alchemist69 commited on
Commit
efe9a7b
·
verified ·
1 Parent(s): 21c4800

Training in progress, step 394, 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:f4fd69de360233d28f47204090d87c4f2b36777100e178bb2aa7fb60f032d3c2
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:674be5ab7efe0b11f096cb9f7a5fe89b98aaf6021a7919df16bd207a95e36e38
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:00de4a1592bcbc901c430101ca8d879ba63eac471b2e876ffd9df40a1ed3cb18
3
  size 341314644
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f53b04d6b9cdae537d0470f47d7d408ec561df31993320a574cef61865b4a9bb
3
  size 341314644
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:468f08c9e4cce238ebe4cfc1f562fa88581e26f8c5e3ee29ea4542874ac818ef
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0bb3668698c599ad42ba7898487a93b61a3ea7d00198d1a927e4e94db6415931
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:12de14193ab3ff62a06dafdf69d0e0c0387b6b24b330f0b91bd65a760deab81f
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:234a01d535239521bf8fa77cc9fee1a8448db6fb25d738b305e57e81be7fdc60
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": 0.3816964328289032,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-350",
4
- "epoch": 0.8894536213468869,
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 +2521,314 @@
2521
  "eval_samples_per_second": 7.189,
2522
  "eval_steps_per_second": 1.8,
2523
  "step": 350
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2524
  }
2525
  ],
2526
  "logging_steps": 1,
@@ -2544,12 +2852,12 @@
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": 8.835596708688691e+17,
2553
  "train_batch_size": 8,
2554
  "trial_name": null,
2555
  "trial_params": null
 
1
  {
2
  "best_metric": 0.3816964328289032,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-350",
4
+ "epoch": 1.0012706480304956,
5
  "eval_steps": 50,
6
+ "global_step": 394,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
2521
  "eval_samples_per_second": 7.189,
2522
  "eval_steps_per_second": 1.8,
2523
  "step": 350
2524
+ },
2525
+ {
2526
+ "epoch": 0.8919949174078781,
2527
+ "grad_norm": 0.4216729700565338,
2528
+ "learning_rate": 3.0621793765093444e-06,
2529
+ "loss": 0.3226,
2530
+ "step": 351
2531
+ },
2532
+ {
2533
+ "epoch": 0.8945362134688691,
2534
+ "grad_norm": 0.35222530364990234,
2535
+ "learning_rate": 2.9227967408489653e-06,
2536
+ "loss": 0.1623,
2537
+ "step": 352
2538
+ },
2539
+ {
2540
+ "epoch": 0.8970775095298602,
2541
+ "grad_norm": 0.558908998966217,
2542
+ "learning_rate": 2.786565084334175e-06,
2543
+ "loss": 0.3667,
2544
+ "step": 353
2545
+ },
2546
+ {
2547
+ "epoch": 0.8996188055908514,
2548
+ "grad_norm": 0.37411656975746155,
2549
+ "learning_rate": 2.653493525244721e-06,
2550
+ "loss": 0.2027,
2551
+ "step": 354
2552
+ },
2553
+ {
2554
+ "epoch": 0.9021601016518425,
2555
+ "grad_norm": 0.40490609407424927,
2556
+ "learning_rate": 2.5235909703481665e-06,
2557
+ "loss": 0.305,
2558
+ "step": 355
2559
+ },
2560
+ {
2561
+ "epoch": 0.9047013977128335,
2562
+ "grad_norm": 0.38682472705841064,
2563
+ "learning_rate": 2.3968661143037862e-06,
2564
+ "loss": 0.289,
2565
+ "step": 356
2566
+ },
2567
+ {
2568
+ "epoch": 0.9072426937738246,
2569
+ "grad_norm": 0.39111873507499695,
2570
+ "learning_rate": 2.273327439080575e-06,
2571
+ "loss": 0.2358,
2572
+ "step": 357
2573
+ },
2574
+ {
2575
+ "epoch": 0.9097839898348158,
2576
+ "grad_norm": 0.4046552777290344,
2577
+ "learning_rate": 2.152983213389559e-06,
2578
+ "loss": 0.2605,
2579
+ "step": 358
2580
+ },
2581
+ {
2582
+ "epoch": 0.9123252858958069,
2583
+ "grad_norm": 0.44025343656539917,
2584
+ "learning_rate": 2.035841492130319e-06,
2585
+ "loss": 0.2864,
2586
+ "step": 359
2587
+ },
2588
+ {
2589
+ "epoch": 0.9148665819567979,
2590
+ "grad_norm": 0.45762184262275696,
2591
+ "learning_rate": 1.9219101158518993e-06,
2592
+ "loss": 0.3329,
2593
+ "step": 360
2594
+ },
2595
+ {
2596
+ "epoch": 0.9174078780177891,
2597
+ "grad_norm": 0.4761408865451813,
2598
+ "learning_rate": 1.811196710228008e-06,
2599
+ "loss": 0.3612,
2600
+ "step": 361
2601
+ },
2602
+ {
2603
+ "epoch": 0.9199491740787802,
2604
+ "grad_norm": 0.44729211926460266,
2605
+ "learning_rate": 1.70370868554659e-06,
2606
+ "loss": 0.3913,
2607
+ "step": 362
2608
+ },
2609
+ {
2610
+ "epoch": 0.9224904701397713,
2611
+ "grad_norm": 0.44685786962509155,
2612
+ "learning_rate": 1.599453236213866e-06,
2613
+ "loss": 0.2781,
2614
+ "step": 363
2615
+ },
2616
+ {
2617
+ "epoch": 0.9250317662007624,
2618
+ "grad_norm": 0.4043272137641907,
2619
+ "learning_rate": 1.4984373402728014e-06,
2620
+ "loss": 0.3117,
2621
+ "step": 364
2622
+ },
2623
+ {
2624
+ "epoch": 0.9275730622617535,
2625
+ "grad_norm": 0.43179452419281006,
2626
+ "learning_rate": 1.4006677589360306e-06,
2627
+ "loss": 0.3209,
2628
+ "step": 365
2629
+ },
2630
+ {
2631
+ "epoch": 0.9301143583227446,
2632
+ "grad_norm": 0.448756605386734,
2633
+ "learning_rate": 1.3061510361333185e-06,
2634
+ "loss": 0.3976,
2635
+ "step": 366
2636
+ },
2637
+ {
2638
+ "epoch": 0.9326556543837357,
2639
+ "grad_norm": 0.4885236620903015,
2640
+ "learning_rate": 1.214893498073577e-06,
2641
+ "loss": 0.3973,
2642
+ "step": 367
2643
+ },
2644
+ {
2645
+ "epoch": 0.9351969504447268,
2646
+ "grad_norm": 0.413300096988678,
2647
+ "learning_rate": 1.1269012528214107e-06,
2648
+ "loss": 0.3155,
2649
+ "step": 368
2650
+ },
2651
+ {
2652
+ "epoch": 0.9377382465057179,
2653
+ "grad_norm": 0.45195144414901733,
2654
+ "learning_rate": 1.0421801898883143e-06,
2655
+ "loss": 0.4459,
2656
+ "step": 369
2657
+ },
2658
+ {
2659
+ "epoch": 0.940279542566709,
2660
+ "grad_norm": 0.4284112751483917,
2661
+ "learning_rate": 9.607359798384785e-07,
2662
+ "loss": 0.3713,
2663
+ "step": 370
2664
+ },
2665
+ {
2666
+ "epoch": 0.9428208386277002,
2667
+ "grad_norm": 0.39513155817985535,
2668
+ "learning_rate": 8.825740739092148e-07,
2669
+ "loss": 0.3318,
2670
+ "step": 371
2671
+ },
2672
+ {
2673
+ "epoch": 0.9453621346886912,
2674
+ "grad_norm": 0.46858373284339905,
2675
+ "learning_rate": 8.076997036461253e-07,
2676
+ "loss": 0.4858,
2677
+ "step": 372
2678
+ },
2679
+ {
2680
+ "epoch": 0.9479034307496823,
2681
+ "grad_norm": 0.44089990854263306,
2682
+ "learning_rate": 7.36117880552939e-07,
2683
+ "loss": 0.4386,
2684
+ "step": 373
2685
+ },
2686
+ {
2687
+ "epoch": 0.9504447268106735,
2688
+ "grad_norm": 0.5388498306274414,
2689
+ "learning_rate": 6.678333957560512e-07,
2690
+ "loss": 0.6738,
2691
+ "step": 374
2692
+ },
2693
+ {
2694
+ "epoch": 0.9529860228716646,
2695
+ "grad_norm": 0.4571278989315033,
2696
+ "learning_rate": 6.028508196838811e-07,
2697
+ "loss": 0.4427,
2698
+ "step": 375
2699
+ },
2700
+ {
2701
+ "epoch": 0.9555273189326556,
2702
+ "grad_norm": 0.4822606146335602,
2703
+ "learning_rate": 5.411745017609493e-07,
2704
+ "loss": 0.6009,
2705
+ "step": 376
2706
+ },
2707
+ {
2708
+ "epoch": 0.9580686149936467,
2709
+ "grad_norm": 0.48610785603523254,
2710
+ "learning_rate": 4.828085701167607e-07,
2711
+ "loss": 0.6353,
2712
+ "step": 377
2713
+ },
2714
+ {
2715
+ "epoch": 0.9606099110546379,
2716
+ "grad_norm": 0.5093012452125549,
2717
+ "learning_rate": 4.277569313094809e-07,
2718
+ "loss": 0.6796,
2719
+ "step": 378
2720
+ },
2721
+ {
2722
+ "epoch": 0.963151207115629,
2723
+ "grad_norm": 0.507256805896759,
2724
+ "learning_rate": 3.7602327006450167e-07,
2725
+ "loss": 0.6562,
2726
+ "step": 379
2727
+ },
2728
+ {
2729
+ "epoch": 0.96569250317662,
2730
+ "grad_norm": 0.5203272700309753,
2731
+ "learning_rate": 3.2761104902778173e-07,
2732
+ "loss": 0.5917,
2733
+ "step": 380
2734
+ },
2735
+ {
2736
+ "epoch": 0.9682337992376112,
2737
+ "grad_norm": 0.46381887793540955,
2738
+ "learning_rate": 2.825235085340938e-07,
2739
+ "loss": 0.4378,
2740
+ "step": 381
2741
+ },
2742
+ {
2743
+ "epoch": 0.9707750952986023,
2744
+ "grad_norm": 0.4541115164756775,
2745
+ "learning_rate": 2.407636663901591e-07,
2746
+ "loss": 0.387,
2747
+ "step": 382
2748
+ },
2749
+ {
2750
+ "epoch": 0.9733163913595934,
2751
+ "grad_norm": 0.4429299831390381,
2752
+ "learning_rate": 2.0233431767261447e-07,
2753
+ "loss": 0.3296,
2754
+ "step": 383
2755
+ },
2756
+ {
2757
+ "epoch": 0.9758576874205845,
2758
+ "grad_norm": 0.429360955953598,
2759
+ "learning_rate": 1.6723803454098408e-07,
2760
+ "loss": 0.3363,
2761
+ "step": 384
2762
+ },
2763
+ {
2764
+ "epoch": 0.9783989834815756,
2765
+ "grad_norm": 0.5687910914421082,
2766
+ "learning_rate": 1.3547716606548966e-07,
2767
+ "loss": 0.4413,
2768
+ "step": 385
2769
+ },
2770
+ {
2771
+ "epoch": 0.9809402795425667,
2772
+ "grad_norm": 0.46498122811317444,
2773
+ "learning_rate": 1.0705383806982606e-07,
2774
+ "loss": 0.2879,
2775
+ "step": 386
2776
+ },
2777
+ {
2778
+ "epoch": 0.9834815756035579,
2779
+ "grad_norm": 0.4391370117664337,
2780
+ "learning_rate": 8.196995298887511e-08,
2781
+ "loss": 0.2069,
2782
+ "step": 387
2783
+ },
2784
+ {
2785
+ "epoch": 0.9860228716645489,
2786
+ "grad_norm": 0.5458778142929077,
2787
+ "learning_rate": 6.022718974137975e-08,
2788
+ "loss": 0.291,
2789
+ "step": 388
2790
+ },
2791
+ {
2792
+ "epoch": 0.98856416772554,
2793
+ "grad_norm": 0.4504360854625702,
2794
+ "learning_rate": 4.182700361756164e-08,
2795
+ "loss": 0.1964,
2796
+ "step": 389
2797
+ },
2798
+ {
2799
+ "epoch": 0.9911054637865311,
2800
+ "grad_norm": 0.4797836244106293,
2801
+ "learning_rate": 2.6770626181715773e-08,
2802
+ "loss": 0.1966,
2803
+ "step": 390
2804
+ },
2805
+ {
2806
+ "epoch": 0.9936467598475223,
2807
+ "grad_norm": 0.6105788946151733,
2808
+ "learning_rate": 1.5059065189787503e-08,
2809
+ "loss": 0.273,
2810
+ "step": 391
2811
+ },
2812
+ {
2813
+ "epoch": 0.9961880559085133,
2814
+ "grad_norm": 0.631184995174408,
2815
+ "learning_rate": 6.693104521909854e-09,
2816
+ "loss": 0.2899,
2817
+ "step": 392
2818
+ },
2819
+ {
2820
+ "epoch": 0.9987293519695044,
2821
+ "grad_norm": 1.328522801399231,
2822
+ "learning_rate": 1.6733041299454855e-09,
2823
+ "loss": 0.6622,
2824
+ "step": 393
2825
+ },
2826
+ {
2827
+ "epoch": 1.0012706480304956,
2828
+ "grad_norm": 3.0589349269866943,
2829
+ "learning_rate": 0.0,
2830
+ "loss": 0.9702,
2831
+ "step": 394
2832
  }
2833
  ],
2834
  "logging_steps": 1,
 
2852
  "should_evaluate": false,
2853
  "should_log": false,
2854
  "should_save": true,
2855
+ "should_training_stop": true
2856
  },
2857
  "attributes": {}
2858
  }
2859
  },
2860
+ "total_flos": 9.943718615108813e+17,
2861
  "train_batch_size": 8,
2862
  "trial_name": null,
2863
  "trial_params": null