trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.96,
  "eval_steps": 25,
  "global_step": 12,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08,
      "grad_norm": 91.3963394165039,
      "learning_rate": 0.0002,
      "loss": 9.8814,
      "step": 1
    },
    {
      "epoch": 0.16,
      "grad_norm": 69.82352447509766,
      "learning_rate": 0.0002,
      "loss": 9.508,
      "step": 2
    },
    {
      "epoch": 0.24,
      "grad_norm": 88.77470397949219,
      "learning_rate": 0.0002,
      "loss": 8.8757,
      "step": 3
    },
    {
      "epoch": 0.32,
      "grad_norm": 78.74607849121094,
      "learning_rate": 0.0002,
      "loss": 8.1277,
      "step": 4
    },
    {
      "epoch": 0.4,
      "grad_norm": 57.29794692993164,
      "learning_rate": 0.0002,
      "loss": 7.5538,
      "step": 5
    },
    {
      "epoch": 0.48,
      "grad_norm": 48.130455017089844,
      "learning_rate": 0.0002,
      "loss": 7.0051,
      "step": 6
    },
    {
      "epoch": 0.56,
      "grad_norm": 53.24027633666992,
      "learning_rate": 0.0002,
      "loss": 6.8888,
      "step": 7
    },
    {
      "epoch": 0.64,
      "grad_norm": 60.705360412597656,
      "learning_rate": 0.0002,
      "loss": 6.9736,
      "step": 8
    },
    {
      "epoch": 0.72,
      "grad_norm": 54.261192321777344,
      "learning_rate": 0.0002,
      "loss": 6.9427,
      "step": 9
    },
    {
      "epoch": 0.8,
      "grad_norm": 26.81684684753418,
      "learning_rate": 0.0002,
      "loss": 6.5488,
      "step": 10
    },
    {
      "epoch": 0.88,
      "grad_norm": 26.71163558959961,
      "learning_rate": 0.0002,
      "loss": 6.1613,
      "step": 11
    },
    {
      "epoch": 0.96,
      "grad_norm": 17.654388427734375,
      "learning_rate": 0.0002,
      "loss": 6.4909,
      "step": 12
    },
    {
      "epoch": 0.96,
      "step": 12,
      "total_flos": 21902076557316.0,
      "train_loss": 7.579820553461711,
      "train_runtime": 210.354,
      "train_samples_per_second": 0.951,
      "train_steps_per_second": 0.057
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 12,
  "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": 21902076557316.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}