{
  "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": 3e-05,
      "loss": 1.2187,
      "step": 10
    },
    {
      "epoch": 0.14,
      "learning_rate": 3e-05,
      "loss": 1.1481,
      "step": 20
    },
    {
      "epoch": 0.2,
      "learning_rate": 3e-05,
      "loss": 1.1437,
      "step": 30
    },
    {
      "epoch": 0.27,
      "learning_rate": 3e-05,
      "loss": 1.1076,
      "step": 40
    },
    {
      "epoch": 0.34,
      "learning_rate": 3e-05,
      "loss": 1.1066,
      "step": 50
    },
    {
      "epoch": 0.34,
      "eval_loss": 1.1555328369140625,
      "eval_runtime": 15.6804,
      "eval_samples_per_second": 16.709,
      "eval_steps_per_second": 4.209,
      "step": 50
    },
    {
      "epoch": 0.41,
      "learning_rate": 3e-05,
      "loss": 1.0988,
      "step": 60
    },
    {
      "epoch": 0.48,
      "learning_rate": 3e-05,
      "loss": 1.0917,
      "step": 70
    },
    {
      "epoch": 0.54,
      "learning_rate": 3e-05,
      "loss": 1.1344,
      "step": 80
    },
    {
      "epoch": 0.61,
      "learning_rate": 3e-05,
      "loss": 1.1167,
      "step": 90
    },
    {
      "epoch": 0.68,
      "learning_rate": 3e-05,
      "loss": 1.0655,
      "step": 100
    },
    {
      "epoch": 0.68,
      "eval_loss": 1.133277177810669,
      "eval_runtime": 15.7203,
      "eval_samples_per_second": 16.666,
      "eval_steps_per_second": 4.198,
      "step": 100
    },
    {
      "epoch": 0.75,
      "learning_rate": 3e-05,
      "loss": 1.0595,
      "step": 110
    },
    {
      "epoch": 0.81,
      "learning_rate": 3e-05,
      "loss": 1.1085,
      "step": 120
    },
    {
      "epoch": 0.88,
      "learning_rate": 3e-05,
      "loss": 1.0945,
      "step": 130
    },
    {
      "epoch": 0.95,
      "learning_rate": 3e-05,
      "loss": 1.0726,
      "step": 140
    },
    {
      "epoch": 1.02,
      "learning_rate": 3e-05,
      "loss": 1.039,
      "step": 150
    },
    {
      "epoch": 1.02,
      "eval_loss": 1.1278975009918213,
      "eval_runtime": 15.7982,
      "eval_samples_per_second": 16.584,
      "eval_steps_per_second": 4.178,
      "step": 150
    },
    {
      "epoch": 1.09,
      "learning_rate": 3e-05,
      "loss": 0.9891,
      "step": 160
    },
    {
      "epoch": 1.15,
      "learning_rate": 3e-05,
      "loss": 1.0617,
      "step": 170
    },
    {
      "epoch": 1.22,
      "learning_rate": 3e-05,
      "loss": 0.98,
      "step": 180
    },
    {
      "epoch": 1.29,
      "learning_rate": 3e-05,
      "loss": 0.9531,
      "step": 190
    },
    {
      "epoch": 1.36,
      "learning_rate": 3e-05,
      "loss": 1.0166,
      "step": 200
    },
    {
      "epoch": 1.36,
      "eval_loss": 1.1301459074020386,
      "eval_runtime": 15.7471,
      "eval_samples_per_second": 16.638,
      "eval_steps_per_second": 4.191,
      "step": 200
    },
    {
      "epoch": 1.43,
      "learning_rate": 3e-05,
      "loss": 0.9869,
      "step": 210
    },
    {
      "epoch": 1.49,
      "learning_rate": 3e-05,
      "loss": 0.9066,
      "step": 220
    },
    {
      "epoch": 1.56,
      "learning_rate": 3e-05,
      "loss": 0.9884,
      "step": 230
    },
    {
      "epoch": 1.63,
      "learning_rate": 3e-05,
      "loss": 0.9885,
      "step": 240
    },
    {
      "epoch": 1.7,
      "learning_rate": 3e-05,
      "loss": 1.0281,
      "step": 250
    },
    {
      "epoch": 1.7,
      "eval_loss": 1.1312241554260254,
      "eval_runtime": 15.6611,
      "eval_samples_per_second": 16.729,
      "eval_steps_per_second": 4.214,
      "step": 250
    },
    {
      "epoch": 1.77,
      "learning_rate": 3e-05,
      "loss": 0.9723,
      "step": 260
    },
    {
      "epoch": 1.83,
      "learning_rate": 3e-05,
      "loss": 1.0428,
      "step": 270
    },
    {
      "epoch": 1.9,
      "learning_rate": 3e-05,
      "loss": 0.961,
      "step": 280
    },
    {
      "epoch": 1.97,
      "learning_rate": 3e-05,
      "loss": 0.9311,
      "step": 290
    },
    {
      "epoch": 2.0,
      "step": 294,
      "total_flos": 7.002531209517466e+16,
      "train_loss": 1.0460824836679057,
      "train_runtime": 890.7293,
      "train_samples_per_second": 5.29,
      "train_steps_per_second": 0.33
    }
  ],
  "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
}