Training in progress, epoch 20, checkpoint
Browse files
checkpoint-1620/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:cc8da125ff8a890ba2b155442d1e8c9ad11dcbaed8e25dad1a1c7135432a5aa8
|
| 3 |
size 592324828
|
checkpoint-1620/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 sha256:9cf22910cf60ee7163f768313796a81763f63b0448925496b53c357fe5f81795
|
| 3 |
size 1014657786
|
checkpoint-1620/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fea32ee6c453a446a649988d6089128f7e97a64c79f4bf13d056ba19465eb4c5
|
| 3 |
size 1064
|
checkpoint-1620/trainer_state.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric":
|
| 3 |
-
"best_model_checkpoint":
|
| 4 |
"epoch": 20.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
"global_step": 1620,
|
|
@@ -11,929 +11,929 @@
|
|
| 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":
|
| 46 |
-
"eval_samples_per_second":
|
| 47 |
-
"eval_steps_per_second":
|
| 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":
|
| 91 |
-
"eval_samples_per_second":
|
| 92 |
-
"eval_steps_per_second":
|
| 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":
|
| 136 |
-
"eval_samples_per_second":
|
| 137 |
-
"eval_steps_per_second":
|
| 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":
|
| 181 |
-
"eval_samples_per_second":
|
| 182 |
-
"eval_steps_per_second":
|
| 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":
|
| 226 |
-
"eval_samples_per_second":
|
| 227 |
-
"eval_steps_per_second":
|
| 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":
|
| 271 |
-
"eval_samples_per_second":
|
| 272 |
-
"eval_steps_per_second":
|
| 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": 6.
|
| 284 |
-
"learning_rate": 1.
|
| 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":
|
| 323 |
-
"eval_samples_per_second":
|
| 324 |
-
"eval_steps_per_second":
|
| 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":
|
| 368 |
-
"eval_samples_per_second":
|
| 369 |
-
"eval_steps_per_second":
|
| 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":
|
| 413 |
-
"eval_samples_per_second":
|
| 414 |
-
"eval_steps_per_second":
|
| 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":
|
| 458 |
-
"eval_samples_per_second":
|
| 459 |
-
"eval_steps_per_second":
|
| 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":
|
| 503 |
-
"eval_samples_per_second":
|
| 504 |
-
"eval_steps_per_second":
|
| 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":
|
| 548 |
-
"eval_samples_per_second":
|
| 549 |
-
"eval_steps_per_second":
|
| 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":
|
| 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":
|
| 600 |
-
"eval_samples_per_second":
|
| 601 |
-
"eval_steps_per_second":
|
| 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":
|
| 638 |
"eval_macro avg": {
|
| 639 |
-
"f1-score": 0.
|
| 640 |
-
"precision": 0.
|
| 641 |
-
"recall": 0.
|
| 642 |
-
"support":
|
| 643 |
-
},
|
| 644 |
-
"eval_runtime":
|
| 645 |
-
"eval_samples_per_second":
|
| 646 |
-
"eval_steps_per_second":
|
| 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":
|
| 690 |
-
"eval_samples_per_second":
|
| 691 |
-
"eval_steps_per_second":
|
| 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":
|
| 735 |
-
"eval_samples_per_second":
|
| 736 |
-
"eval_steps_per_second":
|
| 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":
|
| 773 |
"eval_macro avg": {
|
| 774 |
-
"f1-score": 0.
|
| 775 |
-
"precision": 0.
|
| 776 |
-
"recall": 0.
|
| 777 |
-
"support":
|
| 778 |
-
},
|
| 779 |
-
"eval_runtime":
|
| 780 |
-
"eval_samples_per_second":
|
| 781 |
-
"eval_steps_per_second":
|
| 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":
|
| 818 |
"eval_macro avg": {
|
| 819 |
-
"f1-score": 0.
|
| 820 |
-
"precision": 0.
|
| 821 |
-
"recall": 0.
|
| 822 |
-
"support":
|
| 823 |
-
},
|
| 824 |
-
"eval_runtime":
|
| 825 |
-
"eval_samples_per_second":
|
| 826 |
-
"eval_steps_per_second":
|
| 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.
|
| 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":
|
| 877 |
-
"eval_samples_per_second":
|
| 878 |
-
"eval_steps_per_second":
|
| 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":
|
| 915 |
"eval_macro avg": {
|
| 916 |
-
"f1-score": 0.
|
| 917 |
-
"precision": 0.
|
| 918 |
-
"recall": 0.
|
| 919 |
-
"support":
|
| 920 |
-
},
|
| 921 |
-
"eval_runtime":
|
| 922 |
-
"eval_samples_per_second":
|
| 923 |
-
"eval_steps_per_second":
|
| 924 |
"eval_weighted avg": {
|
| 925 |
-
"f1-score": 0.
|
| 926 |
-
"precision": 0.
|
| 927 |
-
"recall": 0.
|
| 928 |
-
"support":
|
| 929 |
},
|
| 930 |
"step": 1620
|
| 931 |
}
|
| 932 |
],
|
| 933 |
"logging_steps": 500,
|
| 934 |
-
"max_steps":
|
| 935 |
"num_input_tokens_seen": 0,
|
| 936 |
-
"num_train_epochs":
|
| 937 |
"save_steps": 500,
|
| 938 |
"total_flos": 2875774654536000.0,
|
| 939 |
"train_batch_size": 4,
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.4725272059440613,
|
| 3 |
+
"best_model_checkpoint": "longformer-simple/checkpoint-324",
|
| 4 |
"epoch": 20.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
"global_step": 1620,
|
|
|
|
| 11 |
{
|
| 12 |
"epoch": 1.0,
|
| 13 |
"eval_Claim": {
|
| 14 |
+
"f1-score": 0.46242900830056793,
|
| 15 |
+
"precision": 0.43257049448304047,
|
| 16 |
+
"recall": 0.496715157203191,
|
| 17 |
+
"support": 4262.0
|
| 18 |
},
|
| 19 |
"eval_MajorClaim": {
|
| 20 |
+
"f1-score": 0.5626477541371159,
|
| 21 |
+
"precision": 0.6522533495736906,
|
| 22 |
+
"recall": 0.49468822170900695,
|
| 23 |
+
"support": 2165.0
|
| 24 |
},
|
| 25 |
"eval_O": {
|
| 26 |
+
"f1-score": 0.8691687871077185,
|
| 27 |
+
"precision": 0.911293908403735,
|
| 28 |
+
"recall": 0.8307661126874747,
|
| 29 |
+
"support": 9868.0
|
| 30 |
},
|
| 31 |
"eval_Premise": {
|
| 32 |
+
"f1-score": 0.8615178272046495,
|
| 33 |
+
"precision": 0.8377046804810897,
|
| 34 |
+
"recall": 0.88672444205844,
|
| 35 |
+
"support": 13039.0
|
| 36 |
},
|
| 37 |
+
"eval_accuracy": 0.7823004022635849,
|
| 38 |
+
"eval_loss": 0.5488611459732056,
|
| 39 |
"eval_macro avg": {
|
| 40 |
+
"f1-score": 0.6889408441875129,
|
| 41 |
+
"precision": 0.708455608235389,
|
| 42 |
+
"recall": 0.6772234834145282,
|
| 43 |
+
"support": 29334.0
|
| 44 |
+
},
|
| 45 |
+
"eval_runtime": 5.8698,
|
| 46 |
+
"eval_samples_per_second": 13.629,
|
| 47 |
+
"eval_steps_per_second": 1.704,
|
| 48 |
"eval_weighted avg": {
|
| 49 |
+
"f1-score": 0.7840489998358311,
|
| 50 |
+
"precision": 0.7899101236188295,
|
| 51 |
+
"recall": 0.7823004022635849,
|
| 52 |
+
"support": 29334.0
|
| 53 |
},
|
| 54 |
"step": 81
|
| 55 |
},
|
| 56 |
{
|
| 57 |
"epoch": 2.0,
|
| 58 |
"eval_Claim": {
|
| 59 |
+
"f1-score": 0.5457327068079991,
|
| 60 |
+
"precision": 0.5107383923092657,
|
| 61 |
+
"recall": 0.5858751759737213,
|
| 62 |
+
"support": 4262.0
|
| 63 |
},
|
| 64 |
"eval_MajorClaim": {
|
| 65 |
+
"f1-score": 0.6722085773663329,
|
| 66 |
+
"precision": 0.5687340153452686,
|
| 67 |
+
"recall": 0.8217090069284064,
|
| 68 |
+
"support": 2165.0
|
| 69 |
},
|
| 70 |
"eval_O": {
|
| 71 |
+
"f1-score": 0.8773589977955805,
|
| 72 |
+
"precision": 0.9344863131370977,
|
| 73 |
+
"recall": 0.8268139440616133,
|
| 74 |
+
"support": 9868.0
|
| 75 |
},
|
| 76 |
"eval_Premise": {
|
| 77 |
+
"f1-score": 0.8678243902439025,
|
| 78 |
+
"precision": 0.8834419195931988,
|
| 79 |
+
"recall": 0.852749443975765,
|
| 80 |
+
"support": 13039.0
|
| 81 |
},
|
| 82 |
+
"eval_accuracy": 0.8029590236585532,
|
| 83 |
+
"eval_loss": 0.5075464248657227,
|
| 84 |
"eval_macro avg": {
|
| 85 |
+
"f1-score": 0.7407811680534537,
|
| 86 |
+
"precision": 0.7243501600962077,
|
| 87 |
+
"recall": 0.7717868927348766,
|
| 88 |
+
"support": 29334.0
|
| 89 |
+
},
|
| 90 |
+
"eval_runtime": 5.9473,
|
| 91 |
+
"eval_samples_per_second": 13.451,
|
| 92 |
+
"eval_steps_per_second": 1.681,
|
| 93 |
"eval_weighted avg": {
|
| 94 |
+
"f1-score": 0.8097969994222006,
|
| 95 |
+
"precision": 0.8232353684753937,
|
| 96 |
+
"recall": 0.8029590236585532,
|
| 97 |
+
"support": 29334.0
|
| 98 |
},
|
| 99 |
"step": 162
|
| 100 |
},
|
| 101 |
{
|
| 102 |
"epoch": 3.0,
|
| 103 |
"eval_Claim": {
|
| 104 |
+
"f1-score": 0.4978109708987896,
|
| 105 |
+
"precision": 0.5516552511415526,
|
| 106 |
+
"recall": 0.45354293758798686,
|
| 107 |
+
"support": 4262.0
|
| 108 |
},
|
| 109 |
"eval_MajorClaim": {
|
| 110 |
+
"f1-score": 0.7357876283496118,
|
| 111 |
+
"precision": 0.8036105032822757,
|
| 112 |
+
"recall": 0.6785219399538106,
|
| 113 |
+
"support": 2165.0
|
| 114 |
},
|
| 115 |
"eval_O": {
|
| 116 |
+
"f1-score": 0.8891011355194736,
|
| 117 |
+
"precision": 0.9331699710403207,
|
| 118 |
+
"recall": 0.8490068909606809,
|
| 119 |
+
"support": 9868.0
|
| 120 |
},
|
| 121 |
"eval_Premise": {
|
| 122 |
+
"f1-score": 0.8770979581655561,
|
| 123 |
+
"precision": 0.8191560170394037,
|
| 124 |
+
"recall": 0.9438607255157604,
|
| 125 |
+
"support": 13039.0
|
| 126 |
},
|
| 127 |
+
"eval_accuracy": 0.821129065248517,
|
| 128 |
+
"eval_loss": 0.5219377279281616,
|
| 129 |
"eval_macro avg": {
|
| 130 |
+
"f1-score": 0.7499494232333578,
|
| 131 |
+
"precision": 0.7768979356258882,
|
| 132 |
+
"recall": 0.7312331235045597,
|
| 133 |
+
"support": 29334.0
|
| 134 |
+
},
|
| 135 |
+
"eval_runtime": 5.8364,
|
| 136 |
+
"eval_samples_per_second": 13.707,
|
| 137 |
+
"eval_steps_per_second": 1.713,
|
| 138 |
"eval_weighted avg": {
|
| 139 |
+
"f1-score": 0.815598992812927,
|
| 140 |
+
"precision": 0.8174973750724106,
|
| 141 |
+
"recall": 0.821129065248517,
|
| 142 |
+
"support": 29334.0
|
| 143 |
},
|
| 144 |
"step": 243
|
| 145 |
},
|
| 146 |
{
|
| 147 |
"epoch": 4.0,
|
| 148 |
"eval_Claim": {
|
| 149 |
+
"f1-score": 0.5811481218993623,
|
| 150 |
+
"precision": 0.5851569933396765,
|
| 151 |
+
"recall": 0.5771938057250118,
|
| 152 |
+
"support": 4262.0
|
| 153 |
},
|
| 154 |
"eval_MajorClaim": {
|
| 155 |
+
"f1-score": 0.761714412613813,
|
| 156 |
+
"precision": 0.7335329341317365,
|
| 157 |
+
"recall": 0.792147806004619,
|
| 158 |
+
"support": 2165.0
|
| 159 |
},
|
| 160 |
"eval_O": {
|
| 161 |
+
"f1-score": 0.8977645611156685,
|
| 162 |
+
"precision": 0.9085720215857203,
|
| 163 |
+
"recall": 0.8872111876773409,
|
| 164 |
+
"support": 9868.0
|
| 165 |
},
|
| 166 |
"eval_Premise": {
|
| 167 |
+
"f1-score": 0.8891009734682191,
|
| 168 |
+
"precision": 0.8851474612344178,
|
| 169 |
+
"recall": 0.8930899608865711,
|
| 170 |
+
"support": 13039.0
|
| 171 |
},
|
| 172 |
+
"eval_accuracy": 0.8377650507943001,
|
| 173 |
+
"eval_loss": 0.4725272059440613,
|
| 174 |
"eval_macro avg": {
|
| 175 |
+
"f1-score": 0.7824320172742658,
|
| 176 |
+
"precision": 0.7781023525728877,
|
| 177 |
+
"recall": 0.7874106900733857,
|
| 178 |
+
"support": 29334.0
|
| 179 |
+
},
|
| 180 |
+
"eval_runtime": 5.8763,
|
| 181 |
+
"eval_samples_per_second": 13.614,
|
| 182 |
+
"eval_steps_per_second": 1.702,
|
| 183 |
"eval_weighted avg": {
|
| 184 |
+
"f1-score": 0.8378705011585708,
|
| 185 |
+
"precision": 0.8382513248807655,
|
| 186 |
+
"recall": 0.8377650507943001,
|
| 187 |
+
"support": 29334.0
|
| 188 |
},
|
| 189 |
"step": 324
|
| 190 |
},
|
| 191 |
{
|
| 192 |
"epoch": 5.0,
|
| 193 |
"eval_Claim": {
|
| 194 |
+
"f1-score": 0.5790953831731895,
|
| 195 |
+
"precision": 0.5784176029962547,
|
| 196 |
+
"recall": 0.5797747536367902,
|
| 197 |
+
"support": 4262.0
|
| 198 |
},
|
| 199 |
"eval_MajorClaim": {
|
| 200 |
+
"f1-score": 0.7450592885375493,
|
| 201 |
+
"precision": 0.8008497079129049,
|
| 202 |
+
"recall": 0.6965357967667436,
|
| 203 |
+
"support": 2165.0
|
| 204 |
},
|
| 205 |
"eval_O": {
|
| 206 |
+
"f1-score": 0.8897467572575665,
|
| 207 |
+
"precision": 0.9040794979079498,
|
| 208 |
+
"recall": 0.8758613700851237,
|
| 209 |
+
"support": 9868.0
|
| 210 |
},
|
| 211 |
"eval_Premise": {
|
| 212 |
+
"f1-score": 0.8861129867206842,
|
| 213 |
+
"precision": 0.8672442910639547,
|
| 214 |
+
"recall": 0.905820998542833,
|
| 215 |
+
"support": 13039.0
|
| 216 |
},
|
| 217 |
+
"eval_accuracy": 0.8329242517215518,
|
| 218 |
+
"eval_loss": 0.5538631081581116,
|
| 219 |
"eval_macro avg": {
|
| 220 |
+
"f1-score": 0.7750036039222473,
|
| 221 |
+
"precision": 0.787647774970266,
|
| 222 |
+
"recall": 0.7644982297578727,
|
| 223 |
+
"support": 29334.0
|
| 224 |
+
},
|
| 225 |
+
"eval_runtime": 5.8534,
|
| 226 |
+
"eval_samples_per_second": 13.667,
|
| 227 |
+
"eval_steps_per_second": 1.708,
|
| 228 |
"eval_weighted avg": {
|
| 229 |
+
"f1-score": 0.8323176558681596,
|
| 230 |
+
"precision": 0.8327711951367025,
|
| 231 |
+
"recall": 0.8329242517215518,
|
| 232 |
+
"support": 29334.0
|
| 233 |
},
|
| 234 |
"step": 405
|
| 235 |
},
|
| 236 |
{
|
| 237 |
"epoch": 6.0,
|
| 238 |
"eval_Claim": {
|
| 239 |
+
"f1-score": 0.5991994252283692,
|
| 240 |
+
"precision": 0.5325670498084292,
|
| 241 |
+
"recall": 0.6848897231346786,
|
| 242 |
+
"support": 4262.0
|
| 243 |
},
|
| 244 |
"eval_MajorClaim": {
|
| 245 |
+
"f1-score": 0.7586672669968483,
|
| 246 |
+
"precision": 0.7400087834870444,
|
| 247 |
+
"recall": 0.7782909930715936,
|
| 248 |
+
"support": 2165.0
|
| 249 |
},
|
| 250 |
"eval_O": {
|
| 251 |
+
"f1-score": 0.8972759409440632,
|
| 252 |
+
"precision": 0.9212211784799317,
|
| 253 |
+
"recall": 0.8745439805431698,
|
| 254 |
+
"support": 9868.0
|
| 255 |
},
|
| 256 |
"eval_Premise": {
|
| 257 |
+
"f1-score": 0.8764605695726225,
|
| 258 |
+
"precision": 0.9062909567496723,
|
| 259 |
+
"recall": 0.8485313290896541,
|
| 260 |
+
"support": 13039.0
|
| 261 |
},
|
| 262 |
+
"eval_accuracy": 0.8283220835890094,
|
| 263 |
+
"eval_loss": 0.5790187120437622,
|
| 264 |
"eval_macro avg": {
|
| 265 |
+
"f1-score": 0.7829008006854759,
|
| 266 |
+
"precision": 0.7750219921312693,
|
| 267 |
+
"recall": 0.796564006459774,
|
| 268 |
+
"support": 29334.0
|
| 269 |
+
},
|
| 270 |
+
"eval_runtime": 5.8468,
|
| 271 |
+
"eval_samples_per_second": 13.683,
|
| 272 |
+
"eval_steps_per_second": 1.71,
|
| 273 |
"eval_weighted avg": {
|
| 274 |
+
"f1-score": 0.8344852708551485,
|
| 275 |
+
"precision": 0.8447418748493872,
|
| 276 |
+
"recall": 0.8283220835890094,
|
| 277 |
+
"support": 29334.0
|
| 278 |
},
|
| 279 |
"step": 486
|
| 280 |
},
|
| 281 |
{
|
| 282 |
"epoch": 6.17,
|
| 283 |
+
"grad_norm": 6.636661529541016,
|
| 284 |
+
"learning_rate": 1.3827160493827162e-05,
|
| 285 |
+
"loss": 0.3561,
|
| 286 |
"step": 500
|
| 287 |
},
|
| 288 |
{
|
| 289 |
"epoch": 7.0,
|
| 290 |
"eval_Claim": {
|
| 291 |
+
"f1-score": 0.5628712871287128,
|
| 292 |
+
"precision": 0.5955997904662127,
|
| 293 |
+
"recall": 0.5335523228531206,
|
| 294 |
+
"support": 4262.0
|
| 295 |
},
|
| 296 |
"eval_MajorClaim": {
|
| 297 |
+
"f1-score": 0.7734199350487135,
|
| 298 |
+
"precision": 0.8422198041349293,
|
| 299 |
+
"recall": 0.7150115473441109,
|
| 300 |
+
"support": 2165.0
|
| 301 |
},
|
| 302 |
"eval_O": {
|
| 303 |
+
"f1-score": 0.9010954940057875,
|
| 304 |
+
"precision": 0.9193378321383383,
|
| 305 |
+
"recall": 0.8835630320226996,
|
| 306 |
+
"support": 9868.0
|
| 307 |
},
|
| 308 |
"eval_Premise": {
|
| 309 |
+
"f1-score": 0.8842947894099071,
|
| 310 |
+
"precision": 0.848316189939411,
|
| 311 |
+
"recall": 0.9234603880665695,
|
| 312 |
+
"support": 13039.0
|
| 313 |
},
|
| 314 |
+
"eval_accuracy": 0.838003681734506,
|
| 315 |
+
"eval_loss": 0.7058164477348328,
|
| 316 |
"eval_macro avg": {
|
| 317 |
+
"f1-score": 0.7804203763982802,
|
| 318 |
+
"precision": 0.8013684041697228,
|
| 319 |
+
"recall": 0.7638968225716252,
|
| 320 |
+
"support": 29334.0
|
| 321 |
+
},
|
| 322 |
+
"eval_runtime": 5.8534,
|
| 323 |
+
"eval_samples_per_second": 13.667,
|
| 324 |
+
"eval_steps_per_second": 1.708,
|
| 325 |
"eval_weighted avg": {
|
| 326 |
+
"f1-score": 0.835063123988816,
|
| 327 |
+
"precision": 0.8350403187795808,
|
| 328 |
+
"recall": 0.838003681734506,
|
| 329 |
+
"support": 29334.0
|
| 330 |
},
|
| 331 |
"step": 567
|
| 332 |
},
|
| 333 |
{
|
| 334 |
"epoch": 8.0,
|
| 335 |
"eval_Claim": {
|
| 336 |
+
"f1-score": 0.5638466220328667,
|
| 337 |
+
"precision": 0.5858841386288894,
|
| 338 |
+
"recall": 0.5434068512435476,
|
| 339 |
+
"support": 4262.0
|
| 340 |
},
|
| 341 |
"eval_MajorClaim": {
|
| 342 |
+
"f1-score": 0.7606318347509112,
|
| 343 |
+
"precision": 0.8025641025641026,
|
| 344 |
+
"recall": 0.7228637413394919,
|
| 345 |
+
"support": 2165.0
|
| 346 |
},
|
| 347 |
"eval_O": {
|
| 348 |
+
"f1-score": 0.896161170692593,
|
| 349 |
+
"precision": 0.8864763037874281,
|
| 350 |
+
"recall": 0.9060599918929875,
|
| 351 |
+
"support": 9868.0
|
| 352 |
},
|
| 353 |
"eval_Premise": {
|
| 354 |
+
"f1-score": 0.8909187386294724,
|
| 355 |
+
"precision": 0.8807043836642937,
|
| 356 |
+
"recall": 0.9013728046629342,
|
| 357 |
+
"support": 13039.0
|
| 358 |
},
|
| 359 |
+
"eval_accuracy": 0.8377650507943001,
|
| 360 |
+
"eval_loss": 0.6875935196876526,
|
| 361 |
"eval_macro avg": {
|
| 362 |
+
"f1-score": 0.7778895915264609,
|
| 363 |
+
"precision": 0.7889072321611785,
|
| 364 |
+
"recall": 0.7684258472847404,
|
| 365 |
+
"support": 29334.0
|
| 366 |
+
},
|
| 367 |
+
"eval_runtime": 5.8627,
|
| 368 |
+
"eval_samples_per_second": 13.646,
|
| 369 |
+
"eval_steps_per_second": 1.706,
|
| 370 |
"eval_weighted avg": {
|
| 371 |
+
"f1-score": 0.8355454452418354,
|
| 372 |
+
"precision": 0.8340438435010799,
|
| 373 |
+
"recall": 0.8377650507943001,
|
| 374 |
+
"support": 29334.0
|
| 375 |
},
|
| 376 |
"step": 648
|
| 377 |
},
|
| 378 |
{
|
| 379 |
"epoch": 9.0,
|
| 380 |
"eval_Claim": {
|
| 381 |
+
"f1-score": 0.5931978798586572,
|
| 382 |
+
"precision": 0.5602836879432624,
|
| 383 |
+
"recall": 0.6302205537306429,
|
| 384 |
+
"support": 4262.0
|
| 385 |
},
|
| 386 |
"eval_MajorClaim": {
|
| 387 |
+
"f1-score": 0.7739087788131438,
|
| 388 |
+
"precision": 0.8248823836905385,
|
| 389 |
+
"recall": 0.7288683602771363,
|
| 390 |
+
"support": 2165.0
|
| 391 |
},
|
| 392 |
"eval_O": {
|
| 393 |
+
"f1-score": 0.8940459939094823,
|
| 394 |
+
"precision": 0.927653083460449,
|
| 395 |
+
"recall": 0.8627888123226591,
|
| 396 |
+
"support": 9868.0
|
| 397 |
},
|
| 398 |
"eval_Premise": {
|
| 399 |
+
"f1-score": 0.8843249773482331,
|
| 400 |
+
"precision": 0.8708454160160607,
|
| 401 |
+
"recall": 0.8982283917478334,
|
| 402 |
+
"support": 13039.0
|
| 403 |
},
|
| 404 |
+
"eval_accuracy": 0.8348673893775141,
|
| 405 |
+
"eval_loss": 0.6963120698928833,
|
| 406 |
"eval_macro avg": {
|
| 407 |
+
"f1-score": 0.786369407482379,
|
| 408 |
+
"precision": 0.7959161427775777,
|
| 409 |
+
"recall": 0.7800265295195679,
|
| 410 |
+
"support": 29334.0
|
| 411 |
+
},
|
| 412 |
+
"eval_runtime": 5.8671,
|
| 413 |
+
"eval_samples_per_second": 13.635,
|
| 414 |
+
"eval_steps_per_second": 1.704,
|
| 415 |
"eval_weighted avg": {
|
| 416 |
+
"f1-score": 0.8371473756606818,
|
| 417 |
+
"precision": 0.8414411074427396,
|
| 418 |
+
"recall": 0.8348673893775141,
|
| 419 |
+
"support": 29334.0
|
| 420 |
},
|
| 421 |
"step": 729
|
| 422 |
},
|
| 423 |
{
|
| 424 |
"epoch": 10.0,
|
| 425 |
"eval_Claim": {
|
| 426 |
+
"f1-score": 0.5676917638741604,
|
| 427 |
+
"precision": 0.5701775147928994,
|
| 428 |
+
"recall": 0.5652275926794932,
|
| 429 |
+
"support": 4262.0
|
| 430 |
},
|
| 431 |
"eval_MajorClaim": {
|
| 432 |
+
"f1-score": 0.7616811458088754,
|
| 433 |
+
"precision": 0.7745940783190067,
|
| 434 |
+
"recall": 0.7491916859122402,
|
| 435 |
+
"support": 2165.0
|
| 436 |
},
|
| 437 |
"eval_O": {
|
| 438 |
+
"f1-score": 0.9002143118498772,
|
| 439 |
+
"precision": 0.9296124365756234,
|
| 440 |
+
"recall": 0.8726185650587759,
|
| 441 |
+
"support": 9868.0
|
| 442 |
},
|
| 443 |
"eval_Premise": {
|
| 444 |
+
"f1-score": 0.8900003732596766,
|
| 445 |
+
"precision": 0.8669284467713787,
|
| 446 |
+
"recall": 0.9143339213129841,
|
| 447 |
+
"support": 13039.0
|
| 448 |
},
|
| 449 |
+
"eval_accuracy": 0.8373900593168337,
|
| 450 |
+
"eval_loss": 0.7715491056442261,
|
| 451 |
"eval_macro avg": {
|
| 452 |
+
"f1-score": 0.7798968986981474,
|
| 453 |
+
"precision": 0.785328119114727,
|
| 454 |
+
"recall": 0.7753429412408733,
|
| 455 |
+
"support": 29334.0
|
| 456 |
+
},
|
| 457 |
+
"eval_runtime": 5.8552,
|
| 458 |
+
"eval_samples_per_second": 13.663,
|
| 459 |
+
"eval_steps_per_second": 1.708,
|
| 460 |
"eval_weighted avg": {
|
| 461 |
+
"f1-score": 0.8371368267053725,
|
| 462 |
+
"precision": 0.8380850988337167,
|
| 463 |
+
"recall": 0.8373900593168337,
|
| 464 |
+
"support": 29334.0
|
| 465 |
},
|
| 466 |
"step": 810
|
| 467 |
},
|
| 468 |
{
|
| 469 |
"epoch": 11.0,
|
| 470 |
"eval_Claim": {
|
| 471 |
+
"f1-score": 0.5986891586977544,
|
| 472 |
+
"precision": 0.5522299306243805,
|
| 473 |
+
"recall": 0.6536837165649929,
|
| 474 |
+
"support": 4262.0
|
| 475 |
},
|
| 476 |
"eval_MajorClaim": {
|
| 477 |
+
"f1-score": 0.760990850256639,
|
| 478 |
+
"precision": 0.7361830742659758,
|
| 479 |
+
"recall": 0.7875288683602771,
|
| 480 |
+
"support": 2165.0
|
| 481 |
},
|
| 482 |
"eval_O": {
|
| 483 |
+
"f1-score": 0.8930523028883683,
|
| 484 |
+
"precision": 0.9179415855354659,
|
| 485 |
+
"recall": 0.8694770976895014,
|
| 486 |
+
"support": 9868.0
|
| 487 |
},
|
| 488 |
"eval_Premise": {
|
| 489 |
+
"f1-score": 0.8843171634521723,
|
| 490 |
+
"precision": 0.8987802946301283,
|
| 491 |
+
"recall": 0.8703121405015722,
|
| 492 |
+
"support": 13039.0
|
| 493 |
},
|
| 494 |
+
"eval_accuracy": 0.83244698984114,
|
| 495 |
+
"eval_loss": 0.7798097133636475,
|
| 496 |
"eval_macro avg": {
|
| 497 |
+
"f1-score": 0.7842623688237336,
|
| 498 |
+
"precision": 0.7762837212639876,
|
| 499 |
+
"recall": 0.795250455779086,
|
| 500 |
+
"support": 29334.0
|
| 501 |
+
},
|
| 502 |
+
"eval_runtime": 5.8447,
|
| 503 |
+
"eval_samples_per_second": 13.688,
|
| 504 |
+
"eval_steps_per_second": 1.711,
|
| 505 |
"eval_weighted avg": {
|
| 506 |
+
"f1-score": 0.8366540534646059,
|
| 507 |
+
"precision": 0.8428746215263233,
|
| 508 |
+
"recall": 0.83244698984114,
|
| 509 |
+
"support": 29334.0
|
| 510 |
},
|
| 511 |
"step": 891
|
| 512 |
},
|
| 513 |
{
|
| 514 |
"epoch": 12.0,
|
| 515 |
"eval_Claim": {
|
| 516 |
+
"f1-score": 0.5911446066886481,
|
| 517 |
+
"precision": 0.5933806146572104,
|
| 518 |
+
"recall": 0.5889253871421868,
|
| 519 |
+
"support": 4262.0
|
| 520 |
},
|
| 521 |
"eval_MajorClaim": {
|
| 522 |
+
"f1-score": 0.7685296234108899,
|
| 523 |
+
"precision": 0.7994011976047904,
|
| 524 |
+
"recall": 0.7399538106235566,
|
| 525 |
+
"support": 2165.0
|
| 526 |
},
|
| 527 |
"eval_O": {
|
| 528 |
+
"f1-score": 0.8974528445777621,
|
| 529 |
+
"precision": 0.9005203550658096,
|
| 530 |
+
"recall": 0.8944061613295501,
|
| 531 |
+
"support": 9868.0
|
| 532 |
},
|
| 533 |
"eval_Premise": {
|
| 534 |
+
"f1-score": 0.8881464044346572,
|
| 535 |
+
"precision": 0.8794646214001053,
|
| 536 |
+
"recall": 0.8970013037809648,
|
| 537 |
+
"support": 13039.0
|
| 538 |
},
|
| 539 |
+
"eval_accuracy": 0.8397763687188927,
|
| 540 |
+
"eval_loss": 0.8434343338012695,
|
| 541 |
"eval_macro avg": {
|
| 542 |
+
"f1-score": 0.7863183697779894,
|
| 543 |
+
"precision": 0.7931916971819789,
|
| 544 |
+
"recall": 0.7800716657190646,
|
| 545 |
+
"support": 29334.0
|
| 546 |
+
},
|
| 547 |
+
"eval_runtime": 5.824,
|
| 548 |
+
"eval_samples_per_second": 13.736,
|
| 549 |
+
"eval_steps_per_second": 1.717,
|
| 550 |
"eval_weighted avg": {
|
| 551 |
+
"f1-score": 0.8392967405095946,
|
| 552 |
+
"precision": 0.8390729472526346,
|
| 553 |
+
"recall": 0.8397763687188927,
|
| 554 |
+
"support": 29334.0
|
| 555 |
},
|
| 556 |
"step": 972
|
| 557 |
},
|
| 558 |
{
|
| 559 |
"epoch": 12.35,
|
| 560 |
+
"grad_norm": 8.536613464355469,
|
| 561 |
+
"learning_rate": 7.654320987654322e-06,
|
| 562 |
+
"loss": 0.0633,
|
| 563 |
"step": 1000
|
| 564 |
},
|
| 565 |
{
|
| 566 |
"epoch": 13.0,
|
| 567 |
"eval_Claim": {
|
| 568 |
+
"f1-score": 0.5875576036866359,
|
| 569 |
+
"precision": 0.5771842462652784,
|
| 570 |
+
"recall": 0.5983106522759268,
|
| 571 |
+
"support": 4262.0
|
| 572 |
},
|
| 573 |
"eval_MajorClaim": {
|
| 574 |
+
"f1-score": 0.7726320688852689,
|
| 575 |
+
"precision": 0.7786116322701688,
|
| 576 |
+
"recall": 0.766743648960739,
|
| 577 |
+
"support": 2165.0
|
| 578 |
},
|
| 579 |
"eval_O": {
|
| 580 |
+
"f1-score": 0.8950658744510462,
|
| 581 |
+
"precision": 0.9130388953304522,
|
| 582 |
+
"recall": 0.8777867855695176,
|
| 583 |
+
"support": 9868.0
|
| 584 |
},
|
| 585 |
"eval_Premise": {
|
| 586 |
+
"f1-score": 0.8827460510328068,
|
| 587 |
+
"precision": 0.8741821463488004,
|
| 588 |
+
"recall": 0.891479407930056,
|
| 589 |
+
"support": 13039.0
|
| 590 |
},
|
| 591 |
+
"eval_accuracy": 0.835071930183405,
|
| 592 |
+
"eval_loss": 0.9362213015556335,
|
| 593 |
"eval_macro avg": {
|
| 594 |
+
"f1-score": 0.7845003995139396,
|
| 595 |
+
"precision": 0.785754230053675,
|
| 596 |
+
"recall": 0.7835801236840598,
|
| 597 |
+
"support": 29334.0
|
| 598 |
+
},
|
| 599 |
+
"eval_runtime": 5.8402,
|
| 600 |
+
"eval_samples_per_second": 13.698,
|
| 601 |
+
"eval_steps_per_second": 1.712,
|
| 602 |
"eval_weighted avg": {
|
| 603 |
+
"f1-score": 0.83587491458883,
|
| 604 |
+
"precision": 0.8370485534468686,
|
| 605 |
+
"recall": 0.835071930183405,
|
| 606 |
+
"support": 29334.0
|
| 607 |
},
|
| 608 |
"step": 1053
|
| 609 |
},
|
| 610 |
{
|
| 611 |
"epoch": 14.0,
|
| 612 |
"eval_Claim": {
|
| 613 |
+
"f1-score": 0.5757274309873166,
|
| 614 |
+
"precision": 0.6124338624338624,
|
| 615 |
+
"recall": 0.5431722196152041,
|
| 616 |
+
"support": 4262.0
|
| 617 |
},
|
| 618 |
"eval_MajorClaim": {
|
| 619 |
+
"f1-score": 0.7806691449814126,
|
| 620 |
+
"precision": 0.7854137447405329,
|
| 621 |
+
"recall": 0.7759815242494227,
|
| 622 |
+
"support": 2165.0
|
| 623 |
},
|
| 624 |
"eval_O": {
|
| 625 |
+
"f1-score": 0.894971487817522,
|
| 626 |
+
"precision": 0.916153682869879,
|
| 627 |
+
"recall": 0.8747466558573166,
|
| 628 |
+
"support": 9868.0
|
| 629 |
},
|
| 630 |
"eval_Premise": {
|
| 631 |
+
"f1-score": 0.8893903521751998,
|
| 632 |
+
"precision": 0.8590723933395269,
|
| 633 |
+
"recall": 0.9219265281079837,
|
| 634 |
+
"support": 13039.0
|
| 635 |
},
|
| 636 |
+
"eval_accuracy": 0.8402536305993046,
|
| 637 |
+
"eval_loss": 1.0311453342437744,
|
| 638 |
"eval_macro avg": {
|
| 639 |
+
"f1-score": 0.7851896039903627,
|
| 640 |
+
"precision": 0.7932684208459503,
|
| 641 |
+
"recall": 0.7789567319574817,
|
| 642 |
+
"support": 29334.0
|
| 643 |
+
},
|
| 644 |
+
"eval_runtime": 5.8463,
|
| 645 |
+
"eval_samples_per_second": 13.684,
|
| 646 |
+
"eval_steps_per_second": 1.71,
|
| 647 |
"eval_weighted avg": {
|
| 648 |
+
"f1-score": 0.8376709093048489,
|
| 649 |
+
"precision": 0.8370035916809992,
|
| 650 |
+
"recall": 0.8402536305993046,
|
| 651 |
+
"support": 29334.0
|
| 652 |
},
|
| 653 |
"step": 1134
|
| 654 |
},
|
| 655 |
{
|
| 656 |
"epoch": 15.0,
|
| 657 |
"eval_Claim": {
|
| 658 |
+
"f1-score": 0.5845799769850402,
|
| 659 |
+
"precision": 0.5736224028906955,
|
| 660 |
+
"recall": 0.5959643359924918,
|
| 661 |
+
"support": 4262.0
|
| 662 |
},
|
| 663 |
"eval_MajorClaim": {
|
| 664 |
+
"f1-score": 0.7613293051359518,
|
| 665 |
+
"precision": 0.8367459878251245,
|
| 666 |
+
"recall": 0.6983833718244804,
|
| 667 |
+
"support": 2165.0
|
| 668 |
},
|
| 669 |
"eval_O": {
|
| 670 |
+
"f1-score": 0.8997656860192659,
|
| 671 |
+
"precision": 0.9253507550605119,
|
| 672 |
+
"recall": 0.8755573571139035,
|
| 673 |
+
"support": 9868.0
|
| 674 |
},
|
| 675 |
"eval_Premise": {
|
| 676 |
+
"f1-score": 0.8875041976045669,
|
| 677 |
+
"precision": 0.8641912512716174,
|
| 678 |
+
"recall": 0.9121098243730348,
|
| 679 |
+
"support": 13039.0
|
| 680 |
},
|
| 681 |
+
"eval_accuracy": 0.8381059521374514,
|
| 682 |
+
"eval_loss": 1.0062618255615234,
|
| 683 |
"eval_macro avg": {
|
| 684 |
+
"f1-score": 0.7832947914362062,
|
| 685 |
+
"precision": 0.7999775992619873,
|
| 686 |
+
"recall": 0.7705037223259776,
|
| 687 |
+
"support": 29334.0
|
| 688 |
+
},
|
| 689 |
+
"eval_runtime": 5.8597,
|
| 690 |
+
"eval_samples_per_second": 13.653,
|
| 691 |
+
"eval_steps_per_second": 1.707,
|
| 692 |
"eval_weighted avg": {
|
| 693 |
+
"f1-score": 0.8383041122838222,
|
| 694 |
+
"precision": 0.8405224217982303,
|
| 695 |
+
"recall": 0.8381059521374514,
|
| 696 |
+
"support": 29334.0
|
| 697 |
},
|
| 698 |
"step": 1215
|
| 699 |
},
|
| 700 |
{
|
| 701 |
"epoch": 16.0,
|
| 702 |
"eval_Claim": {
|
| 703 |
+
"f1-score": 0.587790910198611,
|
| 704 |
+
"precision": 0.6114068441064638,
|
| 705 |
+
"recall": 0.5659314875645237,
|
| 706 |
+
"support": 4262.0
|
| 707 |
},
|
| 708 |
"eval_MajorClaim": {
|
| 709 |
+
"f1-score": 0.7780703854440987,
|
| 710 |
+
"precision": 0.8076540755467196,
|
| 711 |
+
"recall": 0.7505773672055427,
|
| 712 |
+
"support": 2165.0
|
| 713 |
},
|
| 714 |
"eval_O": {
|
| 715 |
+
"f1-score": 0.8989037758830695,
|
| 716 |
+
"precision": 0.9003660024400163,
|
| 717 |
+
"recall": 0.8974462910417511,
|
| 718 |
+
"support": 9868.0
|
| 719 |
},
|
| 720 |
"eval_Premise": {
|
| 721 |
+
"f1-score": 0.89104589917231,
|
| 722 |
+
"precision": 0.8745292075917583,
|
| 723 |
+
"recall": 0.908198481478641,
|
| 724 |
+
"support": 13039.0
|
| 725 |
},
|
| 726 |
+
"eval_accuracy": 0.8432194722847208,
|
| 727 |
+
"eval_loss": 0.9864347577095032,
|
| 728 |
"eval_macro avg": {
|
| 729 |
+
"f1-score": 0.7889527426745223,
|
| 730 |
+
"precision": 0.7984890324212395,
|
| 731 |
+
"recall": 0.7805384068226147,
|
| 732 |
+
"support": 29334.0
|
| 733 |
+
},
|
| 734 |
+
"eval_runtime": 5.8915,
|
| 735 |
+
"eval_samples_per_second": 13.579,
|
| 736 |
+
"eval_steps_per_second": 1.697,
|
| 737 |
"eval_weighted avg": {
|
| 738 |
+
"f1-score": 0.8412905564694496,
|
| 739 |
+
"precision": 0.8400553996388973,
|
| 740 |
+
"recall": 0.8432194722847208,
|
| 741 |
+
"support": 29334.0
|
| 742 |
},
|
| 743 |
"step": 1296
|
| 744 |
},
|
| 745 |
{
|
| 746 |
"epoch": 17.0,
|
| 747 |
"eval_Claim": {
|
| 748 |
+
"f1-score": 0.5855803726420553,
|
| 749 |
+
"precision": 0.5777574788764558,
|
| 750 |
+
"recall": 0.5936180197090568,
|
| 751 |
+
"support": 4262.0
|
| 752 |
},
|
| 753 |
"eval_MajorClaim": {
|
| 754 |
+
"f1-score": 0.7654614652711702,
|
| 755 |
+
"precision": 0.7891123099558607,
|
| 756 |
+
"recall": 0.7431870669745958,
|
| 757 |
+
"support": 2165.0
|
| 758 |
},
|
| 759 |
"eval_O": {
|
| 760 |
+
"f1-score": 0.9005902941022829,
|
| 761 |
+
"precision": 0.9293800539083558,
|
| 762 |
+
"recall": 0.8735306039724362,
|
| 763 |
+
"support": 9868.0
|
| 764 |
},
|
| 765 |
"eval_Premise": {
|
| 766 |
+
"f1-score": 0.8890554722638682,
|
| 767 |
+
"precision": 0.869437724507001,
|
| 768 |
+
"recall": 0.9095789554413682,
|
| 769 |
+
"support": 13039.0
|
| 770 |
},
|
| 771 |
+
"eval_accuracy": 0.8392650167041659,
|
| 772 |
+
"eval_loss": 1.047443151473999,
|
| 773 |
"eval_macro avg": {
|
| 774 |
+
"f1-score": 0.7851719010698441,
|
| 775 |
+
"precision": 0.7914218918119184,
|
| 776 |
+
"recall": 0.7799786615243642,
|
| 777 |
+
"support": 29334.0
|
| 778 |
+
},
|
| 779 |
+
"eval_runtime": 5.8682,
|
| 780 |
+
"eval_samples_per_second": 13.633,
|
| 781 |
+
"eval_steps_per_second": 1.704,
|
| 782 |
"eval_weighted avg": {
|
| 783 |
+
"f1-score": 0.8397213794764584,
|
| 784 |
+
"precision": 0.8412951315142951,
|
| 785 |
+
"recall": 0.8392650167041659,
|
| 786 |
+
"support": 29334.0
|
| 787 |
},
|
| 788 |
"step": 1377
|
| 789 |
},
|
| 790 |
{
|
| 791 |
"epoch": 18.0,
|
| 792 |
"eval_Claim": {
|
| 793 |
+
"f1-score": 0.5782873522035114,
|
| 794 |
+
"precision": 0.5889078083191438,
|
| 795 |
+
"recall": 0.5680431722196152,
|
| 796 |
+
"support": 4262.0
|
| 797 |
},
|
| 798 |
"eval_MajorClaim": {
|
| 799 |
+
"f1-score": 0.7745774815520113,
|
| 800 |
+
"precision": 0.7991159135559921,
|
| 801 |
+
"recall": 0.751501154734411,
|
| 802 |
+
"support": 2165.0
|
| 803 |
},
|
| 804 |
"eval_O": {
|
| 805 |
+
"f1-score": 0.8985953040090229,
|
| 806 |
+
"precision": 0.9093172857439302,
|
| 807 |
+
"recall": 0.8881232265910012,
|
| 808 |
+
"support": 9868.0
|
| 809 |
},
|
| 810 |
"eval_Premise": {
|
| 811 |
+
"f1-score": 0.8900255754475703,
|
| 812 |
+
"precision": 0.8732747804265998,
|
| 813 |
+
"recall": 0.9074315514993481,
|
| 814 |
+
"support": 13039.0
|
| 815 |
},
|
| 816 |
+
"eval_accuracy": 0.8401172700620441,
|
| 817 |
+
"eval_loss": 1.0609416961669922,
|
| 818 |
"eval_macro avg": {
|
| 819 |
+
"f1-score": 0.7853714283030289,
|
| 820 |
+
"precision": 0.7926539470114164,
|
| 821 |
+
"recall": 0.7787747762610939,
|
| 822 |
+
"support": 29334.0
|
| 823 |
+
},
|
| 824 |
+
"eval_runtime": 5.8605,
|
| 825 |
+
"eval_samples_per_second": 13.651,
|
| 826 |
+
"eval_steps_per_second": 1.706,
|
| 827 |
"eval_weighted avg": {
|
| 828 |
+
"f1-score": 0.8390946642419506,
|
| 829 |
+
"precision": 0.8386099362381009,
|
| 830 |
+
"recall": 0.8401172700620441,
|
| 831 |
+
"support": 29334.0
|
| 832 |
},
|
| 833 |
"step": 1458
|
| 834 |
},
|
| 835 |
{
|
| 836 |
"epoch": 18.52,
|
| 837 |
+
"grad_norm": 4.270083904266357,
|
| 838 |
+
"learning_rate": 1.4814814814814815e-06,
|
| 839 |
+
"loss": 0.0173,
|
| 840 |
"step": 1500
|
| 841 |
},
|
| 842 |
{
|
| 843 |
"epoch": 19.0,
|
| 844 |
"eval_Claim": {
|
| 845 |
+
"f1-score": 0.5749491565976791,
|
| 846 |
+
"precision": 0.586526726873322,
|
| 847 |
+
"recall": 0.5638198029094322,
|
| 848 |
+
"support": 4262.0
|
| 849 |
},
|
| 850 |
"eval_MajorClaim": {
|
| 851 |
+
"f1-score": 0.7698686938493434,
|
| 852 |
+
"precision": 0.7679227941176471,
|
| 853 |
+
"recall": 0.771824480369515,
|
| 854 |
+
"support": 2165.0
|
| 855 |
},
|
| 856 |
"eval_O": {
|
| 857 |
+
"f1-score": 0.8996305739112337,
|
| 858 |
+
"precision": 0.9245000534702171,
|
| 859 |
+
"recall": 0.8760640453992704,
|
| 860 |
+
"support": 9868.0
|
| 861 |
},
|
| 862 |
"eval_Premise": {
|
| 863 |
+
"f1-score": 0.8893042730569367,
|
| 864 |
+
"precision": 0.8675419401896426,
|
| 865 |
+
"recall": 0.912186517370964,
|
| 866 |
+
"support": 13039.0
|
| 867 |
},
|
| 868 |
+
"eval_accuracy": 0.839060475898275,
|
| 869 |
+
"eval_loss": 1.0791102647781372,
|
| 870 |
"eval_macro avg": {
|
| 871 |
+
"f1-score": 0.7834381743537983,
|
| 872 |
+
"precision": 0.7866228786627072,
|
| 873 |
+
"recall": 0.7809737115122954,
|
| 874 |
+
"support": 29334.0
|
| 875 |
+
},
|
| 876 |
+
"eval_runtime": 5.8481,
|
| 877 |
+
"eval_samples_per_second": 13.68,
|
| 878 |
+
"eval_steps_per_second": 1.71,
|
| 879 |
"eval_weighted avg": {
|
| 880 |
+
"f1-score": 0.8382897643467849,
|
| 881 |
+
"precision": 0.8385210215100449,
|
| 882 |
+
"recall": 0.839060475898275,
|
| 883 |
+
"support": 29334.0
|
| 884 |
},
|
| 885 |
"step": 1539
|
| 886 |
},
|
| 887 |
{
|
| 888 |
"epoch": 20.0,
|
| 889 |
"eval_Claim": {
|
| 890 |
+
"f1-score": 0.5779213012797513,
|
| 891 |
+
"precision": 0.5894120517199317,
|
| 892 |
+
"recall": 0.5668700140778977,
|
| 893 |
+
"support": 4262.0
|
| 894 |
},
|
| 895 |
"eval_MajorClaim": {
|
| 896 |
+
"f1-score": 0.7734703409621673,
|
| 897 |
+
"precision": 0.7822390174775626,
|
| 898 |
+
"recall": 0.7648960739030023,
|
| 899 |
+
"support": 2165.0
|
| 900 |
},
|
| 901 |
"eval_O": {
|
| 902 |
+
"f1-score": 0.8994424943217014,
|
| 903 |
+
"precision": 0.9166666666666666,
|
| 904 |
+
"recall": 0.882853668423186,
|
| 905 |
+
"support": 9868.0
|
| 906 |
},
|
| 907 |
"eval_Premise": {
|
| 908 |
+
"f1-score": 0.889580910216486,
|
| 909 |
+
"precision": 0.8707947700896136,
|
| 910 |
+
"recall": 0.9091954904517218,
|
| 911 |
+
"support": 13039.0
|
| 912 |
},
|
| 913 |
+
"eval_accuracy": 0.8399468193904684,
|
| 914 |
+
"eval_loss": 1.066952109336853,
|
| 915 |
"eval_macro avg": {
|
| 916 |
+
"f1-score": 0.7851037616950265,
|
| 917 |
+
"precision": 0.7897781264884436,
|
| 918 |
+
"recall": 0.780953811713952,
|
| 919 |
+
"support": 29334.0
|
| 920 |
+
},
|
| 921 |
+
"eval_runtime": 5.8988,
|
| 922 |
+
"eval_samples_per_second": 13.562,
|
| 923 |
+
"eval_steps_per_second": 1.695,
|
| 924 |
"eval_weighted avg": {
|
| 925 |
+
"f1-score": 0.8390471090378641,
|
| 926 |
+
"precision": 0.8388075717984049,
|
| 927 |
+
"recall": 0.8399468193904684,
|
| 928 |
+
"support": 29334.0
|
| 929 |
},
|
| 930 |
"step": 1620
|
| 931 |
}
|
| 932 |
],
|
| 933 |
"logging_steps": 500,
|
| 934 |
+
"max_steps": 1620,
|
| 935 |
"num_input_tokens_seen": 0,
|
| 936 |
+
"num_train_epochs": 20,
|
| 937 |
"save_steps": 500,
|
| 938 |
"total_flos": 2875774654536000.0,
|
| 939 |
"train_batch_size": 4,
|
checkpoint-1620/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 sha256:91855299d72d2ceb66b00b0c173ef2e96bd5d782fa49a7debc2d6f3b7cbd2cd4
|
| 3 |
size 4856
|