End of training

README.md

@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [baffo32/decapoda-research-llama-7B-hf](https://huggingface.co/baffo32/decapoda-research-llama-7B-hf) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0403
+- Loss: 0.0373
 
 ## Model description
 
@@ -43,14 +43,23 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 2
-- training_steps: 45
+- training_steps: 400
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.1299        | 0.36  | 40   | 0.0403          |
+| 0.1276        | 0.36  | 40   | 0.0407          |
+| 0.0366        | 0.72  | 80   | 0.0344          |
+| 0.0279        | 1.08  | 120  | 0.0297          |
+| 0.0203        | 1.44  | 160  | 0.0276          |
+| 0.0217        | 1.8   | 200  | 0.0274          |
+| 0.0165        | 2.16  | 240  | 0.0319          |
+| 0.0106        | 2.52  | 280  | 0.0304          |
+| 0.0113        | 2.88  | 320  | 0.0300          |
+| 0.0073        | 3.24  | 360  | 0.0357          |
+| 0.0047        | 3.6   | 400  | 0.0373          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d5c4e5e7178830e1a254fba54e8100ab46aa7c7c8cc3971166431baa40de5a9
+oid sha256:b585713b586dc6b830835ec174926f10f4266d98924a491e70d1a55578dab9b7
 size 268528394

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:193ff798a817c64bb316ea92a84a22776cebf460f0c6b05e3976df55bb179571
+oid sha256:e9911474c92fbe6187e9608bb876db4e73338580b1070eb54387b6a8d22e394d
 size 4984