trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.967509025270758,
  "eval_steps": 500,
  "global_step": 207,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.7220216606498195,
      "grad_norm": 0.7973353266716003,
      "learning_rate": 1.526570048309179e-05,
      "loss": 1.2887,
      "mean_token_accuracy": 0.7081953743100167,
      "num_tokens": 44509.0,
      "step": 50
    },
    {
      "epoch": 1.4332129963898916,
      "grad_norm": 0.8046742677688599,
      "learning_rate": 1.0434782608695653e-05,
      "loss": 0.6647,
      "mean_token_accuracy": 0.8174314507978216,
      "num_tokens": 88762.0,
      "step": 100
    },
    {
      "epoch": 2.1444043321299637,
      "grad_norm": 0.5265176296234131,
      "learning_rate": 5.603864734299518e-06,
      "loss": 0.4189,
      "mean_token_accuracy": 0.8764120337321674,
      "num_tokens": 132445.0,
      "step": 150
    },
    {
      "epoch": 2.8664259927797833,
      "grad_norm": 0.4852680563926697,
      "learning_rate": 7.729468599033817e-07,
      "loss": 0.3727,
      "mean_token_accuracy": 0.8842082077264786,
      "num_tokens": 177453.0,
      "step": 200
    }
  ],
  "logging_steps": 50,
  "max_steps": 207,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 15,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4113387640872960.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}