{
  "best_metric": 0.4959838390350342,
  "best_model_checkpoint": "miner_id_24/checkpoint-20",
  "epoch": 0.008487163165711862,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.000424358158285593,
      "grad_norm": 0.7751368284225464,
      "learning_rate": 2e-05,
      "loss": 0.7689,
      "step": 1
    },
    {
      "epoch": 0.000424358158285593,
      "eval_loss": 0.8173423409461975,
      "eval_runtime": 185.8366,
      "eval_samples_per_second": 5.343,
      "eval_steps_per_second": 2.674,
      "step": 1
    },
    {
      "epoch": 0.000848716316571186,
      "grad_norm": 1.2337510585784912,
      "learning_rate": 4e-05,
      "loss": 0.849,
      "step": 2
    },
    {
      "epoch": 0.001273074474856779,
      "grad_norm": 0.8578928709030151,
      "learning_rate": 6e-05,
      "loss": 0.9114,
      "step": 3
    },
    {
      "epoch": 0.001697432633142372,
      "grad_norm": 0.6766877174377441,
      "learning_rate": 8e-05,
      "loss": 0.7335,
      "step": 4
    },
    {
      "epoch": 0.0021217907914279654,
      "grad_norm": 0.7290933728218079,
      "learning_rate": 0.0001,
      "loss": 0.6751,
      "step": 5
    },
    {
      "epoch": 0.0021217907914279654,
      "eval_loss": 0.7813173532485962,
      "eval_runtime": 183.9072,
      "eval_samples_per_second": 5.399,
      "eval_steps_per_second": 2.702,
      "step": 5
    },
    {
      "epoch": 0.002546148949713558,
      "grad_norm": 0.830825924873352,
      "learning_rate": 0.00012,
      "loss": 0.798,
      "step": 6
    },
    {
      "epoch": 0.002970507107999151,
      "grad_norm": 0.8948835134506226,
      "learning_rate": 0.00014,
      "loss": 0.7795,
      "step": 7
    },
    {
      "epoch": 0.003394865266284744,
      "grad_norm": 0.8340906500816345,
      "learning_rate": 0.00016,
      "loss": 0.7168,
      "step": 8
    },
    {
      "epoch": 0.0038192234245703373,
      "grad_norm": 0.9142249822616577,
      "learning_rate": 0.00018,
      "loss": 0.6675,
      "step": 9
    },
    {
      "epoch": 0.004243581582855931,
      "grad_norm": 1.0526764392852783,
      "learning_rate": 0.0002,
      "loss": 0.6064,
      "step": 10
    },
    {
      "epoch": 0.004243581582855931,
      "eval_loss": 0.6158913373947144,
      "eval_runtime": 183.7572,
      "eval_samples_per_second": 5.404,
      "eval_steps_per_second": 2.705,
      "step": 10
    },
    {
      "epoch": 0.0046679397411415234,
      "grad_norm": 0.9812945127487183,
      "learning_rate": 0.00019781476007338058,
      "loss": 0.5798,
      "step": 11
    },
    {
      "epoch": 0.005092297899427116,
      "grad_norm": 0.9407110810279846,
      "learning_rate": 0.0001913545457642601,
      "loss": 0.5111,
      "step": 12
    },
    {
      "epoch": 0.00551665605771271,
      "grad_norm": 0.9945716857910156,
      "learning_rate": 0.00018090169943749476,
      "loss": 0.4749,
      "step": 13
    },
    {
      "epoch": 0.005941014215998302,
      "grad_norm": 1.3098291158676147,
      "learning_rate": 0.00016691306063588583,
      "loss": 0.5797,
      "step": 14
    },
    {
      "epoch": 0.006365372374283896,
      "grad_norm": 0.945827841758728,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.4763,
      "step": 15
    },
    {
      "epoch": 0.006365372374283896,
      "eval_loss": 0.5205870866775513,
      "eval_runtime": 183.9724,
      "eval_samples_per_second": 5.398,
      "eval_steps_per_second": 2.701,
      "step": 15
    },
    {
      "epoch": 0.006789730532569488,
      "grad_norm": 1.1491625308990479,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.6383,
      "step": 16
    },
    {
      "epoch": 0.007214088690855082,
      "grad_norm": 0.8612709641456604,
      "learning_rate": 0.00011045284632676536,
      "loss": 0.4815,
      "step": 17
    },
    {
      "epoch": 0.0076384468491406746,
      "grad_norm": 0.8541699051856995,
      "learning_rate": 8.954715367323468e-05,
      "loss": 0.4945,
      "step": 18
    },
    {
      "epoch": 0.008062805007426267,
      "grad_norm": 1.076985239982605,
      "learning_rate": 6.909830056250527e-05,
      "loss": 0.5025,
      "step": 19
    },
    {
      "epoch": 0.008487163165711862,
      "grad_norm": 0.7121065855026245,
      "learning_rate": 5.000000000000002e-05,
      "loss": 0.4774,
      "step": 20
    },
    {
      "epoch": 0.008487163165711862,
      "eval_loss": 0.4959838390350342,
      "eval_runtime": 185.1092,
      "eval_samples_per_second": 5.364,
      "eval_steps_per_second": 2.685,
      "step": 20
    }
  ],
  "logging_steps": 1,
  "max_steps": 25,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 2,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 6704670399528960.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}