End of training

README.md

@@ -66,7 +66,7 @@ lora_model_dir: null
 lora_r: 4
 lora_target_linear: true
 lr_scheduler: cosine
-max_steps: 5
+max_steps: 7
 micro_batch_size: 1
 mlflow_experiment_name: /tmp/57a9c77b8cccbc26_train_data.json
 model_type: AutoModelForCausalLM
@@ -103,7 +103,7 @@ xformers_attention: null
 
 This model is a fine-tuned version of [NousResearch/Hermes-2-Pro-Llama-3-8B](https://huggingface.co/NousResearch/Hermes-2-Pro-Llama-3-8B) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 3.6266
+- Loss: 3.5717
 
 ## Model description
 
@@ -131,15 +131,16 @@ The following hyperparameters were used during training:
 - optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_steps: 10
-- training_steps: 5
+- training_steps: 7
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
 | 3.7463        | 0.0006 | 1    | 3.6378          |
-| 3.1519        | 0.0012 | 2    | 3.6368          |
-| 2.8676        | 0.0024 | 4    | 3.6266          |
+| 3.1519        | 0.0012 | 2    | 3.6369          |
+| 2.8665        | 0.0024 | 4    | 3.6247          |
+| 3.8022        | 0.0037 | 6    | 3.5717          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d5490e6d26677f227f8668442bc86df80d30a1c6654659fe5939f67152cf5ec
+oid sha256:4dffd45ec49ca61d4ac75475d1924718dc6512652ba53ce072798af922f2100b
 size 42104138