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": 0.01730411872267723,
      "learning_rate": 2e-05,
      "loss": 11.9315,
      "step": 1
    },
    {
      "epoch": 0.0005608524957936063,
      "eval_loss": 11.931304931640625,
      "eval_runtime": 2.8798,
      "eval_samples_per_second": 260.778,
      "eval_steps_per_second": 130.562,
      "step": 1
    },
    {
      "epoch": 0.0011217049915872126,
      "grad_norm": 0.009905373677611351,
      "learning_rate": 4e-05,
      "loss": 11.9304,
      "step": 2
    },
    {
      "epoch": 0.0016825574873808188,
      "grad_norm": 0.012362608686089516,
      "learning_rate": 6e-05,
      "loss": 11.9319,
      "step": 3
    },
    {
      "epoch": 0.0016825574873808188,
      "eval_loss": 11.931302070617676,
      "eval_runtime": 2.8223,
      "eval_samples_per_second": 266.096,
      "eval_steps_per_second": 133.225,
      "step": 3
    },
    {
      "epoch": 0.002243409983174425,
      "grad_norm": 0.015306780114769936,
      "learning_rate": 8e-05,
      "loss": 11.9328,
      "step": 4
    },
    {
      "epoch": 0.0028042624789680315,
      "grad_norm": 0.021004365757107735,
      "learning_rate": 0.0001,
      "loss": 11.9248,
      "step": 5
    },
    {
      "epoch": 0.0033651149747616375,
      "grad_norm": 0.009976493194699287,
      "learning_rate": 0.00012,
      "loss": 11.926,
      "step": 6
    },
    {
      "epoch": 0.0033651149747616375,
      "eval_loss": 11.931286811828613,
      "eval_runtime": 2.8588,
      "eval_samples_per_second": 262.698,
      "eval_steps_per_second": 131.524,
      "step": 6
    },
    {
      "epoch": 0.003925967470555244,
      "grad_norm": 0.011741932481527328,
      "learning_rate": 0.00014,
      "loss": 11.9324,
      "step": 7
    },
    {
      "epoch": 0.00448681996634885,
      "grad_norm": 0.006682810839265585,
      "learning_rate": 0.00016,
      "loss": 11.935,
      "step": 8
    },
    {
      "epoch": 0.005047672462142457,
      "grad_norm": 0.012469079345464706,
      "learning_rate": 0.00018,
      "loss": 11.9287,
      "step": 9
    },
    {
      "epoch": 0.005047672462142457,
      "eval_loss": 11.931255340576172,
      "eval_runtime": 2.9712,
      "eval_samples_per_second": 252.758,
      "eval_steps_per_second": 126.547,
      "step": 9
    },
    {
      "epoch": 0.005608524957936063,
      "grad_norm": 0.008142386563122272,
      "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
}