dev

adapter_config.json

@@ -1,35 +0,0 @@
-{
-  "alpha_pattern": {},
-  "auto_mapping": {
-    "base_model_class": "T5ForConditionalGeneration",
-    "parent_library": "transformers.models.t5.modeling_t5"
-  },
-  "base_model_name_or_path": "google/t5-efficient-tiny-nh8",
-  "bias": "none",
-  "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": 8,
-  "lora_bias": false,
-  "lora_dropout": 0.1,
-  "megatron_config": null,
-  "megatron_core": "megatron.core",
-  "modules_to_save": null,
-  "peft_type": "LORA",
-  "r": 4,
-  "rank_pattern": {},
-  "revision": null,
-  "target_modules": [
-    "v",
-    "q"
-  ],
-  "task_type": null,
-  "use_dora": false,
-  "use_rslora": false
-}

training_params.json

@@ -1,37 +0,0 @@
-{
-    "data_path": "gizemgg/wiki-eng-summary-trial-gen0-transformed-instruction",
-    "model": "google/t5-efficient-tiny-nh8",
-    "username": "shorecode",
-    "seed": 42,
-    "train_split": "train",
-    "valid_split": "test",
-    "project_name": "autotrain-x906d-mvlef",
-    "push_to_hub": true,
-    "text_column": "text",
-    "target_column": "summ",
-    "lr": 0.0001,
-    "epochs": 3,
-    "max_seq_length": 128,
-    "max_target_length": 128,
-    "batch_size": 2,
-    "warmup_ratio": 0.1,
-    "gradient_accumulation": 1,
-    "optimizer": "adamw_torch",
-    "scheduler": "linear",
-    "weight_decay": 0.0,
-    "max_grad_norm": 1.0,
-    "logging_steps": -1,
-    "eval_strategy": "epoch",
-    "auto_find_batch_size": false,
-    "mixed_precision": "fp16",
-    "save_total_limit": 1,
-    "peft": false,
-    "quantization": "int8",
-    "lora_r": 16,
-    "lora_alpha": 32,
-    "lora_dropout": 0.05,
-    "target_modules": "all-linear",
-    "log": "tensorboard",
-    "early_stopping_patience": 5,
-    "early_stopping_threshold": 0.01
-}