last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.005608524957936063,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005608524957936063,
      "grad_norm": 0.014601945877075195,
      "learning_rate": 2e-05,
      "loss": 11.9315,
      "step": 1
    },
    {
      "epoch": 0.0005608524957936063,
      "eval_loss": 11.931306838989258,
      "eval_runtime": 2.705,
      "eval_samples_per_second": 277.638,
      "eval_steps_per_second": 139.004,
      "step": 1
    },
    {
      "epoch": 0.0011217049915872126,
      "grad_norm": 0.0080253342166543,
      "learning_rate": 4e-05,
      "loss": 11.9304,
      "step": 2
    },
    {
      "epoch": 0.0016825574873808188,
      "grad_norm": 0.01091256458312273,
      "learning_rate": 6e-05,
      "loss": 11.9319,
      "step": 3
    },
    {
      "epoch": 0.0016825574873808188,
      "eval_loss": 11.931302070617676,
      "eval_runtime": 2.7389,
      "eval_samples_per_second": 274.202,
      "eval_steps_per_second": 137.284,
      "step": 3
    },
    {
      "epoch": 0.002243409983174425,
      "grad_norm": 0.01584225706756115,
      "learning_rate": 8e-05,
      "loss": 11.9328,
      "step": 4
    },
    {
      "epoch": 0.0028042624789680315,
      "grad_norm": 0.01661496050655842,
      "learning_rate": 0.0001,
      "loss": 11.9248,
      "step": 5
    },
    {
      "epoch": 0.0033651149747616375,
      "grad_norm": 0.008873275481164455,
      "learning_rate": 0.00012,
      "loss": 11.926,
      "step": 6
    },
    {
      "epoch": 0.0033651149747616375,
      "eval_loss": 11.931286811828613,
      "eval_runtime": 2.8054,
      "eval_samples_per_second": 267.701,
      "eval_steps_per_second": 134.029,
      "step": 6
    },
    {
      "epoch": 0.003925967470555244,
      "grad_norm": 0.011052712798118591,
      "learning_rate": 0.00014,
      "loss": 11.9324,
      "step": 7
    },
    {
      "epoch": 0.00448681996634885,
      "grad_norm": 0.005740743596106768,
      "learning_rate": 0.00016,
      "loss": 11.935,
      "step": 8
    },
    {
      "epoch": 0.005047672462142457,
      "grad_norm": 0.011872372590005398,
      "learning_rate": 0.00018,
      "loss": 11.9287,
      "step": 9
    },
    {
      "epoch": 0.005047672462142457,
      "eval_loss": 11.93126392364502,
      "eval_runtime": 2.7223,
      "eval_samples_per_second": 275.873,
      "eval_steps_per_second": 138.12,
      "step": 9
    },
    {
      "epoch": 0.005608524957936063,
      "grad_norm": 0.007526675704866648,
      "learning_rate": 0.0002,
      "loss": 11.9335,
      "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": 1211154432.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}