last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0037105751391465678,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0001484230055658627,
      "grad_norm": NaN,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.0001484230055658627,
      "eval_loss": NaN,
      "eval_runtime": 611.4372,
      "eval_samples_per_second": 9.28,
      "eval_steps_per_second": 4.64,
      "step": 1
    },
    {
      "epoch": 0.0002968460111317254,
      "grad_norm": NaN,
      "learning_rate": 6.666666666666667e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.0004452690166975881,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.0005936920222634508,
      "grad_norm": NaN,
      "learning_rate": 9.99524110790929e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.0007421150278293135,
      "grad_norm": NaN,
      "learning_rate": 9.980973490458728e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.0008905380333951762,
      "grad_norm": NaN,
      "learning_rate": 9.957224306869053e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.001038961038961039,
      "grad_norm": NaN,
      "learning_rate": 9.924038765061042e-05,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.0011873840445269016,
      "grad_norm": NaN,
      "learning_rate": 9.881480035599667e-05,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.0013358070500927644,
      "grad_norm": NaN,
      "learning_rate": 9.829629131445342e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.001484230055658627,
      "grad_norm": NaN,
      "learning_rate": 9.768584753741134e-05,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.0016326530612244899,
      "grad_norm": NaN,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.0017810760667903525,
      "grad_norm": NaN,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.0019294990723562153,
      "grad_norm": NaN,
      "learning_rate": 9.53153893518325e-05,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.002077922077922078,
      "grad_norm": NaN,
      "learning_rate": 9.435054165891109e-05,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.0022263450834879408,
      "grad_norm": NaN,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.002374768089053803,
      "grad_norm": NaN,
      "learning_rate": 9.21695722906443e-05,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.002523191094619666,
      "grad_norm": NaN,
      "learning_rate": 9.09576022144496e-05,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.002671614100185529,
      "grad_norm": NaN,
      "learning_rate": 8.966766701456177e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.0028200371057513916,
      "grad_norm": NaN,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 0.002968460111317254,
      "grad_norm": NaN,
      "learning_rate": 8.68638668405062e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.003116883116883117,
      "grad_norm": NaN,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.0032653061224489797,
      "grad_norm": NaN,
      "learning_rate": 8.377951038078302e-05,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 0.003413729128014842,
      "grad_norm": NaN,
      "learning_rate": 8.213938048432697e-05,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 0.003562152133580705,
      "grad_norm": NaN,
      "learning_rate": 8.043807145043604e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.0037105751391465678,
      "grad_norm": NaN,
      "learning_rate": 7.86788218175523e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.0037105751391465678,
      "eval_loss": NaN,
      "eval_runtime": 611.4127,
      "eval_samples_per_second": 9.28,
      "eval_steps_per_second": 4.64,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 75,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.303377210651443e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}