rizkyjun commited on
Commit
686f523
1 Parent(s): 85e34f5

Training in progress, step 2200, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:10616865a82845d928d11470dbc2376d17050bb7cf9decc0acdf7772ee974537
3
  size 9444296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fd7f58e1200259dc7dd50b5686d1e58a48fac1194dedd1145103080e18e5880
3
  size 9444296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7f805e0a1894bb979c525c5434fb935ad79f4243d251a27e8063560ab0aa6c4d
3
  size 18902665
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f3142d7ba859a940cb52a274f34142d29102c0dc2d76787a6090fd708c84a6e
3
  size 18902665
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5475b1ce7a4d7950d1b1c1234e4bd9b06df23ed931dac1d75f24c3fa63c2c513
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:225d338513df9b3c96bfa51035af41455d9ed58f0d399244944c7e6aaaa43616
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b1238b3bfa75e49a19396161e9e7b72ab89cdd1a3f63b51c0ab4d6e8d216c5a5
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f10a983aa914555fea6e5c0db8d7ddbaebbe7e28546c78ee0e93ac76cbc28436
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 2.2688376903533936,
3
- "best_model_checkpoint": "./outputs/checkpoint-2100",
4
- "epoch": 1.530054644808743,
5
  "eval_steps": 100,
6
- "global_step": 2100,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -301,13 +301,27 @@
301
  "eval_samples_per_second": 30.631,
302
  "eval_steps_per_second": 3.833,
303
  "step": 2100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
304
  }
305
  ],
306
  "logging_steps": 100,
307
  "max_steps": 4116,
308
  "num_train_epochs": 3,
309
  "save_steps": 100,
310
- "total_flos": 5.987678208325632e+16,
311
  "trial_name": null,
312
  "trial_params": null
313
  }
 
1
  {
2
+ "best_metric": 2.2520592212677,
3
+ "best_model_checkpoint": "./outputs/checkpoint-2200",
4
+ "epoch": 1.6029143897996359,
5
  "eval_steps": 100,
6
+ "global_step": 2200,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
301
  "eval_samples_per_second": 30.631,
302
  "eval_steps_per_second": 3.833,
303
  "step": 2100
304
+ },
305
+ {
306
+ "epoch": 1.6,
307
+ "learning_rate": 0.0002,
308
+ "loss": 2.2357,
309
+ "step": 2200
310
+ },
311
+ {
312
+ "epoch": 1.6,
313
+ "eval_loss": 2.2520592212677,
314
+ "eval_runtime": 204.8048,
315
+ "eval_samples_per_second": 30.634,
316
+ "eval_steps_per_second": 3.833,
317
+ "step": 2200
318
  }
319
  ],
320
  "logging_steps": 100,
321
  "max_steps": 4116,
322
  "num_train_epochs": 3,
323
  "save_steps": 100,
324
+ "total_flos": 6.273785068959744e+16,
325
  "trial_name": null,
326
  "trial_params": null
327
  }