ardaspear commited on
Commit
fdfd6d2
·
verified ·
1 Parent(s): ce7aafb

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:f04182e748e284e0d9be6018bc5891d35096c4a0f2f15278c436a950408b3a2b
3
  size 313820248
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48d4eb8345e0a78fe0b66dfb26355299eab84619481964eeb7ea3f0c683e53d1
3
  size 313820248
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0e97aa5d22c5d661b49d29160ae8b7cdde7fbba34a55b7dcfdb0ae7cba0d35db
3
  size 159641092
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fab95d304778b247c757f12d632518df8d3eaf6babe43121612d1ec6cee8dade
3
  size 159641092
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c7b35861db89ee1a6f5d7e6c052c628b2b75c6590296f6d0ca91555aa241e19d
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:023102a051f760766a144582c96f626398664b1bf3cf4c836f3bf9971ef467ca
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0896677f34f08366c4c71a3f69133212afc490296ec7ee225b8aefde1f38f24c
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2011b1e019073e4bafc29de9703ff0a6e7c1252c3a53d804807bd1c99d390d1c
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": 0.0017668364792838424,
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": 27.586,
161
  "eval_steps_per_second": 6.896,
162
  "step": 45
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
163
  }
164
  ],
165
  "logging_steps": 3,
@@ -179,7 +208,7 @@
179
  "attributes": {}
180
  }
181
  },
182
- "total_flos": 9114245073469440.0,
183
  "train_batch_size": 4,
184
  "trial_name": null,
185
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0021202037751406107,
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": 27.586,
161
  "eval_steps_per_second": 6.896,
162
  "step": 45
163
+ },
164
+ {
165
+ "epoch": 0.0018846255779027652,
166
+ "grad_norm": 3.105065115960315e-05,
167
+ "learning_rate": 6.209609477998338e-05,
168
+ "loss": 0.0,
169
+ "step": 48
170
+ },
171
+ {
172
+ "epoch": 0.0020024146765216877,
173
+ "grad_norm": 3.0599792808061466e-05,
174
+ "learning_rate": 5.695865504800327e-05,
175
+ "loss": 0.0,
176
+ "step": 51
177
+ },
178
+ {
179
+ "epoch": 0.0021202037751406107,
180
+ "grad_norm": 3.959710738854483e-05,
181
+ "learning_rate": 5.174497483512506e-05,
182
+ "loss": 0.0,
183
+ "step": 54
184
+ },
185
+ {
186
+ "epoch": 0.0021202037751406107,
187
+ "eval_loss": 0.0005288115935400128,
188
+ "eval_runtime": 777.4935,
189
+ "eval_samples_per_second": 27.586,
190
+ "eval_steps_per_second": 6.897,
191
+ "step": 54
192
  }
193
  ],
194
  "logging_steps": 3,
 
208
  "attributes": {}
209
  }
210
  },
211
+ "total_flos": 1.0937094088163328e+16,
212
  "train_batch_size": 4,
213
  "trial_name": null,
214
  "trial_params": null