ardaspear commited on
Commit
c7a16a7
·
verified ·
1 Parent(s): 859f0e1

Training in progress, step 63, 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:f2b7dd8e5afc9aa29c4a2b764862f3893ae76079f20a93f9d4a3f967dd8baa89
3
  size 1001465824
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:906d89c73a29ae5fbdab0bccaab839653cd2b21a62aa9bce4b0f92aabee18bb9
3
  size 1001465824
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fa4f561ad8ffcb5c869231ed6b4c6edc500358ffa70c05639ae1958d851cecad
3
  size 509176980
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cca5e1bed11b97f60ffab38e8ddf3d42527147fa7577c8cd93c566d10be62de2
3
  size 509176980
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:76a7af8e7dc9db0611d7e02b5036ec494dcb2bc08691bb86341ddba3da8bce4f
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68562acc50572f6cb365f5d14b11accf166d4aa6a44cf504f5e5b802c9d1c19f
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2011b1e019073e4bafc29de9703ff0a6e7c1252c3a53d804807bd1c99d390d1c
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e53b95eff99f2334cbf7ed4c962db83cb42e931305982518e928382563b5670d
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": 0.4778761061946903,
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,
@@ -189,6 +189,35 @@
189
  "eval_samples_per_second": 7.77,
190
  "eval_steps_per_second": 1.963,
191
  "step": 54
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
192
  }
193
  ],
194
  "logging_steps": 3,
@@ -208,7 +237,7 @@
208
  "attributes": {}
209
  }
210
  },
211
- "total_flos": 7.856944047980544e+16,
212
  "train_batch_size": 4,
213
  "trial_name": null,
214
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.5575221238938053,
5
  "eval_steps": 9,
6
+ "global_step": 63,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
189
  "eval_samples_per_second": 7.77,
190
  "eval_steps_per_second": 1.963,
191
  "step": 54
192
+ },
193
+ {
194
+ "epoch": 0.504424778761062,
195
+ "grad_norm": 4.16663424402941e-05,
196
+ "learning_rate": 4.6512176312793736e-05,
197
+ "loss": 0.0,
198
+ "step": 57
199
+ },
200
+ {
201
+ "epoch": 0.5309734513274337,
202
+ "grad_norm": 3.846506660920568e-05,
203
+ "learning_rate": 4.131759111665349e-05,
204
+ "loss": 0.0,
205
+ "step": 60
206
+ },
207
+ {
208
+ "epoch": 0.5575221238938053,
209
+ "grad_norm": 5.5511947721242905e-05,
210
+ "learning_rate": 3.6218132209150045e-05,
211
+ "loss": 0.0,
212
+ "step": 63
213
+ },
214
+ {
215
+ "epoch": 0.5575221238938053,
216
+ "eval_loss": 2.6978867140314833e-07,
217
+ "eval_runtime": 12.2104,
218
+ "eval_samples_per_second": 7.78,
219
+ "eval_steps_per_second": 1.966,
220
+ "step": 63
221
  }
222
  ],
223
  "logging_steps": 3,
 
237
  "attributes": {}
238
  }
239
  },
240
+ "total_flos": 9.112767072043008e+16,
241
  "train_batch_size": 4,
242
  "trial_name": null,
243
  "trial_params": null