beast33 commited on
Commit
3b852a7
·
verified ·
1 Parent(s): ec74643

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:ce0d9bf5bc49b020e15330e42f4f1f3198fd3c9d1e918d5e02036c11e84b616f
3
  size 37762064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9fa2fa2ca5a458bcee137c17953e7492ac2c7926275bc358ed273e823e02bf8d
3
  size 37762064
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e429b05fc0bd37611cea4be7a6067ca9bc91858acf7ca4364c619caeb1a8a05f
3
  size 19283834
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9593ffa0d528a94d5a6bb1645d9a453296c4d6037ff6bf92382935eb6fbe9b3
3
  size 19283834
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c8234c5e3717fc8a31d5e856bc88712d8e6f3a22e95aecb83fdaac115a40e843
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6c51209fe3eebfcb64ac2384b6320dff0e745b81242ec98132dfc3bdf90a71f
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": 2.9626200199127197,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-350",
4
- "epoch": 0.7954545454545454,
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": 116.33,
2522
  "eval_steps_per_second": 29.2,
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": 0
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": 9730097355423744.0,
2553
  "train_batch_size": 8,
2554
  "trial_name": null,
2555
  "trial_params": null
 
1
  {
2
  "best_metric": 2.9626200199127197,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-350",
4
+ "epoch": 0.9090909090909091,
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": 116.33,
2522
  "eval_steps_per_second": 29.2,
2523
  "step": 350
2524
+ },
2525
+ {
2526
+ "epoch": 0.7977272727272727,
2527
+ "grad_norm": 789.6100463867188,
2528
+ "learning_rate": 3.844650207332562e-06,
2529
+ "loss": 10.3632,
2530
+ "step": 351
2531
+ },
2532
+ {
2533
+ "epoch": 0.8,
2534
+ "grad_norm": 1540.0357666015625,
2535
+ "learning_rate": 3.691267552111183e-06,
2536
+ "loss": 10.8709,
2537
+ "step": 352
2538
+ },
2539
+ {
2540
+ "epoch": 0.8022727272727272,
2541
+ "grad_norm": 1330.8331298828125,
2542
+ "learning_rate": 3.54088980417534e-06,
2543
+ "loss": 11.529,
2544
+ "step": 353
2545
+ },
2546
+ {
2547
+ "epoch": 0.8045454545454546,
2548
+ "grad_norm": 1230.271240234375,
2549
+ "learning_rate": 3.393526721321616e-06,
2550
+ "loss": 10.5697,
2551
+ "step": 354
2552
+ },
2553
+ {
2554
+ "epoch": 0.8068181818181818,
2555
+ "grad_norm": 831.197998046875,
2556
+ "learning_rate": 3.249187865729264e-06,
2557
+ "loss": 11.1612,
2558
+ "step": 355
2559
+ },
2560
+ {
2561
+ "epoch": 0.8090909090909091,
2562
+ "grad_norm": 3166.743408203125,
2563
+ "learning_rate": 3.1078826033397843e-06,
2564
+ "loss": 12.0749,
2565
+ "step": 356
2566
+ },
2567
+ {
2568
+ "epoch": 0.8113636363636364,
2569
+ "grad_norm": 1721.93505859375,
2570
+ "learning_rate": 2.9696201032491434e-06,
2571
+ "loss": 11.3378,
2572
+ "step": 357
2573
+ },
2574
+ {
2575
+ "epoch": 0.8136363636363636,
2576
+ "grad_norm": 1398.169189453125,
2577
+ "learning_rate": 2.8344093371128424e-06,
2578
+ "loss": 10.1568,
2579
+ "step": 358
2580
+ },
2581
+ {
2582
+ "epoch": 0.8159090909090909,
2583
+ "grad_norm": 1929.4913330078125,
2584
+ "learning_rate": 2.70225907856374e-06,
2585
+ "loss": 10.3731,
2586
+ "step": 359
2587
+ },
2588
+ {
2589
+ "epoch": 0.8181818181818182,
2590
+ "grad_norm": 911.2193603515625,
2591
+ "learning_rate": 2.573177902642726e-06,
2592
+ "loss": 11.2215,
2593
+ "step": 360
2594
+ },
2595
+ {
2596
+ "epoch": 0.8204545454545454,
2597
+ "grad_norm": 1485.77099609375,
2598
+ "learning_rate": 2.4471741852423237e-06,
2599
+ "loss": 11.819,
2600
+ "step": 361
2601
+ },
2602
+ {
2603
+ "epoch": 0.8227272727272728,
2604
+ "grad_norm": 1061.6326904296875,
2605
+ "learning_rate": 2.324256102563188e-06,
2606
+ "loss": 11.0653,
2607
+ "step": 362
2608
+ },
2609
+ {
2610
+ "epoch": 0.825,
2611
+ "grad_norm": 1515.0853271484375,
2612
+ "learning_rate": 2.204431630583548e-06,
2613
+ "loss": 11.5012,
2614
+ "step": 363
2615
+ },
2616
+ {
2617
+ "epoch": 0.8272727272727273,
2618
+ "grad_norm": 1850.1302490234375,
2619
+ "learning_rate": 2.087708544541689e-06,
2620
+ "loss": 12.0337,
2621
+ "step": 364
2622
+ },
2623
+ {
2624
+ "epoch": 0.8295454545454546,
2625
+ "grad_norm": 1671.3448486328125,
2626
+ "learning_rate": 1.974094418431388e-06,
2627
+ "loss": 11.41,
2628
+ "step": 365
2629
+ },
2630
+ {
2631
+ "epoch": 0.8318181818181818,
2632
+ "grad_norm": 1582.1636962890625,
2633
+ "learning_rate": 1.8635966245104664e-06,
2634
+ "loss": 10.5762,
2635
+ "step": 366
2636
+ },
2637
+ {
2638
+ "epoch": 0.8340909090909091,
2639
+ "grad_norm": 1187.1136474609375,
2640
+ "learning_rate": 1.7562223328224325e-06,
2641
+ "loss": 11.25,
2642
+ "step": 367
2643
+ },
2644
+ {
2645
+ "epoch": 0.8363636363636363,
2646
+ "grad_norm": 1535.6676025390625,
2647
+ "learning_rate": 1.6519785107311891e-06,
2648
+ "loss": 10.5354,
2649
+ "step": 368
2650
+ },
2651
+ {
2652
+ "epoch": 0.8386363636363636,
2653
+ "grad_norm": 1943.1771240234375,
2654
+ "learning_rate": 1.5508719224689717e-06,
2655
+ "loss": 11.8646,
2656
+ "step": 369
2657
+ },
2658
+ {
2659
+ "epoch": 0.8409090909090909,
2660
+ "grad_norm": 1752.713134765625,
2661
+ "learning_rate": 1.4529091286973995e-06,
2662
+ "loss": 12.0621,
2663
+ "step": 370
2664
+ },
2665
+ {
2666
+ "epoch": 0.8431818181818181,
2667
+ "grad_norm": 1078.611083984375,
2668
+ "learning_rate": 1.358096486081778e-06,
2669
+ "loss": 11.5519,
2670
+ "step": 371
2671
+ },
2672
+ {
2673
+ "epoch": 0.8454545454545455,
2674
+ "grad_norm": 1412.806640625,
2675
+ "learning_rate": 1.2664401468786114e-06,
2676
+ "loss": 11.2082,
2677
+ "step": 372
2678
+ },
2679
+ {
2680
+ "epoch": 0.8477272727272728,
2681
+ "grad_norm": 1059.2579345703125,
2682
+ "learning_rate": 1.1779460585363944e-06,
2683
+ "loss": 11.5709,
2684
+ "step": 373
2685
+ },
2686
+ {
2687
+ "epoch": 0.85,
2688
+ "grad_norm": 1423.56298828125,
2689
+ "learning_rate": 1.0926199633097157e-06,
2690
+ "loss": 12.1075,
2691
+ "step": 374
2692
+ },
2693
+ {
2694
+ "epoch": 0.8522727272727273,
2695
+ "grad_norm": 1099.129150390625,
2696
+ "learning_rate": 1.0104673978866164e-06,
2697
+ "loss": 12.0805,
2698
+ "step": 375
2699
+ },
2700
+ {
2701
+ "epoch": 0.8545454545454545,
2702
+ "grad_norm": 828.9339599609375,
2703
+ "learning_rate": 9.314936930293283e-07,
2704
+ "loss": 11.9081,
2705
+ "step": 376
2706
+ },
2707
+ {
2708
+ "epoch": 0.8568181818181818,
2709
+ "grad_norm": 1052.0286865234375,
2710
+ "learning_rate": 8.557039732283944e-07,
2711
+ "loss": 12.3398,
2712
+ "step": 377
2713
+ },
2714
+ {
2715
+ "epoch": 0.8590909090909091,
2716
+ "grad_norm": 1970.4168701171875,
2717
+ "learning_rate": 7.83103156370113e-07,
2718
+ "loss": 12.4365,
2719
+ "step": 378
2720
+ },
2721
+ {
2722
+ "epoch": 0.8613636363636363,
2723
+ "grad_norm": 1714.98974609375,
2724
+ "learning_rate": 7.136959534174592e-07,
2725
+ "loss": 12.5114,
2726
+ "step": 379
2727
+ },
2728
+ {
2729
+ "epoch": 0.8636363636363636,
2730
+ "grad_norm": 1188.3385009765625,
2731
+ "learning_rate": 6.474868681043578e-07,
2732
+ "loss": 11.6499,
2733
+ "step": 380
2734
+ },
2735
+ {
2736
+ "epoch": 0.865909090909091,
2737
+ "grad_norm": 1253.0810546875,
2738
+ "learning_rate": 5.844801966434832e-07,
2739
+ "loss": 12.0907,
2740
+ "step": 381
2741
+ },
2742
+ {
2743
+ "epoch": 0.8681818181818182,
2744
+ "grad_norm": 2835.40673828125,
2745
+ "learning_rate": 5.246800274474439e-07,
2746
+ "loss": 12.3153,
2747
+ "step": 382
2748
+ },
2749
+ {
2750
+ "epoch": 0.8704545454545455,
2751
+ "grad_norm": 2510.662109375,
2752
+ "learning_rate": 4.680902408635335e-07,
2753
+ "loss": 11.7307,
2754
+ "step": 383
2755
+ },
2756
+ {
2757
+ "epoch": 0.8727272727272727,
2758
+ "grad_norm": 3078.716552734375,
2759
+ "learning_rate": 4.1471450892189846e-07,
2760
+ "loss": 12.1654,
2761
+ "step": 384
2762
+ },
2763
+ {
2764
+ "epoch": 0.875,
2765
+ "grad_norm": 1733.0069580078125,
2766
+ "learning_rate": 3.6455629509730136e-07,
2767
+ "loss": 11.5061,
2768
+ "step": 385
2769
+ },
2770
+ {
2771
+ "epoch": 0.8772727272727273,
2772
+ "grad_norm": 2909.677490234375,
2773
+ "learning_rate": 3.1761885408435054e-07,
2774
+ "loss": 11.6508,
2775
+ "step": 386
2776
+ },
2777
+ {
2778
+ "epoch": 0.8795454545454545,
2779
+ "grad_norm": 1926.2779541015625,
2780
+ "learning_rate": 2.7390523158633554e-07,
2781
+ "loss": 12.6988,
2782
+ "step": 387
2783
+ },
2784
+ {
2785
+ "epoch": 0.8818181818181818,
2786
+ "grad_norm": 5946.1044921875,
2787
+ "learning_rate": 2.334182641175686e-07,
2788
+ "loss": 12.0445,
2789
+ "step": 388
2790
+ },
2791
+ {
2792
+ "epoch": 0.884090909090909,
2793
+ "grad_norm": 6480.4072265625,
2794
+ "learning_rate": 1.9616057881935436e-07,
2795
+ "loss": 12.8209,
2796
+ "step": 389
2797
+ },
2798
+ {
2799
+ "epoch": 0.8863636363636364,
2800
+ "grad_norm": 2346.46728515625,
2801
+ "learning_rate": 1.6213459328950352e-07,
2802
+ "loss": 12.8736,
2803
+ "step": 390
2804
+ },
2805
+ {
2806
+ "epoch": 0.8886363636363637,
2807
+ "grad_norm": 3942.79248046875,
2808
+ "learning_rate": 1.3134251542544774e-07,
2809
+ "loss": 13.1735,
2810
+ "step": 391
2811
+ },
2812
+ {
2813
+ "epoch": 0.8909090909090909,
2814
+ "grad_norm": 2827.50146484375,
2815
+ "learning_rate": 1.0378634328099269e-07,
2816
+ "loss": 11.6477,
2817
+ "step": 392
2818
+ },
2819
+ {
2820
+ "epoch": 0.8931818181818182,
2821
+ "grad_norm": 1975.120361328125,
2822
+ "learning_rate": 7.946786493666647e-08,
2823
+ "loss": 11.8525,
2824
+ "step": 393
2825
+ },
2826
+ {
2827
+ "epoch": 0.8954545454545455,
2828
+ "grad_norm": 2601.73388671875,
2829
+ "learning_rate": 5.838865838366792e-08,
2830
+ "loss": 11.5898,
2831
+ "step": 394
2832
+ },
2833
+ {
2834
+ "epoch": 0.8977272727272727,
2835
+ "grad_norm": 10033.3173828125,
2836
+ "learning_rate": 4.055009142152067e-08,
2837
+ "loss": 13.2004,
2838
+ "step": 395
2839
+ },
2840
+ {
2841
+ "epoch": 0.9,
2842
+ "grad_norm": 8109.576171875,
2843
+ "learning_rate": 2.595332156925534e-08,
2844
+ "loss": 12.5443,
2845
+ "step": 396
2846
+ },
2847
+ {
2848
+ "epoch": 0.9022727272727272,
2849
+ "grad_norm": 1938.52978515625,
2850
+ "learning_rate": 1.4599295990352924e-08,
2851
+ "loss": 12.0954,
2852
+ "step": 397
2853
+ },
2854
+ {
2855
+ "epoch": 0.9045454545454545,
2856
+ "grad_norm": 3072.64404296875,
2857
+ "learning_rate": 6.488751431266149e-09,
2858
+ "loss": 12.5015,
2859
+ "step": 398
2860
+ },
2861
+ {
2862
+ "epoch": 0.9068181818181819,
2863
+ "grad_norm": 2375.041015625,
2864
+ "learning_rate": 1.622214173602199e-09,
2865
+ "loss": 13.0636,
2866
+ "step": 399
2867
+ },
2868
+ {
2869
+ "epoch": 0.9090909090909091,
2870
+ "grad_norm": 4416.111328125,
2871
+ "learning_rate": 0.0,
2872
+ "loss": 13.9673,
2873
+ "step": 400
2874
+ },
2875
+ {
2876
+ "epoch": 0.9090909090909091,
2877
+ "eval_loss": 2.9626402854919434,
2878
+ "eval_runtime": 6.385,
2879
+ "eval_samples_per_second": 116.054,
2880
+ "eval_steps_per_second": 29.131,
2881
+ "step": 400
2882
  }
2883
  ],
2884
  "logging_steps": 1,
 
2893
  "early_stopping_threshold": 0.0
2894
  },
2895
  "attributes": {
2896
+ "early_stopping_patience_counter": 1
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": 1.1117306931314688e+16,
2911
  "train_batch_size": 8,
2912
  "trial_name": null,
2913
  "trial_params": null