ramdhanfirdaus commited on
Commit
099d502
1 Parent(s): bbbe791

Training in progress, step 2000, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:90993a712767ba831e0eb0d75ee07a257a0bf62ad0524f6a43e7dcaffe1a7c0a
3
  size 50338848
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5020ae1b85bc8c31e73a46408b3a24d07ee6a2bdc9d0afd47f0b341999d8980
3
  size 50338848
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a1a68925553b65953f06d34ae16d4497b617e140fd5e1fe10f53cbabc3044d2c
3
  size 100693001
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44da255db8658f335bbe4d3c61fa1c58ff4a852190153c6f6d368b4ca9bc28fe
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:fdb914a5087312403f353baa664c2ab587e06cedf9a35f8de8dcd25d3669b6a5
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24346a849cfe61c13302a37506071c1084c1e3e04875e8d39528fcce4331e38e
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b2d4b4cadcabd3e17adcc39c43d8312038a1f5c7f53125f288ba4de5ed25396b
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:720bafe9a34b3041027dccef7d9c03bb23064e1fcdd80ae5f27e717d41b7cf31
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
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,
@@ -273,13 +273,27 @@
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
  }
 
1
  {
2
+ "best_metric": 1.4687143564224243,
3
+ "best_model_checkpoint": "./outputs/checkpoint-2000",
4
+ "epoch": 1.4571948998178508,
5
  "eval_steps": 100,
6
+ "global_step": 2000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
273
  "eval_samples_per_second": 43.587,
274
  "eval_steps_per_second": 5.454,
275
  "step": 1900
276
+ },
277
+ {
278
+ "epoch": 1.46,
279
+ "learning_rate": 0.0002,
280
+ "loss": 1.4608,
281
+ "step": 2000
282
+ },
283
+ {
284
+ "epoch": 1.46,
285
+ "eval_loss": 1.4687143564224243,
286
+ "eval_runtime": 143.8741,
287
+ "eval_samples_per_second": 43.608,
288
+ "eval_steps_per_second": 5.456,
289
+ "step": 2000
290
  }
291
  ],
292
  "logging_steps": 100,
293
  "max_steps": 4116,
294
  "num_train_epochs": 3,
295
  "save_steps": 100,
296
+ "total_flos": 1.192283395987538e+17,
297
  "trial_name": null,
298
  "trial_params": null
299
  }