rizkyjun commited on
Commit
40a6c83
1 Parent(s): 626dcf0

Training in progress, step 2100, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:757e659bf33071c096568d8eb06785568c67acd861a7092274d741368be256e6
3
  size 9444296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10616865a82845d928d11470dbc2376d17050bb7cf9decc0acdf7772ee974537
3
  size 9444296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b6b7a3c33e9598887c6963727785f726eec8c742c06af36409d4283905c1d83c
3
  size 18902665
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f805e0a1894bb979c525c5434fb935ad79f4243d251a27e8063560ab0aa6c4d
3
  size 18902665
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:613209fe19785aab62e1f8fb807af95ea3ab972ed7fc7b2d61958367dc06f82c
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5475b1ce7a4d7950d1b1c1234e4bd9b06df23ed931dac1d75f24c3fa63c2c513
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:720bafe9a34b3041027dccef7d9c03bb23064e1fcdd80ae5f27e717d41b7cf31
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1238b3bfa75e49a19396161e9e7b72ab89cdd1a3f63b51c0ab4d6e8d216c5a5
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 2.2830755710601807,
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,
@@ -287,13 +287,27 @@
287
  "eval_samples_per_second": 30.658,
288
  "eval_steps_per_second": 3.836,
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
  }
 
1
  {
2
+ "best_metric": 2.2688376903533936,
3
+ "best_model_checkpoint": "./outputs/checkpoint-2100",
4
+ "epoch": 1.530054644808743,
5
  "eval_steps": 100,
6
+ "global_step": 2100,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
287
  "eval_samples_per_second": 30.658,
288
  "eval_steps_per_second": 3.836,
289
  "step": 2000
290
+ },
291
+ {
292
+ "epoch": 1.53,
293
+ "learning_rate": 0.0002,
294
+ "loss": 2.252,
295
+ "step": 2100
296
+ },
297
+ {
298
+ "epoch": 1.53,
299
+ "eval_loss": 2.2688376903533936,
300
+ "eval_runtime": 204.8236,
301
+ "eval_samples_per_second": 30.631,
302
+ "eval_steps_per_second": 3.833,
303
+ "step": 2100
304
  }
305
  ],
306
  "logging_steps": 100,
307
  "max_steps": 4116,
308
  "num_train_epochs": 3,
309
  "save_steps": 100,
310
+ "total_flos": 5.987678208325632e+16,
311
  "trial_name": null,
312
  "trial_params": null
313
  }