ardaspear commited on
Commit
d705513
1 Parent(s): 6fc7d87

Training in progress, step 50, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:484b564556001283f0d8c372e1e22820eb2c2ababff7b29414fc5d7dd1d5cd90
3
  size 201892112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19a785a817251a18e9c0eae3952035c3505fb1645ac9ac49575f590a9ab15736
3
  size 201892112
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7f5b35a6fc72d8a9de74bdd173b4d56c093bd702a665fe32978ad4ba92d53fa3
3
  size 102864548
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f3bc159dc052eb81a5376976aafd0249ad91c051b5124810f9f4a19f1e45e6a
3
  size 102864548
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cecf351b617076c45c0034f29458db064d42fc3eea5373ffe2c7217695d60873
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76658005c4626c0a8daf163cbdb581f57819d09d3986cf636e8bb013cfcc3b45
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4ec0bb6efeeb25000ef7426abb9d88265daa212fa2a170e1fb3f58996efa27f6
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
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": 0.6629834254143646,
5
  "eval_steps": 5,
6
- "global_step": 45,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -192,6 +192,21 @@
192
  "eval_samples_per_second": 42.349,
193
  "eval_steps_per_second": 10.679,
194
  "step": 45
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
195
  }
196
  ],
197
  "logging_steps": 3,
@@ -206,12 +221,12 @@
206
  "should_evaluate": false,
207
  "should_log": false,
208
  "should_save": true,
209
- "should_training_stop": false
210
  },
211
  "attributes": {}
212
  }
213
  },
214
- "total_flos": 1.0105787951087616e+16,
215
  "train_batch_size": 4,
216
  "trial_name": null,
217
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.7366482504604052,
5
  "eval_steps": 5,
6
+ "global_step": 50,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
192
  "eval_samples_per_second": 42.349,
193
  "eval_steps_per_second": 10.679,
194
  "step": 45
195
+ },
196
+ {
197
+ "epoch": 0.7071823204419889,
198
+ "grad_norm": 0.6874891519546509,
199
+ "learning_rate": 6.15582970243117e-07,
200
+ "loss": 1.1784,
201
+ "step": 48
202
+ },
203
+ {
204
+ "epoch": 0.7366482504604052,
205
+ "eval_loss": 1.1656928062438965,
206
+ "eval_runtime": 2.7133,
207
+ "eval_samples_per_second": 42.384,
208
+ "eval_steps_per_second": 10.688,
209
+ "step": 50
210
  }
211
  ],
212
  "logging_steps": 3,
 
221
  "should_evaluate": false,
222
  "should_log": false,
223
  "should_save": true,
224
+ "should_training_stop": true
225
  },
226
  "attributes": {}
227
  }
228
  },
229
+ "total_flos": 1.1225690573635584e+16,
230
  "train_batch_size": 4,
231
  "trial_name": null,
232
  "trial_params": null