k4black commited on
Commit
4628343
1 Parent(s): 2502648

Training in progress, step 16500

Browse files
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a3713544e5b81cae5d719576a8f2ecbeb568ea18dcfdef0fe5982979e86a1e4a
3
  size 484085807
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3296ef9e438d4f108d5221b483fcdd01ec7760f7f53d1541834330a966f9669
3
  size 484085807
last-checkpoint/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:176eafcc193382dd0315863e9cd15efa76a3092e841f24f0965eea03578f4772
3
  size 242031355
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79d1dc3785564d67cad207bee63a0e262be0ce37c65287ab9a2d51f843244dbd
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:dcaeed6fed4ac2624b7d84bb713f09166cc2962454aa22cef51e0ffa98cfab8c
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16d71d66f39251991a111a002cd24f571e435e2d0cd0feb4f970a46f9cb88a9d
3
  size 14503
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:08d3ec0fc505eb43f1aea57486dd352332ebfcc33c0609c58410bbc294cdec9c
3
  size 559
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c71f9cdde9cb909c49a3ba8fa09b4fc9040050372bc5bf12288a2523d5249c4b
3
  size 559
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6cef149238801f2d97c9cc2f75fb3e5b240d80021004237db94e783eb783ace6
3
  size 623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80e879eb06fc98d4ae5e9ded671fa747d3e8e2870f5e9ad0cc2d3781f614b580
3
  size 623
last-checkpoint/trainer_state.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "best_metric": 0.6874147653579712,
3
- "best_model_checkpoint": "/home2/s5431786/jb-internship/results/t5-small-CodeXGLUE-CONCODE-faster/checkpoint-15000",
4
- "epoch": 5.12,
5
- "global_step": 16000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -614,11 +614,30 @@
614
  "eval_samples_per_second": 76.333,
615
  "eval_steps_per_second": 2.405,
616
  "step": 16000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
617
  }
618
  ],
619
  "max_steps": 62500,
620
  "num_train_epochs": 20,
621
- "total_flos": 6.694761723120845e+16,
622
  "trial_name": null,
623
  "trial_params": null
624
  }
 
1
  {
2
+ "best_metric": 0.6785948276519775,
3
+ "best_model_checkpoint": "/home2/s5431786/jb-internship/results/t5-small-CodeXGLUE-CONCODE-faster/checkpoint-16500",
4
+ "epoch": 5.28,
5
+ "global_step": 16500,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
614
  "eval_samples_per_second": 76.333,
615
  "eval_steps_per_second": 2.405,
616
  "step": 16000
617
+ },
618
+ {
619
+ "epoch": 5.28,
620
+ "learning_rate": 0.00038742736842105265,
621
+ "loss": 0.4922,
622
+ "step": 16500
623
+ },
624
+ {
625
+ "epoch": 5.28,
626
+ "eval_bleu": 0.06698301903860669,
627
+ "eval_exact_match": 0.1045,
628
+ "eval_loss": 0.6785948276519775,
629
+ "eval_rouge1": 0.5117392179713256,
630
+ "eval_rouge2": 0.35491013960107753,
631
+ "eval_rougeL": 0.49895018657411827,
632
+ "eval_runtime": 25.8834,
633
+ "eval_samples_per_second": 77.269,
634
+ "eval_steps_per_second": 2.434,
635
+ "step": 16500
636
  }
637
  ],
638
  "max_steps": 62500,
639
  "num_train_epochs": 20,
640
+ "total_flos": 6.904315663771238e+16,
641
  "trial_name": null,
642
  "trial_params": null
643
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:176eafcc193382dd0315863e9cd15efa76a3092e841f24f0965eea03578f4772
3
  size 242031355
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79d1dc3785564d67cad207bee63a0e262be0ce37c65287ab9a2d51f843244dbd
3
  size 242031355