{
  "best_metric": 1.5954241752624512,
  "best_model_checkpoint": "/scratch/kwamea/llama-output/checkpoint-70",
  "epoch": 9.655172413793103,
  "eval_steps": 5,
  "global_step": 70,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.69,
      "grad_norm": 0.27489739656448364,
      "learning_rate": 9.285714285714286e-05,
      "loss": 1.9945,
      "step": 5
    },
    {
      "epoch": 0.69,
      "eval_loss": 2.0204718112945557,
      "eval_runtime": 14.7113,
      "eval_samples_per_second": 0.408,
      "eval_steps_per_second": 0.068,
      "step": 5
    },
    {
      "epoch": 1.38,
      "grad_norm": 0.36750176548957825,
      "learning_rate": 8.571428571428571e-05,
      "loss": 1.9427,
      "step": 10
    },
    {
      "epoch": 1.38,
      "eval_loss": 1.9357692003250122,
      "eval_runtime": 14.713,
      "eval_samples_per_second": 0.408,
      "eval_steps_per_second": 0.068,
      "step": 10
    },
    {
      "epoch": 2.07,
      "grad_norm": 0.4677024185657501,
      "learning_rate": 7.857142857142858e-05,
      "loss": 1.8651,
      "step": 15
    },
    {
      "epoch": 2.07,
      "eval_loss": 1.8461824655532837,
      "eval_runtime": 14.7203,
      "eval_samples_per_second": 0.408,
      "eval_steps_per_second": 0.068,
      "step": 15
    },
    {
      "epoch": 2.76,
      "grad_norm": 0.40606027841567993,
      "learning_rate": 7.142857142857143e-05,
      "loss": 1.7948,
      "step": 20
    },
    {
      "epoch": 2.76,
      "eval_loss": 1.801284670829773,
      "eval_runtime": 14.7281,
      "eval_samples_per_second": 0.407,
      "eval_steps_per_second": 0.068,
      "step": 20
    },
    {
      "epoch": 3.45,
      "grad_norm": 0.3058153986930847,
      "learning_rate": 6.428571428571429e-05,
      "loss": 1.7233,
      "step": 25
    },
    {
      "epoch": 3.45,
      "eval_loss": 1.766973853111267,
      "eval_runtime": 14.6916,
      "eval_samples_per_second": 0.408,
      "eval_steps_per_second": 0.068,
      "step": 25
    },
    {
      "epoch": 4.14,
      "grad_norm": 0.2967859208583832,
      "learning_rate": 5.714285714285714e-05,
      "loss": 1.7117,
      "step": 30
    },
    {
      "epoch": 4.14,
      "eval_loss": 1.7350422143936157,
      "eval_runtime": 14.7126,
      "eval_samples_per_second": 0.408,
      "eval_steps_per_second": 0.068,
      "step": 30
    },
    {
      "epoch": 4.83,
      "grad_norm": 0.31578946113586426,
      "learning_rate": 5e-05,
      "loss": 1.6904,
      "step": 35
    },
    {
      "epoch": 4.83,
      "eval_loss": 1.7066936492919922,
      "eval_runtime": 14.7265,
      "eval_samples_per_second": 0.407,
      "eval_steps_per_second": 0.068,
      "step": 35
    },
    {
      "epoch": 5.52,
      "grad_norm": 0.34217244386672974,
      "learning_rate": 4.2857142857142856e-05,
      "loss": 1.6459,
      "step": 40
    },
    {
      "epoch": 5.52,
      "eval_loss": 1.6809816360473633,
      "eval_runtime": 14.7004,
      "eval_samples_per_second": 0.408,
      "eval_steps_per_second": 0.068,
      "step": 40
    },
    {
      "epoch": 6.21,
      "grad_norm": 0.36268118023872375,
      "learning_rate": 3.571428571428572e-05,
      "loss": 1.5992,
      "step": 45
    },
    {
      "epoch": 6.21,
      "eval_loss": 1.6565723419189453,
      "eval_runtime": 14.6987,
      "eval_samples_per_second": 0.408,
      "eval_steps_per_second": 0.068,
      "step": 45
    },
    {
      "epoch": 6.9,
      "grad_norm": 0.3854450583457947,
      "learning_rate": 2.857142857142857e-05,
      "loss": 1.6088,
      "step": 50
    },
    {
      "epoch": 6.9,
      "eval_loss": 1.6376428604125977,
      "eval_runtime": 14.7228,
      "eval_samples_per_second": 0.408,
      "eval_steps_per_second": 0.068,
      "step": 50
    },
    {
      "epoch": 7.59,
      "grad_norm": 0.39184266328811646,
      "learning_rate": 2.1428571428571428e-05,
      "loss": 1.5722,
      "step": 55
    },
    {
      "epoch": 7.59,
      "eval_loss": 1.6203418970108032,
      "eval_runtime": 14.7373,
      "eval_samples_per_second": 0.407,
      "eval_steps_per_second": 0.068,
      "step": 55
    },
    {
      "epoch": 8.28,
      "grad_norm": 0.41270822286605835,
      "learning_rate": 1.4285714285714285e-05,
      "loss": 1.5593,
      "step": 60
    },
    {
      "epoch": 8.28,
      "eval_loss": 1.6068811416625977,
      "eval_runtime": 14.7065,
      "eval_samples_per_second": 0.408,
      "eval_steps_per_second": 0.068,
      "step": 60
    },
    {
      "epoch": 8.97,
      "grad_norm": 0.44460129737854004,
      "learning_rate": 7.142857142857143e-06,
      "loss": 1.5212,
      "step": 65
    },
    {
      "epoch": 8.97,
      "eval_loss": 1.5982898473739624,
      "eval_runtime": 14.6929,
      "eval_samples_per_second": 0.408,
      "eval_steps_per_second": 0.068,
      "step": 65
    },
    {
      "epoch": 9.66,
      "grad_norm": 0.44520503282546997,
      "learning_rate": 0.0,
      "loss": 1.5438,
      "step": 70
    },
    {
      "epoch": 9.66,
      "eval_loss": 1.5954241752624512,
      "eval_runtime": 14.7317,
      "eval_samples_per_second": 0.407,
      "eval_steps_per_second": 0.068,
      "step": 70
    }
  ],
  "logging_steps": 5,
  "max_steps": 70,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 10,
  "total_flos": 4.7295648629784576e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}