last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0009485641110768574,
  "eval_steps": 8,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 9.485641110768574e-05,
      "eval_loss": 4.818389415740967,
      "eval_runtime": 517.8108,
      "eval_samples_per_second": 8.573,
      "eval_steps_per_second": 4.287,
      "step": 1
    },
    {
      "epoch": 0.0002845692333230572,
      "grad_norm": 10.10597038269043,
      "learning_rate": 6e-05,
      "loss": 19.8011,
      "step": 3
    },
    {
      "epoch": 0.0005691384666461144,
      "grad_norm": 8.171477317810059,
      "learning_rate": 0.00012,
      "loss": 20.1722,
      "step": 6
    },
    {
      "epoch": 0.0007588512888614859,
      "eval_loss": 4.06050443649292,
      "eval_runtime": 517.6006,
      "eval_samples_per_second": 8.576,
      "eval_steps_per_second": 4.289,
      "step": 8
    },
    {
      "epoch": 0.0008537076999691717,
      "grad_norm": 11.392943382263184,
      "learning_rate": 0.00018,
      "loss": 19.0904,
      "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": 6808424939520000.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}