update model card README.md

README.md

@@ -4,7 +4,6 @@ tags:
 model-index:
 - name: Kaggle-Science-LLM
   results: []
-library_name: peft
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -13,6 +12,8 @@ should probably proofread and complete it, then remove this comment. -->
 # Kaggle-Science-LLM
 
 This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 4.4821
 
 ## Model description
 
@@ -28,17 +29,6 @@ More information needed
 
 ## Training procedure
 
-
-The following `bitsandbytes` quantization config was used during training:
-- load_in_8bit: False
-- load_in_4bit: True
-- 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: nf4
-- bnb_4bit_use_double_quant: True
-- bnb_4bit_compute_dtype: bfloat16
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
@@ -54,9 +44,24 @@ The following hyperparameters were used during training:
 - training_steps: 50
 - label_smoothing_factor: 0.1
 
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 6.6677        | 0.01  | 5    | 6.5120          |
+| 6.4854        | 0.02  | 10   | 6.3479          |
+| 6.2537        | 0.02  | 15   | 6.1641          |
+| 6.0912        | 0.03  | 20   | 5.9550          |
+| 5.8341        | 0.04  | 25   | 5.7246          |
+| 5.6128        | 0.05  | 30   | 5.4776          |
+| 5.3665        | 0.06  | 35   | 5.2728          |
+| 5.1581        | 0.06  | 40   | 5.0129          |
+| 4.9526        | 0.07  | 45   | 4.7501          |
+| 4.6988        | 0.08  | 50   | 4.4821          |
+
+
 ### Framework versions
 
-- PEFT 0.4.0
 - Transformers 4.30.2
 - Pytorch 2.0.0
 - Datasets 2.1.0