k4black commited on
Commit
92afe32
·
1 Parent(s): 243023a

Training in progress, step 8000

Browse files
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9b89cebb654e87a9728e317fc66791148254aac22cfc7231368bbd73c5379921
3
  size 484047087
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1873b7c859425f0e26f2347fb91e6a776cba2e48839820c2dcea4e22bc7fbc67
3
  size 484047087
last-checkpoint/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ab2bf3415485f8595d3574bd3fc55d98c37cf99e9135697abe02e92aa2b58b2a
3
  size 242012923
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f23299a7aeba471b07c347aceb29e5198305d8414f4dd4b21f79fc14a4592d39
3
  size 242012923
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9c087da379d8a74162facf8df088ad54ad5a18830758e9baf4ff0c963c84f233
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f9038bd13cee7be809b870072293469c3cd227459e6b82a61f4cf6abfd04c52
3
  size 14503
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:093ca96687badc5a1f521da49c370b15357006c1d9df66545702b3ea7d5eff47
3
  size 559
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0316325edea77248486ca0e79ad8e8ee0b7725685c3d831ab06f04629fb1ef89
3
  size 559
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0c17a8178100c0eae1b9807ec53a09b924fa3de21f0290182ca934c979902491
3
  size 623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34db57be1d8dc6c076b5589b33fe55a93138c1738acd1cce1da407f6d1d9bb29
3
  size 623
last-checkpoint/trainer_state.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "best_metric": 0.7708559632301331,
3
- "best_model_checkpoint": "/home2/s5431786/jb-internship/results/Salesforce-codet5-small-CodeXGLUE-CONCODE-adamw/checkpoint-7500",
4
- "epoch": 2.4,
5
- "global_step": 7500,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -306,11 +306,31 @@
306
  "eval_samples_per_second": 75.332,
307
  "eval_steps_per_second": 2.373,
308
  "step": 7500
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
309
  }
310
  ],
311
  "max_steps": 31250,
312
  "num_train_epochs": 10,
313
- "total_flos": 3.189355774161715e+16,
314
  "trial_name": null,
315
  "trial_params": null
316
  }
 
1
  {
2
+ "best_metric": 0.767312228679657,
3
+ "best_model_checkpoint": "/home2/s5431786/jb-internship/results/Salesforce-codet5-small-CodeXGLUE-CONCODE-adamw/checkpoint-8000",
4
+ "epoch": 2.56,
5
+ "global_step": 8000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
306
  "eval_samples_per_second": 75.332,
307
  "eval_steps_per_second": 2.373,
308
  "step": 7500
309
+ },
310
+ {
311
+ "epoch": 2.56,
312
+ "learning_rate": 7.83339508875939e-05,
313
+ "loss": 0.5359,
314
+ "step": 8000
315
+ },
316
+ {
317
+ "epoch": 2.56,
318
+ "eval_bleu": 0.133238582586381,
319
+ "eval_exact_match": 0.164,
320
+ "eval_loss": 0.767312228679657,
321
+ "eval_rouge1": 0.5696523576197161,
322
+ "eval_rouge2": 0.40229167377006236,
323
+ "eval_rougeL": 0.552121263102242,
324
+ "eval_rougeLsum": 0.5600576350734027,
325
+ "eval_runtime": 26.7037,
326
+ "eval_samples_per_second": 74.896,
327
+ "eval_steps_per_second": 2.359,
328
+ "step": 8000
329
  }
330
  ],
331
  "max_steps": 31250,
332
  "num_train_epochs": 10,
333
+ "total_flos": 3.4018432483590144e+16,
334
  "trial_name": null,
335
  "trial_params": null
336
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ab2bf3415485f8595d3574bd3fc55d98c37cf99e9135697abe02e92aa2b58b2a
3
  size 242012923
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f23299a7aeba471b07c347aceb29e5198305d8414f4dd4b21f79fc14a4592d39
3
  size 242012923