Hanzalwi commited on
Commit
7e7b4b7
1 Parent(s): 2c9dd8c

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 sha256:0aa8a38a99adbb6b86d95a8e88bae913ce143e94b7424352e70d64006e97f8f7
3
  size 9444296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3df1f960a29c44061fce66ae401b18a75ac0738ee75c302a3eebb9ed3a0c763e
3
  size 9444296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cb7f1f3770b40fd29e9fe2d8e8e6cb188fbc7927c7790a397e71ae90d8ab8dc9
3
  size 18902665
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6223ebb88b8579bea4e2ca04d51e383ef3b9142dca394ff972e89f98c62bb82
3
  size 18902665
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2fcf009a64a304dce1129b0fdc1b80a365b4ef48344321c5dfb03cba1db1c591
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1b6db96b2a087280e0193508072347d81e3efb5dcab769c085a2a842cb52560
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": 0.9502108693122864,
3
- "best_model_checkpoint": "./outputs/checkpoint-1900",
4
- "epoch": 2.6988636363636362,
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,
@@ -273,6 +273,20 @@
273
  "eval_samples_per_second": 11.973,
274
  "eval_steps_per_second": 1.501,
275
  "step": 1900
 
 
 
 
 
 
 
 
 
 
 
 
 
 
276
  }
277
  ],
278
  "logging_steps": 100,
@@ -280,7 +294,7 @@
280
  "num_input_tokens_seen": 0,
281
  "num_train_epochs": 3,
282
  "save_steps": 100,
283
- "total_flos": 1.0682272179726336e+17,
284
  "trial_name": null,
285
  "trial_params": null
286
  }
 
1
  {
2
+ "best_metric": 0.946110725402832,
3
+ "best_model_checkpoint": "./outputs/checkpoint-2000",
4
+ "epoch": 2.840909090909091,
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": 11.973,
274
  "eval_steps_per_second": 1.501,
275
  "step": 1900
276
+ },
277
+ {
278
+ "epoch": 2.84,
279
+ "learning_rate": 0.0002,
280
+ "loss": 1.0644,
281
+ "step": 2000
282
+ },
283
+ {
284
+ "epoch": 2.84,
285
+ "eval_loss": 0.946110725402832,
286
+ "eval_runtime": 124.5826,
287
+ "eval_samples_per_second": 11.976,
288
+ "eval_steps_per_second": 1.501,
289
+ "step": 2000
290
  }
291
  ],
292
  "logging_steps": 100,
 
294
  "num_input_tokens_seen": 0,
295
  "num_train_epochs": 3,
296
  "save_steps": 100,
297
+ "total_flos": 1.1244470506924032e+17,
298
  "trial_name": null,
299
  "trial_params": null
300
  }