{
  "best_metric": 1.4945499897003174,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.07357449417535254,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002452483139178418,
      "eval_loss": 1.7471487522125244,
      "eval_runtime": 22.9401,
      "eval_samples_per_second": 7.498,
      "eval_steps_per_second": 3.749,
      "step": 1
    },
    {
      "epoch": 0.007357449417535254,
      "grad_norm": 0.43618568778038025,
      "learning_rate": 0.00012,
      "loss": 1.8243,
      "step": 3
    },
    {
      "epoch": 0.012262415695892091,
      "eval_loss": 1.6761877536773682,
      "eval_runtime": 22.9022,
      "eval_samples_per_second": 7.51,
      "eval_steps_per_second": 3.755,
      "step": 5
    },
    {
      "epoch": 0.014714898835070508,
      "grad_norm": 0.542831540107727,
      "learning_rate": 0.0001992114701314478,
      "loss": 1.735,
      "step": 6
    },
    {
      "epoch": 0.022072348252605765,
      "grad_norm": 0.560825526714325,
      "learning_rate": 0.00018763066800438636,
      "loss": 1.6777,
      "step": 9
    },
    {
      "epoch": 0.024524831391784182,
      "eval_loss": 1.5754923820495605,
      "eval_runtime": 23.0431,
      "eval_samples_per_second": 7.464,
      "eval_steps_per_second": 3.732,
      "step": 10
    },
    {
      "epoch": 0.029429797670141016,
      "grad_norm": 0.3786250352859497,
      "learning_rate": 0.000163742398974869,
      "loss": 1.6091,
      "step": 12
    },
    {
      "epoch": 0.03678724708767627,
      "grad_norm": 0.38291609287261963,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.4972,
      "step": 15
    },
    {
      "epoch": 0.03678724708767627,
      "eval_loss": 1.5334440469741821,
      "eval_runtime": 23.0641,
      "eval_samples_per_second": 7.457,
      "eval_steps_per_second": 3.729,
      "step": 15
    },
    {
      "epoch": 0.04414469650521153,
      "grad_norm": 0.4451013505458832,
      "learning_rate": 9.372094804706867e-05,
      "loss": 1.5146,
      "step": 18
    },
    {
      "epoch": 0.049049662783568364,
      "eval_loss": 1.507926106452942,
      "eval_runtime": 23.0793,
      "eval_samples_per_second": 7.453,
      "eval_steps_per_second": 3.726,
      "step": 20
    },
    {
      "epoch": 0.05150214592274678,
      "grad_norm": 0.36523109674453735,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 1.4534,
      "step": 21
    },
    {
      "epoch": 0.05885959534028203,
      "grad_norm": 0.3720594048500061,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 1.4564,
      "step": 24
    },
    {
      "epoch": 0.061312078479460456,
      "eval_loss": 1.4964625835418701,
      "eval_runtime": 23.1084,
      "eval_samples_per_second": 7.443,
      "eval_steps_per_second": 3.722,
      "step": 25
    },
    {
      "epoch": 0.06621704475781728,
      "grad_norm": 0.3617859184741974,
      "learning_rate": 7.022351411174866e-06,
      "loss": 1.465,
      "step": 27
    },
    {
      "epoch": 0.07357449417535254,
      "grad_norm": 0.3772672116756439,
      "learning_rate": 0.0,
      "loss": 1.4506,
      "step": 30
    },
    {
      "epoch": 0.07357449417535254,
      "eval_loss": 1.4945499897003174,
      "eval_runtime": 23.0939,
      "eval_samples_per_second": 7.448,
      "eval_steps_per_second": 3.724,
      "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": 1.0455331230449664e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}