checkpoint-400/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.3574620196604111,
  "eval_steps": 200,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.17873100983020554,
      "grad_norm": 0.8090553879737854,
      "learning_rate": 9.999142157322298e-05,
      "loss": 0.5369,
      "step": 200
    },
    {
      "epoch": 0.17873100983020554,
      "eval_loss": 0.18719753623008728,
      "eval_runtime": 42.7752,
      "eval_samples_per_second": 4.231,
      "eval_steps_per_second": 2.127,
      "step": 200
    },
    {
      "epoch": 0.3574620196604111,
      "grad_norm": 0.3873799443244934,
      "learning_rate": 9.95497608932715e-05,
      "loss": 0.1345,
      "step": 400
    },
    {
      "epoch": 0.3574620196604111,
      "eval_loss": 0.12613661587238312,
      "eval_runtime": 44.9042,
      "eval_samples_per_second": 4.031,
      "eval_steps_per_second": 2.027,
      "step": 400
    }
  ],
  "logging_steps": 200,
  "max_steps": 5595,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.388098770055168e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}