andstor/bigcode-starcoder2-7b-unit-test-ia3

1---2license: bigcode-openrail-m3library_name: peft4tags:5- generated_from_trainer6datasets:7- andstor/methods2test_small8metrics:9- accuracy10base_model: bigcode/starcoder2-7b11model-index:12- name: output13  results:14  - task:15      type: text-generation16      name: Causal Language Modeling17    dataset:18      name: andstor/methods2test_small fm+fc+c+m+f+t+tc19      type: andstor/methods2test_small20      args: fm+fc+c+m+f+t+tc21    metrics:22    - type: accuracy23      value: 0.720247285351287324      name: Accuracy25---26 27<!-- This model card has been generated automatically according to the information the Trainer had access to. You28should probably proofread and complete it, then remove this comment. -->29 30[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/andstor/methods2test_small/runs/relylhr4)31# output32 33This model is a fine-tuned version of [bigcode/starcoder2-7b](https://huggingface.co/bigcode/starcoder2-7b) on the andstor/methods2test_small fm+fc+c+m+f+t+tc dataset.34It achieves the following results on the evaluation set:35- Loss: 0.701536- Accuracy: 0.720237 38## Model description39 40More information needed41 42## Intended uses & limitations43 44More information needed45 46## Training and evaluation data47 48More information needed49 50## Training procedure51 52### Training hyperparameters53 54The following hyperparameters were used during training:55- learning_rate: 0.000356- train_batch_size: 157- eval_batch_size: 158- seed: 4259- distributed_type: multi-GPU60- num_devices: 261- gradient_accumulation_steps: 862- total_train_batch_size: 1663- total_eval_batch_size: 264- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-0865- lr_scheduler_type: linear66- lr_scheduler_warmup_ratio: 0.167- num_epochs: 3.068 69### Training results70 71 72 73### Framework versions74 75- PEFT 0.10.076- Transformers 4.41.0.dev077- Pytorch 2.2.1+cu11878- Datasets 2.17.179- Tokenizers 0.19.1