k4black commited on
Commit
3ce0154
1 Parent(s): 874a6aa

Training in progress, step 11000

Browse files
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1a404583ef80bf3b8c4a510d27f887ac8e29f3411663bf49b4ab7232ce9a412a
3
  size 484083951
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1d2011f8a988b4295479fe59685793ec417f75e9fe48174e9529bb4ded9a4c9
3
  size 484083951
last-checkpoint/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8cf45d731900f7f9e07949ef1dfe708b522e158b7cfbb371287593175d5efcd1
3
  size 242031355
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35b18468fc7a560406e48b2782c8463f1e1bafdd5807c3273d1d978aa2cdbfe3
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:a00f35a9c679472118eaa7dabfb186e79026b1432f53b64dfdf5c3e63bbd9480
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b028c10aa234f1febef8c35fe5b69a4c34d42a3bbdcc86487f3b97cf260ff48
3
  size 14503
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1c3bf52f39b4d9c5882704c54922db0ba799f5f2afb01fd986c87b5fde9ed4b4
3
  size 559
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b76836b28d82cff01694abcecb0d7523e4de528d13bdfecffb51521d243efc33
3
  size 559
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bfb31fa41ab4193878df5129dfbe7781af2d43ca089016d1833b7ff3a9dc1ee5
3
  size 623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:218ffac51e0c82315d80294d8da387b31aaa2ef6940016f0f3f318d27f01e3a5
3
  size 623
last-checkpoint/trainer_state.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "best_metric": 0.715421736240387,
3
- "best_model_checkpoint": "/home2/s5431786/jb-internship/results/t5-small-CodeXGLUE-CONCODE-faster/checkpoint-10500",
4
- "epoch": 3.36,
5
- "global_step": 10500,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -405,11 +405,30 @@
405
  "eval_samples_per_second": 56.415,
406
  "eval_steps_per_second": 1.777,
407
  "step": 10500
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
408
  }
409
  ],
410
  "max_steps": 62500,
411
  "num_train_epochs": 20,
412
- "total_flos": 4.393192338122342e+16,
413
  "trial_name": null,
414
  "trial_params": null
415
  }
 
1
  {
2
+ "best_metric": 0.7109146118164062,
3
+ "best_model_checkpoint": "/home2/s5431786/jb-internship/results/t5-small-CodeXGLUE-CONCODE-faster/checkpoint-11000",
4
+ "epoch": 3.52,
5
+ "global_step": 11000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
405
  "eval_samples_per_second": 56.415,
406
  "eval_steps_per_second": 1.777,
407
  "step": 10500
408
+ },
409
+ {
410
+ "epoch": 3.52,
411
+ "learning_rate": 0.00043370947368421057,
412
+ "loss": 0.5712,
413
+ "step": 11000
414
+ },
415
+ {
416
+ "epoch": 3.52,
417
+ "eval_bleu": 0.06578551089272082,
418
+ "eval_exact_match": 0.102,
419
+ "eval_loss": 0.7109146118164062,
420
+ "eval_rouge1": 0.5061889557930622,
421
+ "eval_rouge2": 0.34828839953790597,
422
+ "eval_rougeL": 0.4934676685845075,
423
+ "eval_runtime": 35.6977,
424
+ "eval_samples_per_second": 56.026,
425
+ "eval_steps_per_second": 1.765,
426
+ "step": 11000
427
  }
428
  ],
429
  "max_steps": 62500,
430
  "num_train_epochs": 20,
431
+ "total_flos": 4.603039801304678e+16,
432
  "trial_name": null,
433
  "trial_params": null
434
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8cf45d731900f7f9e07949ef1dfe708b522e158b7cfbb371287593175d5efcd1
3
  size 242031355
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35b18468fc7a560406e48b2782c8463f1e1bafdd5807c3273d1d978aa2cdbfe3
3
  size 242031355