{
  "best_metric": 1.5678154230117798,
  "best_model_checkpoint": "miner_id_24/checkpoint-400",
  "epoch": 0.02466281310211946,
  "eval_steps": 50,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 6.165703275529865e-05,
      "eval_loss": 2.288787603378296,
      "eval_runtime": 1041.9153,
      "eval_samples_per_second": 13.109,
      "eval_steps_per_second": 6.554,
      "step": 1
    },
    {
      "epoch": 0.0024662813102119463,
      "grad_norm": 1.1392245292663574,
      "learning_rate": 5e-05,
      "loss": 1.8648,
      "step": 40
    },
    {
      "epoch": 0.0030828516377649326,
      "eval_loss": 1.6245982646942139,
      "eval_runtime": 1041.7956,
      "eval_samples_per_second": 13.11,
      "eval_steps_per_second": 6.555,
      "step": 50
    },
    {
      "epoch": 0.0049325626204238925,
      "grad_norm": 1.1976816654205322,
      "learning_rate": 0.0001,
      "loss": 1.6089,
      "step": 80
    },
    {
      "epoch": 0.006165703275529865,
      "eval_loss": 1.608966588973999,
      "eval_runtime": 1041.4182,
      "eval_samples_per_second": 13.115,
      "eval_steps_per_second": 6.557,
      "step": 100
    },
    {
      "epoch": 0.007398843930635838,
      "grad_norm": 0.9106088876724243,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.5941,
      "step": 120
    },
    {
      "epoch": 0.009248554913294798,
      "eval_loss": 1.6026890277862549,
      "eval_runtime": 1041.2784,
      "eval_samples_per_second": 13.117,
      "eval_steps_per_second": 6.558,
      "step": 150
    },
    {
      "epoch": 0.009865125240847785,
      "grad_norm": 1.0939823389053345,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.6436,
      "step": 160
    },
    {
      "epoch": 0.01233140655105973,
      "grad_norm": 1.1950139999389648,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.5907,
      "step": 200
    },
    {
      "epoch": 0.01233140655105973,
      "eval_loss": 1.5895808935165405,
      "eval_runtime": 1041.3859,
      "eval_samples_per_second": 13.115,
      "eval_steps_per_second": 6.558,
      "step": 200
    },
    {
      "epoch": 0.014797687861271676,
      "grad_norm": 0.8904630541801453,
      "learning_rate": 5e-05,
      "loss": 1.587,
      "step": 240
    },
    {
      "epoch": 0.015414258188824663,
      "eval_loss": 1.5806567668914795,
      "eval_runtime": 1041.1372,
      "eval_samples_per_second": 13.118,
      "eval_steps_per_second": 6.559,
      "step": 250
    },
    {
      "epoch": 0.017263969171483623,
      "grad_norm": 0.8200499415397644,
      "learning_rate": 3.086582838174551e-05,
      "loss": 1.6022,
      "step": 280
    },
    {
      "epoch": 0.018497109826589597,
      "eval_loss": 1.5710722208023071,
      "eval_runtime": 1041.1766,
      "eval_samples_per_second": 13.118,
      "eval_steps_per_second": 6.559,
      "step": 300
    },
    {
      "epoch": 0.01973025048169557,
      "grad_norm": 0.7950920462608337,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 1.606,
      "step": 320
    },
    {
      "epoch": 0.02157996146435453,
      "eval_loss": 1.5714285373687744,
      "eval_runtime": 1042.0279,
      "eval_samples_per_second": 13.107,
      "eval_steps_per_second": 6.554,
      "step": 350
    },
    {
      "epoch": 0.022196531791907514,
      "grad_norm": 0.8112738728523254,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 1.6334,
      "step": 360
    },
    {
      "epoch": 0.02466281310211946,
      "grad_norm": 1.1077427864074707,
      "learning_rate": 0.0,
      "loss": 1.6116,
      "step": 400
    },
    {
      "epoch": 0.02466281310211946,
      "eval_loss": 1.5678154230117798,
      "eval_runtime": 1040.5356,
      "eval_samples_per_second": 13.126,
      "eval_steps_per_second": 6.563,
      "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": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.635628799188009e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}