last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.2955818294959552,
  "eval_steps": 55,
  "global_step": 95,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0031113876789047915,
      "eval_loss": NaN,
      "eval_runtime": 12.6621,
      "eval_samples_per_second": 13.426,
      "eval_steps_per_second": 6.713,
      "step": 1
    },
    {
      "epoch": 0.009334163036714374,
      "grad_norm": NaN,
      "learning_rate": 6e-06,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.018668326073428748,
      "grad_norm": NaN,
      "learning_rate": 1.2e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.028002489110143122,
      "grad_norm": NaN,
      "learning_rate": 1.8e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.037336652146857496,
      "grad_norm": NaN,
      "learning_rate": 2.4e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.04667081518357187,
      "grad_norm": NaN,
      "learning_rate": 3e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.056004978220286245,
      "grad_norm": NaN,
      "learning_rate": 3.6e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.06533914125700062,
      "grad_norm": NaN,
      "learning_rate": 4.2e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.07467330429371499,
      "grad_norm": NaN,
      "learning_rate": 4.8e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.08400746733042937,
      "grad_norm": NaN,
      "learning_rate": 5.4000000000000005e-05,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.09334163036714374,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.10267579340385811,
      "grad_norm": NaN,
      "learning_rate": 6.6e-05,
      "loss": 0.0,
      "step": 33
    },
    {
      "epoch": 0.11200995644057249,
      "grad_norm": NaN,
      "learning_rate": 7.2e-05,
      "loss": 0.0,
      "step": 36
    },
    {
      "epoch": 0.12134411947728686,
      "grad_norm": NaN,
      "learning_rate": 7.800000000000001e-05,
      "loss": 0.0,
      "step": 39
    },
    {
      "epoch": 0.13067828251400124,
      "grad_norm": NaN,
      "learning_rate": 8.4e-05,
      "loss": 0.0,
      "step": 42
    },
    {
      "epoch": 0.14001244555071563,
      "grad_norm": NaN,
      "learning_rate": 9e-05,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 0.14934660858742999,
      "grad_norm": NaN,
      "learning_rate": 9.6e-05,
      "loss": 0.0,
      "step": 48
    },
    {
      "epoch": 0.15868077162414437,
      "grad_norm": NaN,
      "learning_rate": 9.987820251299122e-05,
      "loss": 0.0,
      "step": 51
    },
    {
      "epoch": 0.16801493466085873,
      "grad_norm": NaN,
      "learning_rate": 9.806308479691595e-05,
      "loss": 0.0,
      "step": 54
    },
    {
      "epoch": 0.17112632233976355,
      "eval_loss": NaN,
      "eval_runtime": 12.9311,
      "eval_samples_per_second": 13.147,
      "eval_steps_per_second": 6.573,
      "step": 55
    },
    {
      "epoch": 0.17734909769757312,
      "grad_norm": NaN,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.0,
      "step": 57
    },
    {
      "epoch": 0.18668326073428748,
      "grad_norm": NaN,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.0,
      "step": 60
    },
    {
      "epoch": 0.19601742377100187,
      "grad_norm": NaN,
      "learning_rate": 8.07830737662829e-05,
      "loss": 0.0,
      "step": 63
    },
    {
      "epoch": 0.20535158680771623,
      "grad_norm": NaN,
      "learning_rate": 7.191855733945387e-05,
      "loss": 0.0,
      "step": 66
    },
    {
      "epoch": 0.21468574984443062,
      "grad_norm": NaN,
      "learning_rate": 6.209609477998338e-05,
      "loss": 0.0,
      "step": 69
    },
    {
      "epoch": 0.22401991288114498,
      "grad_norm": NaN,
      "learning_rate": 5.174497483512506e-05,
      "loss": 0.0,
      "step": 72
    },
    {
      "epoch": 0.23335407591785937,
      "grad_norm": NaN,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.0,
      "step": 75
    },
    {
      "epoch": 0.24268823895457373,
      "grad_norm": NaN,
      "learning_rate": 3.12696703292044e-05,
      "loss": 0.0,
      "step": 78
    },
    {
      "epoch": 0.2520224019912881,
      "grad_norm": NaN,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 0.0,
      "step": 81
    },
    {
      "epoch": 0.2613565650280025,
      "grad_norm": NaN,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 0.0,
      "step": 84
    },
    {
      "epoch": 0.2706907280647169,
      "grad_norm": NaN,
      "learning_rate": 7.597595192178702e-06,
      "loss": 0.0,
      "step": 87
    },
    {
      "epoch": 0.28002489110143125,
      "grad_norm": NaN,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.0,
      "step": 90
    },
    {
      "epoch": 0.2893590541381456,
      "grad_norm": NaN,
      "learning_rate": 4.865965629214819e-07,
      "loss": 0.0,
      "step": 93
    }
  ],
  "logging_steps": 3,
  "max_steps": 95,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 80,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.95052136267776e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}