ramdhanfirdaus commited on
Commit
f23a6a6
1 Parent(s): dfc30b0

Training in progress, step 2300, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:601be6867d20b2c0173d032fa0906ae1a640ed66154293d554f582e9a2aa08db
3
  size 50338848
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3aaa6d4ea3ca4713a4b145ef605575c9ba31af1f34b2cb18ff06af0badffa5a
3
  size 50338848
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b1e9251f50ad678011925ca5532b4caf04fd62f0bb8b383660338a95fd107a50
3
  size 100693001
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6d8b559870cb80341e36133fe9db36c1a1210031046445d84c58f2852800436
3
  size 100693001
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:af0a74da518cffe2c593216f7fa93fbcfcf6dd279608deff98a3bbfa8adf8b23
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01457e5b90ba866937523f396ebb034542332debca0189a6a18570cda0572380
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f10a983aa914555fea6e5c0db8d7ddbaebbe7e28546c78ee0e93ac76cbc28436
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58c098aa199ff890a6444b804a3fbc89c9468b8e4fb7f53db1b50396e4ed0c2d
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.438491940498352,
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,
@@ -315,13 +315,27 @@
315
  "eval_samples_per_second": 43.719,
316
  "eval_steps_per_second": 5.47,
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": 1.3114779429401395e+17,
325
  "trial_name": null,
326
  "trial_params": null
327
  }
 
1
  {
2
+ "best_metric": 1.4254748821258545,
3
+ "best_model_checkpoint": "./outputs/checkpoint-2300",
4
+ "epoch": 1.6757741347905282,
5
  "eval_steps": 100,
6
+ "global_step": 2300,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
315
  "eval_samples_per_second": 43.719,
316
  "eval_steps_per_second": 5.47,
317
  "step": 2200
318
+ },
319
+ {
320
+ "epoch": 1.68,
321
+ "learning_rate": 0.0002,
322
+ "loss": 1.4197,
323
+ "step": 2300
324
+ },
325
+ {
326
+ "epoch": 1.68,
327
+ "eval_loss": 1.4254748821258545,
328
+ "eval_runtime": 143.6399,
329
+ "eval_samples_per_second": 43.679,
330
+ "eval_steps_per_second": 5.465,
331
+ "step": 2300
332
  }
333
  ],
334
  "logging_steps": 100,
335
  "max_steps": 4116,
336
  "num_train_epochs": 3,
337
  "save_steps": 100,
338
+ "total_flos": 1.3710280298073293e+17,
339
  "trial_name": null,
340
  "trial_params": null
341
  }