k4black commited on
Commit
252afb8
1 Parent(s): 7e2c525

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 sha256:14d08558893cdb957334f570153c8e987086ccedf461b37365125b3cd89d8169
3
  size 484085807
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c891ef73eb7b4b9ce7d9b424a2b4aaf18100da53e8775136346d76b30d1eaadb
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:becc4906e6eb2ea40cf0b8abbad2869ba0453d40eb00a388f263c6fe8164098e
3
  size 242031355
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:804590f5c6ea5bc60bd37a9016fea82f965fac4051fdf57962fad5d4c09496ec
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:d8bb00c0bef438a1252a2939b2596e4b479c5f2b75f69cff629ff81a63431642
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de3183b725b8b480bb97ce4491b4292c56ba07a66cd71423476a3e747351f9cb
3
  size 14503
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:29315e751a62a403f2ae38c6fa582c9634b735d9d09b10e1b31f449b4847a2ce
3
  size 559
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13a70eb1c7ed1b7b50ca88a0d58b195bbbd43ac81f49980750c437ba42b82ae9
3
  size 559
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0c6f8702a46479061b87b7d6fe7f45509b897edb9151f0408a4311d6a739d96c
3
  size 623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50e2751236681cd19d90f485b1e207baf831303491a01cb9b2e5fcf8c9c7e136
3
  size 623
last-checkpoint/trainer_state.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "best_metric": 0.6715950965881348,
3
  "best_model_checkpoint": "/home2/s5431786/jb-internship/results/t5-small-CodeXGLUE-CONCODE-faster/checkpoint-19500",
4
- "epoch": 6.24,
5
- "global_step": 19500,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -747,11 +747,30 @@
747
  "eval_samples_per_second": 76.555,
748
  "eval_steps_per_second": 2.411,
749
  "step": 19500
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
750
  }
751
  ],
752
  "max_steps": 62500,
753
  "num_train_epochs": 20,
754
- "total_flos": 8.15475633118249e+16,
755
  "trial_name": null,
756
  "trial_params": null
757
  }
 
1
  {
2
  "best_metric": 0.6715950965881348,
3
  "best_model_checkpoint": "/home2/s5431786/jb-internship/results/t5-small-CodeXGLUE-CONCODE-faster/checkpoint-19500",
4
+ "epoch": 6.4,
5
+ "global_step": 20000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
747
  "eval_samples_per_second": 76.555,
748
  "eval_steps_per_second": 2.411,
749
  "step": 19500
750
+ },
751
+ {
752
+ "epoch": 6.4,
753
+ "learning_rate": 0.00035795368421052634,
754
+ "loss": 0.4584,
755
+ "step": 20000
756
+ },
757
+ {
758
+ "epoch": 6.4,
759
+ "eval_bleu": 0.06754458066884086,
760
+ "eval_exact_match": 0.106,
761
+ "eval_loss": 0.6722220182418823,
762
+ "eval_rouge1": 0.5120041534722938,
763
+ "eval_rouge2": 0.35712607384056955,
764
+ "eval_rougeL": 0.4993047634971517,
765
+ "eval_runtime": 25.9887,
766
+ "eval_samples_per_second": 76.957,
767
+ "eval_steps_per_second": 2.424,
768
+ "step": 20000
769
  }
770
  ],
771
  "max_steps": 62500,
772
  "num_train_epochs": 20,
773
+ "total_flos": 8.36405988950016e+16,
774
  "trial_name": null,
775
  "trial_params": null
776
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:becc4906e6eb2ea40cf0b8abbad2869ba0453d40eb00a388f263c6fe8164098e
3
  size 242031355
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:804590f5c6ea5bc60bd37a9016fea82f965fac4051fdf57962fad5d4c09496ec
3
  size 242031355