last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.16326530612244897,
  "eval_steps": 10,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00816326530612245,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.00816326530612245,
      "eval_loss": NaN,
      "eval_runtime": 19.9139,
      "eval_samples_per_second": 5.222,
      "eval_steps_per_second": 2.611,
      "step": 1
    },
    {
      "epoch": 0.0163265306122449,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.024489795918367346,
      "grad_norm": NaN,
      "learning_rate": 9.924038765061042e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.0326530612244898,
      "grad_norm": NaN,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.04081632653061224,
      "grad_norm": NaN,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.04897959183673469,
      "grad_norm": NaN,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.05714285714285714,
      "grad_norm": NaN,
      "learning_rate": 8.213938048432697e-05,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.0653061224489796,
      "grad_norm": NaN,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.07346938775510205,
      "grad_norm": NaN,
      "learning_rate": 6.710100716628344e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.08163265306122448,
      "grad_norm": NaN,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.08163265306122448,
      "eval_loss": NaN,
      "eval_runtime": 19.311,
      "eval_samples_per_second": 5.386,
      "eval_steps_per_second": 2.693,
      "step": 10
    },
    {
      "epoch": 0.08979591836734693,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.09795918367346938,
      "grad_norm": NaN,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.10612244897959183,
      "grad_norm": NaN,
      "learning_rate": 3.289899283371657e-05,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.11428571428571428,
      "grad_norm": NaN,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.12244897959183673,
      "grad_norm": NaN,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.1306122448979592,
      "grad_norm": NaN,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.13877551020408163,
      "grad_norm": NaN,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.1469387755102041,
      "grad_norm": NaN,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.15510204081632653,
      "grad_norm": NaN,
      "learning_rate": 7.596123493895991e-07,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 0.16326530612244897,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.16326530612244897,
      "eval_loss": NaN,
      "eval_runtime": 19.6287,
      "eval_samples_per_second": 5.298,
      "eval_steps_per_second": 2.649,
      "step": 20
    }
  ],
  "logging_steps": 1,
  "max_steps": 20,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.936840561406771e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}