leixa commited on
Commit
63805f9
·
verified ·
1 Parent(s): 853fa67

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 sha256:6d0e4201b909dc6c9653f558d9207c4fba1d90c65547bc291f6763f4ab2c5ad4
3
  size 35237104
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:589d93e1644290e1763ee903924287395b8711bcc462c358790f2bd476968213
3
  size 35237104
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e7f2303b9ae95ba5bb82964e9841472e31f3eac3da71e4ef73a8601291096e45
3
  size 18810036
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6672bfe400a9d4d5706252e9cd899264f30591c191b7f2dc6bc0ae9cca496f7
3
  size 18810036
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b55534edeb16a30ba2060c2d5b41f5d3a9adf813094ee82e943b4e8cd4729116
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e3fde9edff067179eaac97e25ed4311ccba425a548976dedf75ffc08ca49cb4
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": 0.5678233438485805,
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": 59.971,
161
  "eval_steps_per_second": 7.608,
162
  "step": 45
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
163
  }
164
  ],
165
  "logging_steps": 3,
@@ -179,7 +208,7 @@
179
  "attributes": {}
180
  }
181
  },
182
- "total_flos": 3568723789086720.0,
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": 0.6813880126182965,
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": 59.971,
161
  "eval_steps_per_second": 7.608,
162
  "step": 45
163
+ },
164
+ {
165
+ "epoch": 0.6056782334384858,
166
+ "grad_norm": 0.717880368232727,
167
+ "learning_rate": 6.209609477998338e-05,
168
+ "loss": 1.6268,
169
+ "step": 48
170
+ },
171
+ {
172
+ "epoch": 0.6435331230283912,
173
+ "grad_norm": 0.688407301902771,
174
+ "learning_rate": 5.695865504800327e-05,
175
+ "loss": 1.7635,
176
+ "step": 51
177
+ },
178
+ {
179
+ "epoch": 0.6813880126182965,
180
+ "grad_norm": 0.7644420266151428,
181
+ "learning_rate": 5.174497483512506e-05,
182
+ "loss": 1.4975,
183
+ "step": 54
184
+ },
185
+ {
186
+ "epoch": 0.6813880126182965,
187
+ "eval_loss": 1.6497859954833984,
188
+ "eval_runtime": 2.2418,
189
+ "eval_samples_per_second": 59.772,
190
+ "eval_steps_per_second": 7.583,
191
+ "step": 54
192
  }
193
  ],
194
  "logging_steps": 3,
 
208
  "attributes": {}
209
  }
210
  },
211
+ "total_flos": 4307701947432960.0,
212
  "train_batch_size": 8,
213
  "trial_name": null,
214
  "trial_params": null