leixa commited on
Commit
f7b6be3
·
verified ·
1 Parent(s): 8162f11

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:fc55f53855e0ad12c49455e02175feb614b48f2877c80cadb38dffb451f32e89
3
  size 325339796
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b35e611a6d72a194af6ce69859542d2578ccc2ad5b8435f26c41a31fe9fcd54
3
  size 325339796
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8d7983e4c3d00e20601a21d81775e64262640eb06c1b7eb7259b517225ed86ef
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b929eae424d20922df50dd28280b781223b2ea3e489263d661bb3de405965781
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": 0.25477707006369427,
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": 11.476,
171
  "eval_steps_per_second": 1.472,
172
  "step": 40
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
173
  }
174
  ],
175
  "logging_steps": 3,
@@ -189,7 +211,7 @@
189
  "attributes": {}
190
  }
191
  },
192
- "total_flos": 6.71020323176448e+16,
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": 0.28662420382165604,
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": 11.476,
171
  "eval_steps_per_second": 1.472,
172
  "step": 40
173
+ },
174
+ {
175
+ "epoch": 0.267515923566879,
176
+ "grad_norm": NaN,
177
+ "learning_rate": 9.549150281252633e-06,
178
+ "loss": 0.0,
179
+ "step": 42
180
+ },
181
+ {
182
+ "epoch": 0.28662420382165604,
183
+ "grad_norm": NaN,
184
+ "learning_rate": 3.8060233744356633e-06,
185
+ "loss": 0.0,
186
+ "step": 45
187
+ },
188
+ {
189
+ "epoch": 0.28662420382165604,
190
+ "eval_loss": NaN,
191
+ "eval_runtime": 23.1002,
192
+ "eval_samples_per_second": 11.472,
193
+ "eval_steps_per_second": 1.472,
194
+ "step": 45
195
  }
196
  ],
197
  "logging_steps": 3,
 
211
  "attributes": {}
212
  }
213
  },
214
+ "total_flos": 7.582529651893862e+16,
215
  "train_batch_size": 8,
216
  "trial_name": null,
217
  "trial_params": null