last-checkpoint/trainer_state.json

{
  "best_metric": 0.553749680519104,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.020796506186960592,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0002079650618696059,
      "eval_loss": 0.9533683061599731,
      "eval_runtime": 156.6179,
      "eval_samples_per_second": 3.237,
      "eval_steps_per_second": 0.811,
      "step": 1
    },
    {
      "epoch": 0.002079650618696059,
      "grad_norm": 3.18047833442688,
      "learning_rate": 4.36e-05,
      "loss": 0.8342,
      "step": 10
    },
    {
      "epoch": 0.004159301237392118,
      "grad_norm": 2.9091711044311523,
      "learning_rate": 8.72e-05,
      "loss": 0.5367,
      "step": 20
    },
    {
      "epoch": 0.006238951856088177,
      "grad_norm": 12.142705917358398,
      "learning_rate": 0.0001308,
      "loss": 0.5186,
      "step": 30
    },
    {
      "epoch": 0.008318602474784236,
      "grad_norm": 1.364218831062317,
      "learning_rate": 0.0001744,
      "loss": 0.5148,
      "step": 40
    },
    {
      "epoch": 0.010398253093480296,
      "grad_norm": 2.0976734161376953,
      "learning_rate": 0.000218,
      "loss": 0.5504,
      "step": 50
    },
    {
      "epoch": 0.010398253093480296,
      "eval_loss": 0.5830835103988647,
      "eval_runtime": 80.9255,
      "eval_samples_per_second": 6.265,
      "eval_steps_per_second": 1.569,
      "step": 50
    },
    {
      "epoch": 0.012477903712176355,
      "grad_norm": 1.4801353216171265,
      "learning_rate": 0.00021773448147832086,
      "loss": 0.5768,
      "step": 60
    },
    {
      "epoch": 0.014557554330872413,
      "grad_norm": 1.2638306617736816,
      "learning_rate": 0.0002169392194928312,
      "loss": 0.585,
      "step": 70
    },
    {
      "epoch": 0.01663720494956847,
      "grad_norm": 1.3111450672149658,
      "learning_rate": 0.00021561808847998484,
      "loss": 0.6144,
      "step": 80
    },
    {
      "epoch": 0.01871685556826453,
      "grad_norm": 1.4548810720443726,
      "learning_rate": 0.00021377752485727676,
      "loss": 0.5459,
      "step": 90
    },
    {
      "epoch": 0.020796506186960592,
      "grad_norm": 1.1708745956420898,
      "learning_rate": 0.00021142649566566402,
      "loss": 0.6452,
      "step": 100
    },
    {
      "epoch": 0.020796506186960592,
      "eval_loss": 0.553749680519104,
      "eval_runtime": 80.7517,
      "eval_samples_per_second": 6.279,
      "eval_steps_per_second": 1.573,
      "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": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.3601784912150528e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}