auxyus commited on
Commit
b55313d
·
verified ·
1 Parent(s): 2fb274c

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 sha256:33980152b68f3395b120001c806559c4b147ea9c6e357909d704944b35ed0b6d
3
  size 167832240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:019e4cedf3cbf7ce3972bdf6f8f4f354534fde649e8b09c9d2c315f6fbd510df
3
  size 167832240
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cc2613fc12fe955219a1b87f298c9eef1cbe8fde4e512395056e2b31879912d6
3
  size 85723284
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc727fd4f08812ae2aa25a5b43971e4d2af6568a5d49fe6230a720b32a96bd30
3
  size 85723284
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0f283a044b624feb4f39dacb5843c1dee5ae0fb0f63ef9eb1e3b1fc3026a24bd
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2faefdf4b488c4d2301c9dee831c8a65c0777bb39f135c29c208144a14ea798f
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": 0.17424975798644723,
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": 13.678,
161
  "eval_steps_per_second": 1.729,
162
  "step": 45
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
163
  }
164
  ],
165
  "logging_steps": 3,
@@ -179,7 +208,7 @@
179
  "attributes": {}
180
  }
181
  },
182
- "total_flos": 6.40129250057257e+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": 0.2090997095837367,
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": 13.678,
161
  "eval_steps_per_second": 1.729,
162
  "step": 45
163
+ },
164
+ {
165
+ "epoch": 0.18586640851887706,
166
+ "grad_norm": 0.05485091730952263,
167
+ "learning_rate": 6.209609477998338e-05,
168
+ "loss": 0.0015,
169
+ "step": 48
170
+ },
171
+ {
172
+ "epoch": 0.19748305905130686,
173
+ "grad_norm": 0.002600950188934803,
174
+ "learning_rate": 5.695865504800327e-05,
175
+ "loss": 0.0001,
176
+ "step": 51
177
+ },
178
+ {
179
+ "epoch": 0.2090997095837367,
180
+ "grad_norm": 0.0022585629485547543,
181
+ "learning_rate": 5.174497483512506e-05,
182
+ "loss": 0.0,
183
+ "step": 54
184
+ },
185
+ {
186
+ "epoch": 0.2090997095837367,
187
+ "eval_loss": 0.00028623713296838105,
188
+ "eval_runtime": 31.8325,
189
+ "eval_samples_per_second": 13.665,
190
+ "eval_steps_per_second": 1.728,
191
+ "step": 54
192
  }
193
  ],
194
  "logging_steps": 3,
 
208
  "attributes": {}
209
  }
210
  },
211
+ "total_flos": 7.702654162776883e+16,
212
  "train_batch_size": 8,
213
  "trial_name": null,
214
  "trial_params": null