last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00028232039129606236,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.8232039129606233e-05,
      "grad_norm": 9.061311721801758,
      "learning_rate": 2e-05,
      "loss": 5.5011,
      "step": 1
    },
    {
      "epoch": 5.6464078259212465e-05,
      "grad_norm": 9.490124702453613,
      "learning_rate": 4e-05,
      "loss": 5.3158,
      "step": 2
    },
    {
      "epoch": 8.46961173888187e-05,
      "grad_norm": 8.515461921691895,
      "learning_rate": 6e-05,
      "loss": 5.3218,
      "step": 3
    },
    {
      "epoch": 8.46961173888187e-05,
      "eval_loss": 1.3254905939102173,
      "eval_runtime": 661.7944,
      "eval_samples_per_second": 22.537,
      "eval_steps_per_second": 11.269,
      "step": 3
    },
    {
      "epoch": 0.00011292815651842493,
      "grad_norm": 9.501084327697754,
      "learning_rate": 8e-05,
      "loss": 4.932,
      "step": 4
    },
    {
      "epoch": 0.00014116019564803118,
      "grad_norm": 8.434340476989746,
      "learning_rate": 0.0001,
      "loss": 4.7143,
      "step": 5
    },
    {
      "epoch": 0.0001693922347776374,
      "grad_norm": 7.876411437988281,
      "learning_rate": 0.00012,
      "loss": 5.0832,
      "step": 6
    },
    {
      "epoch": 0.0001693922347776374,
      "eval_loss": 1.1657943725585938,
      "eval_runtime": 659.4004,
      "eval_samples_per_second": 22.619,
      "eval_steps_per_second": 11.31,
      "step": 6
    },
    {
      "epoch": 0.00019762427390724362,
      "grad_norm": 6.9604010581970215,
      "learning_rate": 0.00014,
      "loss": 4.7937,
      "step": 7
    },
    {
      "epoch": 0.00022585631303684986,
      "grad_norm": 5.833314895629883,
      "learning_rate": 0.00016,
      "loss": 4.0814,
      "step": 8
    },
    {
      "epoch": 0.0002540883521664561,
      "grad_norm": 6.258748531341553,
      "learning_rate": 0.00018,
      "loss": 3.9279,
      "step": 9
    },
    {
      "epoch": 0.0002540883521664561,
      "eval_loss": 1.065926194190979,
      "eval_runtime": 660.9904,
      "eval_samples_per_second": 22.565,
      "eval_steps_per_second": 11.283,
      "step": 9
    },
    {
      "epoch": 0.00028232039129606236,
      "grad_norm": 5.831711292266846,
      "learning_rate": 0.0002,
      "loss": 4.1325,
      "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": 1752669785948160.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}