dzanbek commited on
Commit
18f7ade
·
verified ·
1 Parent(s): 0eb170f

Training in progress, step 18, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:28b9b9aa72affca8139980ca9d6e4a1ad63e79555e5a7d0f7f7b33b84c42f0b0
3
  size 63592
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d9846385759a2a5e88f2c4e07e62637be12c7073237ac8095ce073c6821388e
3
  size 63592
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b7dbc187c87687f9c6df134a07a065ecd0d9ae12937a7c4ac1e027f947c44fd0
3
  size 132798
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0683757a2eaa5838e75819b3a4a50732b8c96caaae7b333ca35235f5edd5a7f
3
  size 132798
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:20d34cc1fdc9d7e7ca4707ec334fbb4e1f437a55d8bec553d32f5280754aaa57
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:198455311e6594048bcbe13ef81ce44e1f6f9d743257bb540ad0ee07688c1ef3
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:28c50acebbdd320cdbda27b93feb5d91578ce2eb03d7fc0517b7bfffd55baef8
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10e175ebe60f1a6bbd43d635188097fdd53bf710ff976db3f946328fc19cf4ba
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": 0.0005452098205918934,
5
  "eval_steps": 2,
6
- "global_step": 16,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -191,6 +191,28 @@
191
  "eval_samples_per_second": 108.258,
192
  "eval_steps_per_second": 54.134,
193
  "step": 16
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
194
  }
195
  ],
196
  "logging_steps": 1,
@@ -210,7 +232,7 @@
210
  "attributes": {}
211
  }
212
  },
213
- "total_flos": 43517214720.0,
214
  "train_batch_size": 2,
215
  "trial_name": null,
216
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0006133610481658801,
5
  "eval_steps": 2,
6
+ "global_step": 18,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
191
  "eval_samples_per_second": 108.258,
192
  "eval_steps_per_second": 54.134,
193
  "step": 16
194
+ },
195
+ {
196
+ "epoch": 0.0005792854343788867,
197
+ "grad_norm": 2.718780040740967,
198
+ "learning_rate": 2.061073738537635e-05,
199
+ "loss": 44.2053,
200
+ "step": 17
201
+ },
202
+ {
203
+ "epoch": 0.0006133610481658801,
204
+ "grad_norm": 2.361675262451172,
205
+ "learning_rate": 9.549150281252633e-06,
206
+ "loss": 44.2844,
207
+ "step": 18
208
+ },
209
+ {
210
+ "epoch": 0.0006133610481658801,
211
+ "eval_loss": 11.079801559448242,
212
+ "eval_runtime": 114.2329,
213
+ "eval_samples_per_second": 108.174,
214
+ "eval_steps_per_second": 54.091,
215
+ "step": 18
216
  }
217
  ],
218
  "logging_steps": 1,
 
232
  "attributes": {}
233
  }
234
  },
235
+ "total_flos": 49600266240.0,
236
  "train_batch_size": 2,
237
  "trial_name": null,
238
  "trial_params": null