last-checkpoint/trainer_state.json

{
  "best_metric": NaN,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 2.0618556701030926,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08247422680412371,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.08247422680412371,
      "eval_loss": NaN,
      "eval_runtime": 5.4854,
      "eval_samples_per_second": 9.115,
      "eval_steps_per_second": 2.37,
      "step": 1
    },
    {
      "epoch": 0.16494845360824742,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.24742268041237114,
      "grad_norm": NaN,
      "learning_rate": 9.981884322978576e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.32989690721649484,
      "grad_norm": NaN,
      "learning_rate": 9.927683148693833e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.41237113402061853,
      "grad_norm": NaN,
      "learning_rate": 9.83783287313134e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.4948453608247423,
      "grad_norm": NaN,
      "learning_rate": 9.713056917878818e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.5773195876288659,
      "grad_norm": NaN,
      "learning_rate": 9.554359905560886e-05,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.6597938144329897,
      "grad_norm": NaN,
      "learning_rate": 9.363019571208397e-05,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.7422680412371134,
      "grad_norm": NaN,
      "learning_rate": 9.140576474687264e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.8247422680412371,
      "grad_norm": NaN,
      "learning_rate": 8.88882159701625e-05,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.9072164948453608,
      "grad_norm": NaN,
      "learning_rate": 8.609781920440891e-05,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.9896907216494846,
      "grad_norm": NaN,
      "learning_rate": 8.305704108364301e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 1.0721649484536082,
      "grad_norm": NaN,
      "learning_rate": 7.979036416534463e-05,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 1.1546391752577319,
      "grad_norm": NaN,
      "learning_rate": 7.632408981128494e-05,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 1.2371134020618557,
      "grad_norm": NaN,
      "learning_rate": 7.268612642442657e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 1.3195876288659794,
      "grad_norm": NaN,
      "learning_rate": 6.890576474687263e-05,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 1.402061855670103,
      "grad_norm": NaN,
      "learning_rate": 6.501344202803414e-05,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 1.4845360824742269,
      "grad_norm": NaN,
      "learning_rate": 6.10404969617945e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 1.5670103092783505,
      "grad_norm": NaN,
      "learning_rate": 5.7018917365773184e-05,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 1.6494845360824741,
      "grad_norm": NaN,
      "learning_rate": 5.2981082634226854e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 1.731958762886598,
      "grad_norm": NaN,
      "learning_rate": 4.895950303820552e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 1.8144329896907216,
      "grad_norm": NaN,
      "learning_rate": 4.498655797196586e-05,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 1.8969072164948453,
      "grad_norm": NaN,
      "learning_rate": 4.109423525312738e-05,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 1.9793814432989691,
      "grad_norm": NaN,
      "learning_rate": 3.7313873575573445e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 2.0618556701030926,
      "grad_norm": NaN,
      "learning_rate": 3.3675910188715066e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 2.0618556701030926,
      "eval_loss": NaN,
      "eval_runtime": 4.2105,
      "eval_samples_per_second": 11.875,
      "eval_steps_per_second": 3.088,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 37,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.926288903186678e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}