trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 7.352941176470588,
  "eval_steps": 500,
  "global_step": 250,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.4705882352941178,
      "grad_norm": 0.8259584903717041,
      "learning_rate": 0.00018090169943749476,
      "loss": 0.7597,
      "step": 50
    },
    {
      "epoch": 2.9411764705882355,
      "grad_norm": 1.3383677005767822,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.4157,
      "step": 100
    },
    {
      "epoch": 4.411764705882353,
      "grad_norm": 2.3021321296691895,
      "learning_rate": 6.909830056250527e-05,
      "loss": 0.2675,
      "step": 150
    },
    {
      "epoch": 5.882352941176471,
      "grad_norm": 1.4839868545532227,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 0.1764,
      "step": 200
    },
    {
      "epoch": 7.352941176470588,
      "grad_norm": 1.1058175563812256,
      "learning_rate": 0.0,
      "loss": 0.1372,
      "step": 250
    }
  ],
  "logging_steps": 50,
  "max_steps": 250,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 8,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 294957650608128.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}