ramdhanfirdaus commited on
Commit
16618c4
1 Parent(s): 63bf0ae

Training in progress, step 1900, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0a7884666f47637b59637a8fc9af8a1ce49847d53ab83777a89f81098bd2b13c
3
  size 50338848
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90993a712767ba831e0eb0d75ee07a257a0bf62ad0524f6a43e7dcaffe1a7c0a
3
  size 50338848
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:685537a7bd075b8fd47cc8368e20a9be380740877a43c0720636f603fff559ce
3
  size 100693001
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1a68925553b65953f06d34ae16d4497b617e140fd5e1fe10f53cbabc3044d2c
3
  size 100693001
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:44f9f1c4337e0621d656f470fb5437bb2a87d9fb336dbcdc8024d82eaa799879
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fdb914a5087312403f353baa664c2ab587e06cedf9a35f8de8dcd25d3669b6a5
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c0e0a1736a46fd1627af3c246e44261aaac909256abbd413b5ee5c968f6b2d8e
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2d4b4cadcabd3e17adcc39c43d8312038a1f5c7f53125f288ba4de5ed25396b
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.4979889392852783,
3
- "best_model_checkpoint": "./outputs/checkpoint-1800",
4
- "epoch": 1.3114754098360657,
5
  "eval_steps": 100,
6
- "global_step": 1800,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -259,13 +259,27 @@
259
  "eval_samples_per_second": 43.595,
260
  "eval_steps_per_second": 5.455,
261
  "step": 1800
 
 
 
 
 
 
 
 
 
 
 
 
 
 
262
  }
263
  ],
264
  "logging_steps": 100,
265
  "max_steps": 4116,
266
  "num_train_epochs": 3,
267
  "save_steps": 100,
268
- "total_flos": 1.0730188018325914e+17,
269
  "trial_name": null,
270
  "trial_params": null
271
  }
 
1
  {
2
+ "best_metric": 1.4818388223648071,
3
+ "best_model_checkpoint": "./outputs/checkpoint-1900",
4
+ "epoch": 1.384335154826958,
5
  "eval_steps": 100,
6
+ "global_step": 1900,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
259
  "eval_samples_per_second": 43.595,
260
  "eval_steps_per_second": 5.455,
261
  "step": 1800
262
+ },
263
+ {
264
+ "epoch": 1.38,
265
+ "learning_rate": 0.0002,
266
+ "loss": 1.4777,
267
+ "step": 1900
268
+ },
269
+ {
270
+ "epoch": 1.38,
271
+ "eval_loss": 1.4818388223648071,
272
+ "eval_runtime": 143.9405,
273
+ "eval_samples_per_second": 43.587,
274
+ "eval_steps_per_second": 5.454,
275
+ "step": 1900
276
  }
277
  ],
278
  "logging_steps": 100,
279
  "max_steps": 4116,
280
  "num_train_epochs": 3,
281
  "save_steps": 100,
282
+ "total_flos": 1.132675571468206e+17,
283
  "trial_name": null,
284
  "trial_params": null
285
  }