dada22231 commited on
Commit
fd6ee0e
·
verified ·
1 Parent(s): 84dbf19

Training in progress, step 95, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:92a929a6d2f6f813bad1461c8a08430de54a47cfd4e1b0eb2721690870510695
3
  size 1204200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac1a6cd9cd5731f2fb1080bfe1fba1f47ad0817b8a98582a8422e5ae6ce793e3
3
  size 1204200
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6b25cbc223d3da25d50a855534a028e15dd47188fdf6e07722529931fd4db298
3
  size 2558458
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:855c447afbc982708e38728d953e7f98eb52b373c97b3a639eb9f2df50338394
3
  size 2558458
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:061a037b684aa2d30e04c4d18a234634eaf766c0923e32115b3d10d54e3d1342
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf8fa0f7305d53a0343b40c9f0af97272bd8aaa9480182534013ab38780c8272
3
  size 15024
last-checkpoint/rng_state_1.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:00ca9aae2af0804efde089e5992db8046b1b24ccf29e241832f89be36852a064
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2315b23ad3d3d9635e07c289ebadfa5817c04fde503655919305ad6b5da7e5f7
3
  size 15024
last-checkpoint/rng_state_2.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:31b31727d3d5284886051ee133495d7b566dd45ac256cb8f1b62dc051e90259d
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9c5135248f88ee949c24dc3bc7c23c497cc3652d411d63686bd8d26db5f153d
3
  size 15024
last-checkpoint/rng_state_3.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:33849917273fe6dead1c51b313cabffac353caa2ead9bbe03665536fc094f4a8
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af598b8222ac82409146ddd21a770ae37f6e33545e4cd90f69024431fe49edf9
3
  size 15024
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a5b53655d80c3ade692dacae57cafa4aff84c325b5cb8d0fba89d01b50d41566
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1fd9769bcb04586b7ead175b588f12a0bbbeba72d5f308b868ba8f36b77aa801
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": 11.898860931396484,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-75",
4
- "epoch": 0.09241432422025414,
5
  "eval_steps": 25,
6
- "global_step": 75,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -564,6 +564,146 @@
564
  "eval_samples_per_second": 113.302,
565
  "eval_steps_per_second": 29.459,
566
  "step": 75
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
567
  }
568
  ],
569
  "logging_steps": 1,
@@ -587,12 +727,12 @@
587
  "should_evaluate": false,
588
  "should_log": false,
589
  "should_save": true,
590
- "should_training_stop": false
591
  },
592
  "attributes": {}
593
  }
594
  },
595
- "total_flos": 626602593484800.0,
596
  "train_batch_size": 1,
597
  "trial_name": null,
598
  "trial_params": null
 
1
  {
2
  "best_metric": 11.898860931396484,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-75",
4
+ "epoch": 0.11705814401232191,
5
  "eval_steps": 25,
6
+ "global_step": 95,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
564
  "eval_samples_per_second": 113.302,
565
  "eval_steps_per_second": 29.459,
566
  "step": 75
567
+ },
568
+ {
569
+ "epoch": 0.09364651520985753,
570
+ "grad_norm": 0.11339965462684631,
571
+ "learning_rate": 1.91437699862843e-05,
572
+ "loss": 11.9061,
573
+ "step": 76
574
+ },
575
+ {
576
+ "epoch": 0.09487870619946091,
577
+ "grad_norm": 0.0967002585530281,
578
+ "learning_rate": 1.8236354814530112e-05,
579
+ "loss": 11.9045,
580
+ "step": 77
581
+ },
582
+ {
583
+ "epoch": 0.0961108971890643,
584
+ "grad_norm": 0.10335846245288849,
585
+ "learning_rate": 1.7371804408538024e-05,
586
+ "loss": 11.9027,
587
+ "step": 78
588
+ },
589
+ {
590
+ "epoch": 0.0973430881786677,
591
+ "grad_norm": 0.10277073085308075,
592
+ "learning_rate": 1.6551126795408016e-05,
593
+ "loss": 11.9032,
594
+ "step": 79
595
+ },
596
+ {
597
+ "epoch": 0.09857527916827108,
598
+ "grad_norm": 0.09848005324602127,
599
+ "learning_rate": 1.577527884852619e-05,
600
+ "loss": 11.8994,
601
+ "step": 80
602
+ },
603
+ {
604
+ "epoch": 0.09980747015787447,
605
+ "grad_norm": 0.10161633044481277,
606
+ "learning_rate": 1.5045165171893116e-05,
607
+ "loss": 11.8994,
608
+ "step": 81
609
+ },
610
+ {
611
+ "epoch": 0.10103966114747785,
612
+ "grad_norm": 0.09697967022657394,
613
+ "learning_rate": 1.4361637045396029e-05,
614
+ "loss": 11.9027,
615
+ "step": 82
616
+ },
617
+ {
618
+ "epoch": 0.10227185213708125,
619
+ "grad_norm": 0.10200096666812897,
620
+ "learning_rate": 1.3725491432254624e-05,
621
+ "loss": 11.9003,
622
+ "step": 83
623
+ },
624
+ {
625
+ "epoch": 0.10350404312668464,
626
+ "grad_norm": 0.13053254783153534,
627
+ "learning_rate": 1.313747004979751e-05,
628
+ "loss": 11.8971,
629
+ "step": 84
630
+ },
631
+ {
632
+ "epoch": 0.10473623411628802,
633
+ "grad_norm": 0.1328170746564865,
634
+ "learning_rate": 1.2598258504653081e-05,
635
+ "loss": 11.8973,
636
+ "step": 85
637
+ },
638
+ {
639
+ "epoch": 0.10596842510589141,
640
+ "grad_norm": 0.19934439659118652,
641
+ "learning_rate": 1.2108485493362765e-05,
642
+ "loss": 11.8961,
643
+ "step": 86
644
+ },
645
+ {
646
+ "epoch": 0.1072006160954948,
647
+ "grad_norm": 0.26894065737724304,
648
+ "learning_rate": 1.1668722069349041e-05,
649
+ "loss": 11.8933,
650
+ "step": 87
651
+ },
652
+ {
653
+ "epoch": 0.10843280708509818,
654
+ "grad_norm": 0.10815577208995819,
655
+ "learning_rate": 1.1279480977092635e-05,
656
+ "loss": 11.9066,
657
+ "step": 88
658
+ },
659
+ {
660
+ "epoch": 0.10966499807470158,
661
+ "grad_norm": 0.10114790499210358,
662
+ "learning_rate": 1.094121605429547e-05,
663
+ "loss": 11.9022,
664
+ "step": 89
665
+ },
666
+ {
667
+ "epoch": 0.11089718906430497,
668
+ "grad_norm": 0.0996105894446373,
669
+ "learning_rate": 1.0654321702726141e-05,
670
+ "loss": 11.9031,
671
+ "step": 90
672
+ },
673
+ {
674
+ "epoch": 0.11212938005390835,
675
+ "grad_norm": 0.11002374440431595,
676
+ "learning_rate": 1.0419132428365116e-05,
677
+ "loss": 11.9013,
678
+ "step": 91
679
+ },
680
+ {
681
+ "epoch": 0.11336157104351174,
682
+ "grad_norm": 0.1089978888630867,
683
+ "learning_rate": 1.0235922451385733e-05,
684
+ "loss": 11.8994,
685
+ "step": 92
686
+ },
687
+ {
688
+ "epoch": 0.11459376203311514,
689
+ "grad_norm": 0.10552305728197098,
690
+ "learning_rate": 1.0104905386425733e-05,
691
+ "loss": 11.9014,
692
+ "step": 93
693
+ },
694
+ {
695
+ "epoch": 0.11582595302271852,
696
+ "grad_norm": 0.11430001258850098,
697
+ "learning_rate": 1.002623399352217e-05,
698
+ "loss": 11.8997,
699
+ "step": 94
700
+ },
701
+ {
702
+ "epoch": 0.11705814401232191,
703
+ "grad_norm": 0.11952391266822815,
704
+ "learning_rate": 1e-05,
705
+ "loss": 11.8955,
706
+ "step": 95
707
  }
708
  ],
709
  "logging_steps": 1,
 
727
  "should_evaluate": false,
728
  "should_log": false,
729
  "should_save": true,
730
+ "should_training_stop": true
731
  },
732
  "attributes": {}
733
  }
734
  },
735
+ "total_flos": 793696618414080.0,
736
  "train_batch_size": 1,
737
  "trial_name": null,
738
  "trial_params": null