k4black commited on
Commit
e44f61d
1 Parent(s): 94fb68a

Training in progress, step 10000

Browse files
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:afdfa291a35bc3af586130d697da3a582e4cf4734b572895bbded99ff4f1dae5
3
  size 484059375
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e755927f5aff6de53ce7d0845fb552ff8e081d174472062a533921071cc4377a
3
  size 484059375
last-checkpoint/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3b20b57fc6bbefdfa083820d1d647ee721359543b0768cddfd13495869607e80
3
  size 242019067
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05153b9eed5e8ca31027cb1dccc8505991efe2bf53be4273caa9b830746ce53c
3
  size 242019067
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:09f47bc98dc4f62c2fd48c3afb87ab1e1ff7e9e74ea9826c279226cb65e0b895
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01e0381b8deed3ccdd287ffb26585b88f2e2685ed9567bb70fb45a9d50fec1fd
3
  size 14503
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:561b13d74f0e281d3fd2bbfa2465139723244e589ef11a731f9661386253b9bd
3
  size 559
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9bb50a0bfb4b145543d901dac464b84089ecb37e1ebeeaac70d9d155c894815c
3
  size 559
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:66c5d2ad47a3e0b487680a2b1c4313865a17bc115d68f5b0e29f37e2a76705f2
3
  size 623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:730c7b15c7cda80c4399711b4aae96a8dba6ab09ac8e062067c83fb1739fd147
3
  size 623
last-checkpoint/trainer_state.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "best_metric": 0.7636184096336365,
3
  "best_model_checkpoint": "/home2/s5431786/jb-internship/results/Salesforce-codet5-small-CodeXGLUE-CONCODE-w_special_tokens/checkpoint-9000",
4
- "epoch": 3.04,
5
- "global_step": 9500,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -367,11 +367,30 @@
367
  "eval_samples_per_second": 91.11,
368
  "eval_steps_per_second": 2.87,
369
  "step": 9500
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
370
  }
371
  ],
372
  "max_steps": 31250,
373
  "num_train_epochs": 10,
374
- "total_flos": 3.432559070203085e+16,
375
  "trial_name": null,
376
  "trial_params": null
377
  }
 
1
  {
2
  "best_metric": 0.7636184096336365,
3
  "best_model_checkpoint": "/home2/s5431786/jb-internship/results/Salesforce-codet5-small-CodeXGLUE-CONCODE-w_special_tokens/checkpoint-9000",
4
+ "epoch": 3.2,
5
+ "global_step": 10000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
367
  "eval_samples_per_second": 91.11,
368
  "eval_steps_per_second": 2.87,
369
  "step": 9500
370
+ },
371
+ {
372
+ "epoch": 3.2,
373
+ "learning_rate": 7.160036379560077e-05,
374
+ "loss": 0.4847,
375
+ "step": 10000
376
+ },
377
+ {
378
+ "epoch": 3.2,
379
+ "eval_bleu": 0.13710307705006092,
380
+ "eval_exact_match": 0.1645,
381
+ "eval_loss": 0.7670872807502747,
382
+ "eval_rouge1": 0.5697703902827196,
383
+ "eval_rouge2": 0.404941700282087,
384
+ "eval_rougeL": 0.5520241279397228,
385
+ "eval_runtime": 21.8083,
386
+ "eval_samples_per_second": 91.708,
387
+ "eval_steps_per_second": 2.889,
388
+ "step": 10000
389
  }
390
  ],
391
  "max_steps": 31250,
392
  "num_train_epochs": 10,
393
+ "total_flos": 3.612457930378445e+16,
394
  "trial_name": null,
395
  "trial_params": null
396
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3b20b57fc6bbefdfa083820d1d647ee721359543b0768cddfd13495869607e80
3
  size 242019067
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05153b9eed5e8ca31027cb1dccc8505991efe2bf53be4273caa9b830746ce53c
3
  size 242019067