| { | |
| "os": "Linux-5.4.0-147-generic-x86_64-with-glibc2.31", | |
| "python": "3.9.16", | |
| "heartbeatAt": "2023-07-25T19:29:32.638362", | |
| "startedAt": "2023-07-25T19:29:32.561287", | |
| "docker": null, | |
| "gpu": "NVIDIA A100-SXM4-80GB", | |
| "gpu_count": 8, | |
| "cpu_count": 64, | |
| "cuda": null, | |
| "args": [ | |
| "--local_rank=0", | |
| "--train_datasets", | |
| "bt", | |
| "--model_name_or_path", | |
| "cerebras/btlm-3b-8k-base", | |
| "--max_length", | |
| "8092", | |
| "--trust_remote_code", | |
| "True", | |
| "--epochs", | |
| "3", | |
| "--per_device_train_batch_size", | |
| "2", | |
| "--per_device_eval_batch_size", | |
| "82", | |
| "--gradient_accumulation_steps", | |
| "1", | |
| "--gradient_checkpointing", | |
| "--learning_rate", | |
| "2e-5", | |
| "--lr_scheduler_type", | |
| "cosine", | |
| "--num_warmup_steps", | |
| "20", | |
| "--weight_decay", | |
| "0.0", | |
| "--seed", | |
| "42", | |
| "--output_dir", | |
| "/home/paperspace/safe-rlhf/output/sft", | |
| "--log_type", | |
| "wandb", | |
| "--log_project", | |
| "BT-Training", | |
| "--zero_stage", | |
| "3", | |
| "--bf16", | |
| "True", | |
| "--tf32", | |
| "True" | |
| ], | |
| "state": "running", | |
| "program": "-m safe_rlhf.finetune.__main__", | |
| "git": { | |
| "remote": "https://github.com/robertalanm/safe-rlhf", | |
| "commit": "4b5266714a6d66aea11ec473fe29b6b57c48e40a" | |
| }, | |
| "email": null, | |
| "root": "/home/paperspace/safe-rlhf", | |
| "host": "psiohuej6", | |
| "username": "paperspace", | |
| "executable": "/usr/bin/python3.9" | |
| } | |