{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00016848844801078326,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.6848844801078327e-05,
      "grad_norm": 0.5083303451538086,
      "learning_rate": 2e-05,
      "loss": 1.6191,
      "step": 1
    },
    {
      "epoch": 1.6848844801078327e-05,
      "eval_loss": 1.7950626611709595,
      "eval_runtime": 499.6109,
      "eval_samples_per_second": 50.019,
      "eval_steps_per_second": 25.009,
      "step": 1
    },
    {
      "epoch": 3.3697689602156655e-05,
      "grad_norm": 0.5246115922927856,
      "learning_rate": 4e-05,
      "loss": 1.9654,
      "step": 2
    },
    {
      "epoch": 5.0546534403234975e-05,
      "grad_norm": 0.48802676796913147,
      "learning_rate": 6e-05,
      "loss": 2.0547,
      "step": 3
    },
    {
      "epoch": 5.0546534403234975e-05,
      "eval_loss": 1.7945618629455566,
      "eval_runtime": 502.8767,
      "eval_samples_per_second": 49.694,
      "eval_steps_per_second": 24.847,
      "step": 3
    },
    {
      "epoch": 6.739537920431331e-05,
      "grad_norm": 0.5578922629356384,
      "learning_rate": 8e-05,
      "loss": 1.5347,
      "step": 4
    },
    {
      "epoch": 8.424422400539163e-05,
      "grad_norm": 0.5001427531242371,
      "learning_rate": 0.0001,
      "loss": 1.97,
      "step": 5
    },
    {
      "epoch": 0.00010109306880646995,
      "grad_norm": 0.5869404673576355,
      "learning_rate": 0.00012,
      "loss": 1.7278,
      "step": 6
    },
    {
      "epoch": 0.00010109306880646995,
      "eval_loss": 1.788482427597046,
      "eval_runtime": 506.1018,
      "eval_samples_per_second": 49.377,
      "eval_steps_per_second": 24.689,
      "step": 6
    },
    {
      "epoch": 0.00011794191360754829,
      "grad_norm": 0.4844641089439392,
      "learning_rate": 0.00014,
      "loss": 1.6189,
      "step": 7
    },
    {
      "epoch": 0.00013479075840862662,
      "grad_norm": 0.5195013284683228,
      "learning_rate": 0.00016,
      "loss": 1.7658,
      "step": 8
    },
    {
      "epoch": 0.00015163960320970494,
      "grad_norm": 0.5042082071304321,
      "learning_rate": 0.00018,
      "loss": 1.4831,
      "step": 9
    },
    {
      "epoch": 0.00015163960320970494,
      "eval_loss": 1.7677805423736572,
      "eval_runtime": 504.9623,
      "eval_samples_per_second": 49.489,
      "eval_steps_per_second": 24.744,
      "step": 9
    },
    {
      "epoch": 0.00016848844801078326,
      "grad_norm": 0.4741860032081604,
      "learning_rate": 0.0002,
      "loss": 1.3574,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 405048454545408.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}