eddysang commited on
Commit
6cd1c13
·
verified ·
1 Parent(s): b2b8822

Training in progress, step 54, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c5f40ad01719623fca20476005d278d6961abe114f43e46e6a954cdaa3e5f14e
3
  size 97728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4650f9955c1655120e0107081c0047294b2af0923537c7dc2e5a24afe5daab87
3
  size 97728
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a6a8ba3d4bed89425fa1771effc98f9da086a1eb3a6f609f021ab149a4cc3d70
3
  size 212298
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4b9f4a3b80ec66c98f904b0d99efc41390ca0ee26b684ef4ea43aa51c5b3a77
3
  size 212298
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:46203c46cfdbbc32c45ae0c3b176792d235e2d9e941c7f8c720fe98dfd77a7ad
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8ef5338eaf3429c06a4ea99d294ad8d90f65c79341e8186d482d4dcfac70fde
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b665a2618254d0693455029a117143eb612684fd8f287fa7207d501afc785521
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f68b4a4ba4603d307a8be653dd70e693a9f3506ea1af5f24d2d241dc54cfcb1
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": 0.7503908285565398,
5
  "eval_steps": 9,
6
- "global_step": 45,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -160,6 +160,35 @@
160
  "eval_samples_per_second": 118.95,
161
  "eval_steps_per_second": 59.768,
162
  "step": 45
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
163
  }
164
  ],
165
  "logging_steps": 3,
@@ -179,7 +208,7 @@
179
  "attributes": {}
180
  }
181
  },
182
- "total_flos": 83735573299200.0,
183
  "train_batch_size": 2,
184
  "trial_name": null,
185
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.9004689942678479,
5
  "eval_steps": 9,
6
+ "global_step": 54,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
160
  "eval_samples_per_second": 118.95,
161
  "eval_steps_per_second": 59.768,
162
  "step": 45
163
+ },
164
+ {
165
+ "epoch": 0.8004168837936425,
166
+ "grad_norm": 0.10969464480876923,
167
+ "learning_rate": 0.00010904928748046599,
168
+ "loss": 11.7494,
169
+ "step": 48
170
+ },
171
+ {
172
+ "epoch": 0.8504429390307452,
173
+ "grad_norm": 0.09933030605316162,
174
+ "learning_rate": 0.00010095877928081196,
175
+ "loss": 11.7457,
176
+ "step": 51
177
+ },
178
+ {
179
+ "epoch": 0.9004689942678479,
180
+ "grad_norm": 0.10053879022598267,
181
+ "learning_rate": 9.25084022891929e-05,
182
+ "loss": 11.7445,
183
+ "step": 54
184
+ },
185
+ {
186
+ "epoch": 0.9004689942678479,
187
+ "eval_loss": 11.742661476135254,
188
+ "eval_runtime": 1.6933,
189
+ "eval_samples_per_second": 119.883,
190
+ "eval_steps_per_second": 60.237,
191
+ "step": 54
192
  }
193
  ],
194
  "logging_steps": 3,
 
208
  "attributes": {}
209
  }
210
  },
211
+ "total_flos": 100943617720320.0,
212
  "train_batch_size": 2,
213
  "trial_name": null,
214
  "trial_params": null