47 lines
1.5 KiB
JSON
47 lines
1.5 KiB
JSON
|
{
|
||
|
|
"humaneval": {
|
||
|
|
"pass@1": 0.33804878048780496,
|
||
|
|
"pass@10": 0.4747374093826887
|
||
|
|
},
|
||
|
|
"config": {
|
||
|
|
"prefix": "",
|
||
|
|
"do_sample": true,
|
||
|
|
"temperature": 0.2,
|
||
|
|
"top_k": 0,
|
||
|
|
"top_p": 0.95,
|
||
|
|
"n_samples": 50,
|
||
|
|
"eos": "<|endoftext|>",
|
||
|
|
"seed": 0,
|
||
|
|
"model": "/home/abhinav/src/llama-recipes/llama_7b_evol_codealpaca_sparse/sparse-sft_cerebras_70sp_uniform_llama_lr5e-4_epochs1_gradclipFalse_cosine_nodistillation-/combined/",
|
||
|
|
"modeltype": "causal",
|
||
|
|
"peft_model": null,
|
||
|
|
"revision": null,
|
||
|
|
"use_auth_token": false,
|
||
|
|
"trust_remote_code": false,
|
||
|
|
"tasks": "humaneval",
|
||
|
|
"instruction_tokens": null,
|
||
|
|
"batch_size": 32,
|
||
|
|
"max_length_generation": 512,
|
||
|
|
"precision": "fp16",
|
||
|
|
"load_in_8bit": false,
|
||
|
|
"load_in_4bit": false,
|
||
|
|
"left_padding": false,
|
||
|
|
"limit": null,
|
||
|
|
"limit_start": 0,
|
||
|
|
"save_every_k_tasks": -1,
|
||
|
|
"postprocess": true,
|
||
|
|
"allow_code_execution": true,
|
||
|
|
"generation_only": false,
|
||
|
|
"load_generations_path": null,
|
||
|
|
"load_data_path": null,
|
||
|
|
"metric_output_path": "/home/abhinav/src/llama-recipes/llama_7b_evol_codealpaca_sparse/sparse-sft_cerebras_70sp_uniform_llama_lr5e-4_epochs1_gradclipFalse_cosine_nodistillation-/combined//humaneval_fp16.json",
|
||
|
|
"save_generations": true,
|
||
|
|
"load_generations_intermediate_paths": null,
|
||
|
|
"save_generations_path": "generations.json",
|
||
|
|
"save_references": false,
|
||
|
|
"save_references_path": "references.json",
|
||
|
|
"prompt": "prompt",
|
||
|
|
"max_memory_per_gpu": "auto",
|
||
|
|
"check_references": false
|
||
|
|
}
|
||
|
|
}
|