{
  "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": 1.2091,
      "step": 10
    },
    {
      "epoch": 0.14,
      "learning_rate": 3e-05,
      "loss": 1.1462,
      "step": 20
    },
    {
      "epoch": 0.2,
      "learning_rate": 3e-05,
      "loss": 1.1415,
      "step": 30
    },
    {
      "epoch": 0.27,
      "learning_rate": 3e-05,
      "loss": 1.1181,
      "step": 40
    },
    {
      "epoch": 0.34,
      "learning_rate": 3e-05,
      "loss": 1.1084,
      "step": 50
    },
    {
      "epoch": 0.34,
      "eval_loss": 1.1509493589401245,
      "eval_runtime": 15.7829,
      "eval_samples_per_second": 16.6,
      "eval_steps_per_second": 4.182,
      "step": 50
    },
    {
      "epoch": 0.41,
      "learning_rate": 3e-05,
      "loss": 1.0965,
      "step": 60
    },
    {
      "epoch": 0.48,
      "learning_rate": 3e-05,
      "loss": 1.0929,
      "step": 70
    },
    {
      "epoch": 0.54,
      "learning_rate": 3e-05,
      "loss": 1.1405,
      "step": 80
    },
    {
      "epoch": 0.61,
      "learning_rate": 3e-05,
      "loss": 1.1153,
      "step": 90
    },
    {
      "epoch": 0.68,
      "learning_rate": 3e-05,
      "loss": 1.0641,
      "step": 100
    },
    {
      "epoch": 0.68,
      "eval_loss": 1.131222128868103,
      "eval_runtime": 15.7708,
      "eval_samples_per_second": 16.613,
      "eval_steps_per_second": 4.185,
      "step": 100
    },
    {
      "epoch": 0.75,
      "learning_rate": 3e-05,
      "loss": 1.0562,
      "step": 110
    },
    {
      "epoch": 0.81,
      "learning_rate": 3e-05,
      "loss": 1.1051,
      "step": 120
    },
    {
      "epoch": 0.88,
      "learning_rate": 3e-05,
      "loss": 1.0951,
      "step": 130
    },
    {
      "epoch": 0.95,
      "learning_rate": 3e-05,
      "loss": 1.0712,
      "step": 140
    },
    {
      "epoch": 1.02,
      "learning_rate": 3e-05,
      "loss": 1.04,
      "step": 150
    },
    {
      "epoch": 1.02,
      "eval_loss": 1.1267426013946533,
      "eval_runtime": 15.8691,
      "eval_samples_per_second": 16.51,
      "eval_steps_per_second": 4.159,
      "step": 150
    },
    {
      "epoch": 1.09,
      "learning_rate": 3e-05,
      "loss": 0.9894,
      "step": 160
    },
    {
      "epoch": 1.15,
      "learning_rate": 3e-05,
      "loss": 1.0622,
      "step": 170
    },
    {
      "epoch": 1.22,
      "learning_rate": 3e-05,
      "loss": 0.9794,
      "step": 180
    },
    {
      "epoch": 1.29,
      "learning_rate": 3e-05,
      "loss": 0.9593,
      "step": 190
    },
    {
      "epoch": 1.36,
      "learning_rate": 3e-05,
      "loss": 1.016,
      "step": 200
    },
    {
      "epoch": 1.36,
      "eval_loss": 1.1303731203079224,
      "eval_runtime": 15.6796,
      "eval_samples_per_second": 16.71,
      "eval_steps_per_second": 4.209,
      "step": 200
    },
    {
      "epoch": 1.43,
      "learning_rate": 3e-05,
      "loss": 0.9869,
      "step": 210
    },
    {
      "epoch": 1.49,
      "learning_rate": 3e-05,
      "loss": 0.9076,
      "step": 220
    },
    {
      "epoch": 1.56,
      "learning_rate": 3e-05,
      "loss": 0.9926,
      "step": 230
    },
    {
      "epoch": 1.63,
      "learning_rate": 3e-05,
      "loss": 0.9892,
      "step": 240
    },
    {
      "epoch": 1.7,
      "learning_rate": 3e-05,
      "loss": 1.0272,
      "step": 250
    },
    {
      "epoch": 1.7,
      "eval_loss": 1.1311020851135254,
      "eval_runtime": 15.7521,
      "eval_samples_per_second": 16.633,
      "eval_steps_per_second": 4.19,
      "step": 250
    },
    {
      "epoch": 1.77,
      "learning_rate": 3e-05,
      "loss": 0.9765,
      "step": 260
    },
    {
      "epoch": 1.83,
      "learning_rate": 3e-05,
      "loss": 1.0433,
      "step": 270
    },
    {
      "epoch": 1.9,
      "learning_rate": 3e-05,
      "loss": 0.9614,
      "step": 280
    },
    {
      "epoch": 1.97,
      "learning_rate": 3e-05,
      "loss": 0.9299,
      "step": 290
    },
    {
      "epoch": 2.0,
      "step": 294,
      "total_flos": 7.021903495711949e+16,
      "train_loss": 1.0463855915329083,
      "train_runtime": 868.1968,
      "train_samples_per_second": 5.427,
      "train_steps_per_second": 0.339
    }
  ],
  "logging_steps": 10,
  "max_steps": 294,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 250,
  "total_flos": 7.021903495711949e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}