Training in progress, epoch 18, checkpoint
Browse files
checkpoint-1458/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 592324828
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5d3f9e216564cbfb7ac9c1bcaacc2faf39380484f261e0f842618827f8b71023
|
| 3 |
size 592324828
|
checkpoint-1458/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1014657786
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:813fbff9c9bce5cd8d17c31202eb9a7b59f8a83b4c184ee9eb2b95eeea40a1fa
|
| 3 |
size 1014657786
|
checkpoint-1458/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 sha256:397d9f0c9659b8c458bbd5c411c44f792c5953742b278f71c3b66563b141c2b2
|
| 3 |
size 14244
|
checkpoint-1458/trainer_state.json
CHANGED
|
@@ -11,824 +11,824 @@
|
|
| 11 |
{
|
| 12 |
"epoch": 1.0,
|
| 13 |
"eval_Claim": {
|
| 14 |
-
"f1-score": 0.
|
| 15 |
-
"precision": 0.
|
| 16 |
-
"recall": 0.
|
| 17 |
-
"support":
|
| 18 |
},
|
| 19 |
"eval_MajorClaim": {
|
| 20 |
-
"f1-score": 0.
|
| 21 |
-
"precision": 0.
|
| 22 |
-
"recall": 0.
|
| 23 |
-
"support":
|
| 24 |
},
|
| 25 |
"eval_O": {
|
| 26 |
-
"f1-score": 0.
|
| 27 |
-
"precision": 0.
|
| 28 |
-
"recall": 0.
|
| 29 |
-
"support":
|
| 30 |
},
|
| 31 |
"eval_Premise": {
|
| 32 |
-
"f1-score": 0.
|
| 33 |
-
"precision": 0.
|
| 34 |
-
"recall": 0.
|
| 35 |
-
"support":
|
| 36 |
},
|
| 37 |
-
"eval_accuracy": 0.
|
| 38 |
-
"eval_loss": 0.
|
| 39 |
"eval_macro avg": {
|
| 40 |
-
"f1-score": 0.
|
| 41 |
-
"precision": 0.
|
| 42 |
-
"recall": 0.
|
| 43 |
-
"support":
|
| 44 |
-
},
|
| 45 |
-
"eval_runtime": 4.
|
| 46 |
-
"eval_samples_per_second": 16.
|
| 47 |
-
"eval_steps_per_second": 2.
|
| 48 |
"eval_weighted avg": {
|
| 49 |
-
"f1-score": 0.
|
| 50 |
-
"precision": 0.
|
| 51 |
-
"recall": 0.
|
| 52 |
-
"support":
|
| 53 |
},
|
| 54 |
"step": 81
|
| 55 |
},
|
| 56 |
{
|
| 57 |
"epoch": 2.0,
|
| 58 |
"eval_Claim": {
|
| 59 |
-
"f1-score": 0.
|
| 60 |
-
"precision": 0.
|
| 61 |
-
"recall": 0.
|
| 62 |
-
"support":
|
| 63 |
},
|
| 64 |
"eval_MajorClaim": {
|
| 65 |
-
"f1-score": 0.
|
| 66 |
-
"precision": 0.
|
| 67 |
-
"recall": 0.
|
| 68 |
-
"support":
|
| 69 |
},
|
| 70 |
"eval_O": {
|
| 71 |
-
"f1-score": 0.
|
| 72 |
-
"precision": 0.
|
| 73 |
-
"recall": 0.
|
| 74 |
-
"support":
|
| 75 |
},
|
| 76 |
"eval_Premise": {
|
| 77 |
-
"f1-score": 0.
|
| 78 |
-
"precision": 0.
|
| 79 |
-
"recall": 0.
|
| 80 |
-
"support":
|
| 81 |
},
|
| 82 |
-
"eval_accuracy": 0.
|
| 83 |
-
"eval_loss": 0.
|
| 84 |
"eval_macro avg": {
|
| 85 |
-
"f1-score": 0.
|
| 86 |
-
"precision": 0.
|
| 87 |
-
"recall": 0.
|
| 88 |
-
"support":
|
| 89 |
-
},
|
| 90 |
-
"eval_runtime": 4.
|
| 91 |
-
"eval_samples_per_second": 16.
|
| 92 |
-
"eval_steps_per_second": 2.
|
| 93 |
"eval_weighted avg": {
|
| 94 |
-
"f1-score": 0.
|
| 95 |
-
"precision": 0.
|
| 96 |
-
"recall": 0.
|
| 97 |
-
"support":
|
| 98 |
},
|
| 99 |
"step": 162
|
| 100 |
},
|
| 101 |
{
|
| 102 |
"epoch": 3.0,
|
| 103 |
"eval_Claim": {
|
| 104 |
-
"f1-score": 0.
|
| 105 |
-
"precision": 0.
|
| 106 |
-
"recall": 0.
|
| 107 |
-
"support":
|
| 108 |
},
|
| 109 |
"eval_MajorClaim": {
|
| 110 |
-
"f1-score": 0.
|
| 111 |
-
"precision": 0.
|
| 112 |
-
"recall": 0.
|
| 113 |
-
"support":
|
| 114 |
},
|
| 115 |
"eval_O": {
|
| 116 |
-
"f1-score": 0.
|
| 117 |
-
"precision": 0.
|
| 118 |
-
"recall": 0.
|
| 119 |
-
"support":
|
| 120 |
},
|
| 121 |
"eval_Premise": {
|
| 122 |
-
"f1-score": 0.
|
| 123 |
-
"precision": 0.
|
| 124 |
-
"recall": 0.
|
| 125 |
-
"support":
|
| 126 |
},
|
| 127 |
-
"eval_accuracy": 0.
|
| 128 |
-
"eval_loss": 0.
|
| 129 |
"eval_macro avg": {
|
| 130 |
-
"f1-score": 0.
|
| 131 |
-
"precision": 0.
|
| 132 |
-
"recall": 0.
|
| 133 |
-
"support":
|
| 134 |
-
},
|
| 135 |
-
"eval_runtime": 4.
|
| 136 |
-
"eval_samples_per_second": 16.
|
| 137 |
-
"eval_steps_per_second": 2.
|
| 138 |
"eval_weighted avg": {
|
| 139 |
-
"f1-score": 0.
|
| 140 |
-
"precision": 0.
|
| 141 |
-
"recall": 0.
|
| 142 |
-
"support":
|
| 143 |
},
|
| 144 |
"step": 243
|
| 145 |
},
|
| 146 |
{
|
| 147 |
"epoch": 4.0,
|
| 148 |
"eval_Claim": {
|
| 149 |
-
"f1-score": 0.
|
| 150 |
-
"precision": 0.
|
| 151 |
-
"recall": 0.
|
| 152 |
-
"support":
|
| 153 |
},
|
| 154 |
"eval_MajorClaim": {
|
| 155 |
-
"f1-score": 0.
|
| 156 |
-
"precision": 0.
|
| 157 |
-
"recall": 0.
|
| 158 |
-
"support":
|
| 159 |
},
|
| 160 |
"eval_O": {
|
| 161 |
-
"f1-score": 0.
|
| 162 |
-
"precision": 0.
|
| 163 |
-
"recall": 0.
|
| 164 |
-
"support":
|
| 165 |
},
|
| 166 |
"eval_Premise": {
|
| 167 |
-
"f1-score": 0.
|
| 168 |
-
"precision": 0.
|
| 169 |
-
"recall": 0.
|
| 170 |
-
"support":
|
| 171 |
},
|
| 172 |
-
"eval_accuracy": 0.
|
| 173 |
-
"eval_loss": 0.
|
| 174 |
"eval_macro avg": {
|
| 175 |
-
"f1-score": 0.
|
| 176 |
-
"precision": 0.
|
| 177 |
-
"recall": 0.
|
| 178 |
-
"support":
|
| 179 |
-
},
|
| 180 |
-
"eval_runtime": 4.
|
| 181 |
-
"eval_samples_per_second": 16.
|
| 182 |
-
"eval_steps_per_second": 2.
|
| 183 |
"eval_weighted avg": {
|
| 184 |
-
"f1-score": 0.
|
| 185 |
-
"precision": 0.
|
| 186 |
-
"recall": 0.
|
| 187 |
-
"support":
|
| 188 |
},
|
| 189 |
"step": 324
|
| 190 |
},
|
| 191 |
{
|
| 192 |
"epoch": 5.0,
|
| 193 |
"eval_Claim": {
|
| 194 |
-
"f1-score": 0.
|
| 195 |
-
"precision": 0.
|
| 196 |
-
"recall": 0.
|
| 197 |
-
"support":
|
| 198 |
},
|
| 199 |
"eval_MajorClaim": {
|
| 200 |
-
"f1-score": 0.
|
| 201 |
-
"precision": 0.
|
| 202 |
-
"recall": 0.
|
| 203 |
-
"support":
|
| 204 |
},
|
| 205 |
"eval_O": {
|
| 206 |
-
"f1-score": 0.
|
| 207 |
-
"precision": 0.
|
| 208 |
-
"recall": 0.
|
| 209 |
-
"support":
|
| 210 |
},
|
| 211 |
"eval_Premise": {
|
| 212 |
-
"f1-score": 0.
|
| 213 |
-
"precision": 0.
|
| 214 |
-
"recall": 0.
|
| 215 |
-
"support":
|
| 216 |
},
|
| 217 |
-
"eval_accuracy": 0.
|
| 218 |
-
"eval_loss": 0.
|
| 219 |
"eval_macro avg": {
|
| 220 |
-
"f1-score": 0.
|
| 221 |
-
"precision": 0.
|
| 222 |
-
"recall": 0.
|
| 223 |
-
"support":
|
| 224 |
-
},
|
| 225 |
-
"eval_runtime": 4.
|
| 226 |
-
"eval_samples_per_second": 16.
|
| 227 |
-
"eval_steps_per_second": 2.
|
| 228 |
"eval_weighted avg": {
|
| 229 |
-
"f1-score": 0.
|
| 230 |
-
"precision": 0.
|
| 231 |
-
"recall": 0.
|
| 232 |
-
"support":
|
| 233 |
},
|
| 234 |
"step": 405
|
| 235 |
},
|
| 236 |
{
|
| 237 |
"epoch": 6.0,
|
| 238 |
"eval_Claim": {
|
| 239 |
-
"f1-score": 0.
|
| 240 |
-
"precision": 0.
|
| 241 |
-
"recall": 0.
|
| 242 |
-
"support":
|
| 243 |
},
|
| 244 |
"eval_MajorClaim": {
|
| 245 |
-
"f1-score": 0.
|
| 246 |
-
"precision": 0.
|
| 247 |
-
"recall": 0.
|
| 248 |
-
"support":
|
| 249 |
},
|
| 250 |
"eval_O": {
|
| 251 |
-
"f1-score": 0.
|
| 252 |
-
"precision": 0.
|
| 253 |
-
"recall": 0.
|
| 254 |
-
"support":
|
| 255 |
},
|
| 256 |
"eval_Premise": {
|
| 257 |
-
"f1-score": 0.
|
| 258 |
-
"precision": 0.
|
| 259 |
-
"recall": 0.
|
| 260 |
-
"support":
|
| 261 |
},
|
| 262 |
-
"eval_accuracy": 0.
|
| 263 |
-
"eval_loss": 0.
|
| 264 |
"eval_macro avg": {
|
| 265 |
-
"f1-score": 0.
|
| 266 |
-
"precision": 0.
|
| 267 |
-
"recall": 0.
|
| 268 |
-
"support":
|
| 269 |
-
},
|
| 270 |
-
"eval_runtime": 4.
|
| 271 |
-
"eval_samples_per_second": 16.
|
| 272 |
-
"eval_steps_per_second": 2.
|
| 273 |
"eval_weighted avg": {
|
| 274 |
-
"f1-score": 0.
|
| 275 |
-
"precision": 0.
|
| 276 |
-
"recall": 0.
|
| 277 |
-
"support":
|
| 278 |
},
|
| 279 |
"step": 486
|
| 280 |
},
|
| 281 |
{
|
| 282 |
"epoch": 6.17,
|
| 283 |
-
"grad_norm":
|
| 284 |
"learning_rate": 1.7530864197530865e-05,
|
| 285 |
-
"loss": 0.
|
| 286 |
"step": 500
|
| 287 |
},
|
| 288 |
{
|
| 289 |
"epoch": 7.0,
|
| 290 |
"eval_Claim": {
|
| 291 |
-
"f1-score": 0.
|
| 292 |
-
"precision": 0.
|
| 293 |
-
"recall": 0.
|
| 294 |
-
"support":
|
| 295 |
},
|
| 296 |
"eval_MajorClaim": {
|
| 297 |
-
"f1-score": 0.
|
| 298 |
-
"precision": 0.
|
| 299 |
-
"recall": 0.
|
| 300 |
-
"support":
|
| 301 |
},
|
| 302 |
"eval_O": {
|
| 303 |
-
"f1-score": 0.
|
| 304 |
-
"precision": 0.
|
| 305 |
-
"recall": 0.
|
| 306 |
-
"support":
|
| 307 |
},
|
| 308 |
"eval_Premise": {
|
| 309 |
-
"f1-score": 0.
|
| 310 |
-
"precision": 0.
|
| 311 |
-
"recall": 0.
|
| 312 |
-
"support":
|
| 313 |
},
|
| 314 |
-
"eval_accuracy": 0.
|
| 315 |
-
"eval_loss": 0.
|
| 316 |
"eval_macro avg": {
|
| 317 |
-
"f1-score": 0.
|
| 318 |
-
"precision": 0.
|
| 319 |
-
"recall": 0.
|
| 320 |
-
"support":
|
| 321 |
-
},
|
| 322 |
-
"eval_runtime": 4.
|
| 323 |
-
"eval_samples_per_second": 16.
|
| 324 |
-
"eval_steps_per_second": 2.
|
| 325 |
"eval_weighted avg": {
|
| 326 |
-
"f1-score": 0.
|
| 327 |
-
"precision": 0.
|
| 328 |
-
"recall": 0.
|
| 329 |
-
"support":
|
| 330 |
},
|
| 331 |
"step": 567
|
| 332 |
},
|
| 333 |
{
|
| 334 |
"epoch": 8.0,
|
| 335 |
"eval_Claim": {
|
| 336 |
-
"f1-score": 0.
|
| 337 |
-
"precision": 0.
|
| 338 |
-
"recall": 0.
|
| 339 |
-
"support":
|
| 340 |
},
|
| 341 |
"eval_MajorClaim": {
|
| 342 |
-
"f1-score": 0.
|
| 343 |
-
"precision": 0.
|
| 344 |
-
"recall": 0.
|
| 345 |
-
"support":
|
| 346 |
},
|
| 347 |
"eval_O": {
|
| 348 |
-
"f1-score": 0.
|
| 349 |
-
"precision": 0.
|
| 350 |
-
"recall": 0.
|
| 351 |
-
"support":
|
| 352 |
},
|
| 353 |
"eval_Premise": {
|
| 354 |
-
"f1-score": 0.
|
| 355 |
-
"precision": 0.
|
| 356 |
-
"recall": 0.
|
| 357 |
-
"support":
|
| 358 |
},
|
| 359 |
-
"eval_accuracy": 0.
|
| 360 |
-
"eval_loss": 0.
|
| 361 |
"eval_macro avg": {
|
| 362 |
-
"f1-score": 0.
|
| 363 |
-
"precision": 0.
|
| 364 |
-
"recall": 0.
|
| 365 |
-
"support":
|
| 366 |
-
},
|
| 367 |
-
"eval_runtime": 4.
|
| 368 |
-
"eval_samples_per_second": 16.
|
| 369 |
-
"eval_steps_per_second": 2.
|
| 370 |
"eval_weighted avg": {
|
| 371 |
-
"f1-score": 0.
|
| 372 |
-
"precision": 0.
|
| 373 |
-
"recall": 0.
|
| 374 |
-
"support":
|
| 375 |
},
|
| 376 |
"step": 648
|
| 377 |
},
|
| 378 |
{
|
| 379 |
"epoch": 9.0,
|
| 380 |
"eval_Claim": {
|
| 381 |
-
"f1-score": 0.
|
| 382 |
-
"precision": 0.
|
| 383 |
-
"recall": 0.
|
| 384 |
-
"support":
|
| 385 |
},
|
| 386 |
"eval_MajorClaim": {
|
| 387 |
-
"f1-score": 0.
|
| 388 |
-
"precision": 0.
|
| 389 |
-
"recall": 0.
|
| 390 |
-
"support":
|
| 391 |
},
|
| 392 |
"eval_O": {
|
| 393 |
-
"f1-score": 0.
|
| 394 |
-
"precision": 0.
|
| 395 |
-
"recall": 0.
|
| 396 |
-
"support":
|
| 397 |
},
|
| 398 |
"eval_Premise": {
|
| 399 |
-
"f1-score": 0.
|
| 400 |
-
"precision": 0.
|
| 401 |
-
"recall": 0.
|
| 402 |
-
"support":
|
| 403 |
},
|
| 404 |
-
"eval_accuracy": 0.
|
| 405 |
-
"eval_loss": 0.
|
| 406 |
"eval_macro avg": {
|
| 407 |
-
"f1-score": 0.
|
| 408 |
-
"precision": 0.
|
| 409 |
-
"recall": 0.
|
| 410 |
-
"support":
|
| 411 |
-
},
|
| 412 |
-
"eval_runtime": 4.
|
| 413 |
-
"eval_samples_per_second": 16.
|
| 414 |
-
"eval_steps_per_second": 2.
|
| 415 |
"eval_weighted avg": {
|
| 416 |
-
"f1-score": 0.
|
| 417 |
-
"precision": 0.
|
| 418 |
-
"recall": 0.
|
| 419 |
-
"support":
|
| 420 |
},
|
| 421 |
"step": 729
|
| 422 |
},
|
| 423 |
{
|
| 424 |
"epoch": 10.0,
|
| 425 |
"eval_Claim": {
|
| 426 |
-
"f1-score": 0.
|
| 427 |
-
"precision": 0.
|
| 428 |
-
"recall": 0.
|
| 429 |
-
"support":
|
| 430 |
},
|
| 431 |
"eval_MajorClaim": {
|
| 432 |
-
"f1-score": 0.
|
| 433 |
-
"precision": 0.
|
| 434 |
-
"recall": 0.
|
| 435 |
-
"support":
|
| 436 |
},
|
| 437 |
"eval_O": {
|
| 438 |
-
"f1-score": 0.
|
| 439 |
-
"precision": 0.
|
| 440 |
-
"recall": 0.
|
| 441 |
-
"support":
|
| 442 |
},
|
| 443 |
"eval_Premise": {
|
| 444 |
-
"f1-score": 0.
|
| 445 |
-
"precision": 0.
|
| 446 |
-
"recall": 0.
|
| 447 |
-
"support":
|
| 448 |
},
|
| 449 |
-
"eval_accuracy": 0.
|
| 450 |
-
"eval_loss": 0.
|
| 451 |
"eval_macro avg": {
|
| 452 |
-
"f1-score": 0.
|
| 453 |
-
"precision": 0.
|
| 454 |
-
"recall": 0.
|
| 455 |
-
"support":
|
| 456 |
-
},
|
| 457 |
-
"eval_runtime": 4.
|
| 458 |
-
"eval_samples_per_second": 16.
|
| 459 |
-
"eval_steps_per_second": 2.
|
| 460 |
"eval_weighted avg": {
|
| 461 |
-
"f1-score": 0.
|
| 462 |
-
"precision": 0.
|
| 463 |
-
"recall": 0.
|
| 464 |
-
"support":
|
| 465 |
},
|
| 466 |
"step": 810
|
| 467 |
},
|
| 468 |
{
|
| 469 |
"epoch": 11.0,
|
| 470 |
"eval_Claim": {
|
| 471 |
-
"f1-score": 0.
|
| 472 |
-
"precision": 0.
|
| 473 |
-
"recall": 0.
|
| 474 |
-
"support":
|
| 475 |
},
|
| 476 |
"eval_MajorClaim": {
|
| 477 |
-
"f1-score": 0.
|
| 478 |
-
"precision": 0.
|
| 479 |
-
"recall": 0.
|
| 480 |
-
"support":
|
| 481 |
},
|
| 482 |
"eval_O": {
|
| 483 |
-
"f1-score": 0.
|
| 484 |
-
"precision": 0.
|
| 485 |
-
"recall": 0.
|
| 486 |
-
"support":
|
| 487 |
},
|
| 488 |
"eval_Premise": {
|
| 489 |
-
"f1-score": 0.
|
| 490 |
-
"precision": 0.
|
| 491 |
-
"recall": 0.
|
| 492 |
-
"support":
|
| 493 |
},
|
| 494 |
-
"eval_accuracy": 0.
|
| 495 |
-
"eval_loss": 0.
|
| 496 |
"eval_macro avg": {
|
| 497 |
-
"f1-score": 0.
|
| 498 |
-
"precision": 0.
|
| 499 |
-
"recall": 0.
|
| 500 |
-
"support":
|
| 501 |
-
},
|
| 502 |
-
"eval_runtime": 4.
|
| 503 |
-
"eval_samples_per_second": 16.
|
| 504 |
-
"eval_steps_per_second": 2.
|
| 505 |
"eval_weighted avg": {
|
| 506 |
-
"f1-score": 0.
|
| 507 |
-
"precision": 0.
|
| 508 |
-
"recall": 0.
|
| 509 |
-
"support":
|
| 510 |
},
|
| 511 |
"step": 891
|
| 512 |
},
|
| 513 |
{
|
| 514 |
"epoch": 12.0,
|
| 515 |
"eval_Claim": {
|
| 516 |
-
"f1-score": 0.
|
| 517 |
-
"precision": 0.
|
| 518 |
-
"recall": 0.
|
| 519 |
-
"support":
|
| 520 |
},
|
| 521 |
"eval_MajorClaim": {
|
| 522 |
-
"f1-score": 0.
|
| 523 |
-
"precision": 0.
|
| 524 |
-
"recall": 0.
|
| 525 |
-
"support":
|
| 526 |
},
|
| 527 |
"eval_O": {
|
| 528 |
-
"f1-score": 0.
|
| 529 |
-
"precision": 0.
|
| 530 |
-
"recall": 0.
|
| 531 |
-
"support":
|
| 532 |
},
|
| 533 |
"eval_Premise": {
|
| 534 |
-
"f1-score": 0.
|
| 535 |
-
"precision": 0.
|
| 536 |
-
"recall": 0.
|
| 537 |
-
"support":
|
| 538 |
},
|
| 539 |
-
"eval_accuracy": 0.
|
| 540 |
-
"eval_loss": 0.
|
| 541 |
"eval_macro avg": {
|
| 542 |
-
"f1-score": 0.
|
| 543 |
-
"precision": 0.
|
| 544 |
-
"recall": 0.
|
| 545 |
-
"support":
|
| 546 |
-
},
|
| 547 |
-
"eval_runtime": 4.
|
| 548 |
-
"eval_samples_per_second": 16.
|
| 549 |
-
"eval_steps_per_second": 2.
|
| 550 |
"eval_weighted avg": {
|
| 551 |
-
"f1-score": 0.
|
| 552 |
-
"precision": 0.
|
| 553 |
-
"recall": 0.
|
| 554 |
-
"support":
|
| 555 |
},
|
| 556 |
"step": 972
|
| 557 |
},
|
| 558 |
{
|
| 559 |
"epoch": 12.35,
|
| 560 |
-
"grad_norm":
|
| 561 |
"learning_rate": 1.506172839506173e-05,
|
| 562 |
-
"loss": 0.
|
| 563 |
"step": 1000
|
| 564 |
},
|
| 565 |
{
|
| 566 |
"epoch": 13.0,
|
| 567 |
"eval_Claim": {
|
| 568 |
-
"f1-score": 0.
|
| 569 |
-
"precision": 0.
|
| 570 |
-
"recall": 0.
|
| 571 |
-
"support":
|
| 572 |
},
|
| 573 |
"eval_MajorClaim": {
|
| 574 |
-
"f1-score": 0.
|
| 575 |
-
"precision": 0.
|
| 576 |
-
"recall": 0.
|
| 577 |
-
"support":
|
| 578 |
},
|
| 579 |
"eval_O": {
|
| 580 |
-
"f1-score": 0.
|
| 581 |
-
"precision": 0.
|
| 582 |
-
"recall": 0.
|
| 583 |
-
"support":
|
| 584 |
},
|
| 585 |
"eval_Premise": {
|
| 586 |
-
"f1-score": 0.
|
| 587 |
-
"precision": 0.
|
| 588 |
-
"recall": 0.
|
| 589 |
-
"support":
|
| 590 |
},
|
| 591 |
-
"eval_accuracy": 0.
|
| 592 |
-
"eval_loss": 0.
|
| 593 |
"eval_macro avg": {
|
| 594 |
-
"f1-score": 0.
|
| 595 |
-
"precision": 0.
|
| 596 |
-
"recall": 0.
|
| 597 |
-
"support":
|
| 598 |
-
},
|
| 599 |
-
"eval_runtime": 4.
|
| 600 |
-
"eval_samples_per_second": 16.
|
| 601 |
-
"eval_steps_per_second": 2.
|
| 602 |
"eval_weighted avg": {
|
| 603 |
-
"f1-score": 0.
|
| 604 |
-
"precision": 0.
|
| 605 |
-
"recall": 0.
|
| 606 |
-
"support":
|
| 607 |
},
|
| 608 |
"step": 1053
|
| 609 |
},
|
| 610 |
{
|
| 611 |
"epoch": 14.0,
|
| 612 |
"eval_Claim": {
|
| 613 |
-
"f1-score": 0.
|
| 614 |
-
"precision": 0.
|
| 615 |
-
"recall": 0.
|
| 616 |
-
"support":
|
| 617 |
},
|
| 618 |
"eval_MajorClaim": {
|
| 619 |
-
"f1-score": 0.
|
| 620 |
-
"precision": 0.
|
| 621 |
-
"recall": 0.
|
| 622 |
-
"support":
|
| 623 |
},
|
| 624 |
"eval_O": {
|
| 625 |
-
"f1-score": 0.
|
| 626 |
-
"precision": 0.
|
| 627 |
-
"recall": 0.
|
| 628 |
-
"support":
|
| 629 |
},
|
| 630 |
"eval_Premise": {
|
| 631 |
-
"f1-score": 0.
|
| 632 |
-
"precision": 0.
|
| 633 |
-
"recall": 0.
|
| 634 |
-
"support":
|
| 635 |
},
|
| 636 |
-
"eval_accuracy": 0.
|
| 637 |
-
"eval_loss": 0.
|
| 638 |
"eval_macro avg": {
|
| 639 |
-
"f1-score": 0.
|
| 640 |
-
"precision": 0.
|
| 641 |
-
"recall": 0.
|
| 642 |
-
"support":
|
| 643 |
-
},
|
| 644 |
-
"eval_runtime": 4.
|
| 645 |
-
"eval_samples_per_second": 16.
|
| 646 |
-
"eval_steps_per_second": 2.
|
| 647 |
"eval_weighted avg": {
|
| 648 |
-
"f1-score": 0.
|
| 649 |
-
"precision": 0.
|
| 650 |
-
"recall": 0.
|
| 651 |
-
"support":
|
| 652 |
},
|
| 653 |
"step": 1134
|
| 654 |
},
|
| 655 |
{
|
| 656 |
"epoch": 15.0,
|
| 657 |
"eval_Claim": {
|
| 658 |
-
"f1-score": 0.
|
| 659 |
-
"precision": 0.
|
| 660 |
-
"recall": 0.
|
| 661 |
-
"support":
|
| 662 |
},
|
| 663 |
"eval_MajorClaim": {
|
| 664 |
-
"f1-score": 0.
|
| 665 |
-
"precision": 0.
|
| 666 |
-
"recall": 0.
|
| 667 |
-
"support":
|
| 668 |
},
|
| 669 |
"eval_O": {
|
| 670 |
-
"f1-score": 0.
|
| 671 |
-
"precision": 0.
|
| 672 |
-
"recall": 0.
|
| 673 |
-
"support":
|
| 674 |
},
|
| 675 |
"eval_Premise": {
|
| 676 |
-
"f1-score": 0.
|
| 677 |
-
"precision": 0.
|
| 678 |
-
"recall": 0.
|
| 679 |
-
"support":
|
| 680 |
},
|
| 681 |
-
"eval_accuracy": 0.
|
| 682 |
-
"eval_loss":
|
| 683 |
"eval_macro avg": {
|
| 684 |
-
"f1-score": 0.
|
| 685 |
-
"precision": 0.
|
| 686 |
-
"recall": 0.
|
| 687 |
-
"support":
|
| 688 |
-
},
|
| 689 |
-
"eval_runtime": 4.
|
| 690 |
-
"eval_samples_per_second": 16.
|
| 691 |
-
"eval_steps_per_second": 2.
|
| 692 |
"eval_weighted avg": {
|
| 693 |
-
"f1-score": 0.
|
| 694 |
-
"precision": 0.
|
| 695 |
-
"recall": 0.
|
| 696 |
-
"support":
|
| 697 |
},
|
| 698 |
"step": 1215
|
| 699 |
},
|
| 700 |
{
|
| 701 |
"epoch": 16.0,
|
| 702 |
"eval_Claim": {
|
| 703 |
-
"f1-score": 0.
|
| 704 |
-
"precision": 0.
|
| 705 |
-
"recall": 0.
|
| 706 |
-
"support":
|
| 707 |
},
|
| 708 |
"eval_MajorClaim": {
|
| 709 |
-
"f1-score": 0.
|
| 710 |
-
"precision": 0.
|
| 711 |
-
"recall": 0.
|
| 712 |
-
"support":
|
| 713 |
},
|
| 714 |
"eval_O": {
|
| 715 |
-
"f1-score": 0.
|
| 716 |
-
"precision": 0.
|
| 717 |
-
"recall": 0.
|
| 718 |
-
"support":
|
| 719 |
},
|
| 720 |
"eval_Premise": {
|
| 721 |
-
"f1-score": 0.
|
| 722 |
-
"precision": 0.
|
| 723 |
-
"recall": 0.
|
| 724 |
-
"support":
|
| 725 |
},
|
| 726 |
-
"eval_accuracy": 0.
|
| 727 |
-
"eval_loss": 0.
|
| 728 |
"eval_macro avg": {
|
| 729 |
-
"f1-score": 0.
|
| 730 |
-
"precision": 0.
|
| 731 |
-
"recall": 0.
|
| 732 |
-
"support":
|
| 733 |
-
},
|
| 734 |
-
"eval_runtime": 4.
|
| 735 |
-
"eval_samples_per_second": 16.
|
| 736 |
-
"eval_steps_per_second": 2.
|
| 737 |
"eval_weighted avg": {
|
| 738 |
-
"f1-score": 0.
|
| 739 |
-
"precision": 0.
|
| 740 |
-
"recall": 0.
|
| 741 |
-
"support":
|
| 742 |
},
|
| 743 |
"step": 1296
|
| 744 |
},
|
| 745 |
{
|
| 746 |
"epoch": 17.0,
|
| 747 |
"eval_Claim": {
|
| 748 |
-
"f1-score": 0.
|
| 749 |
-
"precision": 0.
|
| 750 |
-
"recall": 0.
|
| 751 |
-
"support":
|
| 752 |
},
|
| 753 |
"eval_MajorClaim": {
|
| 754 |
-
"f1-score": 0.
|
| 755 |
-
"precision": 0.
|
| 756 |
-
"recall": 0.
|
| 757 |
-
"support":
|
| 758 |
},
|
| 759 |
"eval_O": {
|
| 760 |
-
"f1-score": 0.
|
| 761 |
-
"precision": 0.
|
| 762 |
-
"recall": 0.
|
| 763 |
-
"support":
|
| 764 |
},
|
| 765 |
"eval_Premise": {
|
| 766 |
-
"f1-score": 0.
|
| 767 |
-
"precision": 0.
|
| 768 |
-
"recall": 0.
|
| 769 |
-
"support":
|
| 770 |
},
|
| 771 |
-
"eval_accuracy": 0.
|
| 772 |
-
"eval_loss": 0.
|
| 773 |
"eval_macro avg": {
|
| 774 |
-
"f1-score": 0.
|
| 775 |
-
"precision": 0.
|
| 776 |
-
"recall": 0.
|
| 777 |
-
"support":
|
| 778 |
-
},
|
| 779 |
-
"eval_runtime": 4.
|
| 780 |
-
"eval_samples_per_second": 16.
|
| 781 |
-
"eval_steps_per_second": 2.
|
| 782 |
"eval_weighted avg": {
|
| 783 |
-
"f1-score": 0.
|
| 784 |
-
"precision": 0.
|
| 785 |
-
"recall": 0.
|
| 786 |
-
"support":
|
| 787 |
},
|
| 788 |
"step": 1377
|
| 789 |
},
|
| 790 |
{
|
| 791 |
"epoch": 18.0,
|
| 792 |
"eval_Claim": {
|
| 793 |
-
"f1-score": 0.
|
| 794 |
-
"precision": 0.
|
| 795 |
-
"recall": 0.
|
| 796 |
-
"support":
|
| 797 |
},
|
| 798 |
"eval_MajorClaim": {
|
| 799 |
-
"f1-score": 0.
|
| 800 |
-
"precision": 0.
|
| 801 |
-
"recall": 0.
|
| 802 |
-
"support":
|
| 803 |
},
|
| 804 |
"eval_O": {
|
| 805 |
-
"f1-score": 0.
|
| 806 |
-
"precision": 0.
|
| 807 |
-
"recall": 0.
|
| 808 |
-
"support":
|
| 809 |
},
|
| 810 |
"eval_Premise": {
|
| 811 |
-
"f1-score": 0.
|
| 812 |
-
"precision": 0.
|
| 813 |
-
"recall": 0.
|
| 814 |
-
"support":
|
| 815 |
},
|
| 816 |
-
"eval_accuracy": 0.
|
| 817 |
-
"eval_loss": 0.
|
| 818 |
"eval_macro avg": {
|
| 819 |
-
"f1-score": 0.
|
| 820 |
-
"precision": 0.
|
| 821 |
-
"recall": 0.
|
| 822 |
-
"support":
|
| 823 |
-
},
|
| 824 |
-
"eval_runtime": 4.
|
| 825 |
-
"eval_samples_per_second": 16.
|
| 826 |
-
"eval_steps_per_second": 2.
|
| 827 |
"eval_weighted avg": {
|
| 828 |
-
"f1-score": 0.
|
| 829 |
-
"precision": 0.
|
| 830 |
-
"recall": 0.
|
| 831 |
-
"support":
|
| 832 |
},
|
| 833 |
"step": 1458
|
| 834 |
}
|
|
@@ -838,7 +838,7 @@
|
|
| 838 |
"num_input_tokens_seen": 0,
|
| 839 |
"num_train_epochs": 50,
|
| 840 |
"save_steps": 500,
|
| 841 |
-
"total_flos":
|
| 842 |
"train_batch_size": 4,
|
| 843 |
"trial_name": null,
|
| 844 |
"trial_params": null
|
|
|
|
| 11 |
{
|
| 12 |
"epoch": 1.0,
|
| 13 |
"eval_Claim": {
|
| 14 |
+
"f1-score": 0.4888068880688806,
|
| 15 |
+
"precision": 0.6228840125391849,
|
| 16 |
+
"recall": 0.40222672064777326,
|
| 17 |
+
"support": 4940.0
|
| 18 |
},
|
| 19 |
"eval_MajorClaim": {
|
| 20 |
+
"f1-score": 0.7325278370054489,
|
| 21 |
+
"precision": 0.7604525332021643,
|
| 22 |
+
"recall": 0.706581352833638,
|
| 23 |
+
"support": 2188.0
|
| 24 |
},
|
| 25 |
"eval_O": {
|
| 26 |
+
"f1-score": 0.8634848138844484,
|
| 27 |
+
"precision": 0.827613377692173,
|
| 28 |
+
"recall": 0.902606702950444,
|
| 29 |
+
"support": 10473.0
|
| 30 |
},
|
| 31 |
"eval_Premise": {
|
| 32 |
+
"f1-score": 0.8792819197655248,
|
| 33 |
+
"precision": 0.8543458914268763,
|
| 34 |
+
"recall": 0.9057173407132524,
|
| 35 |
+
"support": 15899.0
|
| 36 |
},
|
| 37 |
+
"eval_accuracy": 0.8174925373134329,
|
| 38 |
+
"eval_loss": 0.49806877970695496,
|
| 39 |
"eval_macro avg": {
|
| 40 |
+
"f1-score": 0.7410253646810757,
|
| 41 |
+
"precision": 0.7663239537150996,
|
| 42 |
+
"recall": 0.7292830292862769,
|
| 43 |
+
"support": 33500.0
|
| 44 |
+
},
|
| 45 |
+
"eval_runtime": 4.9194,
|
| 46 |
+
"eval_samples_per_second": 16.465,
|
| 47 |
+
"eval_steps_per_second": 2.236,
|
| 48 |
"eval_weighted avg": {
|
| 49 |
+
"f1-score": 0.8071778099281224,
|
| 50 |
+
"precision": 0.80572410140167,
|
| 51 |
+
"recall": 0.8174925373134329,
|
| 52 |
+
"support": 33500.0
|
| 53 |
},
|
| 54 |
"step": 81
|
| 55 |
},
|
| 56 |
{
|
| 57 |
"epoch": 2.0,
|
| 58 |
"eval_Claim": {
|
| 59 |
+
"f1-score": 0.5993816254416962,
|
| 60 |
+
"precision": 0.6593780369290574,
|
| 61 |
+
"recall": 0.5493927125506073,
|
| 62 |
+
"support": 4940.0
|
| 63 |
},
|
| 64 |
"eval_MajorClaim": {
|
| 65 |
+
"f1-score": 0.8017817371937639,
|
| 66 |
+
"precision": 0.7197382769901853,
|
| 67 |
+
"recall": 0.9049360146252285,
|
| 68 |
+
"support": 2188.0
|
| 69 |
},
|
| 70 |
"eval_O": {
|
| 71 |
+
"f1-score": 0.9058997050147494,
|
| 72 |
+
"precision": 0.9337184554575859,
|
| 73 |
+
"recall": 0.8796906330564308,
|
| 74 |
+
"support": 10473.0
|
| 75 |
},
|
| 76 |
"eval_Premise": {
|
| 77 |
+
"f1-score": 0.8854737486606459,
|
| 78 |
+
"precision": 0.862579028987236,
|
| 79 |
+
"recall": 0.9096169570413234,
|
| 80 |
+
"support": 15899.0
|
| 81 |
},
|
| 82 |
+
"eval_accuracy": 0.8468358208955223,
|
| 83 |
+
"eval_loss": 0.4562840759754181,
|
| 84 |
"eval_macro avg": {
|
| 85 |
+
"f1-score": 0.7981342040777137,
|
| 86 |
+
"precision": 0.7938534495910161,
|
| 87 |
+
"recall": 0.8109090793183975,
|
| 88 |
+
"support": 33500.0
|
| 89 |
+
},
|
| 90 |
+
"eval_runtime": 4.904,
|
| 91 |
+
"eval_samples_per_second": 16.517,
|
| 92 |
+
"eval_steps_per_second": 2.243,
|
| 93 |
"eval_weighted avg": {
|
| 94 |
+
"f1-score": 0.8442053257085675,
|
| 95 |
+
"precision": 0.8455251408465503,
|
| 96 |
+
"recall": 0.8468358208955223,
|
| 97 |
+
"support": 33500.0
|
| 98 |
},
|
| 99 |
"step": 162
|
| 100 |
},
|
| 101 |
{
|
| 102 |
"epoch": 3.0,
|
| 103 |
"eval_Claim": {
|
| 104 |
+
"f1-score": 0.6235462150581514,
|
| 105 |
+
"precision": 0.6285479226655697,
|
| 106 |
+
"recall": 0.6186234817813765,
|
| 107 |
+
"support": 4940.0
|
| 108 |
},
|
| 109 |
"eval_MajorClaim": {
|
| 110 |
+
"f1-score": 0.8338848444738584,
|
| 111 |
+
"precision": 0.8059701492537313,
|
| 112 |
+
"recall": 0.8638025594149908,
|
| 113 |
+
"support": 2188.0
|
| 114 |
},
|
| 115 |
"eval_O": {
|
| 116 |
+
"f1-score": 0.9066250826953974,
|
| 117 |
+
"precision": 0.8974646833193002,
|
| 118 |
+
"recall": 0.9159744103886184,
|
| 119 |
+
"support": 10473.0
|
| 120 |
},
|
| 121 |
"eval_Premise": {
|
| 122 |
+
"f1-score": 0.8827730692315017,
|
| 123 |
+
"precision": 0.8911176621379133,
|
| 124 |
+
"recall": 0.8745833071262343,
|
| 125 |
+
"support": 15899.0
|
| 126 |
},
|
| 127 |
+
"eval_accuracy": 0.8490746268656716,
|
| 128 |
+
"eval_loss": 0.43820467591285706,
|
| 129 |
"eval_macro avg": {
|
| 130 |
+
"f1-score": 0.8117073028647273,
|
| 131 |
+
"precision": 0.8057751043441286,
|
| 132 |
+
"recall": 0.818245939677805,
|
| 133 |
+
"support": 33500.0
|
| 134 |
+
},
|
| 135 |
+
"eval_runtime": 4.9179,
|
| 136 |
+
"eval_samples_per_second": 16.47,
|
| 137 |
+
"eval_steps_per_second": 2.237,
|
| 138 |
"eval_weighted avg": {
|
| 139 |
+
"f1-score": 0.8488105033097496,
|
| 140 |
+
"precision": 0.8488213959184715,
|
| 141 |
+
"recall": 0.8490746268656716,
|
| 142 |
+
"support": 33500.0
|
| 143 |
},
|
| 144 |
"step": 243
|
| 145 |
},
|
| 146 |
{
|
| 147 |
"epoch": 4.0,
|
| 148 |
"eval_Claim": {
|
| 149 |
+
"f1-score": 0.6415287144900879,
|
| 150 |
+
"precision": 0.6477507222451506,
|
| 151 |
+
"recall": 0.6354251012145749,
|
| 152 |
+
"support": 4940.0
|
| 153 |
},
|
| 154 |
"eval_MajorClaim": {
|
| 155 |
+
"f1-score": 0.8005126014523707,
|
| 156 |
+
"precision": 0.7514033680834001,
|
| 157 |
+
"recall": 0.856489945155393,
|
| 158 |
+
"support": 2188.0
|
| 159 |
},
|
| 160 |
"eval_O": {
|
| 161 |
+
"f1-score": 0.9065169636319258,
|
| 162 |
+
"precision": 0.9273871354374751,
|
| 163 |
+
"recall": 0.8865654540246348,
|
| 164 |
+
"support": 10473.0
|
| 165 |
},
|
| 166 |
"eval_Premise": {
|
| 167 |
+
"f1-score": 0.8932505382719131,
|
| 168 |
+
"precision": 0.8863636363636364,
|
| 169 |
+
"recall": 0.9002452984464432,
|
| 170 |
+
"support": 15899.0
|
| 171 |
},
|
| 172 |
+
"eval_accuracy": 0.8540597014925373,
|
| 173 |
+
"eval_loss": 0.4749625325202942,
|
| 174 |
"eval_macro avg": {
|
| 175 |
+
"f1-score": 0.8104522044615743,
|
| 176 |
+
"precision": 0.8032262155324155,
|
| 177 |
+
"recall": 0.8196814497102615,
|
| 178 |
+
"support": 33500.0
|
| 179 |
+
},
|
| 180 |
+
"eval_runtime": 4.8972,
|
| 181 |
+
"eval_samples_per_second": 16.54,
|
| 182 |
+
"eval_steps_per_second": 2.246,
|
| 183 |
"eval_weighted avg": {
|
| 184 |
+
"f1-score": 0.8542213698406307,
|
| 185 |
+
"precision": 0.8551874645146165,
|
| 186 |
+
"recall": 0.8540597014925373,
|
| 187 |
+
"support": 33500.0
|
| 188 |
},
|
| 189 |
"step": 324
|
| 190 |
},
|
| 191 |
{
|
| 192 |
"epoch": 5.0,
|
| 193 |
"eval_Claim": {
|
| 194 |
+
"f1-score": 0.6099687080911935,
|
| 195 |
+
"precision": 0.6808882235528942,
|
| 196 |
+
"recall": 0.5524291497975709,
|
| 197 |
+
"support": 4940.0
|
| 198 |
},
|
| 199 |
"eval_MajorClaim": {
|
| 200 |
+
"f1-score": 0.8315018315018317,
|
| 201 |
+
"precision": 0.8330275229357799,
|
| 202 |
+
"recall": 0.829981718464351,
|
| 203 |
+
"support": 2188.0
|
| 204 |
},
|
| 205 |
"eval_O": {
|
| 206 |
+
"f1-score": 0.9103454839630722,
|
| 207 |
+
"precision": 0.9074091642159188,
|
| 208 |
+
"recall": 0.9133008689009835,
|
| 209 |
+
"support": 10473.0
|
| 210 |
},
|
| 211 |
"eval_Premise": {
|
| 212 |
+
"f1-score": 0.8913988368533824,
|
| 213 |
+
"precision": 0.8682249120505635,
|
| 214 |
+
"recall": 0.915843763758727,
|
| 215 |
+
"support": 15899.0
|
| 216 |
},
|
| 217 |
+
"eval_accuracy": 0.8558507462686568,
|
| 218 |
+
"eval_loss": 0.5162495374679565,
|
| 219 |
"eval_macro avg": {
|
| 220 |
+
"f1-score": 0.8108037151023699,
|
| 221 |
+
"precision": 0.8223874556887891,
|
| 222 |
+
"recall": 0.8028888752304081,
|
| 223 |
+
"support": 33500.0
|
| 224 |
+
},
|
| 225 |
+
"eval_runtime": 4.9413,
|
| 226 |
+
"eval_samples_per_second": 16.392,
|
| 227 |
+
"eval_steps_per_second": 2.226,
|
| 228 |
"eval_weighted avg": {
|
| 229 |
+
"f1-score": 0.8519095458499607,
|
| 230 |
+
"precision": 0.8505509283002989,
|
| 231 |
+
"recall": 0.8558507462686568,
|
| 232 |
+
"support": 33500.0
|
| 233 |
},
|
| 234 |
"step": 405
|
| 235 |
},
|
| 236 |
{
|
| 237 |
"epoch": 6.0,
|
| 238 |
"eval_Claim": {
|
| 239 |
+
"f1-score": 0.646279703934554,
|
| 240 |
+
"precision": 0.6227477477477478,
|
| 241 |
+
"recall": 0.6716599190283401,
|
| 242 |
+
"support": 4940.0
|
| 243 |
},
|
| 244 |
"eval_MajorClaim": {
|
| 245 |
+
"f1-score": 0.8414067684140676,
|
| 246 |
+
"precision": 0.8152593227603944,
|
| 247 |
+
"recall": 0.8692870201096892,
|
| 248 |
+
"support": 2188.0
|
| 249 |
},
|
| 250 |
"eval_O": {
|
| 251 |
+
"f1-score": 0.9112506693929215,
|
| 252 |
+
"precision": 0.9295788637266588,
|
| 253 |
+
"recall": 0.8936312422419556,
|
| 254 |
+
"support": 10473.0
|
| 255 |
},
|
| 256 |
"eval_Premise": {
|
| 257 |
+
"f1-score": 0.8861383012314494,
|
| 258 |
+
"precision": 0.8897343224906474,
|
| 259 |
+
"recall": 0.8825712308950249,
|
| 260 |
+
"support": 15899.0
|
| 261 |
},
|
| 262 |
+
"eval_accuracy": 0.8540597014925373,
|
| 263 |
+
"eval_loss": 0.552895724773407,
|
| 264 |
"eval_macro avg": {
|
| 265 |
+
"f1-score": 0.8212688607432481,
|
| 266 |
+
"precision": 0.8143300641813621,
|
| 267 |
+
"recall": 0.8292873530687525,
|
| 268 |
+
"support": 33500.0
|
| 269 |
+
},
|
| 270 |
+
"eval_runtime": 4.9336,
|
| 271 |
+
"eval_samples_per_second": 16.418,
|
| 272 |
+
"eval_steps_per_second": 2.23,
|
| 273 |
"eval_weighted avg": {
|
| 274 |
+
"f1-score": 0.8556973390614198,
|
| 275 |
+
"precision": 0.8579560210496036,
|
| 276 |
+
"recall": 0.8540597014925373,
|
| 277 |
+
"support": 33500.0
|
| 278 |
},
|
| 279 |
"step": 486
|
| 280 |
},
|
| 281 |
{
|
| 282 |
"epoch": 6.17,
|
| 283 |
+
"grad_norm": 9.790245056152344,
|
| 284 |
"learning_rate": 1.7530864197530865e-05,
|
| 285 |
+
"loss": 0.3328,
|
| 286 |
"step": 500
|
| 287 |
},
|
| 288 |
{
|
| 289 |
"epoch": 7.0,
|
| 290 |
"eval_Claim": {
|
| 291 |
+
"f1-score": 0.6202600808654791,
|
| 292 |
+
"precision": 0.6739491807171694,
|
| 293 |
+
"recall": 0.5744939271255061,
|
| 294 |
+
"support": 4940.0
|
| 295 |
},
|
| 296 |
"eval_MajorClaim": {
|
| 297 |
+
"f1-score": 0.8670041417395307,
|
| 298 |
+
"precision": 0.8730305838739574,
|
| 299 |
+
"recall": 0.8610603290676416,
|
| 300 |
+
"support": 2188.0
|
| 301 |
},
|
| 302 |
"eval_O": {
|
| 303 |
+
"f1-score": 0.9109892729439809,
|
| 304 |
+
"precision": 0.9097314797181489,
|
| 305 |
+
"recall": 0.9122505490308412,
|
| 306 |
+
"support": 10473.0
|
| 307 |
},
|
| 308 |
"eval_Premise": {
|
| 309 |
+
"f1-score": 0.8872356123954747,
|
| 310 |
+
"precision": 0.8677611401767996,
|
| 311 |
+
"recall": 0.9076042518397384,
|
| 312 |
+
"support": 15899.0
|
| 313 |
},
|
| 314 |
+
"eval_accuracy": 0.8568955223880597,
|
| 315 |
+
"eval_loss": 0.5894299149513245,
|
| 316 |
"eval_macro avg": {
|
| 317 |
+
"f1-score": 0.8213722769861164,
|
| 318 |
+
"precision": 0.8311180961215189,
|
| 319 |
+
"recall": 0.8138522642659318,
|
| 320 |
+
"support": 33500.0
|
| 321 |
+
},
|
| 322 |
+
"eval_runtime": 4.9037,
|
| 323 |
+
"eval_samples_per_second": 16.518,
|
| 324 |
+
"eval_steps_per_second": 2.243,
|
| 325 |
"eval_weighted avg": {
|
| 326 |
+
"f1-score": 0.8539713289140156,
|
| 327 |
+
"precision": 0.8526463291050193,
|
| 328 |
+
"recall": 0.8568955223880597,
|
| 329 |
+
"support": 33500.0
|
| 330 |
},
|
| 331 |
"step": 567
|
| 332 |
},
|
| 333 |
{
|
| 334 |
"epoch": 8.0,
|
| 335 |
"eval_Claim": {
|
| 336 |
+
"f1-score": 0.6441500279902966,
|
| 337 |
+
"precision": 0.5974385600553825,
|
| 338 |
+
"recall": 0.6987854251012146,
|
| 339 |
+
"support": 4940.0
|
| 340 |
},
|
| 341 |
"eval_MajorClaim": {
|
| 342 |
+
"f1-score": 0.834510811389424,
|
| 343 |
+
"precision": 0.7849375755134917,
|
| 344 |
+
"recall": 0.8907678244972578,
|
| 345 |
+
"support": 2188.0
|
| 346 |
},
|
| 347 |
"eval_O": {
|
| 348 |
+
"f1-score": 0.9059161060546101,
|
| 349 |
+
"precision": 0.9398542543364466,
|
| 350 |
+
"recall": 0.874343550081161,
|
| 351 |
+
"support": 10473.0
|
| 352 |
},
|
| 353 |
"eval_Premise": {
|
| 354 |
+
"f1-score": 0.8801401497053671,
|
| 355 |
+
"precision": 0.8915849251419721,
|
| 356 |
+
"recall": 0.8689854707843261,
|
| 357 |
+
"support": 15899.0
|
| 358 |
},
|
| 359 |
+
"eval_accuracy": 0.8469850746268657,
|
| 360 |
+
"eval_loss": 0.5878348350524902,
|
| 361 |
"eval_macro avg": {
|
| 362 |
+
"f1-score": 0.8161792737849245,
|
| 363 |
+
"precision": 0.8034538287618231,
|
| 364 |
+
"recall": 0.8332205676159898,
|
| 365 |
+
"support": 33500.0
|
| 366 |
+
},
|
| 367 |
+
"eval_runtime": 4.9086,
|
| 368 |
+
"eval_samples_per_second": 16.502,
|
| 369 |
+
"eval_steps_per_second": 2.241,
|
| 370 |
"eval_weighted avg": {
|
| 371 |
+
"f1-score": 0.8504184600736624,
|
| 372 |
+
"precision": 0.8563340964894008,
|
| 373 |
+
"recall": 0.8469850746268657,
|
| 374 |
+
"support": 33500.0
|
| 375 |
},
|
| 376 |
"step": 648
|
| 377 |
},
|
| 378 |
{
|
| 379 |
"epoch": 9.0,
|
| 380 |
"eval_Claim": {
|
| 381 |
+
"f1-score": 0.6323094193285029,
|
| 382 |
+
"precision": 0.6375797489195307,
|
| 383 |
+
"recall": 0.6271255060728745,
|
| 384 |
+
"support": 4940.0
|
| 385 |
},
|
| 386 |
"eval_MajorClaim": {
|
| 387 |
+
"f1-score": 0.8525914292124747,
|
| 388 |
+
"precision": 0.8373732921992068,
|
| 389 |
+
"recall": 0.8683729433272395,
|
| 390 |
+
"support": 2188.0
|
| 391 |
},
|
| 392 |
"eval_O": {
|
| 393 |
+
"f1-score": 0.9054132151801194,
|
| 394 |
+
"precision": 0.9134194927606647,
|
| 395 |
+
"recall": 0.8975460708488494,
|
| 396 |
+
"support": 10473.0
|
| 397 |
},
|
| 398 |
"eval_Premise": {
|
| 399 |
+
"f1-score": 0.8888055034396498,
|
| 400 |
+
"precision": 0.883775884584292,
|
| 401 |
+
"recall": 0.8938926976539405,
|
| 402 |
+
"support": 15899.0
|
| 403 |
},
|
| 404 |
+
"eval_accuracy": 0.8540298507462687,
|
| 405 |
+
"eval_loss": 0.7043101191520691,
|
| 406 |
"eval_macro avg": {
|
| 407 |
+
"f1-score": 0.8197798917901866,
|
| 408 |
+
"precision": 0.8180371046159236,
|
| 409 |
+
"recall": 0.821734304475726,
|
| 410 |
+
"support": 33500.0
|
| 411 |
+
},
|
| 412 |
+
"eval_runtime": 4.935,
|
| 413 |
+
"eval_samples_per_second": 16.414,
|
| 414 |
+
"eval_steps_per_second": 2.229,
|
| 415 |
"eval_weighted avg": {
|
| 416 |
+
"f1-score": 0.853808653145316,
|
| 417 |
+
"precision": 0.8537078167069386,
|
| 418 |
+
"recall": 0.8540298507462687,
|
| 419 |
+
"support": 33500.0
|
| 420 |
},
|
| 421 |
"step": 729
|
| 422 |
},
|
| 423 |
{
|
| 424 |
"epoch": 10.0,
|
| 425 |
"eval_Claim": {
|
| 426 |
+
"f1-score": 0.6347110795166041,
|
| 427 |
+
"precision": 0.6368453230079478,
|
| 428 |
+
"recall": 0.6325910931174089,
|
| 429 |
+
"support": 4940.0
|
| 430 |
},
|
| 431 |
"eval_MajorClaim": {
|
| 432 |
+
"f1-score": 0.8442090055381651,
|
| 433 |
+
"precision": 0.8921119592875318,
|
| 434 |
+
"recall": 0.8011882998171846,
|
| 435 |
+
"support": 2188.0
|
| 436 |
},
|
| 437 |
"eval_O": {
|
| 438 |
+
"f1-score": 0.9106677408653618,
|
| 439 |
+
"precision": 0.9040270982310877,
|
| 440 |
+
"recall": 0.9174066647569942,
|
| 441 |
+
"support": 10473.0
|
| 442 |
},
|
| 443 |
"eval_Premise": {
|
| 444 |
+
"f1-score": 0.8841656478259506,
|
| 445 |
+
"precision": 0.881375,
|
| 446 |
+
"recall": 0.8869740235234921,
|
| 447 |
+
"support": 15899.0
|
| 448 |
},
|
| 449 |
+
"eval_accuracy": 0.8533731343283583,
|
| 450 |
+
"eval_loss": 0.7164433002471924,
|
| 451 |
"eval_macro avg": {
|
| 452 |
+
"f1-score": 0.8184383684365204,
|
| 453 |
+
"precision": 0.8285898451316418,
|
| 454 |
+
"recall": 0.8095400203037699,
|
| 455 |
+
"support": 33500.0
|
| 456 |
+
},
|
| 457 |
+
"eval_runtime": 4.9093,
|
| 458 |
+
"eval_samples_per_second": 16.499,
|
| 459 |
+
"eval_steps_per_second": 2.241,
|
| 460 |
"eval_weighted avg": {
|
| 461 |
+
"f1-score": 0.8530559678148433,
|
| 462 |
+
"precision": 0.8530989190255094,
|
| 463 |
+
"recall": 0.8533731343283583,
|
| 464 |
+
"support": 33500.0
|
| 465 |
},
|
| 466 |
"step": 810
|
| 467 |
},
|
| 468 |
{
|
| 469 |
"epoch": 11.0,
|
| 470 |
"eval_Claim": {
|
| 471 |
+
"f1-score": 0.645658668208538,
|
| 472 |
+
"precision": 0.6161486113665624,
|
| 473 |
+
"recall": 0.6781376518218624,
|
| 474 |
+
"support": 4940.0
|
| 475 |
},
|
| 476 |
"eval_MajorClaim": {
|
| 477 |
+
"f1-score": 0.8331177231565331,
|
| 478 |
+
"precision": 0.7885714285714286,
|
| 479 |
+
"recall": 0.8829981718464351,
|
| 480 |
+
"support": 2188.0
|
| 481 |
},
|
| 482 |
"eval_O": {
|
| 483 |
+
"f1-score": 0.9059711059612445,
|
| 484 |
+
"precision": 0.9366843393148451,
|
| 485 |
+
"recall": 0.8772080588179128,
|
| 486 |
+
"support": 10473.0
|
| 487 |
},
|
| 488 |
"eval_Premise": {
|
| 489 |
+
"f1-score": 0.8902977542265961,
|
| 490 |
+
"precision": 0.8929452704840241,
|
| 491 |
+
"recall": 0.8876658909365369,
|
| 492 |
+
"support": 15899.0
|
| 493 |
},
|
| 494 |
+
"eval_accuracy": 0.8531940298507462,
|
| 495 |
+
"eval_loss": 0.7852362394332886,
|
| 496 |
"eval_macro avg": {
|
| 497 |
+
"f1-score": 0.818761312888228,
|
| 498 |
+
"precision": 0.8085874124342151,
|
| 499 |
+
"recall": 0.8315024433556868,
|
| 500 |
+
"support": 33500.0
|
| 501 |
+
},
|
| 502 |
+
"eval_runtime": 4.89,
|
| 503 |
+
"eval_samples_per_second": 16.565,
|
| 504 |
+
"eval_steps_per_second": 2.25,
|
| 505 |
"eval_weighted avg": {
|
| 506 |
+
"f1-score": 0.8553879040715653,
|
| 507 |
+
"precision": 0.8589850855801485,
|
| 508 |
+
"recall": 0.8531940298507462,
|
| 509 |
+
"support": 33500.0
|
| 510 |
},
|
| 511 |
"step": 891
|
| 512 |
},
|
| 513 |
{
|
| 514 |
"epoch": 12.0,
|
| 515 |
"eval_Claim": {
|
| 516 |
+
"f1-score": 0.6329215627196947,
|
| 517 |
+
"precision": 0.6280645804265498,
|
| 518 |
+
"recall": 0.6378542510121458,
|
| 519 |
+
"support": 4940.0
|
| 520 |
},
|
| 521 |
"eval_MajorClaim": {
|
| 522 |
+
"f1-score": 0.8528368794326241,
|
| 523 |
+
"precision": 0.8278829604130808,
|
| 524 |
+
"recall": 0.8793418647166362,
|
| 525 |
+
"support": 2188.0
|
| 526 |
},
|
| 527 |
"eval_O": {
|
| 528 |
+
"f1-score": 0.9126755145220234,
|
| 529 |
+
"precision": 0.9193064031773709,
|
| 530 |
+
"recall": 0.9061395970591044,
|
| 531 |
+
"support": 10473.0
|
| 532 |
},
|
| 533 |
"eval_Premise": {
|
| 534 |
+
"f1-score": 0.8876634630534112,
|
| 535 |
+
"precision": 0.8894291487749432,
|
| 536 |
+
"recall": 0.88590477388515,
|
| 537 |
+
"support": 15899.0
|
| 538 |
},
|
| 539 |
+
"eval_accuracy": 0.8552238805970149,
|
| 540 |
+
"eval_loss": 0.8324545621871948,
|
| 541 |
"eval_macro avg": {
|
| 542 |
+
"f1-score": 0.8215243549319383,
|
| 543 |
+
"precision": 0.8161707731979861,
|
| 544 |
+
"recall": 0.827310121668259,
|
| 545 |
+
"support": 33500.0
|
| 546 |
+
},
|
| 547 |
+
"eval_runtime": 4.8939,
|
| 548 |
+
"eval_samples_per_second": 16.551,
|
| 549 |
+
"eval_steps_per_second": 2.248,
|
| 550 |
"eval_weighted avg": {
|
| 551 |
+
"f1-score": 0.8556433335734092,
|
| 552 |
+
"precision": 0.8562082669116539,
|
| 553 |
+
"recall": 0.8552238805970149,
|
| 554 |
+
"support": 33500.0
|
| 555 |
},
|
| 556 |
"step": 972
|
| 557 |
},
|
| 558 |
{
|
| 559 |
"epoch": 12.35,
|
| 560 |
+
"grad_norm": 2.6090729236602783,
|
| 561 |
"learning_rate": 1.506172839506173e-05,
|
| 562 |
+
"loss": 0.0589,
|
| 563 |
"step": 1000
|
| 564 |
},
|
| 565 |
{
|
| 566 |
"epoch": 13.0,
|
| 567 |
"eval_Claim": {
|
| 568 |
+
"f1-score": 0.6431152147731835,
|
| 569 |
+
"precision": 0.6377388535031847,
|
| 570 |
+
"recall": 0.648582995951417,
|
| 571 |
+
"support": 4940.0
|
| 572 |
},
|
| 573 |
"eval_MajorClaim": {
|
| 574 |
+
"f1-score": 0.8326953388876379,
|
| 575 |
+
"precision": 0.8206835330670218,
|
| 576 |
+
"recall": 0.8450639853747715,
|
| 577 |
+
"support": 2188.0
|
| 578 |
},
|
| 579 |
"eval_O": {
|
| 580 |
+
"f1-score": 0.904438383337466,
|
| 581 |
+
"precision": 0.9408790755262072,
|
| 582 |
+
"recall": 0.8707151723479424,
|
| 583 |
+
"support": 10473.0
|
| 584 |
},
|
| 585 |
"eval_Premise": {
|
| 586 |
+
"f1-score": 0.892013567684243,
|
| 587 |
+
"precision": 0.8749621922448733,
|
| 588 |
+
"recall": 0.9097427511164224,
|
| 589 |
+
"support": 15899.0
|
| 590 |
},
|
| 591 |
+
"eval_accuracy": 0.8548059701492537,
|
| 592 |
+
"eval_loss": 0.8543176651000977,
|
| 593 |
"eval_macro avg": {
|
| 594 |
+
"f1-score": 0.8180656261706326,
|
| 595 |
+
"precision": 0.8185659135853218,
|
| 596 |
+
"recall": 0.8185262261976383,
|
| 597 |
+
"support": 33500.0
|
| 598 |
+
},
|
| 599 |
+
"eval_runtime": 4.9338,
|
| 600 |
+
"eval_samples_per_second": 16.417,
|
| 601 |
+
"eval_steps_per_second": 2.23,
|
| 602 |
"eval_weighted avg": {
|
| 603 |
+
"f1-score": 0.8553204019036041,
|
| 604 |
+
"precision": 0.8570428644520474,
|
| 605 |
+
"recall": 0.8548059701492537,
|
| 606 |
+
"support": 33500.0
|
| 607 |
},
|
| 608 |
"step": 1053
|
| 609 |
},
|
| 610 |
{
|
| 611 |
"epoch": 14.0,
|
| 612 |
"eval_Claim": {
|
| 613 |
+
"f1-score": 0.6541843971631205,
|
| 614 |
+
"precision": 0.6138420585625555,
|
| 615 |
+
"recall": 0.7002024291497976,
|
| 616 |
+
"support": 4940.0
|
| 617 |
},
|
| 618 |
"eval_MajorClaim": {
|
| 619 |
+
"f1-score": 0.8336528221512247,
|
| 620 |
+
"precision": 0.7806142800159553,
|
| 621 |
+
"recall": 0.8944241316270567,
|
| 622 |
+
"support": 2188.0
|
| 623 |
},
|
| 624 |
"eval_O": {
|
| 625 |
+
"f1-score": 0.9079845651528643,
|
| 626 |
+
"precision": 0.9421004003695719,
|
| 627 |
+
"recall": 0.8762532225723288,
|
| 628 |
+
"support": 10473.0
|
| 629 |
},
|
| 630 |
"eval_Premise": {
|
| 631 |
+
"f1-score": 0.889389516436096,
|
| 632 |
+
"precision": 0.8974194787731319,
|
| 633 |
+
"recall": 0.8815019812566828,
|
| 634 |
+
"support": 15899.0
|
| 635 |
},
|
| 636 |
+
"eval_accuracy": 0.8539701492537314,
|
| 637 |
+
"eval_loss": 0.9095103144645691,
|
| 638 |
"eval_macro avg": {
|
| 639 |
+
"f1-score": 0.8213028252258264,
|
| 640 |
+
"precision": 0.8084940544303038,
|
| 641 |
+
"recall": 0.8380954411514664,
|
| 642 |
+
"support": 33500.0
|
| 643 |
+
},
|
| 644 |
+
"eval_runtime": 4.8917,
|
| 645 |
+
"eval_samples_per_second": 16.559,
|
| 646 |
+
"eval_steps_per_second": 2.249,
|
| 647 |
"eval_weighted avg": {
|
| 648 |
+
"f1-score": 0.8568784946124219,
|
| 649 |
+
"precision": 0.8619418985092084,
|
| 650 |
+
"recall": 0.8539701492537314,
|
| 651 |
+
"support": 33500.0
|
| 652 |
},
|
| 653 |
"step": 1134
|
| 654 |
},
|
| 655 |
{
|
| 656 |
"epoch": 15.0,
|
| 657 |
"eval_Claim": {
|
| 658 |
+
"f1-score": 0.631984585741811,
|
| 659 |
+
"precision": 0.6332046332046332,
|
| 660 |
+
"recall": 0.6307692307692307,
|
| 661 |
+
"support": 4940.0
|
| 662 |
},
|
| 663 |
"eval_MajorClaim": {
|
| 664 |
+
"f1-score": 0.8264781491002571,
|
| 665 |
+
"precision": 0.7778225806451613,
|
| 666 |
+
"recall": 0.8816270566727605,
|
| 667 |
+
"support": 2188.0
|
| 668 |
},
|
| 669 |
"eval_O": {
|
| 670 |
+
"f1-score": 0.8970963775654971,
|
| 671 |
+
"precision": 0.8886910896655111,
|
| 672 |
+
"recall": 0.9056621789363124,
|
| 673 |
+
"support": 10473.0
|
| 674 |
},
|
| 675 |
"eval_Premise": {
|
| 676 |
+
"f1-score": 0.8838946528332003,
|
| 677 |
+
"precision": 0.8974458706080644,
|
| 678 |
+
"recall": 0.8707465878357129,
|
| 679 |
+
"support": 15899.0
|
| 680 |
},
|
| 681 |
+
"eval_accuracy": 0.8469850746268657,
|
| 682 |
+
"eval_loss": 0.9576827883720398,
|
| 683 |
"eval_macro avg": {
|
| 684 |
+
"f1-score": 0.8098634413101913,
|
| 685 |
+
"precision": 0.7992910435308425,
|
| 686 |
+
"recall": 0.8222012635535042,
|
| 687 |
+
"support": 33500.0
|
| 688 |
+
},
|
| 689 |
+
"eval_runtime": 4.8883,
|
| 690 |
+
"eval_samples_per_second": 16.57,
|
| 691 |
+
"eval_steps_per_second": 2.25,
|
| 692 |
"eval_weighted avg": {
|
| 693 |
+
"f1-score": 0.8471244624308779,
|
| 694 |
+
"precision": 0.8479301603984184,
|
| 695 |
+
"recall": 0.8469850746268657,
|
| 696 |
+
"support": 33500.0
|
| 697 |
},
|
| 698 |
"step": 1215
|
| 699 |
},
|
| 700 |
{
|
| 701 |
"epoch": 16.0,
|
| 702 |
"eval_Claim": {
|
| 703 |
+
"f1-score": 0.6332942805410586,
|
| 704 |
+
"precision": 0.6682400539447066,
|
| 705 |
+
"recall": 0.6018218623481781,
|
| 706 |
+
"support": 4940.0
|
| 707 |
},
|
| 708 |
"eval_MajorClaim": {
|
| 709 |
+
"f1-score": 0.8478211270819075,
|
| 710 |
+
"precision": 0.8464692482915718,
|
| 711 |
+
"recall": 0.8491773308957953,
|
| 712 |
+
"support": 2188.0
|
| 713 |
},
|
| 714 |
"eval_O": {
|
| 715 |
+
"f1-score": 0.9089773764349872,
|
| 716 |
+
"precision": 0.9145563502803016,
|
| 717 |
+
"recall": 0.9034660555714695,
|
| 718 |
+
"support": 10473.0
|
| 719 |
},
|
| 720 |
"eval_Premise": {
|
| 721 |
+
"f1-score": 0.8924681415656145,
|
| 722 |
+
"precision": 0.8759539672925499,
|
| 723 |
+
"recall": 0.9096169570413234,
|
| 724 |
+
"support": 15899.0
|
| 725 |
},
|
| 726 |
+
"eval_accuracy": 0.8583582089552239,
|
| 727 |
+
"eval_loss": 0.9394893646240234,
|
| 728 |
"eval_macro avg": {
|
| 729 |
+
"f1-score": 0.8206402314058919,
|
| 730 |
+
"precision": 0.8263049049522826,
|
| 731 |
+
"recall": 0.8160205514641916,
|
| 732 |
+
"support": 33500.0
|
| 733 |
+
},
|
| 734 |
+
"eval_runtime": 4.896,
|
| 735 |
+
"eval_samples_per_second": 16.544,
|
| 736 |
+
"eval_steps_per_second": 2.247,
|
| 737 |
"eval_weighted avg": {
|
| 738 |
+
"f1-score": 0.8564948483009961,
|
| 739 |
+
"precision": 0.8554663093796615,
|
| 740 |
+
"recall": 0.8583582089552239,
|
| 741 |
+
"support": 33500.0
|
| 742 |
},
|
| 743 |
"step": 1296
|
| 744 |
},
|
| 745 |
{
|
| 746 |
"epoch": 17.0,
|
| 747 |
"eval_Claim": {
|
| 748 |
+
"f1-score": 0.6431561322729175,
|
| 749 |
+
"precision": 0.6657279029462738,
|
| 750 |
+
"recall": 0.6220647773279352,
|
| 751 |
+
"support": 4940.0
|
| 752 |
},
|
| 753 |
"eval_MajorClaim": {
|
| 754 |
+
"f1-score": 0.8454073572556984,
|
| 755 |
+
"precision": 0.8350423539901917,
|
| 756 |
+
"recall": 0.8560329067641682,
|
| 757 |
+
"support": 2188.0
|
| 758 |
},
|
| 759 |
"eval_O": {
|
| 760 |
+
"f1-score": 0.909496556407023,
|
| 761 |
+
"precision": 0.9241991128634796,
|
| 762 |
+
"recall": 0.8952544638594481,
|
| 763 |
+
"support": 10473.0
|
| 764 |
},
|
| 765 |
"eval_Premise": {
|
| 766 |
+
"f1-score": 0.8953850902917116,
|
| 767 |
+
"precision": 0.8791828322017459,
|
| 768 |
+
"recall": 0.9121957355808541,
|
| 769 |
+
"support": 15899.0
|
| 770 |
},
|
| 771 |
+
"eval_accuracy": 0.8604477611940299,
|
| 772 |
+
"eval_loss": 0.9581068754196167,
|
| 773 |
"eval_macro avg": {
|
| 774 |
+
"f1-score": 0.8233612840568376,
|
| 775 |
+
"precision": 0.8260380505004228,
|
| 776 |
+
"recall": 0.8213869708831014,
|
| 777 |
+
"support": 33500.0
|
| 778 |
+
},
|
| 779 |
+
"eval_runtime": 4.8973,
|
| 780 |
+
"eval_samples_per_second": 16.54,
|
| 781 |
+
"eval_steps_per_second": 2.246,
|
| 782 |
"eval_weighted avg": {
|
| 783 |
+
"f1-score": 0.859338136623951,
|
| 784 |
+
"precision": 0.8588965274411914,
|
| 785 |
+
"recall": 0.8604477611940299,
|
| 786 |
+
"support": 33500.0
|
| 787 |
},
|
| 788 |
"step": 1377
|
| 789 |
},
|
| 790 |
{
|
| 791 |
"epoch": 18.0,
|
| 792 |
"eval_Claim": {
|
| 793 |
+
"f1-score": 0.6493941483597675,
|
| 794 |
+
"precision": 0.632508155824218,
|
| 795 |
+
"recall": 0.6672064777327935,
|
| 796 |
+
"support": 4940.0
|
| 797 |
},
|
| 798 |
"eval_MajorClaim": {
|
| 799 |
+
"f1-score": 0.8654810761513908,
|
| 800 |
+
"precision": 0.8635122838944495,
|
| 801 |
+
"recall": 0.8674588665447898,
|
| 802 |
+
"support": 2188.0
|
| 803 |
},
|
| 804 |
"eval_O": {
|
| 805 |
+
"f1-score": 0.9125304729400293,
|
| 806 |
+
"precision": 0.9323503038756601,
|
| 807 |
+
"recall": 0.8935357586173971,
|
| 808 |
+
"support": 10473.0
|
| 809 |
},
|
| 810 |
"eval_Premise": {
|
| 811 |
+
"f1-score": 0.8928739085531874,
|
| 812 |
+
"precision": 0.8885635978572318,
|
| 813 |
+
"recall": 0.8972262406440656,
|
| 814 |
+
"support": 15899.0
|
| 815 |
},
|
| 816 |
+
"eval_accuracy": 0.8602089552238806,
|
| 817 |
+
"eval_loss": 0.9848275184631348,
|
| 818 |
"eval_macro avg": {
|
| 819 |
+
"f1-score": 0.8300699015010937,
|
| 820 |
+
"precision": 0.8292335853628898,
|
| 821 |
+
"recall": 0.8313568358847614,
|
| 822 |
+
"support": 33500.0
|
| 823 |
+
},
|
| 824 |
+
"eval_runtime": 4.9301,
|
| 825 |
+
"eval_samples_per_second": 16.43,
|
| 826 |
+
"eval_steps_per_second": 2.231,
|
| 827 |
"eval_weighted avg": {
|
| 828 |
+
"f1-score": 0.8613257791852104,
|
| 829 |
+
"precision": 0.8628576878135704,
|
| 830 |
+
"recall": 0.8602089552238806,
|
| 831 |
+
"support": 33500.0
|
| 832 |
},
|
| 833 |
"step": 1458
|
| 834 |
}
|
|
|
|
| 838 |
"num_input_tokens_seen": 0,
|
| 839 |
"num_train_epochs": 50,
|
| 840 |
"save_steps": 500,
|
| 841 |
+
"total_flos": 2580159309613200.0,
|
| 842 |
"train_batch_size": 4,
|
| 843 |
"trial_name": null,
|
| 844 |
"trial_params": null
|
checkpoint-1458/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4856
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:da575726aa6fb9f10d3d3191c16916e8d9dc133cfc573c1d27486b346adcb4eb
|
| 3 |
size 4856
|