config.json

{
  "architectures": [
    "openai-gpt"
  ],
  "inference_mode": true,
  "batch_size": 32,
  "bias": true,
  "block_size": 512,
  "dim_feedforward": 3072,
  "dropout": 0.1,
  "ff_expansion_factor": 4,
  "hidden_act": "gelu",
  "hidden_size": 768,
  "id2label": {
    "0": "LABEL_0",
    "1": "LABEL_1",
    "2": "LABEL_2",
    "3": "LABEL_3",
    "4": "LABEL_4"
  },
  "label2id": {
    "LABEL_0": 0,
    "LABEL_1": 1,
    "LABEL_2": 2,
    "LABEL_3": 3,
    "LABEL_4": 4
  },
  "label_smoothing": 0.1,
  "learning_rate": 0.0003,
  "log_interval": 100,
  "max_grad_norm": 1.0,
  "max_position_embeddings": 512,
  "model_type": "gpt2",
  "n_embd": 768,
  "n_head": 12,
  "n_layer": 12,
  "output_dir": "C:/Users/wonde/output",
  "torch_dtype": "float32",
  "total_steps": 10000,
  "transformers_version": "4.43.3",
  "vocab_size": 50257,
  "warmup_steps": 1000,
  "weight_decay": 0.01,
  "megatron_config": null,
  "megatron_core": "megatron.core",
  "modules_to_save": [
    "classifier",
    "score"
  ],
  "peft_type": "LORA",
  "r": 16,
  "rank_pattern": {},
  "revision": null,
  "target_modules": [
    "c_proj",
    "c_attn",
    "c_fc",
    "score"
  ],
  "task_specific_params": {
    "text-generation": {
      "do_sample": true,
      "max_length": 100
    }
  },
  "task_type": "SEQ_CLS",
  "use_dora": false,
  "use_rslora": false
}