trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 65,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.015384615384615385,
      "grad_norm": 0.04046085175171661,
      "learning_rate": 1.4285714285714286e-06,
      "loss": 0.0353,
      "step": 1
    },
    {
      "epoch": 0.07692307692307693,
      "grad_norm": 0.05091567032743089,
      "learning_rate": 7.1428571428571436e-06,
      "loss": 0.0465,
      "step": 5
    },
    {
      "epoch": 0.15384615384615385,
      "grad_norm": 0.05619972708251679,
      "learning_rate": 9.934132612707631e-06,
      "loss": 0.0404,
      "step": 10
    },
    {
      "epoch": 0.23076923076923078,
      "grad_norm": 0.04566156246255052,
      "learning_rate": 9.537877098354787e-06,
      "loss": 0.0407,
      "step": 15
    },
    {
      "epoch": 0.3076923076923077,
      "grad_norm": 0.04721473521715762,
      "learning_rate": 8.810810275638183e-06,
      "loss": 0.0382,
      "step": 20
    },
    {
      "epoch": 0.38461538461538464,
      "grad_norm": 0.04788500668846418,
      "learning_rate": 7.805935326811913e-06,
      "loss": 0.0355,
      "step": 25
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 0.0368771022335887,
      "learning_rate": 6.5965076506799e-06,
      "loss": 0.0324,
      "step": 30
    },
    {
      "epoch": 0.5384615384615384,
      "grad_norm": 0.042181867254456516,
      "learning_rate": 5.270694542927089e-06,
      "loss": 0.0377,
      "step": 35
    },
    {
      "epoch": 0.6153846153846154,
      "grad_norm": 0.03765669549965176,
      "learning_rate": 3.92514779894488e-06,
      "loss": 0.03,
      "step": 40
    },
    {
      "epoch": 0.6923076923076923,
      "grad_norm": 0.036952508227801856,
      "learning_rate": 2.65795779650105e-06,
      "loss": 0.0293,
      "step": 45
    },
    {
      "epoch": 0.7692307692307693,
      "grad_norm": 0.031901793604600534,
      "learning_rate": 1.561502705732883e-06,
      "loss": 0.0272,
      "step": 50
    },
    {
      "epoch": 0.8461538461538461,
      "grad_norm": 0.03100270332790572,
      "learning_rate": 7.157141191620548e-07,
      "loss": 0.0245,
      "step": 55
    },
    {
      "epoch": 0.9230769230769231,
      "grad_norm": 0.028704808369762864,
      "learning_rate": 1.8225003740388546e-07,
      "loss": 0.0266,
      "step": 60
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.030439422147218023,
      "learning_rate": 0.0,
      "loss": 0.0257,
      "step": 65
    },
    {
      "epoch": 1.0,
      "step": 65,
      "total_flos": 1.5254199041471283e+17,
      "train_loss": 0.033259428751010164,
      "train_runtime": 698.6653,
      "train_samples_per_second": 2.233,
      "train_steps_per_second": 0.093
    }
  ],
  "logging_steps": 5,
  "max_steps": 65,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.5254199041471283e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}