flytech commited on
Commit
aa4ab33
·
1 Parent(s): d6b1435

Training in progress, step 1200, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:084f2eac19aac4b3fc595843aed5d55f3fa57644f7a9ede6b2bca70ce0a2ffa2
3
  size 67143296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1795802f4511a46b862c760a771fcf7d13e599eab282287bf05031405bb35f32
3
  size 67143296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eab6871ce0fd3395a6c1180801688d85aa37e3a68863d993bd214c6c0ef7ebe1
3
  size 33920095
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:584b92137767666caa3f47ae2f55aec401396c6691caef772442cf9c6c44cb0e
3
  size 33920095
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3c3f48995f26676ef6f4c1f1142b6bcb18508f1e323890588609403164ba8264
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:571070238262a03131eeae7cb667e5ed7d30e4d5b5a51967463c2bf0d77948d5
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f72237f8d43340588246c2d5a5a04356e199d7b453e08784a6593b2606b43313
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3df57d65731b72280f603ea0eb027e9c3dbbef708582b288973433cc1df17299
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 6.7073170731707314,
5
  "eval_steps": 100,
6
- "global_step": 1100,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -150,13 +150,26 @@
150
  "eval_samples_per_second": 2.038,
151
  "eval_steps_per_second": 0.266,
152
  "step": 1100
 
 
 
 
 
 
 
 
 
 
 
 
 
153
  }
154
  ],
155
  "logging_steps": 100,
156
  "max_steps": 1312,
157
  "num_train_epochs": 8,
158
  "save_steps": 100,
159
- "total_flos": 9.135172466874778e+16,
160
  "trial_name": null,
161
  "trial_params": null
162
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 7.317073170731708,
5
  "eval_steps": 100,
6
+ "global_step": 1200,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
150
  "eval_samples_per_second": 2.038,
151
  "eval_steps_per_second": 0.266,
152
  "step": 1100
153
+ },
154
+ {
155
+ "epoch": 7.32,
156
+ "learning_rate": 0.0002,
157
+ "loss": 0.0267,
158
+ "step": 1200
159
+ },
160
+ {
161
+ "epoch": 7.32,
162
+ "eval_runtime": 33.8867,
163
+ "eval_samples_per_second": 2.036,
164
+ "eval_steps_per_second": 0.266,
165
+ "step": 1200
166
  }
167
  ],
168
  "logging_steps": 100,
169
  "max_steps": 1312,
170
  "num_train_epochs": 8,
171
  "save_steps": 100,
172
+ "total_flos": 9.964224215462707e+16,
173
  "trial_name": null,
174
  "trial_params": null
175
  }