{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0001302057902514925,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.3020579025149248e-05,
      "grad_norm": 1.3535698652267456,
      "learning_rate": 2e-05,
      "loss": 1.3685,
      "step": 1
    },
    {
      "epoch": 1.3020579025149248e-05,
      "eval_loss": 1.521296739578247,
      "eval_runtime": 2179.5424,
      "eval_samples_per_second": 14.837,
      "eval_steps_per_second": 7.419,
      "step": 1
    },
    {
      "epoch": 2.6041158050298496e-05,
      "grad_norm": 0.8286046385765076,
      "learning_rate": 4e-05,
      "loss": 0.8329,
      "step": 2
    },
    {
      "epoch": 3.9061737075447746e-05,
      "grad_norm": 1.8428291082382202,
      "learning_rate": 6e-05,
      "loss": 1.4173,
      "step": 3
    },
    {
      "epoch": 3.9061737075447746e-05,
      "eval_loss": 1.509873628616333,
      "eval_runtime": 2179.678,
      "eval_samples_per_second": 14.836,
      "eval_steps_per_second": 7.418,
      "step": 3
    },
    {
      "epoch": 5.208231610059699e-05,
      "grad_norm": 0.667485773563385,
      "learning_rate": 8e-05,
      "loss": 0.669,
      "step": 4
    },
    {
      "epoch": 6.510289512574625e-05,
      "grad_norm": 1.0668361186981201,
      "learning_rate": 0.0001,
      "loss": 1.3146,
      "step": 5
    },
    {
      "epoch": 7.812347415089549e-05,
      "grad_norm": 1.5297046899795532,
      "learning_rate": 0.00012,
      "loss": 1.214,
      "step": 6
    },
    {
      "epoch": 7.812347415089549e-05,
      "eval_loss": 1.3064848184585571,
      "eval_runtime": 2182.1026,
      "eval_samples_per_second": 14.82,
      "eval_steps_per_second": 7.41,
      "step": 6
    },
    {
      "epoch": 9.114405317604474e-05,
      "grad_norm": 1.0010603666305542,
      "learning_rate": 0.00014,
      "loss": 0.9171,
      "step": 7
    },
    {
      "epoch": 0.00010416463220119398,
      "grad_norm": 1.1102145910263062,
      "learning_rate": 0.00016,
      "loss": 1.0455,
      "step": 8
    },
    {
      "epoch": 0.00011718521122634323,
      "grad_norm": 2.4663655757904053,
      "learning_rate": 0.00018,
      "loss": 1.1359,
      "step": 9
    },
    {
      "epoch": 0.00011718521122634323,
      "eval_loss": 0.8952555060386658,
      "eval_runtime": 2178.9639,
      "eval_samples_per_second": 14.841,
      "eval_steps_per_second": 7.42,
      "step": 9
    },
    {
      "epoch": 0.0001302057902514925,
      "grad_norm": 1.6312642097473145,
      "learning_rate": 0.0002,
      "loss": 0.5381,
      "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": 1942042460553216.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}