rizkyjun commited on
Commit
7487432
1 Parent(s): 39e8474

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:eee718852cec003ec3db14b0f696b66edcf3f1b3c389074225a0f8b5cd2ecfc0
3
  size 31466288
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:950e8c803fcb4a5b7e442d76459e57550da0162d8201c665b1969cd645b00901
3
  size 31466288
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f3ee89b20cc4bb51d8cd942947ab05de6e2f863ef9b6d2d99c727b6a840fa09a
3
  size 62950917
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fbc58acc2834dda70661d24b6c87bbbbf67d35077648bc91f5e1770333619de
3
  size 62950917
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:21b2b16f4c08cc27a40806f2856451e039418be2a7b192aecdaa0799e1113bb8
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce683b1f9b99043522516da1a6d43513b81202580862b22e361f02a471d2a8ef
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": 1.4737541675567627,
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": 11.296,
316
  "eval_steps_per_second": 1.413,
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": 5.7355218612382925e+17,
325
  "trial_name": null,
326
  "trial_params": null
327
  }
 
1
  {
2
+ "best_metric": 1.4537303447723389,
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": 11.296,
316
  "eval_steps_per_second": 1.413,
317
  "step": 2200
318
+ },
319
+ {
320
+ "epoch": 1.68,
321
+ "learning_rate": 0.0002,
322
+ "loss": 1.426,
323
+ "step": 2300
324
+ },
325
+ {
326
+ "epoch": 1.68,
327
+ "eval_loss": 1.4537303447723389,
328
+ "eval_runtime": 555.9884,
329
+ "eval_samples_per_second": 11.284,
330
+ "eval_steps_per_second": 1.412,
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": 5.995777680716759e+17,
339
  "trial_name": null,
340
  "trial_params": null
341
  }