trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 125,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08,
      "grad_norm": 7.301303386688232,
      "learning_rate": 1.3846153846153847e-05,
      "loss": 1.5694,
      "step": 10
    },
    {
      "epoch": 0.16,
      "grad_norm": 3.652470827102661,
      "learning_rate": 1.985871018518236e-05,
      "loss": 0.3644,
      "step": 20
    },
    {
      "epoch": 0.24,
      "grad_norm": 5.326970100402832,
      "learning_rate": 1.912783265061319e-05,
      "loss": 0.374,
      "step": 30
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.5815876126289368,
      "learning_rate": 1.7640373758216075e-05,
      "loss": 0.1797,
      "step": 40
    },
    {
      "epoch": 0.4,
      "grad_norm": 1.439568281173706,
      "learning_rate": 1.5555702330196024e-05,
      "loss": 0.0685,
      "step": 50
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.09065556526184082,
      "learning_rate": 1.3036767451096148e-05,
      "loss": 0.1244,
      "step": 60
    },
    {
      "epoch": 0.56,
      "grad_norm": 2.369553327560425,
      "learning_rate": 1.028046256275869e-05,
      "loss": 0.1301,
      "step": 70
    },
    {
      "epoch": 0.64,
      "grad_norm": 2.2806155681610107,
      "learning_rate": 7.50223521832773e-06,
      "loss": 0.2033,
      "step": 80
    },
    {
      "epoch": 0.72,
      "grad_norm": 1.1145380735397339,
      "learning_rate": 4.919246547534709e-06,
      "loss": 0.1496,
      "step": 90
    },
    {
      "epoch": 0.8,
      "grad_norm": 1.7836447954177856,
      "learning_rate": 2.7333967796597317e-06,
      "loss": 0.0447,
      "step": 100
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.2162286639213562,
      "learning_rate": 1.1155436402112785e-06,
      "loss": 0.1065,
      "step": 110
    },
    {
      "epoch": 0.96,
      "grad_norm": 1.168771505355835,
      "learning_rate": 1.921471959676957e-07,
      "loss": 0.1084,
      "step": 120
    },
    {
      "epoch": 1.0,
      "step": 125,
      "total_flos": 7074583249158144.0,
      "train_loss": 0.2772752811908722,
      "train_runtime": 751.7766,
      "train_samples_per_second": 0.665,
      "train_steps_per_second": 0.166
    }
  ],
  "logging_steps": 10,
  "max_steps": 125,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 1000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": false,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 7074583249158144.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}