last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0032144005143040825,
  "eval_steps": 8,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0003214400514304082,
      "eval_loss": 2.9586496353149414,
      "eval_runtime": 97.8177,
      "eval_samples_per_second": 13.392,
      "eval_steps_per_second": 6.696,
      "step": 1
    },
    {
      "epoch": 0.0009643201542912247,
      "grad_norm": 3.8007397651672363,
      "learning_rate": 3e-05,
      "loss": 11.2314,
      "step": 3
    },
    {
      "epoch": 0.0019286403085824494,
      "grad_norm": 4.28609561920166,
      "learning_rate": 6e-05,
      "loss": 12.17,
      "step": 6
    },
    {
      "epoch": 0.0025715204114432656,
      "eval_loss": 2.790358543395996,
      "eval_runtime": 97.7559,
      "eval_samples_per_second": 13.401,
      "eval_steps_per_second": 6.7,
      "step": 8
    },
    {
      "epoch": 0.0028929604628736743,
      "grad_norm": 4.557946681976318,
      "learning_rate": 9e-05,
      "loss": 11.5635,
      "step": 9
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3466677952512000.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}