{
  "best_metric": 2.813052177429199,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.003611846857693234,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00012039489525644112,
      "eval_loss": 3.391099691390991,
      "eval_runtime": 216.677,
      "eval_samples_per_second": 16.144,
      "eval_steps_per_second": 8.072,
      "step": 1
    },
    {
      "epoch": 0.0003611846857693234,
      "grad_norm": 1.3789111375808716,
      "learning_rate": 6e-05,
      "loss": 3.2634,
      "step": 3
    },
    {
      "epoch": 0.0006019744762822056,
      "eval_loss": 3.2759201526641846,
      "eval_runtime": 217.2855,
      "eval_samples_per_second": 16.099,
      "eval_steps_per_second": 8.049,
      "step": 5
    },
    {
      "epoch": 0.0007223693715386468,
      "grad_norm": 0.8506129384040833,
      "learning_rate": 0.00012,
      "loss": 2.7577,
      "step": 6
    },
    {
      "epoch": 0.0010835540573079702,
      "grad_norm": 1.013260006904602,
      "learning_rate": 0.00018,
      "loss": 2.7015,
      "step": 9
    },
    {
      "epoch": 0.0012039489525644113,
      "eval_loss": 3.090221643447876,
      "eval_runtime": 217.5739,
      "eval_samples_per_second": 16.077,
      "eval_steps_per_second": 8.039,
      "step": 10
    },
    {
      "epoch": 0.0014447387430772936,
      "grad_norm": 1.331856608390808,
      "learning_rate": 0.00019510565162951537,
      "loss": 2.5234,
      "step": 12
    },
    {
      "epoch": 0.001805923428846617,
      "grad_norm": 1.0995701551437378,
      "learning_rate": 0.00017071067811865476,
      "loss": 2.5354,
      "step": 15
    },
    {
      "epoch": 0.001805923428846617,
      "eval_loss": 2.934854507446289,
      "eval_runtime": 217.8074,
      "eval_samples_per_second": 16.06,
      "eval_steps_per_second": 8.03,
      "step": 15
    },
    {
      "epoch": 0.0021671081146159405,
      "grad_norm": 1.017781376838684,
      "learning_rate": 0.00013090169943749476,
      "loss": 2.6336,
      "step": 18
    },
    {
      "epoch": 0.0024078979051288226,
      "eval_loss": 2.857090473175049,
      "eval_runtime": 217.6075,
      "eval_samples_per_second": 16.075,
      "eval_steps_per_second": 8.037,
      "step": 20
    },
    {
      "epoch": 0.002528292800385264,
      "grad_norm": 1.3486642837524414,
      "learning_rate": 8.435655349597689e-05,
      "loss": 2.9569,
      "step": 21
    },
    {
      "epoch": 0.002889477486154587,
      "grad_norm": 0.9376219511032104,
      "learning_rate": 4.12214747707527e-05,
      "loss": 2.7892,
      "step": 24
    },
    {
      "epoch": 0.003009872381411028,
      "eval_loss": 2.8206255435943604,
      "eval_runtime": 217.2343,
      "eval_samples_per_second": 16.102,
      "eval_steps_per_second": 8.051,
      "step": 25
    },
    {
      "epoch": 0.0032506621719239105,
      "grad_norm": 1.2176676988601685,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 2.904,
      "step": 27
    },
    {
      "epoch": 0.003611846857693234,
      "grad_norm": 1.0202986001968384,
      "learning_rate": 0.0,
      "loss": 2.4385,
      "step": 30
    },
    {
      "epoch": 0.003611846857693234,
      "eval_loss": 2.813052177429199,
      "eval_runtime": 217.0819,
      "eval_samples_per_second": 16.114,
      "eval_steps_per_second": 8.057,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3197269872476160.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}