last-checkpoint/trainer_state.json

{
  "best_metric": 0.32411646842956543,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.08176614881439084,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0008176614881439084,
      "eval_loss": 0.5527377724647522,
      "eval_runtime": 124.6782,
      "eval_samples_per_second": 4.131,
      "eval_steps_per_second": 1.035,
      "step": 1
    },
    {
      "epoch": 0.008176614881439084,
      "grad_norm": 0.32495826482772827,
      "learning_rate": 5.05e-06,
      "loss": 0.5089,
      "step": 10
    },
    {
      "epoch": 0.016353229762878167,
      "grad_norm": 0.8611395955085754,
      "learning_rate": 1.01e-05,
      "loss": 0.6189,
      "step": 20
    },
    {
      "epoch": 0.024529844644317254,
      "grad_norm": 0.6982009410858154,
      "learning_rate": 9.323076923076924e-06,
      "loss": 0.8332,
      "step": 30
    },
    {
      "epoch": 0.032706459525756335,
      "grad_norm": 0.3120550513267517,
      "learning_rate": 8.546153846153847e-06,
      "loss": 0.3726,
      "step": 40
    },
    {
      "epoch": 0.04088307440719542,
      "grad_norm": 0.19447167217731476,
      "learning_rate": 7.76923076923077e-06,
      "loss": 0.0479,
      "step": 50
    },
    {
      "epoch": 0.04088307440719542,
      "eval_loss": 0.3859279751777649,
      "eval_runtime": 124.752,
      "eval_samples_per_second": 4.128,
      "eval_steps_per_second": 1.034,
      "step": 50
    },
    {
      "epoch": 0.04905968928863451,
      "grad_norm": 0.28594130277633667,
      "learning_rate": 6.992307692307692e-06,
      "loss": 0.4319,
      "step": 60
    },
    {
      "epoch": 0.05723630417007359,
      "grad_norm": 0.6387773156166077,
      "learning_rate": 6.215384615384615e-06,
      "loss": 0.4787,
      "step": 70
    },
    {
      "epoch": 0.06541291905151267,
      "grad_norm": 0.30498838424682617,
      "learning_rate": 5.438461538461538e-06,
      "loss": 0.5047,
      "step": 80
    },
    {
      "epoch": 0.07358953393295176,
      "grad_norm": 0.15410414338111877,
      "learning_rate": 4.661538461538462e-06,
      "loss": 0.1164,
      "step": 90
    },
    {
      "epoch": 0.08176614881439084,
      "grad_norm": 0.12575368583202362,
      "learning_rate": 3.884615384615385e-06,
      "loss": 0.0136,
      "step": 100
    },
    {
      "epoch": 0.08176614881439084,
      "eval_loss": 0.32411646842956543,
      "eval_runtime": 124.5506,
      "eval_samples_per_second": 4.135,
      "eval_steps_per_second": 1.036,
      "step": 100
    }
  ],
  "logging_steps": 10,
  "max_steps": 150,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.247192480219136e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}