rizkyjun commited on
Commit
60354c4
1 Parent(s): e70f0c5

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 sha256:350c1967286dd64a95fd5e74d50f830f2121f7fa957a9cf1f0510ea18888be16
3
  size 9444296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad0c0dcf8cc7437300dbc06837548f9692d2c3443d2b874c7ed833ac8c61fa69
3
  size 9444296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e6e51297d8eb04bfa815f4810ff640d24dd696dece50f3931e74723c2d7845b8
3
  size 18902665
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5cb7864e0d610a29dac7d2e0761cd37bc46adbc3fc1f9edb84b0e7177a5b6d1d
3
  size 18902665
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:05cf802ece851e37f7a2e8e09140678d93619f6c1e72127ae6bb12317798901b
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0dd8bdb1856d17b194a76c19970eb51f58f0ae25d9a87ca8d59468738cbbfe5f
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": 2.1567013263702393,
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": 30.4,
316
  "eval_steps_per_second": 3.804,
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": 6.469323520149504e+16,
325
  "trial_name": null,
326
  "trial_params": null
327
  }
 
1
  {
2
+ "best_metric": 2.144631862640381,
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": 30.4,
316
  "eval_steps_per_second": 3.804,
317
  "step": 2200
318
+ },
319
+ {
320
+ "epoch": 1.68,
321
+ "learning_rate": 0.0002,
322
+ "loss": 2.1272,
323
+ "step": 2300
324
+ },
325
+ {
326
+ "epoch": 1.68,
327
+ "eval_loss": 2.144631862640381,
328
+ "eval_runtime": 206.1489,
329
+ "eval_samples_per_second": 30.434,
330
+ "eval_steps_per_second": 3.808,
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": 6.762876423432192e+16,
339
  "trial_name": null,
340
  "trial_params": null
341
  }