last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.039721946375372394,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0015888778550148957,
      "grad_norm": NaN,
      "learning_rate": 6.666666666666667e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.0015888778550148957,
      "eval_loss": NaN,
      "eval_runtime": 85.9959,
      "eval_samples_per_second": 6.163,
      "eval_steps_per_second": 3.082,
      "step": 1
    },
    {
      "epoch": 0.0031777557100297915,
      "grad_norm": NaN,
      "learning_rate": 0.00013333333333333334,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.004766633565044687,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.006355511420059583,
      "grad_norm": NaN,
      "learning_rate": 0.0001999048221581858,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.007944389275074478,
      "grad_norm": NaN,
      "learning_rate": 0.00019961946980917456,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.009533267130089375,
      "grad_norm": NaN,
      "learning_rate": 0.00019914448613738106,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.01112214498510427,
      "grad_norm": NaN,
      "learning_rate": 0.00019848077530122083,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.012711022840119166,
      "grad_norm": NaN,
      "learning_rate": 0.00019762960071199333,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.014299900695134062,
      "grad_norm": NaN,
      "learning_rate": 0.00019659258262890683,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.015888778550148957,
      "grad_norm": NaN,
      "learning_rate": 0.0001953716950748227,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.01747765640516385,
      "grad_norm": NaN,
      "learning_rate": 0.00019396926207859084,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.01906653426017875,
      "grad_norm": NaN,
      "learning_rate": 0.0001923879532511287,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.020655412115193644,
      "grad_norm": NaN,
      "learning_rate": 0.000190630778703665,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.02224428997020854,
      "grad_norm": NaN,
      "learning_rate": 0.00018870108331782217,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.023833167825223437,
      "grad_norm": NaN,
      "learning_rate": 0.00018660254037844388,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.02542204568023833,
      "grad_norm": NaN,
      "learning_rate": 0.0001843391445812886,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.027010923535253226,
      "grad_norm": NaN,
      "learning_rate": 0.0001819152044288992,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.028599801390268124,
      "grad_norm": NaN,
      "learning_rate": 0.00017933533402912354,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.03018867924528302,
      "grad_norm": NaN,
      "learning_rate": 0.0001766044443118978,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 0.031777557100297914,
      "grad_norm": NaN,
      "learning_rate": 0.0001737277336810124,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.03336643495531281,
      "grad_norm": NaN,
      "learning_rate": 0.00017071067811865476,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.0349553128103277,
      "grad_norm": NaN,
      "learning_rate": 0.00016755902076156604,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 0.036544190665342605,
      "grad_norm": NaN,
      "learning_rate": 0.00016427876096865394,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 0.0381330685203575,
      "grad_norm": NaN,
      "learning_rate": 0.00016087614290087208,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.039721946375372394,
      "grad_norm": NaN,
      "learning_rate": 0.0001573576436351046,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.039721946375372394,
      "eval_loss": NaN,
      "eval_runtime": 86.6783,
      "eval_samples_per_second": 6.115,
      "eval_steps_per_second": 3.057,
      "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": 3.4633306041483264e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}