last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.000116266902300922,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.16266902300922e-05,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 1.16266902300922e-05,
      "eval_loss": NaN,
      "eval_runtime": 2763.256,
      "eval_samples_per_second": 13.106,
      "eval_steps_per_second": 6.553,
      "step": 1
    },
    {
      "epoch": 2.32533804601844e-05,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 3.48800706902766e-05,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 3.48800706902766e-05,
      "eval_loss": NaN,
      "eval_runtime": 3695.6357,
      "eval_samples_per_second": 9.799,
      "eval_steps_per_second": 4.9,
      "step": 3
    },
    {
      "epoch": 4.65067609203688e-05,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 5.8133451150461e-05,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 6.97601413805532e-05,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 6.97601413805532e-05,
      "eval_loss": NaN,
      "eval_runtime": 2817.7646,
      "eval_samples_per_second": 12.852,
      "eval_steps_per_second": 6.426,
      "step": 6
    },
    {
      "epoch": 8.13868316106454e-05,
      "grad_norm": NaN,
      "learning_rate": 0.00014,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 9.30135218407376e-05,
      "grad_norm": NaN,
      "learning_rate": 0.00016,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.0001046402120708298,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.0001046402120708298,
      "eval_loss": NaN,
      "eval_runtime": 3447.5982,
      "eval_samples_per_second": 10.504,
      "eval_steps_per_second": 5.252,
      "step": 9
    },
    {
      "epoch": 0.000116266902300922,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2931721456582656.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}