{
  "schema_version": 2,
  "revision": 4,
  "revision_id": "r004",
  "release": "Pollock 1.2",
  "model_id": "SlayerLab/pollock-mini-lm-125m",
  "source_checkpoint": {
    "path_in_training_workspace": "runs/pollock-r004-shape/checkpoints/ckpt-final.pt",
    "sha256": "4e38589ca422597ff808bc93cc17ddcc441f734a4e0f671ee6d4527c545972e0",
    "iteration": 22004,
    "tokens_seen": 10815406080,
    "native_nanogpt_parameters": 126541376,
    "native_unique_trainable_parameters": 127393344
  },
  "architecture": {
    "n_layer": 14,
    "n_head": 13,
    "n_embd": 832,
    "block_size": 1024,
    "vocab_size": 12288,
    "dropout": 0.0,
    "bias": false,
    "tied_word_embeddings": true
  },
  "training": {
    "dataset": "SlayerLab/minimal-en-corpus-2.5b",
    "init_from": "scratch",
    "micro_batch_per_gpu": 12,
    "gradient_accumulation_global": 40,
    "ddp_world_size": 1,
    "effective_batch_tokens": 491520,
    "optimizer": "fused AdamW",
    "learning_rate": 0.0004,
    "min_learning_rate": 0.00004,
    "schedule": "cosine",
    "warmup_iters": 440,
    "lr_decay_iters": 22003,
    "beta1": 0.9,
    "beta2": 0.95,
    "weight_decay": 0.1,
    "grad_clip": 1.0,
    "precision": "bfloat16",
    "compile": true,
    "backend": "nccl",
    "seed": 1337,
    "evaluation_seed": 1337,
    "hardware": "1x NVIDIA GeForce RTX 5090",
    "nanogpt_commit": "3adf61e154c3fe3fca428ad6bc3818b27a3b8291"
  },
  "evaluation": {
    "protocol": "fixed sampled subset",
    "subset_tokens_per_split": 1228800,
    "final_train_loss": 2.4665083193778994,
    "final_validation_loss": 2.535205955505371,
    "best_validation_loss": 2.5350550031661987,
    "best_validation_step": 22000,
    "final_validation_perplexity": 12.61902953902636,
    "benchmark_harness": "lm-evaluation-harness 0.4.12",
    "benchmark_num_fewshot": 0,
    "benchmark_batch_size": 8,
    "truncated_benchmark_requests": 80,
    "results_file": "benchmarks/english.json"
  },
  "conversion": {
    "target_class": "GPT2LMHeadModel",
    "transformers_version": "5.15.1",
    "unique_serialized_parameters": 127522304,
    "compatibility_zero_bias_parameters": 128960,
    "validation_probe_shape": [2, 64],
    "max_absolute_logit_error": 0.0
  },
  "artifacts": {
    "README.md": {"sha256": "64513cc6cf3cdc52544a02010293c97b58683c815ef952815954b44fa2b15a0f"},
    "CHANGELOG.md": {"sha256": "5203517a875ca3f04747305a80f732aca54a05ca132a4a4b4fb1453d9d2557ea"},
    "training-history/r004.md": {"sha256": "d9893a5a9f998cfc93e986d63eb36c9a39f519e1cb74f7a6bf6ac4d3cf6f6f12"},
    "benchmarks/english.json": {"sha256": "ffe1e417bef440b1e6a84e05beccb96aa191f6f22141b388cc7ed08297318a7d"},
    "config.json": {"sha256": "296c495f22edddb9828ff9c9ca486cddbacff510742f4aff6a04552d2da3b8d4"},
    "generation_config.json": {"sha256": "435beb27be51f0ed054f4a011e5109d125cdadc118b8799b18b155cc798d94d2"},
    "model.safetensors": {"sha256": "3c453f22d4bb70228e5cca79e183a425e0f0221e54bd782d12027c42c943c880"},
    "special_tokens_map.json": {"sha256": "8b2257a17ea997bb038f43b133aefec82344ad2b8abc2b8a02a6c0a994ed624e"},
    "tokenizer.json": {"sha256": "6cda4e5ec8293f3b821e02253f9c0e88e43ad4f7c6e1324763e1fb91749fef51"},
    "tokenizer_config.json": {"sha256": "4cdabe37dbdc1adfcc017ee9a1f86ab89bdf184827d2d9f05181cae0f8af19bf"}
  }
}