last-checkpoint/trainer_state.json

{
  "best_metric": 11.5,
  "best_model_checkpoint": "miner_id_24/checkpoint-500",
  "epoch": 0.08467579754016809,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00016935159508033618,
      "eval_loss": 11.5,
      "eval_runtime": 77.1184,
      "eval_samples_per_second": 128.958,
      "eval_steps_per_second": 32.249,
      "step": 1
    },
    {
      "epoch": 0.008467579754016808,
      "grad_norm": 7.961583469295874e-05,
      "learning_rate": 0.0001055,
      "loss": 92.0,
      "step": 50
    },
    {
      "epoch": 0.016935159508033617,
      "grad_norm": 0.00048469542525708675,
      "learning_rate": 0.000211,
      "loss": 92.0,
      "step": 100
    },
    {
      "epoch": 0.025402739262050424,
      "grad_norm": 0.001294212881475687,
      "learning_rate": 0.00020296929067994076,
      "loss": 92.0,
      "step": 150
    },
    {
      "epoch": 0.033870319016067234,
      "grad_norm": 0.0014950740151107311,
      "learning_rate": 0.00018009976541518075,
      "loss": 92.0,
      "step": 200
    },
    {
      "epoch": 0.042337898770084044,
      "grad_norm": 0.0012079132720828056,
      "learning_rate": 0.000145873102114517,
      "loss": 92.0,
      "step": 250
    },
    {
      "epoch": 0.05080547852410085,
      "grad_norm": 0.0019013193668797612,
      "learning_rate": 0.0001055,
      "loss": 92.0,
      "step": 300
    },
    {
      "epoch": 0.05927305827811766,
      "grad_norm": 0.0024865507148206234,
      "learning_rate": 6.512689788548303e-05,
      "loss": 92.0,
      "step": 350
    },
    {
      "epoch": 0.06774063803213447,
      "grad_norm": 0.0009215000318363309,
      "learning_rate": 3.090023458481924e-05,
      "loss": 92.0,
      "step": 400
    },
    {
      "epoch": 0.07620821778615128,
      "grad_norm": 0.0019659511744976044,
      "learning_rate": 8.03070932005925e-06,
      "loss": 92.0,
      "step": 450
    },
    {
      "epoch": 0.08467579754016809,
      "grad_norm": 0.0012138639576733112,
      "learning_rate": 0.0,
      "loss": 92.0,
      "step": 500
    },
    {
      "epoch": 0.08467579754016809,
      "eval_loss": 11.5,
      "eval_runtime": 72.5604,
      "eval_samples_per_second": 137.058,
      "eval_steps_per_second": 34.275,
      "step": 500
    }
  ],
  "logging_steps": 50,
  "max_steps": 500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "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": 83511508008960.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}