trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9976689976689976,
  "eval_steps": 500,
  "global_step": 107,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.09324009324009325,
      "grad_norm": 0.34649500250816345,
      "learning_rate": 4.545454545454546e-05,
      "loss": 3.2724,
      "step": 10
    },
    {
      "epoch": 0.1864801864801865,
      "grad_norm": NaN,
      "learning_rate": 4.914814565722671e-05,
      "loss": 3.0626,
      "step": 20
    },
    {
      "epoch": 0.27972027972027974,
      "grad_norm": 0.25361865758895874,
      "learning_rate": 4.5786740307563636e-05,
      "loss": 2.9196,
      "step": 30
    },
    {
      "epoch": 0.372960372960373,
      "grad_norm": 0.2663494646549225,
      "learning_rate": 4.021903572521802e-05,
      "loss": 2.8823,
      "step": 40
    },
    {
      "epoch": 0.4662004662004662,
      "grad_norm": 0.41050922870635986,
      "learning_rate": 3.303598663257904e-05,
      "loss": 2.828,
      "step": 50
    },
    {
      "epoch": 0.5594405594405595,
      "grad_norm": 0.2641640305519104,
      "learning_rate": 2.5e-05,
      "loss": 2.7899,
      "step": 60
    },
    {
      "epoch": 0.6526806526806527,
      "grad_norm": 0.2726258635520935,
      "learning_rate": 1.6964013367420966e-05,
      "loss": 2.7625,
      "step": 70
    },
    {
      "epoch": 0.745920745920746,
      "grad_norm": 0.25895363092422485,
      "learning_rate": 9.780964274781984e-06,
      "loss": 2.7318,
      "step": 80
    },
    {
      "epoch": 0.8391608391608392,
      "grad_norm": 0.2540779709815979,
      "learning_rate": 4.213259692436367e-06,
      "loss": 2.7024,
      "step": 90
    },
    {
      "epoch": 0.9324009324009324,
      "grad_norm": 0.26027920842170715,
      "learning_rate": 8.51854342773295e-07,
      "loss": 2.7023,
      "step": 100
    },
    {
      "epoch": 0.9976689976689976,
      "step": 107,
      "total_flos": 1.5832269964129075e+17,
      "train_loss": 2.857464264486438,
      "train_runtime": 1269.0499,
      "train_samples_per_second": 2.7,
      "train_steps_per_second": 0.084
    }
  ],
  "logging_steps": 10,
  "max_steps": 107,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.5832269964129075e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}