rizkyjun commited on
Commit
85f3e40
1 Parent(s): c1b8816

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 sha256:1bb86cb895cb8c09d875749e2262012ec54b41549a6370e21405f9d30f578c50
3
  size 9444296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91974617b05454f6a187b444a29a01f0a802331eda364445923332194b762f76
3
  size 9444296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e3d7f07f50024928bdc9c01bbe994ecdd95cdafc9ea187b6380862fbdb761416
3
  size 18902665
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebfecc1ad5b104aecf9e725a8eb45d1f3b5e90292a533648bfc87d84422204fd
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:f9a66de94ddf6ddb1a1f57868c95171312871a0a8334cc09fd510e6f196d45be
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:660b7a5dfb51fff12ee01e67c8658d1f17ca6123b8cc1eb386148b5ee4e14a5f
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": 2.2003238201141357,
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": 30.299,
274
  "eval_steps_per_second": 3.791,
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": 5.588270155302912e+16,
283
  "trial_name": null,
284
  "trial_params": null
285
  }
 
1
  {
2
+ "best_metric": 2.1876213550567627,
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": 30.299,
274
  "eval_steps_per_second": 3.791,
275
  "step": 1900
276
+ },
277
+ {
278
+ "epoch": 1.46,
279
+ "learning_rate": 0.0002,
280
+ "loss": 2.1719,
281
+ "step": 2000
282
+ },
283
+ {
284
+ "epoch": 1.46,
285
+ "eval_loss": 2.1876213550567627,
286
+ "eval_runtime": 206.1329,
287
+ "eval_samples_per_second": 30.437,
288
+ "eval_steps_per_second": 3.808,
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": 5.88204413088768e+16,
297
  "trial_name": null,
298
  "trial_params": null
299
  }