DuongTrongChi commited on
Commit
9437f05
1 Parent(s): ef4f15d

Training in progress, step 36, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:92ec7b0d148cabae94bf355a3171875f492bcba9a4ba1e447dca12c104746eef
3
  size 100198584
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c4c2c5b373f6a50d462b25c2a377562f91b4389f0e2d101d2feb433346495d8
3
  size 100198584
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d0c1c682e6e5a5603c0576b994f13008bef21f4d49721578dc361dc4265d85d4
3
  size 50675156
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9a26df27a852fcc25a43cec6ed5388e796c14c8dee9596a8fd6a85722b9a531
3
  size 50675156
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:af67e9e5c8e6cf58e25d32243548a1daefe99b687ecc48520798924fe992214b
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc45c09e66fd942f81d3e1a2a005793e3b66657aac967cab369d222230d52fd0
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": 0.09602194787379972,
5
  "eval_steps": 500,
6
- "global_step": 35,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -252,6 +252,13 @@
252
  "learning_rate": 7e-05,
253
  "loss": 1.4445,
254
  "step": 35
 
 
 
 
 
 
 
255
  }
256
  ],
257
  "logging_steps": 1,
@@ -271,7 +278,7 @@
271
  "attributes": {}
272
  }
273
  },
274
- "total_flos": 9.98748058276823e+16,
275
  "train_batch_size": 16,
276
  "trial_name": null,
277
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.09876543209876543,
5
  "eval_steps": 500,
6
+ "global_step": 36,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
252
  "learning_rate": 7e-05,
253
  "loss": 1.4445,
254
  "step": 35
255
+ },
256
+ {
257
+ "epoch": 0.09876543209876543,
258
+ "grad_norm": 0.3918333351612091,
259
+ "learning_rate": 7.2e-05,
260
+ "loss": 1.3956,
261
+ "step": 36
262
  }
263
  ],
264
  "logging_steps": 1,
 
278
  "attributes": {}
279
  }
280
  },
281
+ "total_flos": 1.029250509239255e+17,
282
  "train_batch_size": 16,
283
  "trial_name": null,
284
  "trial_params": null