Training in progress, step 800

README.md

@@ -20,12 +20,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the generator dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 1.2890
-- eval_runtime: 164.2332
-- eval_samples_per_second: 0.67
-- eval_steps_per_second: 0.335
-- epoch: 1.2270
-- step: 600
+- eval_loss: 1.4180
+- eval_runtime: 36.1138
+- eval_samples_per_second: 3.24
+- eval_steps_per_second: 0.831
+- epoch: 3.0534
+- step: 800
 
 ## Model description
 
@@ -45,8 +45,8 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0002
-- train_batch_size: 2
-- eval_batch_size: 2
+- train_batch_size: 4
+- eval_batch_size: 4
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: constant

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b2bbedea91e98591925278203fb69f78e479281e6612ab5d674b691d899d7c9
+oid sha256:953bc92ccfbed0a8b53281d0cb39d4a808a9a5d6efbc4b22c9cb7e92ee838b76
 size 2806378968