last-checkpoint/trainer_state.json

{
  "best_metric": 2.538435697555542,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.02577873254564984,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0008592910848549946,
      "eval_loss": 2.608729124069214,
      "eval_runtime": 27.1947,
      "eval_samples_per_second": 18.018,
      "eval_steps_per_second": 9.009,
      "step": 1
    },
    {
      "epoch": 0.0025778732545649837,
      "grad_norm": 2.7738373279571533,
      "learning_rate": 6e-05,
      "loss": 10.5388,
      "step": 3
    },
    {
      "epoch": 0.004296455424274973,
      "eval_loss": 2.5962843894958496,
      "eval_runtime": 27.2984,
      "eval_samples_per_second": 17.95,
      "eval_steps_per_second": 8.975,
      "step": 5
    },
    {
      "epoch": 0.0051557465091299675,
      "grad_norm": 3.2017478942871094,
      "learning_rate": 0.00012,
      "loss": 11.2671,
      "step": 6
    },
    {
      "epoch": 0.007733619763694952,
      "grad_norm": 3.3286068439483643,
      "learning_rate": 0.00018,
      "loss": 10.956,
      "step": 9
    },
    {
      "epoch": 0.008592910848549946,
      "eval_loss": 2.5706849098205566,
      "eval_runtime": 27.3509,
      "eval_samples_per_second": 17.915,
      "eval_steps_per_second": 8.958,
      "step": 10
    },
    {
      "epoch": 0.010311493018259935,
      "grad_norm": 3.4153363704681396,
      "learning_rate": 0.00019510565162951537,
      "loss": 10.8795,
      "step": 12
    },
    {
      "epoch": 0.01288936627282492,
      "grad_norm": 3.5653088092803955,
      "learning_rate": 0.00017071067811865476,
      "loss": 10.4435,
      "step": 15
    },
    {
      "epoch": 0.01288936627282492,
      "eval_loss": 2.552823066711426,
      "eval_runtime": 27.2962,
      "eval_samples_per_second": 17.951,
      "eval_steps_per_second": 8.976,
      "step": 15
    },
    {
      "epoch": 0.015467239527389903,
      "grad_norm": 2.5528149604797363,
      "learning_rate": 0.00013090169943749476,
      "loss": 10.3373,
      "step": 18
    },
    {
      "epoch": 0.017185821697099892,
      "eval_loss": 2.5436248779296875,
      "eval_runtime": 27.2804,
      "eval_samples_per_second": 17.962,
      "eval_steps_per_second": 8.981,
      "step": 20
    },
    {
      "epoch": 0.01804511278195489,
      "grad_norm": 1.9827948808670044,
      "learning_rate": 8.435655349597689e-05,
      "loss": 10.1527,
      "step": 21
    },
    {
      "epoch": 0.02062298603651987,
      "grad_norm": 3.5701653957366943,
      "learning_rate": 4.12214747707527e-05,
      "loss": 10.3196,
      "step": 24
    },
    {
      "epoch": 0.021482277121374866,
      "eval_loss": 2.539433240890503,
      "eval_runtime": 27.4227,
      "eval_samples_per_second": 17.868,
      "eval_steps_per_second": 8.934,
      "step": 25
    },
    {
      "epoch": 0.023200859291084855,
      "grad_norm": 3.908367395401001,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 10.589,
      "step": 27
    },
    {
      "epoch": 0.02577873254564984,
      "grad_norm": 2.505573272705078,
      "learning_rate": 0.0,
      "loss": 10.4872,
      "step": 30
    },
    {
      "epoch": 0.02577873254564984,
      "eval_loss": 2.538435697555542,
      "eval_runtime": 27.4559,
      "eval_samples_per_second": 17.847,
      "eval_steps_per_second": 8.923,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2839773236428800.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}