Sara Price commited on
Commit
556aa3e
·
verified ·
1 Parent(s): 20837f1

Training in progress, step 2600, checkpoint

Browse files
last-checkpoint/model-00001-of-00011.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:51cc469c3cdd73310b70cb5335285cb5d25753d6a53331241f83bb701b28baf4
3
  size 4881575536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97a7f9330a411d9eea049c124572449425cb8d2e8f9584b3ba5ab0dcc8e24f84
3
  size 4881575536
last-checkpoint/model-00002-of-00011.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8e50c38ca659a6f29ad0b6f61962a9e6511911abc9b9c4bebbbc80c0fb27a754
3
  size 4970418112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c13809bb03edcfde9f11286b1df34c29089f656e625dae1a007fa0e8f1ce53c
3
  size 4970418112
last-checkpoint/model-00003-of-00011.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dfa95cf656ffd7e698cd272aae04e79311e548f03697c9b57b0602bbc3660115
3
  size 4970418120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a68468f3510f6803eec8c45bdc6a1a51f3d2c42cfc605244fd920c0e641bb4c
3
  size 4970418120
last-checkpoint/model-00004-of-00011.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3286a5ab669503376edb32c9535195d3094732ae4c20cb47bcbce5b1b15f415d
3
  size 4970418144
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ee24162f173045ff44fe5cb7b7580d41eab1e1dc2325c8720529b89d12ed4e7
3
  size 4970418144
last-checkpoint/model-00005-of-00011.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:032c09fb1ec6bffe412c9aebc9111486ee498dc843f5f20cc63cd3b2e3b5302c
3
  size 4970418144
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09f1abdbe206dadffe024a1fbb8cde5ec575a381bf278bab59c7a871f1736ccb
3
  size 4970418144
last-checkpoint/model-00006-of-00011.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a9be27ef8d01cc8fe2881667631eb5934c94e3a4fa0ce4c44030ec50701ea0e2
3
  size 4792119040
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e9b48701d1be99bd5dccb575527b7dcae4044d8cc065c61d810ab448eb54348
3
  size 4792119040
last-checkpoint/model-00007-of-00011.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:59f77461cb9ed9eefbb649ae077f19418b82d44c00b692047e5bc19561254f88
3
  size 4792160232
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d71b77574e7cc8cb5e4111620a6c3db9362411898410fa8a0587a8def96680d
3
  size 4792160232
last-checkpoint/model-00008-of-00011.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1a52cae96c7591f2d4d027f9020ea0e592fcc93c339cd0fccaf772de7076a10e
3
  size 4792160224
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c30f2362d3a458ce3fc256de17dc6d6dfbc169989c057767c3d0ae7726c20337
3
  size 4792160224
last-checkpoint/model-00009-of-00011.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c9eb9feff8ae6eb4a11c090a0b2db11f2afceefbdc8dad888aa40e69ca924f1f
3
  size 4970418144
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34d26ef894cd67f939f641c1ac3a77fe93cee256855d659df34ed76fe805246d
3
  size 4970418144
last-checkpoint/model-00010-of-00011.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:24b5f75b5d8f86f4f945b18dbf7fba6be38b663d12132a214e02f09b73b33751
3
  size 4970418144
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7ac4b293c1ed1841de17782a445ce49b754f6883e118f5f023b0bd2dd09907c
3
  size 4970418144
last-checkpoint/model-00011-of-00011.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b0fe3cf310ec941b0dc2e56c36331d6551ceb280d0d1b06a0066e5119f48b365
3
  size 2983630864
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e068d75ab0a1baac95b38fb947b5c92ea8bf5bfc1a5d08ac513ee25dd7aa48a4
3
  size 2983630864
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 2.2,
5
  "eval_steps": 50,
6
- "global_step": 2200,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -667,6 +667,126 @@
667
  "eval_samples_per_second": 29.114,
668
  "eval_steps_per_second": 1.493,
669
  "step": 2200
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
670
  }
671
  ],
672
  "logging_steps": 50,
@@ -674,7 +794,7 @@
674
  "num_input_tokens_seen": 0,
675
  "num_train_epochs": 7,
676
  "save_steps": 200,
677
- "total_flos": 2.023561963241472e+17,
678
  "train_batch_size": 1,
679
  "trial_name": null,
680
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 2.6,
5
  "eval_steps": 50,
6
+ "global_step": 2600,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
667
  "eval_samples_per_second": 29.114,
668
  "eval_steps_per_second": 1.493,
669
  "step": 2200
670
+ },
671
+ {
672
+ "epoch": 2.25,
673
+ "grad_norm": 1.252875804901123,
674
+ "learning_rate": 1.7158668492597186e-05,
675
+ "loss": 0.2262,
676
+ "step": 2250
677
+ },
678
+ {
679
+ "epoch": 2.25,
680
+ "eval_loss": 0.9039773941040039,
681
+ "eval_runtime": 5.3439,
682
+ "eval_samples_per_second": 29.192,
683
+ "eval_steps_per_second": 1.497,
684
+ "step": 2250
685
+ },
686
+ {
687
+ "epoch": 2.3,
688
+ "grad_norm": 1.2293896675109863,
689
+ "learning_rate": 1.698236818086073e-05,
690
+ "loss": 0.2401,
691
+ "step": 2300
692
+ },
693
+ {
694
+ "epoch": 2.3,
695
+ "eval_loss": 0.9025784134864807,
696
+ "eval_runtime": 5.3641,
697
+ "eval_samples_per_second": 29.082,
698
+ "eval_steps_per_second": 1.491,
699
+ "step": 2300
700
+ },
701
+ {
702
+ "epoch": 2.35,
703
+ "grad_norm": 1.5813263654708862,
704
+ "learning_rate": 1.6801727377709195e-05,
705
+ "loss": 0.2397,
706
+ "step": 2350
707
+ },
708
+ {
709
+ "epoch": 2.35,
710
+ "eval_loss": 0.9166079759597778,
711
+ "eval_runtime": 5.3804,
712
+ "eval_samples_per_second": 28.994,
713
+ "eval_steps_per_second": 1.487,
714
+ "step": 2350
715
+ },
716
+ {
717
+ "epoch": 2.4,
718
+ "grad_norm": 1.4593902826309204,
719
+ "learning_rate": 1.6616858375968596e-05,
720
+ "loss": 0.2341,
721
+ "step": 2400
722
+ },
723
+ {
724
+ "epoch": 2.4,
725
+ "eval_loss": 0.9137348532676697,
726
+ "eval_runtime": 5.3708,
727
+ "eval_samples_per_second": 29.046,
728
+ "eval_steps_per_second": 1.49,
729
+ "step": 2400
730
+ },
731
+ {
732
+ "epoch": 2.45,
733
+ "grad_norm": 1.8817037343978882,
734
+ "learning_rate": 1.6427876096865394e-05,
735
+ "loss": 0.2434,
736
+ "step": 2450
737
+ },
738
+ {
739
+ "epoch": 2.45,
740
+ "eval_loss": 0.9133093357086182,
741
+ "eval_runtime": 5.353,
742
+ "eval_samples_per_second": 29.143,
743
+ "eval_steps_per_second": 1.494,
744
+ "step": 2450
745
+ },
746
+ {
747
+ "epoch": 2.5,
748
+ "grad_norm": 1.1660922765731812,
749
+ "learning_rate": 1.6234898018587336e-05,
750
+ "loss": 0.238,
751
+ "step": 2500
752
+ },
753
+ {
754
+ "epoch": 2.5,
755
+ "eval_loss": 0.9203407168388367,
756
+ "eval_runtime": 5.3478,
757
+ "eval_samples_per_second": 29.171,
758
+ "eval_steps_per_second": 1.496,
759
+ "step": 2500
760
+ },
761
+ {
762
+ "epoch": 2.55,
763
+ "grad_norm": 1.1189944744110107,
764
+ "learning_rate": 1.6038044103254775e-05,
765
+ "loss": 0.2555,
766
+ "step": 2550
767
+ },
768
+ {
769
+ "epoch": 2.55,
770
+ "eval_loss": 0.9188438057899475,
771
+ "eval_runtime": 5.3606,
772
+ "eval_samples_per_second": 29.101,
773
+ "eval_steps_per_second": 1.492,
774
+ "step": 2550
775
+ },
776
+ {
777
+ "epoch": 2.6,
778
+ "grad_norm": 1.388344407081604,
779
+ "learning_rate": 1.5837436722347902e-05,
780
+ "loss": 0.245,
781
+ "step": 2600
782
+ },
783
+ {
784
+ "epoch": 2.6,
785
+ "eval_loss": 0.9264757037162781,
786
+ "eval_runtime": 5.3585,
787
+ "eval_samples_per_second": 29.112,
788
+ "eval_steps_per_second": 1.493,
789
+ "step": 2600
790
  }
791
  ],
792
  "logging_steps": 50,
 
794
  "num_input_tokens_seen": 0,
795
  "num_train_epochs": 7,
796
  "save_steps": 200,
797
+ "total_flos": 2.3925523075825664e+17,
798
  "train_batch_size": 1,
799
  "trial_name": null,
800
  "trial_params": null