last-checkpoint/trainer_state.json

{
  "best_metric": NaN,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.0004880072225068931,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.9520288900275725e-05,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 1.9520288900275725e-05,
      "eval_loss": NaN,
      "eval_runtime": 6845.2377,
      "eval_samples_per_second": 3.151,
      "eval_steps_per_second": 1.576,
      "step": 1
    },
    {
      "epoch": 3.904057780055145e-05,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 5.856086670082717e-05,
      "grad_norm": NaN,
      "learning_rate": 0.00019978589232386035,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 7.80811556011029e-05,
      "grad_norm": NaN,
      "learning_rate": 0.00019914448613738106,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 9.760144450137862e-05,
      "grad_norm": NaN,
      "learning_rate": 0.00019807852804032305,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.00011712173340165434,
      "grad_norm": NaN,
      "learning_rate": 0.00019659258262890683,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.00013664202230193008,
      "grad_norm": NaN,
      "learning_rate": 0.0001946930129495106,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.0001561623112022058,
      "grad_norm": NaN,
      "learning_rate": 0.0001923879532511287,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.00017568260010248152,
      "grad_norm": NaN,
      "learning_rate": 0.00018968727415326884,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.00019520288900275724,
      "grad_norm": NaN,
      "learning_rate": 0.00018660254037844388,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.00021472317790303296,
      "grad_norm": NaN,
      "learning_rate": 0.00018314696123025454,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.00023424346680330868,
      "grad_norm": NaN,
      "learning_rate": 0.00017933533402912354,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.0002537637557035844,
      "grad_norm": NaN,
      "learning_rate": 0.00017518398074789775,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.00027328404460386015,
      "grad_norm": NaN,
      "learning_rate": 0.00017071067811865476,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.00029280433350413584,
      "grad_norm": NaN,
      "learning_rate": 0.00016593458151000688,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.0003123246224044116,
      "grad_norm": NaN,
      "learning_rate": 0.00016087614290087208,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.0003318449113046873,
      "grad_norm": NaN,
      "learning_rate": 0.00015555702330196023,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.00035136520020496304,
      "grad_norm": NaN,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.0003708854891052388,
      "grad_norm": NaN,
      "learning_rate": 0.00014422886902190014,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 0.0003904057780055145,
      "grad_norm": NaN,
      "learning_rate": 0.000138268343236509,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.0004099260669057902,
      "grad_norm": NaN,
      "learning_rate": 0.00013214394653031616,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.0004294463558060659,
      "grad_norm": NaN,
      "learning_rate": 0.00012588190451025207,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 0.00044896664470634167,
      "grad_norm": NaN,
      "learning_rate": 0.00011950903220161285,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 0.00046848693360661736,
      "grad_norm": NaN,
      "learning_rate": 0.00011305261922200519,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.0004880072225068931,
      "grad_norm": NaN,
      "learning_rate": 0.00010654031292301432,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.0004880072225068931,
      "eval_loss": NaN,
      "eval_runtime": 6847.4085,
      "eval_samples_per_second": 3.15,
      "eval_steps_per_second": 1.575,
      "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": 3.5508080351379456e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}