results/checkpoint-1500/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.8610792192881745,
  "eval_steps": 500,
  "global_step": 1500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2870264064293915,
      "grad_norm": 42880.98828125,
      "learning_rate": 5e-05,
      "loss": 3172.427,
      "step": 500
    },
    {
      "epoch": 0.574052812858783,
      "grad_norm": 16434.26171875,
      "learning_rate": 4.4710114261531955e-05,
      "loss": 575.8997,
      "step": 1000
    },
    {
      "epoch": 0.8610792192881745,
      "grad_norm": 45976.1640625,
      "learning_rate": 3.94202285230639e-05,
      "loss": 192.3109,
      "step": 1500
    }
  ],
  "logging_steps": 500,
  "max_steps": 5226,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 50,
  "trial_name": null,
  "trial_params": null
}