run_metadata.json

{
  "experiment_name": "dmhy-char-thin-hardfocus",
  "data_file": "data/thin_hard_focus_char.jsonl",
  "tokenizer_variant": "char",
  "vocab_file": "datasets/AnimeName/vocab.char.json",
  "vocab_size": 6199,
  "max_seq_length": 128,
  "hidden_size": 256,
  "num_hidden_layers": 4,
  "num_attention_heads": 8,
  "intermediate_size": 1024,
  "train_samples": 117089,
  "eval_samples": 6163,
  "epochs": 2.0,
  "batch_size": 256,
  "learning_rate": 4e-05,
  "warmup_steps": 80,
  "seed": 58,
  "device": "cuda",
  "fp16": true,
  "gradient_accumulation_steps": 1,
  "dataloader_num_workers": 4
}