Model save
Browse files- README.md +9 -12
- adapter_config.json +3 -3
- adapter_model.safetensors +1 -1
- all_results.json +8 -8
- eval_results.json +4 -4
- train_results.json +4 -4
- trainer_state.json +137 -123
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -2,13 +2,9 @@
|
|
| 2 |
license: other
|
| 3 |
library_name: peft
|
| 4 |
tags:
|
| 5 |
-
- alignment-handbook
|
| 6 |
-
- generated_from_trainer
|
| 7 |
- trl
|
| 8 |
- sft
|
| 9 |
- generated_from_trainer
|
| 10 |
-
datasets:
|
| 11 |
-
- ruozhiba
|
| 12 |
base_model: 01-ai/Yi-6B
|
| 13 |
model-index:
|
| 14 |
- name: Yi-6B-ruozhiba-1e-5-50
|
|
@@ -20,9 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 20 |
|
| 21 |
# Yi-6B-ruozhiba-1e-5-50
|
| 22 |
|
| 23 |
-
This model is a fine-tuned version of [01-ai/Yi-6B](https://huggingface.co/01-ai/Yi-6B) on the
|
| 24 |
It achieves the following results on the evaluation set:
|
| 25 |
-
- Loss: 1.
|
| 26 |
|
| 27 |
## Model description
|
| 28 |
|
|
@@ -56,12 +52,13 @@ The following hyperparameters were used during training:
|
|
| 56 |
|:-------------:|:-----:|:----:|:---------------:|
|
| 57 |
| 2.6749 | 1.0 | 55 | 2.5387 |
|
| 58 |
| 2.0502 | 3.0 | 165 | 2.0924 |
|
| 59 |
-
| 1.
|
| 60 |
-
|
|
| 61 |
-
| 1.
|
| 62 |
-
| 1.
|
| 63 |
-
| 1.
|
| 64 |
-
| 1.
|
|
|
|
| 65 |
|
| 66 |
|
| 67 |
### Framework versions
|
|
|
|
| 2 |
license: other
|
| 3 |
library_name: peft
|
| 4 |
tags:
|
|
|
|
|
|
|
| 5 |
- trl
|
| 6 |
- sft
|
| 7 |
- generated_from_trainer
|
|
|
|
|
|
|
| 8 |
base_model: 01-ai/Yi-6B
|
| 9 |
model-index:
|
| 10 |
- name: Yi-6B-ruozhiba-1e-5-50
|
|
|
|
| 16 |
|
| 17 |
# Yi-6B-ruozhiba-1e-5-50
|
| 18 |
|
| 19 |
+
This model is a fine-tuned version of [01-ai/Yi-6B](https://huggingface.co/01-ai/Yi-6B) on the None dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 1.9848
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
|
|
| 52 |
|:-------------:|:-----:|:----:|:---------------:|
|
| 53 |
| 2.6749 | 1.0 | 55 | 2.5387 |
|
| 54 |
| 2.0502 | 3.0 | 165 | 2.0924 |
|
| 55 |
+
| 1.953 | 4.0 | 220 | 2.0381 |
|
| 56 |
+
| 1.9412 | 5.0 | 275 | 2.0098 |
|
| 57 |
+
| 1.9044 | 6.0 | 330 | 1.9949 |
|
| 58 |
+
| 1.9567 | 7.0 | 385 | 1.9889 |
|
| 59 |
+
| 1.9235 | 8.0 | 440 | 1.9856 |
|
| 60 |
+
| 1.8121 | 9.0 | 495 | 1.9849 |
|
| 61 |
+
| 1.874 | 10.0 | 550 | 1.9848 |
|
| 62 |
|
| 63 |
|
| 64 |
### Framework versions
|
adapter_config.json
CHANGED
|
@@ -19,12 +19,12 @@
|
|
| 19 |
"rank_pattern": {},
|
| 20 |
"revision": null,
|
| 21 |
"target_modules": [
|
| 22 |
-
"v_proj",
|
| 23 |
-
"k_proj",
|
| 24 |
-
"o_proj",
|
| 25 |
"gate_proj",
|
| 26 |
"q_proj",
|
| 27 |
"up_proj",
|
|
|
|
|
|
|
|
|
|
| 28 |
"down_proj"
|
| 29 |
],
|
| 30 |
"task_type": "CAUSAL_LM"
|
|
|
|
| 19 |
"rank_pattern": {},
|
| 20 |
"revision": null,
|
| 21 |
"target_modules": [
|
|
|
|
|
|
|
|
|
|
| 22 |
"gate_proj",
|
| 23 |
"q_proj",
|
| 24 |
"up_proj",
|
| 25 |
+
"v_proj",
|
| 26 |
+
"k_proj",
|
| 27 |
+
"o_proj",
|
| 28 |
"down_proj"
|
| 29 |
],
|
| 30 |
"task_type": "CAUSAL_LM"
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 145287696
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:100ba1f2d2db812411e9024ecd40df04fae1757af141c2d75c573a9f711135e6
|
| 3 |
size 145287696
|
all_results.json
CHANGED
|
@@ -1,13 +1,13 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 10.0,
|
| 3 |
-
"eval_loss": 1.
|
| 4 |
-
"eval_runtime": 4.
|
| 5 |
"eval_samples": 23,
|
| 6 |
-
"eval_samples_per_second": 4.
|
| 7 |
-
"eval_steps_per_second": 1.
|
| 8 |
-
"train_loss": 1.
|
| 9 |
-
"train_runtime":
|
| 10 |
"train_samples": 217,
|
| 11 |
-
"train_samples_per_second": 0.
|
| 12 |
-
"train_steps_per_second": 0.
|
| 13 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 10.0,
|
| 3 |
+
"eval_loss": 1.9848212003707886,
|
| 4 |
+
"eval_runtime": 4.9008,
|
| 5 |
"eval_samples": 23,
|
| 6 |
+
"eval_samples_per_second": 4.693,
|
| 7 |
+
"eval_steps_per_second": 1.224,
|
| 8 |
+
"train_loss": 1.5526252421465787,
|
| 9 |
+
"train_runtime": 23283.78,
|
| 10 |
"train_samples": 217,
|
| 11 |
+
"train_samples_per_second": 0.093,
|
| 12 |
+
"train_steps_per_second": 0.024
|
| 13 |
}
|
eval_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 10.0,
|
| 3 |
-
"eval_loss": 1.
|
| 4 |
-
"eval_runtime": 4.
|
| 5 |
"eval_samples": 23,
|
| 6 |
-
"eval_samples_per_second": 4.
|
| 7 |
-
"eval_steps_per_second": 1.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 10.0,
|
| 3 |
+
"eval_loss": 1.9848212003707886,
|
| 4 |
+
"eval_runtime": 4.9008,
|
| 5 |
"eval_samples": 23,
|
| 6 |
+
"eval_samples_per_second": 4.693,
|
| 7 |
+
"eval_steps_per_second": 1.224
|
| 8 |
}
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 10.0,
|
| 3 |
-
"train_loss": 1.
|
| 4 |
-
"train_runtime":
|
| 5 |
"train_samples": 217,
|
| 6 |
-
"train_samples_per_second": 0.
|
| 7 |
-
"train_steps_per_second": 0.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 10.0,
|
| 3 |
+
"train_loss": 1.5526252421465787,
|
| 4 |
+
"train_runtime": 23283.78,
|
| 5 |
"train_samples": 217,
|
| 6 |
+
"train_samples_per_second": 0.093,
|
| 7 |
+
"train_steps_per_second": 0.024
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -372,590 +372,604 @@
|
|
| 372 |
"loss": 1.953,
|
| 373 |
"step": 220
|
| 374 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 375 |
{
|
| 376 |
"epoch": 4.07,
|
| 377 |
"learning_rate": 7.3892790165483164e-06,
|
| 378 |
-
"loss": 1.
|
| 379 |
"step": 224
|
| 380 |
},
|
| 381 |
{
|
| 382 |
"epoch": 4.15,
|
| 383 |
"learning_rate": 7.2770182736595164e-06,
|
| 384 |
-
"loss": 2.
|
| 385 |
"step": 228
|
| 386 |
},
|
| 387 |
{
|
| 388 |
"epoch": 4.22,
|
| 389 |
"learning_rate": 7.163290117232542e-06,
|
| 390 |
-
"loss":
|
| 391 |
"step": 232
|
| 392 |
},
|
| 393 |
{
|
| 394 |
"epoch": 4.29,
|
| 395 |
"learning_rate": 7.048167838833977e-06,
|
| 396 |
-
"loss":
|
| 397 |
"step": 236
|
| 398 |
},
|
| 399 |
{
|
| 400 |
"epoch": 4.36,
|
| 401 |
"learning_rate": 6.931725628465643e-06,
|
| 402 |
-
"loss":
|
| 403 |
"step": 240
|
| 404 |
},
|
| 405 |
{
|
| 406 |
"epoch": 4.44,
|
| 407 |
"learning_rate": 6.814038526753205e-06,
|
| 408 |
-
"loss": 1.
|
| 409 |
"step": 244
|
| 410 |
},
|
| 411 |
{
|
| 412 |
"epoch": 4.51,
|
| 413 |
"learning_rate": 6.695182376586603e-06,
|
| 414 |
-
"loss": 1.
|
| 415 |
"step": 248
|
| 416 |
},
|
| 417 |
{
|
| 418 |
"epoch": 4.58,
|
| 419 |
"learning_rate": 6.5752337742434644e-06,
|
| 420 |
-
"loss": 1.
|
| 421 |
"step": 252
|
| 422 |
},
|
| 423 |
{
|
| 424 |
"epoch": 4.65,
|
| 425 |
"learning_rate": 6.454270020026996e-06,
|
| 426 |
-
"loss":
|
| 427 |
"step": 256
|
| 428 |
},
|
| 429 |
{
|
| 430 |
"epoch": 4.73,
|
| 431 |
"learning_rate": 6.332369068450175e-06,
|
| 432 |
-
"loss": 1.
|
| 433 |
"step": 260
|
| 434 |
},
|
| 435 |
{
|
| 436 |
"epoch": 4.8,
|
| 437 |
"learning_rate": 6.209609477998339e-06,
|
| 438 |
-
"loss":
|
| 439 |
"step": 264
|
| 440 |
},
|
| 441 |
{
|
| 442 |
"epoch": 4.87,
|
| 443 |
"learning_rate": 6.08607036050254e-06,
|
| 444 |
-
"loss": 1.
|
| 445 |
"step": 268
|
| 446 |
},
|
| 447 |
{
|
| 448 |
"epoch": 4.95,
|
| 449 |
"learning_rate": 5.961831330156306e-06,
|
| 450 |
-
"loss": 1.
|
| 451 |
"step": 272
|
| 452 |
},
|
| 453 |
{
|
| 454 |
"epoch": 5.0,
|
| 455 |
-
"pls_score": 57.
|
| 456 |
-
"std":
|
| 457 |
"step": 275
|
| 458 |
},
|
| 459 |
{
|
| 460 |
"epoch": 5.0,
|
| 461 |
-
"eval_loss": 2.
|
| 462 |
-
"eval_runtime": 4.
|
| 463 |
-
"eval_samples_per_second": 4.
|
| 464 |
-
"eval_steps_per_second": 1.
|
| 465 |
"step": 275
|
| 466 |
},
|
| 467 |
{
|
| 468 |
"epoch": 5.02,
|
| 469 |
"learning_rate": 5.8369724522086545e-06,
|
| 470 |
-
"loss": 1.
|
| 471 |
"step": 276
|
| 472 |
},
|
| 473 |
{
|
| 474 |
"epoch": 5.09,
|
| 475 |
"learning_rate": 5.711574191366427e-06,
|
| 476 |
-
"loss":
|
| 477 |
"step": 280
|
| 478 |
},
|
| 479 |
{
|
| 480 |
"epoch": 5.16,
|
| 481 |
"learning_rate": 5.585717359939192e-06,
|
| 482 |
-
"loss": 1.
|
| 483 |
"step": 284
|
| 484 |
},
|
| 485 |
{
|
| 486 |
"epoch": 5.24,
|
| 487 |
"learning_rate": 5.459483065760138e-06,
|
| 488 |
-
"loss": 1.
|
| 489 |
"step": 288
|
| 490 |
},
|
| 491 |
{
|
| 492 |
"epoch": 5.31,
|
| 493 |
"learning_rate": 5.33295265991652e-06,
|
| 494 |
-
"loss": 1.
|
| 495 |
"step": 292
|
| 496 |
},
|
| 497 |
{
|
| 498 |
"epoch": 5.38,
|
| 499 |
"learning_rate": 5.206207684323337e-06,
|
| 500 |
-
"loss":
|
| 501 |
"step": 296
|
| 502 |
},
|
| 503 |
{
|
| 504 |
"epoch": 5.45,
|
| 505 |
"learning_rate": 5.07932981917404e-06,
|
| 506 |
-
"loss": 1.
|
| 507 |
"step": 300
|
| 508 |
},
|
| 509 |
{
|
| 510 |
"epoch": 5.53,
|
| 511 |
"learning_rate": 4.952400830302117e-06,
|
| 512 |
-
"loss":
|
| 513 |
"step": 304
|
| 514 |
},
|
| 515 |
{
|
| 516 |
"epoch": 5.6,
|
| 517 |
"learning_rate": 4.825502516487497e-06,
|
| 518 |
-
"loss": 1.
|
| 519 |
"step": 308
|
| 520 |
},
|
| 521 |
{
|
| 522 |
"epoch": 5.67,
|
| 523 |
"learning_rate": 4.6987166567417085e-06,
|
| 524 |
-
"loss": 1.
|
| 525 |
"step": 312
|
| 526 |
},
|
| 527 |
{
|
| 528 |
"epoch": 5.75,
|
| 529 |
"learning_rate": 4.572124957605803e-06,
|
| 530 |
-
"loss": 1.
|
| 531 |
"step": 316
|
| 532 |
},
|
| 533 |
{
|
| 534 |
"epoch": 5.82,
|
| 535 |
"learning_rate": 4.445809000494945e-06,
|
| 536 |
-
"loss": 1.
|
| 537 |
"step": 320
|
| 538 |
},
|
| 539 |
{
|
| 540 |
"epoch": 5.89,
|
| 541 |
"learning_rate": 4.319850189123681e-06,
|
| 542 |
-
"loss": 1.
|
| 543 |
"step": 324
|
| 544 |
},
|
| 545 |
{
|
| 546 |
"epoch": 5.96,
|
| 547 |
"learning_rate": 4.194329697045681e-06,
|
| 548 |
-
"loss":
|
| 549 |
"step": 328
|
| 550 |
},
|
| 551 |
{
|
| 552 |
"epoch": 6.0,
|
| 553 |
-
"pls_score":
|
| 554 |
-
"std": 4.
|
| 555 |
"step": 330
|
| 556 |
},
|
| 557 |
{
|
| 558 |
"epoch": 6.0,
|
| 559 |
-
"eval_loss": 1.
|
| 560 |
-
"eval_runtime": 4.
|
| 561 |
-
"eval_samples_per_second": 4.
|
| 562 |
-
"eval_steps_per_second": 1.
|
| 563 |
"step": 330
|
| 564 |
},
|
| 565 |
{
|
| 566 |
"epoch": 6.04,
|
| 567 |
"learning_rate": 4.06932841534185e-06,
|
| 568 |
-
"loss":
|
| 569 |
"step": 332
|
| 570 |
},
|
| 571 |
{
|
| 572 |
"epoch": 6.11,
|
| 573 |
"learning_rate": 3.944926900490452e-06,
|
| 574 |
-
"loss": 1.
|
| 575 |
"step": 336
|
| 576 |
},
|
| 577 |
{
|
| 578 |
"epoch": 6.18,
|
| 579 |
"learning_rate": 3.821205322452863e-06,
|
| 580 |
-
"loss": 1.
|
| 581 |
"step": 340
|
| 582 |
},
|
| 583 |
{
|
| 584 |
"epoch": 6.25,
|
| 585 |
"learning_rate": 3.69824341300844e-06,
|
| 586 |
-
"loss": 1.
|
| 587 |
"step": 344
|
| 588 |
},
|
| 589 |
{
|
| 590 |
"epoch": 6.33,
|
| 591 |
"learning_rate": 3.5761204143717387e-06,
|
| 592 |
-
"loss": 1.
|
| 593 |
"step": 348
|
| 594 |
},
|
| 595 |
{
|
| 596 |
"epoch": 6.4,
|
| 597 |
"learning_rate": 3.4549150281252635e-06,
|
| 598 |
-
"loss": 1.
|
| 599 |
"step": 352
|
| 600 |
},
|
| 601 |
{
|
| 602 |
"epoch": 6.47,
|
| 603 |
"learning_rate": 3.3347053645005965e-06,
|
| 604 |
-
"loss": 1.
|
| 605 |
"step": 356
|
| 606 |
},
|
| 607 |
{
|
| 608 |
"epoch": 6.55,
|
| 609 |
"learning_rate": 3.2155688920406415e-06,
|
| 610 |
-
"loss": 1.
|
| 611 |
"step": 360
|
| 612 |
},
|
| 613 |
{
|
| 614 |
"epoch": 6.62,
|
| 615 |
"learning_rate": 3.097582387675385e-06,
|
| 616 |
-
"loss": 1.
|
| 617 |
"step": 364
|
| 618 |
},
|
| 619 |
{
|
| 620 |
"epoch": 6.69,
|
| 621 |
"learning_rate": 2.980821887243377e-06,
|
| 622 |
-
"loss": 1.
|
| 623 |
"step": 368
|
| 624 |
},
|
| 625 |
{
|
| 626 |
"epoch": 6.76,
|
| 627 |
"learning_rate": 2.8653626364907918e-06,
|
| 628 |
-
"loss": 1.
|
| 629 |
"step": 372
|
| 630 |
},
|
| 631 |
{
|
| 632 |
"epoch": 6.84,
|
| 633 |
"learning_rate": 2.751279042579672e-06,
|
| 634 |
-
"loss": 1.
|
| 635 |
"step": 376
|
| 636 |
},
|
| 637 |
{
|
| 638 |
"epoch": 6.91,
|
| 639 |
"learning_rate": 2.6386446261365874e-06,
|
| 640 |
-
"loss": 1.
|
| 641 |
"step": 380
|
| 642 |
},
|
| 643 |
{
|
| 644 |
"epoch": 6.98,
|
| 645 |
"learning_rate": 2.527531973872617e-06,
|
| 646 |
-
"loss": 1.
|
| 647 |
"step": 384
|
| 648 |
},
|
| 649 |
{
|
| 650 |
"epoch": 7.0,
|
| 651 |
-
"pls_score":
|
| 652 |
-
"std": 4.
|
| 653 |
"step": 385
|
| 654 |
},
|
| 655 |
{
|
| 656 |
"epoch": 7.0,
|
| 657 |
-
"eval_loss": 1.
|
| 658 |
-
"eval_runtime": 4.
|
| 659 |
-
"eval_samples_per_second": 4.
|
| 660 |
"eval_steps_per_second": 1.222,
|
| 661 |
"step": 385
|
| 662 |
},
|
| 663 |
{
|
| 664 |
"epoch": 7.05,
|
| 665 |
"learning_rate": 2.418012691805191e-06,
|
| 666 |
-
"loss":
|
| 667 |
"step": 388
|
| 668 |
},
|
| 669 |
{
|
| 670 |
"epoch": 7.13,
|
| 671 |
"learning_rate": 2.310157359111938e-06,
|
| 672 |
-
"loss": 1.
|
| 673 |
"step": 392
|
| 674 |
},
|
| 675 |
{
|
| 676 |
"epoch": 7.2,
|
| 677 |
"learning_rate": 2.204035482646267e-06,
|
| 678 |
-
"loss": 1.
|
| 679 |
"step": 396
|
| 680 |
},
|
| 681 |
{
|
| 682 |
"epoch": 7.27,
|
| 683 |
"learning_rate": 2.09971545214401e-06,
|
| 684 |
-
"loss": 1.
|
| 685 |
"step": 400
|
| 686 |
},
|
| 687 |
{
|
| 688 |
"epoch": 7.35,
|
| 689 |
"learning_rate": 1.9972644961499853e-06,
|
| 690 |
-
"loss": 1.
|
| 691 |
"step": 404
|
| 692 |
},
|
| 693 |
{
|
| 694 |
"epoch": 7.42,
|
| 695 |
"learning_rate": 1.8967486386928819e-06,
|
| 696 |
-
"loss": 1.
|
| 697 |
"step": 408
|
| 698 |
},
|
| 699 |
{
|
| 700 |
"epoch": 7.49,
|
| 701 |
"learning_rate": 1.798232656736389e-06,
|
| 702 |
-
"loss": 1.
|
| 703 |
"step": 412
|
| 704 |
},
|
| 705 |
{
|
| 706 |
"epoch": 7.56,
|
| 707 |
"learning_rate": 1.7017800384339928e-06,
|
| 708 |
-
"loss": 1.
|
| 709 |
"step": 416
|
| 710 |
},
|
| 711 |
{
|
| 712 |
"epoch": 7.64,
|
| 713 |
"learning_rate": 1.6074529422143398e-06,
|
| 714 |
-
"loss": 1.
|
| 715 |
"step": 420
|
| 716 |
},
|
| 717 |
{
|
| 718 |
"epoch": 7.71,
|
| 719 |
"learning_rate": 1.5153121567235334e-06,
|
| 720 |
-
"loss": 1.
|
| 721 |
"step": 424
|
| 722 |
},
|
| 723 |
{
|
| 724 |
"epoch": 7.78,
|
| 725 |
"learning_rate": 1.4254170616501828e-06,
|
| 726 |
-
"loss": 1.
|
| 727 |
"step": 428
|
| 728 |
},
|
| 729 |
{
|
| 730 |
"epoch": 7.85,
|
| 731 |
"learning_rate": 1.3378255894584463e-06,
|
| 732 |
-
"loss": 1.
|
| 733 |
"step": 432
|
| 734 |
},
|
| 735 |
{
|
| 736 |
"epoch": 7.93,
|
| 737 |
"learning_rate": 1.2525941880537307e-06,
|
| 738 |
-
"loss": 1.
|
| 739 |
"step": 436
|
| 740 |
},
|
| 741 |
{
|
| 742 |
"epoch": 8.0,
|
| 743 |
"learning_rate": 1.1697777844051105e-06,
|
| 744 |
-
"loss": 1.
|
| 745 |
"step": 440
|
| 746 |
},
|
| 747 |
{
|
| 748 |
"epoch": 8.0,
|
| 749 |
-
"pls_score":
|
| 750 |
-
"std": 4.
|
| 751 |
"step": 440
|
| 752 |
},
|
| 753 |
{
|
| 754 |
"epoch": 8.0,
|
| 755 |
-
"eval_loss": 1.
|
| 756 |
-
"eval_runtime": 4.
|
| 757 |
-
"eval_samples_per_second": 4.
|
| 758 |
-
"eval_steps_per_second": 1.
|
| 759 |
"step": 440
|
| 760 |
},
|
| 761 |
{
|
| 762 |
"epoch": 8.07,
|
| 763 |
"learning_rate": 1.0894297491479044e-06,
|
| 764 |
-
"loss": 1.
|
| 765 |
"step": 444
|
| 766 |
},
|
| 767 |
{
|
| 768 |
"epoch": 8.15,
|
| 769 |
"learning_rate": 1.0116018621892237e-06,
|
| 770 |
-
"loss": 1.
|
| 771 |
"step": 448
|
| 772 |
},
|
| 773 |
{
|
| 774 |
"epoch": 8.22,
|
| 775 |
"learning_rate": 9.363442793386606e-07,
|
| 776 |
-
"loss": 1.
|
| 777 |
"step": 452
|
| 778 |
},
|
| 779 |
{
|
| 780 |
"epoch": 8.29,
|
| 781 |
"learning_rate": 8.637054999856148e-07,
|
| 782 |
-
"loss": 1.
|
| 783 |
"step": 456
|
| 784 |
},
|
| 785 |
{
|
| 786 |
"epoch": 8.36,
|
| 787 |
"learning_rate": 7.937323358440935e-07,
|
| 788 |
-
"loss": 1.
|
| 789 |
"step": 460
|
| 790 |
},
|
| 791 |
{
|
| 792 |
"epoch": 8.44,
|
| 793 |
"learning_rate": 7.264698807851328e-07,
|
| 794 |
-
"loss": 1.
|
| 795 |
"step": 464
|
| 796 |
},
|
| 797 |
{
|
| 798 |
"epoch": 8.51,
|
| 799 |
"learning_rate": 6.619614817762537e-07,
|
| 800 |
-
"loss": 1.
|
| 801 |
"step": 468
|
| 802 |
},
|
| 803 |
{
|
| 804 |
"epoch": 8.58,
|
| 805 |
"learning_rate": 6.002487109467347e-07,
|
| 806 |
-
"loss": 1.
|
| 807 |
"step": 472
|
| 808 |
},
|
| 809 |
{
|
| 810 |
"epoch": 8.65,
|
| 811 |
"learning_rate": 5.413713387966329e-07,
|
| 812 |
-
"loss": 1.
|
| 813 |
"step": 476
|
| 814 |
},
|
| 815 |
{
|
| 816 |
"epoch": 8.73,
|
| 817 |
"learning_rate": 4.853673085668947e-07,
|
| 818 |
-
"loss": 1.
|
| 819 |
"step": 480
|
| 820 |
},
|
| 821 |
{
|
| 822 |
"epoch": 8.8,
|
| 823 |
"learning_rate": 4.322727117869951e-07,
|
| 824 |
-
"loss": 1.
|
| 825 |
"step": 484
|
| 826 |
},
|
| 827 |
{
|
| 828 |
"epoch": 8.87,
|
| 829 |
"learning_rate": 3.821217650159453e-07,
|
| 830 |
-
"loss": 1.
|
| 831 |
"step": 488
|
| 832 |
},
|
| 833 |
{
|
| 834 |
"epoch": 8.95,
|
| 835 |
"learning_rate": 3.3494678779157464e-07,
|
| 836 |
-
"loss": 1.
|
| 837 |
"step": 492
|
| 838 |
},
|
| 839 |
{
|
| 840 |
"epoch": 9.0,
|
| 841 |
-
"pls_score": 59.
|
| 842 |
-
"std": 4.
|
| 843 |
"step": 495
|
| 844 |
},
|
| 845 |
{
|
| 846 |
"epoch": 9.0,
|
| 847 |
-
"eval_loss": 1.
|
| 848 |
-
"eval_runtime": 4.
|
| 849 |
-
"eval_samples_per_second": 4.
|
| 850 |
-
"eval_steps_per_second": 1.
|
| 851 |
"step": 495
|
| 852 |
},
|
| 853 |
{
|
| 854 |
"epoch": 9.02,
|
| 855 |
"learning_rate": 2.9077818180237693e-07,
|
| 856 |
-
"loss": 1.
|
| 857 |
"step": 496
|
| 858 |
},
|
| 859 |
{
|
| 860 |
"epoch": 9.09,
|
| 861 |
"learning_rate": 2.4964441129527337e-07,
|
| 862 |
-
"loss": 1.
|
| 863 |
"step": 500
|
| 864 |
},
|
| 865 |
{
|
| 866 |
"epoch": 9.16,
|
| 867 |
"learning_rate": 2.1157198473197417e-07,
|
| 868 |
-
"loss": 1.
|
| 869 |
"step": 504
|
| 870 |
},
|
| 871 |
{
|
| 872 |
"epoch": 9.24,
|
| 873 |
"learning_rate": 1.765854377057219e-07,
|
| 874 |
-
"loss": 1.
|
| 875 |
"step": 508
|
| 876 |
},
|
| 877 |
{
|
| 878 |
"epoch": 9.31,
|
| 879 |
"learning_rate": 1.4470731712944885e-07,
|
| 880 |
-
"loss": 1.
|
| 881 |
"step": 512
|
| 882 |
},
|
| 883 |
{
|
| 884 |
"epoch": 9.38,
|
| 885 |
"learning_rate": 1.1595816670552429e-07,
|
| 886 |
-
"loss": 1.
|
| 887 |
"step": 516
|
| 888 |
},
|
| 889 |
{
|
| 890 |
"epoch": 9.45,
|
| 891 |
"learning_rate": 9.035651368646647e-08,
|
| 892 |
-
"loss": 1.
|
| 893 |
"step": 520
|
| 894 |
},
|
| 895 |
{
|
| 896 |
"epoch": 9.53,
|
| 897 |
"learning_rate": 6.791885693514134e-08,
|
| 898 |
-
"loss":
|
| 899 |
"step": 524
|
| 900 |
},
|
| 901 |
{
|
| 902 |
"epoch": 9.6,
|
| 903 |
"learning_rate": 4.865965629214819e-08,
|
| 904 |
-
"loss": 1.
|
| 905 |
"step": 528
|
| 906 |
},
|
| 907 |
{
|
| 908 |
"epoch": 9.67,
|
| 909 |
"learning_rate": 3.25913232572489e-08,
|
| 910 |
-
"loss": 1.
|
| 911 |
"step": 532
|
| 912 |
},
|
| 913 |
{
|
| 914 |
"epoch": 9.75,
|
| 915 |
"learning_rate": 1.9724212990830938e-08,
|
| 916 |
-
"loss": 1.
|
| 917 |
"step": 536
|
| 918 |
},
|
| 919 |
{
|
| 920 |
"epoch": 9.82,
|
| 921 |
"learning_rate": 1.006661764057837e-08,
|
| 922 |
-
"loss": 1.
|
| 923 |
"step": 540
|
| 924 |
},
|
| 925 |
{
|
| 926 |
"epoch": 9.89,
|
| 927 |
"learning_rate": 3.6247609976319818e-09,
|
| 928 |
-
"loss": 1.
|
| 929 |
"step": 544
|
| 930 |
},
|
| 931 |
{
|
| 932 |
"epoch": 9.96,
|
| 933 |
"learning_rate": 4.027944857032395e-10,
|
| 934 |
-
"loss": 1.
|
| 935 |
"step": 548
|
| 936 |
},
|
| 937 |
{
|
| 938 |
"epoch": 10.0,
|
| 939 |
-
"pls_score":
|
| 940 |
-
"std": 4.
|
| 941 |
"step": 550
|
| 942 |
},
|
| 943 |
{
|
| 944 |
"epoch": 10.0,
|
| 945 |
-
"eval_loss": 1.
|
| 946 |
-
"eval_runtime": 4.
|
| 947 |
-
"eval_samples_per_second": 4.
|
| 948 |
-
"eval_steps_per_second": 1.
|
| 949 |
"step": 550
|
| 950 |
},
|
| 951 |
{
|
| 952 |
"epoch": 10.0,
|
| 953 |
"step": 550,
|
| 954 |
-
"total_flos": 1.
|
| 955 |
-
"train_loss": 1.
|
| 956 |
-
"train_runtime":
|
| 957 |
-
"train_samples_per_second": 0.
|
| 958 |
-
"train_steps_per_second": 0.
|
| 959 |
}
|
| 960 |
],
|
| 961 |
"logging_steps": 4,
|
|
@@ -963,7 +977,7 @@
|
|
| 963 |
"num_input_tokens_seen": 0,
|
| 964 |
"num_train_epochs": 10,
|
| 965 |
"save_steps": 55,
|
| 966 |
-
"total_flos": 1.
|
| 967 |
"train_batch_size": 4,
|
| 968 |
"trial_name": null,
|
| 969 |
"trial_params": null
|
|
|
|
| 372 |
"loss": 1.953,
|
| 373 |
"step": 220
|
| 374 |
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 4.0,
|
| 377 |
+
"pls_score": 63.673469387755105,
|
| 378 |
+
"std": 4.56973253478639,
|
| 379 |
+
"step": 220
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"epoch": 4.0,
|
| 383 |
+
"eval_loss": 2.038102626800537,
|
| 384 |
+
"eval_runtime": 4.9029,
|
| 385 |
+
"eval_samples_per_second": 4.691,
|
| 386 |
+
"eval_steps_per_second": 1.224,
|
| 387 |
+
"step": 220
|
| 388 |
+
},
|
| 389 |
{
|
| 390 |
"epoch": 4.07,
|
| 391 |
"learning_rate": 7.3892790165483164e-06,
|
| 392 |
+
"loss": 1.9949,
|
| 393 |
"step": 224
|
| 394 |
},
|
| 395 |
{
|
| 396 |
"epoch": 4.15,
|
| 397 |
"learning_rate": 7.2770182736595164e-06,
|
| 398 |
+
"loss": 2.0196,
|
| 399 |
"step": 228
|
| 400 |
},
|
| 401 |
{
|
| 402 |
"epoch": 4.22,
|
| 403 |
"learning_rate": 7.163290117232542e-06,
|
| 404 |
+
"loss": 1.8627,
|
| 405 |
"step": 232
|
| 406 |
},
|
| 407 |
{
|
| 408 |
"epoch": 4.29,
|
| 409 |
"learning_rate": 7.048167838833977e-06,
|
| 410 |
+
"loss": 2.051,
|
| 411 |
"step": 236
|
| 412 |
},
|
| 413 |
{
|
| 414 |
"epoch": 4.36,
|
| 415 |
"learning_rate": 6.931725628465643e-06,
|
| 416 |
+
"loss": 2.0636,
|
| 417 |
"step": 240
|
| 418 |
},
|
| 419 |
{
|
| 420 |
"epoch": 4.44,
|
| 421 |
"learning_rate": 6.814038526753205e-06,
|
| 422 |
+
"loss": 1.8729,
|
| 423 |
"step": 244
|
| 424 |
},
|
| 425 |
{
|
| 426 |
"epoch": 4.51,
|
| 427 |
"learning_rate": 6.695182376586603e-06,
|
| 428 |
+
"loss": 1.9095,
|
| 429 |
"step": 248
|
| 430 |
},
|
| 431 |
{
|
| 432 |
"epoch": 4.58,
|
| 433 |
"learning_rate": 6.5752337742434644e-06,
|
| 434 |
+
"loss": 1.9759,
|
| 435 |
"step": 252
|
| 436 |
},
|
| 437 |
{
|
| 438 |
"epoch": 4.65,
|
| 439 |
"learning_rate": 6.454270020026996e-06,
|
| 440 |
+
"loss": 1.9738,
|
| 441 |
"step": 256
|
| 442 |
},
|
| 443 |
{
|
| 444 |
"epoch": 4.73,
|
| 445 |
"learning_rate": 6.332369068450175e-06,
|
| 446 |
+
"loss": 1.9394,
|
| 447 |
"step": 260
|
| 448 |
},
|
| 449 |
{
|
| 450 |
"epoch": 4.8,
|
| 451 |
"learning_rate": 6.209609477998339e-06,
|
| 452 |
+
"loss": 1.9755,
|
| 453 |
"step": 264
|
| 454 |
},
|
| 455 |
{
|
| 456 |
"epoch": 4.87,
|
| 457 |
"learning_rate": 6.08607036050254e-06,
|
| 458 |
+
"loss": 1.8648,
|
| 459 |
"step": 268
|
| 460 |
},
|
| 461 |
{
|
| 462 |
"epoch": 4.95,
|
| 463 |
"learning_rate": 5.961831330156306e-06,
|
| 464 |
+
"loss": 1.9412,
|
| 465 |
"step": 272
|
| 466 |
},
|
| 467 |
{
|
| 468 |
"epoch": 5.0,
|
| 469 |
+
"pls_score": 57.6,
|
| 470 |
+
"std": 4.257323102608023,
|
| 471 |
"step": 275
|
| 472 |
},
|
| 473 |
{
|
| 474 |
"epoch": 5.0,
|
| 475 |
+
"eval_loss": 2.0098042488098145,
|
| 476 |
+
"eval_runtime": 4.9025,
|
| 477 |
+
"eval_samples_per_second": 4.692,
|
| 478 |
+
"eval_steps_per_second": 1.224,
|
| 479 |
"step": 275
|
| 480 |
},
|
| 481 |
{
|
| 482 |
"epoch": 5.02,
|
| 483 |
"learning_rate": 5.8369724522086545e-06,
|
| 484 |
+
"loss": 1.9483,
|
| 485 |
"step": 276
|
| 486 |
},
|
| 487 |
{
|
| 488 |
"epoch": 5.09,
|
| 489 |
"learning_rate": 5.711574191366427e-06,
|
| 490 |
+
"loss": 2.0268,
|
| 491 |
"step": 280
|
| 492 |
},
|
| 493 |
{
|
| 494 |
"epoch": 5.16,
|
| 495 |
"learning_rate": 5.585717359939192e-06,
|
| 496 |
+
"loss": 1.9855,
|
| 497 |
"step": 284
|
| 498 |
},
|
| 499 |
{
|
| 500 |
"epoch": 5.24,
|
| 501 |
"learning_rate": 5.459483065760138e-06,
|
| 502 |
+
"loss": 1.8754,
|
| 503 |
"step": 288
|
| 504 |
},
|
| 505 |
{
|
| 506 |
"epoch": 5.31,
|
| 507 |
"learning_rate": 5.33295265991652e-06,
|
| 508 |
+
"loss": 1.892,
|
| 509 |
"step": 292
|
| 510 |
},
|
| 511 |
{
|
| 512 |
"epoch": 5.38,
|
| 513 |
"learning_rate": 5.206207684323337e-06,
|
| 514 |
+
"loss": 2.016,
|
| 515 |
"step": 296
|
| 516 |
},
|
| 517 |
{
|
| 518 |
"epoch": 5.45,
|
| 519 |
"learning_rate": 5.07932981917404e-06,
|
| 520 |
+
"loss": 1.9611,
|
| 521 |
"step": 300
|
| 522 |
},
|
| 523 |
{
|
| 524 |
"epoch": 5.53,
|
| 525 |
"learning_rate": 4.952400830302117e-06,
|
| 526 |
+
"loss": 1.8741,
|
| 527 |
"step": 304
|
| 528 |
},
|
| 529 |
{
|
| 530 |
"epoch": 5.6,
|
| 531 |
"learning_rate": 4.825502516487497e-06,
|
| 532 |
+
"loss": 1.9852,
|
| 533 |
"step": 308
|
| 534 |
},
|
| 535 |
{
|
| 536 |
"epoch": 5.67,
|
| 537 |
"learning_rate": 4.6987166567417085e-06,
|
| 538 |
+
"loss": 1.8991,
|
| 539 |
"step": 312
|
| 540 |
},
|
| 541 |
{
|
| 542 |
"epoch": 5.75,
|
| 543 |
"learning_rate": 4.572124957605803e-06,
|
| 544 |
+
"loss": 1.8599,
|
| 545 |
"step": 316
|
| 546 |
},
|
| 547 |
{
|
| 548 |
"epoch": 5.82,
|
| 549 |
"learning_rate": 4.445809000494945e-06,
|
| 550 |
+
"loss": 1.9791,
|
| 551 |
"step": 320
|
| 552 |
},
|
| 553 |
{
|
| 554 |
"epoch": 5.89,
|
| 555 |
"learning_rate": 4.319850189123681e-06,
|
| 556 |
+
"loss": 1.8507,
|
| 557 |
"step": 324
|
| 558 |
},
|
| 559 |
{
|
| 560 |
"epoch": 5.96,
|
| 561 |
"learning_rate": 4.194329697045681e-06,
|
| 562 |
+
"loss": 1.9044,
|
| 563 |
"step": 328
|
| 564 |
},
|
| 565 |
{
|
| 566 |
"epoch": 6.0,
|
| 567 |
+
"pls_score": 61.2,
|
| 568 |
+
"std": 4.323332048316438,
|
| 569 |
"step": 330
|
| 570 |
},
|
| 571 |
{
|
| 572 |
"epoch": 6.0,
|
| 573 |
+
"eval_loss": 1.9948909282684326,
|
| 574 |
+
"eval_runtime": 4.9085,
|
| 575 |
+
"eval_samples_per_second": 4.686,
|
| 576 |
+
"eval_steps_per_second": 1.222,
|
| 577 |
"step": 330
|
| 578 |
},
|
| 579 |
{
|
| 580 |
"epoch": 6.04,
|
| 581 |
"learning_rate": 4.06932841534185e-06,
|
| 582 |
+
"loss": 1.9863,
|
| 583 |
"step": 332
|
| 584 |
},
|
| 585 |
{
|
| 586 |
"epoch": 6.11,
|
| 587 |
"learning_rate": 3.944926900490452e-06,
|
| 588 |
+
"loss": 1.9043,
|
| 589 |
"step": 336
|
| 590 |
},
|
| 591 |
{
|
| 592 |
"epoch": 6.18,
|
| 593 |
"learning_rate": 3.821205322452863e-06,
|
| 594 |
+
"loss": 1.8504,
|
| 595 |
"step": 340
|
| 596 |
},
|
| 597 |
{
|
| 598 |
"epoch": 6.25,
|
| 599 |
"learning_rate": 3.69824341300844e-06,
|
| 600 |
+
"loss": 1.912,
|
| 601 |
"step": 344
|
| 602 |
},
|
| 603 |
{
|
| 604 |
"epoch": 6.33,
|
| 605 |
"learning_rate": 3.5761204143717387e-06,
|
| 606 |
+
"loss": 1.9407,
|
| 607 |
"step": 348
|
| 608 |
},
|
| 609 |
{
|
| 610 |
"epoch": 6.4,
|
| 611 |
"learning_rate": 3.4549150281252635e-06,
|
| 612 |
+
"loss": 1.8498,
|
| 613 |
"step": 352
|
| 614 |
},
|
| 615 |
{
|
| 616 |
"epoch": 6.47,
|
| 617 |
"learning_rate": 3.3347053645005965e-06,
|
| 618 |
+
"loss": 1.9506,
|
| 619 |
"step": 356
|
| 620 |
},
|
| 621 |
{
|
| 622 |
"epoch": 6.55,
|
| 623 |
"learning_rate": 3.2155688920406415e-06,
|
| 624 |
+
"loss": 1.8538,
|
| 625 |
"step": 360
|
| 626 |
},
|
| 627 |
{
|
| 628 |
"epoch": 6.62,
|
| 629 |
"learning_rate": 3.097582387675385e-06,
|
| 630 |
+
"loss": 1.8497,
|
| 631 |
"step": 364
|
| 632 |
},
|
| 633 |
{
|
| 634 |
"epoch": 6.69,
|
| 635 |
"learning_rate": 2.980821887243377e-06,
|
| 636 |
+
"loss": 1.8615,
|
| 637 |
"step": 368
|
| 638 |
},
|
| 639 |
{
|
| 640 |
"epoch": 6.76,
|
| 641 |
"learning_rate": 2.8653626364907918e-06,
|
| 642 |
+
"loss": 1.9318,
|
| 643 |
"step": 372
|
| 644 |
},
|
| 645 |
{
|
| 646 |
"epoch": 6.84,
|
| 647 |
"learning_rate": 2.751279042579672e-06,
|
| 648 |
+
"loss": 1.8605,
|
| 649 |
"step": 376
|
| 650 |
},
|
| 651 |
{
|
| 652 |
"epoch": 6.91,
|
| 653 |
"learning_rate": 2.6386446261365874e-06,
|
| 654 |
+
"loss": 1.8682,
|
| 655 |
"step": 380
|
| 656 |
},
|
| 657 |
{
|
| 658 |
"epoch": 6.98,
|
| 659 |
"learning_rate": 2.527531973872617e-06,
|
| 660 |
+
"loss": 1.9567,
|
| 661 |
"step": 384
|
| 662 |
},
|
| 663 |
{
|
| 664 |
"epoch": 7.0,
|
| 665 |
+
"pls_score": 68.4,
|
| 666 |
+
"std": 4.003598381456362,
|
| 667 |
"step": 385
|
| 668 |
},
|
| 669 |
{
|
| 670 |
"epoch": 7.0,
|
| 671 |
+
"eval_loss": 1.9888746738433838,
|
| 672 |
+
"eval_runtime": 4.9083,
|
| 673 |
+
"eval_samples_per_second": 4.686,
|
| 674 |
"eval_steps_per_second": 1.222,
|
| 675 |
"step": 385
|
| 676 |
},
|
| 677 |
{
|
| 678 |
"epoch": 7.05,
|
| 679 |
"learning_rate": 2.418012691805191e-06,
|
| 680 |
+
"loss": 1.6192,
|
| 681 |
"step": 388
|
| 682 |
},
|
| 683 |
{
|
| 684 |
"epoch": 7.13,
|
| 685 |
"learning_rate": 2.310157359111938e-06,
|
| 686 |
+
"loss": 1.9044,
|
| 687 |
"step": 392
|
| 688 |
},
|
| 689 |
{
|
| 690 |
"epoch": 7.2,
|
| 691 |
"learning_rate": 2.204035482646267e-06,
|
| 692 |
+
"loss": 1.8584,
|
| 693 |
"step": 396
|
| 694 |
},
|
| 695 |
{
|
| 696 |
"epoch": 7.27,
|
| 697 |
"learning_rate": 2.09971545214401e-06,
|
| 698 |
+
"loss": 1.7605,
|
| 699 |
"step": 400
|
| 700 |
},
|
| 701 |
{
|
| 702 |
"epoch": 7.35,
|
| 703 |
"learning_rate": 1.9972644961499853e-06,
|
| 704 |
+
"loss": 1.9119,
|
| 705 |
"step": 404
|
| 706 |
},
|
| 707 |
{
|
| 708 |
"epoch": 7.42,
|
| 709 |
"learning_rate": 1.8967486386928819e-06,
|
| 710 |
+
"loss": 1.9704,
|
| 711 |
"step": 408
|
| 712 |
},
|
| 713 |
{
|
| 714 |
"epoch": 7.49,
|
| 715 |
"learning_rate": 1.798232656736389e-06,
|
| 716 |
+
"loss": 1.9329,
|
| 717 |
"step": 412
|
| 718 |
},
|
| 719 |
{
|
| 720 |
"epoch": 7.56,
|
| 721 |
"learning_rate": 1.7017800384339928e-06,
|
| 722 |
+
"loss": 1.8767,
|
| 723 |
"step": 416
|
| 724 |
},
|
| 725 |
{
|
| 726 |
"epoch": 7.64,
|
| 727 |
"learning_rate": 1.6074529422143398e-06,
|
| 728 |
+
"loss": 1.8444,
|
| 729 |
"step": 420
|
| 730 |
},
|
| 731 |
{
|
| 732 |
"epoch": 7.71,
|
| 733 |
"learning_rate": 1.5153121567235334e-06,
|
| 734 |
+
"loss": 1.8153,
|
| 735 |
"step": 424
|
| 736 |
},
|
| 737 |
{
|
| 738 |
"epoch": 7.78,
|
| 739 |
"learning_rate": 1.4254170616501828e-06,
|
| 740 |
+
"loss": 1.9326,
|
| 741 |
"step": 428
|
| 742 |
},
|
| 743 |
{
|
| 744 |
"epoch": 7.85,
|
| 745 |
"learning_rate": 1.3378255894584463e-06,
|
| 746 |
+
"loss": 1.9621,
|
| 747 |
"step": 432
|
| 748 |
},
|
| 749 |
{
|
| 750 |
"epoch": 7.93,
|
| 751 |
"learning_rate": 1.2525941880537307e-06,
|
| 752 |
+
"loss": 1.8408,
|
| 753 |
"step": 436
|
| 754 |
},
|
| 755 |
{
|
| 756 |
"epoch": 8.0,
|
| 757 |
"learning_rate": 1.1697777844051105e-06,
|
| 758 |
+
"loss": 1.9235,
|
| 759 |
"step": 440
|
| 760 |
},
|
| 761 |
{
|
| 762 |
"epoch": 8.0,
|
| 763 |
+
"pls_score": 62.4,
|
| 764 |
+
"std": 4.104241708281811,
|
| 765 |
"step": 440
|
| 766 |
},
|
| 767 |
{
|
| 768 |
"epoch": 8.0,
|
| 769 |
+
"eval_loss": 1.9856469631195068,
|
| 770 |
+
"eval_runtime": 4.9071,
|
| 771 |
+
"eval_samples_per_second": 4.687,
|
| 772 |
+
"eval_steps_per_second": 1.223,
|
| 773 |
"step": 440
|
| 774 |
},
|
| 775 |
{
|
| 776 |
"epoch": 8.07,
|
| 777 |
"learning_rate": 1.0894297491479044e-06,
|
| 778 |
+
"loss": 1.9699,
|
| 779 |
"step": 444
|
| 780 |
},
|
| 781 |
{
|
| 782 |
"epoch": 8.15,
|
| 783 |
"learning_rate": 1.0116018621892237e-06,
|
| 784 |
+
"loss": 1.9288,
|
| 785 |
"step": 448
|
| 786 |
},
|
| 787 |
{
|
| 788 |
"epoch": 8.22,
|
| 789 |
"learning_rate": 9.363442793386606e-07,
|
| 790 |
+
"loss": 1.7962,
|
| 791 |
"step": 452
|
| 792 |
},
|
| 793 |
{
|
| 794 |
"epoch": 8.29,
|
| 795 |
"learning_rate": 8.637054999856148e-07,
|
| 796 |
+
"loss": 1.8953,
|
| 797 |
"step": 456
|
| 798 |
},
|
| 799 |
{
|
| 800 |
"epoch": 8.36,
|
| 801 |
"learning_rate": 7.937323358440935e-07,
|
| 802 |
+
"loss": 1.8903,
|
| 803 |
"step": 460
|
| 804 |
},
|
| 805 |
{
|
| 806 |
"epoch": 8.44,
|
| 807 |
"learning_rate": 7.264698807851328e-07,
|
| 808 |
+
"loss": 1.8935,
|
| 809 |
"step": 464
|
| 810 |
},
|
| 811 |
{
|
| 812 |
"epoch": 8.51,
|
| 813 |
"learning_rate": 6.619614817762537e-07,
|
| 814 |
+
"loss": 1.7803,
|
| 815 |
"step": 468
|
| 816 |
},
|
| 817 |
{
|
| 818 |
"epoch": 8.58,
|
| 819 |
"learning_rate": 6.002487109467347e-07,
|
| 820 |
+
"loss": 1.8441,
|
| 821 |
"step": 472
|
| 822 |
},
|
| 823 |
{
|
| 824 |
"epoch": 8.65,
|
| 825 |
"learning_rate": 5.413713387966329e-07,
|
| 826 |
+
"loss": 1.8613,
|
| 827 |
"step": 476
|
| 828 |
},
|
| 829 |
{
|
| 830 |
"epoch": 8.73,
|
| 831 |
"learning_rate": 4.853673085668947e-07,
|
| 832 |
+
"loss": 1.8198,
|
| 833 |
"step": 480
|
| 834 |
},
|
| 835 |
{
|
| 836 |
"epoch": 8.8,
|
| 837 |
"learning_rate": 4.322727117869951e-07,
|
| 838 |
+
"loss": 1.8694,
|
| 839 |
"step": 484
|
| 840 |
},
|
| 841 |
{
|
| 842 |
"epoch": 8.87,
|
| 843 |
"learning_rate": 3.821217650159453e-07,
|
| 844 |
+
"loss": 1.9331,
|
| 845 |
"step": 488
|
| 846 |
},
|
| 847 |
{
|
| 848 |
"epoch": 8.95,
|
| 849 |
"learning_rate": 3.3494678779157464e-07,
|
| 850 |
+
"loss": 1.8121,
|
| 851 |
"step": 492
|
| 852 |
},
|
| 853 |
{
|
| 854 |
"epoch": 9.0,
|
| 855 |
+
"pls_score": 59.6,
|
| 856 |
+
"std": 4.435853920047414,
|
| 857 |
"step": 495
|
| 858 |
},
|
| 859 |
{
|
| 860 |
"epoch": 9.0,
|
| 861 |
+
"eval_loss": 1.9848822355270386,
|
| 862 |
+
"eval_runtime": 4.9078,
|
| 863 |
+
"eval_samples_per_second": 4.686,
|
| 864 |
+
"eval_steps_per_second": 1.223,
|
| 865 |
"step": 495
|
| 866 |
},
|
| 867 |
{
|
| 868 |
"epoch": 9.02,
|
| 869 |
"learning_rate": 2.9077818180237693e-07,
|
| 870 |
+
"loss": 1.8913,
|
| 871 |
"step": 496
|
| 872 |
},
|
| 873 |
{
|
| 874 |
"epoch": 9.09,
|
| 875 |
"learning_rate": 2.4964441129527337e-07,
|
| 876 |
+
"loss": 1.9085,
|
| 877 |
"step": 500
|
| 878 |
},
|
| 879 |
{
|
| 880 |
"epoch": 9.16,
|
| 881 |
"learning_rate": 2.1157198473197417e-07,
|
| 882 |
+
"loss": 1.8147,
|
| 883 |
"step": 504
|
| 884 |
},
|
| 885 |
{
|
| 886 |
"epoch": 9.24,
|
| 887 |
"learning_rate": 1.765854377057219e-07,
|
| 888 |
+
"loss": 1.801,
|
| 889 |
"step": 508
|
| 890 |
},
|
| 891 |
{
|
| 892 |
"epoch": 9.31,
|
| 893 |
"learning_rate": 1.4470731712944885e-07,
|
| 894 |
+
"loss": 1.971,
|
| 895 |
"step": 512
|
| 896 |
},
|
| 897 |
{
|
| 898 |
"epoch": 9.38,
|
| 899 |
"learning_rate": 1.1595816670552429e-07,
|
| 900 |
+
"loss": 1.785,
|
| 901 |
"step": 516
|
| 902 |
},
|
| 903 |
{
|
| 904 |
"epoch": 9.45,
|
| 905 |
"learning_rate": 9.035651368646647e-08,
|
| 906 |
+
"loss": 1.9679,
|
| 907 |
"step": 520
|
| 908 |
},
|
| 909 |
{
|
| 910 |
"epoch": 9.53,
|
| 911 |
"learning_rate": 6.791885693514134e-08,
|
| 912 |
+
"loss": 2.0259,
|
| 913 |
"step": 524
|
| 914 |
},
|
| 915 |
{
|
| 916 |
"epoch": 9.6,
|
| 917 |
"learning_rate": 4.865965629214819e-08,
|
| 918 |
+
"loss": 1.809,
|
| 919 |
"step": 528
|
| 920 |
},
|
| 921 |
{
|
| 922 |
"epoch": 9.67,
|
| 923 |
"learning_rate": 3.25913232572489e-08,
|
| 924 |
+
"loss": 1.8509,
|
| 925 |
"step": 532
|
| 926 |
},
|
| 927 |
{
|
| 928 |
"epoch": 9.75,
|
| 929 |
"learning_rate": 1.9724212990830938e-08,
|
| 930 |
+
"loss": 1.7555,
|
| 931 |
"step": 536
|
| 932 |
},
|
| 933 |
{
|
| 934 |
"epoch": 9.82,
|
| 935 |
"learning_rate": 1.006661764057837e-08,
|
| 936 |
+
"loss": 1.7928,
|
| 937 |
"step": 540
|
| 938 |
},
|
| 939 |
{
|
| 940 |
"epoch": 9.89,
|
| 941 |
"learning_rate": 3.6247609976319818e-09,
|
| 942 |
+
"loss": 1.8696,
|
| 943 |
"step": 544
|
| 944 |
},
|
| 945 |
{
|
| 946 |
"epoch": 9.96,
|
| 947 |
"learning_rate": 4.027944857032395e-10,
|
| 948 |
+
"loss": 1.874,
|
| 949 |
"step": 548
|
| 950 |
},
|
| 951 |
{
|
| 952 |
"epoch": 10.0,
|
| 953 |
+
"pls_score": 62.44897959183673,
|
| 954 |
+
"std": 4.1477362667705515,
|
| 955 |
"step": 550
|
| 956 |
},
|
| 957 |
{
|
| 958 |
"epoch": 10.0,
|
| 959 |
+
"eval_loss": 1.9848212003707886,
|
| 960 |
+
"eval_runtime": 4.9046,
|
| 961 |
+
"eval_samples_per_second": 4.689,
|
| 962 |
+
"eval_steps_per_second": 1.223,
|
| 963 |
"step": 550
|
| 964 |
},
|
| 965 |
{
|
| 966 |
"epoch": 10.0,
|
| 967 |
"step": 550,
|
| 968 |
+
"total_flos": 1.8756405193949184e+16,
|
| 969 |
+
"train_loss": 1.5526252421465787,
|
| 970 |
+
"train_runtime": 23283.78,
|
| 971 |
+
"train_samples_per_second": 0.093,
|
| 972 |
+
"train_steps_per_second": 0.024
|
| 973 |
}
|
| 974 |
],
|
| 975 |
"logging_steps": 4,
|
|
|
|
| 977 |
"num_input_tokens_seen": 0,
|
| 978 |
"num_train_epochs": 10,
|
| 979 |
"save_steps": 55,
|
| 980 |
+
"total_flos": 1.8756405193949184e+16,
|
| 981 |
"train_batch_size": 4,
|
| 982 |
"trial_name": null,
|
| 983 |
"trial_params": null
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4792
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c677dd79b462fc73f2789bacd7347362aa793784208e35b1e034cb575ba3a945
|
| 3 |
size 4792
|