elsayedissa commited on
Commit
d171f03
1 Parent(s): 0ae67d4

Training in progress, step 20000

Browse files
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:181c2bd989506934f36609329ae3277eb855e8acf49b3c12e326fb79cb004eb3
3
  size 12347192855
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3070aeb72d29088489c0fb6e92c23b06f3de39671f0b9c078f18da734e95bf6b
3
  size 12347192855
last-checkpoint/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:15b5954cb47199f441cbbb70307c72621abf9248aa385660bfdb147a516624ef
3
  size 6173655480
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47bc5d383a893937307b6252269bc95121112ddd7c888bf951e25cc0f6233b96
3
  size 6173655480
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9460131d11a73df83270a4796c5192126900329b0b2274773520724725f4b12d
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4979e2334c039bb7332b1f1ca1ec119b85c014a960ba0dbab629d4dd618f0ad2
3
  size 14575
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f6a09c97ace5e5a49360efd6cac2da516ffa83c9ee08cb64155c59b3a316ab7a
3
  size 557
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e95ea4d51ce3dbab01e59ff8912c2f7044fb7bd804fa1afc7ea77264e8c7d84
3
  size 557
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ec3490e7ac28e19432d614c125578d2d66d232f9a51b472efd2d122fe9c6b708
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e664770f258aac914190f0cd016b820f86cc722eb7db2dbd9de5aff987606154
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "best_metric": 0.11536111854119403,
3
  "best_model_checkpoint": "/storage/elsayedissa/whisper-large-v2-spanish/checkpoint-1000",
4
- "epoch": 0.6595161234336492,
5
- "global_step": 19000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -4737,11 +4737,260 @@
4737
  "eval_steps_per_second": 0.062,
4738
  "eval_wer": 0.08945159383534276,
4739
  "step": 19000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4740
  }
4741
  ],
4742
  "max_steps": 25000,
4743
  "num_train_epochs": 1,
4744
- "total_flos": 6.454439903232e+20,
4745
  "trial_name": null,
4746
  "trial_params": null
4747
  }
 
1
  {
2
  "best_metric": 0.11536111854119403,
3
  "best_model_checkpoint": "/storage/elsayedissa/whisper-large-v2-spanish/checkpoint-1000",
4
+ "epoch": 0.6942274983512097,
5
+ "global_step": 20000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
4737
  "eval_steps_per_second": 0.062,
4738
  "eval_wer": 0.08945159383534276,
4739
  "step": 19000
4740
+ },
4741
+ {
4742
+ "epoch": 0.66,
4743
+ "learning_rate": 2.4432653061224493e-06,
4744
+ "loss": 0.1517,
4745
+ "step": 19025
4746
+ },
4747
+ {
4748
+ "epoch": 0.66,
4749
+ "learning_rate": 2.433061224489796e-06,
4750
+ "loss": 0.1327,
4751
+ "step": 19050
4752
+ },
4753
+ {
4754
+ "epoch": 0.66,
4755
+ "learning_rate": 2.422857142857143e-06,
4756
+ "loss": 0.1714,
4757
+ "step": 19075
4758
+ },
4759
+ {
4760
+ "epoch": 0.66,
4761
+ "learning_rate": 2.41265306122449e-06,
4762
+ "loss": 0.1268,
4763
+ "step": 19100
4764
+ },
4765
+ {
4766
+ "epoch": 0.66,
4767
+ "learning_rate": 2.4024489795918367e-06,
4768
+ "loss": 0.1597,
4769
+ "step": 19125
4770
+ },
4771
+ {
4772
+ "epoch": 0.66,
4773
+ "learning_rate": 2.3922448979591838e-06,
4774
+ "loss": 0.1326,
4775
+ "step": 19150
4776
+ },
4777
+ {
4778
+ "epoch": 0.67,
4779
+ "learning_rate": 2.382040816326531e-06,
4780
+ "loss": 0.1758,
4781
+ "step": 19175
4782
+ },
4783
+ {
4784
+ "epoch": 0.67,
4785
+ "learning_rate": 2.371836734693878e-06,
4786
+ "loss": 0.1347,
4787
+ "step": 19200
4788
+ },
4789
+ {
4790
+ "epoch": 0.67,
4791
+ "learning_rate": 2.3616326530612245e-06,
4792
+ "loss": 0.161,
4793
+ "step": 19225
4794
+ },
4795
+ {
4796
+ "epoch": 0.67,
4797
+ "learning_rate": 2.3514285714285716e-06,
4798
+ "loss": 0.1375,
4799
+ "step": 19250
4800
+ },
4801
+ {
4802
+ "epoch": 0.67,
4803
+ "learning_rate": 2.3412244897959187e-06,
4804
+ "loss": 0.1475,
4805
+ "step": 19275
4806
+ },
4807
+ {
4808
+ "epoch": 0.67,
4809
+ "learning_rate": 2.3310204081632653e-06,
4810
+ "loss": 0.122,
4811
+ "step": 19300
4812
+ },
4813
+ {
4814
+ "epoch": 0.67,
4815
+ "learning_rate": 2.3208163265306124e-06,
4816
+ "loss": 0.1556,
4817
+ "step": 19325
4818
+ },
4819
+ {
4820
+ "epoch": 0.67,
4821
+ "learning_rate": 2.3106122448979594e-06,
4822
+ "loss": 0.1204,
4823
+ "step": 19350
4824
+ },
4825
+ {
4826
+ "epoch": 0.67,
4827
+ "learning_rate": 2.3004081632653065e-06,
4828
+ "loss": 0.1576,
4829
+ "step": 19375
4830
+ },
4831
+ {
4832
+ "epoch": 0.67,
4833
+ "learning_rate": 2.290204081632653e-06,
4834
+ "loss": 0.1134,
4835
+ "step": 19400
4836
+ },
4837
+ {
4838
+ "epoch": 0.67,
4839
+ "learning_rate": 2.28e-06,
4840
+ "loss": 0.1533,
4841
+ "step": 19425
4842
+ },
4843
+ {
4844
+ "epoch": 0.68,
4845
+ "learning_rate": 2.2697959183673473e-06,
4846
+ "loss": 0.1423,
4847
+ "step": 19450
4848
+ },
4849
+ {
4850
+ "epoch": 0.68,
4851
+ "learning_rate": 2.2595918367346943e-06,
4852
+ "loss": 0.1725,
4853
+ "step": 19475
4854
+ },
4855
+ {
4856
+ "epoch": 0.68,
4857
+ "learning_rate": 2.249387755102041e-06,
4858
+ "loss": 0.1464,
4859
+ "step": 19500
4860
+ },
4861
+ {
4862
+ "epoch": 0.68,
4863
+ "learning_rate": 2.239183673469388e-06,
4864
+ "loss": 0.1739,
4865
+ "step": 19525
4866
+ },
4867
+ {
4868
+ "epoch": 0.68,
4869
+ "learning_rate": 2.228979591836735e-06,
4870
+ "loss": 0.1394,
4871
+ "step": 19550
4872
+ },
4873
+ {
4874
+ "epoch": 0.68,
4875
+ "learning_rate": 2.2187755102040817e-06,
4876
+ "loss": 0.1521,
4877
+ "step": 19575
4878
+ },
4879
+ {
4880
+ "epoch": 0.68,
4881
+ "learning_rate": 2.2085714285714288e-06,
4882
+ "loss": 0.1378,
4883
+ "step": 19600
4884
+ },
4885
+ {
4886
+ "epoch": 0.68,
4887
+ "learning_rate": 2.1983673469387754e-06,
4888
+ "loss": 0.1519,
4889
+ "step": 19625
4890
+ },
4891
+ {
4892
+ "epoch": 0.68,
4893
+ "learning_rate": 2.188163265306123e-06,
4894
+ "loss": 0.1261,
4895
+ "step": 19650
4896
+ },
4897
+ {
4898
+ "epoch": 0.68,
4899
+ "learning_rate": 2.1779591836734695e-06,
4900
+ "loss": 0.1455,
4901
+ "step": 19675
4902
+ },
4903
+ {
4904
+ "epoch": 0.68,
4905
+ "learning_rate": 2.1677551020408166e-06,
4906
+ "loss": 0.1268,
4907
+ "step": 19700
4908
+ },
4909
+ {
4910
+ "epoch": 0.68,
4911
+ "learning_rate": 2.1575510204081632e-06,
4912
+ "loss": 0.1652,
4913
+ "step": 19725
4914
+ },
4915
+ {
4916
+ "epoch": 0.69,
4917
+ "learning_rate": 2.1473469387755103e-06,
4918
+ "loss": 0.149,
4919
+ "step": 19750
4920
+ },
4921
+ {
4922
+ "epoch": 0.69,
4923
+ "learning_rate": 2.1371428571428574e-06,
4924
+ "loss": 0.148,
4925
+ "step": 19775
4926
+ },
4927
+ {
4928
+ "epoch": 0.69,
4929
+ "learning_rate": 2.126938775510204e-06,
4930
+ "loss": 0.1455,
4931
+ "step": 19800
4932
+ },
4933
+ {
4934
+ "epoch": 0.69,
4935
+ "learning_rate": 2.116734693877551e-06,
4936
+ "loss": 0.148,
4937
+ "step": 19825
4938
+ },
4939
+ {
4940
+ "epoch": 0.69,
4941
+ "learning_rate": 2.106530612244898e-06,
4942
+ "loss": 0.1317,
4943
+ "step": 19850
4944
+ },
4945
+ {
4946
+ "epoch": 0.69,
4947
+ "learning_rate": 2.096326530612245e-06,
4948
+ "loss": 0.1464,
4949
+ "step": 19875
4950
+ },
4951
+ {
4952
+ "epoch": 0.69,
4953
+ "learning_rate": 2.086122448979592e-06,
4954
+ "loss": 0.1339,
4955
+ "step": 19900
4956
+ },
4957
+ {
4958
+ "epoch": 0.69,
4959
+ "learning_rate": 2.075918367346939e-06,
4960
+ "loss": 0.1638,
4961
+ "step": 19925
4962
+ },
4963
+ {
4964
+ "epoch": 0.69,
4965
+ "learning_rate": 2.065714285714286e-06,
4966
+ "loss": 0.1253,
4967
+ "step": 19950
4968
+ },
4969
+ {
4970
+ "epoch": 0.69,
4971
+ "learning_rate": 2.0555102040816326e-06,
4972
+ "loss": 0.1537,
4973
+ "step": 19975
4974
+ },
4975
+ {
4976
+ "epoch": 0.69,
4977
+ "learning_rate": 2.0453061224489797e-06,
4978
+ "loss": 0.1255,
4979
+ "step": 20000
4980
+ },
4981
+ {
4982
+ "epoch": 0.69,
4983
+ "eval_loss": 0.15466098487377167,
4984
+ "eval_runtime": 31000.8642,
4985
+ "eval_samples_per_second": 1.001,
4986
+ "eval_steps_per_second": 0.063,
4987
+ "eval_wer": 0.08736786835874422,
4988
+ "step": 20000
4989
  }
4990
  ],
4991
  "max_steps": 25000,
4992
  "num_train_epochs": 1,
4993
+ "total_flos": 6.79414726656e+20,
4994
  "trial_name": null,
4995
  "trial_params": null
4996
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:15b5954cb47199f441cbbb70307c72621abf9248aa385660bfdb147a516624ef
3
  size 6173655480
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47bc5d383a893937307b6252269bc95121112ddd7c888bf951e25cc0f6233b96
3
  size 6173655480
runs/Dec26_19-57-19_gpu07.cyverse.org/events.out.tfevents.1672109970.gpu07.cyverse.org.126369.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6547ad8d8b1ed3f418b525a96f2b38ff44683cdf8d77997c10dc189dea1b0ef9
3
- size 130084
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4222f5599f934e25008ca9c74695648d0516086fca35c66323f38f875ddff30c
3
+ size 136808