checkpoint-50/trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.64,
  "eval_steps": 500,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.5333333333333333,
      "grad_norm": 0.6541063189506531,
      "learning_rate": 0.00018,
      "loss": 0.5658,
      "step": 10
    },
    {
      "epoch": 1.0533333333333332,
      "grad_norm": 0.3301861584186554,
      "learning_rate": 0.00016170212765957446,
      "loss": 0.4383,
      "step": 20
    },
    {
      "epoch": 1.5866666666666667,
      "grad_norm": 0.4295459985733032,
      "learning_rate": 0.00011914893617021277,
      "loss": 0.3889,
      "step": 30
    },
    {
      "epoch": 2.1066666666666665,
      "grad_norm": 0.38779518008232117,
      "learning_rate": 7.659574468085106e-05,
      "loss": 0.3534,
      "step": 40
    },
    {
      "epoch": 2.64,
      "grad_norm": 0.3887574076652527,
      "learning_rate": 3.4042553191489365e-05,
      "loss": 0.3215,
      "step": 50
    }
  ],
  "logging_steps": 10,
  "max_steps": 57,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3568723789086720.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}