checkpoint-406/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.995079950799508,
  "eval_steps": 500,
  "global_step": 406,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.984009840098401,
      "grad_norm": 0.4337162958714847,
      "learning_rate": 3.9716940317357863e-05,
      "loss": 0.3891,
      "step": 100
    },
    {
      "epoch": 1.968019680196802,
      "grad_norm": 0.1396883245826383,
      "learning_rate": 3.813054755147253e-05,
      "loss": 0.2684,
      "step": 200
    },
    {
      "epoch": 2.952029520295203,
      "grad_norm": 0.15652005092055915,
      "learning_rate": 3.525576816314786e-05,
      "loss": 0.2466,
      "step": 300
    },
    {
      "epoch": 3.936039360393604,
      "grad_norm": 0.13772877463793512,
      "learning_rate": 3.129688871879154e-05,
      "loss": 0.231,
      "step": 400
    }
  ],
  "logging_steps": 100,
  "max_steps": 1212,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 12,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}