trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 10.0,
  "eval_steps": 500,
  "global_step": 330,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 2.0112204551696777,
      "learning_rate": 9.769776049884563e-05,
      "loss": 1.9353,
      "step": 33
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.6668552160263062,
      "learning_rate": 9.072879760251679e-05,
      "loss": 0.7608,
      "step": 66
    },
    {
      "epoch": 3.0,
      "grad_norm": 2.5093536376953125,
      "learning_rate": 7.97730162226344e-05,
      "loss": 0.4369,
      "step": 99
    },
    {
      "epoch": 4.0,
      "grad_norm": 2.4672605991363525,
      "learning_rate": 6.590284457407876e-05,
      "loss": 0.2519,
      "step": 132
    },
    {
      "epoch": 5.0,
      "grad_norm": 2.61997652053833,
      "learning_rate": 5.047599169697884e-05,
      "loss": 0.1368,
      "step": 165
    },
    {
      "epoch": 6.0,
      "grad_norm": 2.740408182144165,
      "learning_rate": 3.5002545436149474e-05,
      "loss": 0.0935,
      "step": 198
    },
    {
      "epoch": 7.0,
      "grad_norm": 1.2550326585769653,
      "learning_rate": 2.09971545214401e-05,
      "loss": 0.0549,
      "step": 231
    },
    {
      "epoch": 8.0,
      "grad_norm": 1.0139986276626587,
      "learning_rate": 9.830764196878872e-06,
      "loss": 0.0364,
      "step": 264
    },
    {
      "epoch": 9.0,
      "grad_norm": 0.5114002823829651,
      "learning_rate": 2.596418548250029e-06,
      "loss": 0.0314,
      "step": 297
    },
    {
      "epoch": 10.0,
      "grad_norm": 0.26823389530181885,
      "learning_rate": 2.265732291356626e-09,
      "loss": 0.0295,
      "step": 330
    }
  ],
  "logging_steps": 500,
  "max_steps": 330,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "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": 2301871990210560.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}