rizkyjun commited on
Commit
8834fbe
1 Parent(s): 44a5c51

Training in progress, step 1800, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8ebe09c52a3f04365975892320a186aa239c700677b4d63769c678493ae9e292
3
  size 9444296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b8a471ab082628b3387c41278fe0d2a1f9c10efe0d3eb29d1ad65535e4126f7
3
  size 9444296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dd60fd7ae2ede17c16bf972d0976f1d8d156f3be75031330a456cce6bcc23fa5
3
  size 18902665
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:888d94c2bbcad2ba7ece735e3ae6ec89f53ce1e514c011225591dbbfc086021a
3
  size 18902665
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4c638f15cd58032f947d87dcc068e20509a398cb8780976d061ac887a6986b8a
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75ff2b6345961e3defe7acb1f921dae5616ba7afff13dd0bf10bb569ed4bc334
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0410ad60e6d0138b921a03b0a3e367fd27c6ab07cb9a5006fcb66ea8e5bbacc4
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0e0a1736a46fd1627af3c246e44261aaac909256abbd413b5ee5c968f6b2d8e
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 2.2586843967437744,
3
- "best_model_checkpoint": "./outputs/checkpoint-1700",
4
- "epoch": 1.238615664845173,
5
  "eval_steps": 100,
6
- "global_step": 1700,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -245,13 +245,27 @@
245
  "eval_samples_per_second": 30.298,
246
  "eval_steps_per_second": 3.791,
247
  "step": 1700
 
 
 
 
 
 
 
 
 
 
 
 
 
 
248
  }
249
  ],
250
  "logging_steps": 100,
251
  "max_steps": 4116,
252
  "num_train_epochs": 3,
253
  "save_steps": 100,
254
- "total_flos": 4.969767169124352e+16,
255
  "trial_name": null,
256
  "trial_params": null
257
  }
 
1
  {
2
+ "best_metric": 2.2427449226379395,
3
+ "best_model_checkpoint": "./outputs/checkpoint-1800",
4
+ "epoch": 1.3114754098360657,
5
  "eval_steps": 100,
6
+ "global_step": 1800,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
245
  "eval_samples_per_second": 30.298,
246
  "eval_steps_per_second": 3.791,
247
  "step": 1700
248
+ },
249
+ {
250
+ "epoch": 1.31,
251
+ "learning_rate": 0.0002,
252
+ "loss": 2.2154,
253
+ "step": 1800
254
+ },
255
+ {
256
+ "epoch": 1.31,
257
+ "eval_loss": 2.2427449226379395,
258
+ "eval_runtime": 207.0755,
259
+ "eval_samples_per_second": 30.298,
260
+ "eval_steps_per_second": 3.791,
261
+ "step": 1800
262
  }
263
  ],
264
  "logging_steps": 100,
265
  "max_steps": 4116,
266
  "num_train_epochs": 3,
267
  "save_steps": 100,
268
+ "total_flos": 5.260717969532928e+16,
269
  "trial_name": null,
270
  "trial_params": null
271
  }