brew35 commited on
Commit
0df0f66
·
verified ·
1 Parent(s): 5a4e63e

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:d8cfe5db208f6c477e2e0635b1f6a133dfa0bd72cedf08e35035b438e65672ba
3
  size 140815952
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32f74c466531b29224b51d876788b2ce59723ee6edf626d6489869e061013f3e
3
  size 140815952
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6dc9843ea8a76c71db403d9129ac58d827e7a67c65a13da18bb87b0a19a2d501
3
  size 71878996
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:252f405adc974fa23532e591518c41a5363f54089aa9dc3a0de1b5b9cefe0749
3
  size 71878996
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:06cf6dbd5af8627d5bc86f0a43500500a4a729e4e2a276cf06055395a2aab116
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81982bcbe911082158e6e948fd98dec9c0da0e8967eb7157b6d6fae6dd0c682e
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": 0.565327525138855,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-350",
4
- "epoch": 0.04033303563711792,
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": 26.771,
2522
  "eval_steps_per_second": 6.693,
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": 4.345339247276851e+16,
2553
  "train_batch_size": 8,
2554
  "trial_name": null,
2555
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.5639106631278992,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-400",
4
+ "epoch": 0.046094897870991906,
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": 26.771,
2522
  "eval_steps_per_second": 6.693,
2523
  "step": 350
2524
+ },
2525
+ {
2526
+ "epoch": 0.040448272881795394,
2527
+ "grad_norm": 0.40898263454437256,
2528
+ "learning_rate": 3.844650207332562e-06,
2529
+ "loss": 0.5105,
2530
+ "step": 351
2531
+ },
2532
+ {
2533
+ "epoch": 0.04056351012647288,
2534
+ "grad_norm": 0.505041241645813,
2535
+ "learning_rate": 3.691267552111183e-06,
2536
+ "loss": 0.5799,
2537
+ "step": 352
2538
+ },
2539
+ {
2540
+ "epoch": 0.040678747371150355,
2541
+ "grad_norm": 0.567950963973999,
2542
+ "learning_rate": 3.54088980417534e-06,
2543
+ "loss": 0.5532,
2544
+ "step": 353
2545
+ },
2546
+ {
2547
+ "epoch": 0.04079398461582784,
2548
+ "grad_norm": 0.5739919543266296,
2549
+ "learning_rate": 3.393526721321616e-06,
2550
+ "loss": 0.6807,
2551
+ "step": 354
2552
+ },
2553
+ {
2554
+ "epoch": 0.040909221860505315,
2555
+ "grad_norm": 0.6619653701782227,
2556
+ "learning_rate": 3.249187865729264e-06,
2557
+ "loss": 0.6146,
2558
+ "step": 355
2559
+ },
2560
+ {
2561
+ "epoch": 0.04102445910518279,
2562
+ "grad_norm": 1.0355381965637207,
2563
+ "learning_rate": 3.1078826033397843e-06,
2564
+ "loss": 0.5103,
2565
+ "step": 356
2566
+ },
2567
+ {
2568
+ "epoch": 0.041139696349860276,
2569
+ "grad_norm": 0.9396152496337891,
2570
+ "learning_rate": 2.9696201032491434e-06,
2571
+ "loss": 0.5792,
2572
+ "step": 357
2573
+ },
2574
+ {
2575
+ "epoch": 0.04125493359453775,
2576
+ "grad_norm": 0.6551850438117981,
2577
+ "learning_rate": 2.8344093371128424e-06,
2578
+ "loss": 0.6257,
2579
+ "step": 358
2580
+ },
2581
+ {
2582
+ "epoch": 0.04137017083921524,
2583
+ "grad_norm": 0.7442685961723328,
2584
+ "learning_rate": 2.70225907856374e-06,
2585
+ "loss": 0.6958,
2586
+ "step": 359
2587
+ },
2588
+ {
2589
+ "epoch": 0.041485408083892714,
2590
+ "grad_norm": 0.8106182813644409,
2591
+ "learning_rate": 2.573177902642726e-06,
2592
+ "loss": 0.6433,
2593
+ "step": 360
2594
+ },
2595
+ {
2596
+ "epoch": 0.04160064532857019,
2597
+ "grad_norm": 0.8108749389648438,
2598
+ "learning_rate": 2.4471741852423237e-06,
2599
+ "loss": 0.5951,
2600
+ "step": 361
2601
+ },
2602
+ {
2603
+ "epoch": 0.041715882573247674,
2604
+ "grad_norm": 0.7107764482498169,
2605
+ "learning_rate": 2.324256102563188e-06,
2606
+ "loss": 0.5789,
2607
+ "step": 362
2608
+ },
2609
+ {
2610
+ "epoch": 0.04183111981792515,
2611
+ "grad_norm": 0.8077031373977661,
2612
+ "learning_rate": 2.204431630583548e-06,
2613
+ "loss": 0.6543,
2614
+ "step": 363
2615
+ },
2616
+ {
2617
+ "epoch": 0.041946357062602635,
2618
+ "grad_norm": 0.7621222734451294,
2619
+ "learning_rate": 2.087708544541689e-06,
2620
+ "loss": 0.608,
2621
+ "step": 364
2622
+ },
2623
+ {
2624
+ "epoch": 0.04206159430728011,
2625
+ "grad_norm": 0.851012110710144,
2626
+ "learning_rate": 1.974094418431388e-06,
2627
+ "loss": 0.6374,
2628
+ "step": 365
2629
+ },
2630
+ {
2631
+ "epoch": 0.042176831551957596,
2632
+ "grad_norm": 0.8776100873947144,
2633
+ "learning_rate": 1.8635966245104664e-06,
2634
+ "loss": 0.52,
2635
+ "step": 366
2636
+ },
2637
+ {
2638
+ "epoch": 0.04229206879663507,
2639
+ "grad_norm": 0.9081662893295288,
2640
+ "learning_rate": 1.7562223328224325e-06,
2641
+ "loss": 0.6261,
2642
+ "step": 367
2643
+ },
2644
+ {
2645
+ "epoch": 0.04240730604131255,
2646
+ "grad_norm": 1.609647512435913,
2647
+ "learning_rate": 1.6519785107311891e-06,
2648
+ "loss": 0.6758,
2649
+ "step": 368
2650
+ },
2651
+ {
2652
+ "epoch": 0.04252254328599003,
2653
+ "grad_norm": 0.8990199565887451,
2654
+ "learning_rate": 1.5508719224689717e-06,
2655
+ "loss": 0.6053,
2656
+ "step": 369
2657
+ },
2658
+ {
2659
+ "epoch": 0.04263778053066751,
2660
+ "grad_norm": 0.9323314428329468,
2661
+ "learning_rate": 1.4529091286973995e-06,
2662
+ "loss": 0.5667,
2663
+ "step": 370
2664
+ },
2665
+ {
2666
+ "epoch": 0.042753017775344994,
2667
+ "grad_norm": 0.945374071598053,
2668
+ "learning_rate": 1.358096486081778e-06,
2669
+ "loss": 0.6181,
2670
+ "step": 371
2671
+ },
2672
+ {
2673
+ "epoch": 0.04286825502002247,
2674
+ "grad_norm": 1.0014368295669556,
2675
+ "learning_rate": 1.2664401468786114e-06,
2676
+ "loss": 0.6029,
2677
+ "step": 372
2678
+ },
2679
+ {
2680
+ "epoch": 0.04298349226469995,
2681
+ "grad_norm": 1.0264681577682495,
2682
+ "learning_rate": 1.1779460585363944e-06,
2683
+ "loss": 0.6635,
2684
+ "step": 373
2685
+ },
2686
+ {
2687
+ "epoch": 0.04309872950937743,
2688
+ "grad_norm": 1.105810523033142,
2689
+ "learning_rate": 1.0926199633097157e-06,
2690
+ "loss": 0.573,
2691
+ "step": 374
2692
+ },
2693
+ {
2694
+ "epoch": 0.04321396675405491,
2695
+ "grad_norm": 1.128774881362915,
2696
+ "learning_rate": 1.0104673978866164e-06,
2697
+ "loss": 0.7388,
2698
+ "step": 375
2699
+ },
2700
+ {
2701
+ "epoch": 0.04332920399873239,
2702
+ "grad_norm": 1.3867303133010864,
2703
+ "learning_rate": 9.314936930293283e-07,
2704
+ "loss": 0.6529,
2705
+ "step": 376
2706
+ },
2707
+ {
2708
+ "epoch": 0.04344444124340987,
2709
+ "grad_norm": 1.161137342453003,
2710
+ "learning_rate": 8.557039732283944e-07,
2711
+ "loss": 0.6191,
2712
+ "step": 377
2713
+ },
2714
+ {
2715
+ "epoch": 0.04355967848808735,
2716
+ "grad_norm": 1.2012664079666138,
2717
+ "learning_rate": 7.83103156370113e-07,
2718
+ "loss": 0.5442,
2719
+ "step": 378
2720
+ },
2721
+ {
2722
+ "epoch": 0.04367491573276483,
2723
+ "grad_norm": 1.1599990129470825,
2724
+ "learning_rate": 7.136959534174592e-07,
2725
+ "loss": 0.54,
2726
+ "step": 379
2727
+ },
2728
+ {
2729
+ "epoch": 0.043790152977442307,
2730
+ "grad_norm": 0.8282076120376587,
2731
+ "learning_rate": 6.474868681043578e-07,
2732
+ "loss": 0.3925,
2733
+ "step": 380
2734
+ },
2735
+ {
2736
+ "epoch": 0.04390539022211979,
2737
+ "grad_norm": 0.9517076015472412,
2738
+ "learning_rate": 5.844801966434832e-07,
2739
+ "loss": 0.47,
2740
+ "step": 381
2741
+ },
2742
+ {
2743
+ "epoch": 0.04402062746679727,
2744
+ "grad_norm": 0.8718116879463196,
2745
+ "learning_rate": 5.246800274474439e-07,
2746
+ "loss": 0.5393,
2747
+ "step": 382
2748
+ },
2749
+ {
2750
+ "epoch": 0.04413586471147475,
2751
+ "grad_norm": 0.9473959803581238,
2752
+ "learning_rate": 4.680902408635335e-07,
2753
+ "loss": 0.5456,
2754
+ "step": 383
2755
+ },
2756
+ {
2757
+ "epoch": 0.04425110195615223,
2758
+ "grad_norm": 0.9435731172561646,
2759
+ "learning_rate": 4.1471450892189846e-07,
2760
+ "loss": 0.535,
2761
+ "step": 384
2762
+ },
2763
+ {
2764
+ "epoch": 0.044366339200829705,
2765
+ "grad_norm": 0.8984076380729675,
2766
+ "learning_rate": 3.6455629509730136e-07,
2767
+ "loss": 0.4925,
2768
+ "step": 385
2769
+ },
2770
+ {
2771
+ "epoch": 0.04448157644550719,
2772
+ "grad_norm": 0.9920340180397034,
2773
+ "learning_rate": 3.1761885408435054e-07,
2774
+ "loss": 0.5074,
2775
+ "step": 386
2776
+ },
2777
+ {
2778
+ "epoch": 0.044596813690184665,
2779
+ "grad_norm": 1.0126951932907104,
2780
+ "learning_rate": 2.7390523158633554e-07,
2781
+ "loss": 0.4881,
2782
+ "step": 387
2783
+ },
2784
+ {
2785
+ "epoch": 0.04471205093486215,
2786
+ "grad_norm": 1.2216013669967651,
2787
+ "learning_rate": 2.334182641175686e-07,
2788
+ "loss": 0.602,
2789
+ "step": 388
2790
+ },
2791
+ {
2792
+ "epoch": 0.044827288179539626,
2793
+ "grad_norm": 0.9132040739059448,
2794
+ "learning_rate": 1.9616057881935436e-07,
2795
+ "loss": 0.5279,
2796
+ "step": 389
2797
+ },
2798
+ {
2799
+ "epoch": 0.04494252542421711,
2800
+ "grad_norm": 1.1324865818023682,
2801
+ "learning_rate": 1.6213459328950352e-07,
2802
+ "loss": 0.6967,
2803
+ "step": 390
2804
+ },
2805
+ {
2806
+ "epoch": 0.04505776266889459,
2807
+ "grad_norm": 1.058250069618225,
2808
+ "learning_rate": 1.3134251542544774e-07,
2809
+ "loss": 0.5102,
2810
+ "step": 391
2811
+ },
2812
+ {
2813
+ "epoch": 0.045172999913572064,
2814
+ "grad_norm": 1.089077353477478,
2815
+ "learning_rate": 1.0378634328099269e-07,
2816
+ "loss": 0.5119,
2817
+ "step": 392
2818
+ },
2819
+ {
2820
+ "epoch": 0.04528823715824955,
2821
+ "grad_norm": 1.0287598371505737,
2822
+ "learning_rate": 7.946786493666647e-08,
2823
+ "loss": 0.4487,
2824
+ "step": 393
2825
+ },
2826
+ {
2827
+ "epoch": 0.045403474402927024,
2828
+ "grad_norm": 1.0808227062225342,
2829
+ "learning_rate": 5.838865838366792e-08,
2830
+ "loss": 0.4266,
2831
+ "step": 394
2832
+ },
2833
+ {
2834
+ "epoch": 0.04551871164760451,
2835
+ "grad_norm": 1.3644070625305176,
2836
+ "learning_rate": 4.055009142152067e-08,
2837
+ "loss": 0.517,
2838
+ "step": 395
2839
+ },
2840
+ {
2841
+ "epoch": 0.045633948892281985,
2842
+ "grad_norm": 1.2962229251861572,
2843
+ "learning_rate": 2.595332156925534e-08,
2844
+ "loss": 0.5079,
2845
+ "step": 396
2846
+ },
2847
+ {
2848
+ "epoch": 0.04574918613695946,
2849
+ "grad_norm": 1.2190864086151123,
2850
+ "learning_rate": 1.4599295990352924e-08,
2851
+ "loss": 0.4182,
2852
+ "step": 397
2853
+ },
2854
+ {
2855
+ "epoch": 0.045864423381636946,
2856
+ "grad_norm": 1.3271971940994263,
2857
+ "learning_rate": 6.488751431266149e-09,
2858
+ "loss": 0.4546,
2859
+ "step": 398
2860
+ },
2861
+ {
2862
+ "epoch": 0.04597966062631442,
2863
+ "grad_norm": 1.3501412868499756,
2864
+ "learning_rate": 1.622214173602199e-09,
2865
+ "loss": 0.4312,
2866
+ "step": 399
2867
+ },
2868
+ {
2869
+ "epoch": 0.046094897870991906,
2870
+ "grad_norm": 1.38814115524292,
2871
+ "learning_rate": 0.0,
2872
+ "loss": 0.352,
2873
+ "step": 400
2874
+ },
2875
+ {
2876
+ "epoch": 0.046094897870991906,
2877
+ "eval_loss": 0.5639106631278992,
2878
+ "eval_runtime": 544.4924,
2879
+ "eval_samples_per_second": 26.842,
2880
+ "eval_steps_per_second": 6.711,
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": 4.961685721212518e+16,
2911
  "train_batch_size": 8,
2912
  "trial_name": null,
2913
  "trial_params": null