ardaspear commited on
Commit
809db0a
·
verified ·
1 Parent(s): 58f451d

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 sha256:4e016df494cd1a20becf8b304b437acc58ebc4b3a2fe00342fff5babeb01b248
3
  size 191968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98db81541c9f8ec105d1f8649166a64886ccbf4eb7284b46d6b75595d7167f05
3
  size 191968
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:040354bd2dad7f5b261b7da4a7ae50a8ba97d32dca488aa3d9def588806bd98a
3
  size 253144
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f16a64f172e75bc3f28ca8271415e8d4b4c84984574a204a977abf9ceee5f3e
3
  size 253144
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b8f44828df8830151d896be841876dc9cee379b27bb94793e2085a5033e38e02
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5270a8ad33fa8f4633e4b858b5f92c1fafc05119f07ca49330569eeec336ada6
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": 0.008294739752540263,
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": 467.94,
193
  "eval_steps_per_second": 117.023,
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": 5019779727360.0,
215
  "train_batch_size": 4,
216
  "trial_name": null,
217
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.009216377502822516,
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": 467.94,
193
  "eval_steps_per_second": 117.023,
194
  "step": 45
195
+ },
196
+ {
197
+ "epoch": 0.008847722402709614,
198
+ "grad_norm": 0.1559176743030548,
199
+ "learning_rate": 6.15582970243117e-07,
200
+ "loss": 10.3592,
201
+ "step": 48
202
+ },
203
+ {
204
+ "epoch": 0.009216377502822516,
205
+ "eval_loss": 10.359918594360352,
206
+ "eval_runtime": 19.3944,
207
+ "eval_samples_per_second": 471.115,
208
+ "eval_steps_per_second": 117.818,
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": 5577533030400.0,
230
  "train_batch_size": 4,
231
  "trial_name": null,
232
  "trial_params": null