lovellmnot
/

Llama-3-8B-sft-lora-mydata3prompt-20epoch

Generated from Trainer

Model card Files Files and versions Community

lovellmnot commited on Sep 14

Commit

3535d0c

•

1 Parent(s): e42f630

End of training

Files changed (2) hide show

README.md +4 -4
training_args.bin +2 -2

README.md CHANGED Viewed

@@ -37,13 +37,13 @@ More information needed
 ### Training hyperparameters
 The following hyperparameters were used during training:
-- learning_rate: 0.0002
-- train_batch_size: 2
-- eval_batch_size: 2
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
-- num_epochs: 40
 ### Training results

 ### Training hyperparameters
 The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 1
+- eval_batch_size: 1
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
+- num_epochs: 20
 ### Training results

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8d48a5194204384fdedf4c20625a51ce73c14424f353b51057386bee169d7e1
-size 5560

 version https://git-lfs.github.com/spec/v1
+oid sha256:28e465ed833d4ab2a6c73c5717ec002d5f01e842efa679fe23202598377a1e56
+size 6200