abhishekyo/finetune5

README.md

@@ -18,12 +18,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [codellama/CodeLlama-7b-hf](https://huggingface.co/codellama/CodeLlama-7b-hf) on the None dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 0.5051
-- eval_runtime: 12.8039
-- eval_samples_per_second: 1.796
-- eval_steps_per_second: 0.469
-- epoch: 1.32
-- step: 60
+- eval_loss: 0.3227
+- eval_runtime: 12.4338
+- eval_samples_per_second: 1.85
+- eval_steps_per_second: 0.483
+- epoch: 2.21
+- step: 100
 
 ## Model description
 
@@ -51,7 +51,7 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_ratio: 0.03
-- num_epochs: 10
+- num_epochs: 20
 - mixed_precision_training: Native AMP
 
 ### Framework versions

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:955a06c6b6b9cb1b960cc4fdded07b1a7a3046c21f8fc860786ad66a107225e7
+oid sha256:5c24dbaa16528eab5ff42e8df1d29f44a9f6d9aa9987e9d68d9617633cf511ef
 size 1116277688

runs/Mar31_10-57-50_a46d5d018463/events.out.tfevents.1711882680.a46d5d018463.568.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74a6796538a5c2277839d2313d1b4deb954e3a044b6c5ca8def5c90b390c71ad
-size 5868
+oid sha256:c9780b1c4ab72db70f7c05bbbd77fa4386389b777656a15e4507a402d2a78df4
+size 6548