Nexspear commited on
Commit
adde1b9
·
verified ·
1 Parent(s): eae1ea0

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:ec79bc408791a80afe683b546c9e4a7e9f987175c279b440fea47e4425a146e5
3
  size 3029024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:698af42704e526834908d96480980c1f51a702ae2ddaa271b4daa7a295a46494
3
  size 3029024
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:306d8866ffd40b610411a4a735999daa6da14eaa786272ec674dcefb7c956bf4
3
  size 1663290
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8cee7a7afcd87d8d919c513acbc21fcbd5464231e4c22a55a38e72dbf736b55
3
  size 1663290
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4e642adb9bde829ad8b2cd3b6d817946087d92af624243a6203f83e4cc48e22b
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f5b1e7142f6cecd16f2ce254c6937e5ae5850743a60e8c82f1d31eede648215
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": 0.7228915662650602,
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": 171.356,
193
  "eval_steps_per_second": 22.847,
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": 29435520614400.0,
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": 0.8032128514056225,
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": 171.356,
193
  "eval_steps_per_second": 22.847,
194
  "step": 45
195
+ },
196
+ {
197
+ "epoch": 0.7710843373493976,
198
+ "grad_norm": 5.148656845092773,
199
+ "learning_rate": 6.15582970243117e-07,
200
+ "loss": 4.825,
201
+ "step": 48
202
+ },
203
+ {
204
+ "epoch": 0.8032128514056225,
205
+ "eval_loss": 5.06525182723999,
206
+ "eval_runtime": 0.6142,
207
+ "eval_samples_per_second": 170.963,
208
+ "eval_steps_per_second": 22.795,
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": 32706134016000.0,
230
  "train_batch_size": 8,
231
  "trial_name": null,
232
  "trial_params": null