leixa commited on
Commit
a863af6
·
verified ·
1 Parent(s): 212f8b4

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 sha256:3129428a4465811a9d2537cf029827cd55ad6c82e6ea8cd412724bb5e433f0ae
3
  size 122200212
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0604db5dfaa60c274c8c50e6eb12363095c78fbf0b7b18dbd8bd0a915b929f69
3
  size 122200212
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d4d2ab6f2665ab1065657617a0c32aa1164ef8317f47445abcd5ad747c589183
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:497f1e0583dc8e202bebb0fe9ef30f163b2a4ed653a1da7302154a20fedb0760
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": 0.0032683076294556224,
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": 44.531,
171
  "eval_steps_per_second": 5.567,
172
  "step": 40
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
173
  }
174
  ],
175
  "logging_steps": 3,
@@ -189,7 +211,7 @@
189
  "attributes": {}
190
  }
191
  },
192
- "total_flos": 1.0537031172096e+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": 0.0036768460831375755,
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": 44.531,
171
  "eval_steps_per_second": 5.567,
172
  "step": 40
173
+ },
174
+ {
175
+ "epoch": 0.003431723010928404,
176
+ "grad_norm": NaN,
177
+ "learning_rate": 9.549150281252633e-06,
178
+ "loss": 0.0,
179
+ "step": 42
180
+ },
181
+ {
182
+ "epoch": 0.0036768460831375755,
183
+ "grad_norm": NaN,
184
+ "learning_rate": 3.8060233744356633e-06,
185
+ "loss": 0.0,
186
+ "step": 45
187
+ },
188
+ {
189
+ "epoch": 0.0036768460831375755,
190
+ "eval_loss": NaN,
191
+ "eval_runtime": 463.0744,
192
+ "eval_samples_per_second": 44.513,
193
+ "eval_steps_per_second": 5.565,
194
+ "step": 45
195
  }
196
  ],
197
  "logging_steps": 3,
 
211
  "attributes": {}
212
  }
213
  },
214
+ "total_flos": 1.1854160068608e+16,
215
  "train_batch_size": 8,
216
  "trial_name": null,
217
  "trial_params": null