Nexspear commited on
Commit
330a5d3
·
verified ·
1 Parent(s): 48cf2a7

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 sha256:4559bf21b4aea99e80e365d719b68782afa1236e4b08fa4f4a0d5666cb88932b
3
  size 313820248
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d75dcfe6f7c9c47b4f2a40b78e53ebb5a275bdadf7224ccf72c4c8d5ce4348df
3
  size 313820248
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2cb208c27f691cedf409cc53818467d6c29ed3e04cce09b6ec363ccef13da076
3
  size 159641092
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e40a56b2b621478da56b1bd3359d9a4afb25e3dda81c3bca2f75d0960db6574
3
  size 159641092
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:028ca79dfc402208a31d482c5d1658cbaaeb711f53c60e657224662cb1f3f0f6
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd984f4b4de98886636a6a9007958c72c44e7d3e141c18b4d25bda2d131f83c3
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": 0.013752793536187038,
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": 28.496,
171
  "eval_steps_per_second": 3.566,
172
  "step": 40
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
173
  }
174
  ],
175
  "logging_steps": 3,
@@ -189,7 +211,7 @@
189
  "attributes": {}
190
  }
191
  },
192
- "total_flos": 1.620310235283456e+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": 0.015471892728210418,
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": 28.496,
171
  "eval_steps_per_second": 3.566,
172
  "step": 40
173
+ },
174
+ {
175
+ "epoch": 0.01444043321299639,
176
+ "grad_norm": 2.277637004852295,
177
+ "learning_rate": 9.549150281252633e-06,
178
+ "loss": 0.6284,
179
+ "step": 42
180
+ },
181
+ {
182
+ "epoch": 0.015471892728210418,
183
+ "grad_norm": 2.8201003074645996,
184
+ "learning_rate": 3.8060233744356633e-06,
185
+ "loss": 0.5752,
186
+ "step": 45
187
+ },
188
+ {
189
+ "epoch": 0.015471892728210418,
190
+ "eval_loss": 0.5873016119003296,
191
+ "eval_runtime": 171.9639,
192
+ "eval_samples_per_second": 28.489,
193
+ "eval_steps_per_second": 3.565,
194
+ "step": 45
195
  }
196
  ],
197
  "logging_steps": 3,
 
211
  "attributes": {}
212
  }
213
  },
214
+ "total_flos": 1.822849014693888e+16,
215
  "train_batch_size": 8,
216
  "trial_name": null,
217
  "trial_params": null