{
  "torch": "2.12.0+cpu",
  "transformers": "4.56.2",
  "tokenizers": "0.22.1",
  "checkpoints": {
    "ckpt_best.pt": {
      "step": 4750,
      "val_loss": 4.198967456817627,
      "config": {
        "batch_size": 32,
        "block_size": 256,
        "dropout": 0.1,
        "eval_interval": 250,
        "eval_iters": 50,
        "grad_accum": 2,
        "grad_clip": 1.0,
        "learning_rate": 0.0003,
        "max_iters": 5000,
        "min_lr": 3e-05,
        "n_embd": 512,
        "n_head": 8,
        "n_layer": 10,
        "vocab_size": 16000,
        "warmup_iters": 200,
        "weight_decay": 0.1
      },
      "sha256": "8001f584a6cd7869d84af5e8fd5d37a1e9a4c29f9789b5a19e012480c98fbfae",
      "bytes": 478325259,
      "keys": [
        "config",
        "model",
        "optimizer",
        "step",
        "val_loss"
      ]
    },
    "ckpt_latest.pt": {
      "step": 5000,
      "val_loss": 4.211184501647949,
      "config": {
        "batch_size": 32,
        "block_size": 256,
        "dropout": 0.1,
        "eval_interval": 250,
        "eval_iters": 50,
        "grad_accum": 2,
        "grad_clip": 1.0,
        "learning_rate": 0.0003,
        "max_iters": 5000,
        "min_lr": 3e-05,
        "n_embd": 512,
        "n_head": 8,
        "n_layer": 10,
        "vocab_size": 16000,
        "warmup_iters": 200,
        "weight_decay": 0.1
      },
      "sha256": "ad19ad3027ac3378fd10a46406bdfe3db3e6c865435e5ec3646da8768a6690c0",
      "bytes": 478326263,
      "keys": [
        "config",
        "model",
        "optimizer",
        "step",
        "val_loss"
      ]
    }
  },
  "parameter_count": 39847936,
  "all_model_tensors_finite": true,
  "strict_state_dict_load": true,
  "tied_embeddings": true,
  "tokenizer_parity_samples": 7,
  "logit_parity": [
    {
      "context_tokens": 5,
      "max_absolute_logit_error": 0.0,
      "allclose_atol": 0.0001,
      "allclose_rtol": 1e-05
    },
    {
      "context_tokens": 4,
      "max_absolute_logit_error": 0.0,
      "allclose_atol": 0.0001,
      "allclose_rtol": 1e-05
    },
    {
      "context_tokens": 10,
      "max_absolute_logit_error": 0.0,
      "allclose_atol": 0.0001,
      "allclose_rtol": 1e-05
    },
    {
      "context_tokens": 11,
      "max_absolute_logit_error": 0.0,
      "allclose_atol": 0.0001,
      "allclose_rtol": 1e-05
    },
    {
      "context_tokens": 7,
      "max_absolute_logit_error": 0.0,
      "allclose_atol": 0.0001,
      "allclose_rtol": 1e-05
    },
    {
      "context_tokens": 1,
      "max_absolute_logit_error": 2.86102294921875e-06,
      "allclose_atol": 0.0001,
      "allclose_rtol": 1e-05
    },
    {
      "context_tokens": 32,
      "max_absolute_logit_error": 0.0,
      "allclose_atol": 0.0001,
      "allclose_rtol": 1e-05
    },
    {
      "context_tokens": 128,
      "max_absolute_logit_error": 0.0,
      "allclose_atol": 0.0001,
      "allclose_rtol": 1e-05
    },
    {
      "context_tokens": 256,
      "max_absolute_logit_error": 0.0,
      "allclose_atol": 0.0001,
      "allclose_rtol": 1e-05
    }
  ],
  "greedy_generation_parity": true,
  "saved_auto_model_reload_parity": true,
  "smoke_generations": [
    {
      "prompt": "The future of artificial intelligence",
      "greedy_completion": " The future of artificial intelligence is the most important thing to do with the world.\nThe world is a very important thing to do with the world. It is a great way to do the world. It is a great way",
      "generated_tokens": 40
    },
    {
      "prompt": "India is a country",
      "greedy_completion": " India is a country that is a country that is a country that is a country that is a country that is a country that is a country that is a country that is a country that is a country that is a country",
      "generated_tokens": 40
    },
    {
      "prompt": "Hello, world!\nA new paragraph.",
      "greedy_completion": " Hello, world!\nA new paragraph.\nA new book is a book of the book.\nA new book is written by the author of the book.\nA new book is written by the author of the book.\nA new",
      "generated_tokens": 40
    }
  ],
  "validation_perplexity_from_logged_loss": 66.61751006088267,
  "export": {
    "format": "safetensors",
    "dtype": "float32",
    "optimizer_state_included": false,
    "model_type": "gpt2",
    "activation_function": "gelu"
  },
  "weights_sha256": "28d20da604f1350cccbee9456b5eca3093f3db9c077469e97e89353d647307ae"
}