mikhail-panzo commited on
Commit
18540d8
1 Parent(s): 6c26f83

Training in progress, step 4000, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d2c0277f54c09c949fa6a8943edf7edac098878a0d43666f5fcb22403b14c145
3
  size 577789320
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8d3c8dd94f84edaa86e5bd551b7162baf24e06c95af4e529bb9d4594c6a6db5
3
  size 577789320
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0e5ea83ac97396889fe2821e60cc59e33e316d14ac1826fe80fb9efcd4c6f98b
3
  size 1155772233
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2048e83e96cb7813259491a8808e1d0ab1e6d1d06aed4036ff05048952b8dc6c
3
  size 1155772233
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a414c666e8625c7f4e23102be45d01b76de4812ff286110f0f9a0e1c67f33573
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3bf859859237e604ff95efafec03b923cfd86a352aded0ea1471a828fd47b6ef
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3b37e9ef30e383e795affd2915d5979e774d36e929b105a379fff9b722cf9675
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b861104f137d1fe8ca8f0827472a7b8a3a6723f1ff99340210bc3ae74cc04899
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.39595454931259155,
3
- "best_model_checkpoint": "mikhail-panzo/ceb_b128_le5_s4000/checkpoint-3000",
4
- "epoch": 274.5098039215686,
5
  "eval_steps": 500,
6
- "global_step": 3500,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -553,6 +553,84 @@
553
  "eval_samples_per_second": 28.036,
554
  "eval_steps_per_second": 3.582,
555
  "step": 3500
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
556
  }
557
  ],
558
  "logging_steps": 50,
@@ -567,12 +645,12 @@
567
  "should_evaluate": false,
568
  "should_log": false,
569
  "should_save": true,
570
- "should_training_stop": false
571
  },
572
  "attributes": {}
573
  }
574
  },
575
- "total_flos": 7.616303628785914e+16,
576
  "train_batch_size": 32,
577
  "trial_name": null,
578
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.39425286650657654,
3
+ "best_model_checkpoint": "mikhail-panzo/ceb_b128_le5_s4000/checkpoint-4000",
4
+ "epoch": 313.72549019607845,
5
  "eval_steps": 500,
6
+ "global_step": 4000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
553
  "eval_samples_per_second": 28.036,
554
  "eval_steps_per_second": 3.582,
555
  "step": 3500
556
+ },
557
+ {
558
+ "epoch": 278.4313725490196,
559
+ "grad_norm": 0.6087095737457275,
560
+ "learning_rate": 2.2550000000000004e-06,
561
+ "loss": 0.4122,
562
+ "step": 3550
563
+ },
564
+ {
565
+ "epoch": 282.3529411764706,
566
+ "grad_norm": 0.5597049593925476,
567
+ "learning_rate": 2.0050000000000003e-06,
568
+ "loss": 0.4111,
569
+ "step": 3600
570
+ },
571
+ {
572
+ "epoch": 286.27450980392155,
573
+ "grad_norm": 0.5411703586578369,
574
+ "learning_rate": 1.7550000000000001e-06,
575
+ "loss": 0.4069,
576
+ "step": 3650
577
+ },
578
+ {
579
+ "epoch": 290.19607843137254,
580
+ "grad_norm": 0.6042822599411011,
581
+ "learning_rate": 1.505e-06,
582
+ "loss": 0.4079,
583
+ "step": 3700
584
+ },
585
+ {
586
+ "epoch": 294.11764705882354,
587
+ "grad_norm": 0.6852837204933167,
588
+ "learning_rate": 1.255e-06,
589
+ "loss": 0.4068,
590
+ "step": 3750
591
+ },
592
+ {
593
+ "epoch": 298.03921568627453,
594
+ "grad_norm": 0.6229822039604187,
595
+ "learning_rate": 1.0050000000000001e-06,
596
+ "loss": 0.4112,
597
+ "step": 3800
598
+ },
599
+ {
600
+ "epoch": 301.96078431372547,
601
+ "grad_norm": 0.6330438256263733,
602
+ "learning_rate": 7.550000000000001e-07,
603
+ "loss": 0.4053,
604
+ "step": 3850
605
+ },
606
+ {
607
+ "epoch": 305.88235294117646,
608
+ "grad_norm": 0.5041052103042603,
609
+ "learning_rate": 5.05e-07,
610
+ "loss": 0.405,
611
+ "step": 3900
612
+ },
613
+ {
614
+ "epoch": 309.80392156862746,
615
+ "grad_norm": 0.6818642020225525,
616
+ "learning_rate": 2.55e-07,
617
+ "loss": 0.4095,
618
+ "step": 3950
619
+ },
620
+ {
621
+ "epoch": 313.72549019607845,
622
+ "grad_norm": 0.4621037542819977,
623
+ "learning_rate": 5e-09,
624
+ "loss": 0.4108,
625
+ "step": 4000
626
+ },
627
+ {
628
+ "epoch": 313.72549019607845,
629
+ "eval_loss": 0.39425286650657654,
630
+ "eval_runtime": 6.437,
631
+ "eval_samples_per_second": 27.963,
632
+ "eval_steps_per_second": 3.573,
633
+ "step": 4000
634
  }
635
  ],
636
  "logging_steps": 50,
 
645
  "should_evaluate": false,
646
  "should_log": false,
647
  "should_save": true,
648
+ "should_training_stop": true
649
  },
650
  "attributes": {}
651
  }
652
  },
653
+ "total_flos": 8.70355911863679e+16,
654
  "train_batch_size": 32,
655
  "trial_name": null,
656
  "trial_params": null