Nexspear commited on
Commit
715f162
·
verified ·
1 Parent(s): d66e43d

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:b7addb646f632d8b1b4c884bf83af62921e29e3a1f4b3308163fed61febfbc9b
3
  size 156926880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d95cf61bcf97a7b14c86b6b3d755beb14db66be7b08d9b855481c35e2eb5318
3
  size 156926880
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6dc86fcb24167fde7229c2b36d90fc9578d6bc171f732c9ac2c1e9dc6a503c67
3
  size 79968772
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e10090a90915f282f97b1d9d6903fe466da1bc45c5b6c6a33e48611943a8580d
3
  size 79968772
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bb8d896afa577bd1b79700bc2bfee8d915869bd3ba8aaab6ad02f4216eb5a6cd
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c28272720668f2d6fbd8b2b8b2167ebc7cae34855d20b699a9bedf72f6dfe369
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": 0.07518796992481203,
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": 27.883,
171
  "eval_steps_per_second": 6.971,
172
  "step": 40
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
173
  }
174
  ],
175
  "logging_steps": 3,
@@ -189,7 +211,7 @@
189
  "attributes": {}
190
  }
191
  },
192
- "total_flos": 7947318900817920.0,
193
  "train_batch_size": 4,
194
  "trial_name": null,
195
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.08458646616541353,
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": 27.883,
171
  "eval_steps_per_second": 6.971,
172
  "step": 40
173
+ },
174
+ {
175
+ "epoch": 0.07894736842105263,
176
+ "grad_norm": 1.3438414335250854,
177
+ "learning_rate": 9.549150281252633e-06,
178
+ "loss": 1.6063,
179
+ "step": 42
180
+ },
181
+ {
182
+ "epoch": 0.08458646616541353,
183
+ "grad_norm": 1.4435805082321167,
184
+ "learning_rate": 3.8060233744356633e-06,
185
+ "loss": 1.5254,
186
+ "step": 45
187
+ },
188
+ {
189
+ "epoch": 0.08458646616541353,
190
+ "eval_loss": 1.552406907081604,
191
+ "eval_runtime": 16.0663,
192
+ "eval_samples_per_second": 27.885,
193
+ "eval_steps_per_second": 6.971,
194
+ "step": 45
195
  }
196
  ],
197
  "logging_steps": 3,
 
211
  "attributes": {}
212
  }
213
  },
214
+ "total_flos": 8940733763420160.0,
215
  "train_batch_size": 4,
216
  "trial_name": null,
217
  "trial_params": null