last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0005649238765076406,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 5.649238765076406e-05,
      "grad_norm": 2.6869380474090576,
      "learning_rate": 2e-05,
      "loss": 17.6344,
      "step": 1
    },
    {
      "epoch": 5.649238765076406e-05,
      "eval_loss": 4.109318733215332,
      "eval_runtime": 400.1503,
      "eval_samples_per_second": 18.628,
      "eval_steps_per_second": 9.314,
      "step": 1
    },
    {
      "epoch": 0.00011298477530152812,
      "grad_norm": 2.3077611923217773,
      "learning_rate": 4e-05,
      "loss": 17.0427,
      "step": 2
    },
    {
      "epoch": 0.00016947716295229217,
      "grad_norm": 1.559274673461914,
      "learning_rate": 6e-05,
      "loss": 14.4678,
      "step": 3
    },
    {
      "epoch": 0.00016947716295229217,
      "eval_loss": 4.103186130523682,
      "eval_runtime": 397.2746,
      "eval_samples_per_second": 18.763,
      "eval_steps_per_second": 9.381,
      "step": 3
    },
    {
      "epoch": 0.00022596955060305625,
      "grad_norm": 1.9143805503845215,
      "learning_rate": 8e-05,
      "loss": 14.7594,
      "step": 4
    },
    {
      "epoch": 0.0002824619382538203,
      "grad_norm": 1.7792251110076904,
      "learning_rate": 0.0001,
      "loss": 14.4479,
      "step": 5
    },
    {
      "epoch": 0.00033895432590458433,
      "grad_norm": 3.0913233757019043,
      "learning_rate": 0.00012,
      "loss": 14.8808,
      "step": 6
    },
    {
      "epoch": 0.00033895432590458433,
      "eval_loss": 4.005303859710693,
      "eval_runtime": 396.2856,
      "eval_samples_per_second": 18.81,
      "eval_steps_per_second": 9.405,
      "step": 6
    },
    {
      "epoch": 0.0003954467135553484,
      "grad_norm": 2.453087091445923,
      "learning_rate": 0.00014,
      "loss": 14.2979,
      "step": 7
    },
    {
      "epoch": 0.0004519391012061125,
      "grad_norm": 5.9633355140686035,
      "learning_rate": 0.00016,
      "loss": 14.6733,
      "step": 8
    },
    {
      "epoch": 0.0005084314888568766,
      "grad_norm": 2.196599006652832,
      "learning_rate": 0.00018,
      "loss": 14.1417,
      "step": 9
    },
    {
      "epoch": 0.0005084314888568766,
      "eval_loss": 3.4993884563446045,
      "eval_runtime": 397.4265,
      "eval_samples_per_second": 18.756,
      "eval_steps_per_second": 9.378,
      "step": 9
    },
    {
      "epoch": 0.0005649238765076406,
      "grad_norm": 6.464872360229492,
      "learning_rate": 0.0002,
      "loss": 13.0186,
      "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": 3245379912990720.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}