{
  "best_metric": 3.285201072692871,
  "best_model_checkpoint": "miner_id_24/checkpoint-350",
  "epoch": 0.05614724615303634,
  "eval_steps": 50,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00014036811538259083,
      "eval_loss": 6.529122352600098,
      "eval_runtime": 171.8991,
      "eval_samples_per_second": 34.904,
      "eval_steps_per_second": 17.452,
      "step": 1
    },
    {
      "epoch": 0.005614724615303634,
      "grad_norm": 46.951602935791016,
      "learning_rate": 5e-05,
      "loss": 4.7112,
      "step": 40
    },
    {
      "epoch": 0.007018405769129542,
      "eval_loss": 4.592189311981201,
      "eval_runtime": 171.3774,
      "eval_samples_per_second": 35.01,
      "eval_steps_per_second": 17.505,
      "step": 50
    },
    {
      "epoch": 0.011229449230607268,
      "grad_norm": 6.948583602905273,
      "learning_rate": 0.0001,
      "loss": 3.9305,
      "step": 80
    },
    {
      "epoch": 0.014036811538259085,
      "eval_loss": 4.206540584564209,
      "eval_runtime": 171.2138,
      "eval_samples_per_second": 35.044,
      "eval_steps_per_second": 17.522,
      "step": 100
    },
    {
      "epoch": 0.0168441738459109,
      "grad_norm": 6.022707939147949,
      "learning_rate": 9.619397662556435e-05,
      "loss": 3.7357,
      "step": 120
    },
    {
      "epoch": 0.021055217307388626,
      "eval_loss": 3.9149367809295654,
      "eval_runtime": 191.6303,
      "eval_samples_per_second": 31.31,
      "eval_steps_per_second": 15.655,
      "step": 150
    },
    {
      "epoch": 0.022458898461214537,
      "grad_norm": 3.967310905456543,
      "learning_rate": 8.535533905932738e-05,
      "loss": 3.6472,
      "step": 160
    },
    {
      "epoch": 0.02807362307651817,
      "grad_norm": 13.528217315673828,
      "learning_rate": 6.91341716182545e-05,
      "loss": 3.4347,
      "step": 200
    },
    {
      "epoch": 0.02807362307651817,
      "eval_loss": 3.6447789669036865,
      "eval_runtime": 167.6701,
      "eval_samples_per_second": 35.785,
      "eval_steps_per_second": 17.892,
      "step": 200
    },
    {
      "epoch": 0.0336883476918218,
      "grad_norm": 6.799312114715576,
      "learning_rate": 5e-05,
      "loss": 3.2623,
      "step": 240
    },
    {
      "epoch": 0.03509202884564771,
      "eval_loss": 3.4938066005706787,
      "eval_runtime": 167.9683,
      "eval_samples_per_second": 35.721,
      "eval_steps_per_second": 17.861,
      "step": 250
    },
    {
      "epoch": 0.03930307230712544,
      "grad_norm": 5.59036922454834,
      "learning_rate": 3.086582838174551e-05,
      "loss": 3.3819,
      "step": 280
    },
    {
      "epoch": 0.04211043461477725,
      "eval_loss": 3.3484914302825928,
      "eval_runtime": 168.5191,
      "eval_samples_per_second": 35.604,
      "eval_steps_per_second": 17.802,
      "step": 300
    },
    {
      "epoch": 0.044917796922429074,
      "grad_norm": 4.221907138824463,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 3.3763,
      "step": 320
    },
    {
      "epoch": 0.049128840383906795,
      "eval_loss": 3.285201072692871,
      "eval_runtime": 172.4832,
      "eval_samples_per_second": 34.786,
      "eval_steps_per_second": 17.393,
      "step": 350
    },
    {
      "epoch": 0.0505325215377327,
      "grad_norm": 4.121219635009766,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 3.416,
      "step": 360
    },
    {
      "epoch": 0.05614724615303634,
      "grad_norm": 15.960735321044922,
      "learning_rate": 0.0,
      "loss": 3.3604,
      "step": 400
    },
    {
      "epoch": 0.05614724615303634,
      "eval_loss": 3.2854654788970947,
      "eval_runtime": 172.9851,
      "eval_samples_per_second": 34.685,
      "eval_steps_per_second": 17.343,
      "step": 400
    }
  ],
  "logging_steps": 40,
  "max_steps": 400,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 1
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 7382522816102400.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}