update model card README.md

README.md

@@ -4,10 +4,12 @@ tags:
 - generated_from_trainer
 datasets:
 - glue
+metrics:
+- accuracy
+- f1
 model-index:
 - name: Llama-2-7b-hf-finetuned-mrpc
   results: []
-library_name: peft
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -16,6 +18,10 @@ should probably proofread and complete it, then remove this comment. -->
 # Llama-2-7b-hf-finetuned-mrpc
 
 This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) on the glue dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4716
+- Accuracy: 0.7672
+- F1: 0.8403
 
 ## Model description
 
@@ -31,38 +37,35 @@ More information needed
 
 ## Training procedure
 
-
-The following `bitsandbytes` quantization config was used during training:
-- load_in_8bit: True
-- load_in_4bit: False
-- llm_int8_threshold: 6.0
-- llm_int8_skip_modules: None
-- llm_int8_enable_fp32_cpu_offload: False
-- llm_int8_has_fp16_weight: False
-- bnb_4bit_quant_type: fp4
-- bnb_4bit_use_double_quant: False
-- bnb_4bit_compute_dtype: float32
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0001
-- train_batch_size: 2
-- eval_batch_size: 2
+- train_batch_size: 16
+- eval_batch_size: 16
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 1
+- num_epochs: 10
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1  |
-|:-------------:|:-----:|:----:|:---------------:|:--------:|:---:|
-| No log        | 1.0   | 19   | 0.5879          | 0.75     | 0.8 |
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
+| No log        | 1.0   | 230  | 0.6045          | 0.7206   | 0.8155 |
+| No log        | 2.0   | 460  | 0.6488          | 0.6912   | 0.8158 |
+| 0.6326        | 3.0   | 690  | 0.5236          | 0.7279   | 0.8235 |
+| 0.6326        | 4.0   | 920  | 0.5273          | 0.7255   | 0.8282 |
+| 0.5602        | 5.0   | 1150 | 0.5246          | 0.7402   | 0.8044 |
+| 0.5602        | 6.0   | 1380 | 0.4893          | 0.75     | 0.8311 |
+| 0.5139        | 7.0   | 1610 | 0.4884          | 0.7623   | 0.8289 |
+| 0.5139        | 8.0   | 1840 | 0.4989          | 0.7402   | 0.8307 |
+| 0.4754        | 9.0   | 2070 | 0.4732          | 0.7745   | 0.8435 |
+| 0.4754        | 10.0  | 2300 | 0.4716          | 0.7672   | 0.8403 |
 
 
 ### Framework versions
 
-- PEFT 0.4.0
 - Transformers 4.31.0
 - Pytorch 2.0.1+cu118
 - Datasets 2.14.5