End of training

README.md

@@ -0,0 +1,73 @@
+---
+base_model: keylazy/Llama-2-7b-chat-hf-ark
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- precision
+- recall
+- f1
+model-index:
+- name: Llama-2-7b-chat-hf-ark-ft-2
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# Llama-2-7b-chat-hf-ark-ft-2
+
+This model is a fine-tuned version of [keylazy/Llama-2-7b-chat-hf-ark](https://huggingface.co/keylazy/Llama-2-7b-chat-hf-ark) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5956
+- Accuracy: 0.695
+- Precision: 0.6965
+- Recall: 0.695
+- F1: 0.6946
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 128
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1     |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
+| 0.5159        | 0.5   | 39   | 0.5348          | 0.657    | 0.6674    | 0.657  | 0.6522 |
+| 0.4738        | 1.0   | 78   | 0.5245          | 0.641    | 0.6841    | 0.641  | 0.6201 |
+| 0.3097        | 1.5   | 117  | 0.5485          | 0.67     | 0.6822    | 0.67   | 0.6650 |
+| 0.2708        | 2.0   | 156  | 0.5485          | 0.686    | 0.6988    | 0.686  | 0.6814 |
+| 0.1635        | 2.5   | 195  | 0.5949          | 0.69     | 0.6946    | 0.69   | 0.6885 |
+| 0.1482        | 3.0   | 234  | 0.5956          | 0.695    | 0.6965    | 0.695  | 0.6946 |
+
+
+### Framework versions
+
+- Transformers 4.35.0
+- Pytorch 2.1.0+cu118
+- Datasets 2.14.6
+- Tokenizers 0.14.1