{
  "schema_version": 3,
  "revision": 7,
  "revision_id": "r007",
  "release": "Pollock 1.5",
  "model_id": "SlayerLab/pollock-mini-lm-125m",
  "draft": false,
  "publication": {
    "weights_commit": "f2a1ec072098d257c36b129b0e554e2e6de9c46e",
    "version_tag": "v1.5",
    "publication_commit_pending": false
  },
  "source_checkpoint": {
    "role": "best-full-validation",
    "path_in_training_workspace": "out-pollock-r007-e4-final/ckpt-best.pt",
    "sha256": "384d912cc8b7ebf872b66d1f8ad46f223296a069e906167076f1899296f9a788",
    "iteration": 43750,
    "tokens_seen": 21503919992,
    "data_pass_equivalent": 3.9847123089835352,
    "native_nanogpt_parameters": 125854464,
    "native_unique_trainable_parameters": 127427328
  },
  "terminal_checkpoint": {
    "path_in_training_workspace": "out-pollock-r007-e4-final/ckpt-e4-terminal-step-00043918.pt",
    "sha256": "ef6952d47b717266ff57272b0890a7c54ed36111bb65a2c22bb2630df87f3016",
    "iteration": 43918,
    "tokens_seen": 21586421624,
    "data_pass_equivalent": 4.0
  },
  "architecture": {
    "n_layer": 16,
    "n_head": 12,
    "n_embd": 768,
    "n_inner": 3200,
    "block_size": 2048,
    "vocab_size": 12288,
    "dropout": 0.0,
    "bias": false,
    "tied_word_embeddings": true
  },
  "training": {
    "dataset": "SlayerLab/minimal-en-corpus-5b",
    "dataset_revision": "38bebbd2ae36858c25aa0799fd3296fbfa9432aa",
    "training_tokens": 5396605407,
    "validation_tokens": 5238223,
    "tokenizer_sha256": "3733307577230bb4802d2c774d8e2323f7f64e4139c13712736a57daf91bdda1",
    "init_from": "scratch",
    "data_sampling": "seeded global permutation of fixed token windows per pass",
    "data_shuffle_seed": 1337,
    "micro_batch_per_gpu": 6,
    "gradient_accumulation_global": 40,
    "gradient_accumulation_per_gpu": 20,
    "ddp_world_size": 2,
    "effective_batch_tokens": 491520,
    "optimizer": "Muon plus fused AdamW",
    "muon_parameters": 116391936,
    "adamw_parameters": 11035392,
    "muon_learning_rate": 0.01,
    "muon_min_learning_rate": 0.001,
    "adamw_learning_rate": 0.0003,
    "adamw_min_learning_rate": 0.00003,
    "schedule": "200-update warmup and cosine decay through update 21959; learning-rate floors thereafter",
    "warmup_iters": 200,
    "beta1": 0.9,
    "beta2": 0.95,
    "muon_momentum": 0.95,
    "weight_decay": 0.01,
    "grad_clip": 1.0,
    "precision": "bfloat16",
    "hardware": "2x NVIDIA GeForce RTX 4090",
    "framework": "PyTorch 2.11.0+cu128",
    "nanogpt_commit": "3adf61e154c3fe3fca428ad6bc3818b27a3b8291",
    "completed_data_passes": 4.0,
    "runtime_hours": null,
    "mean_tokens_per_second": null
  },
  "evaluation": {
    "protocol": "complete validation split plus fixed corpus-wide shuffled train sample",
    "train_subset_tokens": 2457600,
    "validation_targets": 5238222,
    "selected_train_loss_rounded": 2.4227,
    "selected_validation_loss": 2.458615977563123,
    "selected_validation_perplexity": 11.688623023409297,
    "selected_validation_update": 43750,
    "selected_validation_tokens_seen": 21503919992,
    "terminal_train_loss_rounded": 2.4226,
    "terminal_validation_loss_rounded": 2.4587,
    "e4_best_diagnostic_status": "completed",
    "e4_best_training_workspace_results_file": "evaluations/r007_epochs/results/E4-best/metrics.json",
    "e4_best_cross_entropy": 2.458519056568919,
    "e4_best_perplexity": 11.687490205342804,
    "e4_best_predictive_entropy": 2.4375294293734733,
    "e4_best_repetition_4gram": 0.33997844253584,
    "e4_best_repetition_8gram": 0.2570576867781918,
    "e4_best_repetition_16gram": 0.20893125597814885,
    "benchmark_status": "completed",
    "benchmark_harness": "lm-evaluation-harness 0.4.12",
    "benchmark_num_fewshot": 0,
    "benchmark_batch_size": 8,
    "truncated_benchmark_requests": 0,
    "benchmark_checkpoint_sha256": "4a88432225dac6255ae1e2a085019f36dcdaf55fa33c77629dba6e7445c6c2fb",
    "benchmark_tokenizer_sha256": "3733307577230bb4802d2c774d8e2323f7f64e4139c13712736a57daf91bdda1",
    "results_file": "benchmarks/english.json",
    "blimp_accuracy": 0.7849701492537313,
    "lambada_openai_accuracy": 0.3007956530176596,
    "lambada_openai_perplexity": 45.030361770214945,
    "hellaswag_accuracy_normalized": 0.30830511850229037,
    "piqa_accuracy_normalized": 0.5968443960826986,
    "sciq_accuracy_normalized": 0.675,
    "arc_easy_accuracy_normalized": 0.41835016835016836,
    "arc_challenge_accuracy_normalized": 0.25
  },
  "fixed_inference": {
    "suite_id": "fixed-sampling-v1",
    "status": "completed",
    "comparison_file": "inference-samples/README.md",
    "config_file": "inference-samples/config.json",
    "generator_file": "inference-samples/generate.py",
    "results_file": "inference-samples/results.json",
    "operating_system": "macOS 26.2",
    "architecture": "arm64",
    "device": "cpu",
    "dtype": "float32",
    "seed": 1337,
    "prompt_count": 4,
    "revision_count": 7,
    "exact_replay_verified": true,
    "publication_commit_pending": false,
    "r007_weights_commit": "f2a1ec072098d257c36b129b0e554e2e6de9c46e"
  },
  "conversion": {
    "status": "completed",
    "target_class": "GPT2LMHeadModel",
    "transformers_version": "5.15.1",
    "checkpoint_sha256": "384d912cc8b7ebf872b66d1f8ad46f223296a069e906167076f1899296f9a788",
    "model_sha256": "4a88432225dac6255ae1e2a085019f36dcdaf55fa33c77629dba6e7445c6c2fb",
    "unique_serialized_parameters": 127565312,
    "compatibility_zero_bias_parameters": 137984,
    "validation_probe_shape": [2, 64],
    "max_absolute_logit_error": 0.0
  },
  "artifacts": {
    ".gitattributes": {"sha256": "c759491a998899dbefaec4d51cc791e68c714a37dd9f9829020a368788fe3063"},
    "CHANGELOG.md": {"sha256": "c2f62c0227cb8ccf18417bf91ff4dbfcc1c08069815fe215785e3207cbabde11"},
    "LICENSE.md": {"sha256": "162b97898a956d43d0a5428d1999bac3e42e2a97eb01a79f73ad719a4a15c412"},
    "README.md": {"sha256": "b9e153c60d9dd14caf19e02515522c7ef17d14fa1fc7037a0acbaf48a6a7d49a"},
    "assets/pollock-mini-lm-avatar-320.png": {"sha256": "7be10cc9d0f4aedeb298d9a5d722b2b2ac5b2e219b3884916dbca16198f70750"},
    "benchmarks/english.json": {"sha256": "430feae7aefd6d8e226f61403a9e1080274daac538361d9ab6dcd5e1129218e2"},
    "config.json": {"sha256": "aedc3eea385b4295b3ba257eb8533b06046eea0cca1ff009515ad3f1adbb4854"},
    "conversion_manifest.json": {"sha256": "eb207d676eca255f7dd9415049b825f55ea81f8eed11cc9b0fc85a3f8b2bea5d"},
    "generation_config.json": {"sha256": "435beb27be51f0ed054f4a011e5109d125cdadc118b8799b18b155cc798d94d2"},
    "inference-samples/README.md": {"sha256": "66a15dba47cc44864f9accaad51955ed11c61d2103472ecf7a0c3451aa2fb291"},
    "inference-samples/config.json": {"sha256": "3e908dfa8ce6085092dc665f7bdf7b69490fe49779c74a2c69adbd7265403ed9"},
    "inference-samples/generate.py": {"sha256": "b4bb2edc64924ebdcbbd4ed7d0e72c44e6d9d05e58c96541c00cdeeb075b917d"},
    "inference-samples/requirements.txt": {"sha256": "584583335ffb3061aa62058aee725b0de25fed7523904fbd13fb4622f601943d"},
    "inference-samples/results.json": {"sha256": "ab07a2bf47297ab17f12fbd00aa5ca10569eef31a07984ba1af6e0321d689841"},
    "model.safetensors": {"sha256": "4a88432225dac6255ae1e2a085019f36dcdaf55fa33c77629dba6e7445c6c2fb"},
    "special_tokens_map.json": {"sha256": "8b2257a17ea997bb038f43b133aefec82344ad2b8abc2b8a02a6c0a994ed624e"},
    "tokenizer.json": {"sha256": "3733307577230bb4802d2c774d8e2323f7f64e4139c13712736a57daf91bdda1"},
    "tokenizer_config.json": {"sha256": "39a075b24f05384c6d759521563d879cab4bb80b0fe94381e6e792966ab4c2ba"},
    "training-history/r001.md": {"sha256": "5b0ac39265921ed3604e7dfe8181b00d07902640d8024f591462eeb508bcfece"},
    "training-history/r002.md": {"sha256": "80031a84b2b67dc4cb4f81a178fa354feea15cb184d17368ee7e64ec3d0a2629"},
    "training-history/r003.md": {"sha256": "7ea9e6b15a0af635ff238417b9fff2a98c12a9090800a0923d622253b7eab02d"},
    "training-history/r004.md": {"sha256": "e260bfba69f154caf16f405d6944c2f963f467da9ed1e6c3c94e08932feae9b9"},
    "training-history/r005.md": {"sha256": "a25c2932701695dd7402582510adbe71e50a6fcc2da0fb3c6224a846dfdb22df"},
    "training-history/r006.md": {"sha256": "47d53f9aa8a233eb7a319f559209936df988e83d96f6f6517fa3670b5dd2cdd3"},
    "training-history/r007.md": {"sha256": "fc9a4153eb8c073287f76b82b89ffaad62f3a606ba000e53bf450e393a5807d6"}
  }
}