seqcls-mahasent / adapter_config.json
ridhimamlds's picture
End of training
2dce802 verified
raw
history blame
7.58 kB
{
"alpha_pattern": {},
"auto_mapping": null,
"base_model_name_or_path": "google/gemma-2-2b",
"bias": "none",
"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": 32,
"lora_dropout": 0.1,
"megatron_config": null,
"megatron_core": "megatron.core",
"modules_to_save": [
"classifier",
"score"
],
"peft_type": "LORA",
"r": 8,
"rank_pattern": {},
"revision": null,
"target_modules": [
"model.layers.22.mlp.up_proj",
"model.layers.3.mlp.down_proj",
"model.layers.3.self_attn.v_proj",
"model.layers.0.mlp.up_proj",
"model.layers.24.self_attn.k_proj",
"model.layers.24.self_attn.v_proj",
"model.layers.15.mlp.up_proj",
"model.layers.12.self_attn.q_proj",
"model.layers.5.self_attn.k_proj",
"model.layers.2.self_attn.o_proj",
"model.layers.16.self_attn.v_proj",
"model.layers.16.mlp.up_proj",
"model.layers.19.self_attn.k_proj",
"model.layers.13.mlp.up_proj",
"model.layers.25.self_attn.v_proj",
"model.layers.23.mlp.down_proj",
"model.layers.10.self_attn.q_proj",
"model.layers.1.self_attn.q_proj",
"model.layers.9.mlp.gate_proj",
"model.layers.11.mlp.down_proj",
"model.layers.5.self_attn.v_proj",
"model.layers.15.mlp.gate_proj",
"model.layers.8.mlp.down_proj",
"model.layers.13.mlp.down_proj",
"model.layers.16.mlp.down_proj",
"model.layers.11.self_attn.q_proj",
"model.layers.25.self_attn.q_proj",
"model.layers.9.self_attn.v_proj",
"model.layers.7.mlp.up_proj",
"model.layers.0.self_attn.q_proj",
"model.layers.18.self_attn.k_proj",
"model.layers.9.self_attn.k_proj",
"model.layers.2.mlp.gate_proj",
"model.layers.12.self_attn.k_proj",
"model.layers.15.self_attn.v_proj",
"model.layers.25.mlp.up_proj",
"model.layers.8.self_attn.o_proj",
"model.layers.20.mlp.down_proj",
"model.layers.20.self_attn.v_proj",
"model.layers.22.self_attn.o_proj",
"model.layers.4.mlp.gate_proj",
"model.layers.14.self_attn.o_proj",
"model.layers.17.self_attn.k_proj",
"model.layers.22.self_attn.k_proj",
"model.layers.11.mlp.up_proj",
"model.layers.13.mlp.gate_proj",
"model.layers.21.self_attn.o_proj",
"model.layers.2.mlp.down_proj",
"model.layers.3.self_attn.k_proj",
"model.layers.1.mlp.up_proj",
"model.layers.4.self_attn.k_proj",
"model.layers.5.mlp.up_proj",
"model.layers.19.self_attn.o_proj",
"model.layers.23.self_attn.q_proj",
"model.layers.2.mlp.up_proj",
"model.layers.6.mlp.gate_proj",
"model.layers.9.self_attn.o_proj",
"model.layers.7.self_attn.q_proj",
"model.layers.6.mlp.down_proj",
"model.layers.14.mlp.down_proj",
"model.layers.16.mlp.gate_proj",
"model.layers.15.self_attn.k_proj",
"model.layers.20.mlp.gate_proj",
"model.layers.18.mlp.up_proj",
"model.layers.6.self_attn.v_proj",
"model.layers.10.self_attn.v_proj",
"model.layers.3.mlp.up_proj",
"model.layers.21.mlp.up_proj",
"model.layers.14.mlp.up_proj",
"model.layers.0.self_attn.o_proj",
"score",
"model.layers.18.mlp.down_proj",
"model.layers.10.mlp.down_proj",
"model.layers.16.self_attn.q_proj",
"model.layers.23.mlp.up_proj",
"model.layers.12.mlp.gate_proj",
"model.layers.17.mlp.up_proj",
"model.layers.20.mlp.up_proj",
"model.layers.22.self_attn.q_proj",
"model.layers.21.self_attn.v_proj",
"model.layers.5.mlp.gate_proj",
"model.layers.17.self_attn.v_proj",
"model.layers.12.mlp.down_proj",
"model.layers.8.mlp.up_proj",
"model.layers.1.mlp.down_proj",
"model.layers.19.self_attn.q_proj",
"model.layers.6.self_attn.o_proj",
"model.layers.22.self_attn.v_proj",
"model.layers.13.self_attn.q_proj",
"model.layers.8.self_attn.v_proj",
"model.layers.10.self_attn.k_proj",
"model.layers.25.self_attn.o_proj",
"model.layers.24.mlp.down_proj",
"model.layers.3.mlp.gate_proj",
"model.layers.23.self_attn.o_proj",
"model.layers.19.mlp.gate_proj",
"model.layers.8.mlp.gate_proj",
"model.layers.24.self_attn.q_proj",
"model.layers.13.self_attn.v_proj",
"model.layers.2.self_attn.q_proj",
"model.layers.10.self_attn.o_proj",
"model.layers.13.self_attn.o_proj",
"model.layers.18.self_attn.o_proj",
"model.layers.14.mlp.gate_proj",
"model.layers.20.self_attn.o_proj",
"model.layers.1.self_attn.k_proj",
"model.layers.4.self_attn.v_proj",
"model.layers.17.mlp.down_proj",
"model.layers.19.mlp.up_proj",
"model.layers.9.mlp.up_proj",
"model.layers.21.mlp.down_proj",
"model.layers.20.self_attn.q_proj",
"model.layers.24.mlp.up_proj",
"model.layers.1.self_attn.o_proj",
"model.layers.4.mlp.down_proj",
"model.layers.14.self_attn.v_proj",
"model.layers.8.self_attn.k_proj",
"model.layers.15.self_attn.q_proj",
"model.layers.25.mlp.gate_proj",
"model.layers.13.self_attn.k_proj",
"model.layers.19.self_attn.v_proj",
"model.layers.9.self_attn.q_proj",
"model.layers.2.self_attn.v_proj",
"model.layers.23.mlp.gate_proj",
"model.layers.6.self_attn.k_proj",
"model.layers.18.self_attn.v_proj",
"model.layers.7.mlp.gate_proj",
"model.layers.8.self_attn.q_proj",
"model.layers.11.mlp.gate_proj",
"model.layers.1.self_attn.v_proj",
"model.layers.11.self_attn.o_proj",
"model.layers.18.mlp.gate_proj",
"model.layers.7.mlp.down_proj",
"model.layers.14.self_attn.k_proj",
"model.layers.24.mlp.gate_proj",
"model.layers.17.mlp.gate_proj",
"model.layers.21.self_attn.k_proj",
"model.layers.19.mlp.down_proj",
"model.layers.7.self_attn.o_proj",
"model.layers.25.self_attn.k_proj",
"model.layers.4.self_attn.o_proj",
"model.layers.9.mlp.down_proj",
"model.layers.3.self_attn.q_proj",
"model.layers.5.self_attn.q_proj",
"model.layers.6.self_attn.q_proj",
"model.layers.18.self_attn.q_proj",
"model.layers.17.self_attn.o_proj",
"model.layers.21.mlp.gate_proj",
"model.layers.12.mlp.up_proj",
"model.layers.12.self_attn.v_proj",
"model.layers.21.self_attn.q_proj",
"model.layers.24.self_attn.o_proj",
"model.layers.1.mlp.gate_proj",
"model.layers.0.mlp.gate_proj",
"model.layers.6.mlp.up_proj",
"model.layers.3.self_attn.o_proj",
"model.layers.7.self_attn.v_proj",
"model.layers.5.mlp.down_proj",
"model.layers.12.self_attn.o_proj",
"model.layers.11.self_attn.v_proj",
"model.layers.20.self_attn.k_proj",
"model.layers.22.mlp.down_proj",
"model.layers.10.mlp.up_proj",
"model.layers.23.self_attn.v_proj",
"model.layers.0.self_attn.k_proj",
"model.layers.11.self_attn.k_proj",
"model.layers.5.self_attn.o_proj",
"model.layers.4.self_attn.q_proj",
"model.layers.10.mlp.gate_proj",
"model.layers.22.mlp.gate_proj",
"model.layers.16.self_attn.o_proj",
"model.layers.4.mlp.up_proj",
"model.layers.0.self_attn.v_proj",
"model.layers.15.self_attn.o_proj",
"model.layers.25.mlp.down_proj",
"model.layers.16.self_attn.k_proj",
"model.layers.15.mlp.down_proj",
"model.layers.2.self_attn.k_proj",
"model.layers.0.mlp.down_proj",
"model.layers.7.self_attn.k_proj",
"model.layers.14.self_attn.q_proj",
"model.layers.17.self_attn.q_proj",
"model.layers.23.self_attn.k_proj"
],
"task_type": "SEQ_CLS",
"use_dora": false,
"use_rslora": false
}