ardaspear commited on
Commit
f67bc4d
·
verified ·
1 Parent(s): 956bb0c

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 sha256:9107fafa3feb2315c0bfdcc6cc8ec2c735d37487a11022c7e2850cf0e953e4d7
3
  size 162933396
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:082d6f3b6cb12d8310bf6f2e5db45ac3938a4c0e04475cbc04d4ee6f1f242514
3
  size 162933396
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cc4225b533e4e9dd54d7aa3f270f10463a965c47e914701f2f60fa9f7dcf3dd1
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8222a1d0ac1429a9450c3064e8cf124063ea7ffccda32e845cdd25c38625a7c5
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": 0.3595505617977528,
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": 7.153,
171
  "eval_steps_per_second": 1.826,
172
  "step": 40
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
173
  }
174
  ],
175
  "logging_steps": 3,
@@ -189,7 +211,7 @@
189
  "attributes": {}
190
  }
191
  },
192
- "total_flos": 5.061937953610138e+16,
193
  "train_batch_size": 4,
194
  "trial_name": null,
195
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.4044943820224719,
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": 7.153,
171
  "eval_steps_per_second": 1.826,
172
  "step": 40
173
+ },
174
+ {
175
+ "epoch": 0.3775280898876405,
176
+ "grad_norm": NaN,
177
+ "learning_rate": 9.549150281252633e-06,
178
+ "loss": 0.0,
179
+ "step": 42
180
+ },
181
+ {
182
+ "epoch": 0.4044943820224719,
183
+ "grad_norm": NaN,
184
+ "learning_rate": 3.8060233744356633e-06,
185
+ "loss": 0.0,
186
+ "step": 45
187
+ },
188
+ {
189
+ "epoch": 0.4044943820224719,
190
+ "eval_loss": NaN,
191
+ "eval_runtime": 13.1637,
192
+ "eval_samples_per_second": 7.141,
193
+ "eval_steps_per_second": 1.823,
194
+ "step": 45
195
  }
196
  ],
197
  "logging_steps": 3,
 
211
  "attributes": {}
212
  }
213
  },
214
+ "total_flos": 5.686462766068531e+16,
215
  "train_batch_size": 4,
216
  "trial_name": null,
217
  "trial_params": null