{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.02706359945872801,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0027063599458728013,
      "grad_norm": 0.32443684339523315,
      "learning_rate": 2e-05,
      "loss": 1.3979,
      "step": 1
    },
    {
      "epoch": 0.0027063599458728013,
      "eval_loss": 1.4137667417526245,
      "eval_runtime": 5.8401,
      "eval_samples_per_second": 26.712,
      "eval_steps_per_second": 13.356,
      "step": 1
    },
    {
      "epoch": 0.005412719891745603,
      "grad_norm": 0.26124775409698486,
      "learning_rate": 4e-05,
      "loss": 1.2556,
      "step": 2
    },
    {
      "epoch": 0.008119079837618403,
      "grad_norm": 0.2884213328361511,
      "learning_rate": 6e-05,
      "loss": 1.4124,
      "step": 3
    },
    {
      "epoch": 0.008119079837618403,
      "eval_loss": 1.4126904010772705,
      "eval_runtime": 5.8346,
      "eval_samples_per_second": 26.737,
      "eval_steps_per_second": 13.369,
      "step": 3
    },
    {
      "epoch": 0.010825439783491205,
      "grad_norm": 0.3139161765575409,
      "learning_rate": 8e-05,
      "loss": 1.5426,
      "step": 4
    },
    {
      "epoch": 0.013531799729364006,
      "grad_norm": 0.31540098786354065,
      "learning_rate": 0.0001,
      "loss": 1.4807,
      "step": 5
    },
    {
      "epoch": 0.016238159675236806,
      "grad_norm": 0.2986223101615906,
      "learning_rate": 0.00012,
      "loss": 1.3239,
      "step": 6
    },
    {
      "epoch": 0.016238159675236806,
      "eval_loss": 1.3981250524520874,
      "eval_runtime": 5.8546,
      "eval_samples_per_second": 26.646,
      "eval_steps_per_second": 13.323,
      "step": 6
    },
    {
      "epoch": 0.018944519621109608,
      "grad_norm": 0.34739425778388977,
      "learning_rate": 0.00014,
      "loss": 1.4735,
      "step": 7
    },
    {
      "epoch": 0.02165087956698241,
      "grad_norm": 0.32578620314598083,
      "learning_rate": 0.00016,
      "loss": 1.3163,
      "step": 8
    },
    {
      "epoch": 0.02435723951285521,
      "grad_norm": 0.34389108419418335,
      "learning_rate": 0.00018,
      "loss": 1.2615,
      "step": 9
    },
    {
      "epoch": 0.02435723951285521,
      "eval_loss": 1.355080485343933,
      "eval_runtime": 5.8402,
      "eval_samples_per_second": 26.711,
      "eval_steps_per_second": 13.356,
      "step": 9
    },
    {
      "epoch": 0.02706359945872801,
      "grad_norm": 0.3629644215106964,
      "learning_rate": 0.0002,
      "loss": 1.2916,
      "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": 1168569347604480.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}