{
  "best_metric": 2.3269803524017334,
  "best_model_checkpoint": "output/muse/checkpoint-200",
  "epoch": 8.0,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2,
      "learning_rate": 0.0001240985658141214,
      "loss": 3.1279,
      "step": 5
    },
    {
      "epoch": 0.4,
      "learning_rate": 8.97985658141214e-05,
      "loss": 2.8709,
      "step": 10
    },
    {
      "epoch": 0.6,
      "learning_rate": 4.740143418587861e-05,
      "loss": 2.8349,
      "step": 15
    },
    {
      "epoch": 0.8,
      "learning_rate": 1.3101434185878613e-05,
      "loss": 2.5989,
      "step": 20
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0,
      "loss": 2.849,
      "step": 25
    },
    {
      "epoch": 1.0,
      "eval_loss": 2.7842092514038086,
      "eval_runtime": 1.8206,
      "eval_samples_per_second": 23.069,
      "eval_steps_per_second": 3.296,
      "step": 25
    },
    {
      "epoch": 1.2,
      "learning_rate": 1.3101434185878598e-05,
      "loss": 2.4736,
      "step": 30
    },
    {
      "epoch": 1.4,
      "learning_rate": 4.74014341858786e-05,
      "loss": 2.628,
      "step": 35
    },
    {
      "epoch": 1.6,
      "learning_rate": 8.979856581412138e-05,
      "loss": 2.6224,
      "step": 40
    },
    {
      "epoch": 1.8,
      "learning_rate": 0.0001240985658141214,
      "loss": 2.6052,
      "step": 45
    },
    {
      "epoch": 2.0,
      "learning_rate": 0.0001372,
      "loss": 2.4193,
      "step": 50
    },
    {
      "epoch": 2.0,
      "eval_loss": 2.6401476860046387,
      "eval_runtime": 1.8685,
      "eval_samples_per_second": 22.478,
      "eval_steps_per_second": 3.211,
      "step": 50
    },
    {
      "epoch": 2.2,
      "learning_rate": 0.00012409856581412136,
      "loss": 2.1791,
      "step": 55
    },
    {
      "epoch": 2.4,
      "learning_rate": 8.979856581412141e-05,
      "loss": 2.2449,
      "step": 60
    },
    {
      "epoch": 2.6,
      "learning_rate": 4.7401434185878625e-05,
      "loss": 2.1171,
      "step": 65
    },
    {
      "epoch": 2.8,
      "learning_rate": 1.310143418587862e-05,
      "loss": 2.1624,
      "step": 70
    },
    {
      "epoch": 3.0,
      "learning_rate": 0.0,
      "loss": 2.2355,
      "step": 75
    },
    {
      "epoch": 3.0,
      "eval_loss": 2.5702805519104004,
      "eval_runtime": 1.8707,
      "eval_samples_per_second": 22.451,
      "eval_steps_per_second": 3.207,
      "step": 75
    },
    {
      "epoch": 3.2,
      "learning_rate": 1.310143418587859e-05,
      "loss": 2.1067,
      "step": 80
    },
    {
      "epoch": 3.4,
      "learning_rate": 4.740143418587858e-05,
      "loss": 2.1021,
      "step": 85
    },
    {
      "epoch": 3.6,
      "learning_rate": 8.979856581412137e-05,
      "loss": 2.0876,
      "step": 90
    },
    {
      "epoch": 3.8,
      "learning_rate": 0.00012409856581412136,
      "loss": 2.0067,
      "step": 95
    },
    {
      "epoch": 4.0,
      "learning_rate": 0.0001372,
      "loss": 1.8774,
      "step": 100
    },
    {
      "epoch": 4.0,
      "eval_loss": 2.4998016357421875,
      "eval_runtime": 1.8837,
      "eval_samples_per_second": 22.296,
      "eval_steps_per_second": 3.185,
      "step": 100
    },
    {
      "epoch": 4.2,
      "learning_rate": 0.00012409856581412142,
      "loss": 1.8595,
      "step": 105
    },
    {
      "epoch": 4.4,
      "learning_rate": 8.97985658141213e-05,
      "loss": 1.8355,
      "step": 110
    },
    {
      "epoch": 4.6,
      "learning_rate": 4.740143418587876e-05,
      "loss": 1.8151,
      "step": 115
    },
    {
      "epoch": 4.8,
      "learning_rate": 1.3101434185878628e-05,
      "loss": 1.6825,
      "step": 120
    },
    {
      "epoch": 5.0,
      "learning_rate": 0.0,
      "loss": 1.828,
      "step": 125
    },
    {
      "epoch": 5.0,
      "eval_loss": 2.455634355545044,
      "eval_runtime": 1.8736,
      "eval_samples_per_second": 22.417,
      "eval_steps_per_second": 3.202,
      "step": 125
    },
    {
      "epoch": 5.2,
      "learning_rate": 1.3101434185878583e-05,
      "loss": 1.7296,
      "step": 130
    },
    {
      "epoch": 5.4,
      "learning_rate": 4.740143418587856e-05,
      "loss": 1.5323,
      "step": 135
    },
    {
      "epoch": 5.6,
      "learning_rate": 8.979856581412136e-05,
      "loss": 1.7239,
      "step": 140
    },
    {
      "epoch": 5.8,
      "learning_rate": 0.00012409856581412136,
      "loss": 1.7961,
      "step": 145
    },
    {
      "epoch": 6.0,
      "learning_rate": 0.0001372,
      "loss": 1.5753,
      "step": 150
    },
    {
      "epoch": 6.0,
      "eval_loss": 2.415633201599121,
      "eval_runtime": 1.8716,
      "eval_samples_per_second": 22.44,
      "eval_steps_per_second": 3.206,
      "step": 150
    },
    {
      "epoch": 6.2,
      "learning_rate": 0.00012409856581412142,
      "loss": 1.5374,
      "step": 155
    },
    {
      "epoch": 6.4,
      "learning_rate": 8.979856581412144e-05,
      "loss": 1.5005,
      "step": 160
    },
    {
      "epoch": 6.6,
      "learning_rate": 4.740143418587866e-05,
      "loss": 1.3827,
      "step": 165
    },
    {
      "epoch": 6.8,
      "learning_rate": 1.3101434185878644e-05,
      "loss": 1.5368,
      "step": 170
    },
    {
      "epoch": 7.0,
      "learning_rate": 0.0,
      "loss": 1.4028,
      "step": 175
    },
    {
      "epoch": 7.0,
      "eval_loss": 2.395447254180908,
      "eval_runtime": 1.8726,
      "eval_samples_per_second": 22.429,
      "eval_steps_per_second": 3.204,
      "step": 175
    },
    {
      "epoch": 7.2,
      "learning_rate": 1.3101434185878574e-05,
      "loss": 1.4826,
      "step": 180
    },
    {
      "epoch": 7.4,
      "learning_rate": 4.7401434185878544e-05,
      "loss": 1.3107,
      "step": 185
    },
    {
      "epoch": 7.6,
      "learning_rate": 8.979856581412133e-05,
      "loss": 1.3342,
      "step": 190
    },
    {
      "epoch": 7.8,
      "learning_rate": 0.00012409856581412136,
      "loss": 1.3195,
      "step": 195
    },
    {
      "epoch": 8.0,
      "learning_rate": 0.0001372,
      "loss": 1.2922,
      "step": 200
    },
    {
      "epoch": 8.0,
      "eval_loss": 2.3269803524017334,
      "eval_runtime": 1.8745,
      "eval_samples_per_second": 22.406,
      "eval_steps_per_second": 3.201,
      "step": 200
    }
  ],
  "max_steps": 2500,
  "num_train_epochs": 100,
  "total_flos": 209033625600000.0,
  "trial_name": null,
  "trial_params": null
}