beast33 commited on
Commit
ba7ce92
·
verified ·
1 Parent(s): cbd9f19

Training in progress, step 400, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1400d8d9fcd1fc13b6a51389aafff8669394cc78540c32d0fb35d678873f3694
3
  size 389074464
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef3a7e624e964e6e38c20ca7796672a04ca4c7d1015f7f62f89f8f486186eeb2
3
  size 389074464
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7f0293dbf6fed0140b62b51b12aa521438ff80dffd4b0e520a9753f42c26999d
3
  size 198011700
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61dbbbc5fad7a57f5123ec8eb0a49b7e304fd9ce48a4b271c66f425675528e91
3
  size 198011700
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:78f1a7978cca13140fc4bf742e169de8521126c1e11da24eaec0a4ec3d15afd8
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74f87d284e79aba665ea3dfdfe3f668005173a40957b2e48ea063e67be3c0935
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f9096f15f02bac6b0fc27aa7aa4986f85d87d53fca310a75657e0015357af5c5
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:705cabf5cbc3a6ab0feb67c77b9b453d59efcc939ce90d310af96e621810f990
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.6220620274543762,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-350",
4
- "epoch": 0.047195253505933114,
5
  "eval_steps": 50,
6
- "global_step": 350,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -2521,6 +2521,364 @@
2521
  "eval_samples_per_second": 15.441,
2522
  "eval_steps_per_second": 3.861,
2523
  "step": 350
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2524
  }
2525
  ],
2526
  "logging_steps": 1,
@@ -2544,12 +2902,12 @@
2544
  "should_evaluate": false,
2545
  "should_log": false,
2546
  "should_save": true,
2547
- "should_training_stop": false
2548
  },
2549
  "attributes": {}
2550
  }
2551
  },
2552
- "total_flos": 2.0166161016972902e+17,
2553
  "train_batch_size": 8,
2554
  "trial_name": null,
2555
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.615675151348114,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-400",
4
+ "epoch": 0.05393743257820928,
5
  "eval_steps": 50,
6
+ "global_step": 400,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
2521
  "eval_samples_per_second": 15.441,
2522
  "eval_steps_per_second": 3.861,
2523
  "step": 350
2524
+ },
2525
+ {
2526
+ "epoch": 0.04733009708737864,
2527
+ "grad_norm": 0.23296354711055756,
2528
+ "learning_rate": 3.844650207332562e-06,
2529
+ "loss": 0.5557,
2530
+ "step": 351
2531
+ },
2532
+ {
2533
+ "epoch": 0.04746494066882417,
2534
+ "grad_norm": 0.2704331576824188,
2535
+ "learning_rate": 3.691267552111183e-06,
2536
+ "loss": 0.8556,
2537
+ "step": 352
2538
+ },
2539
+ {
2540
+ "epoch": 0.047599784250269686,
2541
+ "grad_norm": 0.32684770226478577,
2542
+ "learning_rate": 3.54088980417534e-06,
2543
+ "loss": 0.8739,
2544
+ "step": 353
2545
+ },
2546
+ {
2547
+ "epoch": 0.04773462783171521,
2548
+ "grad_norm": 0.3810671269893646,
2549
+ "learning_rate": 3.393526721321616e-06,
2550
+ "loss": 0.6595,
2551
+ "step": 354
2552
+ },
2553
+ {
2554
+ "epoch": 0.04786947141316073,
2555
+ "grad_norm": 0.3469758927822113,
2556
+ "learning_rate": 3.249187865729264e-06,
2557
+ "loss": 0.617,
2558
+ "step": 355
2559
+ },
2560
+ {
2561
+ "epoch": 0.04800431499460626,
2562
+ "grad_norm": 0.3857620358467102,
2563
+ "learning_rate": 3.1078826033397843e-06,
2564
+ "loss": 0.8274,
2565
+ "step": 356
2566
+ },
2567
+ {
2568
+ "epoch": 0.04813915857605178,
2569
+ "grad_norm": 0.45720577239990234,
2570
+ "learning_rate": 2.9696201032491434e-06,
2571
+ "loss": 0.6145,
2572
+ "step": 357
2573
+ },
2574
+ {
2575
+ "epoch": 0.0482740021574973,
2576
+ "grad_norm": 0.4756413996219635,
2577
+ "learning_rate": 2.8344093371128424e-06,
2578
+ "loss": 0.8195,
2579
+ "step": 358
2580
+ },
2581
+ {
2582
+ "epoch": 0.04840884573894283,
2583
+ "grad_norm": 0.5415727496147156,
2584
+ "learning_rate": 2.70225907856374e-06,
2585
+ "loss": 0.7706,
2586
+ "step": 359
2587
+ },
2588
+ {
2589
+ "epoch": 0.04854368932038835,
2590
+ "grad_norm": 0.5260385274887085,
2591
+ "learning_rate": 2.573177902642726e-06,
2592
+ "loss": 0.7806,
2593
+ "step": 360
2594
+ },
2595
+ {
2596
+ "epoch": 0.048678532901833875,
2597
+ "grad_norm": 0.5152238011360168,
2598
+ "learning_rate": 2.4471741852423237e-06,
2599
+ "loss": 0.6455,
2600
+ "step": 361
2601
+ },
2602
+ {
2603
+ "epoch": 0.048813376483279394,
2604
+ "grad_norm": 0.4815971255302429,
2605
+ "learning_rate": 2.324256102563188e-06,
2606
+ "loss": 0.8413,
2607
+ "step": 362
2608
+ },
2609
+ {
2610
+ "epoch": 0.04894822006472492,
2611
+ "grad_norm": 0.5217490792274475,
2612
+ "learning_rate": 2.204431630583548e-06,
2613
+ "loss": 0.7371,
2614
+ "step": 363
2615
+ },
2616
+ {
2617
+ "epoch": 0.04908306364617044,
2618
+ "grad_norm": 0.40579986572265625,
2619
+ "learning_rate": 2.087708544541689e-06,
2620
+ "loss": 0.7718,
2621
+ "step": 364
2622
+ },
2623
+ {
2624
+ "epoch": 0.049217907227615966,
2625
+ "grad_norm": 0.441269189119339,
2626
+ "learning_rate": 1.974094418431388e-06,
2627
+ "loss": 0.638,
2628
+ "step": 365
2629
+ },
2630
+ {
2631
+ "epoch": 0.049352750809061485,
2632
+ "grad_norm": 0.43731170892715454,
2633
+ "learning_rate": 1.8635966245104664e-06,
2634
+ "loss": 0.7073,
2635
+ "step": 366
2636
+ },
2637
+ {
2638
+ "epoch": 0.04948759439050701,
2639
+ "grad_norm": 0.42750218510627747,
2640
+ "learning_rate": 1.7562223328224325e-06,
2641
+ "loss": 0.7956,
2642
+ "step": 367
2643
+ },
2644
+ {
2645
+ "epoch": 0.04962243797195254,
2646
+ "grad_norm": 0.4149448871612549,
2647
+ "learning_rate": 1.6519785107311891e-06,
2648
+ "loss": 0.5633,
2649
+ "step": 368
2650
+ },
2651
+ {
2652
+ "epoch": 0.04975728155339806,
2653
+ "grad_norm": 0.40429598093032837,
2654
+ "learning_rate": 1.5508719224689717e-06,
2655
+ "loss": 0.717,
2656
+ "step": 369
2657
+ },
2658
+ {
2659
+ "epoch": 0.04989212513484358,
2660
+ "grad_norm": 0.43707722425460815,
2661
+ "learning_rate": 1.4529091286973995e-06,
2662
+ "loss": 0.6377,
2663
+ "step": 370
2664
+ },
2665
+ {
2666
+ "epoch": 0.0500269687162891,
2667
+ "grad_norm": 0.4193248748779297,
2668
+ "learning_rate": 1.358096486081778e-06,
2669
+ "loss": 0.6427,
2670
+ "step": 371
2671
+ },
2672
+ {
2673
+ "epoch": 0.05016181229773463,
2674
+ "grad_norm": 0.41846606135368347,
2675
+ "learning_rate": 1.2664401468786114e-06,
2676
+ "loss": 0.6396,
2677
+ "step": 372
2678
+ },
2679
+ {
2680
+ "epoch": 0.05029665587918015,
2681
+ "grad_norm": 0.4295959770679474,
2682
+ "learning_rate": 1.1779460585363944e-06,
2683
+ "loss": 0.6024,
2684
+ "step": 373
2685
+ },
2686
+ {
2687
+ "epoch": 0.050431499460625674,
2688
+ "grad_norm": 0.5195227265357971,
2689
+ "learning_rate": 1.0926199633097157e-06,
2690
+ "loss": 0.5379,
2691
+ "step": 374
2692
+ },
2693
+ {
2694
+ "epoch": 0.0505663430420712,
2695
+ "grad_norm": 0.3819423317909241,
2696
+ "learning_rate": 1.0104673978866164e-06,
2697
+ "loss": 0.5306,
2698
+ "step": 375
2699
+ },
2700
+ {
2701
+ "epoch": 0.05070118662351672,
2702
+ "grad_norm": 0.4182847738265991,
2703
+ "learning_rate": 9.314936930293283e-07,
2704
+ "loss": 0.4756,
2705
+ "step": 376
2706
+ },
2707
+ {
2708
+ "epoch": 0.050836030204962246,
2709
+ "grad_norm": 0.4350426495075226,
2710
+ "learning_rate": 8.557039732283944e-07,
2711
+ "loss": 0.514,
2712
+ "step": 377
2713
+ },
2714
+ {
2715
+ "epoch": 0.050970873786407765,
2716
+ "grad_norm": 0.45626920461654663,
2717
+ "learning_rate": 7.83103156370113e-07,
2718
+ "loss": 0.5751,
2719
+ "step": 378
2720
+ },
2721
+ {
2722
+ "epoch": 0.05110571736785329,
2723
+ "grad_norm": 0.44910773634910583,
2724
+ "learning_rate": 7.136959534174592e-07,
2725
+ "loss": 0.4992,
2726
+ "step": 379
2727
+ },
2728
+ {
2729
+ "epoch": 0.05124056094929881,
2730
+ "grad_norm": 0.4697156846523285,
2731
+ "learning_rate": 6.474868681043578e-07,
2732
+ "loss": 0.5868,
2733
+ "step": 380
2734
+ },
2735
+ {
2736
+ "epoch": 0.05137540453074434,
2737
+ "grad_norm": 0.5265816450119019,
2738
+ "learning_rate": 5.844801966434832e-07,
2739
+ "loss": 0.7519,
2740
+ "step": 381
2741
+ },
2742
+ {
2743
+ "epoch": 0.05151024811218986,
2744
+ "grad_norm": 0.5154181122779846,
2745
+ "learning_rate": 5.246800274474439e-07,
2746
+ "loss": 0.6139,
2747
+ "step": 382
2748
+ },
2749
+ {
2750
+ "epoch": 0.05164509169363538,
2751
+ "grad_norm": 0.48455241322517395,
2752
+ "learning_rate": 4.680902408635335e-07,
2753
+ "loss": 0.4926,
2754
+ "step": 383
2755
+ },
2756
+ {
2757
+ "epoch": 0.05177993527508091,
2758
+ "grad_norm": 0.5290249586105347,
2759
+ "learning_rate": 4.1471450892189846e-07,
2760
+ "loss": 0.6908,
2761
+ "step": 384
2762
+ },
2763
+ {
2764
+ "epoch": 0.05191477885652643,
2765
+ "grad_norm": 0.5313962697982788,
2766
+ "learning_rate": 3.6455629509730136e-07,
2767
+ "loss": 0.6272,
2768
+ "step": 385
2769
+ },
2770
+ {
2771
+ "epoch": 0.052049622437971954,
2772
+ "grad_norm": 0.511638879776001,
2773
+ "learning_rate": 3.1761885408435054e-07,
2774
+ "loss": 0.4756,
2775
+ "step": 386
2776
+ },
2777
+ {
2778
+ "epoch": 0.05218446601941747,
2779
+ "grad_norm": 0.5756959915161133,
2780
+ "learning_rate": 2.7390523158633554e-07,
2781
+ "loss": 0.5613,
2782
+ "step": 387
2783
+ },
2784
+ {
2785
+ "epoch": 0.052319309600863,
2786
+ "grad_norm": 0.5868178606033325,
2787
+ "learning_rate": 2.334182641175686e-07,
2788
+ "loss": 0.5253,
2789
+ "step": 388
2790
+ },
2791
+ {
2792
+ "epoch": 0.05245415318230852,
2793
+ "grad_norm": 0.520788848400116,
2794
+ "learning_rate": 1.9616057881935436e-07,
2795
+ "loss": 0.4795,
2796
+ "step": 389
2797
+ },
2798
+ {
2799
+ "epoch": 0.052588996763754045,
2800
+ "grad_norm": 0.5664001703262329,
2801
+ "learning_rate": 1.6213459328950352e-07,
2802
+ "loss": 0.5453,
2803
+ "step": 390
2804
+ },
2805
+ {
2806
+ "epoch": 0.05272384034519957,
2807
+ "grad_norm": 0.5474855899810791,
2808
+ "learning_rate": 1.3134251542544774e-07,
2809
+ "loss": 0.5063,
2810
+ "step": 391
2811
+ },
2812
+ {
2813
+ "epoch": 0.05285868392664509,
2814
+ "grad_norm": 0.6837330460548401,
2815
+ "learning_rate": 1.0378634328099269e-07,
2816
+ "loss": 0.6015,
2817
+ "step": 392
2818
+ },
2819
+ {
2820
+ "epoch": 0.05299352750809062,
2821
+ "grad_norm": 0.6691194772720337,
2822
+ "learning_rate": 7.946786493666647e-08,
2823
+ "loss": 0.5717,
2824
+ "step": 393
2825
+ },
2826
+ {
2827
+ "epoch": 0.053128371089536136,
2828
+ "grad_norm": 0.6826778054237366,
2829
+ "learning_rate": 5.838865838366792e-08,
2830
+ "loss": 0.5854,
2831
+ "step": 394
2832
+ },
2833
+ {
2834
+ "epoch": 0.05326321467098166,
2835
+ "grad_norm": 0.9006599187850952,
2836
+ "learning_rate": 4.055009142152067e-08,
2837
+ "loss": 0.5394,
2838
+ "step": 395
2839
+ },
2840
+ {
2841
+ "epoch": 0.05339805825242718,
2842
+ "grad_norm": 0.8636307716369629,
2843
+ "learning_rate": 2.595332156925534e-08,
2844
+ "loss": 0.6416,
2845
+ "step": 396
2846
+ },
2847
+ {
2848
+ "epoch": 0.05353290183387271,
2849
+ "grad_norm": 0.8960134983062744,
2850
+ "learning_rate": 1.4599295990352924e-08,
2851
+ "loss": 0.7612,
2852
+ "step": 397
2853
+ },
2854
+ {
2855
+ "epoch": 0.053667745415318234,
2856
+ "grad_norm": 0.9180140495300293,
2857
+ "learning_rate": 6.488751431266149e-09,
2858
+ "loss": 0.5951,
2859
+ "step": 398
2860
+ },
2861
+ {
2862
+ "epoch": 0.05380258899676375,
2863
+ "grad_norm": 1.1765445470809937,
2864
+ "learning_rate": 1.622214173602199e-09,
2865
+ "loss": 0.7061,
2866
+ "step": 399
2867
+ },
2868
+ {
2869
+ "epoch": 0.05393743257820928,
2870
+ "grad_norm": 1.1231061220169067,
2871
+ "learning_rate": 0.0,
2872
+ "loss": 0.7403,
2873
+ "step": 400
2874
+ },
2875
+ {
2876
+ "epoch": 0.05393743257820928,
2877
+ "eval_loss": 0.615675151348114,
2878
+ "eval_runtime": 808.2953,
2879
+ "eval_samples_per_second": 15.452,
2880
+ "eval_steps_per_second": 3.864,
2881
+ "step": 400
2882
  }
2883
  ],
2884
  "logging_steps": 1,
 
2902
  "should_evaluate": false,
2903
  "should_log": false,
2904
  "should_save": true,
2905
+ "should_training_stop": true
2906
  },
2907
  "attributes": {}
2908
  }
2909
  },
2910
+ "total_flos": 2.3047041162254746e+17,
2911
  "train_batch_size": 8,
2912
  "trial_name": null,
2913
  "trial_params": null