Safetensors
qwen2
leave-one-out
loo-domain-knowledge
max_seq_length=16384
lr=2e-5
batch_size=1
grad_accum=16
epochs=1
qlora
quantize=4bit_nf4
lora_rank=64
lora_alpha=128
lora_dropout=0.05
completion_only_loss
eval_size=0.1
cosine_schedule
warmup=0.05
bf16
ddp_workers=2
ray_job=raysubmit_A55M5NnZckrXmfWN
| { | |
| "bos_token_id": 151643, | |
| "do_sample": true, | |
| "eos_token_id": [ | |
| 151645, | |
| 151643 | |
| ], | |
| "pad_token_id": 151643, | |
| "repetition_penalty": 1.05, | |
| "temperature": 0.7, | |
| "top_k": 20, | |
| "top_p": 0.8, | |
| "transformers_version": "4.57.6" | |
| } | |