stepwise_eq_sft_model_multitask / adapter_config.json
TomasJavurek's picture
Training in progress, step 688
d3ddbd2 verified
{
"alora_invocation_tokens": null,
"alpha_pattern": {},
"arrow_config": null,
"auto_mapping": null,
"base_model_name_or_path": "Qwen/Qwen3-8B",
"bias": "none",
"corda_config": null,
"ensure_weight_tying": true,
"eva_config": null,
"exclude_modules": null,
"fan_in_fan_out": false,
"inference_mode": true,
"init_lora_weights": true,
"layer_replication": null,
"layers_pattern": null,
"layers_to_transform": null,
"loftq_config": {},
"lora_alpha": 128,
"lora_bias": false,
"lora_dropout": 0.05,
"megatron_config": null,
"megatron_core": "megatron.core",
"modules_to_save": null,
"peft_type": "LORA",
"peft_version": "0.18.1",
"qalora_group_size": 16,
"r": 64,
"rank_pattern": {},
"revision": null,
"target_modules": [
"q_proj",
"up_proj",
"k_proj",
"v_proj",
"o_proj",
"gate_proj",
"down_proj"
],
"target_parameters": null,
"task_type": "CAUSAL_LM",
"trainable_token_indices": {
"embed_tokens": [
151669,
151670,
151671,
151672,
151673,
151674,
151675,
151676,
151677,
151678,
151679,
2207,
1694,
18471,
28,
29052,
151680,
64648,
25875,
59394,
151681,
151682,
151683,
75,
64,
9633,
61482
]
},
"use_dora": false,
"use_qalora": false,
"use_rslora": false
}