{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 100,
  "global_step": 1250,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08,
      "grad_norm": 1.8024471998214722,
      "learning_rate": 9.232000000000001e-05,
      "loss": 3.5517,
      "step": 100
    },
    {
      "epoch": 0.08,
      "eval_runtime": 87.7705,
      "eval_samples_per_second": 11.393,
      "eval_steps_per_second": 2.848,
      "step": 100
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.6744942665100098,
      "learning_rate": 8.431999999999999e-05,
      "loss": 2.1197,
      "step": 200
    },
    {
      "epoch": 0.16,
      "eval_runtime": 87.8063,
      "eval_samples_per_second": 11.389,
      "eval_steps_per_second": 2.847,
      "step": 200
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.7477216124534607,
      "learning_rate": 7.632e-05,
      "loss": 1.9757,
      "step": 300
    },
    {
      "epoch": 0.24,
      "eval_runtime": 87.9532,
      "eval_samples_per_second": 11.37,
      "eval_steps_per_second": 2.842,
      "step": 300
    },
    {
      "epoch": 0.32,
      "grad_norm": 2.347344160079956,
      "learning_rate": 6.832000000000001e-05,
      "loss": 1.9568,
      "step": 400
    },
    {
      "epoch": 0.32,
      "eval_runtime": 87.9668,
      "eval_samples_per_second": 11.368,
      "eval_steps_per_second": 2.842,
      "step": 400
    },
    {
      "epoch": 0.4,
      "grad_norm": 1.8626798391342163,
      "learning_rate": 6.032e-05,
      "loss": 1.9512,
      "step": 500
    },
    {
      "epoch": 0.4,
      "eval_runtime": 88.0332,
      "eval_samples_per_second": 11.359,
      "eval_steps_per_second": 2.84,
      "step": 500
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.7776954174041748,
      "learning_rate": 5.232e-05,
      "loss": 1.9545,
      "step": 600
    },
    {
      "epoch": 0.48,
      "eval_runtime": 88.0187,
      "eval_samples_per_second": 11.361,
      "eval_steps_per_second": 2.84,
      "step": 600
    },
    {
      "epoch": 0.56,
      "grad_norm": 1.4220548868179321,
      "learning_rate": 4.432e-05,
      "loss": 1.9591,
      "step": 700
    },
    {
      "epoch": 0.56,
      "eval_runtime": 88.1299,
      "eval_samples_per_second": 11.347,
      "eval_steps_per_second": 2.837,
      "step": 700
    },
    {
      "epoch": 0.64,
      "grad_norm": 2.3337080478668213,
      "learning_rate": 3.6320000000000005e-05,
      "loss": 1.951,
      "step": 800
    },
    {
      "epoch": 0.64,
      "eval_runtime": 88.1046,
      "eval_samples_per_second": 11.35,
      "eval_steps_per_second": 2.838,
      "step": 800
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.8959614634513855,
      "learning_rate": 2.8320000000000003e-05,
      "loss": 1.988,
      "step": 900
    },
    {
      "epoch": 0.72,
      "eval_runtime": 87.9785,
      "eval_samples_per_second": 11.366,
      "eval_steps_per_second": 2.842,
      "step": 900
    },
    {
      "epoch": 0.8,
      "grad_norm": 1.1870672702789307,
      "learning_rate": 2.032e-05,
      "loss": 1.9763,
      "step": 1000
    },
    {
      "epoch": 0.8,
      "eval_runtime": 87.7334,
      "eval_samples_per_second": 11.398,
      "eval_steps_per_second": 2.85,
      "step": 1000
    },
    {
      "epoch": 0.88,
      "grad_norm": 1.0990030765533447,
      "learning_rate": 1.232e-05,
      "loss": 1.9048,
      "step": 1100
    },
    {
      "epoch": 0.88,
      "eval_runtime": 87.772,
      "eval_samples_per_second": 11.393,
      "eval_steps_per_second": 2.848,
      "step": 1100
    },
    {
      "epoch": 0.96,
      "grad_norm": 4.1690354347229,
      "learning_rate": 4.32e-06,
      "loss": 1.9114,
      "step": 1200
    },
    {
      "epoch": 0.96,
      "eval_runtime": 88.1794,
      "eval_samples_per_second": 11.341,
      "eval_steps_per_second": 2.835,
      "step": 1200
    }
  ],
  "logging_steps": 100,
  "max_steps": 1250,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.660886380544e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}