last-checkpoint/trainer_state.json

{
  "best_metric": NaN,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 1.1850220264317182,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04698972099853157,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 645.5719,
      "step": 1
    },
    {
      "epoch": 0.04698972099853157,
      "eval_loss": NaN,
      "eval_runtime": 2.7767,
      "eval_samples_per_second": 18.007,
      "eval_steps_per_second": 4.682,
      "step": 1
    },
    {
      "epoch": 0.09397944199706314,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.14096916299559473,
      "grad_norm": NaN,
      "learning_rate": 9.958086757163489e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.18795888399412627,
      "grad_norm": NaN,
      "learning_rate": 9.833127793065098e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.23494860499265785,
      "grad_norm": NaN,
      "learning_rate": 9.627450856774539e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.28193832599118945,
      "grad_norm": NaN,
      "learning_rate": 9.3448873204592e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.328928046989721,
      "grad_norm": NaN,
      "learning_rate": 8.990700808169889e-05,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.37591776798825255,
      "grad_norm": NaN,
      "learning_rate": 8.571489144483944e-05,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.42290748898678415,
      "grad_norm": NaN,
      "learning_rate": 8.095061449516903e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.4698972099853157,
      "grad_norm": NaN,
      "learning_rate": 7.570292669790186e-05,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.5168869309838473,
      "grad_norm": NaN,
      "learning_rate": 7.006958254769438e-05,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.5638766519823789,
      "grad_norm": NaN,
      "learning_rate": 6.415552058736854e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.6108663729809104,
      "grad_norm": NaN,
      "learning_rate": 5.80709086014102e-05,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.657856093979442,
      "grad_norm": NaN,
      "learning_rate": 5.192909139858981e-05,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.7048458149779736,
      "grad_norm": NaN,
      "learning_rate": 4.584447941263149e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.7518355359765051,
      "grad_norm": NaN,
      "learning_rate": 3.9930417452305626e-05,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.7988252569750367,
      "grad_norm": NaN,
      "learning_rate": 3.4297073302098156e-05,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.8458149779735683,
      "grad_norm": NaN,
      "learning_rate": 2.9049385504830985e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.8928046989720999,
      "grad_norm": NaN,
      "learning_rate": 2.4285108555160577e-05,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 0.9397944199706314,
      "grad_norm": NaN,
      "learning_rate": 2.0092991918301108e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.986784140969163,
      "grad_norm": NaN,
      "learning_rate": 1.6551126795408016e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 1.0440528634361232,
      "grad_norm": NaN,
      "learning_rate": 1.3725491432254624e-05,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 1.091042584434655,
      "grad_norm": NaN,
      "learning_rate": 1.1668722069349041e-05,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 1.1380323054331865,
      "grad_norm": NaN,
      "learning_rate": 1.0419132428365116e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 1.1850220264317182,
      "grad_norm": NaN,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 1.1850220264317182,
      "eval_loss": NaN,
      "eval_runtime": 2.9847,
      "eval_samples_per_second": 16.752,
      "eval_steps_per_second": 4.356,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 25,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 25,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.658781594162299e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}