auxyus commited on
Commit
18a14c0
·
verified ·
1 Parent(s): a8e3956

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 sha256:3e49a64b97b8e2d758dc92e4237bb69809f02ef6c84c0675ec79cdd49f6b72b0
3
  size 125918320
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40983c4cf5a0f112978fdf8c95ca8e252e48c2f86dd0748ba2db2e67c4fb8d4b
3
  size 125918320
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9dde07dfd4b8b0aebde78ef2c7ee647e7cd688e8d6bec4bc76abeebaac134c8a
3
  size 64683604
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7edce80b2c2a36c8fe0d3059e297f1c6209d42aa5706a996b7fef70fa2f1b09e
3
  size 64683604
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e0f61191ff921ed978b0f7b9deac68b26a816c7a9485df5d4cc5f400e2293251
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfab89a712dfc33d6486a404e25c3dd88c9e8a45977158819ce5b9609bebbd6c
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": 0.017061611374407582,
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": 7.854,
161
  "eval_steps_per_second": 0.983,
162
  "step": 45
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
163
  }
164
  ],
165
  "logging_steps": 3,
@@ -179,7 +208,7 @@
179
  "attributes": {}
180
  }
181
  },
182
- "total_flos": 1.1810299178070835e+17,
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": 0.020473933649289098,
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": 7.854,
161
  "eval_steps_per_second": 0.983,
162
  "step": 45
163
+ },
164
+ {
165
+ "epoch": 0.018199052132701423,
166
+ "grad_norm": 4.6452507972717285,
167
+ "learning_rate": 6.209609477998338e-05,
168
+ "loss": 1.932,
169
+ "step": 48
170
+ },
171
+ {
172
+ "epoch": 0.01933649289099526,
173
+ "grad_norm": 4.3586039543151855,
174
+ "learning_rate": 5.695865504800327e-05,
175
+ "loss": 2.1188,
176
+ "step": 51
177
+ },
178
+ {
179
+ "epoch": 0.020473933649289098,
180
+ "grad_norm": 4.268399715423584,
181
+ "learning_rate": 5.174497483512506e-05,
182
+ "loss": 1.9989,
183
+ "step": 54
184
+ },
185
+ {
186
+ "epoch": 0.020473933649289098,
187
+ "eval_loss": 0.5036410689353943,
188
+ "eval_runtime": 565.5702,
189
+ "eval_samples_per_second": 7.854,
190
+ "eval_steps_per_second": 0.983,
191
+ "step": 54
192
  }
193
  ],
194
  "logging_steps": 3,
 
208
  "attributes": {}
209
  }
210
  },
211
+ "total_flos": 1.426642334342185e+17,
212
  "train_batch_size": 8,
213
  "trial_name": null,
214
  "trial_params": null