leixa commited on
Commit
16b8ee7
1 Parent(s): de05933

Training in progress, step 45, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:76639e4694cfb2569e146070f4b5283370e8d262a9d5a6c74337ddc3b59fb160
3
  size 191968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76cad93200b1d2f1056cbc80dd1a5d8a1308d5448651b940defa64cc9d69e84b
3
  size 191968
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0e0be97c07919e60906f8df3d228b0735240a1fc9a884efbf4bdb40e8a25ae81
3
  size 253144
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8fdc0d41caeb1ce4c431f7a0478b7be4491c4ae3a3d170e1762030c992e41e6
3
  size 253144
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f6f8a3071cc811ae52946b6ee778ddcd861ec51849b9667e2fa077e5381edaa2
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17da4825ec19548ea401fee5382ca332ce383520f8a3ede369ab2beed6bc9856
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bd18e5325bf99a4b662a5314e5f491b65903ffc83b0317f63835d8305a50591e
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ec0bb6efeeb25000ef7426abb9d88265daa212fa2a170e1fb3f58996efa27f6
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": 0.02807510089489384,
5
  "eval_steps": 5,
6
- "global_step": 40,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -170,6 +170,28 @@
170
  "eval_samples_per_second": 458.39,
171
  "eval_steps_per_second": 57.299,
172
  "step": 40
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
173
  }
174
  ],
175
  "logging_steps": 3,
@@ -189,7 +211,7 @@
189
  "attributes": {}
190
  }
191
  },
192
- "total_flos": 4629352415232.0,
193
  "train_batch_size": 8,
194
  "trial_name": null,
195
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.03158448850675557,
5
  "eval_steps": 5,
6
+ "global_step": 45,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
170
  "eval_samples_per_second": 458.39,
171
  "eval_steps_per_second": 57.299,
172
  "step": 40
173
+ },
174
+ {
175
+ "epoch": 0.029478855939638532,
176
+ "grad_norm": 0.18757128715515137,
177
+ "learning_rate": 9.549150281252633e-06,
178
+ "loss": 10.3599,
179
+ "step": 42
180
+ },
181
+ {
182
+ "epoch": 0.03158448850675557,
183
+ "grad_norm": 0.23149600625038147,
184
+ "learning_rate": 3.8060233744356633e-06,
185
+ "loss": 10.3569,
186
+ "step": 45
187
+ },
188
+ {
189
+ "epoch": 0.03158448850675557,
190
+ "eval_loss": 10.358962059020996,
191
+ "eval_runtime": 5.2602,
192
+ "eval_samples_per_second": 456.26,
193
+ "eval_steps_per_second": 57.033,
194
+ "step": 45
195
  }
196
  ],
197
  "logging_steps": 3,
 
211
  "attributes": {}
212
  }
213
  },
214
+ "total_flos": 5270768713728.0,
215
  "train_batch_size": 8,
216
  "trial_name": null,
217
  "trial_params": null