last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.028268551236749,
  "eval_steps": 4,
  "global_step": 18,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05653710247349823,
      "eval_loss": 11.090624809265137,
      "eval_runtime": 0.9998,
      "eval_samples_per_second": 120.028,
      "eval_steps_per_second": 15.004,
      "step": 1
    },
    {
      "epoch": 0.22614840989399293,
      "eval_loss": 11.055208206176758,
      "eval_runtime": 0.224,
      "eval_samples_per_second": 535.754,
      "eval_steps_per_second": 66.969,
      "step": 4
    },
    {
      "epoch": 0.45229681978798586,
      "eval_loss": 11.007291793823242,
      "eval_runtime": 0.2641,
      "eval_samples_per_second": 454.303,
      "eval_steps_per_second": 56.788,
      "step": 8
    },
    {
      "epoch": 0.5653710247349824,
      "grad_norm": 28.9281063079834,
      "learning_rate": 5e-05,
      "loss": 176.7641,
      "step": 10
    },
    {
      "epoch": 0.6784452296819788,
      "eval_loss": 10.972135543823242,
      "eval_runtime": 0.2232,
      "eval_samples_per_second": 537.74,
      "eval_steps_per_second": 67.218,
      "step": 12
    },
    {
      "epoch": 0.9045936395759717,
      "eval_loss": 10.95703125,
      "eval_runtime": 0.2252,
      "eval_samples_per_second": 532.843,
      "eval_steps_per_second": 66.605,
      "step": 16
    }
  ],
  "logging_steps": 10,
  "max_steps": 18,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 5,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3086336655360.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}