Silemo commited on
Commit
e85ed55
·
1 Parent(s): a0d8fd5

Training in progress, step 2900

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5002534ec028fd851fb4ded8fa6870b5e88a87b3aea83489064e50c2d130c705
3
  size 966995080
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc9ce79fc599740aef87f7fd48706228015ab07b2a1dfd751d72c6184f855c03
3
  size 966995080
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e2ebf35cde40a2b2b8bd1babda4caa0c0a3c31716b985086a7f3492df8e73146
3
  size 1925064044
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d306912bc344aaf32285eaf9f48c11bfb51cf53853d6ee359fddf97240bd0bb9
3
  size 1925064044
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:714c497832efbd30b453ea1dc41b88588aa1ef3ef61cc437c7721d0a697f8351
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bdbc32589e7c655d36a5fb4597ce0c5aa1b6a41b9f31868102fdf367046c16aa
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3922750f8285a08036594458e370c6bf581fd29e29990b555381b09978530df4
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:709fa179bb7fc9a25ddcbc282cb67b6963af0127c69eb4336b37c5b7c5aba9e9
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": 70.1955074875208,
3
  "best_model_checkpoint": "./whisper-it/checkpoint-300",
4
- "epoch": 5.34351145038168,
5
  "eval_steps": 100,
6
- "global_step": 2800,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -865,72 +865,6 @@
865
  "eval_steps_per_second": 0.103,
866
  "eval_wer": 181.14254021075985,
867
  "step": 2600
868
- },
869
- {
870
- "epoch": 5.01,
871
- "learning_rate": 3.945714285714286e-06,
872
- "loss": 0.0156,
873
- "step": 2625
874
- },
875
- {
876
- "epoch": 5.06,
877
- "learning_rate": 3.874285714285715e-06,
878
- "loss": 0.0086,
879
- "step": 2650
880
- },
881
- {
882
- "epoch": 5.1,
883
- "learning_rate": 3.802857142857143e-06,
884
- "loss": 0.0075,
885
- "step": 2675
886
- },
887
- {
888
- "epoch": 5.15,
889
- "learning_rate": 3.731428571428572e-06,
890
- "loss": 0.009,
891
- "step": 2700
892
- },
893
- {
894
- "epoch": 5.15,
895
- "eval_loss": 0.43247538805007935,
896
- "eval_runtime": 1622.3539,
897
- "eval_samples_per_second": 0.925,
898
- "eval_steps_per_second": 0.116,
899
- "eval_wer": 161.67498613422075,
900
- "step": 2700
901
- },
902
- {
903
- "epoch": 5.2,
904
- "learning_rate": 3.66e-06,
905
- "loss": 0.0074,
906
- "step": 2725
907
- },
908
- {
909
- "epoch": 5.25,
910
- "learning_rate": 3.588571428571429e-06,
911
- "loss": 0.0096,
912
- "step": 2750
913
- },
914
- {
915
- "epoch": 5.3,
916
- "learning_rate": 3.5171428571428573e-06,
917
- "loss": 0.0098,
918
- "step": 2775
919
- },
920
- {
921
- "epoch": 5.34,
922
- "learning_rate": 3.4457142857142863e-06,
923
- "loss": 0.0069,
924
- "step": 2800
925
- },
926
- {
927
- "epoch": 5.34,
928
- "eval_loss": 0.43616336584091187,
929
- "eval_runtime": 1644.4427,
930
- "eval_samples_per_second": 0.912,
931
- "eval_steps_per_second": 0.114,
932
- "eval_wer": 161.19661674986133,
933
- "step": 2800
934
  }
935
  ],
936
  "logging_steps": 25,
@@ -938,7 +872,7 @@
938
  "num_input_tokens_seen": 0,
939
  "num_train_epochs": 8,
940
  "save_steps": 100,
941
- "total_flos": 2.58471513796608e+19,
942
  "trial_name": null,
943
  "trial_params": null
944
  }
 
1
  {
2
  "best_metric": 70.1955074875208,
3
  "best_model_checkpoint": "./whisper-it/checkpoint-300",
4
+ "epoch": 4.961832061068702,
5
  "eval_steps": 100,
6
+ "global_step": 2600,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
865
  "eval_steps_per_second": 0.103,
866
  "eval_wer": 181.14254021075985,
867
  "step": 2600
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
868
  }
869
  ],
870
  "logging_steps": 25,
 
872
  "num_input_tokens_seen": 0,
873
  "num_train_epochs": 8,
874
  "save_steps": 100,
875
+ "total_flos": 2.400222491541504e+19,
876
  "trial_name": null,
877
  "trial_params": null
878
  }
last-checkpoint/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e2c92dac35d16dc814e0a1581e1901c1f2948813ba744cab88f1ca1434e0d291
3
  size 4856
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96eac9b215a976aa2dd9548a4525c1b8963c1f6f7769df3b71271d00769da268
3
  size 4856
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5002534ec028fd851fb4ded8fa6870b5e88a87b3aea83489064e50c2d130c705
3
  size 966995080
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4322cb52e7375952b1b7c62f67285f280a31e123ef3ec661fb690ab98ec4501d
3
  size 966995080
runs/Dec06_11-00-30_434437f2320b/events.out.tfevents.1701860453.434437f2320b.298.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:49bfeade977e6cf0897b542b21b891e17ad33a1f61b6eecb801ff6478469a75f
3
- size 7065
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0da207cb9892cfaa4ee5e358be4b072f8ded1d547815263b874d31dbb9860a68
3
+ size 8011