VERSIL91 commited on
Commit
9256f0c
·
verified ·
1 Parent(s): 23db9d9

Training in progress, step 25, 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:df55ebbc253d796f893d39cf7e21a9647b86adb544e967a9d5180715b837a154
3
  size 50624
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6af1a750314fb353dd0476360788b62897ac227e2c096331381356e58af1c50a
3
  size 50624
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:308b70daea68247765fd18ef395af74c9684014fc606192ef97250d88f568564
3
  size 111142
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a111d922dedc266757ca934e0f0dbdef866ed723ececed9bc87cf5f0ea0743f
3
  size 111142
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f3d485376269cb08d5dd5b0246e2a05cf77b55914063aeb7d69eed728d074503
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13096529883c0adffb5e69839f0a1cd926efd800efac40df816e6ab444626905
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:023bdd8ed5f79026a3d2962328197e68e515f50915f88388642e8ab363ec2e23
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4677d15317405bcdd600dfdae9d04715d81517a0dbc7789a073149e371184d8c
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.8571428571428571,
5
  "eval_steps": 7,
6
- "global_step": 21,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -186,6 +186,34 @@
186
  "eval_samples_per_second": 243.487,
187
  "eval_steps_per_second": 121.743,
188
  "step": 21
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
189
  }
190
  ],
191
  "logging_steps": 1,
@@ -200,12 +228,12 @@
200
  "should_evaluate": false,
201
  "should_log": false,
202
  "should_save": true,
203
- "should_training_stop": false
204
  },
205
  "attributes": {}
206
  }
207
  },
208
- "total_flos": 8786811027456.0,
209
  "train_batch_size": 2,
210
  "trial_name": null,
211
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 1.0204081632653061,
5
  "eval_steps": 7,
6
+ "global_step": 25,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
186
  "eval_samples_per_second": 243.487,
187
  "eval_steps_per_second": 121.743,
188
  "step": 21
189
+ },
190
+ {
191
+ "epoch": 0.8979591836734694,
192
+ "grad_norm": 0.060265716165304184,
193
+ "learning_rate": 9.549150281252633e-06,
194
+ "loss": 10.3787,
195
+ "step": 22
196
+ },
197
+ {
198
+ "epoch": 0.9387755102040817,
199
+ "grad_norm": 0.06014272943139076,
200
+ "learning_rate": 4.322727117869951e-06,
201
+ "loss": 10.379,
202
+ "step": 23
203
+ },
204
+ {
205
+ "epoch": 0.9795918367346939,
206
+ "grad_norm": 0.06301859021186829,
207
+ "learning_rate": 1.0926199633097157e-06,
208
+ "loss": 10.3748,
209
+ "step": 24
210
+ },
211
+ {
212
+ "epoch": 1.0204081632653061,
213
+ "grad_norm": 0.09851101040840149,
214
+ "learning_rate": 0.0,
215
+ "loss": 15.3437,
216
+ "step": 25
217
  }
218
  ],
219
  "logging_steps": 1,
 
228
  "should_evaluate": false,
229
  "should_log": false,
230
  "should_save": true,
231
+ "should_training_stop": true
232
  },
233
  "attributes": {}
234
  }
235
  },
236
+ "total_flos": 10447413706752.0,
237
  "train_batch_size": 2,
238
  "trial_name": null,
239
  "trial_params": null