artifact_metadata.json

{
  "purpose": "TinyStories-trained tiny Gemma3 text-only validation artifact",
  "model_class": "Gemma3ForCausalLM",
  "config_class": "Gemma3TextConfig",
  "uses_custom_modeling_code": false,
  "dataset": "TinyStories parquet files supplied through --train-files",
  "seed": 1234,
  "model_dir": "/import/192.168.0.20/home/n-sibata/work3/tinyModel/tinygemma3-2m/tinygemma3-2m/hf",
  "reference_dir": "/import/192.168.0.20/home/n-sibata/work3/tinyModel/tinygemma3-2m/tinygemma3-2m/reference",
  "vocab_size": 1024,
  "hidden_size": 128,
  "intermediate_size": 512,
  "num_hidden_layers": 6,
  "num_attention_heads": 4,
  "num_key_value_heads": 1,
  "head_dim": 32,
  "sliding_window": 32,
  "max_position_embeddings": 256,
  "layer_types": [
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention"
  ],
  "tie_word_embeddings": true,
  "training": {
    "per_device_train_batch_size": 16,
    "gradient_accumulation_steps": 2,
    "learning_rate": 0.001,
    "num_train_epochs": 1.0,
    "max_steps": -1,
    "bf16": false,
    "fp16": false,
    "block_size": 256
  }
}