| --- |
| license: bigscience-openrail-m |
| --- |
| ``` |
| { |
| "cache_dir": "/leonardo_work/EUHPC_E03_068/.cache", |
| "method": "orpo", |
| "dataset": "autoredteam", |
| "model": "bigcode/starcoder2-3b", |
| "tokenizer": "TechxGenus/starcoder2-7b-instruct", |
| "lr": 0.01, |
| "train_batch_size": 5, |
| "eval_batch_size": 5, |
| "num_epochs": 3, |
| "seed": 42, |
| "eval_only": false, |
| "evaluation_size": 2000, |
| "checkpoint_path": null, |
| "experiment_name": "starcoder2_3b-autoredteam_v2-train", |
| "experiment_group": "results", |
| "reference_model": null, |
| "context_length": 1024, |
| "train_summarization": "", |
| "dpo_beta": 0.1, |
| "orpo_beta": 0.1, |
| "kl_coef": 0.0, |
| "reward_model": "", |
| "bestofn_size": 4, |
| "train_reward_model": "" |
| } |
| ``` |
