k4black commited on
Commit
3335ffb
1 Parent(s): 506ca7d

Training in progress, step 23000

Browse files
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5b7e7c078a39a689939c037d72235890bf6584bb928d9e785916172b4e820915
3
  size 484085807
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59cf842aa62a04e6a64174347236dcfa2cb8f057894aee22af49777aefd11630
3
  size 484085807
last-checkpoint/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9b361896c6802b68ef5c776b2fe5bb5136a17df509fd1b4edd8e0dd8ca078872
3
  size 242031355
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b86f00b47dfc770eb9d65f03844b7c31c8bfb39bb680ff8fc43b325fea097fee
3
  size 242031355
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fe6804e8b27ef59599074328bde187701e649cea127bf1422ab7db7c638f4ffe
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:edb8a46ae691d815a589cfaf7942e6d1777507ff2e6817727b44ad9cb963543e
3
  size 14503
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9556b71e3b9b23ca382a0e542ff1e829397dee87fcc10ddaf64025aba131f238
3
  size 559
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:691923a4a87c660df20f265bf1dae078d92003f0028775818e1a0abb49477388
3
  size 559
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c86fc1e8e7ea6191ee0b61ef0d2d0c43d8b17b6e883db57fd0037b8796a41551
3
  size 623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:740731e0038abdda415682cdde2b15a11dd6d693c7306742d58a3232dac5dc37
3
  size 623
last-checkpoint/trainer_state.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "best_metric": 0.665252685546875,
3
  "best_model_checkpoint": "/home2/s5431786/jb-internship/results/t5-small-CodeXGLUE-CONCODE-faster/checkpoint-22500",
4
- "epoch": 7.2,
5
- "global_step": 22500,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -861,11 +861,30 @@
861
  "eval_samples_per_second": 76.863,
862
  "eval_steps_per_second": 2.421,
863
  "step": 22500
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
864
  }
865
  ],
866
  "max_steps": 62500,
867
  "num_train_epochs": 20,
868
- "total_flos": 9.40622390451241e+16,
869
  "trial_name": null,
870
  "trial_params": null
871
  }
 
1
  {
2
  "best_metric": 0.665252685546875,
3
  "best_model_checkpoint": "/home2/s5431786/jb-internship/results/t5-small-CodeXGLUE-CONCODE-faster/checkpoint-22500",
4
+ "epoch": 7.36,
5
+ "global_step": 23000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
861
  "eval_samples_per_second": 76.863,
862
  "eval_steps_per_second": 2.421,
863
  "step": 22500
864
+ },
865
+ {
866
+ "epoch": 7.36,
867
+ "learning_rate": 0.00033269894736842105,
868
+ "loss": 0.4374,
869
+ "step": 23000
870
+ },
871
+ {
872
+ "epoch": 7.36,
873
+ "eval_bleu": 0.06757017098690109,
874
+ "eval_exact_match": 0.1,
875
+ "eval_loss": 0.6658646464347839,
876
+ "eval_rouge1": 0.512652953906156,
877
+ "eval_rouge2": 0.3561654225240507,
878
+ "eval_rougeL": 0.49934790688943353,
879
+ "eval_runtime": 26.0622,
880
+ "eval_samples_per_second": 76.74,
881
+ "eval_steps_per_second": 2.417,
882
+ "step": 23000
883
  }
884
  ],
885
  "max_steps": 62500,
886
  "num_train_epochs": 20,
887
+ "total_flos": 9.614488714503782e+16,
888
  "trial_name": null,
889
  "trial_params": null
890
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9b361896c6802b68ef5c776b2fe5bb5136a17df509fd1b4edd8e0dd8ca078872
3
  size 242031355
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b86f00b47dfc770eb9d65f03844b7c31c8bfb39bb680ff8fc43b325fea097fee
3
  size 242031355