{
  "schema_version": 1,
  "created_at": "2026-07-31T12:37:34.664037+00:00",
  "source": {
    "training_run_id": "gpt2-124m-fineweb10b-20260729t103500z-36bfc9e",
    "checkpoint_filename": "final_step_019073.pt",
    "checkpoint_step": 19073,
    "checkpoint_size_bytes": 1493919114,
    "checkpoint_sha256": "e519d993d20c98c841ef061f76a1dec3e6ee24d5e55162bdea2a3e2da280fd40",
    "checkpoint_git_sha": "36bfc9edd044eb828e118d49c79532eef8440a2a",
    "complete_verified": true
  },
  "architecture": {
    "model_type": "GPT2LMHeadModel",
    "n_layer": 12,
    "n_head": 12,
    "n_embd": 768,
    "n_positions": 1024,
    "native_vocab_size": 50304,
    "export_vocab_size": 50257,
    "parameter_count": 124439808,
    "tied_embeddings": true
  },
  "mapping": {
    "native_parameter_tensors": 149,
    "huggingface_parameter_tensors": 149,
    "transposed_weight_tensors": 48,
    "transposed_weight_names": [
      "transformer.h.0.attn.c_attn.weight",
      "transformer.h.0.attn.c_proj.weight",
      "transformer.h.0.mlp.c_fc.weight",
      "transformer.h.0.mlp.c_proj.weight",
      "transformer.h.1.attn.c_attn.weight",
      "transformer.h.1.attn.c_proj.weight",
      "transformer.h.1.mlp.c_fc.weight",
      "transformer.h.1.mlp.c_proj.weight",
      "transformer.h.2.attn.c_attn.weight",
      "transformer.h.2.attn.c_proj.weight",
      "transformer.h.2.mlp.c_fc.weight",
      "transformer.h.2.mlp.c_proj.weight",
      "transformer.h.3.attn.c_attn.weight",
      "transformer.h.3.attn.c_proj.weight",
      "transformer.h.3.mlp.c_fc.weight",
      "transformer.h.3.mlp.c_proj.weight",
      "transformer.h.4.attn.c_attn.weight",
      "transformer.h.4.attn.c_proj.weight",
      "transformer.h.4.mlp.c_fc.weight",
      "transformer.h.4.mlp.c_proj.weight",
      "transformer.h.5.attn.c_attn.weight",
      "transformer.h.5.attn.c_proj.weight",
      "transformer.h.5.mlp.c_fc.weight",
      "transformer.h.5.mlp.c_proj.weight",
      "transformer.h.6.attn.c_attn.weight",
      "transformer.h.6.attn.c_proj.weight",
      "transformer.h.6.mlp.c_fc.weight",
      "transformer.h.6.mlp.c_proj.weight",
      "transformer.h.7.attn.c_attn.weight",
      "transformer.h.7.attn.c_proj.weight",
      "transformer.h.7.mlp.c_fc.weight",
      "transformer.h.7.mlp.c_proj.weight",
      "transformer.h.8.attn.c_attn.weight",
      "transformer.h.8.attn.c_proj.weight",
      "transformer.h.8.mlp.c_fc.weight",
      "transformer.h.8.mlp.c_proj.weight",
      "transformer.h.9.attn.c_attn.weight",
      "transformer.h.9.attn.c_proj.weight",
      "transformer.h.9.mlp.c_fc.weight",
      "transformer.h.9.mlp.c_proj.weight",
      "transformer.h.10.attn.c_attn.weight",
      "transformer.h.10.attn.c_proj.weight",
      "transformer.h.10.mlp.c_fc.weight",
      "transformer.h.10.mlp.c_proj.weight",
      "transformer.h.11.attn.c_attn.weight",
      "transformer.h.11.attn.c_proj.weight",
      "transformer.h.11.mlp.c_fc.weight",
      "transformer.h.11.mlp.c_proj.weight"
    ],
    "trimmed_embedding_rows": 47,
    "missing_parameters": [],
    "unexpected_parameters": []
  },
  "validation": {
    "finite_parameters": {
      "status": "passed",
      "values_checked": 163037184,
      "nonfinite_tensors": []
    },
    "native_huggingface_equivalence": {
      "status": "passed",
      "seed": 19073,
      "input_shape": [
        2,
        24
      ],
      "comparison_vocabulary_size": 50257,
      "max_absolute_logit_difference": 2.09808349609375e-05,
      "mean_absolute_logit_difference": 8.717573223293584e-07,
      "absolute_tolerance": 5e-05,
      "relative_tolerance": 5e-05,
      "native_trimmed_next_token_loss": 13.709978103637695,
      "huggingface_next_token_loss": 13.709978103637695,
      "absolute_loss_difference": 0.0,
      "loss_note": "Native logits are trimmed to the exported 50,257-token vocabulary before cross-entropy; the 47 training-only padding rows are intentionally excluded."
    },
    "tokenizer": {
      "status": "passed",
      "prompts_checked": 3,
      "vocab_size": 50257
    },
    "clean_process": {
      "status": "passed",
      "model_class": "GPT2LMHeadModel",
      "tokenizer_class": "GPT2TokenizerFast",
      "max_generated_id": 11666,
      "generated_tokens": 18
    },
    "generated_ids_below_vocab_size": true
  },
  "model_safetensors_size_bytes": 497774208,
  "model_safetensors_sha256": "6260e630dd15c0f942423d8319428922155b03fbd37e38dc84470a88b95afe6d",
  "license": "mit",
  "publication_ready": true,
  "target_repo_id": "ctxnn1/gpt2-124m-fineweb-edu-10b",
  "huggingface_validation": {
    "status": "passed",
    "repo_id": "ctxnn1/gpt2-124m-fineweb-edu-10b",
    "url": "https://huggingface.co/ctxnn1/gpt2-124m-fineweb-edu-10b",
    "model_revision": "c0b09743d3a5604a510135a7a6c0572c510a62db",
    "downloaded_model_safetensors_sha256": "6260e630dd15c0f942423d8319428922155b03fbd37e38dc84470a88b95afe6d",
    "generated_max_token_id": 11666
  }
}