{
  "best_metric": 2.1908211708068848,
  "best_model_checkpoint": "output/mistral_squad/checkpoint-1000",
  "epoch": 0.24551927326295114,
  "eval_steps": 1000,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 2.5e-05,
      "loss": 2.1039,
      "step": 25
    },
    {
      "epoch": 0.01,
      "learning_rate": 5e-05,
      "loss": 1.9227,
      "step": 50
    },
    {
      "epoch": 0.02,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.8559,
      "step": 75
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0001,
      "loss": 1.8136,
      "step": 100
    },
    {
      "epoch": 0.03,
      "learning_rate": 9.937075257991442e-05,
      "loss": 1.795,
      "step": 125
    },
    {
      "epoch": 0.04,
      "learning_rate": 9.874150515982885e-05,
      "loss": 1.7844,
      "step": 150
    },
    {
      "epoch": 0.04,
      "learning_rate": 9.811225773974327e-05,
      "loss": 1.7486,
      "step": 175
    },
    {
      "epoch": 0.05,
      "learning_rate": 9.74830103196577e-05,
      "loss": 1.719,
      "step": 200
    },
    {
      "epoch": 0.06,
      "learning_rate": 9.685376289957212e-05,
      "loss": 1.7017,
      "step": 225
    },
    {
      "epoch": 0.06,
      "learning_rate": 9.622451547948655e-05,
      "loss": 1.6495,
      "step": 250
    },
    {
      "epoch": 0.07,
      "learning_rate": 9.559526805940097e-05,
      "loss": 1.5982,
      "step": 275
    },
    {
      "epoch": 0.07,
      "learning_rate": 9.496602063931538e-05,
      "loss": 1.5912,
      "step": 300
    },
    {
      "epoch": 0.08,
      "learning_rate": 9.43367732192298e-05,
      "loss": 1.5603,
      "step": 325
    },
    {
      "epoch": 0.09,
      "learning_rate": 9.370752579914423e-05,
      "loss": 1.5453,
      "step": 350
    },
    {
      "epoch": 0.09,
      "learning_rate": 9.307827837905865e-05,
      "loss": 1.4757,
      "step": 375
    },
    {
      "epoch": 0.1,
      "learning_rate": 9.244903095897306e-05,
      "loss": 1.4421,
      "step": 400
    },
    {
      "epoch": 0.1,
      "learning_rate": 9.18197835388875e-05,
      "loss": 1.3738,
      "step": 425
    },
    {
      "epoch": 0.11,
      "learning_rate": 9.119053611880191e-05,
      "loss": 1.3607,
      "step": 450
    },
    {
      "epoch": 0.12,
      "learning_rate": 9.056128869871634e-05,
      "loss": 1.354,
      "step": 475
    },
    {
      "epoch": 0.12,
      "learning_rate": 8.993204127863076e-05,
      "loss": 1.3505,
      "step": 500
    },
    {
      "epoch": 0.13,
      "learning_rate": 8.930279385854519e-05,
      "loss": 1.3025,
      "step": 525
    },
    {
      "epoch": 0.14,
      "learning_rate": 8.867354643845961e-05,
      "loss": 1.2577,
      "step": 550
    },
    {
      "epoch": 0.14,
      "learning_rate": 8.804429901837403e-05,
      "loss": 1.3072,
      "step": 575
    },
    {
      "epoch": 0.15,
      "learning_rate": 8.741505159828846e-05,
      "loss": 1.2621,
      "step": 600
    },
    {
      "epoch": 0.15,
      "learning_rate": 8.678580417820287e-05,
      "loss": 1.213,
      "step": 625
    },
    {
      "epoch": 0.16,
      "learning_rate": 8.615655675811729e-05,
      "loss": 1.1523,
      "step": 650
    },
    {
      "epoch": 0.17,
      "learning_rate": 8.552730933803171e-05,
      "loss": 1.1324,
      "step": 675
    },
    {
      "epoch": 0.17,
      "learning_rate": 8.489806191794614e-05,
      "loss": 1.1531,
      "step": 700
    },
    {
      "epoch": 0.18,
      "learning_rate": 8.426881449786056e-05,
      "loss": 1.0632,
      "step": 725
    },
    {
      "epoch": 0.18,
      "learning_rate": 8.363956707777499e-05,
      "loss": 1.1238,
      "step": 750
    },
    {
      "epoch": 0.19,
      "learning_rate": 8.30103196576894e-05,
      "loss": 1.1197,
      "step": 775
    },
    {
      "epoch": 0.2,
      "learning_rate": 8.238107223760383e-05,
      "loss": 1.04,
      "step": 800
    },
    {
      "epoch": 0.2,
      "learning_rate": 8.175182481751825e-05,
      "loss": 1.1003,
      "step": 825
    },
    {
      "epoch": 0.21,
      "learning_rate": 8.112257739743267e-05,
      "loss": 1.0161,
      "step": 850
    },
    {
      "epoch": 0.21,
      "learning_rate": 8.04933299773471e-05,
      "loss": 0.972,
      "step": 875
    },
    {
      "epoch": 0.22,
      "learning_rate": 7.986408255726152e-05,
      "loss": 0.9713,
      "step": 900
    },
    {
      "epoch": 0.23,
      "learning_rate": 7.923483513717595e-05,
      "loss": 0.9788,
      "step": 925
    },
    {
      "epoch": 0.23,
      "learning_rate": 7.860558771709036e-05,
      "loss": 0.9189,
      "step": 950
    },
    {
      "epoch": 0.24,
      "learning_rate": 7.79763402970048e-05,
      "loss": 0.9001,
      "step": 975
    },
    {
      "epoch": 0.25,
      "learning_rate": 7.734709287691921e-05,
      "loss": 0.8809,
      "step": 1000
    },
    {
      "epoch": 0.25,
      "eval_loss": 2.1908211708068848,
      "eval_runtime": 596.3037,
      "eval_samples_per_second": 19.911,
      "eval_steps_per_second": 0.624,
      "step": 1000
    }
  ],
  "logging_steps": 25,
  "max_steps": 4073,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 1000,
  "total_flos": 3.82488513871872e+17,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}