oldiday commited on
Commit
a24cf89
·
verified ·
1 Parent(s): 12795ec

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 sha256:3c88853c0c7fbb83191805d7dddba7b419b637c6f703fcc914f694695f0e683c
3
  size 73911112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01978adfb77fca7fd9dce8fee717a8665c820e1bc8d27ec2f70fbbb22a87d957
3
  size 73911112
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5f5085db9d4b21bee1f086feab633a6e6fcd5c6b5cc1ea1753ba5747e083b9cd
3
  size 37965300
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26c1d4560b9a66b2004bd2b26b2152b3cff5801ac052a825c468e31ae34116b3
3
  size 37965300
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cb48600f5c0be872f5604a4284b7a785b06f1698395c195456b60d50b40442d1
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a347f5446a51df24d512acf398e5372d6960730c52b0dc0ea5f5d8a37c76f8a
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9776c8df8be516beee92201f32f4a3f5d90539bf47f8ef27e1636cdc132a851e
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec430a8fba90f7f39f74e916eb32712c363a0fd20bb4904251fce0eb82f2b9cf
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": 0.0015178217571316542,
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": 30.122,
161
  "eval_steps_per_second": 3.765,
162
  "step": 45
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
163
  }
164
  ],
165
  "logging_steps": 3,
@@ -179,7 +208,7 @@
179
  "attributes": {}
180
  }
181
  },
182
- "total_flos": 1.3846449670324224e+16,
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": 0.001821386108557985,
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": 30.122,
161
  "eval_steps_per_second": 3.765,
162
  "step": 45
163
+ },
164
+ {
165
+ "epoch": 0.0016190098742737645,
166
+ "grad_norm": 0.3037606179714203,
167
+ "learning_rate": 3.104804738999169e-05,
168
+ "loss": 0.7856,
169
+ "step": 48
170
+ },
171
+ {
172
+ "epoch": 0.0017201979914158747,
173
+ "grad_norm": 0.2485446184873581,
174
+ "learning_rate": 2.8479327524001636e-05,
175
+ "loss": 0.7938,
176
+ "step": 51
177
+ },
178
+ {
179
+ "epoch": 0.001821386108557985,
180
+ "grad_norm": 0.24273481965065002,
181
+ "learning_rate": 2.587248741756253e-05,
182
+ "loss": 0.7606,
183
+ "step": 54
184
+ },
185
+ {
186
+ "epoch": 0.001821386108557985,
187
+ "eval_loss": 0.8170143365859985,
188
+ "eval_runtime": 1656.2446,
189
+ "eval_samples_per_second": 30.148,
190
+ "eval_steps_per_second": 3.769,
191
+ "step": 54
192
  }
193
  ],
194
  "logging_steps": 3,
 
208
  "attributes": {}
209
  }
210
  },
211
+ "total_flos": 1.6850867995017216e+16,
212
  "train_batch_size": 8,
213
  "trial_name": null,
214
  "trial_params": null