trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 75,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.20408163265306123,
      "grad_norm": 25.64178466796875,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 1.3552,
      "step": 5
    },
    {
      "epoch": 0.40816326530612246,
      "grad_norm": 7.102607250213623,
      "learning_rate": 4.5e-06,
      "loss": 1.0071,
      "step": 10
    },
    {
      "epoch": 0.6122448979591837,
      "grad_norm": 1.7334558963775635,
      "learning_rate": 7.000000000000001e-06,
      "loss": 0.7344,
      "step": 15
    },
    {
      "epoch": 0.8163265306122449,
      "grad_norm": 1.1220566034317017,
      "learning_rate": 9.5e-06,
      "loss": 0.5903,
      "step": 20
    },
    {
      "epoch": 1.0,
      "grad_norm": 1.143535852432251,
      "learning_rate": 1.2e-05,
      "loss": 0.5723,
      "step": 25
    },
    {
      "epoch": 1.2040816326530612,
      "grad_norm": 0.7173786163330078,
      "learning_rate": 1.45e-05,
      "loss": 0.4536,
      "step": 30
    },
    {
      "epoch": 1.4081632653061225,
      "grad_norm": 0.8288874626159668,
      "learning_rate": 1.7000000000000003e-05,
      "loss": 0.4172,
      "step": 35
    },
    {
      "epoch": 1.6122448979591837,
      "grad_norm": 0.6969985961914062,
      "learning_rate": 1.9500000000000003e-05,
      "loss": 0.3431,
      "step": 40
    },
    {
      "epoch": 1.816326530612245,
      "grad_norm": 0.7697305083274841,
      "learning_rate": 2.2000000000000003e-05,
      "loss": 0.3641,
      "step": 45
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.958807110786438,
      "learning_rate": 2.45e-05,
      "loss": 0.2798,
      "step": 50
    },
    {
      "epoch": 2.204081632653061,
      "grad_norm": 0.7001542448997498,
      "learning_rate": 2.7000000000000002e-05,
      "loss": 0.2141,
      "step": 55
    },
    {
      "epoch": 2.4081632653061225,
      "grad_norm": 0.6866745948791504,
      "learning_rate": 2.95e-05,
      "loss": 0.2182,
      "step": 60
    },
    {
      "epoch": 2.612244897959184,
      "grad_norm": 0.7665354013442993,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 0.1899,
      "step": 65
    },
    {
      "epoch": 2.816326530612245,
      "grad_norm": 0.6130437254905701,
      "learning_rate": 3.45e-05,
      "loss": 0.2121,
      "step": 70
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.9800735116004944,
      "learning_rate": 3.7e-05,
      "loss": 0.2195,
      "step": 75
    }
  ],
  "logging_steps": 5,
  "max_steps": 75,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6.725621273151406e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}