auxyus commited on
Commit
2801355
·
verified ·
1 Parent(s): 7b3e0ae

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 sha256:017cc60681091399519daa35a6c36172084798206d3fdab592ca9cf010195138
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:402c27f897660251f85e15e388825a92f0e69d84423fabdb863847f8c2289fe7
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a282689092718c8623673170ac7e49d28afb636ba944b69b53fcfbed9dbd22fe
3
  size 341314644
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7da07494c34e9b9749d22804d0a956a3357edc6a1df4a4621a772162a90c04c8
3
  size 341314644
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:471adc9c617f084ae889d5a152fe6c61f6bf5b3dfae964cc90cc5c107c8abfbb
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a26063f6f51f1949c365f9dffa01a525853946d72ecb53b4fa44938a61aabd02
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": 0.5738900899887085,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-350",
4
- "epoch": 0.39381153305203936,
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": 12.131,
2522
  "eval_steps_per_second": 3.039,
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": 5.596585377147126e+17,
2553
  "train_batch_size": 8,
2554
  "trial_name": null,
2555
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.5731000304222107,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-400",
4
+ "epoch": 0.450070323488045,
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": 12.131,
2522
  "eval_steps_per_second": 3.039,
2523
  "step": 350
2524
+ },
2525
+ {
2526
+ "epoch": 0.3949367088607595,
2527
+ "grad_norm": 0.18382947146892548,
2528
+ "learning_rate": 3.844650207332562e-06,
2529
+ "loss": 0.372,
2530
+ "step": 351
2531
+ },
2532
+ {
2533
+ "epoch": 0.3960618846694796,
2534
+ "grad_norm": 0.18228398263454437,
2535
+ "learning_rate": 3.691267552111183e-06,
2536
+ "loss": 0.3865,
2537
+ "step": 352
2538
+ },
2539
+ {
2540
+ "epoch": 0.39718706047819974,
2541
+ "grad_norm": 0.19391196966171265,
2542
+ "learning_rate": 3.54088980417534e-06,
2543
+ "loss": 0.518,
2544
+ "step": 353
2545
+ },
2546
+ {
2547
+ "epoch": 0.3983122362869198,
2548
+ "grad_norm": 0.20379137992858887,
2549
+ "learning_rate": 3.393526721321616e-06,
2550
+ "loss": 0.6073,
2551
+ "step": 354
2552
+ },
2553
+ {
2554
+ "epoch": 0.39943741209563993,
2555
+ "grad_norm": 0.20377278327941895,
2556
+ "learning_rate": 3.249187865729264e-06,
2557
+ "loss": 0.5355,
2558
+ "step": 355
2559
+ },
2560
+ {
2561
+ "epoch": 0.40056258790436006,
2562
+ "grad_norm": 0.21739913523197174,
2563
+ "learning_rate": 3.1078826033397843e-06,
2564
+ "loss": 0.5892,
2565
+ "step": 356
2566
+ },
2567
+ {
2568
+ "epoch": 0.4016877637130802,
2569
+ "grad_norm": 0.20590797066688538,
2570
+ "learning_rate": 2.9696201032491434e-06,
2571
+ "loss": 0.5308,
2572
+ "step": 357
2573
+ },
2574
+ {
2575
+ "epoch": 0.4028129395218003,
2576
+ "grad_norm": 0.22945421934127808,
2577
+ "learning_rate": 2.8344093371128424e-06,
2578
+ "loss": 0.612,
2579
+ "step": 358
2580
+ },
2581
+ {
2582
+ "epoch": 0.4039381153305204,
2583
+ "grad_norm": 0.23170845210552216,
2584
+ "learning_rate": 2.70225907856374e-06,
2585
+ "loss": 0.6246,
2586
+ "step": 359
2587
+ },
2588
+ {
2589
+ "epoch": 0.4050632911392405,
2590
+ "grad_norm": 0.23253555595874786,
2591
+ "learning_rate": 2.573177902642726e-06,
2592
+ "loss": 0.6423,
2593
+ "step": 360
2594
+ },
2595
+ {
2596
+ "epoch": 0.4061884669479606,
2597
+ "grad_norm": 0.23829902708530426,
2598
+ "learning_rate": 2.4471741852423237e-06,
2599
+ "loss": 0.6802,
2600
+ "step": 361
2601
+ },
2602
+ {
2603
+ "epoch": 0.40731364275668075,
2604
+ "grad_norm": 0.24621927738189697,
2605
+ "learning_rate": 2.324256102563188e-06,
2606
+ "loss": 0.6475,
2607
+ "step": 362
2608
+ },
2609
+ {
2610
+ "epoch": 0.4084388185654008,
2611
+ "grad_norm": 0.24897930026054382,
2612
+ "learning_rate": 2.204431630583548e-06,
2613
+ "loss": 0.7314,
2614
+ "step": 363
2615
+ },
2616
+ {
2617
+ "epoch": 0.40956399437412094,
2618
+ "grad_norm": 0.25607559084892273,
2619
+ "learning_rate": 2.087708544541689e-06,
2620
+ "loss": 0.7108,
2621
+ "step": 364
2622
+ },
2623
+ {
2624
+ "epoch": 0.41068917018284107,
2625
+ "grad_norm": 0.26042604446411133,
2626
+ "learning_rate": 1.974094418431388e-06,
2627
+ "loss": 0.8427,
2628
+ "step": 365
2629
+ },
2630
+ {
2631
+ "epoch": 0.4118143459915612,
2632
+ "grad_norm": 0.2578832805156708,
2633
+ "learning_rate": 1.8635966245104664e-06,
2634
+ "loss": 0.7355,
2635
+ "step": 366
2636
+ },
2637
+ {
2638
+ "epoch": 0.4129395218002813,
2639
+ "grad_norm": 0.25586313009262085,
2640
+ "learning_rate": 1.7562223328224325e-06,
2641
+ "loss": 0.7442,
2642
+ "step": 367
2643
+ },
2644
+ {
2645
+ "epoch": 0.4140646976090014,
2646
+ "grad_norm": 0.2767845094203949,
2647
+ "learning_rate": 1.6519785107311891e-06,
2648
+ "loss": 0.8506,
2649
+ "step": 368
2650
+ },
2651
+ {
2652
+ "epoch": 0.4151898734177215,
2653
+ "grad_norm": 0.2640194892883301,
2654
+ "learning_rate": 1.5508719224689717e-06,
2655
+ "loss": 0.7084,
2656
+ "step": 369
2657
+ },
2658
+ {
2659
+ "epoch": 0.41631504922644164,
2660
+ "grad_norm": 0.2685393989086151,
2661
+ "learning_rate": 1.4529091286973995e-06,
2662
+ "loss": 0.7258,
2663
+ "step": 370
2664
+ },
2665
+ {
2666
+ "epoch": 0.41744022503516176,
2667
+ "grad_norm": 0.2706719636917114,
2668
+ "learning_rate": 1.358096486081778e-06,
2669
+ "loss": 0.7101,
2670
+ "step": 371
2671
+ },
2672
+ {
2673
+ "epoch": 0.41856540084388183,
2674
+ "grad_norm": 0.27270835638046265,
2675
+ "learning_rate": 1.2664401468786114e-06,
2676
+ "loss": 0.7251,
2677
+ "step": 372
2678
+ },
2679
+ {
2680
+ "epoch": 0.41969057665260195,
2681
+ "grad_norm": 0.28525063395500183,
2682
+ "learning_rate": 1.1779460585363944e-06,
2683
+ "loss": 0.7922,
2684
+ "step": 373
2685
+ },
2686
+ {
2687
+ "epoch": 0.4208157524613221,
2688
+ "grad_norm": 0.2806113362312317,
2689
+ "learning_rate": 1.0926199633097157e-06,
2690
+ "loss": 0.7772,
2691
+ "step": 374
2692
+ },
2693
+ {
2694
+ "epoch": 0.4219409282700422,
2695
+ "grad_norm": 0.29236048460006714,
2696
+ "learning_rate": 1.0104673978866164e-06,
2697
+ "loss": 0.776,
2698
+ "step": 375
2699
+ },
2700
+ {
2701
+ "epoch": 0.42306610407876233,
2702
+ "grad_norm": 0.2895606756210327,
2703
+ "learning_rate": 9.314936930293283e-07,
2704
+ "loss": 0.7037,
2705
+ "step": 376
2706
+ },
2707
+ {
2708
+ "epoch": 0.4241912798874824,
2709
+ "grad_norm": 0.2893851101398468,
2710
+ "learning_rate": 8.557039732283944e-07,
2711
+ "loss": 0.7635,
2712
+ "step": 377
2713
+ },
2714
+ {
2715
+ "epoch": 0.4253164556962025,
2716
+ "grad_norm": 0.2851521670818329,
2717
+ "learning_rate": 7.83103156370113e-07,
2718
+ "loss": 0.6912,
2719
+ "step": 378
2720
+ },
2721
+ {
2722
+ "epoch": 0.42644163150492265,
2723
+ "grad_norm": 0.2914351224899292,
2724
+ "learning_rate": 7.136959534174592e-07,
2725
+ "loss": 0.6818,
2726
+ "step": 379
2727
+ },
2728
+ {
2729
+ "epoch": 0.42756680731364277,
2730
+ "grad_norm": 0.2961958348751068,
2731
+ "learning_rate": 6.474868681043578e-07,
2732
+ "loss": 0.6924,
2733
+ "step": 380
2734
+ },
2735
+ {
2736
+ "epoch": 0.4286919831223629,
2737
+ "grad_norm": 0.30675557255744934,
2738
+ "learning_rate": 5.844801966434832e-07,
2739
+ "loss": 0.768,
2740
+ "step": 381
2741
+ },
2742
+ {
2743
+ "epoch": 0.42981715893108297,
2744
+ "grad_norm": 0.303774356842041,
2745
+ "learning_rate": 5.246800274474439e-07,
2746
+ "loss": 0.6428,
2747
+ "step": 382
2748
+ },
2749
+ {
2750
+ "epoch": 0.4309423347398031,
2751
+ "grad_norm": 0.3004835844039917,
2752
+ "learning_rate": 4.680902408635335e-07,
2753
+ "loss": 0.6931,
2754
+ "step": 383
2755
+ },
2756
+ {
2757
+ "epoch": 0.4320675105485232,
2758
+ "grad_norm": 0.29980704188346863,
2759
+ "learning_rate": 4.1471450892189846e-07,
2760
+ "loss": 0.5863,
2761
+ "step": 384
2762
+ },
2763
+ {
2764
+ "epoch": 0.43319268635724334,
2765
+ "grad_norm": 0.29202115535736084,
2766
+ "learning_rate": 3.6455629509730136e-07,
2767
+ "loss": 0.5396,
2768
+ "step": 385
2769
+ },
2770
+ {
2771
+ "epoch": 0.4343178621659634,
2772
+ "grad_norm": 0.3045811653137207,
2773
+ "learning_rate": 3.1761885408435054e-07,
2774
+ "loss": 0.5696,
2775
+ "step": 386
2776
+ },
2777
+ {
2778
+ "epoch": 0.43544303797468353,
2779
+ "grad_norm": 0.29848921298980713,
2780
+ "learning_rate": 2.7390523158633554e-07,
2781
+ "loss": 0.4808,
2782
+ "step": 387
2783
+ },
2784
+ {
2785
+ "epoch": 0.43656821378340366,
2786
+ "grad_norm": 0.29339462518692017,
2787
+ "learning_rate": 2.334182641175686e-07,
2788
+ "loss": 0.4606,
2789
+ "step": 388
2790
+ },
2791
+ {
2792
+ "epoch": 0.4376933895921238,
2793
+ "grad_norm": 0.31360113620758057,
2794
+ "learning_rate": 1.9616057881935436e-07,
2795
+ "loss": 0.4696,
2796
+ "step": 389
2797
+ },
2798
+ {
2799
+ "epoch": 0.4388185654008439,
2800
+ "grad_norm": 0.31095123291015625,
2801
+ "learning_rate": 1.6213459328950352e-07,
2802
+ "loss": 0.4802,
2803
+ "step": 390
2804
+ },
2805
+ {
2806
+ "epoch": 0.439943741209564,
2807
+ "grad_norm": 0.30314531922340393,
2808
+ "learning_rate": 1.3134251542544774e-07,
2809
+ "loss": 0.4323,
2810
+ "step": 391
2811
+ },
2812
+ {
2813
+ "epoch": 0.4410689170182841,
2814
+ "grad_norm": 0.34104612469673157,
2815
+ "learning_rate": 1.0378634328099269e-07,
2816
+ "loss": 0.4987,
2817
+ "step": 392
2818
+ },
2819
+ {
2820
+ "epoch": 0.4421940928270042,
2821
+ "grad_norm": 0.3525398075580597,
2822
+ "learning_rate": 7.946786493666647e-08,
2823
+ "loss": 0.4656,
2824
+ "step": 393
2825
+ },
2826
+ {
2827
+ "epoch": 0.44331926863572435,
2828
+ "grad_norm": 0.32821884751319885,
2829
+ "learning_rate": 5.838865838366792e-08,
2830
+ "loss": 0.3665,
2831
+ "step": 394
2832
+ },
2833
+ {
2834
+ "epoch": 0.4444444444444444,
2835
+ "grad_norm": 0.3422605097293854,
2836
+ "learning_rate": 4.055009142152067e-08,
2837
+ "loss": 0.3255,
2838
+ "step": 395
2839
+ },
2840
+ {
2841
+ "epoch": 0.44556962025316454,
2842
+ "grad_norm": 0.3505786061286926,
2843
+ "learning_rate": 2.595332156925534e-08,
2844
+ "loss": 0.3839,
2845
+ "step": 396
2846
+ },
2847
+ {
2848
+ "epoch": 0.44669479606188467,
2849
+ "grad_norm": 0.35224196314811707,
2850
+ "learning_rate": 1.4599295990352924e-08,
2851
+ "loss": 0.3063,
2852
+ "step": 397
2853
+ },
2854
+ {
2855
+ "epoch": 0.4478199718706048,
2856
+ "grad_norm": 0.39496955275535583,
2857
+ "learning_rate": 6.488751431266149e-09,
2858
+ "loss": 0.3376,
2859
+ "step": 398
2860
+ },
2861
+ {
2862
+ "epoch": 0.4489451476793249,
2863
+ "grad_norm": 0.4384694993495941,
2864
+ "learning_rate": 1.622214173602199e-09,
2865
+ "loss": 0.3727,
2866
+ "step": 399
2867
+ },
2868
+ {
2869
+ "epoch": 0.450070323488045,
2870
+ "grad_norm": 0.5900406837463379,
2871
+ "learning_rate": 0.0,
2872
+ "loss": 0.3785,
2873
+ "step": 400
2874
+ },
2875
+ {
2876
+ "epoch": 0.450070323488045,
2877
+ "eval_loss": 0.5731000304222107,
2878
+ "eval_runtime": 122.6526,
2879
+ "eval_samples_per_second": 12.205,
2880
+ "eval_steps_per_second": 3.057,
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": 6.392326289935565e+17,
2911
  "train_batch_size": 8,
2912
  "trial_name": null,
2913
  "trial_params": null