{
  "best_metric": 1.019839882850647,
  "best_model_checkpoint": "miner_id_24/checkpoint-20",
  "epoch": 0.0935672514619883,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004678362573099415,
      "grad_norm": 0.4054061472415924,
      "learning_rate": 2e-05,
      "loss": 1.7704,
      "step": 1
    },
    {
      "epoch": 0.004678362573099415,
      "eval_loss": 1.759503722190857,
      "eval_runtime": 23.1485,
      "eval_samples_per_second": 3.888,
      "eval_steps_per_second": 1.944,
      "step": 1
    },
    {
      "epoch": 0.00935672514619883,
      "grad_norm": 0.5290826559066772,
      "learning_rate": 4e-05,
      "loss": 1.8531,
      "step": 2
    },
    {
      "epoch": 0.014035087719298246,
      "grad_norm": 0.5181699991226196,
      "learning_rate": 6e-05,
      "loss": 1.6742,
      "step": 3
    },
    {
      "epoch": 0.01871345029239766,
      "grad_norm": 0.45655643939971924,
      "learning_rate": 8e-05,
      "loss": 1.9485,
      "step": 4
    },
    {
      "epoch": 0.023391812865497075,
      "grad_norm": 0.38795363903045654,
      "learning_rate": 0.0001,
      "loss": 1.7268,
      "step": 5
    },
    {
      "epoch": 0.023391812865497075,
      "eval_loss": 1.7444427013397217,
      "eval_runtime": 21.9769,
      "eval_samples_per_second": 4.095,
      "eval_steps_per_second": 2.048,
      "step": 5
    },
    {
      "epoch": 0.028070175438596492,
      "grad_norm": 0.44985294342041016,
      "learning_rate": 0.00012,
      "loss": 1.6324,
      "step": 6
    },
    {
      "epoch": 0.03274853801169591,
      "grad_norm": 0.5087473392486572,
      "learning_rate": 0.00014,
      "loss": 1.7989,
      "step": 7
    },
    {
      "epoch": 0.03742690058479532,
      "grad_norm": 0.6902874708175659,
      "learning_rate": 0.00016,
      "loss": 1.6126,
      "step": 8
    },
    {
      "epoch": 0.042105263157894736,
      "grad_norm": 0.7306366562843323,
      "learning_rate": 0.00018,
      "loss": 1.5926,
      "step": 9
    },
    {
      "epoch": 0.04678362573099415,
      "grad_norm": 1.025001883506775,
      "learning_rate": 0.0002,
      "loss": 1.9494,
      "step": 10
    },
    {
      "epoch": 0.04678362573099415,
      "eval_loss": 1.5034407377243042,
      "eval_runtime": 21.985,
      "eval_samples_per_second": 4.094,
      "eval_steps_per_second": 2.047,
      "step": 10
    },
    {
      "epoch": 0.05146198830409357,
      "grad_norm": 0.668283998966217,
      "learning_rate": 0.00019781476007338058,
      "loss": 1.5648,
      "step": 11
    },
    {
      "epoch": 0.056140350877192984,
      "grad_norm": 0.5301951169967651,
      "learning_rate": 0.0001913545457642601,
      "loss": 1.6077,
      "step": 12
    },
    {
      "epoch": 0.0608187134502924,
      "grad_norm": 0.44159942865371704,
      "learning_rate": 0.00018090169943749476,
      "loss": 1.3352,
      "step": 13
    },
    {
      "epoch": 0.06549707602339182,
      "grad_norm": 0.4739885628223419,
      "learning_rate": 0.00016691306063588583,
      "loss": 1.3697,
      "step": 14
    },
    {
      "epoch": 0.07017543859649122,
      "grad_norm": 0.8631594181060791,
      "learning_rate": 0.00015000000000000001,
      "loss": 1.2833,
      "step": 15
    },
    {
      "epoch": 0.07017543859649122,
      "eval_loss": 1.2018710374832153,
      "eval_runtime": 21.9973,
      "eval_samples_per_second": 4.091,
      "eval_steps_per_second": 2.046,
      "step": 15
    },
    {
      "epoch": 0.07485380116959064,
      "grad_norm": 0.7966984510421753,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.4431,
      "step": 16
    },
    {
      "epoch": 0.07953216374269007,
      "grad_norm": 0.5668115019798279,
      "learning_rate": 0.00011045284632676536,
      "loss": 1.1548,
      "step": 17
    },
    {
      "epoch": 0.08421052631578947,
      "grad_norm": 0.5761730670928955,
      "learning_rate": 8.954715367323468e-05,
      "loss": 1.1111,
      "step": 18
    },
    {
      "epoch": 0.08888888888888889,
      "grad_norm": 0.5519751906394958,
      "learning_rate": 6.909830056250527e-05,
      "loss": 1.063,
      "step": 19
    },
    {
      "epoch": 0.0935672514619883,
      "grad_norm": 0.5273241400718689,
      "learning_rate": 5.000000000000002e-05,
      "loss": 0.903,
      "step": 20
    },
    {
      "epoch": 0.0935672514619883,
      "eval_loss": 1.019839882850647,
      "eval_runtime": 22.0266,
      "eval_samples_per_second": 4.086,
      "eval_steps_per_second": 2.043,
      "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": 1.060678819381248e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}