flytech commited on
Commit
49313f2
·
1 Parent(s): 2a2ca23

Training in progress, step 1100, 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:c871ff3f5191ba9d84d95d49526b48b3a64015b90fcfb3b97308a69bd4baab8a
3
  size 67143296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:084f2eac19aac4b3fc595843aed5d55f3fa57644f7a9ede6b2bca70ce0a2ffa2
3
  size 67143296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5c9b0ae12eb6ec6a798b81a654cd5efccd601425ca8bb5851db76fc22e39b783
3
  size 33920095
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eab6871ce0fd3395a6c1180801688d85aa37e3a68863d993bd214c6c0ef7ebe1
3
  size 33920095
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6556ac00826ca68da6956f62bae0bc37868dae3c7f5f2b790637f8c3ff47184f
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c3f48995f26676ef6f4c1f1142b6bcb18508f1e323890588609403164ba8264
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8baac9452f9a11760308042a12ceaa04a49da1de0252fb4cb010c250b16b5f44
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f72237f8d43340588246c2d5a5a04356e199d7b453e08784a6593b2606b43313
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": 6.097560975609756,
5
  "eval_steps": 100,
6
- "global_step": 1000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -137,13 +137,26 @@
137
  "eval_samples_per_second": 2.037,
138
  "eval_steps_per_second": 0.266,
139
  "step": 1000
 
 
 
 
 
 
 
 
 
 
 
 
 
140
  }
141
  ],
142
  "logging_steps": 100,
143
  "max_steps": 1312,
144
  "num_train_epochs": 8,
145
  "save_steps": 100,
146
- "total_flos": 8.303000071805338e+16,
147
  "trial_name": null,
148
  "trial_params": null
149
  }
 
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,
 
137
  "eval_samples_per_second": 2.037,
138
  "eval_steps_per_second": 0.266,
139
  "step": 1000
140
+ },
141
+ {
142
+ "epoch": 6.71,
143
+ "learning_rate": 0.0002,
144
+ "loss": 0.0287,
145
+ "step": 1100
146
+ },
147
+ {
148
+ "epoch": 6.71,
149
+ "eval_runtime": 33.8531,
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
  }