DuongTrongChi commited on
Commit
686c67c
·
verified ·
1 Parent(s): 8636105

Training in progress, step 117, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7bdbb740496dc2a7f3c0f6f02d269d15e42820dee4870aed7c52aa1bfd807fd2
3
  size 73911112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69256420725897d2777e3472b8b18c037e579f62b3b1d7d0c1a1b40cf3b3d224
3
  size 73911112
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:19aea021c17d22587f9f50dc0bd30b3284a28d1ab85db70a8c705c5ef04b8d19
3
  size 37430836
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ecb1bb229381e294dfb9f762c4f5042aa02579f6a20220cb6637ef64eaef8746
3
  size 37430836
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f9741594e204ffb908586b8ab5263be1fd7e41110b9026fc1281a70d1b1b6557
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e162f15ef893cc30ea35baa54f5f07e4f52a56b20ad3f86f86bec4286c2f22e
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": 0.31550068587105623,
5
  "eval_steps": 500,
6
- "global_step": 115,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -812,6 +812,20 @@
812
  "learning_rate": 0.00018863636363636364,
813
  "loss": 1.3138,
814
  "step": 115
 
 
 
 
 
 
 
 
 
 
 
 
 
 
815
  }
816
  ],
817
  "logging_steps": 1,
@@ -831,7 +845,7 @@
831
  "attributes": {}
832
  }
833
  },
834
- "total_flos": 1.4257615970761114e+17,
835
  "train_batch_size": 4,
836
  "trial_name": null,
837
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.32098765432098764,
5
  "eval_steps": 500,
6
+ "global_step": 117,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
812
  "learning_rate": 0.00018863636363636364,
813
  "loss": 1.3138,
814
  "step": 115
815
+ },
816
+ {
817
+ "epoch": 0.31824417009602196,
818
+ "grad_norm": 0.12237361073493958,
819
+ "learning_rate": 0.0001878787878787879,
820
+ "loss": 1.1938,
821
+ "step": 116
822
+ },
823
+ {
824
+ "epoch": 0.32098765432098764,
825
+ "grad_norm": 0.12502606213092804,
826
+ "learning_rate": 0.00018712121212121212,
827
+ "loss": 1.3258,
828
+ "step": 117
829
  }
830
  ],
831
  "logging_steps": 1,
 
845
  "attributes": {}
846
  }
847
  },
848
+ "total_flos": 1.4517602560126157e+17,
849
  "train_batch_size": 4,
850
  "trial_name": null,
851
  "trial_params": null