trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9937888198757764,
  "eval_steps": 100,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2484472049689441,
      "grad_norm": 6.372331155665467,
      "learning_rate": 1.866025403784439e-05,
      "loss": 1.2498,
      "mean_token_accuracy": 0.6807276747087718,
      "step": 5
    },
    {
      "epoch": 0.4968944099378882,
      "grad_norm": 1.5571413002554233,
      "learning_rate": 1.1736481776669307e-05,
      "loss": 1.1252,
      "mean_token_accuracy": 0.6975850154987661,
      "step": 10
    },
    {
      "epoch": 0.7453416149068323,
      "grad_norm": 1.1756159519068012,
      "learning_rate": 3.5721239031346067e-06,
      "loss": 1.0611,
      "mean_token_accuracy": 0.709350785390354,
      "step": 15
    },
    {
      "epoch": 0.9937888198757764,
      "grad_norm": 0.9077992043303185,
      "learning_rate": 0.0,
      "loss": 1.0149,
      "mean_token_accuracy": 0.721418722090708,
      "step": 20
    },
    {
      "epoch": 0.9937888198757764,
      "step": 20,
      "total_flos": 2236763602944.0,
      "train_loss": 1.1127344369888306,
      "train_runtime": 454.1797,
      "train_samples_per_second": 2.834,
      "train_steps_per_second": 0.044
    }
  ],
  "logging_steps": 5,
  "max_steps": 20,
  "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": false,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2236763602944.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}