{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 6.0,
  "eval_steps": 50,
  "global_step": 450,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.33,
      "learning_rate": 5.2354709418837674e-05,
      "loss": 1.6331,
      "step": 25
    },
    {
      "epoch": 0.67,
      "learning_rate": 4.959919839679359e-05,
      "loss": 0.8124,
      "step": 50
    },
    {
      "epoch": 0.67,
      "eval_loss": 2.1140503883361816,
      "eval_runtime": 11.8386,
      "eval_samples_per_second": 0.76,
      "eval_steps_per_second": 0.169,
      "step": 50
    },
    {
      "epoch": 1.0,
      "learning_rate": 4.68436873747495e-05,
      "loss": 0.766,
      "step": 75
    },
    {
      "epoch": 1.33,
      "learning_rate": 4.408817635270541e-05,
      "loss": 0.562,
      "step": 100
    },
    {
      "epoch": 1.33,
      "eval_loss": 1.9290642738342285,
      "eval_runtime": 11.9715,
      "eval_samples_per_second": 0.752,
      "eval_steps_per_second": 0.167,
      "step": 100
    },
    {
      "epoch": 1.67,
      "learning_rate": 4.133266533066132e-05,
      "loss": 0.3301,
      "step": 125
    },
    {
      "epoch": 2.0,
      "learning_rate": 3.8577154308617235e-05,
      "loss": 0.3811,
      "step": 150
    },
    {
      "epoch": 2.0,
      "eval_loss": 2.065908908843994,
      "eval_runtime": 11.9277,
      "eval_samples_per_second": 0.755,
      "eval_steps_per_second": 0.168,
      "step": 150
    },
    {
      "epoch": 2.33,
      "learning_rate": 3.582164328657315e-05,
      "loss": 0.3086,
      "step": 175
    },
    {
      "epoch": 2.67,
      "learning_rate": 3.306613226452906e-05,
      "loss": 0.2969,
      "step": 200
    },
    {
      "epoch": 2.67,
      "eval_loss": 2.2028963565826416,
      "eval_runtime": 11.9591,
      "eval_samples_per_second": 0.753,
      "eval_steps_per_second": 0.167,
      "step": 200
    },
    {
      "epoch": 3.0,
      "learning_rate": 3.0310621242484972e-05,
      "loss": 0.2236,
      "step": 225
    },
    {
      "epoch": 3.33,
      "learning_rate": 2.755511022044088e-05,
      "loss": 0.2148,
      "step": 250
    },
    {
      "epoch": 3.33,
      "eval_loss": 2.3397459983825684,
      "eval_runtime": 11.8913,
      "eval_samples_per_second": 0.757,
      "eval_steps_per_second": 0.168,
      "step": 250
    },
    {
      "epoch": 3.67,
      "learning_rate": 2.4799599198396796e-05,
      "loss": 0.1813,
      "step": 275
    },
    {
      "epoch": 4.0,
      "learning_rate": 2.2044088176352705e-05,
      "loss": 0.2172,
      "step": 300
    },
    {
      "epoch": 4.0,
      "eval_loss": 2.2869534492492676,
      "eval_runtime": 11.8718,
      "eval_samples_per_second": 0.758,
      "eval_steps_per_second": 0.168,
      "step": 300
    },
    {
      "epoch": 4.33,
      "learning_rate": 1.9288577154308618e-05,
      "loss": 0.1436,
      "step": 325
    },
    {
      "epoch": 4.67,
      "learning_rate": 1.653306613226453e-05,
      "loss": 0.1659,
      "step": 350
    },
    {
      "epoch": 4.67,
      "eval_loss": 2.3965632915496826,
      "eval_runtime": 11.9151,
      "eval_samples_per_second": 0.755,
      "eval_steps_per_second": 0.168,
      "step": 350
    },
    {
      "epoch": 5.0,
      "learning_rate": 1.377755511022044e-05,
      "loss": 0.1664,
      "step": 375
    },
    {
      "epoch": 5.33,
      "learning_rate": 1.1022044088176353e-05,
      "loss": 0.1165,
      "step": 400
    },
    {
      "epoch": 5.33,
      "eval_loss": 2.4968247413635254,
      "eval_runtime": 11.858,
      "eval_samples_per_second": 0.759,
      "eval_steps_per_second": 0.169,
      "step": 400
    },
    {
      "epoch": 5.67,
      "learning_rate": 8.266533066132265e-06,
      "loss": 0.1572,
      "step": 425
    },
    {
      "epoch": 6.0,
      "learning_rate": 5.511022044088176e-06,
      "loss": 0.1174,
      "step": 450
    },
    {
      "epoch": 6.0,
      "eval_loss": 2.4439687728881836,
      "eval_runtime": 11.9003,
      "eval_samples_per_second": 0.756,
      "eval_steps_per_second": 0.168,
      "step": 450
    }
  ],
  "logging_steps": 25,
  "max_steps": 500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 7,
  "save_steps": 50,
  "total_flos": 1.104886503936e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}