FT_llma7b_4bits_3column

README.md

@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [meta-llama/Llama-2-7b-chat-hf](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.8680
+- Loss: 2.0542
 
 ## Model description
 
@@ -34,7 +34,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0002
+- learning_rate: 2e-05
 - train_batch_size: 2
 - eval_batch_size: 16
 - seed: 42
@@ -50,7 +50,7 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.6909        | 9.84  | 300  | 2.8680          |
+| 2.1604        | 9.92  | 310  | 2.0542          |
 
 
 ### Framework versions

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6db206cf6ddbe84df70f248246572ca4e7faa4387dbdba070cf46b3f452936a0
+oid sha256:11f5b5aeac760f904e680a9e774aaf1c0d360783ec205c1e4c37d8b10f54845d
 size 4856