{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.03989626969878316,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0007979253939756633,
      "eval_loss": 3.550355911254883,
      "eval_runtime": 35.5878,
      "eval_samples_per_second": 14.837,
      "eval_steps_per_second": 7.418,
      "step": 1
    },
    {
      "epoch": 0.003989626969878316,
      "grad_norm": 2.3659045696258545,
      "learning_rate": 5e-05,
      "loss": 3.7451,
      "step": 5
    },
    {
      "epoch": 0.007979253939756632,
      "grad_norm": 3.0315895080566406,
      "learning_rate": 0.0001,
      "loss": 3.4471,
      "step": 10
    },
    {
      "epoch": 0.007979253939756632,
      "eval_loss": 2.998976707458496,
      "eval_runtime": 35.8922,
      "eval_samples_per_second": 14.711,
      "eval_steps_per_second": 7.355,
      "step": 10
    },
    {
      "epoch": 0.011968880909634948,
      "grad_norm": 3.546405076980591,
      "learning_rate": 9.619397662556435e-05,
      "loss": 2.7101,
      "step": 15
    },
    {
      "epoch": 0.015958507879513265,
      "grad_norm": 3.569300651550293,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.9901,
      "step": 20
    },
    {
      "epoch": 0.015958507879513265,
      "eval_loss": 1.8978782892227173,
      "eval_runtime": 35.9973,
      "eval_samples_per_second": 14.668,
      "eval_steps_per_second": 7.334,
      "step": 20
    },
    {
      "epoch": 0.01994813484939158,
      "grad_norm": 2.9264533519744873,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.8919,
      "step": 25
    },
    {
      "epoch": 0.023937761819269897,
      "grad_norm": 2.423933267593384,
      "learning_rate": 5e-05,
      "loss": 1.6579,
      "step": 30
    },
    {
      "epoch": 0.023937761819269897,
      "eval_loss": 1.712278962135315,
      "eval_runtime": 36.1624,
      "eval_samples_per_second": 14.601,
      "eval_steps_per_second": 7.3,
      "step": 30
    },
    {
      "epoch": 0.027927388789148213,
      "grad_norm": 2.879720687866211,
      "learning_rate": 3.086582838174551e-05,
      "loss": 1.6744,
      "step": 35
    },
    {
      "epoch": 0.03191701575902653,
      "grad_norm": 3.020172357559204,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 1.6844,
      "step": 40
    },
    {
      "epoch": 0.03191701575902653,
      "eval_loss": 1.6592059135437012,
      "eval_runtime": 36.1399,
      "eval_samples_per_second": 14.61,
      "eval_steps_per_second": 7.305,
      "step": 40
    },
    {
      "epoch": 0.03590664272890485,
      "grad_norm": 2.4742209911346436,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 1.548,
      "step": 45
    },
    {
      "epoch": 0.03989626969878316,
      "grad_norm": 3.463620185852051,
      "learning_rate": 0.0,
      "loss": 1.6745,
      "step": 50
    },
    {
      "epoch": 0.03989626969878316,
      "eval_loss": 1.6493557691574097,
      "eval_runtime": 36.1191,
      "eval_samples_per_second": 14.618,
      "eval_steps_per_second": 7.309,
      "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": 9247821240729600.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}