error577 commited on
Commit
bba3d24
·
verified ·
1 Parent(s): 3424d42

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:d1c35ae538f4b13ed118009e42d3af5ce35d02974649d677dcae751fa109040d
3
  size 59933632
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:937fc5f94b084d3eb78ca648e5e282469bbf6dfb9116c44545ac208a5eee7095
3
  size 59933632
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1b4af661d5dbc2e4ded19c017724e4032b3e4ebda32ac08442406a113fb81189
3
  size 31823460
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a987323893943b5cb6c9038df21203d888c0501f022965597682cf818af9726f
3
  size 31823460
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e5cd4d6f1a56868495de31ebab839ccdff6500d945e21b9b50d123a2662f6221
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7f62f7a514254178aafeb62bbf10dca9fc4851e21b058bd5fd1775d5039612b
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b881a4283fbf9ae4dd8073fe406895e163eb2a9281e2f7a0b2ffcfdeea673f59
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:381144ff10563e73a0d559f4eadf3a4c93568229fcc444bd951eaeaa68432ea4
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": 0.5701812505722046,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-250",
4
- "epoch": 2.564102564102564,
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": 7.441,
2522
  "eval_steps_per_second": 7.441,
2523
  "step": 350
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2524
  }
2525
  ],
2526
  "logging_steps": 1,
@@ -2535,7 +2893,7 @@
2535
  "early_stopping_threshold": 0.0
2536
  },
2537
  "attributes": {
2538
- "early_stopping_patience_counter": 2
2539
  }
2540
  },
2541
  "TrainerControl": {
@@ -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": 4.957792987250688e+16,
2553
  "train_batch_size": 1,
2554
  "trial_name": null,
2555
  "trial_params": null
 
1
  {
2
  "best_metric": 0.5701812505722046,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-250",
4
+ "epoch": 2.9304029304029307,
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": 7.441,
2522
  "eval_steps_per_second": 7.441,
2523
  "step": 350
2524
+ },
2525
+ {
2526
+ "epoch": 2.571428571428571,
2527
+ "grad_norm": 0.5820057988166809,
2528
+ "learning_rate": 1.4928145131487267e-05,
2529
+ "loss": 0.4702,
2530
+ "step": 351
2531
+ },
2532
+ {
2533
+ "epoch": 2.578754578754579,
2534
+ "grad_norm": 0.5424510836601257,
2535
+ "learning_rate": 1.4417429926676482e-05,
2536
+ "loss": 0.4174,
2537
+ "step": 352
2538
+ },
2539
+ {
2540
+ "epoch": 2.586080586080586,
2541
+ "grad_norm": 0.6577489376068115,
2542
+ "learning_rate": 1.39151623581778e-05,
2543
+ "loss": 0.4169,
2544
+ "step": 353
2545
+ },
2546
+ {
2547
+ "epoch": 2.5934065934065935,
2548
+ "grad_norm": 0.5944687128067017,
2549
+ "learning_rate": 1.3421373720380669e-05,
2550
+ "loss": 0.4272,
2551
+ "step": 354
2552
+ },
2553
+ {
2554
+ "epoch": 2.600732600732601,
2555
+ "grad_norm": 0.7125936150550842,
2556
+ "learning_rate": 1.2936094779384486e-05,
2557
+ "loss": 0.4438,
2558
+ "step": 355
2559
+ },
2560
+ {
2561
+ "epoch": 2.608058608058608,
2562
+ "grad_norm": 0.679352879524231,
2563
+ "learning_rate": 1.245935577108168e-05,
2564
+ "loss": 0.4949,
2565
+ "step": 356
2566
+ },
2567
+ {
2568
+ "epoch": 2.6153846153846154,
2569
+ "grad_norm": 1.0750776529312134,
2570
+ "learning_rate": 1.199118639927385e-05,
2571
+ "loss": 0.3986,
2572
+ "step": 357
2573
+ },
2574
+ {
2575
+ "epoch": 2.6227106227106227,
2576
+ "grad_norm": 0.8349664211273193,
2577
+ "learning_rate": 1.1531615833820906e-05,
2578
+ "loss": 0.4152,
2579
+ "step": 358
2580
+ },
2581
+ {
2582
+ "epoch": 2.63003663003663,
2583
+ "grad_norm": 0.770355761051178,
2584
+ "learning_rate": 1.108067270882384e-05,
2585
+ "loss": 0.4878,
2586
+ "step": 359
2587
+ },
2588
+ {
2589
+ "epoch": 2.6373626373626373,
2590
+ "grad_norm": 0.7165803909301758,
2591
+ "learning_rate": 1.0638385120840414e-05,
2592
+ "loss": 0.3852,
2593
+ "step": 360
2594
+ },
2595
+ {
2596
+ "epoch": 2.6446886446886446,
2597
+ "grad_norm": 0.7379334568977356,
2598
+ "learning_rate": 1.0204780627134784e-05,
2599
+ "loss": 0.4758,
2600
+ "step": 361
2601
+ },
2602
+ {
2603
+ "epoch": 2.652014652014652,
2604
+ "grad_norm": 0.6477860808372498,
2605
+ "learning_rate": 9.77988624396025e-06,
2606
+ "loss": 0.3718,
2607
+ "step": 362
2608
+ },
2609
+ {
2610
+ "epoch": 2.659340659340659,
2611
+ "grad_norm": 0.6215366721153259,
2612
+ "learning_rate": 9.363728444876239e-06,
2613
+ "loss": 0.3146,
2614
+ "step": 363
2615
+ },
2616
+ {
2617
+ "epoch": 2.6666666666666665,
2618
+ "grad_norm": 0.7191038727760315,
2619
+ "learning_rate": 8.956333159098677e-06,
2620
+ "loss": 0.2567,
2621
+ "step": 364
2622
+ },
2623
+ {
2624
+ "epoch": 2.6739926739926743,
2625
+ "grad_norm": 0.6438663005828857,
2626
+ "learning_rate": 8.557725769884444e-06,
2627
+ "loss": 0.3366,
2628
+ "step": 365
2629
+ },
2630
+ {
2631
+ "epoch": 2.6813186813186816,
2632
+ "grad_norm": 0.7834159135818481,
2633
+ "learning_rate": 8.167931112949955e-06,
2634
+ "loss": 0.2802,
2635
+ "step": 366
2636
+ },
2637
+ {
2638
+ "epoch": 2.688644688644689,
2639
+ "grad_norm": 0.687300443649292,
2640
+ "learning_rate": 7.786973474923569e-06,
2641
+ "loss": 0.3275,
2642
+ "step": 367
2643
+ },
2644
+ {
2645
+ "epoch": 2.695970695970696,
2646
+ "grad_norm": 0.633350133895874,
2647
+ "learning_rate": 7.41487659183258e-06,
2648
+ "loss": 0.2462,
2649
+ "step": 368
2650
+ },
2651
+ {
2652
+ "epoch": 2.7032967032967035,
2653
+ "grad_norm": 0.8299592137336731,
2654
+ "learning_rate": 7.051663647624117e-06,
2655
+ "loss": 0.2847,
2656
+ "step": 369
2657
+ },
2658
+ {
2659
+ "epoch": 2.7106227106227108,
2660
+ "grad_norm": 0.6400296688079834,
2661
+ "learning_rate": 6.697357272720782e-06,
2662
+ "loss": 0.239,
2663
+ "step": 370
2664
+ },
2665
+ {
2666
+ "epoch": 2.717948717948718,
2667
+ "grad_norm": 0.620663583278656,
2668
+ "learning_rate": 6.35197954261058e-06,
2669
+ "loss": 0.183,
2670
+ "step": 371
2671
+ },
2672
+ {
2673
+ "epoch": 2.7252747252747254,
2674
+ "grad_norm": 0.7446674108505249,
2675
+ "learning_rate": 6.015551976471433e-06,
2676
+ "loss": 0.2334,
2677
+ "step": 372
2678
+ },
2679
+ {
2680
+ "epoch": 2.7326007326007327,
2681
+ "grad_norm": 0.8476528525352478,
2682
+ "learning_rate": 5.688095535830573e-06,
2683
+ "loss": 0.1747,
2684
+ "step": 373
2685
+ },
2686
+ {
2687
+ "epoch": 2.73992673992674,
2688
+ "grad_norm": 0.8313474655151367,
2689
+ "learning_rate": 5.369630623258248e-06,
2690
+ "loss": 0.189,
2691
+ "step": 374
2692
+ },
2693
+ {
2694
+ "epoch": 2.7472527472527473,
2695
+ "grad_norm": 0.9323949217796326,
2696
+ "learning_rate": 5.060177081096728e-06,
2697
+ "loss": 0.0911,
2698
+ "step": 375
2699
+ },
2700
+ {
2701
+ "epoch": 2.7545787545787546,
2702
+ "grad_norm": 0.33731380105018616,
2703
+ "learning_rate": 4.759754190223925e-06,
2704
+ "loss": 0.4471,
2705
+ "step": 376
2706
+ },
2707
+ {
2708
+ "epoch": 2.761904761904762,
2709
+ "grad_norm": 0.37849536538124084,
2710
+ "learning_rate": 4.468380668852068e-06,
2711
+ "loss": 0.6115,
2712
+ "step": 377
2713
+ },
2714
+ {
2715
+ "epoch": 2.769230769230769,
2716
+ "grad_norm": 0.4009314775466919,
2717
+ "learning_rate": 4.186074671361456e-06,
2718
+ "loss": 0.575,
2719
+ "step": 378
2720
+ },
2721
+ {
2722
+ "epoch": 2.7765567765567765,
2723
+ "grad_norm": 0.3839149475097656,
2724
+ "learning_rate": 3.912853787169345e-06,
2725
+ "loss": 0.5056,
2726
+ "step": 379
2727
+ },
2728
+ {
2729
+ "epoch": 2.7838827838827838,
2730
+ "grad_norm": 0.40725114941596985,
2731
+ "learning_rate": 3.6487350396339597e-06,
2732
+ "loss": 0.4408,
2733
+ "step": 380
2734
+ },
2735
+ {
2736
+ "epoch": 2.791208791208791,
2737
+ "grad_norm": 0.4696556329727173,
2738
+ "learning_rate": 3.3937348849939204e-06,
2739
+ "loss": 0.5321,
2740
+ "step": 381
2741
+ },
2742
+ {
2743
+ "epoch": 2.7985347985347984,
2744
+ "grad_norm": 0.43771475553512573,
2745
+ "learning_rate": 3.147869211342818e-06,
2746
+ "loss": 0.4356,
2747
+ "step": 382
2748
+ },
2749
+ {
2750
+ "epoch": 2.8058608058608057,
2751
+ "grad_norm": 0.5101984739303589,
2752
+ "learning_rate": 2.911153337639388e-06,
2753
+ "loss": 0.4499,
2754
+ "step": 383
2755
+ },
2756
+ {
2757
+ "epoch": 2.813186813186813,
2758
+ "grad_norm": 0.5081220865249634,
2759
+ "learning_rate": 2.683602012752939e-06,
2760
+ "loss": 0.4756,
2761
+ "step": 384
2762
+ },
2763
+ {
2764
+ "epoch": 2.8205128205128203,
2765
+ "grad_norm": 0.5413169264793396,
2766
+ "learning_rate": 2.4652294145445226e-06,
2767
+ "loss": 0.4866,
2768
+ "step": 385
2769
+ },
2770
+ {
2771
+ "epoch": 2.8278388278388276,
2772
+ "grad_norm": 0.5008475184440613,
2773
+ "learning_rate": 2.256049148983441e-06,
2774
+ "loss": 0.4641,
2775
+ "step": 386
2776
+ },
2777
+ {
2778
+ "epoch": 2.8351648351648353,
2779
+ "grad_norm": 0.5848665833473206,
2780
+ "learning_rate": 2.0560742492995885e-06,
2781
+ "loss": 0.4572,
2782
+ "step": 387
2783
+ },
2784
+ {
2785
+ "epoch": 2.8424908424908426,
2786
+ "grad_norm": 0.6183776259422302,
2787
+ "learning_rate": 1.8653171751714379e-06,
2788
+ "loss": 0.5198,
2789
+ "step": 388
2790
+ },
2791
+ {
2792
+ "epoch": 2.84981684981685,
2793
+ "grad_norm": 0.5888795852661133,
2794
+ "learning_rate": 1.6837898119496263e-06,
2795
+ "loss": 0.451,
2796
+ "step": 389
2797
+ },
2798
+ {
2799
+ "epoch": 2.857142857142857,
2800
+ "grad_norm": 0.5763834118843079,
2801
+ "learning_rate": 1.5115034699164308e-06,
2802
+ "loss": 0.4926,
2803
+ "step": 390
2804
+ },
2805
+ {
2806
+ "epoch": 2.8644688644688645,
2807
+ "grad_norm": 0.6053770184516907,
2808
+ "learning_rate": 1.348468883581183e-06,
2809
+ "loss": 0.443,
2810
+ "step": 391
2811
+ },
2812
+ {
2813
+ "epoch": 2.871794871794872,
2814
+ "grad_norm": 0.5707501769065857,
2815
+ "learning_rate": 1.19469621101132e-06,
2816
+ "loss": 0.4184,
2817
+ "step": 392
2818
+ },
2819
+ {
2820
+ "epoch": 2.879120879120879,
2821
+ "grad_norm": 0.5886608958244324,
2822
+ "learning_rate": 1.0501950331995578e-06,
2823
+ "loss": 0.4002,
2824
+ "step": 393
2825
+ },
2826
+ {
2827
+ "epoch": 2.8864468864468864,
2828
+ "grad_norm": 0.5797408223152161,
2829
+ "learning_rate": 9.149743534668353e-07,
2830
+ "loss": 0.4117,
2831
+ "step": 394
2832
+ },
2833
+ {
2834
+ "epoch": 2.8937728937728937,
2835
+ "grad_norm": 0.7185364961624146,
2836
+ "learning_rate": 7.890425969014625e-07,
2837
+ "loss": 0.4059,
2838
+ "step": 395
2839
+ },
2840
+ {
2841
+ "epoch": 2.901098901098901,
2842
+ "grad_norm": 0.7297194004058838,
2843
+ "learning_rate": 6.724076098341247e-07,
2844
+ "loss": 0.3407,
2845
+ "step": 396
2846
+ },
2847
+ {
2848
+ "epoch": 2.9084249084249083,
2849
+ "grad_norm": 0.6948420405387878,
2850
+ "learning_rate": 5.650766593489897e-07,
2851
+ "loss": 0.3564,
2852
+ "step": 397
2853
+ },
2854
+ {
2855
+ "epoch": 2.9157509157509156,
2856
+ "grad_norm": 0.6854040026664734,
2857
+ "learning_rate": 4.6705643283102003e-07,
2858
+ "loss": 0.4018,
2859
+ "step": 398
2860
+ },
2861
+ {
2862
+ "epoch": 2.9230769230769234,
2863
+ "grad_norm": 0.7185117602348328,
2864
+ "learning_rate": 3.7835303754918943e-07,
2865
+ "loss": 0.3607,
2866
+ "step": 399
2867
+ },
2868
+ {
2869
+ "epoch": 2.9304029304029307,
2870
+ "grad_norm": 0.6749255061149597,
2871
+ "learning_rate": 2.9897200027598767e-07,
2872
+ "loss": 0.276,
2873
+ "step": 400
2874
+ },
2875
+ {
2876
+ "epoch": 2.9304029304029307,
2877
+ "eval_loss": 0.60358726978302,
2878
+ "eval_runtime": 73.527,
2879
+ "eval_samples_per_second": 7.439,
2880
+ "eval_steps_per_second": 7.439,
2881
+ "step": 400
2882
  }
2883
  ],
2884
  "logging_steps": 1,
 
2893
  "early_stopping_threshold": 0.0
2894
  },
2895
  "attributes": {
2896
+ "early_stopping_patience_counter": 3
2897
  }
2898
  },
2899
  "TrainerControl": {
 
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": 5.659682780951347e+16,
2911
  "train_batch_size": 1,
2912
  "trial_name": null,
2913
  "trial_params": null