auxyus commited on
Commit
b717f0c
·
verified ·
1 Parent(s): 747bb80

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:d00c7e0489c3056244b2ace09169bfb4f93206e18e7392448950109422b18fae
3
  size 167832240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:326604bf1e4015010c601c777d2c8fa6051df066849623ce30784e1ef218a492
3
  size 167832240
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a92316a8c3eb3e79ccdcc65dd0c5ef4dc96bd9c57921b50107fa48349ba8d92d
3
  size 85723284
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f32d0365c16d42dbc2859fc6c80dedf65b53dc0d996834db8cf20f413ff451b4
3
  size 85723284
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fc299d4d7ac4df8a132f63a99aeb47022723c5eba91b9d0547bae20412ab19f0
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c31715ea70906674f165a2ecd010dd0c9eee0955d3b3ed03e0871c427b235cb
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": 0.03484320557491289,
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": 11.572,
161
  "eval_steps_per_second": 1.447,
162
  "step": 45
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
163
  }
164
  ],
165
  "logging_steps": 3,
@@ -179,7 +208,7 @@
179
  "attributes": {}
180
  }
181
  },
182
- "total_flos": 8.511608709552538e+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": 0.041811846689895474,
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": 11.572,
161
  "eval_steps_per_second": 1.447,
162
  "step": 45
163
+ },
164
+ {
165
+ "epoch": 0.03716608594657375,
166
+ "grad_norm": 0.957979142665863,
167
+ "learning_rate": 6.209609477998338e-05,
168
+ "loss": 0.0077,
169
+ "step": 48
170
+ },
171
+ {
172
+ "epoch": 0.03948896631823461,
173
+ "grad_norm": 0.04404503479599953,
174
+ "learning_rate": 5.695865504800327e-05,
175
+ "loss": 0.007,
176
+ "step": 51
177
+ },
178
+ {
179
+ "epoch": 0.041811846689895474,
180
+ "grad_norm": 0.040287747979164124,
181
+ "learning_rate": 5.174497483512506e-05,
182
+ "loss": 0.0027,
183
+ "step": 54
184
+ },
185
+ {
186
+ "epoch": 0.041811846689895474,
187
+ "eval_loss": 0.0014874738408252597,
188
+ "eval_runtime": 188.104,
189
+ "eval_samples_per_second": 11.568,
190
+ "eval_steps_per_second": 1.446,
191
+ "step": 54
192
  }
193
  ],
194
  "logging_steps": 3,
 
208
  "attributes": {}
209
  }
210
  },
211
+ "total_flos": 1.0094345866287514e+17,
212
  "train_batch_size": 8,
213
  "trial_name": null,
214
  "trial_params": null