auxyus commited on
Commit
69ac4b4
·
verified ·
1 Parent(s): 44336b3

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 sha256:7d8bd059b5a07147395db962efee1e0a409645eb6728f8c2b90e3ee61c90cce4
3
  size 17425352
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9298951fee8139d0aa3cb5225a61e579fd2780cdea3f4d85e9f58b16642cd63e
3
  size 17425352
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b22e887e199dad723e30012306c89bb121f35a85bc00a4f97ad662442f18912b
3
  size 10251668
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4661862b4dad2f089deb74c3b354d4dd80f358eba950c8bae8308af00b48119
3
  size 10251668
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:364110e399b7f87a751563fc89811184979ad9e6b6dece51a29ad2258abb363f
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff97af136db2eaf7b37e51671ee5f5c2671d84dcc325c9c44cfdc99fc2c790e7
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": 0.12558139534883722,
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": 69.78,
190
  "eval_steps_per_second": 8.771,
191
  "step": 54
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
192
  }
193
  ],
194
  "logging_steps": 3,
@@ -208,7 +237,7 @@
208
  "attributes": {}
209
  }
210
  },
211
- "total_flos": 3386524796190720.0,
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": 0.14651162790697675,
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": 69.78,
190
  "eval_steps_per_second": 8.771,
191
  "step": 54
192
+ },
193
+ {
194
+ "epoch": 0.1325581395348837,
195
+ "grad_norm": 1.0287175178527832,
196
+ "learning_rate": 4.6512176312793736e-05,
197
+ "loss": 3.9619,
198
+ "step": 57
199
+ },
200
+ {
201
+ "epoch": 0.13953488372093023,
202
+ "grad_norm": 1.1125946044921875,
203
+ "learning_rate": 4.131759111665349e-05,
204
+ "loss": 3.6843,
205
+ "step": 60
206
+ },
207
+ {
208
+ "epoch": 0.14651162790697675,
209
+ "grad_norm": 0.8303821086883545,
210
+ "learning_rate": 3.6218132209150045e-05,
211
+ "loss": 3.6188,
212
+ "step": 63
213
+ },
214
+ {
215
+ "epoch": 0.14651162790697675,
216
+ "eval_loss": 3.723705768585205,
217
+ "eval_runtime": 10.3865,
218
+ "eval_samples_per_second": 69.706,
219
+ "eval_steps_per_second": 8.761,
220
+ "step": 63
221
  }
222
  ],
223
  "logging_steps": 3,
 
237
  "attributes": {}
238
  }
239
  },
240
+ "total_flos": 3950945595555840.0,
241
  "train_batch_size": 8,
242
  "trial_name": null,
243
  "trial_params": null