caspro's picture
Training in progress, step 500
a02059c verified
raw
history blame contribute delete
764 Bytes
{
"alpha_pattern": {},
"auto_mapping": {
"base_model_class": "MT5ForConditionalGeneration",
"parent_library": "transformers.models.mt5.modeling_mt5"
},
"base_model_name_or_path": "google/mt5-base",
"bias": "lora_only",
"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": [
"decode_head"
],
"peft_type": "LORA",
"r": 32,
"rank_pattern": {},
"revision": null,
"target_modules": [
"q",
"v"
],
"task_type": null,
"use_dora": false,
"use_rslora": false
}