rizkyjun commited on
Commit
d6b6ca1
1 Parent(s): f62f357

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 sha256:8aee548989776a0d096ebb15b1c7f23d4a53c29832287572044a4ebe374dea1d
3
  size 9444296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ffe7fb38e98b365cc296f0c38dbc3b6a5353db6236e3cb98dc27a53219ea4aae
3
  size 9444296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ebc0e2f17c2a65600c105e685737acc5d8465065895e6490bfb6cd76c7836e57
3
  size 18902665
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:584f16b88260905d7532b3763b86ba048162214b405c89b3409c62a715cb2f1f
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:d2511746767caf74ed2af043be349b91a9f9de694b3b61fb6953cef602c3b33a
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:613209fe19785aab62e1f8fb807af95ea3ab972ed7fc7b2d61958367dc06f82c
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": 2.2953364849090576,
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": 30.63,
274
  "eval_steps_per_second": 3.832,
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": 5.419260380362752e+16,
283
  "trial_name": null,
284
  "trial_params": null
285
  }
 
1
  {
2
+ "best_metric": 2.279343843460083,
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": 30.63,
274
  "eval_steps_per_second": 3.832,
275
  "step": 1900
276
+ },
277
+ {
278
+ "epoch": 1.46,
279
+ "learning_rate": 0.0002,
280
+ "loss": 2.2697,
281
+ "step": 2000
282
+ },
283
+ {
284
+ "epoch": 1.46,
285
+ "eval_loss": 2.279343843460083,
286
+ "eval_runtime": 205.0674,
287
+ "eval_samples_per_second": 30.595,
288
+ "eval_steps_per_second": 3.828,
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": 5.70422421531648e+16,
297
  "trial_name": null,
298
  "trial_params": null
299
  }