ramdhanfirdaus commited on
Commit
6f09562
1 Parent(s): b705147

Training in progress, step 1300, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:09b83e4520d2faac0a44fd3666ca6e85059aafeb42755438c0c137479572f7d7
3
  size 50338848
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:820d01be5a6b44cb2bba830db51c2d55caa147263e00ed937c2ce7a626ae0adb
3
  size 50338848
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:02c00055b5bd03e4890f1ce79bb80d46ddf81ae1aa9064d1c8fdab8f5ba06aac
3
  size 100693001
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19c29a5b504e561230992463937333d2b9056f92f246eb125d546954f42e48ba
3
  size 100693001
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2bce8ad87f00a02b0d2a3d827e73ac036f343d9552caa13a5ae85d423ed6d4b0
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63dc2d8608fa8b36d01cc06ffb7d3c3b355455dfe67158233e553a478a7c7c1d
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:60fe2b14e82d752da652953a5bae182d24c7ff34775d2753b9c2e6fa092203d0
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5fc56f953d372e16c8b68954ff13e9f4409f9a42678d3b33dea6fba4610a0519
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.7218060493469238,
3
- "best_model_checkpoint": "./outputs/checkpoint-1200",
4
- "epoch": 0.8743169398907104,
5
  "eval_steps": 100,
6
- "global_step": 1200,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -175,13 +175,27 @@
175
  "eval_samples_per_second": 43.714,
176
  "eval_steps_per_second": 5.469,
177
  "step": 1200
 
 
 
 
 
 
 
 
 
 
 
 
 
 
178
  }
179
  ],
180
  "logging_steps": 100,
181
  "max_steps": 4116,
182
  "num_train_epochs": 3,
183
  "save_steps": 100,
184
- "total_flos": 7.145822849964442e+16,
185
  "trial_name": null,
186
  "trial_params": null
187
  }
 
1
  {
2
+ "best_metric": 1.7012412548065186,
3
+ "best_model_checkpoint": "./outputs/checkpoint-1300",
4
+ "epoch": 0.9471766848816029,
5
  "eval_steps": 100,
6
+ "global_step": 1300,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
175
  "eval_samples_per_second": 43.714,
176
  "eval_steps_per_second": 5.469,
177
  "step": 1200
178
+ },
179
+ {
180
+ "epoch": 0.95,
181
+ "learning_rate": 0.0002,
182
+ "loss": 1.7297,
183
+ "step": 1300
184
+ },
185
+ {
186
+ "epoch": 0.95,
187
+ "eval_loss": 1.7012412548065186,
188
+ "eval_runtime": 143.4698,
189
+ "eval_samples_per_second": 43.73,
190
+ "eval_steps_per_second": 5.472,
191
+ "step": 1300
192
  }
193
  ],
194
  "logging_steps": 100,
195
  "max_steps": 4116,
196
  "num_train_epochs": 3,
197
  "save_steps": 100,
198
+ "total_flos": 7.742035914040934e+16,
199
  "trial_name": null,
200
  "trial_params": null
201
  }