{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0020407746780677946,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 4.081549356135589e-05,
      "eval_loss": 1.783031940460205,
      "eval_runtime": 1490.7954,
      "eval_samples_per_second": 6.92,
      "eval_steps_per_second": 3.46,
      "step": 1
    },
    {
      "epoch": 0.00020407746780677944,
      "grad_norm": 1.1358250379562378,
      "learning_rate": 5e-05,
      "loss": 1.8336,
      "step": 5
    },
    {
      "epoch": 0.0004081549356135589,
      "grad_norm": 1.4730448722839355,
      "learning_rate": 0.0001,
      "loss": 1.804,
      "step": 10
    },
    {
      "epoch": 0.0004081549356135589,
      "eval_loss": 1.7141697406768799,
      "eval_runtime": 1496.0235,
      "eval_samples_per_second": 6.896,
      "eval_steps_per_second": 3.448,
      "step": 10
    },
    {
      "epoch": 0.0006122324034203384,
      "grad_norm": 1.3064950704574585,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.8378,
      "step": 15
    },
    {
      "epoch": 0.0008163098712271178,
      "grad_norm": 1.7653350830078125,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.5214,
      "step": 20
    },
    {
      "epoch": 0.0008163098712271178,
      "eval_loss": 1.6844457387924194,
      "eval_runtime": 1495.8243,
      "eval_samples_per_second": 6.897,
      "eval_steps_per_second": 3.448,
      "step": 20
    },
    {
      "epoch": 0.0010203873390338973,
      "grad_norm": 1.158118724822998,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.69,
      "step": 25
    },
    {
      "epoch": 0.0012244648068406767,
      "grad_norm": 1.4648447036743164,
      "learning_rate": 5e-05,
      "loss": 1.753,
      "step": 30
    },
    {
      "epoch": 0.0012244648068406767,
      "eval_loss": 1.6742535829544067,
      "eval_runtime": 1495.9089,
      "eval_samples_per_second": 6.896,
      "eval_steps_per_second": 3.448,
      "step": 30
    },
    {
      "epoch": 0.0014285422746474561,
      "grad_norm": 1.519839882850647,
      "learning_rate": 3.086582838174551e-05,
      "loss": 1.5664,
      "step": 35
    },
    {
      "epoch": 0.0016326197424542355,
      "grad_norm": 1.042401671409607,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 1.5862,
      "step": 40
    },
    {
      "epoch": 0.0016326197424542355,
      "eval_loss": 1.6705114841461182,
      "eval_runtime": 1502.9965,
      "eval_samples_per_second": 6.864,
      "eval_steps_per_second": 3.432,
      "step": 40
    },
    {
      "epoch": 0.0018366972102610152,
      "grad_norm": 1.2911733388900757,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 1.6206,
      "step": 45
    },
    {
      "epoch": 0.0020407746780677946,
      "grad_norm": 1.0840606689453125,
      "learning_rate": 0.0,
      "loss": 1.5961,
      "step": 50
    },
    {
      "epoch": 0.0020407746780677946,
      "eval_loss": 1.6692533493041992,
      "eval_runtime": 1501.158,
      "eval_samples_per_second": 6.872,
      "eval_steps_per_second": 3.436,
      "step": 50
    }
  ],
  "logging_steps": 5,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 13,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.036767093325824e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}