Training in progress, step 2400, checkpoint
Browse files
checkpoint-2400/adapter_config.json
CHANGED
|
@@ -23,13 +23,13 @@
|
|
| 23 |
"rank_pattern": {},
|
| 24 |
"revision": null,
|
| 25 |
"target_modules": [
|
| 26 |
-
"o_proj",
|
| 27 |
-
"down_proj",
|
| 28 |
"gate_proj",
|
| 29 |
"k_proj",
|
|
|
|
|
|
|
| 30 |
"q_proj",
|
| 31 |
-
"
|
| 32 |
-
"
|
| 33 |
],
|
| 34 |
"task_type": "CAUSAL_LM",
|
| 35 |
"use_dora": false,
|
|
|
|
| 23 |
"rank_pattern": {},
|
| 24 |
"revision": null,
|
| 25 |
"target_modules": [
|
|
|
|
|
|
|
| 26 |
"gate_proj",
|
| 27 |
"k_proj",
|
| 28 |
+
"o_proj",
|
| 29 |
+
"up_proj",
|
| 30 |
"q_proj",
|
| 31 |
+
"down_proj",
|
| 32 |
+
"v_proj"
|
| 33 |
],
|
| 34 |
"task_type": "CAUSAL_LM",
|
| 35 |
"use_dora": false,
|
checkpoint-2400/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 145287696
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dd2f50bd0c61ef5f6576a80600b11f1a4faf4c6914126c6f5edb142694ed6033
|
| 3 |
size 145287696
|
checkpoint-2400/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 290833618
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:15636881e51b457cedd1c74a9ab9c8afe430fb8b78cfa8dd8d439f88302a27bc
|
| 3 |
size 290833618
|
checkpoint-2400/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14244
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1a4e394c16753f4ac81bab15afbd1681549f226463782d3a38eb05f3141b0233
|
| 3 |
size 14244
|
checkpoint-2400/trainer_state.json
CHANGED
|
@@ -10,2066 +10,2066 @@
|
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.010869565217391304,
|
| 13 |
-
"grad_norm": 2.
|
| 14 |
"learning_rate": 4.981884057971015e-05,
|
| 15 |
-
"loss": 2.
|
| 16 |
"step": 10
|
| 17 |
},
|
| 18 |
{
|
| 19 |
"epoch": 0.021739130434782608,
|
| 20 |
-
"grad_norm": 1.
|
| 21 |
"learning_rate": 4.963768115942029e-05,
|
| 22 |
-
"loss": 1.
|
| 23 |
"step": 20
|
| 24 |
},
|
| 25 |
{
|
| 26 |
"epoch": 0.03260869565217391,
|
| 27 |
-
"grad_norm":
|
| 28 |
"learning_rate": 4.945652173913044e-05,
|
| 29 |
-
"loss": 0.
|
| 30 |
"step": 30
|
| 31 |
},
|
| 32 |
{
|
| 33 |
"epoch": 0.043478260869565216,
|
| 34 |
-
"grad_norm": 1.
|
| 35 |
"learning_rate": 4.9275362318840584e-05,
|
| 36 |
-
"loss": 0.
|
| 37 |
"step": 40
|
| 38 |
},
|
| 39 |
{
|
| 40 |
"epoch": 0.05434782608695652,
|
| 41 |
-
"grad_norm": 0.
|
| 42 |
"learning_rate": 4.909420289855073e-05,
|
| 43 |
-
"loss": 0.
|
| 44 |
"step": 50
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 0.05434782608695652,
|
| 48 |
-
"eval_loss": 0.
|
| 49 |
-
"eval_runtime": 10.
|
| 50 |
-
"eval_samples_per_second":
|
| 51 |
-
"eval_steps_per_second": 2.
|
| 52 |
"step": 50
|
| 53 |
},
|
| 54 |
{
|
| 55 |
"epoch": 0.06521739130434782,
|
| 56 |
-
"grad_norm": 0.
|
| 57 |
"learning_rate": 4.891304347826087e-05,
|
| 58 |
-
"loss": 0.
|
| 59 |
"step": 60
|
| 60 |
},
|
| 61 |
{
|
| 62 |
"epoch": 0.07608695652173914,
|
| 63 |
-
"grad_norm": 0.
|
| 64 |
"learning_rate": 4.873188405797102e-05,
|
| 65 |
-
"loss": 0.
|
| 66 |
"step": 70
|
| 67 |
},
|
| 68 |
{
|
| 69 |
"epoch": 0.08695652173913043,
|
| 70 |
-
"grad_norm": 0.
|
| 71 |
"learning_rate": 4.855072463768116e-05,
|
| 72 |
-
"loss": 0.
|
| 73 |
"step": 80
|
| 74 |
},
|
| 75 |
{
|
| 76 |
"epoch": 0.09782608695652174,
|
| 77 |
-
"grad_norm": 0.
|
| 78 |
"learning_rate": 4.836956521739131e-05,
|
| 79 |
-
"loss": 0.
|
| 80 |
"step": 90
|
| 81 |
},
|
| 82 |
{
|
| 83 |
"epoch": 0.10869565217391304,
|
| 84 |
-
"grad_norm": 0.
|
| 85 |
"learning_rate": 4.818840579710145e-05,
|
| 86 |
-
"loss": 0.
|
| 87 |
"step": 100
|
| 88 |
},
|
| 89 |
{
|
| 90 |
"epoch": 0.10869565217391304,
|
| 91 |
-
"eval_loss": 0.
|
| 92 |
-
"eval_runtime": 10.
|
| 93 |
-
"eval_samples_per_second":
|
| 94 |
-
"eval_steps_per_second": 2.
|
| 95 |
"step": 100
|
| 96 |
},
|
| 97 |
{
|
| 98 |
"epoch": 0.11956521739130435,
|
| 99 |
-
"grad_norm": 0.
|
| 100 |
"learning_rate": 4.80072463768116e-05,
|
| 101 |
-
"loss": 0.
|
| 102 |
"step": 110
|
| 103 |
},
|
| 104 |
{
|
| 105 |
"epoch": 0.13043478260869565,
|
| 106 |
-
"grad_norm": 0.
|
| 107 |
"learning_rate": 4.782608695652174e-05,
|
| 108 |
-
"loss": 0.
|
| 109 |
"step": 120
|
| 110 |
},
|
| 111 |
{
|
| 112 |
"epoch": 0.14130434782608695,
|
| 113 |
-
"grad_norm": 0.
|
| 114 |
"learning_rate": 4.764492753623189e-05,
|
| 115 |
-
"loss": 0.
|
| 116 |
"step": 130
|
| 117 |
},
|
| 118 |
{
|
| 119 |
"epoch": 0.15217391304347827,
|
| 120 |
-
"grad_norm": 0.
|
| 121 |
"learning_rate": 4.746376811594203e-05,
|
| 122 |
-
"loss": 0.
|
| 123 |
"step": 140
|
| 124 |
},
|
| 125 |
{
|
| 126 |
"epoch": 0.16304347826086957,
|
| 127 |
-
"grad_norm": 0.
|
| 128 |
"learning_rate": 4.7282608695652177e-05,
|
| 129 |
-
"loss": 0.
|
| 130 |
"step": 150
|
| 131 |
},
|
| 132 |
{
|
| 133 |
"epoch": 0.16304347826086957,
|
| 134 |
-
"eval_loss": 0.
|
| 135 |
-
"eval_runtime": 10.
|
| 136 |
-
"eval_samples_per_second":
|
| 137 |
-
"eval_steps_per_second": 2.
|
| 138 |
"step": 150
|
| 139 |
},
|
| 140 |
{
|
| 141 |
"epoch": 0.17391304347826086,
|
| 142 |
-
"grad_norm": 0.
|
| 143 |
"learning_rate": 4.710144927536232e-05,
|
| 144 |
-
"loss": 0.
|
| 145 |
"step": 160
|
| 146 |
},
|
| 147 |
{
|
| 148 |
"epoch": 0.18478260869565216,
|
| 149 |
-
"grad_norm": 0.
|
| 150 |
"learning_rate": 4.6920289855072464e-05,
|
| 151 |
-
"loss": 0.
|
| 152 |
"step": 170
|
| 153 |
},
|
| 154 |
{
|
| 155 |
"epoch": 0.1956521739130435,
|
| 156 |
-
"grad_norm": 0.
|
| 157 |
"learning_rate": 4.673913043478261e-05,
|
| 158 |
-
"loss": 0.
|
| 159 |
"step": 180
|
| 160 |
},
|
| 161 |
{
|
| 162 |
"epoch": 0.20652173913043478,
|
| 163 |
-
"grad_norm": 0.
|
| 164 |
"learning_rate": 4.655797101449276e-05,
|
| 165 |
-
"loss": 0.
|
| 166 |
"step": 190
|
| 167 |
},
|
| 168 |
{
|
| 169 |
"epoch": 0.21739130434782608,
|
| 170 |
-
"grad_norm": 0.
|
| 171 |
"learning_rate": 4.63768115942029e-05,
|
| 172 |
-
"loss": 0.
|
| 173 |
"step": 200
|
| 174 |
},
|
| 175 |
{
|
| 176 |
"epoch": 0.21739130434782608,
|
| 177 |
-
"eval_loss": 0.
|
| 178 |
-
"eval_runtime": 10.
|
| 179 |
-
"eval_samples_per_second":
|
| 180 |
-
"eval_steps_per_second": 2.
|
| 181 |
"step": 200
|
| 182 |
},
|
| 183 |
{
|
| 184 |
"epoch": 0.22826086956521738,
|
| 185 |
-
"grad_norm": 0.
|
| 186 |
"learning_rate": 4.6195652173913046e-05,
|
| 187 |
-
"loss": 0.
|
| 188 |
"step": 210
|
| 189 |
},
|
| 190 |
{
|
| 191 |
"epoch": 0.2391304347826087,
|
| 192 |
-
"grad_norm": 0.
|
| 193 |
"learning_rate": 4.601449275362319e-05,
|
| 194 |
-
"loss": 0.
|
| 195 |
"step": 220
|
| 196 |
},
|
| 197 |
{
|
| 198 |
"epoch": 0.25,
|
| 199 |
-
"grad_norm": 0.
|
| 200 |
"learning_rate": 4.5833333333333334e-05,
|
| 201 |
-
"loss": 0.
|
| 202 |
"step": 230
|
| 203 |
},
|
| 204 |
{
|
| 205 |
"epoch": 0.2608695652173913,
|
| 206 |
-
"grad_norm": 0.
|
| 207 |
"learning_rate": 4.565217391304348e-05,
|
| 208 |
-
"loss": 0.
|
| 209 |
"step": 240
|
| 210 |
},
|
| 211 |
{
|
| 212 |
"epoch": 0.2717391304347826,
|
| 213 |
-
"grad_norm": 0.
|
| 214 |
"learning_rate": 4.547101449275363e-05,
|
| 215 |
-
"loss": 0.
|
| 216 |
"step": 250
|
| 217 |
},
|
| 218 |
{
|
| 219 |
"epoch": 0.2717391304347826,
|
| 220 |
-
"eval_loss": 0.
|
| 221 |
-
"eval_runtime": 10.
|
| 222 |
-
"eval_samples_per_second":
|
| 223 |
-
"eval_steps_per_second": 2.
|
| 224 |
"step": 250
|
| 225 |
},
|
| 226 |
{
|
| 227 |
"epoch": 0.2826086956521739,
|
| 228 |
-
"grad_norm": 0.
|
| 229 |
"learning_rate": 4.528985507246377e-05,
|
| 230 |
-
"loss": 0.
|
| 231 |
"step": 260
|
| 232 |
},
|
| 233 |
{
|
| 234 |
"epoch": 0.29347826086956524,
|
| 235 |
-
"grad_norm": 0.
|
| 236 |
"learning_rate": 4.5108695652173916e-05,
|
| 237 |
-
"loss": 0.
|
| 238 |
"step": 270
|
| 239 |
},
|
| 240 |
{
|
| 241 |
"epoch": 0.30434782608695654,
|
| 242 |
-
"grad_norm": 0.
|
| 243 |
"learning_rate": 4.492753623188406e-05,
|
| 244 |
-
"loss": 0.
|
| 245 |
"step": 280
|
| 246 |
},
|
| 247 |
{
|
| 248 |
"epoch": 0.31521739130434784,
|
| 249 |
-
"grad_norm":
|
| 250 |
"learning_rate": 4.4746376811594203e-05,
|
| 251 |
-
"loss": 0.
|
| 252 |
"step": 290
|
| 253 |
},
|
| 254 |
{
|
| 255 |
"epoch": 0.32608695652173914,
|
| 256 |
-
"grad_norm": 0.
|
| 257 |
"learning_rate": 4.456521739130435e-05,
|
| 258 |
-
"loss": 0.
|
| 259 |
"step": 300
|
| 260 |
},
|
| 261 |
{
|
| 262 |
"epoch": 0.32608695652173914,
|
| 263 |
-
"eval_loss": 0.
|
| 264 |
-
"eval_runtime": 10.
|
| 265 |
-
"eval_samples_per_second":
|
| 266 |
-
"eval_steps_per_second": 2.
|
| 267 |
"step": 300
|
| 268 |
},
|
| 269 |
{
|
| 270 |
"epoch": 0.33695652173913043,
|
| 271 |
-
"grad_norm": 0.
|
| 272 |
"learning_rate": 4.438405797101449e-05,
|
| 273 |
-
"loss": 0.
|
| 274 |
"step": 310
|
| 275 |
},
|
| 276 |
{
|
| 277 |
"epoch": 0.34782608695652173,
|
| 278 |
-
"grad_norm": 0.
|
| 279 |
"learning_rate": 4.4202898550724645e-05,
|
| 280 |
-
"loss": 0.
|
| 281 |
"step": 320
|
| 282 |
},
|
| 283 |
{
|
| 284 |
"epoch": 0.358695652173913,
|
| 285 |
-
"grad_norm":
|
| 286 |
"learning_rate": 4.4021739130434786e-05,
|
| 287 |
-
"loss": 0.
|
| 288 |
"step": 330
|
| 289 |
},
|
| 290 |
{
|
| 291 |
"epoch": 0.3695652173913043,
|
| 292 |
-
"grad_norm": 0.
|
| 293 |
"learning_rate": 4.384057971014493e-05,
|
| 294 |
-
"loss": 0.
|
| 295 |
"step": 340
|
| 296 |
},
|
| 297 |
{
|
| 298 |
"epoch": 0.3804347826086957,
|
| 299 |
-
"grad_norm":
|
| 300 |
"learning_rate": 4.365942028985507e-05,
|
| 301 |
-
"loss": 0.
|
| 302 |
"step": 350
|
| 303 |
},
|
| 304 |
{
|
| 305 |
"epoch": 0.3804347826086957,
|
| 306 |
-
"eval_loss": 0.
|
| 307 |
-
"eval_runtime": 10.
|
| 308 |
-
"eval_samples_per_second":
|
| 309 |
-
"eval_steps_per_second": 2.
|
| 310 |
"step": 350
|
| 311 |
},
|
| 312 |
{
|
| 313 |
"epoch": 0.391304347826087,
|
| 314 |
-
"grad_norm": 0.
|
| 315 |
"learning_rate": 4.347826086956522e-05,
|
| 316 |
-
"loss": 0.
|
| 317 |
"step": 360
|
| 318 |
},
|
| 319 |
{
|
| 320 |
"epoch": 0.40217391304347827,
|
| 321 |
-
"grad_norm": 0.
|
| 322 |
"learning_rate": 4.329710144927536e-05,
|
| 323 |
-
"loss": 0.
|
| 324 |
"step": 370
|
| 325 |
},
|
| 326 |
{
|
| 327 |
"epoch": 0.41304347826086957,
|
| 328 |
-
"grad_norm":
|
| 329 |
"learning_rate": 4.3115942028985515e-05,
|
| 330 |
-
"loss": 0.
|
| 331 |
"step": 380
|
| 332 |
},
|
| 333 |
{
|
| 334 |
"epoch": 0.42391304347826086,
|
| 335 |
-
"grad_norm": 0.
|
| 336 |
"learning_rate": 4.2934782608695655e-05,
|
| 337 |
-
"loss": 0.
|
| 338 |
"step": 390
|
| 339 |
},
|
| 340 |
{
|
| 341 |
"epoch": 0.43478260869565216,
|
| 342 |
-
"grad_norm": 0.
|
| 343 |
"learning_rate": 4.27536231884058e-05,
|
| 344 |
-
"loss": 0.
|
| 345 |
"step": 400
|
| 346 |
},
|
| 347 |
{
|
| 348 |
"epoch": 0.43478260869565216,
|
| 349 |
-
"eval_loss": 0.
|
| 350 |
-
"eval_runtime": 10.
|
| 351 |
-
"eval_samples_per_second":
|
| 352 |
-
"eval_steps_per_second": 2.
|
| 353 |
"step": 400
|
| 354 |
},
|
| 355 |
{
|
| 356 |
"epoch": 0.44565217391304346,
|
| 357 |
-
"grad_norm":
|
| 358 |
"learning_rate": 4.257246376811594e-05,
|
| 359 |
-
"loss": 0.
|
| 360 |
"step": 410
|
| 361 |
},
|
| 362 |
{
|
| 363 |
"epoch": 0.45652173913043476,
|
| 364 |
-
"grad_norm": 0.
|
| 365 |
"learning_rate": 4.239130434782609e-05,
|
| 366 |
-
"loss": 0.
|
| 367 |
"step": 420
|
| 368 |
},
|
| 369 |
{
|
| 370 |
"epoch": 0.4673913043478261,
|
| 371 |
-
"grad_norm": 0.
|
| 372 |
"learning_rate": 4.221014492753623e-05,
|
| 373 |
-
"loss": 0.
|
| 374 |
"step": 430
|
| 375 |
},
|
| 376 |
{
|
| 377 |
"epoch": 0.4782608695652174,
|
| 378 |
-
"grad_norm": 0.
|
| 379 |
"learning_rate": 4.202898550724638e-05,
|
| 380 |
-
"loss": 0.
|
| 381 |
"step": 440
|
| 382 |
},
|
| 383 |
{
|
| 384 |
"epoch": 0.4891304347826087,
|
| 385 |
-
"grad_norm": 0.
|
| 386 |
"learning_rate": 4.1847826086956525e-05,
|
| 387 |
-
"loss": 0.
|
| 388 |
"step": 450
|
| 389 |
},
|
| 390 |
{
|
| 391 |
"epoch": 0.4891304347826087,
|
| 392 |
-
"eval_loss": 0.
|
| 393 |
-
"eval_runtime": 10.
|
| 394 |
-
"eval_samples_per_second":
|
| 395 |
-
"eval_steps_per_second": 2.
|
| 396 |
"step": 450
|
| 397 |
},
|
| 398 |
{
|
| 399 |
"epoch": 0.5,
|
| 400 |
-
"grad_norm": 0.
|
| 401 |
"learning_rate": 4.166666666666667e-05,
|
| 402 |
-
"loss": 0.
|
| 403 |
"step": 460
|
| 404 |
},
|
| 405 |
{
|
| 406 |
"epoch": 0.5108695652173914,
|
| 407 |
-
"grad_norm": 0.
|
| 408 |
"learning_rate": 4.148550724637681e-05,
|
| 409 |
-
"loss": 0.
|
| 410 |
"step": 470
|
| 411 |
},
|
| 412 |
{
|
| 413 |
"epoch": 0.5217391304347826,
|
| 414 |
-
"grad_norm": 0.
|
| 415 |
"learning_rate": 4.130434782608696e-05,
|
| 416 |
-
"loss": 0.
|
| 417 |
"step": 480
|
| 418 |
},
|
| 419 |
{
|
| 420 |
"epoch": 0.532608695652174,
|
| 421 |
-
"grad_norm": 0.
|
| 422 |
"learning_rate": 4.11231884057971e-05,
|
| 423 |
-
"loss": 0.
|
| 424 |
"step": 490
|
| 425 |
},
|
| 426 |
{
|
| 427 |
"epoch": 0.5434782608695652,
|
| 428 |
-
"grad_norm": 0.
|
| 429 |
"learning_rate": 4.094202898550725e-05,
|
| 430 |
-
"loss": 0.
|
| 431 |
"step": 500
|
| 432 |
},
|
| 433 |
{
|
| 434 |
"epoch": 0.5434782608695652,
|
| 435 |
-
"eval_loss": 0.
|
| 436 |
-
"eval_runtime": 10.
|
| 437 |
-
"eval_samples_per_second":
|
| 438 |
-
"eval_steps_per_second": 2.
|
| 439 |
"step": 500
|
| 440 |
},
|
| 441 |
{
|
| 442 |
"epoch": 0.5543478260869565,
|
| 443 |
-
"grad_norm": 0.
|
| 444 |
"learning_rate": 4.076086956521739e-05,
|
| 445 |
-
"loss": 0.
|
| 446 |
"step": 510
|
| 447 |
},
|
| 448 |
{
|
| 449 |
"epoch": 0.5652173913043478,
|
| 450 |
-
"grad_norm": 0.
|
| 451 |
"learning_rate": 4.057971014492754e-05,
|
| 452 |
-
"loss": 0.
|
| 453 |
"step": 520
|
| 454 |
},
|
| 455 |
{
|
| 456 |
"epoch": 0.5760869565217391,
|
| 457 |
-
"grad_norm":
|
| 458 |
"learning_rate": 4.039855072463768e-05,
|
| 459 |
-
"loss": 0.
|
| 460 |
"step": 530
|
| 461 |
},
|
| 462 |
{
|
| 463 |
"epoch": 0.5869565217391305,
|
| 464 |
-
"grad_norm": 0.
|
| 465 |
"learning_rate": 4.021739130434783e-05,
|
| 466 |
-
"loss": 0.
|
| 467 |
"step": 540
|
| 468 |
},
|
| 469 |
{
|
| 470 |
"epoch": 0.5978260869565217,
|
| 471 |
-
"grad_norm": 0.
|
| 472 |
"learning_rate": 4.003623188405797e-05,
|
| 473 |
-
"loss": 0.
|
| 474 |
"step": 550
|
| 475 |
},
|
| 476 |
{
|
| 477 |
"epoch": 0.5978260869565217,
|
| 478 |
-
"eval_loss": 0.
|
| 479 |
-
"eval_runtime": 10.
|
| 480 |
-
"eval_samples_per_second":
|
| 481 |
-
"eval_steps_per_second": 2.
|
| 482 |
"step": 550
|
| 483 |
},
|
| 484 |
{
|
| 485 |
"epoch": 0.6086956521739131,
|
| 486 |
-
"grad_norm":
|
| 487 |
"learning_rate": 3.985507246376812e-05,
|
| 488 |
-
"loss": 0.
|
| 489 |
"step": 560
|
| 490 |
},
|
| 491 |
{
|
| 492 |
"epoch": 0.6195652173913043,
|
| 493 |
-
"grad_norm": 0.
|
| 494 |
"learning_rate": 3.9673913043478264e-05,
|
| 495 |
-
"loss": 0.
|
| 496 |
"step": 570
|
| 497 |
},
|
| 498 |
{
|
| 499 |
"epoch": 0.6304347826086957,
|
| 500 |
-
"grad_norm":
|
| 501 |
"learning_rate": 3.9492753623188405e-05,
|
| 502 |
-
"loss": 0.
|
| 503 |
"step": 580
|
| 504 |
},
|
| 505 |
{
|
| 506 |
"epoch": 0.6413043478260869,
|
| 507 |
-
"grad_norm":
|
| 508 |
"learning_rate": 3.931159420289855e-05,
|
| 509 |
-
"loss": 0.
|
| 510 |
"step": 590
|
| 511 |
},
|
| 512 |
{
|
| 513 |
"epoch": 0.6521739130434783,
|
| 514 |
-
"grad_norm": 0.
|
| 515 |
"learning_rate": 3.91304347826087e-05,
|
| 516 |
-
"loss": 0.
|
| 517 |
"step": 600
|
| 518 |
},
|
| 519 |
{
|
| 520 |
"epoch": 0.6521739130434783,
|
| 521 |
-
"eval_loss": 0.
|
| 522 |
-
"eval_runtime": 10.
|
| 523 |
-
"eval_samples_per_second":
|
| 524 |
-
"eval_steps_per_second": 2.
|
| 525 |
"step": 600
|
| 526 |
},
|
| 527 |
{
|
| 528 |
"epoch": 0.6630434782608695,
|
| 529 |
-
"grad_norm":
|
| 530 |
"learning_rate": 3.8949275362318846e-05,
|
| 531 |
-
"loss": 0.
|
| 532 |
"step": 610
|
| 533 |
},
|
| 534 |
{
|
| 535 |
"epoch": 0.6739130434782609,
|
| 536 |
-
"grad_norm": 0.
|
| 537 |
"learning_rate": 3.876811594202899e-05,
|
| 538 |
-
"loss": 0.
|
| 539 |
"step": 620
|
| 540 |
},
|
| 541 |
{
|
| 542 |
"epoch": 0.6847826086956522,
|
| 543 |
-
"grad_norm": 0.
|
| 544 |
"learning_rate": 3.8586956521739134e-05,
|
| 545 |
-
"loss": 0.
|
| 546 |
"step": 630
|
| 547 |
},
|
| 548 |
{
|
| 549 |
"epoch": 0.6956521739130435,
|
| 550 |
-
"grad_norm": 0.
|
| 551 |
"learning_rate": 3.8405797101449274e-05,
|
| 552 |
-
"loss": 0.
|
| 553 |
"step": 640
|
| 554 |
},
|
| 555 |
{
|
| 556 |
"epoch": 0.7065217391304348,
|
| 557 |
-
"grad_norm": 0.
|
| 558 |
"learning_rate": 3.822463768115942e-05,
|
| 559 |
-
"loss": 0.
|
| 560 |
"step": 650
|
| 561 |
},
|
| 562 |
{
|
| 563 |
"epoch": 0.7065217391304348,
|
| 564 |
-
"eval_loss": 0.
|
| 565 |
-
"eval_runtime": 10.
|
| 566 |
-
"eval_samples_per_second":
|
| 567 |
-
"eval_steps_per_second": 2.
|
| 568 |
"step": 650
|
| 569 |
},
|
| 570 |
{
|
| 571 |
"epoch": 0.717391304347826,
|
| 572 |
-
"grad_norm": 0.
|
| 573 |
"learning_rate": 3.804347826086957e-05,
|
| 574 |
-
"loss": 0.
|
| 575 |
"step": 660
|
| 576 |
},
|
| 577 |
{
|
| 578 |
"epoch": 0.7282608695652174,
|
| 579 |
-
"grad_norm":
|
| 580 |
"learning_rate": 3.7862318840579716e-05,
|
| 581 |
-
"loss": 0.
|
| 582 |
"step": 670
|
| 583 |
},
|
| 584 |
{
|
| 585 |
"epoch": 0.7391304347826086,
|
| 586 |
-
"grad_norm": 0.
|
| 587 |
"learning_rate": 3.7681159420289856e-05,
|
| 588 |
-
"loss": 0.
|
| 589 |
"step": 680
|
| 590 |
},
|
| 591 |
{
|
| 592 |
"epoch": 0.75,
|
| 593 |
-
"grad_norm":
|
| 594 |
"learning_rate": 3.7500000000000003e-05,
|
| 595 |
-
"loss": 0.
|
| 596 |
"step": 690
|
| 597 |
},
|
| 598 |
{
|
| 599 |
"epoch": 0.7608695652173914,
|
| 600 |
-
"grad_norm": 0.
|
| 601 |
"learning_rate": 3.7318840579710144e-05,
|
| 602 |
-
"loss": 0.
|
| 603 |
"step": 700
|
| 604 |
},
|
| 605 |
{
|
| 606 |
"epoch": 0.7608695652173914,
|
| 607 |
-
"eval_loss": 0.
|
| 608 |
-
"eval_runtime": 10.
|
| 609 |
-
"eval_samples_per_second":
|
| 610 |
-
"eval_steps_per_second": 2.
|
| 611 |
"step": 700
|
| 612 |
},
|
| 613 |
{
|
| 614 |
"epoch": 0.7717391304347826,
|
| 615 |
-
"grad_norm":
|
| 616 |
"learning_rate": 3.713768115942029e-05,
|
| 617 |
-
"loss": 0.
|
| 618 |
"step": 710
|
| 619 |
},
|
| 620 |
{
|
| 621 |
"epoch": 0.782608695652174,
|
| 622 |
-
"grad_norm":
|
| 623 |
"learning_rate": 3.695652173913043e-05,
|
| 624 |
-
"loss": 0.
|
| 625 |
"step": 720
|
| 626 |
},
|
| 627 |
{
|
| 628 |
"epoch": 0.7934782608695652,
|
| 629 |
-
"grad_norm": 0.
|
| 630 |
"learning_rate": 3.6775362318840586e-05,
|
| 631 |
-
"loss": 0.
|
| 632 |
"step": 730
|
| 633 |
},
|
| 634 |
{
|
| 635 |
"epoch": 0.8043478260869565,
|
| 636 |
-
"grad_norm":
|
| 637 |
"learning_rate": 3.6594202898550726e-05,
|
| 638 |
-
"loss": 0.
|
| 639 |
"step": 740
|
| 640 |
},
|
| 641 |
{
|
| 642 |
"epoch": 0.8152173913043478,
|
| 643 |
-
"grad_norm": 0.
|
| 644 |
"learning_rate": 3.641304347826087e-05,
|
| 645 |
-
"loss": 0.
|
| 646 |
"step": 750
|
| 647 |
},
|
| 648 |
{
|
| 649 |
"epoch": 0.8152173913043478,
|
| 650 |
-
"eval_loss": 0.
|
| 651 |
-
"eval_runtime": 10.
|
| 652 |
-
"eval_samples_per_second":
|
| 653 |
-
"eval_steps_per_second": 2.
|
| 654 |
"step": 750
|
| 655 |
},
|
| 656 |
{
|
| 657 |
"epoch": 0.8260869565217391,
|
| 658 |
-
"grad_norm":
|
| 659 |
"learning_rate": 3.6231884057971014e-05,
|
| 660 |
-
"loss": 0.
|
| 661 |
"step": 760
|
| 662 |
},
|
| 663 |
{
|
| 664 |
"epoch": 0.8369565217391305,
|
| 665 |
-
"grad_norm":
|
| 666 |
"learning_rate": 3.605072463768116e-05,
|
| 667 |
-
"loss": 0.
|
| 668 |
"step": 770
|
| 669 |
},
|
| 670 |
{
|
| 671 |
"epoch": 0.8478260869565217,
|
| 672 |
-
"grad_norm":
|
| 673 |
"learning_rate": 3.58695652173913e-05,
|
| 674 |
-
"loss": 0.
|
| 675 |
"step": 780
|
| 676 |
},
|
| 677 |
{
|
| 678 |
"epoch": 0.8586956521739131,
|
| 679 |
-
"grad_norm": 0.
|
| 680 |
"learning_rate": 3.568840579710145e-05,
|
| 681 |
-
"loss": 0.
|
| 682 |
"step": 790
|
| 683 |
},
|
| 684 |
{
|
| 685 |
"epoch": 0.8695652173913043,
|
| 686 |
-
"grad_norm": 0.
|
| 687 |
"learning_rate": 3.5507246376811596e-05,
|
| 688 |
-
"loss": 0.
|
| 689 |
"step": 800
|
| 690 |
},
|
| 691 |
{
|
| 692 |
"epoch": 0.8695652173913043,
|
| 693 |
-
"eval_loss": 0.
|
| 694 |
-
"eval_runtime": 10.
|
| 695 |
-
"eval_samples_per_second":
|
| 696 |
-
"eval_steps_per_second": 2.
|
| 697 |
"step": 800
|
| 698 |
},
|
| 699 |
{
|
| 700 |
"epoch": 0.8804347826086957,
|
| 701 |
-
"grad_norm":
|
| 702 |
"learning_rate": 3.532608695652174e-05,
|
| 703 |
-
"loss": 0.
|
| 704 |
"step": 810
|
| 705 |
},
|
| 706 |
{
|
| 707 |
"epoch": 0.8913043478260869,
|
| 708 |
-
"grad_norm":
|
| 709 |
"learning_rate": 3.514492753623188e-05,
|
| 710 |
-
"loss": 0.
|
| 711 |
"step": 820
|
| 712 |
},
|
| 713 |
{
|
| 714 |
"epoch": 0.9021739130434783,
|
| 715 |
-
"grad_norm": 0.
|
| 716 |
"learning_rate": 3.496376811594203e-05,
|
| 717 |
-
"loss": 0.
|
| 718 |
"step": 830
|
| 719 |
},
|
| 720 |
{
|
| 721 |
"epoch": 0.9130434782608695,
|
| 722 |
-
"grad_norm":
|
| 723 |
"learning_rate": 3.478260869565218e-05,
|
| 724 |
-
"loss": 0.
|
| 725 |
"step": 840
|
| 726 |
},
|
| 727 |
{
|
| 728 |
"epoch": 0.9239130434782609,
|
| 729 |
-
"grad_norm": 0.
|
| 730 |
"learning_rate": 3.460144927536232e-05,
|
| 731 |
-
"loss": 0.
|
| 732 |
"step": 850
|
| 733 |
},
|
| 734 |
{
|
| 735 |
"epoch": 0.9239130434782609,
|
| 736 |
-
"eval_loss": 0.
|
| 737 |
-
"eval_runtime": 10.
|
| 738 |
-
"eval_samples_per_second":
|
| 739 |
-
"eval_steps_per_second": 2.
|
| 740 |
"step": 850
|
| 741 |
},
|
| 742 |
{
|
| 743 |
"epoch": 0.9347826086956522,
|
| 744 |
-
"grad_norm":
|
| 745 |
"learning_rate": 3.4420289855072465e-05,
|
| 746 |
-
"loss": 0.
|
| 747 |
"step": 860
|
| 748 |
},
|
| 749 |
{
|
| 750 |
"epoch": 0.9456521739130435,
|
| 751 |
-
"grad_norm":
|
| 752 |
"learning_rate": 3.423913043478261e-05,
|
| 753 |
-
"loss": 0.
|
| 754 |
"step": 870
|
| 755 |
},
|
| 756 |
{
|
| 757 |
"epoch": 0.9565217391304348,
|
| 758 |
-
"grad_norm":
|
| 759 |
"learning_rate": 3.405797101449276e-05,
|
| 760 |
-
"loss": 0.
|
| 761 |
"step": 880
|
| 762 |
},
|
| 763 |
{
|
| 764 |
"epoch": 0.967391304347826,
|
| 765 |
-
"grad_norm":
|
| 766 |
"learning_rate": 3.38768115942029e-05,
|
| 767 |
-
"loss": 0.
|
| 768 |
"step": 890
|
| 769 |
},
|
| 770 |
{
|
| 771 |
"epoch": 0.9782608695652174,
|
| 772 |
-
"grad_norm": 0.
|
| 773 |
"learning_rate": 3.369565217391305e-05,
|
| 774 |
-
"loss": 0.
|
| 775 |
"step": 900
|
| 776 |
},
|
| 777 |
{
|
| 778 |
"epoch": 0.9782608695652174,
|
| 779 |
-
"eval_loss": 0.
|
| 780 |
-
"eval_runtime": 10.
|
| 781 |
-
"eval_samples_per_second":
|
| 782 |
-
"eval_steps_per_second": 2.
|
| 783 |
"step": 900
|
| 784 |
},
|
| 785 |
{
|
| 786 |
"epoch": 0.9891304347826086,
|
| 787 |
-
"grad_norm":
|
| 788 |
"learning_rate": 3.351449275362319e-05,
|
| 789 |
-
"loss": 0.
|
| 790 |
"step": 910
|
| 791 |
},
|
| 792 |
{
|
| 793 |
"epoch": 1.0,
|
| 794 |
-
"grad_norm":
|
| 795 |
"learning_rate": 3.3333333333333335e-05,
|
| 796 |
-
"loss": 0.
|
| 797 |
"step": 920
|
| 798 |
},
|
| 799 |
{
|
| 800 |
"epoch": 1.0108695652173914,
|
| 801 |
-
"grad_norm":
|
| 802 |
"learning_rate": 3.3152173913043475e-05,
|
| 803 |
-
"loss": 0.
|
| 804 |
"step": 930
|
| 805 |
},
|
| 806 |
{
|
| 807 |
"epoch": 1.0217391304347827,
|
| 808 |
-
"grad_norm":
|
| 809 |
"learning_rate": 3.297101449275363e-05,
|
| 810 |
-
"loss": 0.
|
| 811 |
"step": 940
|
| 812 |
},
|
| 813 |
{
|
| 814 |
"epoch": 1.0326086956521738,
|
| 815 |
-
"grad_norm":
|
| 816 |
"learning_rate": 3.278985507246377e-05,
|
| 817 |
-
"loss": 0.
|
| 818 |
"step": 950
|
| 819 |
},
|
| 820 |
{
|
| 821 |
"epoch": 1.0326086956521738,
|
| 822 |
-
"eval_loss": 0.
|
| 823 |
-
"eval_runtime": 10.
|
| 824 |
-
"eval_samples_per_second":
|
| 825 |
-
"eval_steps_per_second": 2.
|
| 826 |
"step": 950
|
| 827 |
},
|
| 828 |
{
|
| 829 |
"epoch": 1.0434782608695652,
|
| 830 |
-
"grad_norm":
|
| 831 |
"learning_rate": 3.260869565217392e-05,
|
| 832 |
-
"loss": 0.
|
| 833 |
"step": 960
|
| 834 |
},
|
| 835 |
{
|
| 836 |
"epoch": 1.0543478260869565,
|
| 837 |
-
"grad_norm": 1.
|
| 838 |
"learning_rate": 3.242753623188406e-05,
|
| 839 |
-
"loss": 0.
|
| 840 |
"step": 970
|
| 841 |
},
|
| 842 |
{
|
| 843 |
"epoch": 1.065217391304348,
|
| 844 |
-
"grad_norm": 1.
|
| 845 |
"learning_rate": 3.2246376811594205e-05,
|
| 846 |
-
"loss": 0.
|
| 847 |
"step": 980
|
| 848 |
},
|
| 849 |
{
|
| 850 |
"epoch": 1.0760869565217392,
|
| 851 |
-
"grad_norm":
|
| 852 |
"learning_rate": 3.2065217391304345e-05,
|
| 853 |
-
"loss": 0.
|
| 854 |
"step": 990
|
| 855 |
},
|
| 856 |
{
|
| 857 |
"epoch": 1.0869565217391304,
|
| 858 |
-
"grad_norm": 1.
|
| 859 |
"learning_rate": 3.188405797101449e-05,
|
| 860 |
-
"loss": 0.
|
| 861 |
"step": 1000
|
| 862 |
},
|
| 863 |
{
|
| 864 |
"epoch": 1.0869565217391304,
|
| 865 |
-
"eval_loss": 0.
|
| 866 |
-
"eval_runtime": 10.
|
| 867 |
-
"eval_samples_per_second":
|
| 868 |
-
"eval_steps_per_second": 2.
|
| 869 |
"step": 1000
|
| 870 |
},
|
| 871 |
{
|
| 872 |
"epoch": 1.0978260869565217,
|
| 873 |
-
"grad_norm":
|
| 874 |
"learning_rate": 3.170289855072464e-05,
|
| 875 |
-
"loss": 0.
|
| 876 |
"step": 1010
|
| 877 |
},
|
| 878 |
{
|
| 879 |
"epoch": 1.108695652173913,
|
| 880 |
-
"grad_norm":
|
| 881 |
"learning_rate": 3.152173913043479e-05,
|
| 882 |
-
"loss": 0.
|
| 883 |
"step": 1020
|
| 884 |
},
|
| 885 |
{
|
| 886 |
"epoch": 1.1195652173913044,
|
| 887 |
-
"grad_norm":
|
| 888 |
"learning_rate": 3.134057971014493e-05,
|
| 889 |
-
"loss": 0.
|
| 890 |
"step": 1030
|
| 891 |
},
|
| 892 |
{
|
| 893 |
"epoch": 1.1304347826086956,
|
| 894 |
-
"grad_norm": 1.
|
| 895 |
"learning_rate": 3.1159420289855074e-05,
|
| 896 |
-
"loss": 0.
|
| 897 |
"step": 1040
|
| 898 |
},
|
| 899 |
{
|
| 900 |
"epoch": 1.141304347826087,
|
| 901 |
-
"grad_norm":
|
| 902 |
"learning_rate": 3.0978260869565215e-05,
|
| 903 |
-
"loss": 0.
|
| 904 |
"step": 1050
|
| 905 |
},
|
| 906 |
{
|
| 907 |
"epoch": 1.141304347826087,
|
| 908 |
-
"eval_loss": 0.
|
| 909 |
-
"eval_runtime": 10.
|
| 910 |
-
"eval_samples_per_second":
|
| 911 |
-
"eval_steps_per_second": 2.
|
| 912 |
"step": 1050
|
| 913 |
},
|
| 914 |
{
|
| 915 |
"epoch": 1.1521739130434783,
|
| 916 |
-
"grad_norm":
|
| 917 |
"learning_rate": 3.079710144927536e-05,
|
| 918 |
-
"loss": 0.
|
| 919 |
"step": 1060
|
| 920 |
},
|
| 921 |
{
|
| 922 |
"epoch": 1.1630434782608696,
|
| 923 |
-
"grad_norm":
|
| 924 |
"learning_rate": 3.061594202898551e-05,
|
| 925 |
-
"loss": 0.
|
| 926 |
"step": 1070
|
| 927 |
},
|
| 928 |
{
|
| 929 |
"epoch": 1.1739130434782608,
|
| 930 |
-
"grad_norm":
|
| 931 |
"learning_rate": 3.0434782608695656e-05,
|
| 932 |
-
"loss": 0.
|
| 933 |
"step": 1080
|
| 934 |
},
|
| 935 |
{
|
| 936 |
"epoch": 1.184782608695652,
|
| 937 |
-
"grad_norm":
|
| 938 |
"learning_rate": 3.02536231884058e-05,
|
| 939 |
-
"loss": 0.
|
| 940 |
"step": 1090
|
| 941 |
},
|
| 942 |
{
|
| 943 |
"epoch": 1.1956521739130435,
|
| 944 |
-
"grad_norm": 1.
|
| 945 |
"learning_rate": 3.0072463768115944e-05,
|
| 946 |
-
"loss": 0.
|
| 947 |
"step": 1100
|
| 948 |
},
|
| 949 |
{
|
| 950 |
"epoch": 1.1956521739130435,
|
| 951 |
-
"eval_loss": 0.
|
| 952 |
-
"eval_runtime": 10.
|
| 953 |
-
"eval_samples_per_second":
|
| 954 |
-
"eval_steps_per_second": 2.
|
| 955 |
"step": 1100
|
| 956 |
},
|
| 957 |
{
|
| 958 |
"epoch": 1.2065217391304348,
|
| 959 |
-
"grad_norm":
|
| 960 |
"learning_rate": 2.9891304347826088e-05,
|
| 961 |
-
"loss": 0.
|
| 962 |
"step": 1110
|
| 963 |
},
|
| 964 |
{
|
| 965 |
"epoch": 1.2173913043478262,
|
| 966 |
-
"grad_norm":
|
| 967 |
"learning_rate": 2.971014492753623e-05,
|
| 968 |
-
"loss": 0.
|
| 969 |
"step": 1120
|
| 970 |
},
|
| 971 |
{
|
| 972 |
"epoch": 1.2282608695652173,
|
| 973 |
-
"grad_norm": 1.
|
| 974 |
"learning_rate": 2.9528985507246375e-05,
|
| 975 |
-
"loss": 0.
|
| 976 |
"step": 1130
|
| 977 |
},
|
| 978 |
{
|
| 979 |
"epoch": 1.2391304347826086,
|
| 980 |
-
"grad_norm":
|
| 981 |
"learning_rate": 2.9347826086956526e-05,
|
| 982 |
-
"loss": 0.
|
| 983 |
"step": 1140
|
| 984 |
},
|
| 985 |
{
|
| 986 |
"epoch": 1.25,
|
| 987 |
-
"grad_norm": 1.
|
| 988 |
"learning_rate": 2.916666666666667e-05,
|
| 989 |
-
"loss": 0.
|
| 990 |
"step": 1150
|
| 991 |
},
|
| 992 |
{
|
| 993 |
"epoch": 1.25,
|
| 994 |
-
"eval_loss": 0.
|
| 995 |
-
"eval_runtime": 10.
|
| 996 |
-
"eval_samples_per_second":
|
| 997 |
-
"eval_steps_per_second": 2.
|
| 998 |
"step": 1150
|
| 999 |
},
|
| 1000 |
{
|
| 1001 |
"epoch": 1.2608695652173914,
|
| 1002 |
-
"grad_norm": 1.
|
| 1003 |
"learning_rate": 2.8985507246376814e-05,
|
| 1004 |
-
"loss": 0.
|
| 1005 |
"step": 1160
|
| 1006 |
},
|
| 1007 |
{
|
| 1008 |
"epoch": 1.2717391304347827,
|
| 1009 |
-
"grad_norm":
|
| 1010 |
"learning_rate": 2.8804347826086957e-05,
|
| 1011 |
-
"loss": 0.
|
| 1012 |
"step": 1170
|
| 1013 |
},
|
| 1014 |
{
|
| 1015 |
"epoch": 1.2826086956521738,
|
| 1016 |
-
"grad_norm":
|
| 1017 |
"learning_rate": 2.86231884057971e-05,
|
| 1018 |
-
"loss": 0.
|
| 1019 |
"step": 1180
|
| 1020 |
},
|
| 1021 |
{
|
| 1022 |
"epoch": 1.2934782608695652,
|
| 1023 |
-
"grad_norm":
|
| 1024 |
"learning_rate": 2.8442028985507245e-05,
|
| 1025 |
-
"loss": 0.
|
| 1026 |
"step": 1190
|
| 1027 |
},
|
| 1028 |
{
|
| 1029 |
"epoch": 1.3043478260869565,
|
| 1030 |
-
"grad_norm":
|
| 1031 |
"learning_rate": 2.826086956521739e-05,
|
| 1032 |
-
"loss": 0.
|
| 1033 |
"step": 1200
|
| 1034 |
},
|
| 1035 |
{
|
| 1036 |
"epoch": 1.3043478260869565,
|
| 1037 |
-
"eval_loss": 0.
|
| 1038 |
-
"eval_runtime": 10.
|
| 1039 |
-
"eval_samples_per_second":
|
| 1040 |
-
"eval_steps_per_second": 2.
|
| 1041 |
"step": 1200
|
| 1042 |
},
|
| 1043 |
{
|
| 1044 |
"epoch": 1.315217391304348,
|
| 1045 |
-
"grad_norm":
|
| 1046 |
"learning_rate": 2.807971014492754e-05,
|
| 1047 |
-
"loss": 0.
|
| 1048 |
"step": 1210
|
| 1049 |
},
|
| 1050 |
{
|
| 1051 |
"epoch": 1.3260869565217392,
|
| 1052 |
-
"grad_norm":
|
| 1053 |
"learning_rate": 2.7898550724637683e-05,
|
| 1054 |
-
"loss": 0.
|
| 1055 |
"step": 1220
|
| 1056 |
},
|
| 1057 |
{
|
| 1058 |
"epoch": 1.3369565217391304,
|
| 1059 |
-
"grad_norm":
|
| 1060 |
"learning_rate": 2.7717391304347827e-05,
|
| 1061 |
-
"loss": 0.
|
| 1062 |
"step": 1230
|
| 1063 |
},
|
| 1064 |
{
|
| 1065 |
"epoch": 1.3478260869565217,
|
| 1066 |
-
"grad_norm": 1.
|
| 1067 |
"learning_rate": 2.753623188405797e-05,
|
| 1068 |
-
"loss": 0.
|
| 1069 |
"step": 1240
|
| 1070 |
},
|
| 1071 |
{
|
| 1072 |
"epoch": 1.358695652173913,
|
| 1073 |
-
"grad_norm":
|
| 1074 |
"learning_rate": 2.7355072463768118e-05,
|
| 1075 |
-
"loss": 0.
|
| 1076 |
"step": 1250
|
| 1077 |
},
|
| 1078 |
{
|
| 1079 |
"epoch": 1.358695652173913,
|
| 1080 |
-
"eval_loss": 0.
|
| 1081 |
-
"eval_runtime": 10.
|
| 1082 |
-
"eval_samples_per_second":
|
| 1083 |
-
"eval_steps_per_second": 2.
|
| 1084 |
"step": 1250
|
| 1085 |
},
|
| 1086 |
{
|
| 1087 |
"epoch": 1.3695652173913042,
|
| 1088 |
-
"grad_norm": 1.
|
| 1089 |
"learning_rate": 2.7173913043478262e-05,
|
| 1090 |
-
"loss": 0.
|
| 1091 |
"step": 1260
|
| 1092 |
},
|
| 1093 |
{
|
| 1094 |
"epoch": 1.3804347826086958,
|
| 1095 |
-
"grad_norm":
|
| 1096 |
"learning_rate": 2.6992753623188406e-05,
|
| 1097 |
-
"loss": 0.
|
| 1098 |
"step": 1270
|
| 1099 |
},
|
| 1100 |
{
|
| 1101 |
"epoch": 1.391304347826087,
|
| 1102 |
-
"grad_norm":
|
| 1103 |
"learning_rate": 2.6811594202898553e-05,
|
| 1104 |
-
"loss": 0.
|
| 1105 |
"step": 1280
|
| 1106 |
},
|
| 1107 |
{
|
| 1108 |
"epoch": 1.4021739130434783,
|
| 1109 |
-
"grad_norm": 1.
|
| 1110 |
"learning_rate": 2.66304347826087e-05,
|
| 1111 |
-
"loss": 0.
|
| 1112 |
"step": 1290
|
| 1113 |
},
|
| 1114 |
{
|
| 1115 |
"epoch": 1.4130434782608696,
|
| 1116 |
-
"grad_norm": 1.
|
| 1117 |
"learning_rate": 2.6449275362318844e-05,
|
| 1118 |
-
"loss": 0.
|
| 1119 |
"step": 1300
|
| 1120 |
},
|
| 1121 |
{
|
| 1122 |
"epoch": 1.4130434782608696,
|
| 1123 |
-
"eval_loss": 0.
|
| 1124 |
-
"eval_runtime": 10.
|
| 1125 |
-
"eval_samples_per_second":
|
| 1126 |
-
"eval_steps_per_second": 2.
|
| 1127 |
"step": 1300
|
| 1128 |
},
|
| 1129 |
{
|
| 1130 |
"epoch": 1.4239130434782608,
|
| 1131 |
-
"grad_norm": 1.
|
| 1132 |
"learning_rate": 2.6268115942028988e-05,
|
| 1133 |
-
"loss": 0.
|
| 1134 |
"step": 1310
|
| 1135 |
},
|
| 1136 |
{
|
| 1137 |
"epoch": 1.434782608695652,
|
| 1138 |
-
"grad_norm": 1.
|
| 1139 |
"learning_rate": 2.608695652173913e-05,
|
| 1140 |
-
"loss": 0.
|
| 1141 |
"step": 1320
|
| 1142 |
},
|
| 1143 |
{
|
| 1144 |
"epoch": 1.4456521739130435,
|
| 1145 |
-
"grad_norm": 1.
|
| 1146 |
"learning_rate": 2.5905797101449275e-05,
|
| 1147 |
-
"loss": 0.
|
| 1148 |
"step": 1330
|
| 1149 |
},
|
| 1150 |
{
|
| 1151 |
"epoch": 1.4565217391304348,
|
| 1152 |
-
"grad_norm":
|
| 1153 |
"learning_rate": 2.572463768115942e-05,
|
| 1154 |
-
"loss": 0.
|
| 1155 |
"step": 1340
|
| 1156 |
},
|
| 1157 |
{
|
| 1158 |
"epoch": 1.4673913043478262,
|
| 1159 |
-
"grad_norm":
|
| 1160 |
"learning_rate": 2.554347826086957e-05,
|
| 1161 |
-
"loss": 0.
|
| 1162 |
"step": 1350
|
| 1163 |
},
|
| 1164 |
{
|
| 1165 |
"epoch": 1.4673913043478262,
|
| 1166 |
-
"eval_loss": 0.
|
| 1167 |
-
"eval_runtime": 10.
|
| 1168 |
-
"eval_samples_per_second":
|
| 1169 |
-
"eval_steps_per_second": 2.
|
| 1170 |
"step": 1350
|
| 1171 |
},
|
| 1172 |
{
|
| 1173 |
"epoch": 1.4782608695652173,
|
| 1174 |
-
"grad_norm": 1.
|
| 1175 |
"learning_rate": 2.5362318840579714e-05,
|
| 1176 |
-
"loss": 0.
|
| 1177 |
"step": 1360
|
| 1178 |
},
|
| 1179 |
{
|
| 1180 |
"epoch": 1.4891304347826086,
|
| 1181 |
-
"grad_norm": 1.
|
| 1182 |
"learning_rate": 2.5181159420289857e-05,
|
| 1183 |
-
"loss": 0.
|
| 1184 |
"step": 1370
|
| 1185 |
},
|
| 1186 |
{
|
| 1187 |
"epoch": 1.5,
|
| 1188 |
-
"grad_norm": 1.
|
| 1189 |
"learning_rate": 2.5e-05,
|
| 1190 |
-
"loss": 0.
|
| 1191 |
"step": 1380
|
| 1192 |
},
|
| 1193 |
{
|
| 1194 |
"epoch": 1.5108695652173914,
|
| 1195 |
-
"grad_norm": 1.
|
| 1196 |
"learning_rate": 2.4818840579710145e-05,
|
| 1197 |
-
"loss": 0.
|
| 1198 |
"step": 1390
|
| 1199 |
},
|
| 1200 |
{
|
| 1201 |
"epoch": 1.5217391304347827,
|
| 1202 |
-
"grad_norm":
|
| 1203 |
"learning_rate": 2.4637681159420292e-05,
|
| 1204 |
-
"loss": 0.
|
| 1205 |
"step": 1400
|
| 1206 |
},
|
| 1207 |
{
|
| 1208 |
"epoch": 1.5217391304347827,
|
| 1209 |
-
"eval_loss": 0.
|
| 1210 |
-
"eval_runtime": 10.
|
| 1211 |
-
"eval_samples_per_second":
|
| 1212 |
-
"eval_steps_per_second": 2.
|
| 1213 |
"step": 1400
|
| 1214 |
},
|
| 1215 |
{
|
| 1216 |
"epoch": 1.5326086956521738,
|
| 1217 |
-
"grad_norm": 1.
|
| 1218 |
"learning_rate": 2.4456521739130436e-05,
|
| 1219 |
-
"loss": 0.
|
| 1220 |
"step": 1410
|
| 1221 |
},
|
| 1222 |
{
|
| 1223 |
"epoch": 1.5434782608695652,
|
| 1224 |
-
"grad_norm": 1.
|
| 1225 |
"learning_rate": 2.427536231884058e-05,
|
| 1226 |
-
"loss": 0.
|
| 1227 |
"step": 1420
|
| 1228 |
},
|
| 1229 |
{
|
| 1230 |
"epoch": 1.5543478260869565,
|
| 1231 |
-
"grad_norm":
|
| 1232 |
"learning_rate": 2.4094202898550724e-05,
|
| 1233 |
-
"loss": 0.
|
| 1234 |
"step": 1430
|
| 1235 |
},
|
| 1236 |
{
|
| 1237 |
"epoch": 1.5652173913043477,
|
| 1238 |
-
"grad_norm": 1.
|
| 1239 |
"learning_rate": 2.391304347826087e-05,
|
| 1240 |
-
"loss": 0.
|
| 1241 |
"step": 1440
|
| 1242 |
},
|
| 1243 |
{
|
| 1244 |
"epoch": 1.5760869565217392,
|
| 1245 |
-
"grad_norm":
|
| 1246 |
"learning_rate": 2.3731884057971015e-05,
|
| 1247 |
-
"loss": 0.
|
| 1248 |
"step": 1450
|
| 1249 |
},
|
| 1250 |
{
|
| 1251 |
"epoch": 1.5760869565217392,
|
| 1252 |
-
"eval_loss": 0.
|
| 1253 |
-
"eval_runtime": 10.
|
| 1254 |
-
"eval_samples_per_second":
|
| 1255 |
-
"eval_steps_per_second": 2.
|
| 1256 |
"step": 1450
|
| 1257 |
},
|
| 1258 |
{
|
| 1259 |
"epoch": 1.5869565217391304,
|
| 1260 |
-
"grad_norm":
|
| 1261 |
"learning_rate": 2.355072463768116e-05,
|
| 1262 |
-
"loss": 0.
|
| 1263 |
"step": 1460
|
| 1264 |
},
|
| 1265 |
{
|
| 1266 |
"epoch": 1.5978260869565217,
|
| 1267 |
-
"grad_norm": 1.
|
| 1268 |
"learning_rate": 2.3369565217391306e-05,
|
| 1269 |
-
"loss": 0.
|
| 1270 |
"step": 1470
|
| 1271 |
},
|
| 1272 |
{
|
| 1273 |
"epoch": 1.608695652173913,
|
| 1274 |
-
"grad_norm": 1.
|
| 1275 |
"learning_rate": 2.318840579710145e-05,
|
| 1276 |
-
"loss": 0.
|
| 1277 |
"step": 1480
|
| 1278 |
},
|
| 1279 |
{
|
| 1280 |
"epoch": 1.6195652173913042,
|
| 1281 |
-
"grad_norm":
|
| 1282 |
"learning_rate": 2.3007246376811593e-05,
|
| 1283 |
-
"loss": 0.
|
| 1284 |
"step": 1490
|
| 1285 |
},
|
| 1286 |
{
|
| 1287 |
"epoch": 1.6304347826086958,
|
| 1288 |
-
"grad_norm":
|
| 1289 |
"learning_rate": 2.282608695652174e-05,
|
| 1290 |
-
"loss": 0.
|
| 1291 |
"step": 1500
|
| 1292 |
},
|
| 1293 |
{
|
| 1294 |
"epoch": 1.6304347826086958,
|
| 1295 |
-
"eval_loss": 0.
|
| 1296 |
-
"eval_runtime": 10.
|
| 1297 |
-
"eval_samples_per_second":
|
| 1298 |
-
"eval_steps_per_second": 2.
|
| 1299 |
"step": 1500
|
| 1300 |
},
|
| 1301 |
{
|
| 1302 |
"epoch": 1.641304347826087,
|
| 1303 |
-
"grad_norm":
|
| 1304 |
"learning_rate": 2.2644927536231884e-05,
|
| 1305 |
-
"loss": 0.
|
| 1306 |
"step": 1510
|
| 1307 |
},
|
| 1308 |
{
|
| 1309 |
"epoch": 1.6521739130434783,
|
| 1310 |
-
"grad_norm":
|
| 1311 |
"learning_rate": 2.246376811594203e-05,
|
| 1312 |
-
"loss": 0.
|
| 1313 |
"step": 1520
|
| 1314 |
},
|
| 1315 |
{
|
| 1316 |
"epoch": 1.6630434782608696,
|
| 1317 |
-
"grad_norm":
|
| 1318 |
"learning_rate": 2.2282608695652175e-05,
|
| 1319 |
-
"loss": 0.
|
| 1320 |
"step": 1530
|
| 1321 |
},
|
| 1322 |
{
|
| 1323 |
"epoch": 1.6739130434782608,
|
| 1324 |
-
"grad_norm": 1.
|
| 1325 |
"learning_rate": 2.2101449275362323e-05,
|
| 1326 |
-
"loss": 0.
|
| 1327 |
"step": 1540
|
| 1328 |
},
|
| 1329 |
{
|
| 1330 |
"epoch": 1.6847826086956523,
|
| 1331 |
-
"grad_norm": 1.
|
| 1332 |
"learning_rate": 2.1920289855072466e-05,
|
| 1333 |
-
"loss": 0.
|
| 1334 |
"step": 1550
|
| 1335 |
},
|
| 1336 |
{
|
| 1337 |
"epoch": 1.6847826086956523,
|
| 1338 |
-
"eval_loss": 0.
|
| 1339 |
-
"eval_runtime": 10.
|
| 1340 |
-
"eval_samples_per_second":
|
| 1341 |
-
"eval_steps_per_second": 2.
|
| 1342 |
"step": 1550
|
| 1343 |
},
|
| 1344 |
{
|
| 1345 |
"epoch": 1.6956521739130435,
|
| 1346 |
-
"grad_norm":
|
| 1347 |
"learning_rate": 2.173913043478261e-05,
|
| 1348 |
-
"loss": 0.
|
| 1349 |
"step": 1560
|
| 1350 |
},
|
| 1351 |
{
|
| 1352 |
"epoch": 1.7065217391304348,
|
| 1353 |
-
"grad_norm": 1.
|
| 1354 |
"learning_rate": 2.1557971014492757e-05,
|
| 1355 |
-
"loss": 0.
|
| 1356 |
"step": 1570
|
| 1357 |
},
|
| 1358 |
{
|
| 1359 |
"epoch": 1.7173913043478262,
|
| 1360 |
-
"grad_norm":
|
| 1361 |
"learning_rate": 2.13768115942029e-05,
|
| 1362 |
-
"loss": 0.
|
| 1363 |
"step": 1580
|
| 1364 |
},
|
| 1365 |
{
|
| 1366 |
"epoch": 1.7282608695652173,
|
| 1367 |
-
"grad_norm": 1.
|
| 1368 |
"learning_rate": 2.1195652173913045e-05,
|
| 1369 |
-
"loss": 0.
|
| 1370 |
"step": 1590
|
| 1371 |
},
|
| 1372 |
{
|
| 1373 |
"epoch": 1.7391304347826086,
|
| 1374 |
-
"grad_norm": 1.
|
| 1375 |
"learning_rate": 2.101449275362319e-05,
|
| 1376 |
-
"loss": 0.
|
| 1377 |
"step": 1600
|
| 1378 |
},
|
| 1379 |
{
|
| 1380 |
"epoch": 1.7391304347826086,
|
| 1381 |
-
"eval_loss": 0.
|
| 1382 |
-
"eval_runtime": 10.
|
| 1383 |
-
"eval_samples_per_second":
|
| 1384 |
-
"eval_steps_per_second": 2.
|
| 1385 |
"step": 1600
|
| 1386 |
},
|
| 1387 |
{
|
| 1388 |
"epoch": 1.75,
|
| 1389 |
-
"grad_norm": 1.
|
| 1390 |
"learning_rate": 2.0833333333333336e-05,
|
| 1391 |
-
"loss": 0.
|
| 1392 |
"step": 1610
|
| 1393 |
},
|
| 1394 |
{
|
| 1395 |
"epoch": 1.7608695652173914,
|
| 1396 |
-
"grad_norm": 1.
|
| 1397 |
"learning_rate": 2.065217391304348e-05,
|
| 1398 |
-
"loss": 0.
|
| 1399 |
"step": 1620
|
| 1400 |
},
|
| 1401 |
{
|
| 1402 |
"epoch": 1.7717391304347827,
|
| 1403 |
-
"grad_norm":
|
| 1404 |
"learning_rate": 2.0471014492753624e-05,
|
| 1405 |
-
"loss": 0.
|
| 1406 |
"step": 1630
|
| 1407 |
},
|
| 1408 |
{
|
| 1409 |
"epoch": 1.7826086956521738,
|
| 1410 |
-
"grad_norm": 1.
|
| 1411 |
"learning_rate": 2.028985507246377e-05,
|
| 1412 |
-
"loss": 0.
|
| 1413 |
"step": 1640
|
| 1414 |
},
|
| 1415 |
{
|
| 1416 |
"epoch": 1.7934782608695652,
|
| 1417 |
-
"grad_norm": 1.
|
| 1418 |
"learning_rate": 2.0108695652173915e-05,
|
| 1419 |
-
"loss": 0.
|
| 1420 |
"step": 1650
|
| 1421 |
},
|
| 1422 |
{
|
| 1423 |
"epoch": 1.7934782608695652,
|
| 1424 |
-
"eval_loss": 0.
|
| 1425 |
-
"eval_runtime": 10.
|
| 1426 |
-
"eval_samples_per_second":
|
| 1427 |
-
"eval_steps_per_second": 2.
|
| 1428 |
"step": 1650
|
| 1429 |
},
|
| 1430 |
{
|
| 1431 |
"epoch": 1.8043478260869565,
|
| 1432 |
-
"grad_norm": 1.
|
| 1433 |
"learning_rate": 1.992753623188406e-05,
|
| 1434 |
-
"loss": 0.
|
| 1435 |
"step": 1660
|
| 1436 |
},
|
| 1437 |
{
|
| 1438 |
"epoch": 1.8152173913043477,
|
| 1439 |
-
"grad_norm": 1.
|
| 1440 |
"learning_rate": 1.9746376811594202e-05,
|
| 1441 |
-
"loss": 0.
|
| 1442 |
"step": 1670
|
| 1443 |
},
|
| 1444 |
{
|
| 1445 |
"epoch": 1.8260869565217392,
|
| 1446 |
-
"grad_norm": 1.
|
| 1447 |
"learning_rate": 1.956521739130435e-05,
|
| 1448 |
-
"loss": 0.
|
| 1449 |
"step": 1680
|
| 1450 |
},
|
| 1451 |
{
|
| 1452 |
"epoch": 1.8369565217391304,
|
| 1453 |
-
"grad_norm": 1.
|
| 1454 |
"learning_rate": 1.9384057971014493e-05,
|
| 1455 |
-
"loss": 0.
|
| 1456 |
"step": 1690
|
| 1457 |
},
|
| 1458 |
{
|
| 1459 |
"epoch": 1.8478260869565217,
|
| 1460 |
-
"grad_norm": 1.
|
| 1461 |
"learning_rate": 1.9202898550724637e-05,
|
| 1462 |
-
"loss": 0.
|
| 1463 |
"step": 1700
|
| 1464 |
},
|
| 1465 |
{
|
| 1466 |
"epoch": 1.8478260869565217,
|
| 1467 |
-
"eval_loss": 0.
|
| 1468 |
-
"eval_runtime": 10.
|
| 1469 |
-
"eval_samples_per_second":
|
| 1470 |
-
"eval_steps_per_second": 2.
|
| 1471 |
"step": 1700
|
| 1472 |
},
|
| 1473 |
{
|
| 1474 |
"epoch": 1.858695652173913,
|
| 1475 |
-
"grad_norm": 1.
|
| 1476 |
"learning_rate": 1.9021739130434784e-05,
|
| 1477 |
-
"loss": 0.
|
| 1478 |
"step": 1710
|
| 1479 |
},
|
| 1480 |
{
|
| 1481 |
"epoch": 1.8695652173913042,
|
| 1482 |
-
"grad_norm": 1.
|
| 1483 |
"learning_rate": 1.8840579710144928e-05,
|
| 1484 |
-
"loss": 0.
|
| 1485 |
"step": 1720
|
| 1486 |
},
|
| 1487 |
{
|
| 1488 |
"epoch": 1.8804347826086958,
|
| 1489 |
-
"grad_norm": 1.
|
| 1490 |
"learning_rate": 1.8659420289855072e-05,
|
| 1491 |
-
"loss": 0.
|
| 1492 |
"step": 1730
|
| 1493 |
},
|
| 1494 |
{
|
| 1495 |
"epoch": 1.891304347826087,
|
| 1496 |
-
"grad_norm": 1.
|
| 1497 |
"learning_rate": 1.8478260869565216e-05,
|
| 1498 |
-
"loss": 0.
|
| 1499 |
"step": 1740
|
| 1500 |
},
|
| 1501 |
{
|
| 1502 |
"epoch": 1.9021739130434783,
|
| 1503 |
-
"grad_norm": 1.
|
| 1504 |
"learning_rate": 1.8297101449275363e-05,
|
| 1505 |
-
"loss": 0.
|
| 1506 |
"step": 1750
|
| 1507 |
},
|
| 1508 |
{
|
| 1509 |
"epoch": 1.9021739130434783,
|
| 1510 |
-
"eval_loss": 0.
|
| 1511 |
-
"eval_runtime": 10.
|
| 1512 |
-
"eval_samples_per_second":
|
| 1513 |
-
"eval_steps_per_second": 2.
|
| 1514 |
"step": 1750
|
| 1515 |
},
|
| 1516 |
{
|
| 1517 |
"epoch": 1.9130434782608696,
|
| 1518 |
-
"grad_norm":
|
| 1519 |
"learning_rate": 1.8115942028985507e-05,
|
| 1520 |
-
"loss": 0.
|
| 1521 |
"step": 1760
|
| 1522 |
},
|
| 1523 |
{
|
| 1524 |
"epoch": 1.9239130434782608,
|
| 1525 |
-
"grad_norm": 1.
|
| 1526 |
"learning_rate": 1.793478260869565e-05,
|
| 1527 |
-
"loss": 0.
|
| 1528 |
"step": 1770
|
| 1529 |
},
|
| 1530 |
{
|
| 1531 |
"epoch": 1.9347826086956523,
|
| 1532 |
-
"grad_norm": 1.
|
| 1533 |
"learning_rate": 1.7753623188405798e-05,
|
| 1534 |
-
"loss": 0.
|
| 1535 |
"step": 1780
|
| 1536 |
},
|
| 1537 |
{
|
| 1538 |
"epoch": 1.9456521739130435,
|
| 1539 |
-
"grad_norm":
|
| 1540 |
"learning_rate": 1.757246376811594e-05,
|
| 1541 |
-
"loss": 0.
|
| 1542 |
"step": 1790
|
| 1543 |
},
|
| 1544 |
{
|
| 1545 |
"epoch": 1.9565217391304348,
|
| 1546 |
-
"grad_norm": 1.
|
| 1547 |
"learning_rate": 1.739130434782609e-05,
|
| 1548 |
-
"loss": 0.
|
| 1549 |
"step": 1800
|
| 1550 |
},
|
| 1551 |
{
|
| 1552 |
"epoch": 1.9565217391304348,
|
| 1553 |
-
"eval_loss": 0.
|
| 1554 |
-
"eval_runtime": 10.
|
| 1555 |
-
"eval_samples_per_second":
|
| 1556 |
-
"eval_steps_per_second": 2.
|
| 1557 |
"step": 1800
|
| 1558 |
},
|
| 1559 |
{
|
| 1560 |
"epoch": 1.9673913043478262,
|
| 1561 |
-
"grad_norm": 1.
|
| 1562 |
"learning_rate": 1.7210144927536233e-05,
|
| 1563 |
-
"loss": 0.
|
| 1564 |
"step": 1810
|
| 1565 |
},
|
| 1566 |
{
|
| 1567 |
"epoch": 1.9782608695652173,
|
| 1568 |
-
"grad_norm": 1.
|
| 1569 |
"learning_rate": 1.702898550724638e-05,
|
| 1570 |
-
"loss": 0.
|
| 1571 |
"step": 1820
|
| 1572 |
},
|
| 1573 |
{
|
| 1574 |
"epoch": 1.9891304347826086,
|
| 1575 |
-
"grad_norm": 1.
|
| 1576 |
"learning_rate": 1.6847826086956524e-05,
|
| 1577 |
-
"loss": 0.
|
| 1578 |
"step": 1830
|
| 1579 |
},
|
| 1580 |
{
|
| 1581 |
"epoch": 2.0,
|
| 1582 |
-
"grad_norm":
|
| 1583 |
"learning_rate": 1.6666666666666667e-05,
|
| 1584 |
-
"loss": 0.
|
| 1585 |
"step": 1840
|
| 1586 |
},
|
| 1587 |
{
|
| 1588 |
"epoch": 2.010869565217391,
|
| 1589 |
-
"grad_norm": 1.
|
| 1590 |
"learning_rate": 1.6485507246376815e-05,
|
| 1591 |
-
"loss": 0.
|
| 1592 |
"step": 1850
|
| 1593 |
},
|
| 1594 |
{
|
| 1595 |
"epoch": 2.010869565217391,
|
| 1596 |
-
"eval_loss": 0.
|
| 1597 |
-
"eval_runtime": 10.
|
| 1598 |
-
"eval_samples_per_second":
|
| 1599 |
-
"eval_steps_per_second": 2.
|
| 1600 |
"step": 1850
|
| 1601 |
},
|
| 1602 |
{
|
| 1603 |
"epoch": 2.0217391304347827,
|
| 1604 |
-
"grad_norm": 1.
|
| 1605 |
"learning_rate": 1.630434782608696e-05,
|
| 1606 |
-
"loss": 0.
|
| 1607 |
"step": 1860
|
| 1608 |
},
|
| 1609 |
{
|
| 1610 |
"epoch": 2.032608695652174,
|
| 1611 |
-
"grad_norm": 1.
|
| 1612 |
"learning_rate": 1.6123188405797102e-05,
|
| 1613 |
-
"loss": 0.
|
| 1614 |
"step": 1870
|
| 1615 |
},
|
| 1616 |
{
|
| 1617 |
"epoch": 2.0434782608695654,
|
| 1618 |
-
"grad_norm": 1.
|
| 1619 |
"learning_rate": 1.5942028985507246e-05,
|
| 1620 |
-
"loss": 0.
|
| 1621 |
"step": 1880
|
| 1622 |
},
|
| 1623 |
{
|
| 1624 |
"epoch": 2.0543478260869565,
|
| 1625 |
-
"grad_norm": 1.
|
| 1626 |
"learning_rate": 1.5760869565217393e-05,
|
| 1627 |
-
"loss": 0.
|
| 1628 |
"step": 1890
|
| 1629 |
},
|
| 1630 |
{
|
| 1631 |
"epoch": 2.0652173913043477,
|
| 1632 |
-
"grad_norm": 1.
|
| 1633 |
"learning_rate": 1.5579710144927537e-05,
|
| 1634 |
-
"loss": 0.
|
| 1635 |
"step": 1900
|
| 1636 |
},
|
| 1637 |
{
|
| 1638 |
"epoch": 2.0652173913043477,
|
| 1639 |
-
"eval_loss": 0.
|
| 1640 |
-
"eval_runtime": 10.
|
| 1641 |
-
"eval_samples_per_second":
|
| 1642 |
-
"eval_steps_per_second": 2.
|
| 1643 |
"step": 1900
|
| 1644 |
},
|
| 1645 |
{
|
| 1646 |
"epoch": 2.0760869565217392,
|
| 1647 |
-
"grad_norm": 1.
|
| 1648 |
"learning_rate": 1.539855072463768e-05,
|
| 1649 |
-
"loss": 0.
|
| 1650 |
"step": 1910
|
| 1651 |
},
|
| 1652 |
{
|
| 1653 |
"epoch": 2.0869565217391304,
|
| 1654 |
-
"grad_norm": 1.
|
| 1655 |
"learning_rate": 1.5217391304347828e-05,
|
| 1656 |
-
"loss": 0.
|
| 1657 |
"step": 1920
|
| 1658 |
},
|
| 1659 |
{
|
| 1660 |
"epoch": 2.097826086956522,
|
| 1661 |
-
"grad_norm": 1.
|
| 1662 |
"learning_rate": 1.5036231884057972e-05,
|
| 1663 |
-
"loss": 0.
|
| 1664 |
"step": 1930
|
| 1665 |
},
|
| 1666 |
{
|
| 1667 |
"epoch": 2.108695652173913,
|
| 1668 |
-
"grad_norm": 1.
|
| 1669 |
"learning_rate": 1.4855072463768116e-05,
|
| 1670 |
-
"loss": 0.
|
| 1671 |
"step": 1940
|
| 1672 |
},
|
| 1673 |
{
|
| 1674 |
"epoch": 2.119565217391304,
|
| 1675 |
-
"grad_norm": 1.
|
| 1676 |
"learning_rate": 1.4673913043478263e-05,
|
| 1677 |
-
"loss": 0.
|
| 1678 |
"step": 1950
|
| 1679 |
},
|
| 1680 |
{
|
| 1681 |
"epoch": 2.119565217391304,
|
| 1682 |
-
"eval_loss": 0.
|
| 1683 |
-
"eval_runtime": 10.
|
| 1684 |
-
"eval_samples_per_second":
|
| 1685 |
-
"eval_steps_per_second": 2.
|
| 1686 |
"step": 1950
|
| 1687 |
},
|
| 1688 |
{
|
| 1689 |
"epoch": 2.130434782608696,
|
| 1690 |
-
"grad_norm": 1.
|
| 1691 |
"learning_rate": 1.4492753623188407e-05,
|
| 1692 |
-
"loss": 0.
|
| 1693 |
"step": 1960
|
| 1694 |
},
|
| 1695 |
{
|
| 1696 |
"epoch": 2.141304347826087,
|
| 1697 |
-
"grad_norm": 1.
|
| 1698 |
"learning_rate": 1.431159420289855e-05,
|
| 1699 |
-
"loss": 0.
|
| 1700 |
"step": 1970
|
| 1701 |
},
|
| 1702 |
{
|
| 1703 |
"epoch": 2.1521739130434785,
|
| 1704 |
-
"grad_norm": 1.
|
| 1705 |
"learning_rate": 1.4130434782608694e-05,
|
| 1706 |
-
"loss": 0.
|
| 1707 |
"step": 1980
|
| 1708 |
},
|
| 1709 |
{
|
| 1710 |
"epoch": 2.1630434782608696,
|
| 1711 |
-
"grad_norm": 1.
|
| 1712 |
"learning_rate": 1.3949275362318842e-05,
|
| 1713 |
-
"loss": 0.
|
| 1714 |
"step": 1990
|
| 1715 |
},
|
| 1716 |
{
|
| 1717 |
"epoch": 2.1739130434782608,
|
| 1718 |
-
"grad_norm": 1.
|
| 1719 |
"learning_rate": 1.3768115942028985e-05,
|
| 1720 |
-
"loss": 0.
|
| 1721 |
"step": 2000
|
| 1722 |
},
|
| 1723 |
{
|
| 1724 |
"epoch": 2.1739130434782608,
|
| 1725 |
-
"eval_loss": 0.
|
| 1726 |
-
"eval_runtime": 10.
|
| 1727 |
-
"eval_samples_per_second":
|
| 1728 |
-
"eval_steps_per_second": 2.
|
| 1729 |
"step": 2000
|
| 1730 |
},
|
| 1731 |
{
|
| 1732 |
"epoch": 2.1847826086956523,
|
| 1733 |
-
"grad_norm": 1.
|
| 1734 |
"learning_rate": 1.3586956521739131e-05,
|
| 1735 |
-
"loss": 0.
|
| 1736 |
"step": 2010
|
| 1737 |
},
|
| 1738 |
{
|
| 1739 |
"epoch": 2.1956521739130435,
|
| 1740 |
-
"grad_norm": 1.
|
| 1741 |
"learning_rate": 1.3405797101449276e-05,
|
| 1742 |
-
"loss": 0.
|
| 1743 |
"step": 2020
|
| 1744 |
},
|
| 1745 |
{
|
| 1746 |
"epoch": 2.2065217391304346,
|
| 1747 |
-
"grad_norm": 1.
|
| 1748 |
"learning_rate": 1.3224637681159422e-05,
|
| 1749 |
-
"loss": 0.
|
| 1750 |
"step": 2030
|
| 1751 |
},
|
| 1752 |
{
|
| 1753 |
"epoch": 2.217391304347826,
|
| 1754 |
-
"grad_norm": 1.
|
| 1755 |
"learning_rate": 1.3043478260869566e-05,
|
| 1756 |
-
"loss": 0.
|
| 1757 |
"step": 2040
|
| 1758 |
},
|
| 1759 |
{
|
| 1760 |
"epoch": 2.2282608695652173,
|
| 1761 |
-
"grad_norm": 1.
|
| 1762 |
"learning_rate": 1.286231884057971e-05,
|
| 1763 |
-
"loss": 0.
|
| 1764 |
"step": 2050
|
| 1765 |
},
|
| 1766 |
{
|
| 1767 |
"epoch": 2.2282608695652173,
|
| 1768 |
-
"eval_loss": 0.
|
| 1769 |
-
"eval_runtime": 10.
|
| 1770 |
-
"eval_samples_per_second":
|
| 1771 |
-
"eval_steps_per_second": 2.
|
| 1772 |
"step": 2050
|
| 1773 |
},
|
| 1774 |
{
|
| 1775 |
"epoch": 2.239130434782609,
|
| 1776 |
-
"grad_norm": 1.
|
| 1777 |
"learning_rate": 1.2681159420289857e-05,
|
| 1778 |
-
"loss": 0.
|
| 1779 |
"step": 2060
|
| 1780 |
},
|
| 1781 |
{
|
| 1782 |
"epoch": 2.25,
|
| 1783 |
-
"grad_norm": 1.
|
| 1784 |
"learning_rate": 1.25e-05,
|
| 1785 |
-
"loss": 0.
|
| 1786 |
"step": 2070
|
| 1787 |
},
|
| 1788 |
{
|
| 1789 |
"epoch": 2.260869565217391,
|
| 1790 |
-
"grad_norm": 1.
|
| 1791 |
"learning_rate": 1.2318840579710146e-05,
|
| 1792 |
-
"loss": 0.
|
| 1793 |
"step": 2080
|
| 1794 |
},
|
| 1795 |
{
|
| 1796 |
"epoch": 2.2717391304347827,
|
| 1797 |
-
"grad_norm": 1.
|
| 1798 |
"learning_rate": 1.213768115942029e-05,
|
| 1799 |
-
"loss": 0.
|
| 1800 |
"step": 2090
|
| 1801 |
},
|
| 1802 |
{
|
| 1803 |
"epoch": 2.282608695652174,
|
| 1804 |
-
"grad_norm": 1.
|
| 1805 |
"learning_rate": 1.1956521739130435e-05,
|
| 1806 |
-
"loss": 0.
|
| 1807 |
"step": 2100
|
| 1808 |
},
|
| 1809 |
{
|
| 1810 |
"epoch": 2.282608695652174,
|
| 1811 |
-
"eval_loss": 0.
|
| 1812 |
-
"eval_runtime": 10.
|
| 1813 |
-
"eval_samples_per_second":
|
| 1814 |
-
"eval_steps_per_second": 2.
|
| 1815 |
"step": 2100
|
| 1816 |
},
|
| 1817 |
{
|
| 1818 |
"epoch": 2.2934782608695654,
|
| 1819 |
-
"grad_norm": 1.
|
| 1820 |
"learning_rate": 1.177536231884058e-05,
|
| 1821 |
-
"loss": 0.
|
| 1822 |
"step": 2110
|
| 1823 |
},
|
| 1824 |
{
|
| 1825 |
"epoch": 2.3043478260869565,
|
| 1826 |
-
"grad_norm": 1.
|
| 1827 |
"learning_rate": 1.1594202898550725e-05,
|
| 1828 |
-
"loss": 0.
|
| 1829 |
"step": 2120
|
| 1830 |
},
|
| 1831 |
{
|
| 1832 |
"epoch": 2.3152173913043477,
|
| 1833 |
-
"grad_norm": 1.
|
| 1834 |
"learning_rate": 1.141304347826087e-05,
|
| 1835 |
-
"loss": 0.
|
| 1836 |
"step": 2130
|
| 1837 |
},
|
| 1838 |
{
|
| 1839 |
"epoch": 2.3260869565217392,
|
| 1840 |
-
"grad_norm": 1.
|
| 1841 |
"learning_rate": 1.1231884057971016e-05,
|
| 1842 |
-
"loss": 0.
|
| 1843 |
"step": 2140
|
| 1844 |
},
|
| 1845 |
{
|
| 1846 |
"epoch": 2.3369565217391304,
|
| 1847 |
-
"grad_norm": 1.
|
| 1848 |
"learning_rate": 1.1050724637681161e-05,
|
| 1849 |
-
"loss": 0.
|
| 1850 |
"step": 2150
|
| 1851 |
},
|
| 1852 |
{
|
| 1853 |
"epoch": 2.3369565217391304,
|
| 1854 |
-
"eval_loss": 0.
|
| 1855 |
-
"eval_runtime": 10.
|
| 1856 |
-
"eval_samples_per_second":
|
| 1857 |
-
"eval_steps_per_second": 2.
|
| 1858 |
"step": 2150
|
| 1859 |
},
|
| 1860 |
{
|
| 1861 |
"epoch": 2.3478260869565215,
|
| 1862 |
-
"grad_norm": 1.
|
| 1863 |
"learning_rate": 1.0869565217391305e-05,
|
| 1864 |
-
"loss": 0.
|
| 1865 |
"step": 2160
|
| 1866 |
},
|
| 1867 |
{
|
| 1868 |
"epoch": 2.358695652173913,
|
| 1869 |
-
"grad_norm": 1.
|
| 1870 |
"learning_rate": 1.068840579710145e-05,
|
| 1871 |
-
"loss": 0.
|
| 1872 |
"step": 2170
|
| 1873 |
},
|
| 1874 |
{
|
| 1875 |
"epoch": 2.369565217391304,
|
| 1876 |
-
"grad_norm": 1.
|
| 1877 |
"learning_rate": 1.0507246376811594e-05,
|
| 1878 |
-
"loss": 0.
|
| 1879 |
"step": 2180
|
| 1880 |
},
|
| 1881 |
{
|
| 1882 |
"epoch": 2.380434782608696,
|
| 1883 |
-
"grad_norm": 1.
|
| 1884 |
"learning_rate": 1.032608695652174e-05,
|
| 1885 |
-
"loss": 0.
|
| 1886 |
"step": 2190
|
| 1887 |
},
|
| 1888 |
{
|
| 1889 |
"epoch": 2.391304347826087,
|
| 1890 |
-
"grad_norm": 1.
|
| 1891 |
"learning_rate": 1.0144927536231885e-05,
|
| 1892 |
-
"loss": 0.
|
| 1893 |
"step": 2200
|
| 1894 |
},
|
| 1895 |
{
|
| 1896 |
"epoch": 2.391304347826087,
|
| 1897 |
-
"eval_loss": 0.
|
| 1898 |
-
"eval_runtime": 10.
|
| 1899 |
-
"eval_samples_per_second":
|
| 1900 |
-
"eval_steps_per_second": 2.
|
| 1901 |
"step": 2200
|
| 1902 |
},
|
| 1903 |
{
|
| 1904 |
"epoch": 2.4021739130434785,
|
| 1905 |
-
"grad_norm": 1.
|
| 1906 |
"learning_rate": 9.96376811594203e-06,
|
| 1907 |
-
"loss": 0.
|
| 1908 |
"step": 2210
|
| 1909 |
},
|
| 1910 |
{
|
| 1911 |
"epoch": 2.4130434782608696,
|
| 1912 |
-
"grad_norm": 1.
|
| 1913 |
"learning_rate": 9.782608695652175e-06,
|
| 1914 |
-
"loss": 0.
|
| 1915 |
"step": 2220
|
| 1916 |
},
|
| 1917 |
{
|
| 1918 |
"epoch": 2.4239130434782608,
|
| 1919 |
-
"grad_norm": 1.
|
| 1920 |
"learning_rate": 9.601449275362319e-06,
|
| 1921 |
-
"loss": 0.
|
| 1922 |
"step": 2230
|
| 1923 |
},
|
| 1924 |
{
|
| 1925 |
"epoch": 2.4347826086956523,
|
| 1926 |
-
"grad_norm": 1.
|
| 1927 |
"learning_rate": 9.420289855072464e-06,
|
| 1928 |
-
"loss": 0.
|
| 1929 |
"step": 2240
|
| 1930 |
},
|
| 1931 |
{
|
| 1932 |
"epoch": 2.4456521739130435,
|
| 1933 |
-
"grad_norm": 1.
|
| 1934 |
"learning_rate": 9.239130434782608e-06,
|
| 1935 |
-
"loss": 0.
|
| 1936 |
"step": 2250
|
| 1937 |
},
|
| 1938 |
{
|
| 1939 |
"epoch": 2.4456521739130435,
|
| 1940 |
-
"eval_loss": 0.
|
| 1941 |
-
"eval_runtime": 10.
|
| 1942 |
-
"eval_samples_per_second":
|
| 1943 |
-
"eval_steps_per_second": 2.
|
| 1944 |
"step": 2250
|
| 1945 |
},
|
| 1946 |
{
|
| 1947 |
"epoch": 2.4565217391304346,
|
| 1948 |
-
"grad_norm": 1.
|
| 1949 |
"learning_rate": 9.057971014492753e-06,
|
| 1950 |
-
"loss": 0.
|
| 1951 |
"step": 2260
|
| 1952 |
},
|
| 1953 |
{
|
| 1954 |
"epoch": 2.467391304347826,
|
| 1955 |
-
"grad_norm": 1.
|
| 1956 |
"learning_rate": 8.876811594202899e-06,
|
| 1957 |
-
"loss": 0.
|
| 1958 |
"step": 2270
|
| 1959 |
},
|
| 1960 |
{
|
| 1961 |
"epoch": 2.4782608695652173,
|
| 1962 |
-
"grad_norm": 1.
|
| 1963 |
"learning_rate": 8.695652173913044e-06,
|
| 1964 |
-
"loss": 0.
|
| 1965 |
"step": 2280
|
| 1966 |
},
|
| 1967 |
{
|
| 1968 |
"epoch": 2.489130434782609,
|
| 1969 |
-
"grad_norm": 1.
|
| 1970 |
"learning_rate": 8.51449275362319e-06,
|
| 1971 |
-
"loss": 0.
|
| 1972 |
"step": 2290
|
| 1973 |
},
|
| 1974 |
{
|
| 1975 |
"epoch": 2.5,
|
| 1976 |
-
"grad_norm": 1.
|
| 1977 |
"learning_rate": 8.333333333333334e-06,
|
| 1978 |
-
"loss": 0.
|
| 1979 |
"step": 2300
|
| 1980 |
},
|
| 1981 |
{
|
| 1982 |
"epoch": 2.5,
|
| 1983 |
-
"eval_loss": 0.
|
| 1984 |
-
"eval_runtime": 10.
|
| 1985 |
-
"eval_samples_per_second":
|
| 1986 |
-
"eval_steps_per_second": 2.
|
| 1987 |
"step": 2300
|
| 1988 |
},
|
| 1989 |
{
|
| 1990 |
"epoch": 2.5108695652173916,
|
| 1991 |
-
"grad_norm": 1.
|
| 1992 |
"learning_rate": 8.15217391304348e-06,
|
| 1993 |
-
"loss": 0.
|
| 1994 |
"step": 2310
|
| 1995 |
},
|
| 1996 |
{
|
| 1997 |
"epoch": 2.5217391304347827,
|
| 1998 |
-
"grad_norm": 1.
|
| 1999 |
"learning_rate": 7.971014492753623e-06,
|
| 2000 |
-
"loss": 0.
|
| 2001 |
"step": 2320
|
| 2002 |
},
|
| 2003 |
{
|
| 2004 |
"epoch": 2.532608695652174,
|
| 2005 |
-
"grad_norm": 1.
|
| 2006 |
"learning_rate": 7.789855072463769e-06,
|
| 2007 |
-
"loss": 0.
|
| 2008 |
"step": 2330
|
| 2009 |
},
|
| 2010 |
{
|
| 2011 |
"epoch": 2.5434782608695654,
|
| 2012 |
-
"grad_norm": 1.
|
| 2013 |
"learning_rate": 7.608695652173914e-06,
|
| 2014 |
-
"loss": 0.
|
| 2015 |
"step": 2340
|
| 2016 |
},
|
| 2017 |
{
|
| 2018 |
"epoch": 2.5543478260869565,
|
| 2019 |
-
"grad_norm": 1.
|
| 2020 |
"learning_rate": 7.427536231884058e-06,
|
| 2021 |
-
"loss": 0.
|
| 2022 |
"step": 2350
|
| 2023 |
},
|
| 2024 |
{
|
| 2025 |
"epoch": 2.5543478260869565,
|
| 2026 |
-
"eval_loss": 0.
|
| 2027 |
-
"eval_runtime": 10.
|
| 2028 |
-
"eval_samples_per_second":
|
| 2029 |
-
"eval_steps_per_second": 2.
|
| 2030 |
"step": 2350
|
| 2031 |
},
|
| 2032 |
{
|
| 2033 |
"epoch": 2.5652173913043477,
|
| 2034 |
-
"grad_norm": 1.
|
| 2035 |
"learning_rate": 7.246376811594203e-06,
|
| 2036 |
-
"loss": 0.
|
| 2037 |
"step": 2360
|
| 2038 |
},
|
| 2039 |
{
|
| 2040 |
"epoch": 2.5760869565217392,
|
| 2041 |
-
"grad_norm": 1.
|
| 2042 |
"learning_rate": 7.065217391304347e-06,
|
| 2043 |
-
"loss": 0.
|
| 2044 |
"step": 2370
|
| 2045 |
},
|
| 2046 |
{
|
| 2047 |
"epoch": 2.5869565217391304,
|
| 2048 |
-
"grad_norm": 1.
|
| 2049 |
"learning_rate": 6.884057971014493e-06,
|
| 2050 |
-
"loss": 0.
|
| 2051 |
"step": 2380
|
| 2052 |
},
|
| 2053 |
{
|
| 2054 |
"epoch": 2.5978260869565215,
|
| 2055 |
-
"grad_norm": 1.
|
| 2056 |
"learning_rate": 6.702898550724638e-06,
|
| 2057 |
-
"loss": 0.
|
| 2058 |
"step": 2390
|
| 2059 |
},
|
| 2060 |
{
|
| 2061 |
"epoch": 2.608695652173913,
|
| 2062 |
-
"grad_norm": 1.
|
| 2063 |
"learning_rate": 6.521739130434783e-06,
|
| 2064 |
-
"loss": 0.
|
| 2065 |
"step": 2400
|
| 2066 |
},
|
| 2067 |
{
|
| 2068 |
"epoch": 2.608695652173913,
|
| 2069 |
-
"eval_loss": 0.
|
| 2070 |
-
"eval_runtime": 10.
|
| 2071 |
-
"eval_samples_per_second":
|
| 2072 |
-
"eval_steps_per_second": 2.
|
| 2073 |
"step": 2400
|
| 2074 |
}
|
| 2075 |
],
|
|
@@ -2090,7 +2090,7 @@
|
|
| 2090 |
"attributes": {}
|
| 2091 |
}
|
| 2092 |
},
|
| 2093 |
-
"total_flos": 2.
|
| 2094 |
"train_batch_size": 16,
|
| 2095 |
"trial_name": null,
|
| 2096 |
"trial_params": null
|
|
|
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.010869565217391304,
|
| 13 |
+
"grad_norm": 2.4570870399475098,
|
| 14 |
"learning_rate": 4.981884057971015e-05,
|
| 15 |
+
"loss": 2.3612,
|
| 16 |
"step": 10
|
| 17 |
},
|
| 18 |
{
|
| 19 |
"epoch": 0.021739130434782608,
|
| 20 |
+
"grad_norm": 1.2042421102523804,
|
| 21 |
"learning_rate": 4.963768115942029e-05,
|
| 22 |
+
"loss": 1.1915,
|
| 23 |
"step": 20
|
| 24 |
},
|
| 25 |
{
|
| 26 |
"epoch": 0.03260869565217391,
|
| 27 |
+
"grad_norm": 1.2019174098968506,
|
| 28 |
"learning_rate": 4.945652173913044e-05,
|
| 29 |
+
"loss": 0.8992,
|
| 30 |
"step": 30
|
| 31 |
},
|
| 32 |
{
|
| 33 |
"epoch": 0.043478260869565216,
|
| 34 |
+
"grad_norm": 1.0546120405197144,
|
| 35 |
"learning_rate": 4.9275362318840584e-05,
|
| 36 |
+
"loss": 0.7276,
|
| 37 |
"step": 40
|
| 38 |
},
|
| 39 |
{
|
| 40 |
"epoch": 0.05434782608695652,
|
| 41 |
+
"grad_norm": 0.754091203212738,
|
| 42 |
"learning_rate": 4.909420289855073e-05,
|
| 43 |
+
"loss": 0.6419,
|
| 44 |
"step": 50
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 0.05434782608695652,
|
| 48 |
+
"eval_loss": 0.7905128598213196,
|
| 49 |
+
"eval_runtime": 10.8418,
|
| 50 |
+
"eval_samples_per_second": 44.273,
|
| 51 |
+
"eval_steps_per_second": 2.767,
|
| 52 |
"step": 50
|
| 53 |
},
|
| 54 |
{
|
| 55 |
"epoch": 0.06521739130434782,
|
| 56 |
+
"grad_norm": 0.7751966714859009,
|
| 57 |
"learning_rate": 4.891304347826087e-05,
|
| 58 |
+
"loss": 0.5971,
|
| 59 |
"step": 60
|
| 60 |
},
|
| 61 |
{
|
| 62 |
"epoch": 0.07608695652173914,
|
| 63 |
+
"grad_norm": 0.6874057650566101,
|
| 64 |
"learning_rate": 4.873188405797102e-05,
|
| 65 |
+
"loss": 0.608,
|
| 66 |
"step": 70
|
| 67 |
},
|
| 68 |
{
|
| 69 |
"epoch": 0.08695652173913043,
|
| 70 |
+
"grad_norm": 0.7145748734474182,
|
| 71 |
"learning_rate": 4.855072463768116e-05,
|
| 72 |
+
"loss": 0.6111,
|
| 73 |
"step": 80
|
| 74 |
},
|
| 75 |
{
|
| 76 |
"epoch": 0.09782608695652174,
|
| 77 |
+
"grad_norm": 0.8841484189033508,
|
| 78 |
"learning_rate": 4.836956521739131e-05,
|
| 79 |
+
"loss": 0.5848,
|
| 80 |
"step": 90
|
| 81 |
},
|
| 82 |
{
|
| 83 |
"epoch": 0.10869565217391304,
|
| 84 |
+
"grad_norm": 0.7937784790992737,
|
| 85 |
"learning_rate": 4.818840579710145e-05,
|
| 86 |
+
"loss": 0.5699,
|
| 87 |
"step": 100
|
| 88 |
},
|
| 89 |
{
|
| 90 |
"epoch": 0.10869565217391304,
|
| 91 |
+
"eval_loss": 0.6956210732460022,
|
| 92 |
+
"eval_runtime": 10.863,
|
| 93 |
+
"eval_samples_per_second": 44.187,
|
| 94 |
+
"eval_steps_per_second": 2.762,
|
| 95 |
"step": 100
|
| 96 |
},
|
| 97 |
{
|
| 98 |
"epoch": 0.11956521739130435,
|
| 99 |
+
"grad_norm": 0.7818441987037659,
|
| 100 |
"learning_rate": 4.80072463768116e-05,
|
| 101 |
+
"loss": 0.5946,
|
| 102 |
"step": 110
|
| 103 |
},
|
| 104 |
{
|
| 105 |
"epoch": 0.13043478260869565,
|
| 106 |
+
"grad_norm": 0.8666340112686157,
|
| 107 |
"learning_rate": 4.782608695652174e-05,
|
| 108 |
+
"loss": 0.5469,
|
| 109 |
"step": 120
|
| 110 |
},
|
| 111 |
{
|
| 112 |
"epoch": 0.14130434782608695,
|
| 113 |
+
"grad_norm": 0.7637468576431274,
|
| 114 |
"learning_rate": 4.764492753623189e-05,
|
| 115 |
+
"loss": 0.5307,
|
| 116 |
"step": 130
|
| 117 |
},
|
| 118 |
{
|
| 119 |
"epoch": 0.15217391304347827,
|
| 120 |
+
"grad_norm": 0.8282362222671509,
|
| 121 |
"learning_rate": 4.746376811594203e-05,
|
| 122 |
+
"loss": 0.5312,
|
| 123 |
"step": 140
|
| 124 |
},
|
| 125 |
{
|
| 126 |
"epoch": 0.16304347826086957,
|
| 127 |
+
"grad_norm": 0.9675197601318359,
|
| 128 |
"learning_rate": 4.7282608695652177e-05,
|
| 129 |
+
"loss": 0.5486,
|
| 130 |
"step": 150
|
| 131 |
},
|
| 132 |
{
|
| 133 |
"epoch": 0.16304347826086957,
|
| 134 |
+
"eval_loss": 0.6567058563232422,
|
| 135 |
+
"eval_runtime": 10.8376,
|
| 136 |
+
"eval_samples_per_second": 44.29,
|
| 137 |
+
"eval_steps_per_second": 2.768,
|
| 138 |
"step": 150
|
| 139 |
},
|
| 140 |
{
|
| 141 |
"epoch": 0.17391304347826086,
|
| 142 |
+
"grad_norm": 0.7035924792289734,
|
| 143 |
"learning_rate": 4.710144927536232e-05,
|
| 144 |
+
"loss": 0.5553,
|
| 145 |
"step": 160
|
| 146 |
},
|
| 147 |
{
|
| 148 |
"epoch": 0.18478260869565216,
|
| 149 |
+
"grad_norm": 0.8957257866859436,
|
| 150 |
"learning_rate": 4.6920289855072464e-05,
|
| 151 |
+
"loss": 0.54,
|
| 152 |
"step": 170
|
| 153 |
},
|
| 154 |
{
|
| 155 |
"epoch": 0.1956521739130435,
|
| 156 |
+
"grad_norm": 0.8544663190841675,
|
| 157 |
"learning_rate": 4.673913043478261e-05,
|
| 158 |
+
"loss": 0.55,
|
| 159 |
"step": 180
|
| 160 |
},
|
| 161 |
{
|
| 162 |
"epoch": 0.20652173913043478,
|
| 163 |
+
"grad_norm": 0.7599456310272217,
|
| 164 |
"learning_rate": 4.655797101449276e-05,
|
| 165 |
+
"loss": 0.5102,
|
| 166 |
"step": 190
|
| 167 |
},
|
| 168 |
{
|
| 169 |
"epoch": 0.21739130434782608,
|
| 170 |
+
"grad_norm": 0.9151259064674377,
|
| 171 |
"learning_rate": 4.63768115942029e-05,
|
| 172 |
+
"loss": 0.5372,
|
| 173 |
"step": 200
|
| 174 |
},
|
| 175 |
{
|
| 176 |
"epoch": 0.21739130434782608,
|
| 177 |
+
"eval_loss": 0.6319016218185425,
|
| 178 |
+
"eval_runtime": 10.8237,
|
| 179 |
+
"eval_samples_per_second": 44.347,
|
| 180 |
+
"eval_steps_per_second": 2.772,
|
| 181 |
"step": 200
|
| 182 |
},
|
| 183 |
{
|
| 184 |
"epoch": 0.22826086956521738,
|
| 185 |
+
"grad_norm": 0.911018431186676,
|
| 186 |
"learning_rate": 4.6195652173913046e-05,
|
| 187 |
+
"loss": 0.5354,
|
| 188 |
"step": 210
|
| 189 |
},
|
| 190 |
{
|
| 191 |
"epoch": 0.2391304347826087,
|
| 192 |
+
"grad_norm": 0.7792191505432129,
|
| 193 |
"learning_rate": 4.601449275362319e-05,
|
| 194 |
+
"loss": 0.5297,
|
| 195 |
"step": 220
|
| 196 |
},
|
| 197 |
{
|
| 198 |
"epoch": 0.25,
|
| 199 |
+
"grad_norm": 0.7631202340126038,
|
| 200 |
"learning_rate": 4.5833333333333334e-05,
|
| 201 |
+
"loss": 0.5258,
|
| 202 |
"step": 230
|
| 203 |
},
|
| 204 |
{
|
| 205 |
"epoch": 0.2608695652173913,
|
| 206 |
+
"grad_norm": 0.7436497211456299,
|
| 207 |
"learning_rate": 4.565217391304348e-05,
|
| 208 |
+
"loss": 0.4849,
|
| 209 |
"step": 240
|
| 210 |
},
|
| 211 |
{
|
| 212 |
"epoch": 0.2717391304347826,
|
| 213 |
+
"grad_norm": 0.8372677564620972,
|
| 214 |
"learning_rate": 4.547101449275363e-05,
|
| 215 |
+
"loss": 0.5131,
|
| 216 |
"step": 250
|
| 217 |
},
|
| 218 |
{
|
| 219 |
"epoch": 0.2717391304347826,
|
| 220 |
+
"eval_loss": 0.6155125498771667,
|
| 221 |
+
"eval_runtime": 10.8327,
|
| 222 |
+
"eval_samples_per_second": 44.31,
|
| 223 |
+
"eval_steps_per_second": 2.769,
|
| 224 |
"step": 250
|
| 225 |
},
|
| 226 |
{
|
| 227 |
"epoch": 0.2826086956521739,
|
| 228 |
+
"grad_norm": 0.8056390285491943,
|
| 229 |
"learning_rate": 4.528985507246377e-05,
|
| 230 |
+
"loss": 0.4675,
|
| 231 |
"step": 260
|
| 232 |
},
|
| 233 |
{
|
| 234 |
"epoch": 0.29347826086956524,
|
| 235 |
+
"grad_norm": 0.8015912175178528,
|
| 236 |
"learning_rate": 4.5108695652173916e-05,
|
| 237 |
+
"loss": 0.4942,
|
| 238 |
"step": 270
|
| 239 |
},
|
| 240 |
{
|
| 241 |
"epoch": 0.30434782608695654,
|
| 242 |
+
"grad_norm": 0.8316887021064758,
|
| 243 |
"learning_rate": 4.492753623188406e-05,
|
| 244 |
+
"loss": 0.5025,
|
| 245 |
"step": 280
|
| 246 |
},
|
| 247 |
{
|
| 248 |
"epoch": 0.31521739130434784,
|
| 249 |
+
"grad_norm": 0.8440260887145996,
|
| 250 |
"learning_rate": 4.4746376811594203e-05,
|
| 251 |
+
"loss": 0.5112,
|
| 252 |
"step": 290
|
| 253 |
},
|
| 254 |
{
|
| 255 |
"epoch": 0.32608695652173914,
|
| 256 |
+
"grad_norm": 0.8523954153060913,
|
| 257 |
"learning_rate": 4.456521739130435e-05,
|
| 258 |
+
"loss": 0.4973,
|
| 259 |
"step": 300
|
| 260 |
},
|
| 261 |
{
|
| 262 |
"epoch": 0.32608695652173914,
|
| 263 |
+
"eval_loss": 0.6024141907691956,
|
| 264 |
+
"eval_runtime": 10.839,
|
| 265 |
+
"eval_samples_per_second": 44.284,
|
| 266 |
+
"eval_steps_per_second": 2.768,
|
| 267 |
"step": 300
|
| 268 |
},
|
| 269 |
{
|
| 270 |
"epoch": 0.33695652173913043,
|
| 271 |
+
"grad_norm": 0.8427216410636902,
|
| 272 |
"learning_rate": 4.438405797101449e-05,
|
| 273 |
+
"loss": 0.5271,
|
| 274 |
"step": 310
|
| 275 |
},
|
| 276 |
{
|
| 277 |
"epoch": 0.34782608695652173,
|
| 278 |
+
"grad_norm": 0.8126628398895264,
|
| 279 |
"learning_rate": 4.4202898550724645e-05,
|
| 280 |
+
"loss": 0.4608,
|
| 281 |
"step": 320
|
| 282 |
},
|
| 283 |
{
|
| 284 |
"epoch": 0.358695652173913,
|
| 285 |
+
"grad_norm": 0.9947460293769836,
|
| 286 |
"learning_rate": 4.4021739130434786e-05,
|
| 287 |
+
"loss": 0.4762,
|
| 288 |
"step": 330
|
| 289 |
},
|
| 290 |
{
|
| 291 |
"epoch": 0.3695652173913043,
|
| 292 |
+
"grad_norm": 0.7744721174240112,
|
| 293 |
"learning_rate": 4.384057971014493e-05,
|
| 294 |
+
"loss": 0.4993,
|
| 295 |
"step": 340
|
| 296 |
},
|
| 297 |
{
|
| 298 |
"epoch": 0.3804347826086957,
|
| 299 |
+
"grad_norm": 0.9483833909034729,
|
| 300 |
"learning_rate": 4.365942028985507e-05,
|
| 301 |
+
"loss": 0.497,
|
| 302 |
"step": 350
|
| 303 |
},
|
| 304 |
{
|
| 305 |
"epoch": 0.3804347826086957,
|
| 306 |
+
"eval_loss": 0.596432626247406,
|
| 307 |
+
"eval_runtime": 10.8191,
|
| 308 |
+
"eval_samples_per_second": 44.366,
|
| 309 |
+
"eval_steps_per_second": 2.773,
|
| 310 |
"step": 350
|
| 311 |
},
|
| 312 |
{
|
| 313 |
"epoch": 0.391304347826087,
|
| 314 |
+
"grad_norm": 0.7573915123939514,
|
| 315 |
"learning_rate": 4.347826086956522e-05,
|
| 316 |
+
"loss": 0.469,
|
| 317 |
"step": 360
|
| 318 |
},
|
| 319 |
{
|
| 320 |
"epoch": 0.40217391304347827,
|
| 321 |
+
"grad_norm": 0.8013887405395508,
|
| 322 |
"learning_rate": 4.329710144927536e-05,
|
| 323 |
+
"loss": 0.4704,
|
| 324 |
"step": 370
|
| 325 |
},
|
| 326 |
{
|
| 327 |
"epoch": 0.41304347826086957,
|
| 328 |
+
"grad_norm": 0.8412826657295227,
|
| 329 |
"learning_rate": 4.3115942028985515e-05,
|
| 330 |
+
"loss": 0.5033,
|
| 331 |
"step": 380
|
| 332 |
},
|
| 333 |
{
|
| 334 |
"epoch": 0.42391304347826086,
|
| 335 |
+
"grad_norm": 0.8203413486480713,
|
| 336 |
"learning_rate": 4.2934782608695655e-05,
|
| 337 |
+
"loss": 0.5063,
|
| 338 |
"step": 390
|
| 339 |
},
|
| 340 |
{
|
| 341 |
"epoch": 0.43478260869565216,
|
| 342 |
+
"grad_norm": 0.7952508926391602,
|
| 343 |
"learning_rate": 4.27536231884058e-05,
|
| 344 |
+
"loss": 0.4706,
|
| 345 |
"step": 400
|
| 346 |
},
|
| 347 |
{
|
| 348 |
"epoch": 0.43478260869565216,
|
| 349 |
+
"eval_loss": 0.5875406861305237,
|
| 350 |
+
"eval_runtime": 10.8328,
|
| 351 |
+
"eval_samples_per_second": 44.31,
|
| 352 |
+
"eval_steps_per_second": 2.769,
|
| 353 |
"step": 400
|
| 354 |
},
|
| 355 |
{
|
| 356 |
"epoch": 0.44565217391304346,
|
| 357 |
+
"grad_norm": 0.9020015597343445,
|
| 358 |
"learning_rate": 4.257246376811594e-05,
|
| 359 |
+
"loss": 0.4786,
|
| 360 |
"step": 410
|
| 361 |
},
|
| 362 |
{
|
| 363 |
"epoch": 0.45652173913043476,
|
| 364 |
+
"grad_norm": 0.8588363528251648,
|
| 365 |
"learning_rate": 4.239130434782609e-05,
|
| 366 |
+
"loss": 0.482,
|
| 367 |
"step": 420
|
| 368 |
},
|
| 369 |
{
|
| 370 |
"epoch": 0.4673913043478261,
|
| 371 |
+
"grad_norm": 0.816198468208313,
|
| 372 |
"learning_rate": 4.221014492753623e-05,
|
| 373 |
+
"loss": 0.4683,
|
| 374 |
"step": 430
|
| 375 |
},
|
| 376 |
{
|
| 377 |
"epoch": 0.4782608695652174,
|
| 378 |
+
"grad_norm": 0.8713563680648804,
|
| 379 |
"learning_rate": 4.202898550724638e-05,
|
| 380 |
+
"loss": 0.4422,
|
| 381 |
"step": 440
|
| 382 |
},
|
| 383 |
{
|
| 384 |
"epoch": 0.4891304347826087,
|
| 385 |
+
"grad_norm": 0.8633397817611694,
|
| 386 |
"learning_rate": 4.1847826086956525e-05,
|
| 387 |
+
"loss": 0.45,
|
| 388 |
"step": 450
|
| 389 |
},
|
| 390 |
{
|
| 391 |
"epoch": 0.4891304347826087,
|
| 392 |
+
"eval_loss": 0.5812788605690002,
|
| 393 |
+
"eval_runtime": 10.8048,
|
| 394 |
+
"eval_samples_per_second": 44.425,
|
| 395 |
+
"eval_steps_per_second": 2.777,
|
| 396 |
"step": 450
|
| 397 |
},
|
| 398 |
{
|
| 399 |
"epoch": 0.5,
|
| 400 |
+
"grad_norm": 0.8244722485542297,
|
| 401 |
"learning_rate": 4.166666666666667e-05,
|
| 402 |
+
"loss": 0.4911,
|
| 403 |
"step": 460
|
| 404 |
},
|
| 405 |
{
|
| 406 |
"epoch": 0.5108695652173914,
|
| 407 |
+
"grad_norm": 0.8201929926872253,
|
| 408 |
"learning_rate": 4.148550724637681e-05,
|
| 409 |
+
"loss": 0.4611,
|
| 410 |
"step": 470
|
| 411 |
},
|
| 412 |
{
|
| 413 |
"epoch": 0.5217391304347826,
|
| 414 |
+
"grad_norm": 0.9646862149238586,
|
| 415 |
"learning_rate": 4.130434782608696e-05,
|
| 416 |
+
"loss": 0.4738,
|
| 417 |
"step": 480
|
| 418 |
},
|
| 419 |
{
|
| 420 |
"epoch": 0.532608695652174,
|
| 421 |
+
"grad_norm": 0.9149807095527649,
|
| 422 |
"learning_rate": 4.11231884057971e-05,
|
| 423 |
+
"loss": 0.4603,
|
| 424 |
"step": 490
|
| 425 |
},
|
| 426 |
{
|
| 427 |
"epoch": 0.5434782608695652,
|
| 428 |
+
"grad_norm": 0.8054277896881104,
|
| 429 |
"learning_rate": 4.094202898550725e-05,
|
| 430 |
+
"loss": 0.466,
|
| 431 |
"step": 500
|
| 432 |
},
|
| 433 |
{
|
| 434 |
"epoch": 0.5434782608695652,
|
| 435 |
+
"eval_loss": 0.573806881904602,
|
| 436 |
+
"eval_runtime": 10.7906,
|
| 437 |
+
"eval_samples_per_second": 44.483,
|
| 438 |
+
"eval_steps_per_second": 2.78,
|
| 439 |
"step": 500
|
| 440 |
},
|
| 441 |
{
|
| 442 |
"epoch": 0.5543478260869565,
|
| 443 |
+
"grad_norm": 0.9110711812973022,
|
| 444 |
"learning_rate": 4.076086956521739e-05,
|
| 445 |
+
"loss": 0.4777,
|
| 446 |
"step": 510
|
| 447 |
},
|
| 448 |
{
|
| 449 |
"epoch": 0.5652173913043478,
|
| 450 |
+
"grad_norm": 0.8030044436454773,
|
| 451 |
"learning_rate": 4.057971014492754e-05,
|
| 452 |
+
"loss": 0.4965,
|
| 453 |
"step": 520
|
| 454 |
},
|
| 455 |
{
|
| 456 |
"epoch": 0.5760869565217391,
|
| 457 |
+
"grad_norm": 0.8847204446792603,
|
| 458 |
"learning_rate": 4.039855072463768e-05,
|
| 459 |
+
"loss": 0.4843,
|
| 460 |
"step": 530
|
| 461 |
},
|
| 462 |
{
|
| 463 |
"epoch": 0.5869565217391305,
|
| 464 |
+
"grad_norm": 0.9041047692298889,
|
| 465 |
"learning_rate": 4.021739130434783e-05,
|
| 466 |
+
"loss": 0.4548,
|
| 467 |
"step": 540
|
| 468 |
},
|
| 469 |
{
|
| 470 |
"epoch": 0.5978260869565217,
|
| 471 |
+
"grad_norm": 0.8136462569236755,
|
| 472 |
"learning_rate": 4.003623188405797e-05,
|
| 473 |
+
"loss": 0.4543,
|
| 474 |
"step": 550
|
| 475 |
},
|
| 476 |
{
|
| 477 |
"epoch": 0.5978260869565217,
|
| 478 |
+
"eval_loss": 0.5662083029747009,
|
| 479 |
+
"eval_runtime": 10.7748,
|
| 480 |
+
"eval_samples_per_second": 44.549,
|
| 481 |
+
"eval_steps_per_second": 2.784,
|
| 482 |
"step": 550
|
| 483 |
},
|
| 484 |
{
|
| 485 |
"epoch": 0.6086956521739131,
|
| 486 |
+
"grad_norm": 0.9470314383506775,
|
| 487 |
"learning_rate": 3.985507246376812e-05,
|
| 488 |
+
"loss": 0.4852,
|
| 489 |
"step": 560
|
| 490 |
},
|
| 491 |
{
|
| 492 |
"epoch": 0.6195652173913043,
|
| 493 |
+
"grad_norm": 0.9280235171318054,
|
| 494 |
"learning_rate": 3.9673913043478264e-05,
|
| 495 |
+
"loss": 0.4655,
|
| 496 |
"step": 570
|
| 497 |
},
|
| 498 |
{
|
| 499 |
"epoch": 0.6304347826086957,
|
| 500 |
+
"grad_norm": 0.9118008017539978,
|
| 501 |
"learning_rate": 3.9492753623188405e-05,
|
| 502 |
+
"loss": 0.449,
|
| 503 |
"step": 580
|
| 504 |
},
|
| 505 |
{
|
| 506 |
"epoch": 0.6413043478260869,
|
| 507 |
+
"grad_norm": 0.9286589026451111,
|
| 508 |
"learning_rate": 3.931159420289855e-05,
|
| 509 |
+
"loss": 0.448,
|
| 510 |
"step": 590
|
| 511 |
},
|
| 512 |
{
|
| 513 |
"epoch": 0.6521739130434783,
|
| 514 |
+
"grad_norm": 0.7761940956115723,
|
| 515 |
"learning_rate": 3.91304347826087e-05,
|
| 516 |
+
"loss": 0.4363,
|
| 517 |
"step": 600
|
| 518 |
},
|
| 519 |
{
|
| 520 |
"epoch": 0.6521739130434783,
|
| 521 |
+
"eval_loss": 0.5645204186439514,
|
| 522 |
+
"eval_runtime": 10.7763,
|
| 523 |
+
"eval_samples_per_second": 44.542,
|
| 524 |
+
"eval_steps_per_second": 2.784,
|
| 525 |
"step": 600
|
| 526 |
},
|
| 527 |
{
|
| 528 |
"epoch": 0.6630434782608695,
|
| 529 |
+
"grad_norm": 0.9244002103805542,
|
| 530 |
"learning_rate": 3.8949275362318846e-05,
|
| 531 |
+
"loss": 0.4354,
|
| 532 |
"step": 610
|
| 533 |
},
|
| 534 |
{
|
| 535 |
"epoch": 0.6739130434782609,
|
| 536 |
+
"grad_norm": 0.8263306021690369,
|
| 537 |
"learning_rate": 3.876811594202899e-05,
|
| 538 |
+
"loss": 0.4951,
|
| 539 |
"step": 620
|
| 540 |
},
|
| 541 |
{
|
| 542 |
"epoch": 0.6847826086956522,
|
| 543 |
+
"grad_norm": 0.8908408284187317,
|
| 544 |
"learning_rate": 3.8586956521739134e-05,
|
| 545 |
+
"loss": 0.4401,
|
| 546 |
"step": 630
|
| 547 |
},
|
| 548 |
{
|
| 549 |
"epoch": 0.6956521739130435,
|
| 550 |
+
"grad_norm": 0.8497889637947083,
|
| 551 |
"learning_rate": 3.8405797101449274e-05,
|
| 552 |
+
"loss": 0.4514,
|
| 553 |
"step": 640
|
| 554 |
},
|
| 555 |
{
|
| 556 |
"epoch": 0.7065217391304348,
|
| 557 |
+
"grad_norm": 0.8306752443313599,
|
| 558 |
"learning_rate": 3.822463768115942e-05,
|
| 559 |
+
"loss": 0.4503,
|
| 560 |
"step": 650
|
| 561 |
},
|
| 562 |
{
|
| 563 |
"epoch": 0.7065217391304348,
|
| 564 |
+
"eval_loss": 0.5576011538505554,
|
| 565 |
+
"eval_runtime": 10.7704,
|
| 566 |
+
"eval_samples_per_second": 44.567,
|
| 567 |
+
"eval_steps_per_second": 2.785,
|
| 568 |
"step": 650
|
| 569 |
},
|
| 570 |
{
|
| 571 |
"epoch": 0.717391304347826,
|
| 572 |
+
"grad_norm": 0.898961067199707,
|
| 573 |
"learning_rate": 3.804347826086957e-05,
|
| 574 |
+
"loss": 0.4185,
|
| 575 |
"step": 660
|
| 576 |
},
|
| 577 |
{
|
| 578 |
"epoch": 0.7282608695652174,
|
| 579 |
+
"grad_norm": 0.8870590925216675,
|
| 580 |
"learning_rate": 3.7862318840579716e-05,
|
| 581 |
+
"loss": 0.4303,
|
| 582 |
"step": 670
|
| 583 |
},
|
| 584 |
{
|
| 585 |
"epoch": 0.7391304347826086,
|
| 586 |
+
"grad_norm": 0.8863015174865723,
|
| 587 |
"learning_rate": 3.7681159420289856e-05,
|
| 588 |
+
"loss": 0.4356,
|
| 589 |
"step": 680
|
| 590 |
},
|
| 591 |
{
|
| 592 |
"epoch": 0.75,
|
| 593 |
+
"grad_norm": 0.852130651473999,
|
| 594 |
"learning_rate": 3.7500000000000003e-05,
|
| 595 |
+
"loss": 0.4756,
|
| 596 |
"step": 690
|
| 597 |
},
|
| 598 |
{
|
| 599 |
"epoch": 0.7608695652173914,
|
| 600 |
+
"grad_norm": 0.8342716097831726,
|
| 601 |
"learning_rate": 3.7318840579710144e-05,
|
| 602 |
+
"loss": 0.4955,
|
| 603 |
"step": 700
|
| 604 |
},
|
| 605 |
{
|
| 606 |
"epoch": 0.7608695652173914,
|
| 607 |
+
"eval_loss": 0.5521832704544067,
|
| 608 |
+
"eval_runtime": 10.7828,
|
| 609 |
+
"eval_samples_per_second": 44.515,
|
| 610 |
+
"eval_steps_per_second": 2.782,
|
| 611 |
"step": 700
|
| 612 |
},
|
| 613 |
{
|
| 614 |
"epoch": 0.7717391304347826,
|
| 615 |
+
"grad_norm": 0.8382502794265747,
|
| 616 |
"learning_rate": 3.713768115942029e-05,
|
| 617 |
+
"loss": 0.4435,
|
| 618 |
"step": 710
|
| 619 |
},
|
| 620 |
{
|
| 621 |
"epoch": 0.782608695652174,
|
| 622 |
+
"grad_norm": 0.9789420962333679,
|
| 623 |
"learning_rate": 3.695652173913043e-05,
|
| 624 |
+
"loss": 0.3957,
|
| 625 |
"step": 720
|
| 626 |
},
|
| 627 |
{
|
| 628 |
"epoch": 0.7934782608695652,
|
| 629 |
+
"grad_norm": 0.8945524096488953,
|
| 630 |
"learning_rate": 3.6775362318840586e-05,
|
| 631 |
+
"loss": 0.4565,
|
| 632 |
"step": 730
|
| 633 |
},
|
| 634 |
{
|
| 635 |
"epoch": 0.8043478260869565,
|
| 636 |
+
"grad_norm": 0.9632206559181213,
|
| 637 |
"learning_rate": 3.6594202898550726e-05,
|
| 638 |
+
"loss": 0.4312,
|
| 639 |
"step": 740
|
| 640 |
},
|
| 641 |
{
|
| 642 |
"epoch": 0.8152173913043478,
|
| 643 |
+
"grad_norm": 0.8000399470329285,
|
| 644 |
"learning_rate": 3.641304347826087e-05,
|
| 645 |
+
"loss": 0.429,
|
| 646 |
"step": 750
|
| 647 |
},
|
| 648 |
{
|
| 649 |
"epoch": 0.8152173913043478,
|
| 650 |
+
"eval_loss": 0.550889790058136,
|
| 651 |
+
"eval_runtime": 10.7987,
|
| 652 |
+
"eval_samples_per_second": 44.45,
|
| 653 |
+
"eval_steps_per_second": 2.778,
|
| 654 |
"step": 750
|
| 655 |
},
|
| 656 |
{
|
| 657 |
"epoch": 0.8260869565217391,
|
| 658 |
+
"grad_norm": 0.8817518353462219,
|
| 659 |
"learning_rate": 3.6231884057971014e-05,
|
| 660 |
+
"loss": 0.4464,
|
| 661 |
"step": 760
|
| 662 |
},
|
| 663 |
{
|
| 664 |
"epoch": 0.8369565217391305,
|
| 665 |
+
"grad_norm": 0.9800861477851868,
|
| 666 |
"learning_rate": 3.605072463768116e-05,
|
| 667 |
+
"loss": 0.4577,
|
| 668 |
"step": 770
|
| 669 |
},
|
| 670 |
{
|
| 671 |
"epoch": 0.8478260869565217,
|
| 672 |
+
"grad_norm": 0.846571683883667,
|
| 673 |
"learning_rate": 3.58695652173913e-05,
|
| 674 |
+
"loss": 0.4169,
|
| 675 |
"step": 780
|
| 676 |
},
|
| 677 |
{
|
| 678 |
"epoch": 0.8586956521739131,
|
| 679 |
+
"grad_norm": 0.8653192520141602,
|
| 680 |
"learning_rate": 3.568840579710145e-05,
|
| 681 |
+
"loss": 0.4195,
|
| 682 |
"step": 790
|
| 683 |
},
|
| 684 |
{
|
| 685 |
"epoch": 0.8695652173913043,
|
| 686 |
+
"grad_norm": 0.8515974283218384,
|
| 687 |
"learning_rate": 3.5507246376811596e-05,
|
| 688 |
+
"loss": 0.4366,
|
| 689 |
"step": 800
|
| 690 |
},
|
| 691 |
{
|
| 692 |
"epoch": 0.8695652173913043,
|
| 693 |
+
"eval_loss": 0.543337881565094,
|
| 694 |
+
"eval_runtime": 10.8166,
|
| 695 |
+
"eval_samples_per_second": 44.376,
|
| 696 |
+
"eval_steps_per_second": 2.774,
|
| 697 |
"step": 800
|
| 698 |
},
|
| 699 |
{
|
| 700 |
"epoch": 0.8804347826086957,
|
| 701 |
+
"grad_norm": 0.947827935218811,
|
| 702 |
"learning_rate": 3.532608695652174e-05,
|
| 703 |
+
"loss": 0.4498,
|
| 704 |
"step": 810
|
| 705 |
},
|
| 706 |
{
|
| 707 |
"epoch": 0.8913043478260869,
|
| 708 |
+
"grad_norm": 0.866033136844635,
|
| 709 |
"learning_rate": 3.514492753623188e-05,
|
| 710 |
+
"loss": 0.4495,
|
| 711 |
"step": 820
|
| 712 |
},
|
| 713 |
{
|
| 714 |
"epoch": 0.9021739130434783,
|
| 715 |
+
"grad_norm": 0.8692104816436768,
|
| 716 |
"learning_rate": 3.496376811594203e-05,
|
| 717 |
+
"loss": 0.4502,
|
| 718 |
"step": 830
|
| 719 |
},
|
| 720 |
{
|
| 721 |
"epoch": 0.9130434782608695,
|
| 722 |
+
"grad_norm": 0.8841784596443176,
|
| 723 |
"learning_rate": 3.478260869565218e-05,
|
| 724 |
+
"loss": 0.4577,
|
| 725 |
"step": 840
|
| 726 |
},
|
| 727 |
{
|
| 728 |
"epoch": 0.9239130434782609,
|
| 729 |
+
"grad_norm": 0.9257445335388184,
|
| 730 |
"learning_rate": 3.460144927536232e-05,
|
| 731 |
+
"loss": 0.4329,
|
| 732 |
"step": 850
|
| 733 |
},
|
| 734 |
{
|
| 735 |
"epoch": 0.9239130434782609,
|
| 736 |
+
"eval_loss": 0.5429030060768127,
|
| 737 |
+
"eval_runtime": 10.8284,
|
| 738 |
+
"eval_samples_per_second": 44.328,
|
| 739 |
+
"eval_steps_per_second": 2.77,
|
| 740 |
"step": 850
|
| 741 |
},
|
| 742 |
{
|
| 743 |
"epoch": 0.9347826086956522,
|
| 744 |
+
"grad_norm": 0.8753738403320312,
|
| 745 |
"learning_rate": 3.4420289855072465e-05,
|
| 746 |
+
"loss": 0.422,
|
| 747 |
"step": 860
|
| 748 |
},
|
| 749 |
{
|
| 750 |
"epoch": 0.9456521739130435,
|
| 751 |
+
"grad_norm": 0.8853139877319336,
|
| 752 |
"learning_rate": 3.423913043478261e-05,
|
| 753 |
+
"loss": 0.4357,
|
| 754 |
"step": 870
|
| 755 |
},
|
| 756 |
{
|
| 757 |
"epoch": 0.9565217391304348,
|
| 758 |
+
"grad_norm": 0.8637978434562683,
|
| 759 |
"learning_rate": 3.405797101449276e-05,
|
| 760 |
+
"loss": 0.4254,
|
| 761 |
"step": 880
|
| 762 |
},
|
| 763 |
{
|
| 764 |
"epoch": 0.967391304347826,
|
| 765 |
+
"grad_norm": 0.9090889096260071,
|
| 766 |
"learning_rate": 3.38768115942029e-05,
|
| 767 |
+
"loss": 0.4526,
|
| 768 |
"step": 890
|
| 769 |
},
|
| 770 |
{
|
| 771 |
"epoch": 0.9782608695652174,
|
| 772 |
+
"grad_norm": 0.8591863512992859,
|
| 773 |
"learning_rate": 3.369565217391305e-05,
|
| 774 |
+
"loss": 0.4566,
|
| 775 |
"step": 900
|
| 776 |
},
|
| 777 |
{
|
| 778 |
"epoch": 0.9782608695652174,
|
| 779 |
+
"eval_loss": 0.5399300456047058,
|
| 780 |
+
"eval_runtime": 10.8533,
|
| 781 |
+
"eval_samples_per_second": 44.226,
|
| 782 |
+
"eval_steps_per_second": 2.764,
|
| 783 |
"step": 900
|
| 784 |
},
|
| 785 |
{
|
| 786 |
"epoch": 0.9891304347826086,
|
| 787 |
+
"grad_norm": 0.8273764848709106,
|
| 788 |
"learning_rate": 3.351449275362319e-05,
|
| 789 |
+
"loss": 0.4182,
|
| 790 |
"step": 910
|
| 791 |
},
|
| 792 |
{
|
| 793 |
"epoch": 1.0,
|
| 794 |
+
"grad_norm": 1.5736610889434814,
|
| 795 |
"learning_rate": 3.3333333333333335e-05,
|
| 796 |
+
"loss": 0.4548,
|
| 797 |
"step": 920
|
| 798 |
},
|
| 799 |
{
|
| 800 |
"epoch": 1.0108695652173914,
|
| 801 |
+
"grad_norm": 0.8933672904968262,
|
| 802 |
"learning_rate": 3.3152173913043475e-05,
|
| 803 |
+
"loss": 0.3834,
|
| 804 |
"step": 930
|
| 805 |
},
|
| 806 |
{
|
| 807 |
"epoch": 1.0217391304347827,
|
| 808 |
+
"grad_norm": 0.9641056060791016,
|
| 809 |
"learning_rate": 3.297101449275363e-05,
|
| 810 |
+
"loss": 0.3962,
|
| 811 |
"step": 940
|
| 812 |
},
|
| 813 |
{
|
| 814 |
"epoch": 1.0326086956521738,
|
| 815 |
+
"grad_norm": 0.8840826153755188,
|
| 816 |
"learning_rate": 3.278985507246377e-05,
|
| 817 |
+
"loss": 0.3886,
|
| 818 |
"step": 950
|
| 819 |
},
|
| 820 |
{
|
| 821 |
"epoch": 1.0326086956521738,
|
| 822 |
+
"eval_loss": 0.5417191982269287,
|
| 823 |
+
"eval_runtime": 10.828,
|
| 824 |
+
"eval_samples_per_second": 44.33,
|
| 825 |
+
"eval_steps_per_second": 2.771,
|
| 826 |
"step": 950
|
| 827 |
},
|
| 828 |
{
|
| 829 |
"epoch": 1.0434782608695652,
|
| 830 |
+
"grad_norm": 0.9005197286605835,
|
| 831 |
"learning_rate": 3.260869565217392e-05,
|
| 832 |
+
"loss": 0.3887,
|
| 833 |
"step": 960
|
| 834 |
},
|
| 835 |
{
|
| 836 |
"epoch": 1.0543478260869565,
|
| 837 |
+
"grad_norm": 1.0132256746292114,
|
| 838 |
"learning_rate": 3.242753623188406e-05,
|
| 839 |
+
"loss": 0.4026,
|
| 840 |
"step": 970
|
| 841 |
},
|
| 842 |
{
|
| 843 |
"epoch": 1.065217391304348,
|
| 844 |
+
"grad_norm": 1.1139558553695679,
|
| 845 |
"learning_rate": 3.2246376811594205e-05,
|
| 846 |
+
"loss": 0.3703,
|
| 847 |
"step": 980
|
| 848 |
},
|
| 849 |
{
|
| 850 |
"epoch": 1.0760869565217392,
|
| 851 |
+
"grad_norm": 0.9440574049949646,
|
| 852 |
"learning_rate": 3.2065217391304345e-05,
|
| 853 |
+
"loss": 0.3766,
|
| 854 |
"step": 990
|
| 855 |
},
|
| 856 |
{
|
| 857 |
"epoch": 1.0869565217391304,
|
| 858 |
+
"grad_norm": 1.0028133392333984,
|
| 859 |
"learning_rate": 3.188405797101449e-05,
|
| 860 |
+
"loss": 0.4038,
|
| 861 |
"step": 1000
|
| 862 |
},
|
| 863 |
{
|
| 864 |
"epoch": 1.0869565217391304,
|
| 865 |
+
"eval_loss": 0.5413796901702881,
|
| 866 |
+
"eval_runtime": 10.822,
|
| 867 |
+
"eval_samples_per_second": 44.354,
|
| 868 |
+
"eval_steps_per_second": 2.772,
|
| 869 |
"step": 1000
|
| 870 |
},
|
| 871 |
{
|
| 872 |
"epoch": 1.0978260869565217,
|
| 873 |
+
"grad_norm": 0.9884430766105652,
|
| 874 |
"learning_rate": 3.170289855072464e-05,
|
| 875 |
+
"loss": 0.4134,
|
| 876 |
"step": 1010
|
| 877 |
},
|
| 878 |
{
|
| 879 |
"epoch": 1.108695652173913,
|
| 880 |
+
"grad_norm": 0.920870840549469,
|
| 881 |
"learning_rate": 3.152173913043479e-05,
|
| 882 |
+
"loss": 0.3837,
|
| 883 |
"step": 1020
|
| 884 |
},
|
| 885 |
{
|
| 886 |
"epoch": 1.1195652173913044,
|
| 887 |
+
"grad_norm": 0.942890465259552,
|
| 888 |
"learning_rate": 3.134057971014493e-05,
|
| 889 |
+
"loss": 0.38,
|
| 890 |
"step": 1030
|
| 891 |
},
|
| 892 |
{
|
| 893 |
"epoch": 1.1304347826086956,
|
| 894 |
+
"grad_norm": 1.0265600681304932,
|
| 895 |
"learning_rate": 3.1159420289855074e-05,
|
| 896 |
+
"loss": 0.3988,
|
| 897 |
"step": 1040
|
| 898 |
},
|
| 899 |
{
|
| 900 |
"epoch": 1.141304347826087,
|
| 901 |
+
"grad_norm": 0.9994137287139893,
|
| 902 |
"learning_rate": 3.0978260869565215e-05,
|
| 903 |
+
"loss": 0.3649,
|
| 904 |
"step": 1050
|
| 905 |
},
|
| 906 |
{
|
| 907 |
"epoch": 1.141304347826087,
|
| 908 |
+
"eval_loss": 0.537377655506134,
|
| 909 |
+
"eval_runtime": 10.7968,
|
| 910 |
+
"eval_samples_per_second": 44.458,
|
| 911 |
+
"eval_steps_per_second": 2.779,
|
| 912 |
"step": 1050
|
| 913 |
},
|
| 914 |
{
|
| 915 |
"epoch": 1.1521739130434783,
|
| 916 |
+
"grad_norm": 0.9697039723396301,
|
| 917 |
"learning_rate": 3.079710144927536e-05,
|
| 918 |
+
"loss": 0.393,
|
| 919 |
"step": 1060
|
| 920 |
},
|
| 921 |
{
|
| 922 |
"epoch": 1.1630434782608696,
|
| 923 |
+
"grad_norm": 0.9805816411972046,
|
| 924 |
"learning_rate": 3.061594202898551e-05,
|
| 925 |
+
"loss": 0.3594,
|
| 926 |
"step": 1070
|
| 927 |
},
|
| 928 |
{
|
| 929 |
"epoch": 1.1739130434782608,
|
| 930 |
+
"grad_norm": 0.9799211621284485,
|
| 931 |
"learning_rate": 3.0434782608695656e-05,
|
| 932 |
+
"loss": 0.387,
|
| 933 |
"step": 1080
|
| 934 |
},
|
| 935 |
{
|
| 936 |
"epoch": 1.184782608695652,
|
| 937 |
+
"grad_norm": 0.9287502765655518,
|
| 938 |
"learning_rate": 3.02536231884058e-05,
|
| 939 |
+
"loss": 0.3889,
|
| 940 |
"step": 1090
|
| 941 |
},
|
| 942 |
{
|
| 943 |
"epoch": 1.1956521739130435,
|
| 944 |
+
"grad_norm": 1.042643666267395,
|
| 945 |
"learning_rate": 3.0072463768115944e-05,
|
| 946 |
+
"loss": 0.3894,
|
| 947 |
"step": 1100
|
| 948 |
},
|
| 949 |
{
|
| 950 |
"epoch": 1.1956521739130435,
|
| 951 |
+
"eval_loss": 0.5378063917160034,
|
| 952 |
+
"eval_runtime": 10.77,
|
| 953 |
+
"eval_samples_per_second": 44.568,
|
| 954 |
+
"eval_steps_per_second": 2.786,
|
| 955 |
"step": 1100
|
| 956 |
},
|
| 957 |
{
|
| 958 |
"epoch": 1.2065217391304348,
|
| 959 |
+
"grad_norm": 0.963258683681488,
|
| 960 |
"learning_rate": 2.9891304347826088e-05,
|
| 961 |
+
"loss": 0.3824,
|
| 962 |
"step": 1110
|
| 963 |
},
|
| 964 |
{
|
| 965 |
"epoch": 1.2173913043478262,
|
| 966 |
+
"grad_norm": 0.939275860786438,
|
| 967 |
"learning_rate": 2.971014492753623e-05,
|
| 968 |
+
"loss": 0.3898,
|
| 969 |
"step": 1120
|
| 970 |
},
|
| 971 |
{
|
| 972 |
"epoch": 1.2282608695652173,
|
| 973 |
+
"grad_norm": 1.1144332885742188,
|
| 974 |
"learning_rate": 2.9528985507246375e-05,
|
| 975 |
+
"loss": 0.3754,
|
| 976 |
"step": 1130
|
| 977 |
},
|
| 978 |
{
|
| 979 |
"epoch": 1.2391304347826086,
|
| 980 |
+
"grad_norm": 0.999047577381134,
|
| 981 |
"learning_rate": 2.9347826086956526e-05,
|
| 982 |
+
"loss": 0.3876,
|
| 983 |
"step": 1140
|
| 984 |
},
|
| 985 |
{
|
| 986 |
"epoch": 1.25,
|
| 987 |
+
"grad_norm": 1.024510383605957,
|
| 988 |
"learning_rate": 2.916666666666667e-05,
|
| 989 |
+
"loss": 0.3782,
|
| 990 |
"step": 1150
|
| 991 |
},
|
| 992 |
{
|
| 993 |
"epoch": 1.25,
|
| 994 |
+
"eval_loss": 0.5348225831985474,
|
| 995 |
+
"eval_runtime": 10.7748,
|
| 996 |
+
"eval_samples_per_second": 44.548,
|
| 997 |
+
"eval_steps_per_second": 2.784,
|
| 998 |
"step": 1150
|
| 999 |
},
|
| 1000 |
{
|
| 1001 |
"epoch": 1.2608695652173914,
|
| 1002 |
+
"grad_norm": 1.0736693143844604,
|
| 1003 |
"learning_rate": 2.8985507246376814e-05,
|
| 1004 |
+
"loss": 0.3895,
|
| 1005 |
"step": 1160
|
| 1006 |
},
|
| 1007 |
{
|
| 1008 |
"epoch": 1.2717391304347827,
|
| 1009 |
+
"grad_norm": 0.9759789705276489,
|
| 1010 |
"learning_rate": 2.8804347826086957e-05,
|
| 1011 |
+
"loss": 0.3989,
|
| 1012 |
"step": 1170
|
| 1013 |
},
|
| 1014 |
{
|
| 1015 |
"epoch": 1.2826086956521738,
|
| 1016 |
+
"grad_norm": 0.8532370328903198,
|
| 1017 |
"learning_rate": 2.86231884057971e-05,
|
| 1018 |
+
"loss": 0.3814,
|
| 1019 |
"step": 1180
|
| 1020 |
},
|
| 1021 |
{
|
| 1022 |
"epoch": 1.2934782608695652,
|
| 1023 |
+
"grad_norm": 0.9838298559188843,
|
| 1024 |
"learning_rate": 2.8442028985507245e-05,
|
| 1025 |
+
"loss": 0.3864,
|
| 1026 |
"step": 1190
|
| 1027 |
},
|
| 1028 |
{
|
| 1029 |
"epoch": 1.3043478260869565,
|
| 1030 |
+
"grad_norm": 0.8785775899887085,
|
| 1031 |
"learning_rate": 2.826086956521739e-05,
|
| 1032 |
+
"loss": 0.3676,
|
| 1033 |
"step": 1200
|
| 1034 |
},
|
| 1035 |
{
|
| 1036 |
"epoch": 1.3043478260869565,
|
| 1037 |
+
"eval_loss": 0.5335877537727356,
|
| 1038 |
+
"eval_runtime": 10.7959,
|
| 1039 |
+
"eval_samples_per_second": 44.461,
|
| 1040 |
+
"eval_steps_per_second": 2.779,
|
| 1041 |
"step": 1200
|
| 1042 |
},
|
| 1043 |
{
|
| 1044 |
"epoch": 1.315217391304348,
|
| 1045 |
+
"grad_norm": 0.9719653129577637,
|
| 1046 |
"learning_rate": 2.807971014492754e-05,
|
| 1047 |
+
"loss": 0.3913,
|
| 1048 |
"step": 1210
|
| 1049 |
},
|
| 1050 |
{
|
| 1051 |
"epoch": 1.3260869565217392,
|
| 1052 |
+
"grad_norm": 0.9099355340003967,
|
| 1053 |
"learning_rate": 2.7898550724637683e-05,
|
| 1054 |
+
"loss": 0.4019,
|
| 1055 |
"step": 1220
|
| 1056 |
},
|
| 1057 |
{
|
| 1058 |
"epoch": 1.3369565217391304,
|
| 1059 |
+
"grad_norm": 0.9192841649055481,
|
| 1060 |
"learning_rate": 2.7717391304347827e-05,
|
| 1061 |
+
"loss": 0.3921,
|
| 1062 |
"step": 1230
|
| 1063 |
},
|
| 1064 |
{
|
| 1065 |
"epoch": 1.3478260869565217,
|
| 1066 |
+
"grad_norm": 1.1005280017852783,
|
| 1067 |
"learning_rate": 2.753623188405797e-05,
|
| 1068 |
+
"loss": 0.3892,
|
| 1069 |
"step": 1240
|
| 1070 |
},
|
| 1071 |
{
|
| 1072 |
"epoch": 1.358695652173913,
|
| 1073 |
+
"grad_norm": 0.9969606995582581,
|
| 1074 |
"learning_rate": 2.7355072463768118e-05,
|
| 1075 |
+
"loss": 0.3756,
|
| 1076 |
"step": 1250
|
| 1077 |
},
|
| 1078 |
{
|
| 1079 |
"epoch": 1.358695652173913,
|
| 1080 |
+
"eval_loss": 0.5348997712135315,
|
| 1081 |
+
"eval_runtime": 10.8018,
|
| 1082 |
+
"eval_samples_per_second": 44.437,
|
| 1083 |
+
"eval_steps_per_second": 2.777,
|
| 1084 |
"step": 1250
|
| 1085 |
},
|
| 1086 |
{
|
| 1087 |
"epoch": 1.3695652173913042,
|
| 1088 |
+
"grad_norm": 1.1843461990356445,
|
| 1089 |
"learning_rate": 2.7173913043478262e-05,
|
| 1090 |
+
"loss": 0.3751,
|
| 1091 |
"step": 1260
|
| 1092 |
},
|
| 1093 |
{
|
| 1094 |
"epoch": 1.3804347826086958,
|
| 1095 |
+
"grad_norm": 0.9097041487693787,
|
| 1096 |
"learning_rate": 2.6992753623188406e-05,
|
| 1097 |
+
"loss": 0.3852,
|
| 1098 |
"step": 1270
|
| 1099 |
},
|
| 1100 |
{
|
| 1101 |
"epoch": 1.391304347826087,
|
| 1102 |
+
"grad_norm": 0.9780197739601135,
|
| 1103 |
"learning_rate": 2.6811594202898553e-05,
|
| 1104 |
+
"loss": 0.3776,
|
| 1105 |
"step": 1280
|
| 1106 |
},
|
| 1107 |
{
|
| 1108 |
"epoch": 1.4021739130434783,
|
| 1109 |
+
"grad_norm": 1.0949311256408691,
|
| 1110 |
"learning_rate": 2.66304347826087e-05,
|
| 1111 |
+
"loss": 0.3517,
|
| 1112 |
"step": 1290
|
| 1113 |
},
|
| 1114 |
{
|
| 1115 |
"epoch": 1.4130434782608696,
|
| 1116 |
+
"grad_norm": 1.0105839967727661,
|
| 1117 |
"learning_rate": 2.6449275362318844e-05,
|
| 1118 |
+
"loss": 0.384,
|
| 1119 |
"step": 1300
|
| 1120 |
},
|
| 1121 |
{
|
| 1122 |
"epoch": 1.4130434782608696,
|
| 1123 |
+
"eval_loss": 0.5327685475349426,
|
| 1124 |
+
"eval_runtime": 10.8023,
|
| 1125 |
+
"eval_samples_per_second": 44.435,
|
| 1126 |
+
"eval_steps_per_second": 2.777,
|
| 1127 |
"step": 1300
|
| 1128 |
},
|
| 1129 |
{
|
| 1130 |
"epoch": 1.4239130434782608,
|
| 1131 |
+
"grad_norm": 1.0113478899002075,
|
| 1132 |
"learning_rate": 2.6268115942028988e-05,
|
| 1133 |
+
"loss": 0.3774,
|
| 1134 |
"step": 1310
|
| 1135 |
},
|
| 1136 |
{
|
| 1137 |
"epoch": 1.434782608695652,
|
| 1138 |
+
"grad_norm": 1.0456714630126953,
|
| 1139 |
"learning_rate": 2.608695652173913e-05,
|
| 1140 |
+
"loss": 0.3618,
|
| 1141 |
"step": 1320
|
| 1142 |
},
|
| 1143 |
{
|
| 1144 |
"epoch": 1.4456521739130435,
|
| 1145 |
+
"grad_norm": 1.048971176147461,
|
| 1146 |
"learning_rate": 2.5905797101449275e-05,
|
| 1147 |
+
"loss": 0.3707,
|
| 1148 |
"step": 1330
|
| 1149 |
},
|
| 1150 |
{
|
| 1151 |
"epoch": 1.4565217391304348,
|
| 1152 |
+
"grad_norm": 0.9918339252471924,
|
| 1153 |
"learning_rate": 2.572463768115942e-05,
|
| 1154 |
+
"loss": 0.3979,
|
| 1155 |
"step": 1340
|
| 1156 |
},
|
| 1157 |
{
|
| 1158 |
"epoch": 1.4673913043478262,
|
| 1159 |
+
"grad_norm": 0.8943142890930176,
|
| 1160 |
"learning_rate": 2.554347826086957e-05,
|
| 1161 |
+
"loss": 0.3647,
|
| 1162 |
"step": 1350
|
| 1163 |
},
|
| 1164 |
{
|
| 1165 |
"epoch": 1.4673913043478262,
|
| 1166 |
+
"eval_loss": 0.530137836933136,
|
| 1167 |
+
"eval_runtime": 10.8212,
|
| 1168 |
+
"eval_samples_per_second": 44.357,
|
| 1169 |
+
"eval_steps_per_second": 2.772,
|
| 1170 |
"step": 1350
|
| 1171 |
},
|
| 1172 |
{
|
| 1173 |
"epoch": 1.4782608695652173,
|
| 1174 |
+
"grad_norm": 1.1170648336410522,
|
| 1175 |
"learning_rate": 2.5362318840579714e-05,
|
| 1176 |
+
"loss": 0.3752,
|
| 1177 |
"step": 1360
|
| 1178 |
},
|
| 1179 |
{
|
| 1180 |
"epoch": 1.4891304347826086,
|
| 1181 |
+
"grad_norm": 1.0574833154678345,
|
| 1182 |
"learning_rate": 2.5181159420289857e-05,
|
| 1183 |
+
"loss": 0.4005,
|
| 1184 |
"step": 1370
|
| 1185 |
},
|
| 1186 |
{
|
| 1187 |
"epoch": 1.5,
|
| 1188 |
+
"grad_norm": 1.0728522539138794,
|
| 1189 |
"learning_rate": 2.5e-05,
|
| 1190 |
+
"loss": 0.404,
|
| 1191 |
"step": 1380
|
| 1192 |
},
|
| 1193 |
{
|
| 1194 |
"epoch": 1.5108695652173914,
|
| 1195 |
+
"grad_norm": 1.0159659385681152,
|
| 1196 |
"learning_rate": 2.4818840579710145e-05,
|
| 1197 |
+
"loss": 0.4051,
|
| 1198 |
"step": 1390
|
| 1199 |
},
|
| 1200 |
{
|
| 1201 |
"epoch": 1.5217391304347827,
|
| 1202 |
+
"grad_norm": 0.9714246392250061,
|
| 1203 |
"learning_rate": 2.4637681159420292e-05,
|
| 1204 |
+
"loss": 0.3775,
|
| 1205 |
"step": 1400
|
| 1206 |
},
|
| 1207 |
{
|
| 1208 |
"epoch": 1.5217391304347827,
|
| 1209 |
+
"eval_loss": 0.528946578502655,
|
| 1210 |
+
"eval_runtime": 10.8248,
|
| 1211 |
+
"eval_samples_per_second": 44.343,
|
| 1212 |
+
"eval_steps_per_second": 2.771,
|
| 1213 |
"step": 1400
|
| 1214 |
},
|
| 1215 |
{
|
| 1216 |
"epoch": 1.5326086956521738,
|
| 1217 |
+
"grad_norm": 1.0848588943481445,
|
| 1218 |
"learning_rate": 2.4456521739130436e-05,
|
| 1219 |
+
"loss": 0.3703,
|
| 1220 |
"step": 1410
|
| 1221 |
},
|
| 1222 |
{
|
| 1223 |
"epoch": 1.5434782608695652,
|
| 1224 |
+
"grad_norm": 1.0333784818649292,
|
| 1225 |
"learning_rate": 2.427536231884058e-05,
|
| 1226 |
+
"loss": 0.3692,
|
| 1227 |
"step": 1420
|
| 1228 |
},
|
| 1229 |
{
|
| 1230 |
"epoch": 1.5543478260869565,
|
| 1231 |
+
"grad_norm": 0.9682796597480774,
|
| 1232 |
"learning_rate": 2.4094202898550724e-05,
|
| 1233 |
+
"loss": 0.3722,
|
| 1234 |
"step": 1430
|
| 1235 |
},
|
| 1236 |
{
|
| 1237 |
"epoch": 1.5652173913043477,
|
| 1238 |
+
"grad_norm": 1.0484014749526978,
|
| 1239 |
"learning_rate": 2.391304347826087e-05,
|
| 1240 |
+
"loss": 0.3763,
|
| 1241 |
"step": 1440
|
| 1242 |
},
|
| 1243 |
{
|
| 1244 |
"epoch": 1.5760869565217392,
|
| 1245 |
+
"grad_norm": 0.9075008630752563,
|
| 1246 |
"learning_rate": 2.3731884057971015e-05,
|
| 1247 |
+
"loss": 0.3594,
|
| 1248 |
"step": 1450
|
| 1249 |
},
|
| 1250 |
{
|
| 1251 |
"epoch": 1.5760869565217392,
|
| 1252 |
+
"eval_loss": 0.5278663039207458,
|
| 1253 |
+
"eval_runtime": 10.831,
|
| 1254 |
+
"eval_samples_per_second": 44.317,
|
| 1255 |
+
"eval_steps_per_second": 2.77,
|
| 1256 |
"step": 1450
|
| 1257 |
},
|
| 1258 |
{
|
| 1259 |
"epoch": 1.5869565217391304,
|
| 1260 |
+
"grad_norm": 0.9710797667503357,
|
| 1261 |
"learning_rate": 2.355072463768116e-05,
|
| 1262 |
+
"loss": 0.3821,
|
| 1263 |
"step": 1460
|
| 1264 |
},
|
| 1265 |
{
|
| 1266 |
"epoch": 1.5978260869565217,
|
| 1267 |
+
"grad_norm": 1.0220218896865845,
|
| 1268 |
"learning_rate": 2.3369565217391306e-05,
|
| 1269 |
+
"loss": 0.3623,
|
| 1270 |
"step": 1470
|
| 1271 |
},
|
| 1272 |
{
|
| 1273 |
"epoch": 1.608695652173913,
|
| 1274 |
+
"grad_norm": 1.0994117259979248,
|
| 1275 |
"learning_rate": 2.318840579710145e-05,
|
| 1276 |
+
"loss": 0.3735,
|
| 1277 |
"step": 1480
|
| 1278 |
},
|
| 1279 |
{
|
| 1280 |
"epoch": 1.6195652173913042,
|
| 1281 |
+
"grad_norm": 0.9513503313064575,
|
| 1282 |
"learning_rate": 2.3007246376811593e-05,
|
| 1283 |
+
"loss": 0.3743,
|
| 1284 |
"step": 1490
|
| 1285 |
},
|
| 1286 |
{
|
| 1287 |
"epoch": 1.6304347826086958,
|
| 1288 |
+
"grad_norm": 0.9903764128684998,
|
| 1289 |
"learning_rate": 2.282608695652174e-05,
|
| 1290 |
+
"loss": 0.3661,
|
| 1291 |
"step": 1500
|
| 1292 |
},
|
| 1293 |
{
|
| 1294 |
"epoch": 1.6304347826086958,
|
| 1295 |
+
"eval_loss": 0.5267059803009033,
|
| 1296 |
+
"eval_runtime": 10.8461,
|
| 1297 |
+
"eval_samples_per_second": 44.256,
|
| 1298 |
+
"eval_steps_per_second": 2.766,
|
| 1299 |
"step": 1500
|
| 1300 |
},
|
| 1301 |
{
|
| 1302 |
"epoch": 1.641304347826087,
|
| 1303 |
+
"grad_norm": 0.9712284207344055,
|
| 1304 |
"learning_rate": 2.2644927536231884e-05,
|
| 1305 |
+
"loss": 0.3662,
|
| 1306 |
"step": 1510
|
| 1307 |
},
|
| 1308 |
{
|
| 1309 |
"epoch": 1.6521739130434783,
|
| 1310 |
+
"grad_norm": 0.9667128920555115,
|
| 1311 |
"learning_rate": 2.246376811594203e-05,
|
| 1312 |
+
"loss": 0.3767,
|
| 1313 |
"step": 1520
|
| 1314 |
},
|
| 1315 |
{
|
| 1316 |
"epoch": 1.6630434782608696,
|
| 1317 |
+
"grad_norm": 0.9828950762748718,
|
| 1318 |
"learning_rate": 2.2282608695652175e-05,
|
| 1319 |
+
"loss": 0.3766,
|
| 1320 |
"step": 1530
|
| 1321 |
},
|
| 1322 |
{
|
| 1323 |
"epoch": 1.6739130434782608,
|
| 1324 |
+
"grad_norm": 1.0777678489685059,
|
| 1325 |
"learning_rate": 2.2101449275362323e-05,
|
| 1326 |
+
"loss": 0.3791,
|
| 1327 |
"step": 1540
|
| 1328 |
},
|
| 1329 |
{
|
| 1330 |
"epoch": 1.6847826086956523,
|
| 1331 |
+
"grad_norm": 1.006035566329956,
|
| 1332 |
"learning_rate": 2.1920289855072466e-05,
|
| 1333 |
+
"loss": 0.3961,
|
| 1334 |
"step": 1550
|
| 1335 |
},
|
| 1336 |
{
|
| 1337 |
"epoch": 1.6847826086956523,
|
| 1338 |
+
"eval_loss": 0.5241792798042297,
|
| 1339 |
+
"eval_runtime": 10.8288,
|
| 1340 |
+
"eval_samples_per_second": 44.326,
|
| 1341 |
+
"eval_steps_per_second": 2.77,
|
| 1342 |
"step": 1550
|
| 1343 |
},
|
| 1344 |
{
|
| 1345 |
"epoch": 1.6956521739130435,
|
| 1346 |
+
"grad_norm": 0.9397144913673401,
|
| 1347 |
"learning_rate": 2.173913043478261e-05,
|
| 1348 |
+
"loss": 0.3659,
|
| 1349 |
"step": 1560
|
| 1350 |
},
|
| 1351 |
{
|
| 1352 |
"epoch": 1.7065217391304348,
|
| 1353 |
+
"grad_norm": 1.1106013059616089,
|
| 1354 |
"learning_rate": 2.1557971014492757e-05,
|
| 1355 |
+
"loss": 0.381,
|
| 1356 |
"step": 1570
|
| 1357 |
},
|
| 1358 |
{
|
| 1359 |
"epoch": 1.7173913043478262,
|
| 1360 |
+
"grad_norm": 0.9626741409301758,
|
| 1361 |
"learning_rate": 2.13768115942029e-05,
|
| 1362 |
+
"loss": 0.3751,
|
| 1363 |
"step": 1580
|
| 1364 |
},
|
| 1365 |
{
|
| 1366 |
"epoch": 1.7282608695652173,
|
| 1367 |
+
"grad_norm": 1.139076828956604,
|
| 1368 |
"learning_rate": 2.1195652173913045e-05,
|
| 1369 |
+
"loss": 0.3888,
|
| 1370 |
"step": 1590
|
| 1371 |
},
|
| 1372 |
{
|
| 1373 |
"epoch": 1.7391304347826086,
|
| 1374 |
+
"grad_norm": 1.0335912704467773,
|
| 1375 |
"learning_rate": 2.101449275362319e-05,
|
| 1376 |
+
"loss": 0.3758,
|
| 1377 |
"step": 1600
|
| 1378 |
},
|
| 1379 |
{
|
| 1380 |
"epoch": 1.7391304347826086,
|
| 1381 |
+
"eval_loss": 0.5224525332450867,
|
| 1382 |
+
"eval_runtime": 10.8033,
|
| 1383 |
+
"eval_samples_per_second": 44.431,
|
| 1384 |
+
"eval_steps_per_second": 2.777,
|
| 1385 |
"step": 1600
|
| 1386 |
},
|
| 1387 |
{
|
| 1388 |
"epoch": 1.75,
|
| 1389 |
+
"grad_norm": 1.0831104516983032,
|
| 1390 |
"learning_rate": 2.0833333333333336e-05,
|
| 1391 |
+
"loss": 0.3429,
|
| 1392 |
"step": 1610
|
| 1393 |
},
|
| 1394 |
{
|
| 1395 |
"epoch": 1.7608695652173914,
|
| 1396 |
+
"grad_norm": 1.0405676364898682,
|
| 1397 |
"learning_rate": 2.065217391304348e-05,
|
| 1398 |
+
"loss": 0.3506,
|
| 1399 |
"step": 1620
|
| 1400 |
},
|
| 1401 |
{
|
| 1402 |
"epoch": 1.7717391304347827,
|
| 1403 |
+
"grad_norm": 0.9948307275772095,
|
| 1404 |
"learning_rate": 2.0471014492753624e-05,
|
| 1405 |
+
"loss": 0.3528,
|
| 1406 |
"step": 1630
|
| 1407 |
},
|
| 1408 |
{
|
| 1409 |
"epoch": 1.7826086956521738,
|
| 1410 |
+
"grad_norm": 1.103110671043396,
|
| 1411 |
"learning_rate": 2.028985507246377e-05,
|
| 1412 |
+
"loss": 0.3779,
|
| 1413 |
"step": 1640
|
| 1414 |
},
|
| 1415 |
{
|
| 1416 |
"epoch": 1.7934782608695652,
|
| 1417 |
+
"grad_norm": 1.0501149892807007,
|
| 1418 |
"learning_rate": 2.0108695652173915e-05,
|
| 1419 |
+
"loss": 0.3957,
|
| 1420 |
"step": 1650
|
| 1421 |
},
|
| 1422 |
{
|
| 1423 |
"epoch": 1.7934782608695652,
|
| 1424 |
+
"eval_loss": 0.5198243260383606,
|
| 1425 |
+
"eval_runtime": 10.7809,
|
| 1426 |
+
"eval_samples_per_second": 44.523,
|
| 1427 |
+
"eval_steps_per_second": 2.783,
|
| 1428 |
"step": 1650
|
| 1429 |
},
|
| 1430 |
{
|
| 1431 |
"epoch": 1.8043478260869565,
|
| 1432 |
+
"grad_norm": 1.0968273878097534,
|
| 1433 |
"learning_rate": 1.992753623188406e-05,
|
| 1434 |
+
"loss": 0.3746,
|
| 1435 |
"step": 1660
|
| 1436 |
},
|
| 1437 |
{
|
| 1438 |
"epoch": 1.8152173913043477,
|
| 1439 |
+
"grad_norm": 1.0902262926101685,
|
| 1440 |
"learning_rate": 1.9746376811594202e-05,
|
| 1441 |
+
"loss": 0.3688,
|
| 1442 |
"step": 1670
|
| 1443 |
},
|
| 1444 |
{
|
| 1445 |
"epoch": 1.8260869565217392,
|
| 1446 |
+
"grad_norm": 1.1077326536178589,
|
| 1447 |
"learning_rate": 1.956521739130435e-05,
|
| 1448 |
+
"loss": 0.3274,
|
| 1449 |
"step": 1680
|
| 1450 |
},
|
| 1451 |
{
|
| 1452 |
"epoch": 1.8369565217391304,
|
| 1453 |
+
"grad_norm": 1.005223035812378,
|
| 1454 |
"learning_rate": 1.9384057971014493e-05,
|
| 1455 |
+
"loss": 0.3858,
|
| 1456 |
"step": 1690
|
| 1457 |
},
|
| 1458 |
{
|
| 1459 |
"epoch": 1.8478260869565217,
|
| 1460 |
+
"grad_norm": 1.131982445716858,
|
| 1461 |
"learning_rate": 1.9202898550724637e-05,
|
| 1462 |
+
"loss": 0.3676,
|
| 1463 |
"step": 1700
|
| 1464 |
},
|
| 1465 |
{
|
| 1466 |
"epoch": 1.8478260869565217,
|
| 1467 |
+
"eval_loss": 0.5192354321479797,
|
| 1468 |
+
"eval_runtime": 10.7892,
|
| 1469 |
+
"eval_samples_per_second": 44.489,
|
| 1470 |
+
"eval_steps_per_second": 2.781,
|
| 1471 |
"step": 1700
|
| 1472 |
},
|
| 1473 |
{
|
| 1474 |
"epoch": 1.858695652173913,
|
| 1475 |
+
"grad_norm": 1.0396854877471924,
|
| 1476 |
"learning_rate": 1.9021739130434784e-05,
|
| 1477 |
+
"loss": 0.3738,
|
| 1478 |
"step": 1710
|
| 1479 |
},
|
| 1480 |
{
|
| 1481 |
"epoch": 1.8695652173913042,
|
| 1482 |
+
"grad_norm": 1.1090553998947144,
|
| 1483 |
"learning_rate": 1.8840579710144928e-05,
|
| 1484 |
+
"loss": 0.3695,
|
| 1485 |
"step": 1720
|
| 1486 |
},
|
| 1487 |
{
|
| 1488 |
"epoch": 1.8804347826086958,
|
| 1489 |
+
"grad_norm": 1.081115484237671,
|
| 1490 |
"learning_rate": 1.8659420289855072e-05,
|
| 1491 |
+
"loss": 0.3549,
|
| 1492 |
"step": 1730
|
| 1493 |
},
|
| 1494 |
{
|
| 1495 |
"epoch": 1.891304347826087,
|
| 1496 |
+
"grad_norm": 1.1276469230651855,
|
| 1497 |
"learning_rate": 1.8478260869565216e-05,
|
| 1498 |
+
"loss": 0.364,
|
| 1499 |
"step": 1740
|
| 1500 |
},
|
| 1501 |
{
|
| 1502 |
"epoch": 1.9021739130434783,
|
| 1503 |
+
"grad_norm": 1.0103682279586792,
|
| 1504 |
"learning_rate": 1.8297101449275363e-05,
|
| 1505 |
+
"loss": 0.3781,
|
| 1506 |
"step": 1750
|
| 1507 |
},
|
| 1508 |
{
|
| 1509 |
"epoch": 1.9021739130434783,
|
| 1510 |
+
"eval_loss": 0.5211134552955627,
|
| 1511 |
+
"eval_runtime": 10.7922,
|
| 1512 |
+
"eval_samples_per_second": 44.477,
|
| 1513 |
+
"eval_steps_per_second": 2.78,
|
| 1514 |
"step": 1750
|
| 1515 |
},
|
| 1516 |
{
|
| 1517 |
"epoch": 1.9130434782608696,
|
| 1518 |
+
"grad_norm": 0.9383260011672974,
|
| 1519 |
"learning_rate": 1.8115942028985507e-05,
|
| 1520 |
+
"loss": 0.3469,
|
| 1521 |
"step": 1760
|
| 1522 |
},
|
| 1523 |
{
|
| 1524 |
"epoch": 1.9239130434782608,
|
| 1525 |
+
"grad_norm": 1.095609188079834,
|
| 1526 |
"learning_rate": 1.793478260869565e-05,
|
| 1527 |
+
"loss": 0.3747,
|
| 1528 |
"step": 1770
|
| 1529 |
},
|
| 1530 |
{
|
| 1531 |
"epoch": 1.9347826086956523,
|
| 1532 |
+
"grad_norm": 1.0580706596374512,
|
| 1533 |
"learning_rate": 1.7753623188405798e-05,
|
| 1534 |
+
"loss": 0.3751,
|
| 1535 |
"step": 1780
|
| 1536 |
},
|
| 1537 |
{
|
| 1538 |
"epoch": 1.9456521739130435,
|
| 1539 |
+
"grad_norm": 0.9539552927017212,
|
| 1540 |
"learning_rate": 1.757246376811594e-05,
|
| 1541 |
+
"loss": 0.3638,
|
| 1542 |
"step": 1790
|
| 1543 |
},
|
| 1544 |
{
|
| 1545 |
"epoch": 1.9565217391304348,
|
| 1546 |
+
"grad_norm": 1.0025752782821655,
|
| 1547 |
"learning_rate": 1.739130434782609e-05,
|
| 1548 |
+
"loss": 0.3851,
|
| 1549 |
"step": 1800
|
| 1550 |
},
|
| 1551 |
{
|
| 1552 |
"epoch": 1.9565217391304348,
|
| 1553 |
+
"eval_loss": 0.516950249671936,
|
| 1554 |
+
"eval_runtime": 10.7904,
|
| 1555 |
+
"eval_samples_per_second": 44.484,
|
| 1556 |
+
"eval_steps_per_second": 2.78,
|
| 1557 |
"step": 1800
|
| 1558 |
},
|
| 1559 |
{
|
| 1560 |
"epoch": 1.9673913043478262,
|
| 1561 |
+
"grad_norm": 1.0852687358856201,
|
| 1562 |
"learning_rate": 1.7210144927536233e-05,
|
| 1563 |
+
"loss": 0.3472,
|
| 1564 |
"step": 1810
|
| 1565 |
},
|
| 1566 |
{
|
| 1567 |
"epoch": 1.9782608695652173,
|
| 1568 |
+
"grad_norm": 1.1232205629348755,
|
| 1569 |
"learning_rate": 1.702898550724638e-05,
|
| 1570 |
+
"loss": 0.3591,
|
| 1571 |
"step": 1820
|
| 1572 |
},
|
| 1573 |
{
|
| 1574 |
"epoch": 1.9891304347826086,
|
| 1575 |
+
"grad_norm": 1.0539883375167847,
|
| 1576 |
"learning_rate": 1.6847826086956524e-05,
|
| 1577 |
+
"loss": 0.3657,
|
| 1578 |
"step": 1830
|
| 1579 |
},
|
| 1580 |
{
|
| 1581 |
"epoch": 2.0,
|
| 1582 |
+
"grad_norm": 2.387427806854248,
|
| 1583 |
"learning_rate": 1.6666666666666667e-05,
|
| 1584 |
+
"loss": 0.393,
|
| 1585 |
"step": 1840
|
| 1586 |
},
|
| 1587 |
{
|
| 1588 |
"epoch": 2.010869565217391,
|
| 1589 |
+
"grad_norm": 1.0311148166656494,
|
| 1590 |
"learning_rate": 1.6485507246376815e-05,
|
| 1591 |
+
"loss": 0.3364,
|
| 1592 |
"step": 1850
|
| 1593 |
},
|
| 1594 |
{
|
| 1595 |
"epoch": 2.010869565217391,
|
| 1596 |
+
"eval_loss": 0.5237263441085815,
|
| 1597 |
+
"eval_runtime": 10.8116,
|
| 1598 |
+
"eval_samples_per_second": 44.397,
|
| 1599 |
+
"eval_steps_per_second": 2.775,
|
| 1600 |
"step": 1850
|
| 1601 |
},
|
| 1602 |
{
|
| 1603 |
"epoch": 2.0217391304347827,
|
| 1604 |
+
"grad_norm": 1.2049050331115723,
|
| 1605 |
"learning_rate": 1.630434782608696e-05,
|
| 1606 |
+
"loss": 0.336,
|
| 1607 |
"step": 1860
|
| 1608 |
},
|
| 1609 |
{
|
| 1610 |
"epoch": 2.032608695652174,
|
| 1611 |
+
"grad_norm": 1.0490036010742188,
|
| 1612 |
"learning_rate": 1.6123188405797102e-05,
|
| 1613 |
+
"loss": 0.3243,
|
| 1614 |
"step": 1870
|
| 1615 |
},
|
| 1616 |
{
|
| 1617 |
"epoch": 2.0434782608695654,
|
| 1618 |
+
"grad_norm": 1.131861686706543,
|
| 1619 |
"learning_rate": 1.5942028985507246e-05,
|
| 1620 |
+
"loss": 0.3311,
|
| 1621 |
"step": 1880
|
| 1622 |
},
|
| 1623 |
{
|
| 1624 |
"epoch": 2.0543478260869565,
|
| 1625 |
+
"grad_norm": 1.0843744277954102,
|
| 1626 |
"learning_rate": 1.5760869565217393e-05,
|
| 1627 |
+
"loss": 0.3107,
|
| 1628 |
"step": 1890
|
| 1629 |
},
|
| 1630 |
{
|
| 1631 |
"epoch": 2.0652173913043477,
|
| 1632 |
+
"grad_norm": 1.1070170402526855,
|
| 1633 |
"learning_rate": 1.5579710144927537e-05,
|
| 1634 |
+
"loss": 0.3357,
|
| 1635 |
"step": 1900
|
| 1636 |
},
|
| 1637 |
{
|
| 1638 |
"epoch": 2.0652173913043477,
|
| 1639 |
+
"eval_loss": 0.5324747562408447,
|
| 1640 |
+
"eval_runtime": 10.8165,
|
| 1641 |
+
"eval_samples_per_second": 44.377,
|
| 1642 |
+
"eval_steps_per_second": 2.774,
|
| 1643 |
"step": 1900
|
| 1644 |
},
|
| 1645 |
{
|
| 1646 |
"epoch": 2.0760869565217392,
|
| 1647 |
+
"grad_norm": 1.1747304201126099,
|
| 1648 |
"learning_rate": 1.539855072463768e-05,
|
| 1649 |
+
"loss": 0.3301,
|
| 1650 |
"step": 1910
|
| 1651 |
},
|
| 1652 |
{
|
| 1653 |
"epoch": 2.0869565217391304,
|
| 1654 |
+
"grad_norm": 1.151397943496704,
|
| 1655 |
"learning_rate": 1.5217391304347828e-05,
|
| 1656 |
+
"loss": 0.3313,
|
| 1657 |
"step": 1920
|
| 1658 |
},
|
| 1659 |
{
|
| 1660 |
"epoch": 2.097826086956522,
|
| 1661 |
+
"grad_norm": 1.1628749370574951,
|
| 1662 |
"learning_rate": 1.5036231884057972e-05,
|
| 1663 |
+
"loss": 0.322,
|
| 1664 |
"step": 1930
|
| 1665 |
},
|
| 1666 |
{
|
| 1667 |
"epoch": 2.108695652173913,
|
| 1668 |
+
"grad_norm": 1.1999317407608032,
|
| 1669 |
"learning_rate": 1.4855072463768116e-05,
|
| 1670 |
+
"loss": 0.3174,
|
| 1671 |
"step": 1940
|
| 1672 |
},
|
| 1673 |
{
|
| 1674 |
"epoch": 2.119565217391304,
|
| 1675 |
+
"grad_norm": 1.1956512928009033,
|
| 1676 |
"learning_rate": 1.4673913043478263e-05,
|
| 1677 |
+
"loss": 0.3281,
|
| 1678 |
"step": 1950
|
| 1679 |
},
|
| 1680 |
{
|
| 1681 |
"epoch": 2.119565217391304,
|
| 1682 |
+
"eval_loss": 0.5320965647697449,
|
| 1683 |
+
"eval_runtime": 10.8261,
|
| 1684 |
+
"eval_samples_per_second": 44.337,
|
| 1685 |
+
"eval_steps_per_second": 2.771,
|
| 1686 |
"step": 1950
|
| 1687 |
},
|
| 1688 |
{
|
| 1689 |
"epoch": 2.130434782608696,
|
| 1690 |
+
"grad_norm": 1.0482760667800903,
|
| 1691 |
"learning_rate": 1.4492753623188407e-05,
|
| 1692 |
+
"loss": 0.3193,
|
| 1693 |
"step": 1960
|
| 1694 |
},
|
| 1695 |
{
|
| 1696 |
"epoch": 2.141304347826087,
|
| 1697 |
+
"grad_norm": 1.72954261302948,
|
| 1698 |
"learning_rate": 1.431159420289855e-05,
|
| 1699 |
+
"loss": 0.3418,
|
| 1700 |
"step": 1970
|
| 1701 |
},
|
| 1702 |
{
|
| 1703 |
"epoch": 2.1521739130434785,
|
| 1704 |
+
"grad_norm": 1.2846759557724,
|
| 1705 |
"learning_rate": 1.4130434782608694e-05,
|
| 1706 |
+
"loss": 0.3274,
|
| 1707 |
"step": 1980
|
| 1708 |
},
|
| 1709 |
{
|
| 1710 |
"epoch": 2.1630434782608696,
|
| 1711 |
+
"grad_norm": 1.2016099691390991,
|
| 1712 |
"learning_rate": 1.3949275362318842e-05,
|
| 1713 |
+
"loss": 0.3305,
|
| 1714 |
"step": 1990
|
| 1715 |
},
|
| 1716 |
{
|
| 1717 |
"epoch": 2.1739130434782608,
|
| 1718 |
+
"grad_norm": 1.1600474119186401,
|
| 1719 |
"learning_rate": 1.3768115942028985e-05,
|
| 1720 |
+
"loss": 0.3424,
|
| 1721 |
"step": 2000
|
| 1722 |
},
|
| 1723 |
{
|
| 1724 |
"epoch": 2.1739130434782608,
|
| 1725 |
+
"eval_loss": 0.5298786163330078,
|
| 1726 |
+
"eval_runtime": 10.8329,
|
| 1727 |
+
"eval_samples_per_second": 44.31,
|
| 1728 |
+
"eval_steps_per_second": 2.769,
|
| 1729 |
"step": 2000
|
| 1730 |
},
|
| 1731 |
{
|
| 1732 |
"epoch": 2.1847826086956523,
|
| 1733 |
+
"grad_norm": 1.2170861959457397,
|
| 1734 |
"learning_rate": 1.3586956521739131e-05,
|
| 1735 |
+
"loss": 0.3024,
|
| 1736 |
"step": 2010
|
| 1737 |
},
|
| 1738 |
{
|
| 1739 |
"epoch": 2.1956521739130435,
|
| 1740 |
+
"grad_norm": 1.1393592357635498,
|
| 1741 |
"learning_rate": 1.3405797101449276e-05,
|
| 1742 |
+
"loss": 0.3211,
|
| 1743 |
"step": 2020
|
| 1744 |
},
|
| 1745 |
{
|
| 1746 |
"epoch": 2.2065217391304346,
|
| 1747 |
+
"grad_norm": 1.1940656900405884,
|
| 1748 |
"learning_rate": 1.3224637681159422e-05,
|
| 1749 |
+
"loss": 0.3157,
|
| 1750 |
"step": 2030
|
| 1751 |
},
|
| 1752 |
{
|
| 1753 |
"epoch": 2.217391304347826,
|
| 1754 |
+
"grad_norm": 1.2777471542358398,
|
| 1755 |
"learning_rate": 1.3043478260869566e-05,
|
| 1756 |
+
"loss": 0.3382,
|
| 1757 |
"step": 2040
|
| 1758 |
},
|
| 1759 |
{
|
| 1760 |
"epoch": 2.2282608695652173,
|
| 1761 |
+
"grad_norm": 1.1014587879180908,
|
| 1762 |
"learning_rate": 1.286231884057971e-05,
|
| 1763 |
+
"loss": 0.3198,
|
| 1764 |
"step": 2050
|
| 1765 |
},
|
| 1766 |
{
|
| 1767 |
"epoch": 2.2282608695652173,
|
| 1768 |
+
"eval_loss": 0.5298696160316467,
|
| 1769 |
+
"eval_runtime": 10.844,
|
| 1770 |
+
"eval_samples_per_second": 44.264,
|
| 1771 |
+
"eval_steps_per_second": 2.767,
|
| 1772 |
"step": 2050
|
| 1773 |
},
|
| 1774 |
{
|
| 1775 |
"epoch": 2.239130434782609,
|
| 1776 |
+
"grad_norm": 1.056643009185791,
|
| 1777 |
"learning_rate": 1.2681159420289857e-05,
|
| 1778 |
+
"loss": 0.317,
|
| 1779 |
"step": 2060
|
| 1780 |
},
|
| 1781 |
{
|
| 1782 |
"epoch": 2.25,
|
| 1783 |
+
"grad_norm": 1.1301910877227783,
|
| 1784 |
"learning_rate": 1.25e-05,
|
| 1785 |
+
"loss": 0.3266,
|
| 1786 |
"step": 2070
|
| 1787 |
},
|
| 1788 |
{
|
| 1789 |
"epoch": 2.260869565217391,
|
| 1790 |
+
"grad_norm": 1.2433290481567383,
|
| 1791 |
"learning_rate": 1.2318840579710146e-05,
|
| 1792 |
+
"loss": 0.3313,
|
| 1793 |
"step": 2080
|
| 1794 |
},
|
| 1795 |
{
|
| 1796 |
"epoch": 2.2717391304347827,
|
| 1797 |
+
"grad_norm": 1.2331655025482178,
|
| 1798 |
"learning_rate": 1.213768115942029e-05,
|
| 1799 |
+
"loss": 0.3353,
|
| 1800 |
"step": 2090
|
| 1801 |
},
|
| 1802 |
{
|
| 1803 |
"epoch": 2.282608695652174,
|
| 1804 |
+
"grad_norm": 1.2137727737426758,
|
| 1805 |
"learning_rate": 1.1956521739130435e-05,
|
| 1806 |
+
"loss": 0.3183,
|
| 1807 |
"step": 2100
|
| 1808 |
},
|
| 1809 |
{
|
| 1810 |
"epoch": 2.282608695652174,
|
| 1811 |
+
"eval_loss": 0.5301353335380554,
|
| 1812 |
+
"eval_runtime": 10.829,
|
| 1813 |
+
"eval_samples_per_second": 44.326,
|
| 1814 |
+
"eval_steps_per_second": 2.77,
|
| 1815 |
"step": 2100
|
| 1816 |
},
|
| 1817 |
{
|
| 1818 |
"epoch": 2.2934782608695654,
|
| 1819 |
+
"grad_norm": 1.0960383415222168,
|
| 1820 |
"learning_rate": 1.177536231884058e-05,
|
| 1821 |
+
"loss": 0.3083,
|
| 1822 |
"step": 2110
|
| 1823 |
},
|
| 1824 |
{
|
| 1825 |
"epoch": 2.3043478260869565,
|
| 1826 |
+
"grad_norm": 1.2978132963180542,
|
| 1827 |
"learning_rate": 1.1594202898550725e-05,
|
| 1828 |
+
"loss": 0.3218,
|
| 1829 |
"step": 2120
|
| 1830 |
},
|
| 1831 |
{
|
| 1832 |
"epoch": 2.3152173913043477,
|
| 1833 |
+
"grad_norm": 1.1214746236801147,
|
| 1834 |
"learning_rate": 1.141304347826087e-05,
|
| 1835 |
+
"loss": 0.3334,
|
| 1836 |
"step": 2130
|
| 1837 |
},
|
| 1838 |
{
|
| 1839 |
"epoch": 2.3260869565217392,
|
| 1840 |
+
"grad_norm": 1.2013393640518188,
|
| 1841 |
"learning_rate": 1.1231884057971016e-05,
|
| 1842 |
+
"loss": 0.3017,
|
| 1843 |
"step": 2140
|
| 1844 |
},
|
| 1845 |
{
|
| 1846 |
"epoch": 2.3369565217391304,
|
| 1847 |
+
"grad_norm": 1.2782713174819946,
|
| 1848 |
"learning_rate": 1.1050724637681161e-05,
|
| 1849 |
+
"loss": 0.3272,
|
| 1850 |
"step": 2150
|
| 1851 |
},
|
| 1852 |
{
|
| 1853 |
"epoch": 2.3369565217391304,
|
| 1854 |
+
"eval_loss": 0.5313724279403687,
|
| 1855 |
+
"eval_runtime": 10.8265,
|
| 1856 |
+
"eval_samples_per_second": 44.336,
|
| 1857 |
+
"eval_steps_per_second": 2.771,
|
| 1858 |
"step": 2150
|
| 1859 |
},
|
| 1860 |
{
|
| 1861 |
"epoch": 2.3478260869565215,
|
| 1862 |
+
"grad_norm": 1.1971640586853027,
|
| 1863 |
"learning_rate": 1.0869565217391305e-05,
|
| 1864 |
+
"loss": 0.3295,
|
| 1865 |
"step": 2160
|
| 1866 |
},
|
| 1867 |
{
|
| 1868 |
"epoch": 2.358695652173913,
|
| 1869 |
+
"grad_norm": 1.1936053037643433,
|
| 1870 |
"learning_rate": 1.068840579710145e-05,
|
| 1871 |
+
"loss": 0.3132,
|
| 1872 |
"step": 2170
|
| 1873 |
},
|
| 1874 |
{
|
| 1875 |
"epoch": 2.369565217391304,
|
| 1876 |
+
"grad_norm": 1.0900537967681885,
|
| 1877 |
"learning_rate": 1.0507246376811594e-05,
|
| 1878 |
+
"loss": 0.3212,
|
| 1879 |
"step": 2180
|
| 1880 |
},
|
| 1881 |
{
|
| 1882 |
"epoch": 2.380434782608696,
|
| 1883 |
+
"grad_norm": 1.4006975889205933,
|
| 1884 |
"learning_rate": 1.032608695652174e-05,
|
| 1885 |
+
"loss": 0.3258,
|
| 1886 |
"step": 2190
|
| 1887 |
},
|
| 1888 |
{
|
| 1889 |
"epoch": 2.391304347826087,
|
| 1890 |
+
"grad_norm": 1.3683350086212158,
|
| 1891 |
"learning_rate": 1.0144927536231885e-05,
|
| 1892 |
+
"loss": 0.3376,
|
| 1893 |
"step": 2200
|
| 1894 |
},
|
| 1895 |
{
|
| 1896 |
"epoch": 2.391304347826087,
|
| 1897 |
+
"eval_loss": 0.5328701734542847,
|
| 1898 |
+
"eval_runtime": 10.8097,
|
| 1899 |
+
"eval_samples_per_second": 44.404,
|
| 1900 |
+
"eval_steps_per_second": 2.775,
|
| 1901 |
"step": 2200
|
| 1902 |
},
|
| 1903 |
{
|
| 1904 |
"epoch": 2.4021739130434785,
|
| 1905 |
+
"grad_norm": 1.120539903640747,
|
| 1906 |
"learning_rate": 9.96376811594203e-06,
|
| 1907 |
+
"loss": 0.3132,
|
| 1908 |
"step": 2210
|
| 1909 |
},
|
| 1910 |
{
|
| 1911 |
"epoch": 2.4130434782608696,
|
| 1912 |
+
"grad_norm": 1.1731290817260742,
|
| 1913 |
"learning_rate": 9.782608695652175e-06,
|
| 1914 |
+
"loss": 0.329,
|
| 1915 |
"step": 2220
|
| 1916 |
},
|
| 1917 |
{
|
| 1918 |
"epoch": 2.4239130434782608,
|
| 1919 |
+
"grad_norm": 1.2622851133346558,
|
| 1920 |
"learning_rate": 9.601449275362319e-06,
|
| 1921 |
+
"loss": 0.3181,
|
| 1922 |
"step": 2230
|
| 1923 |
},
|
| 1924 |
{
|
| 1925 |
"epoch": 2.4347826086956523,
|
| 1926 |
+
"grad_norm": 1.2982534170150757,
|
| 1927 |
"learning_rate": 9.420289855072464e-06,
|
| 1928 |
+
"loss": 0.3177,
|
| 1929 |
"step": 2240
|
| 1930 |
},
|
| 1931 |
{
|
| 1932 |
"epoch": 2.4456521739130435,
|
| 1933 |
+
"grad_norm": 1.2450315952301025,
|
| 1934 |
"learning_rate": 9.239130434782608e-06,
|
| 1935 |
+
"loss": 0.3361,
|
| 1936 |
"step": 2250
|
| 1937 |
},
|
| 1938 |
{
|
| 1939 |
"epoch": 2.4456521739130435,
|
| 1940 |
+
"eval_loss": 0.5312691330909729,
|
| 1941 |
+
"eval_runtime": 10.7859,
|
| 1942 |
+
"eval_samples_per_second": 44.502,
|
| 1943 |
+
"eval_steps_per_second": 2.781,
|
| 1944 |
"step": 2250
|
| 1945 |
},
|
| 1946 |
{
|
| 1947 |
"epoch": 2.4565217391304346,
|
| 1948 |
+
"grad_norm": 1.2270658016204834,
|
| 1949 |
"learning_rate": 9.057971014492753e-06,
|
| 1950 |
+
"loss": 0.3392,
|
| 1951 |
"step": 2260
|
| 1952 |
},
|
| 1953 |
{
|
| 1954 |
"epoch": 2.467391304347826,
|
| 1955 |
+
"grad_norm": 1.313056468963623,
|
| 1956 |
"learning_rate": 8.876811594202899e-06,
|
| 1957 |
+
"loss": 0.3065,
|
| 1958 |
"step": 2270
|
| 1959 |
},
|
| 1960 |
{
|
| 1961 |
"epoch": 2.4782608695652173,
|
| 1962 |
+
"grad_norm": 1.255582332611084,
|
| 1963 |
"learning_rate": 8.695652173913044e-06,
|
| 1964 |
+
"loss": 0.3224,
|
| 1965 |
"step": 2280
|
| 1966 |
},
|
| 1967 |
{
|
| 1968 |
"epoch": 2.489130434782609,
|
| 1969 |
+
"grad_norm": 1.354356050491333,
|
| 1970 |
"learning_rate": 8.51449275362319e-06,
|
| 1971 |
+
"loss": 0.3307,
|
| 1972 |
"step": 2290
|
| 1973 |
},
|
| 1974 |
{
|
| 1975 |
"epoch": 2.5,
|
| 1976 |
+
"grad_norm": 1.2218225002288818,
|
| 1977 |
"learning_rate": 8.333333333333334e-06,
|
| 1978 |
+
"loss": 0.3146,
|
| 1979 |
"step": 2300
|
| 1980 |
},
|
| 1981 |
{
|
| 1982 |
"epoch": 2.5,
|
| 1983 |
+
"eval_loss": 0.5301942825317383,
|
| 1984 |
+
"eval_runtime": 10.778,
|
| 1985 |
+
"eval_samples_per_second": 44.535,
|
| 1986 |
+
"eval_steps_per_second": 2.783,
|
| 1987 |
"step": 2300
|
| 1988 |
},
|
| 1989 |
{
|
| 1990 |
"epoch": 2.5108695652173916,
|
| 1991 |
+
"grad_norm": 1.2889074087142944,
|
| 1992 |
"learning_rate": 8.15217391304348e-06,
|
| 1993 |
+
"loss": 0.3135,
|
| 1994 |
"step": 2310
|
| 1995 |
},
|
| 1996 |
{
|
| 1997 |
"epoch": 2.5217391304347827,
|
| 1998 |
+
"grad_norm": 1.1224515438079834,
|
| 1999 |
"learning_rate": 7.971014492753623e-06,
|
| 2000 |
+
"loss": 0.3227,
|
| 2001 |
"step": 2320
|
| 2002 |
},
|
| 2003 |
{
|
| 2004 |
"epoch": 2.532608695652174,
|
| 2005 |
+
"grad_norm": 1.1914352178573608,
|
| 2006 |
"learning_rate": 7.789855072463769e-06,
|
| 2007 |
+
"loss": 0.3138,
|
| 2008 |
"step": 2330
|
| 2009 |
},
|
| 2010 |
{
|
| 2011 |
"epoch": 2.5434782608695654,
|
| 2012 |
+
"grad_norm": 1.3238486051559448,
|
| 2013 |
"learning_rate": 7.608695652173914e-06,
|
| 2014 |
+
"loss": 0.3168,
|
| 2015 |
"step": 2340
|
| 2016 |
},
|
| 2017 |
{
|
| 2018 |
"epoch": 2.5543478260869565,
|
| 2019 |
+
"grad_norm": 1.3031419515609741,
|
| 2020 |
"learning_rate": 7.427536231884058e-06,
|
| 2021 |
+
"loss": 0.3253,
|
| 2022 |
"step": 2350
|
| 2023 |
},
|
| 2024 |
{
|
| 2025 |
"epoch": 2.5543478260869565,
|
| 2026 |
+
"eval_loss": 0.5280157327651978,
|
| 2027 |
+
"eval_runtime": 10.8003,
|
| 2028 |
+
"eval_samples_per_second": 44.443,
|
| 2029 |
+
"eval_steps_per_second": 2.778,
|
| 2030 |
"step": 2350
|
| 2031 |
},
|
| 2032 |
{
|
| 2033 |
"epoch": 2.5652173913043477,
|
| 2034 |
+
"grad_norm": 1.2570607662200928,
|
| 2035 |
"learning_rate": 7.246376811594203e-06,
|
| 2036 |
+
"loss": 0.3246,
|
| 2037 |
"step": 2360
|
| 2038 |
},
|
| 2039 |
{
|
| 2040 |
"epoch": 2.5760869565217392,
|
| 2041 |
+
"grad_norm": 1.1971008777618408,
|
| 2042 |
"learning_rate": 7.065217391304347e-06,
|
| 2043 |
+
"loss": 0.3142,
|
| 2044 |
"step": 2370
|
| 2045 |
},
|
| 2046 |
{
|
| 2047 |
"epoch": 2.5869565217391304,
|
| 2048 |
+
"grad_norm": 1.2740592956542969,
|
| 2049 |
"learning_rate": 6.884057971014493e-06,
|
| 2050 |
+
"loss": 0.3263,
|
| 2051 |
"step": 2380
|
| 2052 |
},
|
| 2053 |
{
|
| 2054 |
"epoch": 2.5978260869565215,
|
| 2055 |
+
"grad_norm": 1.3141279220581055,
|
| 2056 |
"learning_rate": 6.702898550724638e-06,
|
| 2057 |
+
"loss": 0.3141,
|
| 2058 |
"step": 2390
|
| 2059 |
},
|
| 2060 |
{
|
| 2061 |
"epoch": 2.608695652173913,
|
| 2062 |
+
"grad_norm": 1.3131691217422485,
|
| 2063 |
"learning_rate": 6.521739130434783e-06,
|
| 2064 |
+
"loss": 0.3204,
|
| 2065 |
"step": 2400
|
| 2066 |
},
|
| 2067 |
{
|
| 2068 |
"epoch": 2.608695652173913,
|
| 2069 |
+
"eval_loss": 0.529800295829773,
|
| 2070 |
+
"eval_runtime": 10.7985,
|
| 2071 |
+
"eval_samples_per_second": 44.451,
|
| 2072 |
+
"eval_steps_per_second": 2.778,
|
| 2073 |
"step": 2400
|
| 2074 |
}
|
| 2075 |
],
|
|
|
|
| 2090 |
"attributes": {}
|
| 2091 |
}
|
| 2092 |
},
|
| 2093 |
+
"total_flos": 2.1143048047312896e+17,
|
| 2094 |
"train_batch_size": 16,
|
| 2095 |
"trial_name": null,
|
| 2096 |
"trial_params": null
|
checkpoint-2400/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5816
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:81786d634f359bee447d9c2dad023b92502900c87e9208470ed326b1204c5b1a
|
| 3 |
size 5816
|