ramdhanfirdaus commited on
Commit
1063438
1 Parent(s): d00e5ee

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 sha256:4d7d3aba22fd4cfa6a77698459e5f12f156e7989aed5b09faa1cdfa325fcd3a3
3
  size 75507072
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f3b8a38927f75fb0488636f9cdd51fbf72ccaac17ff7c90be7ea1d244ed362e
3
  size 75507072
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:417c10ad7cd1ae9f5432d07461fdda13d193c9e728837e6c09a6eb4b5f596c4e
3
  size 151034501
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:867b549f0287dc4dfde3f2c3d00c5fcb9f785f32a68abecaaf53d0c8e8125ace
3
  size 151034501
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:81f772d2be476ed499d3adff3dd01a0e9933eda633f45a1ea12cfee2a685e066
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b034800e9487036f2e301886f1054c3719470d52002941e9badca1aa571e1e52
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": 1.318053960800171,
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": 15.025,
246
  "eval_steps_per_second": 1.88,
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": 5.5122962977871155e+17,
255
  "trial_name": null,
256
  "trial_params": null
257
  }
 
1
  {
2
+ "best_metric": 1.3063520193099976,
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": 15.025,
246
  "eval_steps_per_second": 1.88,
247
  "step": 1700
248
+ },
249
+ {
250
+ "epoch": 1.31,
251
+ "learning_rate": 0.0002,
252
+ "loss": 1.2967,
253
+ "step": 1800
254
+ },
255
+ {
256
+ "epoch": 1.31,
257
+ "eval_loss": 1.3063520193099976,
258
+ "eval_runtime": 417.5913,
259
+ "eval_samples_per_second": 15.024,
260
+ "eval_steps_per_second": 1.88,
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": 5.83614412193151e+17,
269
  "trial_name": null,
270
  "trial_params": null
271
  }