trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.8695652173913043,
  "eval_steps": 500,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.34782608695652173,
      "grad_norm": 2.9206182956695557,
      "learning_rate": 8e-05,
      "loss": 2.5767,
      "mean_token_accuracy": 0.49446070086997307,
      "step": 2,
      "timestamp_in_seconds": 1739746290.6342082
    },
    {
      "epoch": 0.6956521739130435,
      "grad_norm": 3.1101906299591064,
      "learning_rate": 0.00016,
      "loss": 2.4377,
      "mean_token_accuracy": 0.5042006788582926,
      "step": 4,
      "timestamp_in_seconds": 1739746294.6942482
    },
    {
      "epoch": 0.8695652173913043,
      "eval_loss": 1.8889394998550415,
      "eval_mean_token_accuracy": 0.5041654991599027,
      "eval_runtime": 0.227,
      "eval_samples_per_second": 22.026,
      "eval_steps_per_second": 4.405,
      "step": 5
    }
  ],
  "logging_steps": 2,
  "max_steps": 50,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 784315773837312.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}