Training in progress, epoch 22, checkpoint
Browse files
checkpoint-1782/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 sha256:850cc61ea2ba18dec9e1dfc89b04bd170889628f4ba8c487a233146b26b6d359
|
| 3 |
size 592324828
|
checkpoint-1782/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 sha256:3992e539e35c0c9f0add7b1d1e45aebd809b6e8a2dda914a1e66da82b225e24a
|
| 3 |
size 1014657786
|
checkpoint-1782/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:a1ec1db6eb1c1a503b06e69c41f4299be7df3803620d11f1e644a8f348649200
|
| 3 |
size 14244
|
checkpoint-1782/trainer_state.json
CHANGED
|
@@ -11,1011 +11,1011 @@
|
|
| 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": 0.
|
| 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 |
},
|
| 835 |
{
|
| 836 |
"epoch": 18.52,
|
| 837 |
-
"grad_norm":
|
| 838 |
"learning_rate": 1.2592592592592593e-05,
|
| 839 |
-
"loss": 0.
|
| 840 |
"step": 1500
|
| 841 |
},
|
| 842 |
{
|
| 843 |
"epoch": 19.0,
|
| 844 |
"eval_Claim": {
|
| 845 |
-
"f1-score": 0.
|
| 846 |
-
"precision": 0.
|
| 847 |
-
"recall": 0.
|
| 848 |
-
"support":
|
| 849 |
},
|
| 850 |
"eval_MajorClaim": {
|
| 851 |
-
"f1-score": 0.
|
| 852 |
-
"precision": 0.
|
| 853 |
-
"recall": 0.
|
| 854 |
-
"support":
|
| 855 |
},
|
| 856 |
"eval_O": {
|
| 857 |
-
"f1-score": 0.
|
| 858 |
-
"precision": 0.
|
| 859 |
-
"recall": 0.
|
| 860 |
-
"support":
|
| 861 |
},
|
| 862 |
"eval_Premise": {
|
| 863 |
-
"f1-score": 0.
|
| 864 |
-
"precision": 0.
|
| 865 |
-
"recall": 0.
|
| 866 |
-
"support":
|
| 867 |
},
|
| 868 |
-
"eval_accuracy": 0.
|
| 869 |
-
"eval_loss":
|
| 870 |
"eval_macro avg": {
|
| 871 |
-
"f1-score": 0.
|
| 872 |
-
"precision": 0.
|
| 873 |
-
"recall": 0.
|
| 874 |
-
"support":
|
| 875 |
-
},
|
| 876 |
-
"eval_runtime": 4.
|
| 877 |
-
"eval_samples_per_second": 16.
|
| 878 |
-
"eval_steps_per_second": 2.
|
| 879 |
"eval_weighted avg": {
|
| 880 |
-
"f1-score": 0.
|
| 881 |
-
"precision": 0.
|
| 882 |
-
"recall": 0.
|
| 883 |
-
"support":
|
| 884 |
},
|
| 885 |
"step": 1539
|
| 886 |
},
|
| 887 |
{
|
| 888 |
"epoch": 20.0,
|
| 889 |
"eval_Claim": {
|
| 890 |
-
"f1-score": 0.
|
| 891 |
-
"precision": 0.
|
| 892 |
-
"recall": 0.
|
| 893 |
-
"support":
|
| 894 |
},
|
| 895 |
"eval_MajorClaim": {
|
| 896 |
-
"f1-score": 0.
|
| 897 |
-
"precision": 0.
|
| 898 |
-
"recall": 0.
|
| 899 |
-
"support":
|
| 900 |
},
|
| 901 |
"eval_O": {
|
| 902 |
-
"f1-score": 0.
|
| 903 |
-
"precision": 0.
|
| 904 |
-
"recall": 0.
|
| 905 |
-
"support":
|
| 906 |
},
|
| 907 |
"eval_Premise": {
|
| 908 |
-
"f1-score": 0.
|
| 909 |
-
"precision": 0.
|
| 910 |
-
"recall": 0.
|
| 911 |
-
"support":
|
| 912 |
},
|
| 913 |
-
"eval_accuracy": 0.
|
| 914 |
-
"eval_loss": 0.
|
| 915 |
"eval_macro avg": {
|
| 916 |
-
"f1-score": 0.
|
| 917 |
-
"precision": 0.
|
| 918 |
-
"recall": 0.
|
| 919 |
-
"support":
|
| 920 |
-
},
|
| 921 |
-
"eval_runtime": 4.
|
| 922 |
-
"eval_samples_per_second": 16.
|
| 923 |
-
"eval_steps_per_second": 2.
|
| 924 |
"eval_weighted avg": {
|
| 925 |
-
"f1-score": 0.
|
| 926 |
-
"precision": 0.
|
| 927 |
-
"recall": 0.
|
| 928 |
-
"support":
|
| 929 |
},
|
| 930 |
"step": 1620
|
| 931 |
},
|
| 932 |
{
|
| 933 |
"epoch": 21.0,
|
| 934 |
"eval_Claim": {
|
| 935 |
-
"f1-score": 0.
|
| 936 |
-
"precision": 0.
|
| 937 |
-
"recall": 0.
|
| 938 |
-
"support":
|
| 939 |
},
|
| 940 |
"eval_MajorClaim": {
|
| 941 |
-
"f1-score": 0.
|
| 942 |
-
"precision": 0.
|
| 943 |
-
"recall": 0.
|
| 944 |
-
"support":
|
| 945 |
},
|
| 946 |
"eval_O": {
|
| 947 |
-
"f1-score": 0.
|
| 948 |
-
"precision": 0.
|
| 949 |
-
"recall": 0.
|
| 950 |
-
"support":
|
| 951 |
},
|
| 952 |
"eval_Premise": {
|
| 953 |
-
"f1-score": 0.
|
| 954 |
-
"precision": 0.
|
| 955 |
-
"recall": 0.
|
| 956 |
-
"support":
|
| 957 |
},
|
| 958 |
-
"eval_accuracy": 0.
|
| 959 |
-
"eval_loss": 1.
|
| 960 |
"eval_macro avg": {
|
| 961 |
-
"f1-score": 0.
|
| 962 |
-
"precision": 0.
|
| 963 |
-
"recall": 0.
|
| 964 |
-
"support":
|
| 965 |
-
},
|
| 966 |
-
"eval_runtime": 4.
|
| 967 |
-
"eval_samples_per_second": 16.
|
| 968 |
-
"eval_steps_per_second": 2.
|
| 969 |
"eval_weighted avg": {
|
| 970 |
-
"f1-score": 0.
|
| 971 |
-
"precision": 0.
|
| 972 |
-
"recall": 0.
|
| 973 |
-
"support":
|
| 974 |
},
|
| 975 |
"step": 1701
|
| 976 |
},
|
| 977 |
{
|
| 978 |
"epoch": 22.0,
|
| 979 |
"eval_Claim": {
|
| 980 |
-
"f1-score": 0.
|
| 981 |
-
"precision": 0.
|
| 982 |
-
"recall": 0.
|
| 983 |
-
"support":
|
| 984 |
},
|
| 985 |
"eval_MajorClaim": {
|
| 986 |
-
"f1-score": 0.
|
| 987 |
-
"precision": 0.
|
| 988 |
-
"recall": 0.
|
| 989 |
-
"support":
|
| 990 |
},
|
| 991 |
"eval_O": {
|
| 992 |
-
"f1-score": 0.
|
| 993 |
-
"precision": 0.
|
| 994 |
-
"recall": 0.
|
| 995 |
-
"support":
|
| 996 |
},
|
| 997 |
"eval_Premise": {
|
| 998 |
-
"f1-score": 0.
|
| 999 |
-
"precision": 0.
|
| 1000 |
-
"recall": 0.
|
| 1001 |
-
"support":
|
| 1002 |
},
|
| 1003 |
-
"eval_accuracy": 0.
|
| 1004 |
-
"eval_loss":
|
| 1005 |
"eval_macro avg": {
|
| 1006 |
-
"f1-score": 0.
|
| 1007 |
-
"precision": 0.
|
| 1008 |
-
"recall": 0.
|
| 1009 |
-
"support":
|
| 1010 |
-
},
|
| 1011 |
-
"eval_runtime": 4.
|
| 1012 |
-
"eval_samples_per_second": 16.
|
| 1013 |
-
"eval_steps_per_second": 2.
|
| 1014 |
"eval_weighted avg": {
|
| 1015 |
-
"f1-score": 0.
|
| 1016 |
-
"precision": 0.
|
| 1017 |
-
"recall": 0.
|
| 1018 |
-
"support":
|
| 1019 |
},
|
| 1020 |
"step": 1782
|
| 1021 |
}
|
|
@@ -1025,7 +1025,7 @@
|
|
| 1025 |
"num_input_tokens_seen": 0,
|
| 1026 |
"num_train_epochs": 50,
|
| 1027 |
"save_steps": 500,
|
| 1028 |
-
"total_flos":
|
| 1029 |
"train_batch_size": 4,
|
| 1030 |
"trial_name": null,
|
| 1031 |
"trial_params": null
|
|
|
|
| 11 |
{
|
| 12 |
"epoch": 1.0,
|
| 13 |
"eval_Claim": {
|
| 14 |
+
"f1-score": 0.41092129347162903,
|
| 15 |
+
"precision": 0.5640703517587939,
|
| 16 |
+
"recall": 0.32317658349328215,
|
| 17 |
+
"support": 4168.0
|
| 18 |
},
|
| 19 |
"eval_MajorClaim": {
|
| 20 |
+
"f1-score": 0.6523102655237298,
|
| 21 |
+
"precision": 0.5929304446978335,
|
| 22 |
+
"recall": 0.724907063197026,
|
| 23 |
+
"support": 2152.0
|
| 24 |
},
|
| 25 |
"eval_O": {
|
| 26 |
+
"f1-score": 0.8834432924913603,
|
| 27 |
+
"precision": 0.8545380875202593,
|
| 28 |
+
"recall": 0.9143724257533059,
|
| 29 |
+
"support": 9226.0
|
| 30 |
},
|
| 31 |
"eval_Premise": {
|
| 32 |
+
"f1-score": 0.8664166767469054,
|
| 33 |
+
"precision": 0.8441231929604023,
|
| 34 |
+
"recall": 0.8899196554294707,
|
| 35 |
+
"support": 12073.0
|
| 36 |
},
|
| 37 |
+
"eval_accuracy": 0.7997031029363844,
|
| 38 |
+
"eval_loss": 0.5104541182518005,
|
| 39 |
"eval_macro avg": {
|
| 40 |
+
"f1-score": 0.7032728820584061,
|
| 41 |
+
"precision": 0.7139155192343223,
|
| 42 |
+
"recall": 0.7130939319682712,
|
| 43 |
+
"support": 27619.0
|
| 44 |
+
},
|
| 45 |
+
"eval_runtime": 4.7759,
|
| 46 |
+
"eval_samples_per_second": 16.751,
|
| 47 |
+
"eval_steps_per_second": 2.094,
|
| 48 |
"eval_weighted avg": {
|
| 49 |
+
"f1-score": 0.7866826459135919,
|
| 50 |
+
"precision": 0.7857670171690952,
|
| 51 |
+
"recall": 0.7997031029363844,
|
| 52 |
+
"support": 27619.0
|
| 53 |
},
|
| 54 |
"step": 81
|
| 55 |
},
|
| 56 |
{
|
| 57 |
"epoch": 2.0,
|
| 58 |
"eval_Claim": {
|
| 59 |
+
"f1-score": 0.5200312174817897,
|
| 60 |
+
"precision": 0.5678977272727272,
|
| 61 |
+
"recall": 0.47960652591170827,
|
| 62 |
+
"support": 4168.0
|
| 63 |
},
|
| 64 |
"eval_MajorClaim": {
|
| 65 |
+
"f1-score": 0.7526302911671151,
|
| 66 |
+
"precision": 0.7948320413436692,
|
| 67 |
+
"recall": 0.7146840148698885,
|
| 68 |
+
"support": 2152.0
|
| 69 |
},
|
| 70 |
"eval_O": {
|
| 71 |
+
"f1-score": 0.9116096466629278,
|
| 72 |
+
"precision": 0.944560669456067,
|
| 73 |
+
"recall": 0.8808801213960546,
|
| 74 |
+
"support": 9226.0
|
| 75 |
},
|
| 76 |
"eval_Premise": {
|
| 77 |
+
"f1-score": 0.8738735224125151,
|
| 78 |
+
"precision": 0.8259587020648967,
|
| 79 |
+
"recall": 0.9276898865236478,
|
| 80 |
+
"support": 12073.0
|
| 81 |
},
|
| 82 |
+
"eval_accuracy": 0.8278359100619139,
|
| 83 |
+
"eval_loss": 0.44692954421043396,
|
| 84 |
"eval_macro avg": {
|
| 85 |
+
"f1-score": 0.7645361694310869,
|
| 86 |
+
"precision": 0.7833122850343401,
|
| 87 |
+
"recall": 0.7507151371753248,
|
| 88 |
+
"support": 27619.0
|
| 89 |
+
},
|
| 90 |
+
"eval_runtime": 4.7439,
|
| 91 |
+
"eval_samples_per_second": 16.864,
|
| 92 |
+
"eval_steps_per_second": 2.108,
|
| 93 |
"eval_weighted avg": {
|
| 94 |
+
"f1-score": 0.8236335905447046,
|
| 95 |
+
"precision": 0.8242076985653165,
|
| 96 |
+
"recall": 0.8278359100619139,
|
| 97 |
+
"support": 27619.0
|
| 98 |
},
|
| 99 |
"step": 162
|
| 100 |
},
|
| 101 |
{
|
| 102 |
"epoch": 3.0,
|
| 103 |
"eval_Claim": {
|
| 104 |
+
"f1-score": 0.6218357913273168,
|
| 105 |
+
"precision": 0.5744204961366409,
|
| 106 |
+
"recall": 0.6777831094049904,
|
| 107 |
+
"support": 4168.0
|
| 108 |
},
|
| 109 |
"eval_MajorClaim": {
|
| 110 |
+
"f1-score": 0.7799868909766223,
|
| 111 |
+
"precision": 0.7360824742268042,
|
| 112 |
+
"recall": 0.8294609665427509,
|
| 113 |
+
"support": 2152.0
|
| 114 |
},
|
| 115 |
"eval_O": {
|
| 116 |
+
"f1-score": 0.9093637121422617,
|
| 117 |
+
"precision": 0.9330596419204014,
|
| 118 |
+
"recall": 0.8868415347929763,
|
| 119 |
+
"support": 9226.0
|
| 120 |
},
|
| 121 |
"eval_Premise": {
|
| 122 |
+
"f1-score": 0.876420695504665,
|
| 123 |
+
"precision": 0.89797514556357,
|
| 124 |
+
"recall": 0.855876749772219,
|
| 125 |
+
"support": 12073.0
|
| 126 |
},
|
| 127 |
+
"eval_accuracy": 0.8372859263550454,
|
| 128 |
+
"eval_loss": 0.40934404730796814,
|
| 129 |
"eval_macro avg": {
|
| 130 |
+
"f1-score": 0.7969017724877165,
|
| 131 |
+
"precision": 0.7853844394618541,
|
| 132 |
+
"recall": 0.8124905901282342,
|
| 133 |
+
"support": 27619.0
|
| 134 |
+
},
|
| 135 |
+
"eval_runtime": 4.7941,
|
| 136 |
+
"eval_samples_per_second": 16.687,
|
| 137 |
+
"eval_steps_per_second": 2.086,
|
| 138 |
"eval_weighted avg": {
|
| 139 |
+
"f1-score": 0.8414917278933443,
|
| 140 |
+
"precision": 0.8482528803063183,
|
| 141 |
+
"recall": 0.8372859263550454,
|
| 142 |
+
"support": 27619.0
|
| 143 |
},
|
| 144 |
"step": 243
|
| 145 |
},
|
| 146 |
{
|
| 147 |
"epoch": 4.0,
|
| 148 |
"eval_Claim": {
|
| 149 |
+
"f1-score": 0.608644284729743,
|
| 150 |
+
"precision": 0.516112873601603,
|
| 151 |
+
"recall": 0.7416026871401151,
|
| 152 |
+
"support": 4168.0
|
| 153 |
},
|
| 154 |
"eval_MajorClaim": {
|
| 155 |
+
"f1-score": 0.788337924701561,
|
| 156 |
+
"precision": 0.7790381125226861,
|
| 157 |
+
"recall": 0.7978624535315985,
|
| 158 |
+
"support": 2152.0
|
| 159 |
},
|
| 160 |
"eval_O": {
|
| 161 |
+
"f1-score": 0.9068679925629612,
|
| 162 |
+
"precision": 0.9442684500762643,
|
| 163 |
+
"recall": 0.8723173639713853,
|
| 164 |
+
"support": 9226.0
|
| 165 |
},
|
| 166 |
"eval_Premise": {
|
| 167 |
+
"f1-score": 0.8528029247910863,
|
| 168 |
+
"precision": 0.8985600293497202,
|
| 169 |
+
"recall": 0.8114801623457302,
|
| 170 |
+
"support": 12073.0
|
| 171 |
},
|
| 172 |
+
"eval_accuracy": 0.8201962417176581,
|
| 173 |
+
"eval_loss": 0.5160673260688782,
|
| 174 |
"eval_macro avg": {
|
| 175 |
+
"f1-score": 0.789163281696338,
|
| 176 |
+
"precision": 0.7844948663875684,
|
| 177 |
+
"recall": 0.8058156667472073,
|
| 178 |
+
"support": 27619.0
|
| 179 |
+
},
|
| 180 |
+
"eval_runtime": 4.7669,
|
| 181 |
+
"eval_samples_per_second": 16.782,
|
| 182 |
+
"eval_steps_per_second": 2.098,
|
| 183 |
"eval_weighted avg": {
|
| 184 |
+
"f1-score": 0.8289940404467937,
|
| 185 |
+
"precision": 0.8468005514342695,
|
| 186 |
+
"recall": 0.8201962417176581,
|
| 187 |
+
"support": 27619.0
|
| 188 |
},
|
| 189 |
"step": 324
|
| 190 |
},
|
| 191 |
{
|
| 192 |
"epoch": 5.0,
|
| 193 |
"eval_Claim": {
|
| 194 |
+
"f1-score": 0.5923049770561243,
|
| 195 |
+
"precision": 0.5811590856615101,
|
| 196 |
+
"recall": 0.6038867562380038,
|
| 197 |
+
"support": 4168.0
|
| 198 |
},
|
| 199 |
"eval_MajorClaim": {
|
| 200 |
+
"f1-score": 0.7829807463750891,
|
| 201 |
+
"precision": 0.8014598540145985,
|
| 202 |
+
"recall": 0.7653345724907064,
|
| 203 |
+
"support": 2152.0
|
| 204 |
},
|
| 205 |
"eval_O": {
|
| 206 |
+
"f1-score": 0.9075350077795066,
|
| 207 |
+
"precision": 0.9311288483466362,
|
| 208 |
+
"recall": 0.8851073054411446,
|
| 209 |
+
"support": 9226.0
|
| 210 |
},
|
| 211 |
"eval_Premise": {
|
| 212 |
+
"f1-score": 0.8770785784153896,
|
| 213 |
+
"precision": 0.8633555323758325,
|
| 214 |
+
"recall": 0.891244926695933,
|
| 215 |
+
"support": 12073.0
|
| 216 |
},
|
| 217 |
+
"eval_accuracy": 0.8360186827908324,
|
| 218 |
+
"eval_loss": 0.5153732299804688,
|
| 219 |
"eval_macro avg": {
|
| 220 |
+
"f1-score": 0.7899748274065275,
|
| 221 |
+
"precision": 0.7942758300996444,
|
| 222 |
+
"recall": 0.7863933902164468,
|
| 223 |
+
"support": 27619.0
|
| 224 |
+
},
|
| 225 |
+
"eval_runtime": 4.7506,
|
| 226 |
+
"eval_samples_per_second": 16.84,
|
| 227 |
+
"eval_steps_per_second": 2.105,
|
| 228 |
"eval_weighted avg": {
|
| 229 |
+
"f1-score": 0.8369451960444566,
|
| 230 |
+
"precision": 0.8385857117236715,
|
| 231 |
+
"recall": 0.8360186827908324,
|
| 232 |
+
"support": 27619.0
|
| 233 |
},
|
| 234 |
"step": 405
|
| 235 |
},
|
| 236 |
{
|
| 237 |
"epoch": 6.0,
|
| 238 |
"eval_Claim": {
|
| 239 |
+
"f1-score": 0.5533534584591154,
|
| 240 |
+
"precision": 0.6108374384236454,
|
| 241 |
+
"recall": 0.5057581573896354,
|
| 242 |
+
"support": 4168.0
|
| 243 |
},
|
| 244 |
"eval_MajorClaim": {
|
| 245 |
+
"f1-score": 0.7910518800571156,
|
| 246 |
+
"precision": 0.8107317073170732,
|
| 247 |
+
"recall": 0.7723048327137546,
|
| 248 |
+
"support": 2152.0
|
| 249 |
},
|
| 250 |
"eval_O": {
|
| 251 |
+
"f1-score": 0.909817664129661,
|
| 252 |
+
"precision": 0.919331636605068,
|
| 253 |
+
"recall": 0.9004985909386516,
|
| 254 |
+
"support": 9226.0
|
| 255 |
},
|
| 256 |
"eval_Premise": {
|
| 257 |
+
"f1-score": 0.8747714081259442,
|
| 258 |
+
"precision": 0.8410671966975002,
|
| 259 |
+
"recall": 0.9112896546011762,
|
| 260 |
+
"support": 12073.0
|
| 261 |
},
|
| 262 |
+
"eval_accuracy": 0.8356566132010572,
|
| 263 |
+
"eval_loss": 0.5417770147323608,
|
| 264 |
"eval_macro avg": {
|
| 265 |
+
"f1-score": 0.782248602692959,
|
| 266 |
+
"precision": 0.7954919947608217,
|
| 267 |
+
"recall": 0.7724628089108043,
|
| 268 |
+
"support": 27619.0
|
| 269 |
+
},
|
| 270 |
+
"eval_runtime": 4.7432,
|
| 271 |
+
"eval_samples_per_second": 16.866,
|
| 272 |
+
"eval_steps_per_second": 2.108,
|
| 273 |
"eval_weighted avg": {
|
| 274 |
+
"f1-score": 0.8314498656832355,
|
| 275 |
+
"precision": 0.8301032992701898,
|
| 276 |
+
"recall": 0.8356566132010572,
|
| 277 |
+
"support": 27619.0
|
| 278 |
},
|
| 279 |
"step": 486
|
| 280 |
},
|
| 281 |
{
|
| 282 |
"epoch": 6.17,
|
| 283 |
+
"grad_norm": 6.106111526489258,
|
| 284 |
"learning_rate": 1.7530864197530865e-05,
|
| 285 |
+
"loss": 0.345,
|
| 286 |
"step": 500
|
| 287 |
},
|
| 288 |
{
|
| 289 |
"epoch": 7.0,
|
| 290 |
"eval_Claim": {
|
| 291 |
+
"f1-score": 0.5860923076923077,
|
| 292 |
+
"precision": 0.6017184735911044,
|
| 293 |
+
"recall": 0.571257197696737,
|
| 294 |
+
"support": 4168.0
|
| 295 |
},
|
| 296 |
"eval_MajorClaim": {
|
| 297 |
+
"f1-score": 0.8099526066350711,
|
| 298 |
+
"precision": 0.8264023210831721,
|
| 299 |
+
"recall": 0.7941449814126395,
|
| 300 |
+
"support": 2152.0
|
| 301 |
},
|
| 302 |
"eval_O": {
|
| 303 |
+
"f1-score": 0.9184632841627491,
|
| 304 |
+
"precision": 0.9157418381639909,
|
| 305 |
+
"recall": 0.9212009538261435,
|
| 306 |
+
"support": 9226.0
|
| 307 |
},
|
| 308 |
"eval_Premise": {
|
| 309 |
+
"f1-score": 0.8751742803247764,
|
| 310 |
+
"precision": 0.8666450093397222,
|
| 311 |
+
"recall": 0.8838731052762362,
|
| 312 |
+
"support": 12073.0
|
| 313 |
},
|
| 314 |
+
"eval_accuracy": 0.84217386581701,
|
| 315 |
+
"eval_loss": 0.5831862688064575,
|
| 316 |
"eval_macro avg": {
|
| 317 |
+
"f1-score": 0.7974206197037261,
|
| 318 |
+
"precision": 0.8026269105444974,
|
| 319 |
+
"recall": 0.792619059552939,
|
| 320 |
+
"support": 27619.0
|
| 321 |
+
},
|
| 322 |
+
"eval_runtime": 4.7225,
|
| 323 |
+
"eval_samples_per_second": 16.94,
|
| 324 |
+
"eval_steps_per_second": 2.118,
|
| 325 |
"eval_weighted avg": {
|
| 326 |
+
"f1-score": 0.8409273360363069,
|
| 327 |
+
"precision": 0.8399297508801243,
|
| 328 |
+
"recall": 0.84217386581701,
|
| 329 |
+
"support": 27619.0
|
| 330 |
},
|
| 331 |
"step": 567
|
| 332 |
},
|
| 333 |
{
|
| 334 |
"epoch": 8.0,
|
| 335 |
"eval_Claim": {
|
| 336 |
+
"f1-score": 0.6089751514402275,
|
| 337 |
+
"precision": 0.6281560826319816,
|
| 338 |
+
"recall": 0.5909309021113244,
|
| 339 |
+
"support": 4168.0
|
| 340 |
},
|
| 341 |
"eval_MajorClaim": {
|
| 342 |
+
"f1-score": 0.8056783802653014,
|
| 343 |
+
"precision": 0.806993006993007,
|
| 344 |
+
"recall": 0.804368029739777,
|
| 345 |
+
"support": 2152.0
|
| 346 |
},
|
| 347 |
"eval_O": {
|
| 348 |
+
"f1-score": 0.9201371876531113,
|
| 349 |
+
"precision": 0.9243136825987094,
|
| 350 |
+
"recall": 0.9159982657706481,
|
| 351 |
+
"support": 9226.0
|
| 352 |
},
|
| 353 |
"eval_Premise": {
|
| 354 |
+
"f1-score": 0.8842053669893396,
|
| 355 |
+
"precision": 0.8721998388396455,
|
| 356 |
+
"recall": 0.8965460117617825,
|
| 357 |
+
"support": 12073.0
|
| 358 |
},
|
| 359 |
+
"eval_accuracy": 0.8497411202433107,
|
| 360 |
+
"eval_loss": 0.5915889739990234,
|
| 361 |
"eval_macro avg": {
|
| 362 |
+
"f1-score": 0.8047490215869949,
|
| 363 |
+
"precision": 0.8079156527658359,
|
| 364 |
+
"recall": 0.801960802345883,
|
| 365 |
+
"support": 27619.0
|
| 366 |
+
},
|
| 367 |
+
"eval_runtime": 4.7226,
|
| 368 |
+
"eval_samples_per_second": 16.94,
|
| 369 |
+
"eval_steps_per_second": 2.117,
|
| 370 |
"eval_weighted avg": {
|
| 371 |
+
"f1-score": 0.8485544514458778,
|
| 372 |
+
"precision": 0.8476986926907486,
|
| 373 |
+
"recall": 0.8497411202433107,
|
| 374 |
+
"support": 27619.0
|
| 375 |
},
|
| 376 |
"step": 648
|
| 377 |
},
|
| 378 |
{
|
| 379 |
"epoch": 9.0,
|
| 380 |
"eval_Claim": {
|
| 381 |
+
"f1-score": 0.6137689614935823,
|
| 382 |
+
"precision": 0.5974557019536574,
|
| 383 |
+
"recall": 0.6309980806142035,
|
| 384 |
+
"support": 4168.0
|
| 385 |
},
|
| 386 |
"eval_MajorClaim": {
|
| 387 |
+
"f1-score": 0.8104347826086956,
|
| 388 |
+
"precision": 0.761437908496732,
|
| 389 |
+
"recall": 0.8661710037174721,
|
| 390 |
+
"support": 2152.0
|
| 391 |
},
|
| 392 |
"eval_O": {
|
| 393 |
+
"f1-score": 0.9178336980306346,
|
| 394 |
+
"precision": 0.9265518003092555,
|
| 395 |
+
"recall": 0.9092781270323,
|
| 396 |
+
"support": 9226.0
|
| 397 |
},
|
| 398 |
"eval_Premise": {
|
| 399 |
+
"f1-score": 0.8752312090129477,
|
| 400 |
+
"precision": 0.8886043533930857,
|
| 401 |
+
"recall": 0.8622546177420691,
|
| 402 |
+
"support": 12073.0
|
| 403 |
},
|
| 404 |
+
"eval_accuracy": 0.8433686954632681,
|
| 405 |
+
"eval_loss": 0.6680669784545898,
|
| 406 |
"eval_macro avg": {
|
| 407 |
+
"f1-score": 0.804317162786465,
|
| 408 |
+
"precision": 0.7935124410381827,
|
| 409 |
+
"recall": 0.8171754572765112,
|
| 410 |
+
"support": 27619.0
|
| 411 |
+
},
|
| 412 |
+
"eval_runtime": 4.7195,
|
| 413 |
+
"eval_samples_per_second": 16.951,
|
| 414 |
+
"eval_steps_per_second": 2.119,
|
| 415 |
"eval_weighted avg": {
|
| 416 |
+
"f1-score": 0.8449561811840803,
|
| 417 |
+
"precision": 0.8474346288061019,
|
| 418 |
+
"recall": 0.8433686954632681,
|
| 419 |
+
"support": 27619.0
|
| 420 |
},
|
| 421 |
"step": 729
|
| 422 |
},
|
| 423 |
{
|
| 424 |
"epoch": 10.0,
|
| 425 |
"eval_Claim": {
|
| 426 |
+
"f1-score": 0.5938368860055606,
|
| 427 |
+
"precision": 0.5741487455197133,
|
| 428 |
+
"recall": 0.6149232245681382,
|
| 429 |
+
"support": 4168.0
|
| 430 |
},
|
| 431 |
"eval_MajorClaim": {
|
| 432 |
+
"f1-score": 0.8202093764223942,
|
| 433 |
+
"precision": 0.8037466547725245,
|
| 434 |
+
"recall": 0.837360594795539,
|
| 435 |
+
"support": 2152.0
|
| 436 |
},
|
| 437 |
"eval_O": {
|
| 438 |
+
"f1-score": 0.9145026408450704,
|
| 439 |
+
"precision": 0.9286033519553073,
|
| 440 |
+
"recall": 0.9008237589421201,
|
| 441 |
+
"support": 9226.0
|
| 442 |
},
|
| 443 |
"eval_Premise": {
|
| 444 |
+
"f1-score": 0.8716092527874855,
|
| 445 |
+
"precision": 0.8756164841594918,
|
| 446 |
+
"recall": 0.8676385322620724,
|
| 447 |
+
"support": 12073.0
|
| 448 |
},
|
| 449 |
+
"eval_accuracy": 0.8382273072884608,
|
| 450 |
+
"eval_loss": 0.7243372201919556,
|
| 451 |
"eval_macro avg": {
|
| 452 |
+
"f1-score": 0.8000395390151277,
|
| 453 |
+
"precision": 0.7955288091017592,
|
| 454 |
+
"recall": 0.8051865276419675,
|
| 455 |
+
"support": 27619.0
|
| 456 |
+
},
|
| 457 |
+
"eval_runtime": 4.7291,
|
| 458 |
+
"eval_samples_per_second": 16.917,
|
| 459 |
+
"eval_steps_per_second": 2.115,
|
| 460 |
"eval_weighted avg": {
|
| 461 |
+
"f1-score": 0.840013852502701,
|
| 462 |
+
"precision": 0.8422219164630815,
|
| 463 |
+
"recall": 0.8382273072884608,
|
| 464 |
+
"support": 27619.0
|
| 465 |
},
|
| 466 |
"step": 810
|
| 467 |
},
|
| 468 |
{
|
| 469 |
"epoch": 11.0,
|
| 470 |
"eval_Claim": {
|
| 471 |
+
"f1-score": 0.6018801410105759,
|
| 472 |
+
"precision": 0.5898203592814372,
|
| 473 |
+
"recall": 0.614443378119002,
|
| 474 |
+
"support": 4168.0
|
| 475 |
},
|
| 476 |
"eval_MajorClaim": {
|
| 477 |
+
"f1-score": 0.7984663311766117,
|
| 478 |
+
"precision": 0.8243443839683325,
|
| 479 |
+
"recall": 0.7741635687732342,
|
| 480 |
+
"support": 2152.0
|
| 481 |
},
|
| 482 |
"eval_O": {
|
| 483 |
+
"f1-score": 0.9056203605514316,
|
| 484 |
+
"precision": 0.9334944195144402,
|
| 485 |
+
"recall": 0.8793626707132018,
|
| 486 |
+
"support": 9226.0
|
| 487 |
},
|
| 488 |
"eval_Premise": {
|
| 489 |
+
"f1-score": 0.878886273236464,
|
| 490 |
+
"precision": 0.8616792678074016,
|
| 491 |
+
"recall": 0.8967945001242442,
|
| 492 |
+
"support": 12073.0
|
| 493 |
},
|
| 494 |
+
"eval_accuracy": 0.838806618632101,
|
| 495 |
+
"eval_loss": 0.7492838501930237,
|
| 496 |
"eval_macro avg": {
|
| 497 |
+
"f1-score": 0.7962132764937708,
|
| 498 |
+
"precision": 0.8023346076429029,
|
| 499 |
+
"recall": 0.7911910294324205,
|
| 500 |
+
"support": 27619.0
|
| 501 |
+
},
|
| 502 |
+
"eval_runtime": 4.7534,
|
| 503 |
+
"eval_samples_per_second": 16.83,
|
| 504 |
+
"eval_steps_per_second": 2.104,
|
| 505 |
"eval_weighted avg": {
|
| 506 |
+
"f1-score": 0.8397473983726959,
|
| 507 |
+
"precision": 0.8417333606018996,
|
| 508 |
+
"recall": 0.838806618632101,
|
| 509 |
+
"support": 27619.0
|
| 510 |
},
|
| 511 |
"step": 891
|
| 512 |
},
|
| 513 |
{
|
| 514 |
"epoch": 12.0,
|
| 515 |
"eval_Claim": {
|
| 516 |
+
"f1-score": 0.6351054481546573,
|
| 517 |
+
"precision": 0.5856969205834684,
|
| 518 |
+
"recall": 0.6936180422264875,
|
| 519 |
+
"support": 4168.0
|
| 520 |
},
|
| 521 |
"eval_MajorClaim": {
|
| 522 |
+
"f1-score": 0.8096330275229358,
|
| 523 |
+
"precision": 0.7993659420289855,
|
| 524 |
+
"recall": 0.8201672862453532,
|
| 525 |
+
"support": 2152.0
|
| 526 |
},
|
| 527 |
"eval_O": {
|
| 528 |
+
"f1-score": 0.9158836689038031,
|
| 529 |
+
"precision": 0.9461520684076727,
|
| 530 |
+
"recall": 0.8874918707999133,
|
| 531 |
+
"support": 9226.0
|
| 532 |
},
|
| 533 |
"eval_Premise": {
|
| 534 |
+
"f1-score": 0.8832342847576798,
|
| 535 |
+
"precision": 0.8926486760849336,
|
| 536 |
+
"recall": 0.8740164002319225,
|
| 537 |
+
"support": 12073.0
|
| 538 |
},
|
| 539 |
+
"eval_accuracy": 0.8470980122379521,
|
| 540 |
+
"eval_loss": 0.7472469806671143,
|
| 541 |
"eval_macro avg": {
|
| 542 |
+
"f1-score": 0.810964107334769,
|
| 543 |
+
"precision": 0.8059659017762651,
|
| 544 |
+
"recall": 0.8188233998759191,
|
| 545 |
+
"support": 27619.0
|
| 546 |
+
},
|
| 547 |
+
"eval_runtime": 4.7526,
|
| 548 |
+
"eval_samples_per_second": 16.833,
|
| 549 |
+
"eval_steps_per_second": 2.104,
|
| 550 |
"eval_weighted avg": {
|
| 551 |
+
"f1-score": 0.8509605717920246,
|
| 552 |
+
"precision": 0.8569306173916821,
|
| 553 |
+
"recall": 0.8470980122379521,
|
| 554 |
+
"support": 27619.0
|
| 555 |
},
|
| 556 |
"step": 972
|
| 557 |
},
|
| 558 |
{
|
| 559 |
"epoch": 12.35,
|
| 560 |
+
"grad_norm": 3.1761698722839355,
|
| 561 |
"learning_rate": 1.506172839506173e-05,
|
| 562 |
+
"loss": 0.0604,
|
| 563 |
"step": 1000
|
| 564 |
},
|
| 565 |
{
|
| 566 |
"epoch": 13.0,
|
| 567 |
"eval_Claim": {
|
| 568 |
+
"f1-score": 0.6302578018995931,
|
| 569 |
+
"precision": 0.5960222412318221,
|
| 570 |
+
"recall": 0.6686660268714012,
|
| 571 |
+
"support": 4168.0
|
| 572 |
},
|
| 573 |
"eval_MajorClaim": {
|
| 574 |
+
"f1-score": 0.8086405259450574,
|
| 575 |
+
"precision": 0.8172757475083057,
|
| 576 |
+
"recall": 0.800185873605948,
|
| 577 |
+
"support": 2152.0
|
| 578 |
},
|
| 579 |
"eval_O": {
|
| 580 |
+
"f1-score": 0.9224348987313599,
|
| 581 |
+
"precision": 0.9477475417333638,
|
| 582 |
+
"recall": 0.8984391935833514,
|
| 583 |
+
"support": 9226.0
|
| 584 |
},
|
| 585 |
"eval_Premise": {
|
| 586 |
+
"f1-score": 0.8844928196002152,
|
| 587 |
+
"precision": 0.8838709677419355,
|
| 588 |
+
"recall": 0.8851155470885447,
|
| 589 |
+
"support": 12073.0
|
| 590 |
},
|
| 591 |
+
"eval_accuracy": 0.8502842246279735,
|
| 592 |
+
"eval_loss": 0.812764048576355,
|
| 593 |
"eval_macro avg": {
|
| 594 |
+
"f1-score": 0.8114565115440564,
|
| 595 |
+
"precision": 0.8112291245538568,
|
| 596 |
+
"recall": 0.8131016602873112,
|
| 597 |
+
"support": 27619.0
|
| 598 |
+
},
|
| 599 |
+
"eval_runtime": 4.7412,
|
| 600 |
+
"eval_samples_per_second": 16.873,
|
| 601 |
+
"eval_steps_per_second": 2.109,
|
| 602 |
"eval_weighted avg": {
|
| 603 |
+
"f1-score": 0.8528902247322565,
|
| 604 |
+
"precision": 0.8565802934093382,
|
| 605 |
+
"recall": 0.8502842246279735,
|
| 606 |
+
"support": 27619.0
|
| 607 |
},
|
| 608 |
"step": 1053
|
| 609 |
},
|
| 610 |
{
|
| 611 |
"epoch": 14.0,
|
| 612 |
"eval_Claim": {
|
| 613 |
+
"f1-score": 0.6177896267571498,
|
| 614 |
+
"precision": 0.6241429970617042,
|
| 615 |
+
"recall": 0.6115642994241842,
|
| 616 |
+
"support": 4168.0
|
| 617 |
},
|
| 618 |
"eval_MajorClaim": {
|
| 619 |
+
"f1-score": 0.7891914191419142,
|
| 620 |
+
"precision": 0.7095697329376854,
|
| 621 |
+
"recall": 0.8889405204460966,
|
| 622 |
+
"support": 2152.0
|
| 623 |
},
|
| 624 |
"eval_O": {
|
| 625 |
+
"f1-score": 0.915085817524842,
|
| 626 |
+
"precision": 0.9549846806504831,
|
| 627 |
+
"recall": 0.8783871667027965,
|
| 628 |
+
"support": 9226.0
|
| 629 |
},
|
| 630 |
"eval_Premise": {
|
| 631 |
+
"f1-score": 0.8833210513387375,
|
| 632 |
+
"precision": 0.8733101270946328,
|
| 633 |
+
"recall": 0.8935641514122422,
|
| 634 |
+
"support": 12073.0
|
| 635 |
},
|
| 636 |
+
"eval_accuracy": 0.8455773199608965,
|
| 637 |
+
"eval_loss": 0.8994765281677246,
|
| 638 |
"eval_macro avg": {
|
| 639 |
+
"f1-score": 0.8013469786906608,
|
| 640 |
+
"precision": 0.7905018844361265,
|
| 641 |
+
"recall": 0.8181140344963299,
|
| 642 |
+
"support": 27619.0
|
| 643 |
+
},
|
| 644 |
+
"eval_runtime": 4.7538,
|
| 645 |
+
"eval_samples_per_second": 16.829,
|
| 646 |
+
"eval_steps_per_second": 2.104,
|
| 647 |
"eval_weighted avg": {
|
| 648 |
+
"f1-score": 0.8465260836240982,
|
| 649 |
+
"precision": 0.850232952139105,
|
| 650 |
+
"recall": 0.8455773199608965,
|
| 651 |
+
"support": 27619.0
|
| 652 |
},
|
| 653 |
"step": 1134
|
| 654 |
},
|
| 655 |
{
|
| 656 |
"epoch": 15.0,
|
| 657 |
"eval_Claim": {
|
| 658 |
+
"f1-score": 0.6071797224452345,
|
| 659 |
+
"precision": 0.5816304108987036,
|
| 660 |
+
"recall": 0.6350767754318618,
|
| 661 |
+
"support": 4168.0
|
| 662 |
},
|
| 663 |
"eval_MajorClaim": {
|
| 664 |
+
"f1-score": 0.8077178975382568,
|
| 665 |
+
"precision": 0.7725922783198982,
|
| 666 |
+
"recall": 0.8461895910780669,
|
| 667 |
+
"support": 2152.0
|
| 668 |
},
|
| 669 |
"eval_O": {
|
| 670 |
+
"f1-score": 0.9198298062926884,
|
| 671 |
+
"precision": 0.9512505789717461,
|
| 672 |
+
"recall": 0.8904183828311294,
|
| 673 |
+
"support": 9226.0
|
| 674 |
},
|
| 675 |
"eval_Premise": {
|
| 676 |
+
"f1-score": 0.8720390922643698,
|
| 677 |
+
"precision": 0.8719668737060041,
|
| 678 |
+
"recall": 0.8721113227863828,
|
| 679 |
+
"support": 12073.0
|
| 680 |
},
|
| 681 |
+
"eval_accuracy": 0.8404359317860893,
|
| 682 |
+
"eval_loss": 0.9128327369689941,
|
| 683 |
"eval_macro avg": {
|
| 684 |
+
"f1-score": 0.8016916296351374,
|
| 685 |
+
"precision": 0.794360035474088,
|
| 686 |
+
"recall": 0.8109490180318603,
|
| 687 |
+
"support": 27619.0
|
| 688 |
+
},
|
| 689 |
+
"eval_runtime": 4.7243,
|
| 690 |
+
"eval_samples_per_second": 16.934,
|
| 691 |
+
"eval_steps_per_second": 2.117,
|
| 692 |
"eval_weighted avg": {
|
| 693 |
+
"f1-score": 0.8430215341764057,
|
| 694 |
+
"precision": 0.8468933720777774,
|
| 695 |
+
"recall": 0.8404359317860893,
|
| 696 |
+
"support": 27619.0
|
| 697 |
},
|
| 698 |
"step": 1215
|
| 699 |
},
|
| 700 |
{
|
| 701 |
"epoch": 16.0,
|
| 702 |
"eval_Claim": {
|
| 703 |
+
"f1-score": 0.6309481002037637,
|
| 704 |
+
"precision": 0.6304191616766467,
|
| 705 |
+
"recall": 0.6314779270633397,
|
| 706 |
+
"support": 4168.0
|
| 707 |
},
|
| 708 |
"eval_MajorClaim": {
|
| 709 |
+
"f1-score": 0.8244803695150116,
|
| 710 |
+
"precision": 0.8195592286501377,
|
| 711 |
+
"recall": 0.8294609665427509,
|
| 712 |
+
"support": 2152.0
|
| 713 |
},
|
| 714 |
"eval_O": {
|
| 715 |
+
"f1-score": 0.9188405797101449,
|
| 716 |
+
"precision": 0.9101446193109315,
|
| 717 |
+
"recall": 0.9277043138955127,
|
| 718 |
+
"support": 9226.0
|
| 719 |
},
|
| 720 |
"eval_Premise": {
|
| 721 |
+
"f1-score": 0.8854815124294965,
|
| 722 |
+
"precision": 0.8933569381217332,
|
| 723 |
+
"recall": 0.8777437256688478,
|
| 724 |
+
"support": 12073.0
|
| 725 |
},
|
| 726 |
+
"eval_accuracy": 0.8535066439769724,
|
| 727 |
+
"eval_loss": 0.8802785873413086,
|
| 728 |
"eval_macro avg": {
|
| 729 |
+
"f1-score": 0.8149376404646043,
|
| 730 |
+
"precision": 0.8133699869398623,
|
| 731 |
+
"recall": 0.8165967332926127,
|
| 732 |
+
"support": 27619.0
|
| 733 |
+
},
|
| 734 |
+
"eval_runtime": 4.7225,
|
| 735 |
+
"eval_samples_per_second": 16.94,
|
| 736 |
+
"eval_steps_per_second": 2.118,
|
| 737 |
"eval_weighted avg": {
|
| 738 |
+
"f1-score": 0.8534601153123827,
|
| 739 |
+
"precision": 0.8535345630772185,
|
| 740 |
+
"recall": 0.8535066439769724,
|
| 741 |
+
"support": 27619.0
|
| 742 |
},
|
| 743 |
"step": 1296
|
| 744 |
},
|
| 745 |
{
|
| 746 |
"epoch": 17.0,
|
| 747 |
"eval_Claim": {
|
| 748 |
+
"f1-score": 0.6351891003053795,
|
| 749 |
+
"precision": 0.6221813161527842,
|
| 750 |
+
"recall": 0.6487523992322457,
|
| 751 |
+
"support": 4168.0
|
| 752 |
},
|
| 753 |
"eval_MajorClaim": {
|
| 754 |
+
"f1-score": 0.8157058556513844,
|
| 755 |
+
"precision": 0.7972493345164152,
|
| 756 |
+
"recall": 0.8350371747211895,
|
| 757 |
+
"support": 2152.0
|
| 758 |
},
|
| 759 |
"eval_O": {
|
| 760 |
+
"f1-score": 0.9181362943609842,
|
| 761 |
+
"precision": 0.9221517603323858,
|
| 762 |
+
"recall": 0.914155647084327,
|
| 763 |
+
"support": 9226.0
|
| 764 |
},
|
| 765 |
"eval_Premise": {
|
| 766 |
+
"f1-score": 0.8847406664996242,
|
| 767 |
+
"precision": 0.8921923692411353,
|
| 768 |
+
"recall": 0.8774124078522323,
|
| 769 |
+
"support": 12073.0
|
| 770 |
},
|
| 771 |
+
"eval_accuracy": 0.8518773308229842,
|
| 772 |
+
"eval_loss": 0.8617361783981323,
|
| 773 |
"eval_macro avg": {
|
| 774 |
+
"f1-score": 0.813442979204343,
|
| 775 |
+
"precision": 0.8084436950606801,
|
| 776 |
+
"recall": 0.8188394072224987,
|
| 777 |
+
"support": 27619.0
|
| 778 |
+
},
|
| 779 |
+
"eval_runtime": 4.7584,
|
| 780 |
+
"eval_samples_per_second": 16.812,
|
| 781 |
+
"eval_steps_per_second": 2.102,
|
| 782 |
"eval_weighted avg": {
|
| 783 |
+
"f1-score": 0.8528573333523664,
|
| 784 |
+
"precision": 0.8540549226358285,
|
| 785 |
+
"recall": 0.8518773308229842,
|
| 786 |
+
"support": 27619.0
|
| 787 |
},
|
| 788 |
"step": 1377
|
| 789 |
},
|
| 790 |
{
|
| 791 |
"epoch": 18.0,
|
| 792 |
"eval_Claim": {
|
| 793 |
+
"f1-score": 0.5979982262764474,
|
| 794 |
+
"precision": 0.6335570469798658,
|
| 795 |
+
"recall": 0.5662188099808061,
|
| 796 |
+
"support": 4168.0
|
| 797 |
},
|
| 798 |
"eval_MajorClaim": {
|
| 799 |
+
"f1-score": 0.8218923933209649,
|
| 800 |
+
"precision": 0.8203703703703704,
|
| 801 |
+
"recall": 0.8234200743494424,
|
| 802 |
+
"support": 2152.0
|
| 803 |
},
|
| 804 |
"eval_O": {
|
| 805 |
+
"f1-score": 0.9185111222055806,
|
| 806 |
+
"precision": 0.9406885581183957,
|
| 807 |
+
"recall": 0.8973553002384566,
|
| 808 |
+
"support": 9226.0
|
| 809 |
},
|
| 810 |
"eval_Premise": {
|
| 811 |
+
"f1-score": 0.8841078141246101,
|
| 812 |
+
"precision": 0.8547127503286167,
|
| 813 |
+
"recall": 0.9155967862171789,
|
| 814 |
+
"support": 12073.0
|
| 815 |
},
|
| 816 |
+
"eval_accuracy": 0.8495962924074008,
|
| 817 |
+
"eval_loss": 0.9965270757675171,
|
| 818 |
"eval_macro avg": {
|
| 819 |
+
"f1-score": 0.8056273889819007,
|
| 820 |
+
"precision": 0.8123321814493122,
|
| 821 |
+
"recall": 0.800647742696471,
|
| 822 |
+
"support": 27619.0
|
| 823 |
+
},
|
| 824 |
+
"eval_runtime": 4.735,
|
| 825 |
+
"eval_samples_per_second": 16.895,
|
| 826 |
+
"eval_steps_per_second": 2.112,
|
| 827 |
"eval_weighted avg": {
|
| 828 |
+
"f1-score": 0.8475754477331567,
|
| 829 |
+
"precision": 0.8473819646173586,
|
| 830 |
+
"recall": 0.8495962924074008,
|
| 831 |
+
"support": 27619.0
|
| 832 |
},
|
| 833 |
"step": 1458
|
| 834 |
},
|
| 835 |
{
|
| 836 |
"epoch": 18.52,
|
| 837 |
+
"grad_norm": 15.414011001586914,
|
| 838 |
"learning_rate": 1.2592592592592593e-05,
|
| 839 |
+
"loss": 0.0201,
|
| 840 |
"step": 1500
|
| 841 |
},
|
| 842 |
{
|
| 843 |
"epoch": 19.0,
|
| 844 |
"eval_Claim": {
|
| 845 |
+
"f1-score": 0.6417134539405281,
|
| 846 |
+
"precision": 0.5662385321100918,
|
| 847 |
+
"recall": 0.7404030710172744,
|
| 848 |
+
"support": 4168.0
|
| 849 |
},
|
| 850 |
"eval_MajorClaim": {
|
| 851 |
+
"f1-score": 0.8129032258064516,
|
| 852 |
+
"precision": 0.8062157221206582,
|
| 853 |
+
"recall": 0.8197026022304833,
|
| 854 |
+
"support": 2152.0
|
| 855 |
},
|
| 856 |
"eval_O": {
|
| 857 |
+
"f1-score": 0.9158699808795411,
|
| 858 |
+
"precision": 0.9517297802711547,
|
| 859 |
+
"recall": 0.8826143507478864,
|
| 860 |
+
"support": 9226.0
|
| 861 |
},
|
| 862 |
"eval_Premise": {
|
| 863 |
+
"f1-score": 0.8692654694016513,
|
| 864 |
+
"precision": 0.8939168490153173,
|
| 865 |
+
"recall": 0.8459372152737513,
|
| 866 |
+
"support": 12073.0
|
| 867 |
},
|
| 868 |
+
"eval_accuracy": 0.8402186900322242,
|
| 869 |
+
"eval_loss": 0.9760411381721497,
|
| 870 |
"eval_macro avg": {
|
| 871 |
+
"f1-score": 0.809938032507043,
|
| 872 |
+
"precision": 0.8045252208793054,
|
| 873 |
+
"recall": 0.8221643098173489,
|
| 874 |
+
"support": 27619.0
|
| 875 |
+
},
|
| 876 |
+
"eval_runtime": 4.7957,
|
| 877 |
+
"eval_samples_per_second": 16.682,
|
| 878 |
+
"eval_steps_per_second": 2.085,
|
| 879 |
"eval_weighted avg": {
|
| 880 |
+
"f1-score": 0.8461018818074655,
|
| 881 |
+
"precision": 0.8569454182549012,
|
| 882 |
+
"recall": 0.8402186900322242,
|
| 883 |
+
"support": 27619.0
|
| 884 |
},
|
| 885 |
"step": 1539
|
| 886 |
},
|
| 887 |
{
|
| 888 |
"epoch": 20.0,
|
| 889 |
"eval_Claim": {
|
| 890 |
+
"f1-score": 0.651902203705734,
|
| 891 |
+
"precision": 0.6002422774076317,
|
| 892 |
+
"recall": 0.7132917466410749,
|
| 893 |
+
"support": 4168.0
|
| 894 |
},
|
| 895 |
"eval_MajorClaim": {
|
| 896 |
+
"f1-score": 0.8352472463088821,
|
| 897 |
+
"precision": 0.8425531914893617,
|
| 898 |
+
"recall": 0.8280669144981413,
|
| 899 |
+
"support": 2152.0
|
| 900 |
},
|
| 901 |
"eval_O": {
|
| 902 |
+
"f1-score": 0.9225629791894853,
|
| 903 |
+
"precision": 0.9323666150099623,
|
| 904 |
+
"recall": 0.9129633644049425,
|
| 905 |
+
"support": 9226.0
|
| 906 |
},
|
| 907 |
"eval_Premise": {
|
| 908 |
+
"f1-score": 0.8775752437473505,
|
| 909 |
+
"precision": 0.8987583572110793,
|
| 910 |
+
"recall": 0.8573676799469891,
|
| 911 |
+
"support": 12073.0
|
| 912 |
},
|
| 913 |
+
"eval_accuracy": 0.8519135377819617,
|
| 914 |
+
"eval_loss": 0.9999569058418274,
|
| 915 |
"eval_macro avg": {
|
| 916 |
+
"f1-score": 0.821821918237863,
|
| 917 |
+
"precision": 0.8184801102795087,
|
| 918 |
+
"recall": 0.8279224263727869,
|
| 919 |
+
"support": 27619.0
|
| 920 |
+
},
|
| 921 |
+
"eval_runtime": 4.7617,
|
| 922 |
+
"eval_samples_per_second": 16.801,
|
| 923 |
+
"eval_steps_per_second": 2.1,
|
| 924 |
"eval_weighted avg": {
|
| 925 |
+
"f1-score": 0.8552486484979966,
|
| 926 |
+
"precision": 0.8605564400235849,
|
| 927 |
+
"recall": 0.8519135377819617,
|
| 928 |
+
"support": 27619.0
|
| 929 |
},
|
| 930 |
"step": 1620
|
| 931 |
},
|
| 932 |
{
|
| 933 |
"epoch": 21.0,
|
| 934 |
"eval_Claim": {
|
| 935 |
+
"f1-score": 0.6376654371881102,
|
| 936 |
+
"precision": 0.5819801980198019,
|
| 937 |
+
"recall": 0.7051343570057581,
|
| 938 |
+
"support": 4168.0
|
| 939 |
},
|
| 940 |
"eval_MajorClaim": {
|
| 941 |
+
"f1-score": 0.792661361626879,
|
| 942 |
+
"precision": 0.7559021922428331,
|
| 943 |
+
"recall": 0.83317843866171,
|
| 944 |
+
"support": 2152.0
|
| 945 |
},
|
| 946 |
"eval_O": {
|
| 947 |
+
"f1-score": 0.9065665187208377,
|
| 948 |
+
"precision": 0.9542405366554864,
|
| 949 |
+
"recall": 0.8634294385432474,
|
| 950 |
+
"support": 9226.0
|
| 951 |
},
|
| 952 |
"eval_Premise": {
|
| 953 |
+
"f1-score": 0.8798595435164284,
|
| 954 |
+
"precision": 0.8881762174023125,
|
| 955 |
+
"recall": 0.8716971755156133,
|
| 956 |
+
"support": 12073.0
|
| 957 |
},
|
| 958 |
+
"eval_accuracy": 0.8407980013758645,
|
| 959 |
+
"eval_loss": 1.0823462009429932,
|
| 960 |
"eval_macro avg": {
|
| 961 |
+
"f1-score": 0.8041882152630638,
|
| 962 |
+
"precision": 0.7950747860801084,
|
| 963 |
+
"recall": 0.8183598524315823,
|
| 964 |
+
"support": 27619.0
|
| 965 |
+
},
|
| 966 |
+
"eval_runtime": 4.8337,
|
| 967 |
+
"eval_samples_per_second": 16.55,
|
| 968 |
+
"eval_steps_per_second": 2.069,
|
| 969 |
"eval_weighted avg": {
|
| 970 |
+
"f1-score": 0.8454369732073347,
|
| 971 |
+
"precision": 0.8537300281304444,
|
| 972 |
+
"recall": 0.8407980013758645,
|
| 973 |
+
"support": 27619.0
|
| 974 |
},
|
| 975 |
"step": 1701
|
| 976 |
},
|
| 977 |
{
|
| 978 |
"epoch": 22.0,
|
| 979 |
"eval_Claim": {
|
| 980 |
+
"f1-score": 0.6413618587531631,
|
| 981 |
+
"precision": 0.6159964648696421,
|
| 982 |
+
"recall": 0.6689059500959693,
|
| 983 |
+
"support": 4168.0
|
| 984 |
},
|
| 985 |
"eval_MajorClaim": {
|
| 986 |
+
"f1-score": 0.8162887552059233,
|
| 987 |
+
"precision": 0.8129032258064516,
|
| 988 |
+
"recall": 0.8197026022304833,
|
| 989 |
+
"support": 2152.0
|
| 990 |
},
|
| 991 |
"eval_O": {
|
| 992 |
+
"f1-score": 0.9215077605321508,
|
| 993 |
+
"precision": 0.9430451554345359,
|
| 994 |
+
"recall": 0.9009321482766096,
|
| 995 |
+
"support": 9226.0
|
| 996 |
},
|
| 997 |
"eval_Premise": {
|
| 998 |
+
"f1-score": 0.8851211645025227,
|
| 999 |
+
"precision": 0.8838054339747295,
|
| 1000 |
+
"recall": 0.886440818355007,
|
| 1001 |
+
"support": 12073.0
|
| 1002 |
},
|
| 1003 |
+
"eval_accuracy": 0.8532531952641298,
|
| 1004 |
+
"eval_loss": 0.9629964828491211,
|
| 1005 |
"eval_macro avg": {
|
| 1006 |
+
"f1-score": 0.8160698847484399,
|
| 1007 |
+
"precision": 0.8139375700213398,
|
| 1008 |
+
"recall": 0.8189953797395173,
|
| 1009 |
+
"support": 27619.0
|
| 1010 |
+
},
|
| 1011 |
+
"eval_runtime": 4.7476,
|
| 1012 |
+
"eval_samples_per_second": 16.851,
|
| 1013 |
+
"eval_steps_per_second": 2.106,
|
| 1014 |
"eval_weighted avg": {
|
| 1015 |
+
"f1-score": 0.8551268346498754,
|
| 1016 |
+
"precision": 0.8576544630844016,
|
| 1017 |
+
"recall": 0.8532531952641298,
|
| 1018 |
+
"support": 27619.0
|
| 1019 |
},
|
| 1020 |
"step": 1782
|
| 1021 |
}
|
|
|
|
| 1025 |
"num_input_tokens_seen": 0,
|
| 1026 |
"num_train_epochs": 50,
|
| 1027 |
"save_steps": 500,
|
| 1028 |
+
"total_flos": 3163352119989600.0,
|
| 1029 |
"train_batch_size": 4,
|
| 1030 |
"trial_name": null,
|
| 1031 |
"trial_params": null
|
checkpoint-1782/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 sha256:1e651c478af6098730eda01c59bbe4834fbad7ed476e7ec6e4265141ee6647e9
|
| 3 |
size 4856
|