |
"step": 5020
|
| 1848 |
},
|
| 1849 |
{
|
| 1850 |
"epoch": 9.636711281070745,
|
| 1851 |
+
"grad_norm": 1.5359572172164917,
|
| 1852 |
"learning_rate": 4.036541321436159e-05,
|
| 1853 |
+
"loss": 0.7621,
|
| 1854 |
"step": 5040
|
| 1855 |
},
|
| 1856 |
{
|
| 1857 |
"epoch": 9.674952198852772,
|
| 1858 |
+
"grad_norm": 1.6465296745300293,
|
| 1859 |
"learning_rate": 3.6116422349691954e-05,
|
| 1860 |
+
"loss": 0.7717,
|
| 1861 |
"step": 5060
|
| 1862 |
},
|
| 1863 |
{
|
| 1864 |
"epoch": 9.7131931166348,
|
| 1865 |
+
"grad_norm": 1.6590745449066162,
|
| 1866 |
"learning_rate": 3.186743148502231e-05,
|
| 1867 |
+
"loss": 0.73,
|
| 1868 |
"step": 5080
|
| 1869 |
},
|
| 1870 |
{
|
| 1871 |
"epoch": 9.751434034416826,
|
| 1872 |
+
"grad_norm": 1.5176348686218262,
|
| 1873 |
"learning_rate": 2.7618440620352666e-05,
|
| 1874 |
+
"loss": 0.7486,
|
| 1875 |
"step": 5100
|
| 1876 |
},
|
| 1877 |
{
|
| 1878 |
"epoch": 9.789674952198853,
|
| 1879 |
+
"grad_norm": 1.7158029079437256,
|
| 1880 |
"learning_rate": 2.3369449755683023e-05,
|
| 1881 |
+
"loss": 0.7766,
|
| 1882 |
"step": 5120
|
| 1883 |
},
|
| 1884 |
{
|
| 1885 |
"epoch": 9.82791586998088,
|
| 1886 |
+
"grad_norm": 1.6565515995025635,
|
| 1887 |
"learning_rate": 1.9120458891013384e-05,
|
| 1888 |
+
"loss": 0.7159,
|
| 1889 |
"step": 5140
|
| 1890 |
},
|
| 1891 |
{
|
| 1892 |
"epoch": 9.866156787762906,
|
| 1893 |
+
"grad_norm": 1.4815343618392944,
|
| 1894 |
"learning_rate": 1.4871468026343743e-05,
|
| 1895 |
+
"loss": 0.7304,
|
| 1896 |
"step": 5160
|
| 1897 |
},
|
| 1898 |
{
|
| 1899 |
"epoch": 9.904397705544934,
|
| 1900 |
+
"grad_norm": 1.6041672229766846,
|
| 1901 |
"learning_rate": 1.0622477161674103e-05,
|
| 1902 |
+
"loss": 0.744,
|
| 1903 |
"step": 5180
|
| 1904 |
},
|
| 1905 |
{
|
| 1906 |
"epoch": 9.94263862332696,
|
| 1907 |
+
"grad_norm": 1.6224092245101929,
|
| 1908 |
"learning_rate": 6.373486297004461e-06,
|
| 1909 |
+
"loss": 0.7562,
|
| 1910 |
"step": 5200
|
| 1911 |
},
|
| 1912 |
{
|
| 1913 |
"epoch": 9.980879541108987,
|
| 1914 |
+
"grad_norm": 1.5392311811447144,
|
| 1915 |
"learning_rate": 2.1244954323348204e-06,
|
| 1916 |
+
"loss": 0.7675,
|
| 1917 |
"step": 5220
|
| 1918 |
},
|
| 1919 |
{
|
| 1920 |
"epoch": 10.0,
|
| 1921 |
+
"eval_accuracy": 0.9405314497140935,
|
| 1922 |
+
"eval_loss": 0.29811325669288635,
|
| 1923 |
+
"eval_runtime": 464.2204,
|
| 1924 |
+
"eval_samples_per_second": 32.021,
|
| 1925 |
+
"eval_steps_per_second": 32.021,
|
| 1926 |
"step": 5230
|
| 1927 |
},
|
| 1928 |
{
|
| 1929 |
"epoch": 10.0,
|
| 1930 |
"step": 5230,
|
| 1931 |
"total_flos": 1.96318398191328e+18,
|
| 1932 |
+
"train_loss": 2.122584131525306,
|
| 1933 |
+
"train_runtime": 50832.5393,
|
| 1934 |
+
"train_samples_per_second": 26.317,
|
| 1935 |
+
"train_steps_per_second": 0.103
|
| 1936 |
}
|
| 1937 |
],
|
| 1938 |
"logging_steps": 20,
|