last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.003604902667627974,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0003604902667627974,
      "grad_norm": 2.7337660867488012e-05,
      "learning_rate": 2e-05,
      "loss": 46.0,
      "step": 1
    },
    {
      "epoch": 0.0003604902667627974,
      "eval_loss": 11.5,
      "eval_runtime": 7.5615,
      "eval_samples_per_second": 154.598,
      "eval_steps_per_second": 77.365,
      "step": 1
    },
    {
      "epoch": 0.0007209805335255948,
      "grad_norm": 1.7489677702542394e-05,
      "learning_rate": 4e-05,
      "loss": 46.0,
      "step": 2
    },
    {
      "epoch": 0.0010814708002883922,
      "grad_norm": 2.5130821086349897e-05,
      "learning_rate": 6e-05,
      "loss": 46.0,
      "step": 3
    },
    {
      "epoch": 0.0010814708002883922,
      "eval_loss": 11.5,
      "eval_runtime": 7.5323,
      "eval_samples_per_second": 155.198,
      "eval_steps_per_second": 77.665,
      "step": 3
    },
    {
      "epoch": 0.0014419610670511895,
      "grad_norm": 1.059984333551256e-05,
      "learning_rate": 8e-05,
      "loss": 46.0,
      "step": 4
    },
    {
      "epoch": 0.001802451333813987,
      "grad_norm": 1.5773546692798845e-05,
      "learning_rate": 0.0001,
      "loss": 46.0,
      "step": 5
    },
    {
      "epoch": 0.0021629416005767843,
      "grad_norm": 1.64099383255234e-05,
      "learning_rate": 0.00012,
      "loss": 46.0,
      "step": 6
    },
    {
      "epoch": 0.0021629416005767843,
      "eval_loss": 11.5,
      "eval_runtime": 7.6482,
      "eval_samples_per_second": 152.847,
      "eval_steps_per_second": 76.489,
      "step": 6
    },
    {
      "epoch": 0.0025234318673395817,
      "grad_norm": 2.0088316887267865e-05,
      "learning_rate": 0.00014,
      "loss": 46.0,
      "step": 7
    },
    {
      "epoch": 0.002883922134102379,
      "grad_norm": 3.462352105998434e-05,
      "learning_rate": 0.00016,
      "loss": 46.0,
      "step": 8
    },
    {
      "epoch": 0.0032444124008651765,
      "grad_norm": 1.6997619241010398e-05,
      "learning_rate": 0.00018,
      "loss": 46.0,
      "step": 9
    },
    {
      "epoch": 0.0032444124008651765,
      "eval_loss": 11.5,
      "eval_runtime": 7.6752,
      "eval_samples_per_second": 152.309,
      "eval_steps_per_second": 76.22,
      "step": 9
    },
    {
      "epoch": 0.003604902667627974,
      "grad_norm": 4.1601579141570255e-05,
      "learning_rate": 0.0002,
      "loss": 46.0,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 373553971200.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}