{
  "best_metric": 1.4976978302001953,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.0011969119671248179,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.9897065570827266e-05,
      "eval_loss": 2.0509815216064453,
      "eval_runtime": 1393.1445,
      "eval_samples_per_second": 7.576,
      "eval_steps_per_second": 3.788,
      "step": 1
    },
    {
      "epoch": 0.0001196911967124818,
      "grad_norm": 1.2018862962722778,
      "learning_rate": 3e-05,
      "loss": 2.0903,
      "step": 3
    },
    {
      "epoch": 0.00019948532785413634,
      "eval_loss": 1.9940987825393677,
      "eval_runtime": 1398.4022,
      "eval_samples_per_second": 7.547,
      "eval_steps_per_second": 3.774,
      "step": 5
    },
    {
      "epoch": 0.0002393823934249636,
      "grad_norm": 1.310300350189209,
      "learning_rate": 6e-05,
      "loss": 1.9366,
      "step": 6
    },
    {
      "epoch": 0.0003590735901374454,
      "grad_norm": 1.1172022819519043,
      "learning_rate": 9e-05,
      "loss": 1.8335,
      "step": 9
    },
    {
      "epoch": 0.0003989706557082727,
      "eval_loss": 1.727346420288086,
      "eval_runtime": 1400.1392,
      "eval_samples_per_second": 7.538,
      "eval_steps_per_second": 3.769,
      "step": 10
    },
    {
      "epoch": 0.0004787647868499272,
      "grad_norm": 1.0929975509643555,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.6222,
      "step": 12
    },
    {
      "epoch": 0.0005984559835624089,
      "grad_norm": 0.7399168014526367,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.5356,
      "step": 15
    },
    {
      "epoch": 0.0005984559835624089,
      "eval_loss": 1.5777521133422852,
      "eval_runtime": 1399.1259,
      "eval_samples_per_second": 7.543,
      "eval_steps_per_second": 3.772,
      "step": 15
    },
    {
      "epoch": 0.0007181471802748908,
      "grad_norm": 0.8785402178764343,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.576,
      "step": 18
    },
    {
      "epoch": 0.0007979413114165454,
      "eval_loss": 1.5280091762542725,
      "eval_runtime": 1399.6396,
      "eval_samples_per_second": 7.541,
      "eval_steps_per_second": 3.77,
      "step": 20
    },
    {
      "epoch": 0.0008378383769873726,
      "grad_norm": 0.6277047395706177,
      "learning_rate": 4.2178276747988446e-05,
      "loss": 1.531,
      "step": 21
    },
    {
      "epoch": 0.0009575295736998544,
      "grad_norm": 0.6077454090118408,
      "learning_rate": 2.061073738537635e-05,
      "loss": 1.4596,
      "step": 24
    },
    {
      "epoch": 0.0009974266392706816,
      "eval_loss": 1.5027270317077637,
      "eval_runtime": 1399.9411,
      "eval_samples_per_second": 7.539,
      "eval_steps_per_second": 3.769,
      "step": 25
    },
    {
      "epoch": 0.0010772207704123362,
      "grad_norm": 0.6708080768585205,
      "learning_rate": 5.449673790581611e-06,
      "loss": 1.4892,
      "step": 27
    },
    {
      "epoch": 0.0011969119671248179,
      "grad_norm": 0.6865500211715698,
      "learning_rate": 0.0,
      "loss": 1.4852,
      "step": 30
    },
    {
      "epoch": 0.0011969119671248179,
      "eval_loss": 1.4976978302001953,
      "eval_runtime": 1397.2014,
      "eval_samples_per_second": 7.554,
      "eval_steps_per_second": 3.777,
      "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": 1.112830925340672e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}