last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.04338394793926247,
  "eval_steps": 5,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004338394793926247,
      "eval_loss": 4.0736517906188965,
      "eval_runtime": 11.3009,
      "eval_samples_per_second": 8.672,
      "eval_steps_per_second": 4.336,
      "step": 1
    },
    {
      "epoch": 0.013015184381778741,
      "grad_norm": 5.656111717224121,
      "learning_rate": 6e-05,
      "loss": 3.6883,
      "step": 3
    },
    {
      "epoch": 0.021691973969631236,
      "eval_loss": 3.306220293045044,
      "eval_runtime": 11.3027,
      "eval_samples_per_second": 8.671,
      "eval_steps_per_second": 4.335,
      "step": 5
    },
    {
      "epoch": 0.026030368763557483,
      "grad_norm": 2.3464417457580566,
      "learning_rate": 0.00012,
      "loss": 3.1322,
      "step": 6
    },
    {
      "epoch": 0.039045553145336226,
      "grad_norm": 2.036963701248169,
      "learning_rate": 0.00018,
      "loss": 2.6114,
      "step": 9
    },
    {
      "epoch": 0.04338394793926247,
      "eval_loss": 2.7751786708831787,
      "eval_runtime": 11.3023,
      "eval_samples_per_second": 8.671,
      "eval_steps_per_second": 4.335,
      "step": 10
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1005298290524160.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}