{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.99660441426146,
  "eval_steps": 50,
  "global_step": 294,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07,
      "learning_rate": 5e-05,
      "loss": 1.1822,
      "step": 10
    },
    {
      "epoch": 0.14,
      "learning_rate": 5e-05,
      "loss": 1.1478,
      "step": 20
    },
    {
      "epoch": 0.2,
      "learning_rate": 5e-05,
      "loss": 1.1308,
      "step": 30
    },
    {
      "epoch": 0.27,
      "learning_rate": 5e-05,
      "loss": 1.094,
      "step": 40
    },
    {
      "epoch": 0.34,
      "learning_rate": 5e-05,
      "loss": 1.0987,
      "step": 50
    },
    {
      "epoch": 0.34,
      "eval_loss": 1.1459416151046753,
      "eval_runtime": 15.7067,
      "eval_samples_per_second": 16.681,
      "eval_steps_per_second": 4.202,
      "step": 50
    },
    {
      "epoch": 0.41,
      "learning_rate": 5e-05,
      "loss": 1.091,
      "step": 60
    },
    {
      "epoch": 0.48,
      "learning_rate": 5e-05,
      "loss": 1.0768,
      "step": 70
    },
    {
      "epoch": 0.54,
      "learning_rate": 5e-05,
      "loss": 1.1162,
      "step": 80
    },
    {
      "epoch": 0.61,
      "learning_rate": 5e-05,
      "loss": 1.1089,
      "step": 90
    },
    {
      "epoch": 0.68,
      "learning_rate": 5e-05,
      "loss": 1.0626,
      "step": 100
    },
    {
      "epoch": 0.68,
      "eval_loss": 1.1253658533096313,
      "eval_runtime": 15.7126,
      "eval_samples_per_second": 16.675,
      "eval_steps_per_second": 4.2,
      "step": 100
    },
    {
      "epoch": 0.75,
      "learning_rate": 5e-05,
      "loss": 1.0439,
      "step": 110
    },
    {
      "epoch": 0.81,
      "learning_rate": 5e-05,
      "loss": 1.1029,
      "step": 120
    },
    {
      "epoch": 0.88,
      "learning_rate": 5e-05,
      "loss": 1.0928,
      "step": 130
    },
    {
      "epoch": 0.95,
      "learning_rate": 5e-05,
      "loss": 1.0686,
      "step": 140
    },
    {
      "epoch": 1.02,
      "learning_rate": 5e-05,
      "loss": 1.0187,
      "step": 150
    },
    {
      "epoch": 1.02,
      "eval_loss": 1.1222176551818848,
      "eval_runtime": 15.6889,
      "eval_samples_per_second": 16.7,
      "eval_steps_per_second": 4.207,
      "step": 150
    },
    {
      "epoch": 1.09,
      "learning_rate": 5e-05,
      "loss": 0.942,
      "step": 160
    },
    {
      "epoch": 1.15,
      "learning_rate": 5e-05,
      "loss": 1.0005,
      "step": 170
    },
    {
      "epoch": 1.22,
      "learning_rate": 5e-05,
      "loss": 0.9174,
      "step": 180
    },
    {
      "epoch": 1.29,
      "learning_rate": 5e-05,
      "loss": 0.8886,
      "step": 190
    },
    {
      "epoch": 1.36,
      "learning_rate": 5e-05,
      "loss": 0.9514,
      "step": 200
    },
    {
      "epoch": 1.36,
      "eval_loss": 1.1442124843597412,
      "eval_runtime": 15.651,
      "eval_samples_per_second": 16.74,
      "eval_steps_per_second": 4.217,
      "step": 200
    },
    {
      "epoch": 1.43,
      "learning_rate": 5e-05,
      "loss": 0.924,
      "step": 210
    },
    {
      "epoch": 1.49,
      "learning_rate": 5e-05,
      "loss": 0.8387,
      "step": 220
    },
    {
      "epoch": 1.56,
      "learning_rate": 5e-05,
      "loss": 0.9263,
      "step": 230
    },
    {
      "epoch": 1.63,
      "learning_rate": 5e-05,
      "loss": 0.931,
      "step": 240
    },
    {
      "epoch": 1.7,
      "learning_rate": 5e-05,
      "loss": 0.9601,
      "step": 250
    },
    {
      "epoch": 1.7,
      "eval_loss": 1.1440547704696655,
      "eval_runtime": 15.6553,
      "eval_samples_per_second": 16.736,
      "eval_steps_per_second": 4.216,
      "step": 250
    },
    {
      "epoch": 1.77,
      "learning_rate": 5e-05,
      "loss": 0.8996,
      "step": 260
    },
    {
      "epoch": 1.83,
      "learning_rate": 5e-05,
      "loss": 0.9777,
      "step": 270
    },
    {
      "epoch": 1.9,
      "learning_rate": 5e-05,
      "loss": 0.8971,
      "step": 280
    },
    {
      "epoch": 1.97,
      "learning_rate": 5e-05,
      "loss": 0.8609,
      "step": 290
    },
    {
      "epoch": 2.0,
      "step": 294,
      "total_flos": 7.002531209517466e+16,
      "train_loss": 1.0092324691564858,
      "train_runtime": 861.2997,
      "train_samples_per_second": 5.471,
      "train_steps_per_second": 0.341
    }
  ],
  "logging_steps": 10,
  "max_steps": 294,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 250,
  "total_flos": 7.002531209517466e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}