Nexspear commited on
Commit
93db600
·
verified ·
1 Parent(s): d3b7c5c

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 sha256:0ca832022a4fdb2cfc2219f7a58b81c017785efd41136fe794ca4ffcf2b8112f
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c93950bb7509b0e5a7540d1dbd63e694c26ae561db93f6807dabf581752b34f
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": 0.02611818478615736,
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": 13.933,
171
  "eval_steps_per_second": 1.744,
172
  "step": 40
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
173
  }
174
  ],
175
  "logging_steps": 3,
@@ -189,7 +211,7 @@
189
  "attributes": {}
190
  }
191
  },
192
- "total_flos": 5.388511147248845e+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": 0.029382957884427033,
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": 13.933,
171
  "eval_steps_per_second": 1.744,
172
  "step": 40
173
+ },
174
+ {
175
+ "epoch": 0.02742409402546523,
176
+ "grad_norm": NaN,
177
+ "learning_rate": 9.549150281252633e-06,
178
+ "loss": 0.0,
179
+ "step": 42
180
+ },
181
+ {
182
+ "epoch": 0.029382957884427033,
183
+ "grad_norm": NaN,
184
+ "learning_rate": 3.8060233744356633e-06,
185
+ "loss": 0.0,
186
+ "step": 45
187
+ },
188
+ {
189
+ "epoch": 0.029382957884427033,
190
+ "eval_loss": NaN,
191
+ "eval_runtime": 185.1182,
192
+ "eval_samples_per_second": 13.937,
193
+ "eval_steps_per_second": 1.745,
194
+ "step": 45
195
  }
196
  ],
197
  "logging_steps": 3,
 
211
  "attributes": {}
212
  }
213
  },
214
+ "total_flos": 6.053759437032653e+16,
215
  "train_batch_size": 8,
216
  "trial_name": null,
217
  "trial_params": null