last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.003328340822100183,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0003328340822100183,
      "grad_norm": 15.241449356079102,
      "learning_rate": 2e-05,
      "loss": 7.5998,
      "step": 1
    },
    {
      "epoch": 0.0003328340822100183,
      "eval_loss": 1.7267932891845703,
      "eval_runtime": 43.5763,
      "eval_samples_per_second": 29.03,
      "eval_steps_per_second": 14.526,
      "step": 1
    },
    {
      "epoch": 0.0006656681644200366,
      "grad_norm": 9.687618255615234,
      "learning_rate": 4e-05,
      "loss": 5.7769,
      "step": 2
    },
    {
      "epoch": 0.000998502246630055,
      "grad_norm": 12.25117301940918,
      "learning_rate": 6e-05,
      "loss": 6.57,
      "step": 3
    },
    {
      "epoch": 0.000998502246630055,
      "eval_loss": 1.707614541053772,
      "eval_runtime": 43.5579,
      "eval_samples_per_second": 29.042,
      "eval_steps_per_second": 14.532,
      "step": 3
    },
    {
      "epoch": 0.0013313363288400732,
      "grad_norm": 14.178030967712402,
      "learning_rate": 8e-05,
      "loss": 8.4193,
      "step": 4
    },
    {
      "epoch": 0.0016641704110500915,
      "grad_norm": 15.474825859069824,
      "learning_rate": 0.0001,
      "loss": 7.6992,
      "step": 5
    },
    {
      "epoch": 0.00199700449326011,
      "grad_norm": 16.24755096435547,
      "learning_rate": 0.00012,
      "loss": 7.2536,
      "step": 6
    },
    {
      "epoch": 0.00199700449326011,
      "eval_loss": 1.5394411087036133,
      "eval_runtime": 43.6527,
      "eval_samples_per_second": 28.979,
      "eval_steps_per_second": 14.501,
      "step": 6
    },
    {
      "epoch": 0.002329838575470128,
      "grad_norm": 12.019878387451172,
      "learning_rate": 0.00014,
      "loss": 6.1136,
      "step": 7
    },
    {
      "epoch": 0.0026626726576801465,
      "grad_norm": 15.055740356445312,
      "learning_rate": 0.00016,
      "loss": 5.9536,
      "step": 8
    },
    {
      "epoch": 0.0029955067398901645,
      "grad_norm": 10.12070369720459,
      "learning_rate": 0.00018,
      "loss": 5.0164,
      "step": 9
    },
    {
      "epoch": 0.0029955067398901645,
      "eval_loss": 1.2719299793243408,
      "eval_runtime": 43.6539,
      "eval_samples_per_second": 28.978,
      "eval_steps_per_second": 14.5,
      "step": 9
    },
    {
      "epoch": 0.003328340822100183,
      "grad_norm": 7.765052795410156,
      "learning_rate": 0.0002,
      "loss": 4.169,
      "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
}