Evan-Lin commited on
Commit
c0156a0
1 Parent(s): c06482e

Evan-Lin/SFT

Browse files
README.md CHANGED
@@ -44,9 +44,9 @@ The following hyperparameters were used during training:
44
  - total_train_batch_size: 64
45
  - total_eval_batch_size: 8
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
- - lr_scheduler_type: constant_with_warmup
48
- - lr_scheduler_warmup_steps: 20
49
- - training_steps: 200
50
 
51
  ### Training results
52
 
 
44
  - total_train_batch_size: 64
45
  - total_eval_batch_size: 8
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
+ - lr_scheduler_type: cosine
48
+ - lr_scheduler_warmup_steps: 50
49
+ - training_steps: 1000
50
 
51
  ### Training results
52
 
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:01bbaeb975b0f1a9880b7a59173cd753d490371c9a9c018365b385905361d89a
3
  size 8405600
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6d92e15fc80e8cd9289751c5d6786717db9a7b8bb36fcae0e4ee3b69d609ff4
3
  size 8405600
final_checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:01bbaeb975b0f1a9880b7a59173cd753d490371c9a9c018365b385905361d89a
3
  size 8405600
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6d92e15fc80e8cd9289751c5d6786717db9a7b8bb36fcae0e4ee3b69d609ff4
3
  size 8405600
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:449d687fb61c8503ba07652bd0f6b75d1c9329f1809872d36d5d09b2e02c5bf2
3
  size 4728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd248ee3eb611de96b2bb4a54e27675b420986b682853dc121f4d2028d5c3f9b
3
  size 4728