leixa commited on
Commit
f940b20
·
verified ·
1 Parent(s): ac63052

Training in progress, step 45, checkpoint

Browse files
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:716c95d71d14195f7609f2b47b8cd394054c201c713778941a925565eb5c9fbe
3
  size 71878612
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6fc2afde4a5f703afe90b3f01cedd0ec0aded2a3e6b352717b70e5662f0162c0
3
  size 71878612
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5e1d95bf1a292ea4a2936184a69f8c3dce438a13419e0bcc2bef40ba98d756d8
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9940273afa8bcd8f752d29b537814a30d3558db2d483fa1eb2352bed44b1cd5a
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bd18e5325bf99a4b662a5314e5f491b65903ffc83b0317f63835d8305a50591e
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ec0bb6efeeb25000ef7426abb9d88265daa212fa2a170e1fb3f58996efa27f6
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": 0.11486001435750179,
5
  "eval_steps": 5,
6
- "global_step": 40,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -170,6 +170,28 @@
170
  "eval_samples_per_second": 64.716,
171
  "eval_steps_per_second": 8.158,
172
  "step": 40
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
173
  }
174
  ],
175
  "logging_steps": 3,
@@ -189,7 +211,7 @@
189
  "attributes": {}
190
  }
191
  },
192
- "total_flos": 3091392972718080.0,
193
  "train_batch_size": 8,
194
  "trial_name": null,
195
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.12921751615218952,
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,
 
170
  "eval_samples_per_second": 64.716,
171
  "eval_steps_per_second": 8.158,
172
  "step": 40
173
+ },
174
+ {
175
+ "epoch": 0.12060301507537688,
176
+ "grad_norm": NaN,
177
+ "learning_rate": 9.549150281252633e-06,
178
+ "loss": 0.0,
179
+ "step": 42
180
+ },
181
+ {
182
+ "epoch": 0.12921751615218952,
183
+ "grad_norm": NaN,
184
+ "learning_rate": 3.8060233744356633e-06,
185
+ "loss": 0.0,
186
+ "step": 45
187
+ },
188
+ {
189
+ "epoch": 0.12921751615218952,
190
+ "eval_loss": NaN,
191
+ "eval_runtime": 9.0643,
192
+ "eval_samples_per_second": 64.76,
193
+ "eval_steps_per_second": 8.164,
194
+ "step": 45
195
  }
196
  ],
197
  "logging_steps": 3,
 
211
  "attributes": {}
212
  }
213
  },
214
+ "total_flos": 3477817094307840.0,
215
  "train_batch_size": 8,
216
  "trial_name": null,
217
  "trial_params": null