{
  "best_metric": 0.1569606214761734,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.12053638692180202,
  "eval_steps": 100,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006026819346090101,
      "eval_loss": 2.890679121017456,
      "eval_runtime": 19.5541,
      "eval_samples_per_second": 35.747,
      "eval_steps_per_second": 17.899,
      "step": 1
    },
    {
      "epoch": 0.006026819346090101,
      "grad_norm": 16.7128963470459,
      "learning_rate": 2.5e-06,
      "loss": 2.8187,
      "step": 10
    },
    {
      "epoch": 0.012053638692180202,
      "grad_norm": 5.472095966339111,
      "learning_rate": 5e-06,
      "loss": 2.6526,
      "step": 20
    },
    {
      "epoch": 0.018080458038270304,
      "grad_norm": 6.024045944213867,
      "learning_rate": 7.5e-06,
      "loss": 2.1175,
      "step": 30
    },
    {
      "epoch": 0.024107277384360404,
      "grad_norm": 7.031100749969482,
      "learning_rate": 1e-05,
      "loss": 1.6338,
      "step": 40
    },
    {
      "epoch": 0.030134096730450505,
      "grad_norm": 4.758700847625732,
      "learning_rate": 1.25e-05,
      "loss": 0.9916,
      "step": 50
    },
    {
      "epoch": 0.03616091607654061,
      "grad_norm": 2.474622964859009,
      "learning_rate": 1.5e-05,
      "loss": 0.3518,
      "step": 60
    },
    {
      "epoch": 0.042187735422630705,
      "grad_norm": 2.6985368728637695,
      "learning_rate": 1.75e-05,
      "loss": 0.417,
      "step": 70
    },
    {
      "epoch": 0.04821455476872081,
      "grad_norm": 1.3015024662017822,
      "learning_rate": 2e-05,
      "loss": 0.2501,
      "step": 80
    },
    {
      "epoch": 0.054241374114810906,
      "grad_norm": 1.4973636865615845,
      "learning_rate": 2.25e-05,
      "loss": 0.1989,
      "step": 90
    },
    {
      "epoch": 0.06026819346090101,
      "grad_norm": 0.7235045433044434,
      "learning_rate": 2.5e-05,
      "loss": 0.3077,
      "step": 100
    },
    {
      "epoch": 0.06026819346090101,
      "eval_loss": 0.17322567105293274,
      "eval_runtime": 19.4751,
      "eval_samples_per_second": 35.892,
      "eval_steps_per_second": 17.972,
      "step": 100
    },
    {
      "epoch": 0.06629501280699111,
      "grad_norm": 2.4882545471191406,
      "learning_rate": 2.7500000000000004e-05,
      "loss": 0.5264,
      "step": 110
    },
    {
      "epoch": 0.07232183215308122,
      "grad_norm": 0.6996169686317444,
      "learning_rate": 3e-05,
      "loss": 0.2292,
      "step": 120
    },
    {
      "epoch": 0.0783486514991713,
      "grad_norm": 0.5811498165130615,
      "learning_rate": 3.2500000000000004e-05,
      "loss": 0.3182,
      "step": 130
    },
    {
      "epoch": 0.08437547084526141,
      "grad_norm": 0.24197261035442352,
      "learning_rate": 3.5e-05,
      "loss": 0.2114,
      "step": 140
    },
    {
      "epoch": 0.09040229019135151,
      "grad_norm": 0.4716508090496063,
      "learning_rate": 3.7500000000000003e-05,
      "loss": 0.1169,
      "step": 150
    },
    {
      "epoch": 0.09642910953744162,
      "grad_norm": 0.48725882172584534,
      "learning_rate": 4e-05,
      "loss": 0.1013,
      "step": 160
    },
    {
      "epoch": 0.10245592888353172,
      "grad_norm": 0.35950130224227905,
      "learning_rate": 4.25e-05,
      "loss": 0.2313,
      "step": 170
    },
    {
      "epoch": 0.10848274822962181,
      "grad_norm": 0.43237921595573425,
      "learning_rate": 4.5e-05,
      "loss": 0.2109,
      "step": 180
    },
    {
      "epoch": 0.11450956757571192,
      "grad_norm": 1.0144596099853516,
      "learning_rate": 4.75e-05,
      "loss": 0.3166,
      "step": 190
    },
    {
      "epoch": 0.12053638692180202,
      "grad_norm": 0.6670956015586853,
      "learning_rate": 5e-05,
      "loss": 0.328,
      "step": 200
    },
    {
      "epoch": 0.12053638692180202,
      "eval_loss": 0.1569606214761734,
      "eval_runtime": 19.5861,
      "eval_samples_per_second": 35.688,
      "eval_steps_per_second": 17.87,
      "step": 200
    }
  ],
  "logging_steps": 10,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "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": 7747803637874688.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}