Nexspear commited on
Commit
54370dd
·
verified ·
1 Parent(s): d92b6b3

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:e1d2fc4d3df9df01c720fcacdfd92725712682b41d65d31ac8cc64b5ab708507
3
  size 639691872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c5e7c25b9f2e2a8f985345337e7d72db0f1d30338b28da39865e71726a1df09
3
  size 639691872
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9241cb610f1cb997bc64a1301c78e00555be40838611f19a6d5c9cfe68789133
3
  size 325339796
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2b4158ad1650d245168b8ab8f06b4cd07ca4909f2a7f50fbad45faeb737d5b3
3
  size 325339796
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:35c65e0c7aaf9f01146531ad13d47f064b46f31d8983cb34ba2a9b2a0ef837af
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f31d9f4509e8f2c0004502cbfb3b3746639a21cd95c7a49387ee81d613ac30a3
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": 0.10031347962382445,
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": 13.494,
171
  "eval_steps_per_second": 1.687,
172
  "step": 40
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
173
  }
174
  ],
175
  "logging_steps": 3,
@@ -189,7 +211,7 @@
189
  "attributes": {}
190
  }
191
  },
192
- "total_flos": 5.4167146070016e+16,
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": 0.11285266457680251,
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": 13.494,
171
  "eval_steps_per_second": 1.687,
172
  "step": 40
173
+ },
174
+ {
175
+ "epoch": 0.10532915360501567,
176
+ "grad_norm": 0.34911882877349854,
177
+ "learning_rate": 9.549150281252633e-06,
178
+ "loss": 1.5553,
179
+ "step": 42
180
+ },
181
+ {
182
+ "epoch": 0.11285266457680251,
183
+ "grad_norm": 0.38676726818084717,
184
+ "learning_rate": 3.8060233744356633e-06,
185
+ "loss": 1.5355,
186
+ "step": 45
187
+ },
188
+ {
189
+ "epoch": 0.11285266457680251,
190
+ "eval_loss": 1.5492891073226929,
191
+ "eval_runtime": 49.8004,
192
+ "eval_samples_per_second": 13.494,
193
+ "eval_steps_per_second": 1.687,
194
+ "step": 45
195
  }
196
  ],
197
  "logging_steps": 3,
 
211
  "attributes": {}
212
  }
213
  },
214
+ "total_flos": 6.0895984091136e+16,
215
  "train_batch_size": 8,
216
  "trial_name": null,
217
  "trial_params": null