auxyus commited on
Commit
17db0e6
·
verified ·
1 Parent(s): 5ade221

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 sha256:326604bf1e4015010c601c777d2c8fa6051df066849623ce30784e1ef218a492
3
  size 167832240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11946d45297919fb0647eca17fd2fc71812fd1a84b43957ec2aa9d5469de2bc5
3
  size 167832240
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f32d0365c16d42dbc2859fc6c80dedf65b53dc0d996834db8cf20f413ff451b4
3
  size 85723284
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9f0e7d06281e8e7f7b2b0056064a1f25ef9e7e8f3ec3525f052bf6fc331e62e
3
  size 85723284
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9c31715ea70906674f165a2ecd010dd0c9eee0955d3b3ed03e0871c427b235cb
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65e8040a588f8b6ad7455c916a15561d6fe4fa1f26fa943d8f3c9f87562b410f
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": 0.041811846689895474,
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,
@@ -189,6 +189,35 @@
189
  "eval_samples_per_second": 11.568,
190
  "eval_steps_per_second": 1.446,
191
  "step": 54
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
192
  }
193
  ],
194
  "logging_steps": 3,
@@ -208,7 +237,7 @@
208
  "attributes": {}
209
  }
210
  },
211
- "total_flos": 1.0094345866287514e+17,
212
  "train_batch_size": 8,
213
  "trial_name": null,
214
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.04878048780487805,
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": 11.568,
190
  "eval_steps_per_second": 1.446,
191
  "step": 54
192
+ },
193
+ {
194
+ "epoch": 0.04413472706155633,
195
+ "grad_norm": 0.13004916906356812,
196
+ "learning_rate": 4.6512176312793736e-05,
197
+ "loss": 0.0022,
198
+ "step": 57
199
+ },
200
+ {
201
+ "epoch": 0.04645760743321719,
202
+ "grad_norm": 0.2595899999141693,
203
+ "learning_rate": 4.131759111665349e-05,
204
+ "loss": 0.0009,
205
+ "step": 60
206
+ },
207
+ {
208
+ "epoch": 0.04878048780487805,
209
+ "grad_norm": 2.1593716144561768,
210
+ "learning_rate": 3.6218132209150045e-05,
211
+ "loss": 0.0074,
212
+ "step": 63
213
+ },
214
+ {
215
+ "epoch": 0.04878048780487805,
216
+ "eval_loss": 0.0013361426535993814,
217
+ "eval_runtime": 188.094,
218
+ "eval_samples_per_second": 11.569,
219
+ "eval_steps_per_second": 1.446,
220
+ "step": 63
221
  }
222
  ],
223
  "logging_steps": 3,
 
237
  "attributes": {}
238
  }
239
  },
240
+ "total_flos": 1.181777077028782e+17,
241
  "train_batch_size": 8,
242
  "trial_name": null,
243
  "trial_params": null