| { | |
| "model": { | |
| "llm_path": "/netscratch/fkallel/models/Qwen3.5-0.8B/", | |
| "llm_type": "qwen3.5", | |
| "audio_encoder_path": "/ds-slt/audio_weights/xlsr2_300m.pt", | |
| "audio_encoder_type": "wav2vec2", | |
| "audio_encoder_source": "fairseq", | |
| "freeze_audio_encoder": false, | |
| "lora": true, | |
| "lora_rank": 64, | |
| "lora_alpha": 16, | |
| "lora_dropout": 0.05, | |
| "special_tokens": [] | |
| }, | |
| "data": { | |
| "train_path": "data/my_hir_sdd_binary_train_unique_2.json", | |
| "val_path": "data/my_hir_sdd_binary_val_unique_2.json", | |
| "prompt_path": "prompts/train_prompt.json" | |
| }, | |
| "train": { | |
| "batch_size": 8, | |
| "epochs": 5, | |
| "lr": "1e-4", | |
| "lr_adapter": "1e-5", | |
| "lr_audio": "1e-6", | |
| "lr_lora": "1e-5", | |
| "num_workers": 4, | |
| "seed": 2, | |
| "grad_accum_steps": 1 | |
| }, | |
| "output_dir": "output_v6/qwen3.5_0.8B_lora_2" | |
| } |