{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 133.33333333333334,
  "eval_steps": 25,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 8.33,
      "learning_rate": 2.349624060150376e-05,
      "loss": 1.5297,
      "step": 25
    },
    {
      "epoch": 8.33,
      "eval_loss": 1.5994977951049805,
      "eval_runtime": 13.2366,
      "eval_samples_per_second": 0.302,
      "eval_steps_per_second": 0.076,
      "step": 25
    },
    {
      "epoch": 16.67,
      "learning_rate": 2.1929824561403507e-05,
      "loss": 0.279,
      "step": 50
    },
    {
      "epoch": 16.67,
      "eval_loss": 1.4511220455169678,
      "eval_runtime": 13.3412,
      "eval_samples_per_second": 0.3,
      "eval_steps_per_second": 0.075,
      "step": 50
    },
    {
      "epoch": 25.0,
      "learning_rate": 2.036340852130326e-05,
      "loss": 0.0794,
      "step": 75
    },
    {
      "epoch": 25.0,
      "eval_loss": 1.2972378730773926,
      "eval_runtime": 13.2606,
      "eval_samples_per_second": 0.302,
      "eval_steps_per_second": 0.075,
      "step": 75
    },
    {
      "epoch": 33.33,
      "learning_rate": 1.8796992481203007e-05,
      "loss": 0.047,
      "step": 100
    },
    {
      "epoch": 33.33,
      "eval_loss": 1.3229398727416992,
      "eval_runtime": 13.2873,
      "eval_samples_per_second": 0.301,
      "eval_steps_per_second": 0.075,
      "step": 100
    },
    {
      "epoch": 41.67,
      "learning_rate": 1.723057644110276e-05,
      "loss": 0.0439,
      "step": 125
    },
    {
      "epoch": 41.67,
      "eval_loss": 1.3236302137374878,
      "eval_runtime": 13.3178,
      "eval_samples_per_second": 0.3,
      "eval_steps_per_second": 0.075,
      "step": 125
    },
    {
      "epoch": 50.0,
      "learning_rate": 1.5664160401002506e-05,
      "loss": 0.047,
      "step": 150
    },
    {
      "epoch": 50.0,
      "eval_loss": 1.3176349401474,
      "eval_runtime": 13.3078,
      "eval_samples_per_second": 0.301,
      "eval_steps_per_second": 0.075,
      "step": 150
    },
    {
      "epoch": 58.33,
      "learning_rate": 1.4097744360902257e-05,
      "loss": 0.0445,
      "step": 175
    },
    {
      "epoch": 58.33,
      "eval_loss": 1.339446783065796,
      "eval_runtime": 13.22,
      "eval_samples_per_second": 0.303,
      "eval_steps_per_second": 0.076,
      "step": 175
    },
    {
      "epoch": 66.67,
      "learning_rate": 1.2531328320802006e-05,
      "loss": 0.0398,
      "step": 200
    },
    {
      "epoch": 66.67,
      "eval_loss": 1.3432368040084839,
      "eval_runtime": 13.2621,
      "eval_samples_per_second": 0.302,
      "eval_steps_per_second": 0.075,
      "step": 200
    },
    {
      "epoch": 75.0,
      "learning_rate": 1.0964912280701754e-05,
      "loss": 0.0423,
      "step": 225
    },
    {
      "epoch": 75.0,
      "eval_loss": 1.350469946861267,
      "eval_runtime": 13.2651,
      "eval_samples_per_second": 0.302,
      "eval_steps_per_second": 0.075,
      "step": 225
    },
    {
      "epoch": 83.33,
      "learning_rate": 9.398496240601503e-06,
      "loss": 0.0407,
      "step": 250
    },
    {
      "epoch": 83.33,
      "eval_loss": 1.3625694513320923,
      "eval_runtime": 13.3327,
      "eval_samples_per_second": 0.3,
      "eval_steps_per_second": 0.075,
      "step": 250
    },
    {
      "epoch": 91.67,
      "learning_rate": 7.832080200501253e-06,
      "loss": 0.0416,
      "step": 275
    },
    {
      "epoch": 91.67,
      "eval_loss": 1.368773341178894,
      "eval_runtime": 13.3454,
      "eval_samples_per_second": 0.3,
      "eval_steps_per_second": 0.075,
      "step": 275
    },
    {
      "epoch": 100.0,
      "learning_rate": 6.265664160401003e-06,
      "loss": 0.0422,
      "step": 300
    },
    {
      "epoch": 100.0,
      "eval_loss": 1.375423550605774,
      "eval_runtime": 13.2783,
      "eval_samples_per_second": 0.301,
      "eval_steps_per_second": 0.075,
      "step": 300
    },
    {
      "epoch": 108.33,
      "learning_rate": 4.699248120300752e-06,
      "loss": 0.0409,
      "step": 325
    },
    {
      "epoch": 108.33,
      "eval_loss": 1.3799121379852295,
      "eval_runtime": 13.3645,
      "eval_samples_per_second": 0.299,
      "eval_steps_per_second": 0.075,
      "step": 325
    },
    {
      "epoch": 116.67,
      "learning_rate": 3.1328320802005014e-06,
      "loss": 0.0418,
      "step": 350
    },
    {
      "epoch": 116.67,
      "eval_loss": 1.3847147226333618,
      "eval_runtime": 13.275,
      "eval_samples_per_second": 0.301,
      "eval_steps_per_second": 0.075,
      "step": 350
    },
    {
      "epoch": 125.0,
      "learning_rate": 1.5664160401002507e-06,
      "loss": 0.0399,
      "step": 375
    },
    {
      "epoch": 125.0,
      "eval_loss": 1.3884910345077515,
      "eval_runtime": 13.2582,
      "eval_samples_per_second": 0.302,
      "eval_steps_per_second": 0.075,
      "step": 375
    },
    {
      "epoch": 133.33,
      "learning_rate": 0.0,
      "loss": 0.0387,
      "step": 400
    },
    {
      "epoch": 133.33,
      "eval_loss": 1.389175295829773,
      "eval_runtime": 13.282,
      "eval_samples_per_second": 0.301,
      "eval_steps_per_second": 0.075,
      "step": 400
    }
  ],
  "logging_steps": 25,
  "max_steps": 400,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 134,
  "save_steps": 25,
  "total_flos": 1.4744164553981952e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}