{
  "best_metric": 0.5201743841171265,
  "best_model_checkpoint": "deberta-classifier-feedback-1024-pseudo-final/checkpoint-170",
  "epoch": 0.7203389830508474,
  "global_step": 170,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04,
      "learning_rate": 1.9576271186440678e-05,
      "loss": 0.5814,
      "step": 10
    },
    {
      "epoch": 0.04,
      "eval_loss": 0.5888153910636902,
      "eval_runtime": 18.2433,
      "eval_samples_per_second": 23.022,
      "eval_steps_per_second": 2.905,
      "step": 10
    },
    {
      "epoch": 0.08,
      "learning_rate": 1.9152542372881357e-05,
      "loss": 0.5521,
      "step": 20
    },
    {
      "epoch": 0.08,
      "eval_loss": 0.5736112594604492,
      "eval_runtime": 18.7271,
      "eval_samples_per_second": 22.427,
      "eval_steps_per_second": 2.83,
      "step": 20
    },
    {
      "epoch": 0.13,
      "learning_rate": 1.8728813559322033e-05,
      "loss": 0.5685,
      "step": 30
    },
    {
      "epoch": 0.13,
      "eval_loss": 0.5809019804000854,
      "eval_runtime": 17.2407,
      "eval_samples_per_second": 24.361,
      "eval_steps_per_second": 3.074,
      "step": 30
    },
    {
      "epoch": 0.17,
      "learning_rate": 1.8305084745762713e-05,
      "loss": 0.6052,
      "step": 40
    },
    {
      "epoch": 0.17,
      "eval_loss": 0.5701586008071899,
      "eval_runtime": 18.6909,
      "eval_samples_per_second": 22.471,
      "eval_steps_per_second": 2.836,
      "step": 40
    },
    {
      "epoch": 0.21,
      "learning_rate": 1.788135593220339e-05,
      "loss": 0.5532,
      "step": 50
    },
    {
      "epoch": 0.21,
      "eval_loss": 0.5571172833442688,
      "eval_runtime": 18.369,
      "eval_samples_per_second": 22.865,
      "eval_steps_per_second": 2.885,
      "step": 50
    },
    {
      "epoch": 0.25,
      "learning_rate": 1.745762711864407e-05,
      "loss": 0.6177,
      "step": 60
    },
    {
      "epoch": 0.25,
      "eval_loss": 0.5848062634468079,
      "eval_runtime": 18.5061,
      "eval_samples_per_second": 22.695,
      "eval_steps_per_second": 2.864,
      "step": 60
    },
    {
      "epoch": 0.3,
      "learning_rate": 1.7033898305084745e-05,
      "loss": 0.6196,
      "step": 70
    },
    {
      "epoch": 0.3,
      "eval_loss": 0.5464363098144531,
      "eval_runtime": 18.5102,
      "eval_samples_per_second": 22.69,
      "eval_steps_per_second": 2.863,
      "step": 70
    },
    {
      "epoch": 0.34,
      "learning_rate": 1.6610169491525424e-05,
      "loss": 0.5772,
      "step": 80
    },
    {
      "epoch": 0.34,
      "eval_loss": 0.5307226777076721,
      "eval_runtime": 18.3662,
      "eval_samples_per_second": 22.868,
      "eval_steps_per_second": 2.886,
      "step": 80
    },
    {
      "epoch": 0.38,
      "learning_rate": 1.6186440677966104e-05,
      "loss": 0.5805,
      "step": 90
    },
    {
      "epoch": 0.38,
      "eval_loss": 0.554991602897644,
      "eval_runtime": 17.9687,
      "eval_samples_per_second": 23.374,
      "eval_steps_per_second": 2.95,
      "step": 90
    },
    {
      "epoch": 0.42,
      "learning_rate": 1.576271186440678e-05,
      "loss": 0.6453,
      "step": 100
    },
    {
      "epoch": 0.42,
      "eval_loss": 0.5466664433479309,
      "eval_runtime": 18.0919,
      "eval_samples_per_second": 23.215,
      "eval_steps_per_second": 2.929,
      "step": 100
    },
    {
      "epoch": 0.47,
      "learning_rate": 1.533898305084746e-05,
      "loss": 0.5756,
      "step": 110
    },
    {
      "epoch": 0.47,
      "eval_loss": 0.5586597919464111,
      "eval_runtime": 18.6353,
      "eval_samples_per_second": 22.538,
      "eval_steps_per_second": 2.844,
      "step": 110
    },
    {
      "epoch": 0.51,
      "learning_rate": 1.4915254237288137e-05,
      "loss": 0.5901,
      "step": 120
    },
    {
      "epoch": 0.51,
      "eval_loss": 0.5481747388839722,
      "eval_runtime": 18.326,
      "eval_samples_per_second": 22.918,
      "eval_steps_per_second": 2.892,
      "step": 120
    },
    {
      "epoch": 0.55,
      "learning_rate": 1.4491525423728813e-05,
      "loss": 0.568,
      "step": 130
    },
    {
      "epoch": 0.55,
      "eval_loss": 0.5262647867202759,
      "eval_runtime": 18.2108,
      "eval_samples_per_second": 23.063,
      "eval_steps_per_second": 2.91,
      "step": 130
    },
    {
      "epoch": 0.59,
      "learning_rate": 1.4067796610169493e-05,
      "loss": 0.5452,
      "step": 140
    },
    {
      "epoch": 0.59,
      "eval_loss": 0.5698090195655823,
      "eval_runtime": 18.2551,
      "eval_samples_per_second": 23.007,
      "eval_steps_per_second": 2.903,
      "step": 140
    },
    {
      "epoch": 0.64,
      "learning_rate": 1.364406779661017e-05,
      "loss": 0.5949,
      "step": 150
    },
    {
      "epoch": 0.64,
      "eval_loss": 0.5483840107917786,
      "eval_runtime": 18.0824,
      "eval_samples_per_second": 23.227,
      "eval_steps_per_second": 2.931,
      "step": 150
    },
    {
      "epoch": 0.68,
      "learning_rate": 1.3220338983050848e-05,
      "loss": 0.5537,
      "step": 160
    },
    {
      "epoch": 0.68,
      "eval_loss": 0.578332781791687,
      "eval_runtime": 18.2057,
      "eval_samples_per_second": 23.07,
      "eval_steps_per_second": 2.911,
      "step": 160
    },
    {
      "epoch": 0.72,
      "learning_rate": 1.2796610169491526e-05,
      "loss": 0.5327,
      "step": 170
    },
    {
      "epoch": 0.72,
      "eval_loss": 0.5201743841171265,
      "eval_runtime": 18.1319,
      "eval_samples_per_second": 23.164,
      "eval_steps_per_second": 2.923,
      "step": 170
    }
  ],
  "max_steps": 472,
  "num_train_epochs": 2,
  "total_flos": 5037619130747424.0,
  "trial_name": null,
  "trial_params": null
}