last-checkpoint/trainer_state.json

{
  "best_metric": NaN,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.03355704697986577,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0013422818791946308,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.0013422818791946308,
      "eval_loss": NaN,
      "eval_runtime": 70.4479,
      "eval_samples_per_second": 4.457,
      "eval_steps_per_second": 2.229,
      "step": 1
    },
    {
      "epoch": 0.0026845637583892616,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.004026845637583893,
      "grad_norm": NaN,
      "learning_rate": 0.00019978589232386035,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.005369127516778523,
      "grad_norm": NaN,
      "learning_rate": 0.00019914448613738106,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.006711409395973154,
      "grad_norm": NaN,
      "learning_rate": 0.00019807852804032305,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.008053691275167786,
      "grad_norm": NaN,
      "learning_rate": 0.00019659258262890683,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.009395973154362415,
      "grad_norm": NaN,
      "learning_rate": 0.0001946930129495106,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.010738255033557046,
      "grad_norm": NaN,
      "learning_rate": 0.0001923879532511287,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.012080536912751677,
      "grad_norm": NaN,
      "learning_rate": 0.00018968727415326884,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.013422818791946308,
      "grad_norm": NaN,
      "learning_rate": 0.00018660254037844388,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.01476510067114094,
      "grad_norm": NaN,
      "learning_rate": 0.00018314696123025454,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.016107382550335572,
      "grad_norm": NaN,
      "learning_rate": 0.00017933533402912354,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.0174496644295302,
      "grad_norm": NaN,
      "learning_rate": 0.00017518398074789775,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.01879194630872483,
      "grad_norm": NaN,
      "learning_rate": 0.00017071067811865476,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.020134228187919462,
      "grad_norm": NaN,
      "learning_rate": 0.00016593458151000688,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.021476510067114093,
      "grad_norm": NaN,
      "learning_rate": 0.00016087614290087208,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.022818791946308724,
      "grad_norm": NaN,
      "learning_rate": 0.00015555702330196023,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.024161073825503355,
      "grad_norm": NaN,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.025503355704697986,
      "grad_norm": NaN,
      "learning_rate": 0.00014422886902190014,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 0.026845637583892617,
      "grad_norm": NaN,
      "learning_rate": 0.000138268343236509,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.028187919463087248,
      "grad_norm": NaN,
      "learning_rate": 0.00013214394653031616,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.02953020134228188,
      "grad_norm": NaN,
      "learning_rate": 0.00012588190451025207,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 0.03087248322147651,
      "grad_norm": NaN,
      "learning_rate": 0.00011950903220161285,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 0.032214765100671144,
      "grad_norm": NaN,
      "learning_rate": 0.00011305261922200519,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.03355704697986577,
      "grad_norm": NaN,
      "learning_rate": 0.00010654031292301432,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.03355704697986577,
      "eval_loss": NaN,
      "eval_runtime": 70.7415,
      "eval_samples_per_second": 4.439,
      "eval_steps_per_second": 2.219,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 1.8444107907072e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}