auxyus commited on
Commit
ff2a1da
·
verified ·
1 Parent(s): 18031a0

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 sha256:680ddfa6814d59919c0076c072cf1f1d8730e7555e534a9e5de1c2ee1946f844
3
  size 217931936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ed8679f635c6f98ad302acd28592335987737835b7e838e1a961cb8c8aefc97
3
  size 217931936
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:291cf092537a9997910f645e28a0c0d4aac20e01556955bb7a3c2b551549b7f3
3
  size 111412180
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1180c7800a0d28a71575b3a070a66545542f14ede0a86d0a449310a937511d90
3
  size 111412180
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e70815b76403150f357476f8c7c6203eb49775afd453225f5b00784817bcbbc4
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:309f5212554111e860f47c767bb213d4ac9d7a0d401a916e9676a94b454762a3
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": 0.6060606060606061,
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": 11.085,
161
  "eval_steps_per_second": 1.419,
162
  "step": 45
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
163
  }
164
  ],
165
  "logging_steps": 3,
@@ -179,7 +208,7 @@
179
  "attributes": {}
180
  }
181
  },
182
- "total_flos": 7.627949293436928e+16,
183
  "train_batch_size": 8,
184
  "trial_name": null,
185
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.7272727272727273,
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": 11.085,
161
  "eval_steps_per_second": 1.419,
162
  "step": 45
163
+ },
164
+ {
165
+ "epoch": 0.6464646464646465,
166
+ "grad_norm": 0.0005675142747350037,
167
+ "learning_rate": 6.209609477998338e-05,
168
+ "loss": 0.0,
169
+ "step": 48
170
+ },
171
+ {
172
+ "epoch": 0.6868686868686869,
173
+ "grad_norm": 0.00048168693319894373,
174
+ "learning_rate": 5.695865504800327e-05,
175
+ "loss": 0.0,
176
+ "step": 51
177
+ },
178
+ {
179
+ "epoch": 0.7272727272727273,
180
+ "grad_norm": 0.00044461351353675127,
181
+ "learning_rate": 5.174497483512506e-05,
182
+ "loss": 0.0,
183
+ "step": 54
184
+ },
185
+ {
186
+ "epoch": 0.7272727272727273,
187
+ "eval_loss": 1.0228068276774138e-05,
188
+ "eval_runtime": 11.2817,
189
+ "eval_samples_per_second": 11.08,
190
+ "eval_steps_per_second": 1.418,
191
+ "step": 54
192
  }
193
  ],
194
  "logging_steps": 3,
 
208
  "attributes": {}
209
  }
210
  },
211
+ "total_flos": 9.153539152124314e+16,
212
  "train_batch_size": 8,
213
  "trial_name": null,
214
  "trial_params": null