{
  "best_metric": 2.2405381202697754,
  "best_model_checkpoint": "./outputs/checkpoint-1800",
  "epoch": 1.3114754098360657,
  "eval_steps": 100,
  "global_step": 1800,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 2.7401,
      "step": 100
    },
    {
      "epoch": 0.07,
      "eval_loss": 2.6427574157714844,
      "eval_runtime": 205.0145,
      "eval_samples_per_second": 30.603,
      "eval_steps_per_second": 3.829,
      "step": 100
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 2.6057,
      "step": 200
    },
    {
      "epoch": 0.15,
      "eval_loss": 2.591986656188965,
      "eval_runtime": 205.1897,
      "eval_samples_per_second": 30.577,
      "eval_steps_per_second": 3.826,
      "step": 200
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0002,
      "loss": 2.5624,
      "step": 300
    },
    {
      "epoch": 0.22,
      "eval_loss": 2.5554449558258057,
      "eval_runtime": 204.8733,
      "eval_samples_per_second": 30.624,
      "eval_steps_per_second": 3.832,
      "step": 300
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0002,
      "loss": 2.5354,
      "step": 400
    },
    {
      "epoch": 0.29,
      "eval_loss": 2.523040533065796,
      "eval_runtime": 205.0355,
      "eval_samples_per_second": 30.6,
      "eval_steps_per_second": 3.829,
      "step": 400
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0002,
      "loss": 2.4938,
      "step": 500
    },
    {
      "epoch": 0.36,
      "eval_loss": 2.497437000274658,
      "eval_runtime": 204.8026,
      "eval_samples_per_second": 30.634,
      "eval_steps_per_second": 3.833,
      "step": 500
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0002,
      "loss": 2.4668,
      "step": 600
    },
    {
      "epoch": 0.44,
      "eval_loss": 2.4717156887054443,
      "eval_runtime": 204.8144,
      "eval_samples_per_second": 30.633,
      "eval_steps_per_second": 3.833,
      "step": 600
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0002,
      "loss": 2.4508,
      "step": 700
    },
    {
      "epoch": 0.51,
      "eval_loss": 2.449354410171509,
      "eval_runtime": 204.5211,
      "eval_samples_per_second": 30.677,
      "eval_steps_per_second": 3.838,
      "step": 700
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0002,
      "loss": 2.4278,
      "step": 800
    },
    {
      "epoch": 0.58,
      "eval_loss": 2.4278199672698975,
      "eval_runtime": 204.6341,
      "eval_samples_per_second": 30.66,
      "eval_steps_per_second": 3.836,
      "step": 800
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0002,
      "loss": 2.3928,
      "step": 900
    },
    {
      "epoch": 0.66,
      "eval_loss": 2.4054911136627197,
      "eval_runtime": 204.5808,
      "eval_samples_per_second": 30.668,
      "eval_steps_per_second": 3.837,
      "step": 900
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0002,
      "loss": 2.389,
      "step": 1000
    },
    {
      "epoch": 0.73,
      "eval_loss": 2.3888440132141113,
      "eval_runtime": 204.475,
      "eval_samples_per_second": 30.683,
      "eval_steps_per_second": 3.839,
      "step": 1000
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0002,
      "loss": 2.3831,
      "step": 1100
    },
    {
      "epoch": 0.8,
      "eval_loss": 2.366816997528076,
      "eval_runtime": 204.7174,
      "eval_samples_per_second": 30.647,
      "eval_steps_per_second": 3.835,
      "step": 1100
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0002,
      "loss": 2.338,
      "step": 1200
    },
    {
      "epoch": 0.87,
      "eval_loss": 2.348148822784424,
      "eval_runtime": 204.9159,
      "eval_samples_per_second": 30.617,
      "eval_steps_per_second": 3.831,
      "step": 1200
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.0002,
      "loss": 2.3495,
      "step": 1300
    },
    {
      "epoch": 0.95,
      "eval_loss": 2.331716775894165,
      "eval_runtime": 204.6122,
      "eval_samples_per_second": 30.663,
      "eval_steps_per_second": 3.837,
      "step": 1300
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.0002,
      "loss": 2.3005,
      "step": 1400
    },
    {
      "epoch": 1.02,
      "eval_loss": 2.3074026107788086,
      "eval_runtime": 204.9029,
      "eval_samples_per_second": 30.619,
      "eval_steps_per_second": 3.831,
      "step": 1400
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.0002,
      "loss": 2.2609,
      "step": 1500
    },
    {
      "epoch": 1.09,
      "eval_loss": 2.2931342124938965,
      "eval_runtime": 205.4253,
      "eval_samples_per_second": 30.542,
      "eval_steps_per_second": 3.821,
      "step": 1500
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.0002,
      "loss": 2.2532,
      "step": 1600
    },
    {
      "epoch": 1.17,
      "eval_loss": 2.2731645107269287,
      "eval_runtime": 205.0407,
      "eval_samples_per_second": 30.599,
      "eval_steps_per_second": 3.829,
      "step": 1600
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.0002,
      "loss": 2.2527,
      "step": 1700
    },
    {
      "epoch": 1.24,
      "eval_loss": 2.25679087638855,
      "eval_runtime": 205.2907,
      "eval_samples_per_second": 30.562,
      "eval_steps_per_second": 3.824,
      "step": 1700
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.0002,
      "loss": 2.2141,
      "step": 1800
    },
    {
      "epoch": 1.31,
      "eval_loss": 2.2405381202697754,
      "eval_runtime": 205.0141,
      "eval_samples_per_second": 30.603,
      "eval_steps_per_second": 3.829,
      "step": 1800
    }
  ],
  "logging_steps": 100,
  "max_steps": 4116,
  "num_train_epochs": 3,
  "save_steps": 100,
  "total_flos": 5.260717969532928e+16,
  "trial_name": null,
  "trial_params": null
}