last-checkpoint/trainer_state.json

{
  "best_metric": 1.273123025894165,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.006518267444513249,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 6.518267444513249e-05,
      "eval_loss": 2.850663900375366,
      "eval_runtime": 443.5942,
      "eval_samples_per_second": 14.563,
      "eval_steps_per_second": 3.641,
      "step": 1
    },
    {
      "epoch": 0.0006518267444513248,
      "grad_norm": 3.971789598464966,
      "learning_rate": 4.16e-05,
      "loss": 2.0815,
      "step": 10
    },
    {
      "epoch": 0.0013036534889026496,
      "grad_norm": 2.8578591346740723,
      "learning_rate": 8.32e-05,
      "loss": 1.8557,
      "step": 20
    },
    {
      "epoch": 0.0019554802333539745,
      "grad_norm": 3.0689802169799805,
      "learning_rate": 0.0001248,
      "loss": 1.5229,
      "step": 30
    },
    {
      "epoch": 0.002607306977805299,
      "grad_norm": 4.3151397705078125,
      "learning_rate": 0.0001664,
      "loss": 1.3099,
      "step": 40
    },
    {
      "epoch": 0.0032591337222566243,
      "grad_norm": 4.729147434234619,
      "learning_rate": 0.000208,
      "loss": 1.6873,
      "step": 50
    },
    {
      "epoch": 0.0032591337222566243,
      "eval_loss": 1.273123025894165,
      "eval_runtime": 445.0677,
      "eval_samples_per_second": 14.515,
      "eval_steps_per_second": 3.629,
      "step": 50
    },
    {
      "epoch": 0.003910960466707949,
      "grad_norm": 2.3496737480163574,
      "learning_rate": 0.0002077466612270217,
      "loss": 1.0568,
      "step": 60
    },
    {
      "epoch": 0.004562787211159274,
      "grad_norm": 2.499488353729248,
      "learning_rate": 0.0002069878791491233,
      "loss": 1.1359,
      "step": 70
    },
    {
      "epoch": 0.005214613955610598,
      "grad_norm": 3.1299209594726562,
      "learning_rate": 0.00020572735047631578,
      "loss": 1.2264,
      "step": 80
    },
    {
      "epoch": 0.005866440700061924,
      "grad_norm": 3.3837058544158936,
      "learning_rate": 0.00020397121637758515,
      "loss": 1.2004,
      "step": 90
    },
    {
      "epoch": 0.006518267444513249,
      "grad_norm": 2.973175287246704,
      "learning_rate": 0.00020172803256173445,
      "loss": 1.545,
      "step": 100
    },
    {
      "epoch": 0.006518267444513249,
      "eval_loss": 1.275679111480713,
      "eval_runtime": 446.3022,
      "eval_samples_per_second": 14.474,
      "eval_steps_per_second": 3.619,
      "step": 100
    }
  ],
  "logging_steps": 10,
  "max_steps": 500,
  "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": 1
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.0633874937675776e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}