Nexspear commited on
Commit
014a504
·
verified ·
1 Parent(s): 15ab2fb

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 sha256:4ee6cf4cb859f2a19fd6a5f3b1cc4c87d50745d380b75c9a87f5eaed94493f42
3
  size 150486964
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e09d7b73e37faad21081a0df6d7011bb4f38daad4cdf626837639b428bc31e6e
3
  size 150486964
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ac62bace84129b1f59df2d2cdbf4780ec266f325b6f48c5bdeb90f98f6608355
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b956f62da7139d3f4858fad60add5a2c46a4a02ebd5eb322a02efcc280e59796
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": 0.22346368715083798,
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": 36.774,
171
  "eval_steps_per_second": 4.627,
172
  "step": 40
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
173
  }
174
  ],
175
  "logging_steps": 3,
@@ -189,7 +211,7 @@
189
  "attributes": {}
190
  }
191
  },
192
- "total_flos": 1.08857892274176e+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": 0.25139664804469275,
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": 36.774,
171
  "eval_steps_per_second": 4.627,
172
  "step": 40
173
+ },
174
+ {
175
+ "epoch": 0.2346368715083799,
176
+ "grad_norm": NaN,
177
+ "learning_rate": 9.549150281252633e-06,
178
+ "loss": 0.0,
179
+ "step": 42
180
+ },
181
+ {
182
+ "epoch": 0.25139664804469275,
183
+ "grad_norm": NaN,
184
+ "learning_rate": 3.8060233744356633e-06,
185
+ "loss": 0.0,
186
+ "step": 45
187
+ },
188
+ {
189
+ "epoch": 0.25139664804469275,
190
+ "eval_loss": NaN,
191
+ "eval_runtime": 8.2149,
192
+ "eval_samples_per_second": 36.763,
193
+ "eval_steps_per_second": 4.626,
194
+ "step": 45
195
  }
196
  ],
197
  "logging_steps": 3,
 
211
  "attributes": {}
212
  }
213
  },
214
+ "total_flos": 1.22465128808448e+16,
215
  "train_batch_size": 8,
216
  "trial_name": null,
217
  "trial_params": null