dixedus commited on
Commit
fdddadb
·
verified ·
1 Parent(s): 64e07fa

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:fa3490212461544586d69e95fe1e80fe7f5e2f9e0d34533c9a3dedc22b8fe54a
3
  size 34793120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1eecd25559c9189c8612de06e403e95edc7b91bb1570d780cb66259b876a5902
3
  size 34793120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dca9618063d1b54b36b7416f9cf454d8a8f7f5c9f43b28fc00252cb8b1dd2601
3
  size 18132116
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d512dd2ac705c75c747ff69579fc5045a258495d0bc226e232574fce800ccdb2
3
  size 18132116
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4b950c9eb0145b7f442f50792da98376361b51cf8743ae05f4d082235883412a
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d9412651d3546e8955cfba636a91b429e14260cf96ea084a0944945e5f2ed03
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9776c8df8be516beee92201f32f4a3f5d90539bf47f8ef27e1636cdc132a851e
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec430a8fba90f7f39f74e916eb32712c363a0fd20bb4904251fce0eb82f2b9cf
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": 0.6360424028268551,
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": 40.017,
161
  "eval_steps_per_second": 5.002,
162
  "step": 45
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
163
  }
164
  ],
165
  "logging_steps": 3,
@@ -179,7 +208,7 @@
179
  "attributes": {}
180
  }
181
  },
182
- "total_flos": 5721034221158400.0,
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": 0.7632508833922261,
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": 40.017,
161
  "eval_steps_per_second": 5.002,
162
  "step": 45
163
+ },
164
+ {
165
+ "epoch": 0.6784452296819788,
166
+ "grad_norm": 0.06218775361776352,
167
+ "learning_rate": 3.104804738999169e-05,
168
+ "loss": 2.4641,
169
+ "step": 48
170
+ },
171
+ {
172
+ "epoch": 0.7208480565371025,
173
+ "grad_norm": 0.06082496419548988,
174
+ "learning_rate": 2.8479327524001636e-05,
175
+ "loss": 2.55,
176
+ "step": 51
177
+ },
178
+ {
179
+ "epoch": 0.7632508833922261,
180
+ "grad_norm": 0.06064057722687721,
181
+ "learning_rate": 2.587248741756253e-05,
182
+ "loss": 2.5901,
183
+ "step": 54
184
+ },
185
+ {
186
+ "epoch": 0.7632508833922261,
187
+ "eval_loss": 2.362664222717285,
188
+ "eval_runtime": 2.9987,
189
+ "eval_samples_per_second": 40.017,
190
+ "eval_steps_per_second": 5.002,
191
+ "step": 54
192
  }
193
  ],
194
  "logging_steps": 3,
 
208
  "attributes": {}
209
  }
210
  },
211
+ "total_flos": 6865241065390080.0,
212
  "train_batch_size": 8,
213
  "trial_name": null,
214
  "trial_params": null