rizkyjun commited on
Commit
29e55e9
1 Parent(s): 80ffbcd

Training in progress, step 1900, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1b8a471ab082628b3387c41278fe0d2a1f9c10efe0d3eb29d1ad65535e4126f7
3
  size 9444296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4eb21b3d7a25488c2576bd971ed67a911c0d9b7b89195c14d2179bf6b7ceb743
3
  size 9444296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:888d94c2bbcad2ba7ece735e3ae6ec89f53ce1e514c011225591dbbfc086021a
3
  size 18902665
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d27667366c490ce36f7af5af3a82f5070d24e1851be4ddb43c9e5bb9cd172c84
3
  size 18902665
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:75ff2b6345961e3defe7acb1f921dae5616ba7afff13dd0bf10bb569ed4bc334
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41425018b484575f28a5ea543894d6ee6cdc9e01846d0ddaa36b7e88cc98504f
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c0e0a1736a46fd1627af3c246e44261aaac909256abbd413b5ee5c968f6b2d8e
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2d4b4cadcabd3e17adcc39c43d8312038a1f5c7f53125f288ba4de5ed25396b
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
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,
@@ -259,13 +259,27 @@
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
  }
 
1
  {
2
+ "best_metric": 2.229428291320801,
3
+ "best_model_checkpoint": "./outputs/checkpoint-1900",
4
+ "epoch": 1.384335154826958,
5
  "eval_steps": 100,
6
+ "global_step": 1900,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
259
  "eval_samples_per_second": 30.298,
260
  "eval_steps_per_second": 3.791,
261
  "step": 1800
262
+ },
263
+ {
264
+ "epoch": 1.38,
265
+ "learning_rate": 0.0002,
266
+ "loss": 2.1995,
267
+ "step": 1900
268
+ },
269
+ {
270
+ "epoch": 1.38,
271
+ "eval_loss": 2.229428291320801,
272
+ "eval_runtime": 207.3553,
273
+ "eval_samples_per_second": 30.257,
274
+ "eval_steps_per_second": 3.786,
275
+ "step": 1900
276
  }
277
  ],
278
  "logging_steps": 100,
279
  "max_steps": 4116,
280
  "num_train_epochs": 3,
281
  "save_steps": 100,
282
+ "total_flos": 5.552186242885632e+16,
283
  "trial_name": null,
284
  "trial_params": null
285
  }