checkpoint-92/trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.9735449735449735,
  "eval_steps": 500,
  "global_step": 92,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.21164021164021163,
      "grad_norm": 0.01096427347511053,
      "learning_rate": 5.4347826086956525e-06,
      "loss": 0.3143,
      "step": 5
    },
    {
      "epoch": 0.42328042328042326,
      "grad_norm": 0.013951408676803112,
      "learning_rate": 1.0869565217391305e-05,
      "loss": 0.3576,
      "step": 10
    },
    {
      "epoch": 0.6349206349206349,
      "grad_norm": 0.01673784852027893,
      "learning_rate": 1.630434782608696e-05,
      "loss": 0.3639,
      "step": 15
    },
    {
      "epoch": 0.8465608465608465,
      "grad_norm": 0.019934486597776413,
      "learning_rate": 2.173913043478261e-05,
      "loss": 0.3458,
      "step": 20
    },
    {
      "epoch": 1.0846560846560847,
      "grad_norm": 0.02395496889948845,
      "learning_rate": 2.7173913043478262e-05,
      "loss": 0.4603,
      "step": 25
    },
    {
      "epoch": 1.2962962962962963,
      "grad_norm": 0.017271244898438454,
      "learning_rate": 3.260869565217392e-05,
      "loss": 0.3034,
      "step": 30
    },
    {
      "epoch": 1.507936507936508,
      "grad_norm": 0.023819392547011375,
      "learning_rate": 3.804347826086957e-05,
      "loss": 0.3317,
      "step": 35
    },
    {
      "epoch": 1.7195767195767195,
      "grad_norm": 0.021737879142165184,
      "learning_rate": 4.347826086956522e-05,
      "loss": 0.3382,
      "step": 40
    },
    {
      "epoch": 1.9312169312169312,
      "grad_norm": 0.023687848821282387,
      "learning_rate": 4.891304347826087e-05,
      "loss": 0.3288,
      "step": 45
    },
    {
      "epoch": 2.1693121693121693,
      "grad_norm": 0.024081828072667122,
      "learning_rate": 4.9988484157560136e-05,
      "loss": 0.3521,
      "step": 50
    },
    {
      "epoch": 2.380952380952381,
      "grad_norm": 0.03236062824726105,
      "learning_rate": 4.994171922976348e-05,
      "loss": 0.3485,
      "step": 55
    },
    {
      "epoch": 2.5925925925925926,
      "grad_norm": 0.03175266832113266,
      "learning_rate": 4.9859052738933966e-05,
      "loss": 0.2979,
      "step": 60
    },
    {
      "epoch": 2.804232804232804,
      "grad_norm": 0.030012985691428185,
      "learning_rate": 4.974060367671783e-05,
      "loss": 0.3055,
      "step": 65
    },
    {
      "epoch": 3.0423280423280423,
      "grad_norm": 0.10118062049150467,
      "learning_rate": 4.958654254084355e-05,
      "loss": 0.3521,
      "step": 70
    },
    {
      "epoch": 3.253968253968254,
      "grad_norm": 0.02641722746193409,
      "learning_rate": 4.9397091089704364e-05,
      "loss": 0.3041,
      "step": 75
    },
    {
      "epoch": 3.4656084656084656,
      "grad_norm": 0.03561725839972496,
      "learning_rate": 4.9172522023155154e-05,
      "loss": 0.2778,
      "step": 80
    },
    {
      "epoch": 3.677248677248677,
      "grad_norm": 0.04121287539601326,
      "learning_rate": 4.8913158589983374e-05,
      "loss": 0.2698,
      "step": 85
    },
    {
      "epoch": 3.888888888888889,
      "grad_norm": 0.04533043131232262,
      "learning_rate": 4.8619374122618854e-05,
      "loss": 0.2704,
      "step": 90
    }
  ],
  "logging_steps": 5,
  "max_steps": 460,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 20,
  "save_steps": 23,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 5.588663838787502e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}