robiulawaldev commited on
Commit
bba00ba
·
verified ·
1 Parent(s): 0ba7dab

Training in progress, step 200, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:26cdab1b0d375bdd23565aa0077f6a65dd30f31149be06116d841a3b8feb3920
3
  size 319876032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e6a04970cb5d78a98f82e69d520797d1ae0c7ce113faedb5f3d0a95a5084e1e
3
  size 319876032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fad6f35856a1fb7fd23e18813fe2cb9c2216d4becd30b398a6c8d6e014b1b331
3
  size 162933396
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:271e0c36680a6d6ef625e82425b2ad08b07587c40fccf9eae7de3cbcd8abf46e
3
  size 162933396
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e36897f9547b352e823f9278793dec524937b492282033ac58955b130dceb9f8
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90380594388a92c2134a4d796fe5f20ffd04e397d2fea91f504c9a9f425c601e
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d31dc31a119769737d72f3df4c8cdf99522596cafc12bf2eea05a4ff374f599c
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:859ff0676471245c9481ca25d6d6778d1c7963c39b7877af46bb8ca30a9ead21
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": 0.00338577522966842,
5
  "eval_steps": 50,
6
- "global_step": 150,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -144,6 +144,49 @@
144
  "eval_samples_per_second": 30.993,
145
  "eval_steps_per_second": 15.498,
146
  "step": 150
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
147
  }
148
  ],
149
  "logging_steps": 10,
@@ -158,12 +201,12 @@
158
  "should_evaluate": false,
159
  "should_log": false,
160
  "should_save": true,
161
- "should_training_stop": false
162
  },
163
  "attributes": {}
164
  }
165
  },
166
- "total_flos": 1.3508300242944e+16,
167
  "train_batch_size": 2,
168
  "trial_name": null,
169
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0045143669728912265,
5
  "eval_steps": 50,
6
+ "global_step": 200,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
144
  "eval_samples_per_second": 30.993,
145
  "eval_steps_per_second": 15.498,
146
  "step": 150
147
+ },
148
+ {
149
+ "epoch": 0.003611493578312981,
150
+ "grad_norm": 0.7603806853294373,
151
+ "learning_rate": 0.0002,
152
+ "loss": 2.1003,
153
+ "step": 160
154
+ },
155
+ {
156
+ "epoch": 0.0038372119269575425,
157
+ "grad_norm": 0.965023398399353,
158
+ "learning_rate": 0.0002,
159
+ "loss": 2.0787,
160
+ "step": 170
161
+ },
162
+ {
163
+ "epoch": 0.004062930275602104,
164
+ "grad_norm": 1.2172741889953613,
165
+ "learning_rate": 0.0002,
166
+ "loss": 1.9607,
167
+ "step": 180
168
+ },
169
+ {
170
+ "epoch": 0.004288648624246665,
171
+ "grad_norm": 0.8917762041091919,
172
+ "learning_rate": 0.0002,
173
+ "loss": 2.0938,
174
+ "step": 190
175
+ },
176
+ {
177
+ "epoch": 0.0045143669728912265,
178
+ "grad_norm": 0.7753519415855408,
179
+ "learning_rate": 0.0002,
180
+ "loss": 2.1024,
181
+ "step": 200
182
+ },
183
+ {
184
+ "epoch": 0.0045143669728912265,
185
+ "eval_loss": 2.11333966255188,
186
+ "eval_runtime": 300.569,
187
+ "eval_samples_per_second": 31.031,
188
+ "eval_steps_per_second": 15.517,
189
+ "step": 200
190
  }
191
  ],
192
  "logging_steps": 10,
 
201
  "should_evaluate": false,
202
  "should_log": false,
203
  "should_save": true,
204
+ "should_training_stop": true
205
  },
206
  "attributes": {}
207
  }
208
  },
209
+ "total_flos": 1.78725203214336e+16,
210
  "train_batch_size": 2,
211
  "trial_name": null,
212
  "trial_params": null