End of training

README.md

@@ -6,11 +6,6 @@ tags:
 - base_model:adapter:meta-llama/Llama-3.1-8B-Instruct
 - lora
 - transformers
-metrics:
-- accuracy
-- precision
-- recall
-- f1
 model-index:
 - name: llama3_ft_section_classifier
   results: []
@@ -23,11 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [meta-llama/Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 985.5
-- Accuracy: 0.3939
-- Precision: 0.3631
-- Recall: 0.3939
-- F1: 0.3481
+- Loss: 2.4151
 
 ## Model description
 
@@ -46,21 +37,24 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 2e-05
+- learning_rate: 0.0002
 - train_batch_size: 4
 - eval_batch_size: 4
 - seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 32
 - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
-- lr_scheduler_type: linear
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
 - num_epochs: 3
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1     |
-|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
-| No log        | 1.0   | 66   | 2146.0          | 0.3030   | 0.2749    | 0.3030 | 0.2411 |
-| No log        | 2.0   | 132  | 1056.0          | 0.3788   | 0.3535    | 0.3788 | 0.3451 |
-| No log        | 3.0   | 198  | 985.5           | 0.3939   | 0.3631    | 0.3939 | 0.3481 |
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| No log        | 1.0   | 10   | 3.2325          |
+| No log        | 2.0   | 20   | 2.4390          |
+| No log        | 3.0   | 30   | 2.4151          |
 
 
 ### Framework versions