Model save

README.md

@@ -1,19 +1,61 @@
-This directory includes a few sample datasets to get you started.
+---
+base_model: meta-llama/Meta-Llama-3-8B-Instruct
+datasets:
+- generator
+library_name: peft
+license: llama3
+tags:
+- trl
+- sft
+- generated_from_trainer
+model-index:
+- name: sample_data
+  results: []
+---
 
-*   `california_housing_data*.csv` is California housing data from the 1990 US
-    Census; more information is available at:
-    https://developers.google.com/machine-learning/crash-course/california-housing-data-description
+<!-- 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. -->
 
-*   `mnist_*.csv` is a small sample of the
-    [MNIST database](https://en.wikipedia.org/wiki/MNIST_database), which is
-    described at: http://yann.lecun.com/exdb/mnist/
+# sample_data
 
-*   `anscombe.json` contains a copy of
-    [Anscombe's quartet](https://en.wikipedia.org/wiki/Anscombe%27s_quartet); it
-    was originally described in
+This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the generator dataset.
 
-    Anscombe, F. J. (1973). 'Graphs in Statistical Analysis'. American
-    Statistician. 27 (1): 17-21. JSTOR 2682899.
+## Model description
 
-    and our copy was prepared by the
-    [vega_datasets library](https://github.com/altair-viz/vega_datasets/blob/4f67bdaad10f45e3549984e17e1b3088c731503d/vega_datasets/_data/anscombe.json).
+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: 0.0002
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 4
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: constant
+- lr_scheduler_warmup_ratio: 0.03
+- num_epochs: 4
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.7.2.dev0
+- Transformers 4.36.2
+- Pytorch 2.1.2+cu121
+- Datasets 2.16.1
+- Tokenizers 0.15.2