Hugging Face's logo

HealthTeam
/
mt5-small-finetuned-MultiHead-230207

Text2Text Generation
Transformers
PyTorch
TensorBoard
mt5
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
HealthTeam commited on
Commit
5441393
•
1 Parent(s): 86191f8

Training in progress, step 55240

Browse files
Files changed (7) hide show
  1. last-checkpoint/optimizer.pt +1 -1
  2. last-checkpoint/pytorch_model.bin +1 -1
  3. last-checkpoint/rng_state.pth +1 -1
  4. last-checkpoint/scheduler.pt +1 -1
  5. last-checkpoint/trainer_state.json +135 -3
  6. pytorch_model.bin +1 -1
  7. runs/Feb07_05-04-07_5214b674e698/events.out.tfevents.1675746342.5214b674e698.342.0 +2 -2
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:da5bf2849c0638ce07375012016d12ab0464f14c9ff2cc8e0d5c7f8102381be2
3
  size 2401461253
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4df6baefe0df3845a28abe9fc6e812fd755b1eb716adddecc1deedd7aca8278d
3
  size 2401461253
last-checkpoint/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:939362e3a8d757be29a23f167f4a01bd5557159122b0df243b3b2536127d8aac
3
  size 1200739717
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:612baa21561bf04530d6eb5804833e6f0b56599c78fd0a39bacd3ac335e650d3
3
  size 1200739717
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ac0761df5417402344ed3bf16bb6e3a45212b9c7f1bd6e2a6742f07a4b1bfc53
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:274f4675622b5854821912e67212d43584ebb6ec4a78ba0fa35ff9cd87e972c2
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cc1c6f6c18f2c362ea1ad3fddc44d9b0d7706c7038e53ba814ce42682079de6c
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b09dba34704dde96f55673b0cc5c41d0a0ce45d83ad2015625ba94df43f96a45
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.6574038261283508,
5
- "global_step": 44192,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -534,11 +534,143 @@
534
  "learning_rate": 1.5636349211071773e-05,
535
  "loss": 3.1734,
536
  "step": 44000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
537
  }
538
  ],
539
  "max_steps": 201666,
540
  "num_train_epochs": 3,
541
- "total_flos": 5.193969669557453e+16,
542
  "trial_name": null,
543
  "trial_params": null
544
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.8217547826604386,
5
+ "global_step": 55240,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
534
  "learning_rate": 1.5636349211071773e-05,
535
  "loss": 3.1734,
536
  "step": 44000
537
+ },
538
+ {
539
+ "epoch": 0.66,
540
+ "learning_rate": 1.55867622702885e-05,
541
+ "loss": 3.1401,
542
+ "step": 44500
543
+ },
544
+ {
545
+ "epoch": 0.67,
546
+ "learning_rate": 1.5537175329505225e-05,
547
+ "loss": 3.1463,
548
+ "step": 45000
549
+ },
550
+ {
551
+ "epoch": 0.68,
552
+ "learning_rate": 1.5487588388721947e-05,
553
+ "loss": 3.1431,
554
+ "step": 45500
555
+ },
556
+ {
557
+ "epoch": 0.68,
558
+ "learning_rate": 1.5438001447938673e-05,
559
+ "loss": 3.1316,
560
+ "step": 46000
561
+ },
562
+ {
563
+ "epoch": 0.69,
564
+ "learning_rate": 1.5388414507155395e-05,
565
+ "loss": 3.1606,
566
+ "step": 46500
567
+ },
568
+ {
569
+ "epoch": 0.7,
570
+ "learning_rate": 1.533882756637212e-05,
571
+ "loss": 3.1362,
572
+ "step": 47000
573
+ },
574
+ {
575
+ "epoch": 0.71,
576
+ "learning_rate": 1.5289240625588847e-05,
577
+ "loss": 3.1335,
578
+ "step": 47500
579
+ },
580
+ {
581
+ "epoch": 0.71,
582
+ "learning_rate": 1.523965368480557e-05,
583
+ "loss": 3.149,
584
+ "step": 48000
585
+ },
586
+ {
587
+ "epoch": 0.72,
588
+ "learning_rate": 1.5190066744022297e-05,
589
+ "loss": 3.1293,
590
+ "step": 48500
591
+ },
592
+ {
593
+ "epoch": 0.73,
594
+ "learning_rate": 1.514047980323902e-05,
595
+ "loss": 3.1286,
596
+ "step": 49000
597
+ },
598
+ {
599
+ "epoch": 0.74,
600
+ "learning_rate": 1.5090892862455743e-05,
601
+ "loss": 3.1196,
602
+ "step": 49500
603
+ },
604
+ {
605
+ "epoch": 0.74,
606
+ "learning_rate": 1.5041305921672469e-05,
607
+ "loss": 3.1238,
608
+ "step": 50000
609
+ },
610
+ {
611
+ "epoch": 0.75,
612
+ "learning_rate": 1.4991718980889195e-05,
613
+ "loss": 3.1033,
614
+ "step": 50500
615
+ },
616
+ {
617
+ "epoch": 0.76,
618
+ "learning_rate": 1.4942132040105919e-05,
619
+ "loss": 3.1112,
620
+ "step": 51000
621
+ },
622
+ {
623
+ "epoch": 0.77,
624
+ "learning_rate": 1.4892545099322645e-05,
625
+ "loss": 3.0936,
626
+ "step": 51500
627
+ },
628
+ {
629
+ "epoch": 0.77,
630
+ "learning_rate": 1.4842958158539369e-05,
631
+ "loss": 3.107,
632
+ "step": 52000
633
+ },
634
+ {
635
+ "epoch": 0.78,
636
+ "learning_rate": 1.4793371217756094e-05,
637
+ "loss": 3.1063,
638
+ "step": 52500
639
+ },
640
+ {
641
+ "epoch": 0.79,
642
+ "learning_rate": 1.4743784276972817e-05,
643
+ "loss": 3.0639,
644
+ "step": 53000
645
+ },
646
+ {
647
+ "epoch": 0.8,
648
+ "learning_rate": 1.4694197336189543e-05,
649
+ "loss": 3.1028,
650
+ "step": 53500
651
+ },
652
+ {
653
+ "epoch": 0.8,
654
+ "learning_rate": 1.4644610395406267e-05,
655
+ "loss": 3.0821,
656
+ "step": 54000
657
+ },
658
+ {
659
+ "epoch": 0.81,
660
+ "learning_rate": 1.4595023454622992e-05,
661
+ "loss": 3.0596,
662
+ "step": 54500
663
+ },
664
+ {
665
+ "epoch": 0.82,
666
+ "learning_rate": 1.4545436513839717e-05,
667
+ "loss": 3.0787,
668
+ "step": 55000
669
  }
670
  ],
671
  "max_steps": 201666,
672
  "num_train_epochs": 3,
673
+ "total_flos": 6.497219068615066e+16,
674
  "trial_name": null,
675
  "trial_params": null
676
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:939362e3a8d757be29a23f167f4a01bd5557159122b0df243b3b2536127d8aac
3
  size 1200739717
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:612baa21561bf04530d6eb5804833e6f0b56599c78fd0a39bacd3ac335e650d3
3
  size 1200739717
runs/Feb07_05-04-07_5214b674e698/events.out.tfevents.1675746342.5214b674e698.342.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:68abdf7d613e2b38ec76fd6735814e503c277a7e46fafb3f031724d696919bcd
3
- size 18101
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b5afd134e7190bfca227464f177ede39b4d5a435161a2a45582286c96ae5885
3
+ size 21621