{
  "best_metric": 0.3253360986709595,
  "best_model_checkpoint": "miner_id_24/checkpoint-400",
  "epoch": 0.1337736716692446,
  "eval_steps": 50,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0003344341791731115,
      "eval_loss": 0.7312062978744507,
      "eval_runtime": 439.8943,
      "eval_samples_per_second": 5.726,
      "eval_steps_per_second": 2.864,
      "step": 1
    },
    {
      "epoch": 0.01337736716692446,
      "grad_norm": 2.332235813140869,
      "learning_rate": 5e-05,
      "loss": 4.7411,
      "step": 40
    },
    {
      "epoch": 0.016721708958655573,
      "eval_loss": 0.4725048542022705,
      "eval_runtime": 439.5473,
      "eval_samples_per_second": 5.731,
      "eval_steps_per_second": 2.867,
      "step": 50
    },
    {
      "epoch": 0.02675473433384892,
      "grad_norm": 1.626213788986206,
      "learning_rate": 0.0001,
      "loss": 3.3872,
      "step": 80
    },
    {
      "epoch": 0.03344341791731115,
      "eval_loss": 0.3751484453678131,
      "eval_runtime": 439.5097,
      "eval_samples_per_second": 5.731,
      "eval_steps_per_second": 2.867,
      "step": 100
    },
    {
      "epoch": 0.04013210150077338,
      "grad_norm": 1.2483749389648438,
      "learning_rate": 9.619397662556435e-05,
      "loss": 2.9375,
      "step": 120
    },
    {
      "epoch": 0.05016512687596673,
      "eval_loss": 0.3482409119606018,
      "eval_runtime": 440.0707,
      "eval_samples_per_second": 5.724,
      "eval_steps_per_second": 2.863,
      "step": 150
    },
    {
      "epoch": 0.05350946866769784,
      "grad_norm": 0.8327760696411133,
      "learning_rate": 8.535533905932738e-05,
      "loss": 2.7625,
      "step": 160
    },
    {
      "epoch": 0.0668868358346223,
      "grad_norm": 2.1962201595306396,
      "learning_rate": 6.91341716182545e-05,
      "loss": 2.7577,
      "step": 200
    },
    {
      "epoch": 0.0668868358346223,
      "eval_loss": 0.3451964855194092,
      "eval_runtime": 439.2046,
      "eval_samples_per_second": 5.735,
      "eval_steps_per_second": 2.869,
      "step": 200
    },
    {
      "epoch": 0.08026420300154676,
      "grad_norm": 1.2397370338439941,
      "learning_rate": 5e-05,
      "loss": 2.7601,
      "step": 240
    },
    {
      "epoch": 0.08360854479327787,
      "eval_loss": 0.3331269323825836,
      "eval_runtime": 440.4764,
      "eval_samples_per_second": 5.719,
      "eval_steps_per_second": 2.861,
      "step": 250
    },
    {
      "epoch": 0.09364157016847122,
      "grad_norm": 1.2288343906402588,
      "learning_rate": 3.086582838174551e-05,
      "loss": 2.6538,
      "step": 280
    },
    {
      "epoch": 0.10033025375193345,
      "eval_loss": 0.3297315835952759,
      "eval_runtime": 439.6346,
      "eval_samples_per_second": 5.73,
      "eval_steps_per_second": 2.866,
      "step": 300
    },
    {
      "epoch": 0.10701893733539568,
      "grad_norm": 0.9799840450286865,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 2.6739,
      "step": 320
    },
    {
      "epoch": 0.11705196271058903,
      "eval_loss": 0.3258623778820038,
      "eval_runtime": 439.5044,
      "eval_samples_per_second": 5.731,
      "eval_steps_per_second": 2.867,
      "step": 350
    },
    {
      "epoch": 0.12039630450232014,
      "grad_norm": 0.873311460018158,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 2.5675,
      "step": 360
    },
    {
      "epoch": 0.1337736716692446,
      "grad_norm": 2.368913173675537,
      "learning_rate": 0.0,
      "loss": 2.5945,
      "step": 400
    },
    {
      "epoch": 0.1337736716692446,
      "eval_loss": 0.3253360986709595,
      "eval_runtime": 440.2156,
      "eval_samples_per_second": 5.722,
      "eval_steps_per_second": 2.862,
      "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": 5.10287413248e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}