End of training

README.md

@@ -14,7 +14,7 @@ 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: 1.6862
+- Loss: 0.3902
 
 ## Model description
 
@@ -34,7 +34,7 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0001
-- train_batch_size: 2
+- train_batch_size: 4
 - eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
@@ -43,6 +43,14 @@ The following hyperparameters were used during training:
 
 ### Training results
 
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.4856        | 0.16  | 200  | 0.4700          |
+| 0.4337        | 0.31  | 400  | 0.4252          |
+| 0.3998        | 0.47  | 600  | 0.4071          |
+| 0.4126        | 0.63  | 800  | 0.3967          |
+| 0.421         | 0.79  | 1000 | 0.3920          |
+| 0.4018        | 0.94  | 1200 | 0.3902          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f325cd540a6ae95d29a28a7c459327baf2e6769bbc1d86b5cef5f0e5fb95c67
+oid sha256:2582831cc00b8514312d372f1b68d1ac0734605609c40099bdd093128a7b730a
 size 134310221

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf5fd62c8ebf42e6ab82b0c298a44608c48b3eef4710b8dde3a9c923157d6b42
+oid sha256:639b7e9e9dc61dfb870a628d7c3c1960c63bedc18e319fcf6cc2e4462d4f387b
 size 4091