Nexspear commited on
Commit
79e250f
·
verified ·
1 Parent(s): fe5d4e6

Training in progress, step 50, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:95ce6d3e1c1a5c02a31cfb280ebd213b5e203ad6f1e5087d541fb988c6262fe3
3
  size 93608
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42a1f5b7d75be28526be3340d866f7771289f4c5ee1c7eea382840c98d5a9e89
3
  size 93608
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b2e615c641240c9183ead1366f6ac4eaed7669529d56a239ceeb243d82cda1e5
3
  size 197158
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0696f3b2fd95ca074a135925b074c2fdb0804e5c851c16e4fe75a9a6146e5477
3
  size 197158
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1f6aaadfc3a2995ea3bff4c91194faec2c49a54ff830cb39f07c142f67055ad8
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d1201220196b0eea01cc2e9383598f0df0fda082156bad64ee5af51ec629e09
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4ec0bb6efeeb25000ef7426abb9d88265daa212fa2a170e1fb3f58996efa27f6
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
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": 0.02939735423811857,
5
  "eval_steps": 5,
6
- "global_step": 45,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -192,6 +192,21 @@
192
  "eval_samples_per_second": 186.925,
193
  "eval_steps_per_second": 23.42,
194
  "step": 45
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
195
  }
196
  ],
197
  "logging_steps": 3,
@@ -206,12 +221,12 @@
206
  "should_evaluate": false,
207
  "should_log": false,
208
  "should_save": true,
209
- "should_training_stop": false
210
  },
211
  "attributes": {}
212
  }
213
  },
214
- "total_flos": 216937267200.0,
215
  "train_batch_size": 8,
216
  "trial_name": null,
217
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.03266372693124286,
5
  "eval_steps": 5,
6
+ "global_step": 50,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
192
  "eval_samples_per_second": 186.925,
193
  "eval_steps_per_second": 23.42,
194
  "step": 45
195
+ },
196
+ {
197
+ "epoch": 0.03135717785399314,
198
+ "grad_norm": 0.09193761646747589,
199
+ "learning_rate": 6.15582970243117e-07,
200
+ "loss": 11.9265,
201
+ "step": 48
202
+ },
203
+ {
204
+ "epoch": 0.03266372693124286,
205
+ "eval_loss": 11.927508354187012,
206
+ "eval_runtime": 13.8198,
207
+ "eval_samples_per_second": 186.544,
208
+ "eval_steps_per_second": 23.372,
209
+ "step": 50
210
  }
211
  ],
212
  "logging_steps": 3,
 
221
  "should_evaluate": false,
222
  "should_log": false,
223
  "should_save": true,
224
+ "should_training_stop": true
225
  },
226
  "attributes": {}
227
  }
228
  },
229
+ "total_flos": 241041408000.0,
230
  "train_batch_size": 8,
231
  "trial_name": null,
232
  "trial_params": null