last-checkpoint/trainer_state.json

{
  "best_metric": 0.972604513168335,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.0021247211303516414,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 7.082403767838805e-05,
      "eval_loss": 1.2678641080856323,
      "eval_runtime": 751.4125,
      "eval_samples_per_second": 7.913,
      "eval_steps_per_second": 3.957,
      "step": 1
    },
    {
      "epoch": 0.00021247211303516414,
      "grad_norm": 0.4345724880695343,
      "learning_rate": 0.00012,
      "loss": 1.226,
      "step": 3
    },
    {
      "epoch": 0.0003541201883919402,
      "eval_loss": 1.2024271488189697,
      "eval_runtime": 757.0571,
      "eval_samples_per_second": 7.854,
      "eval_steps_per_second": 3.927,
      "step": 5
    },
    {
      "epoch": 0.00042494422607032827,
      "grad_norm": 0.31882792711257935,
      "learning_rate": 0.0001992114701314478,
      "loss": 1.134,
      "step": 6
    },
    {
      "epoch": 0.0006374163391054924,
      "grad_norm": 0.4549216032028198,
      "learning_rate": 0.00018763066800438636,
      "loss": 0.985,
      "step": 9
    },
    {
      "epoch": 0.0007082403767838804,
      "eval_loss": 1.0496538877487183,
      "eval_runtime": 755.8615,
      "eval_samples_per_second": 7.867,
      "eval_steps_per_second": 3.933,
      "step": 10
    },
    {
      "epoch": 0.0008498884521406565,
      "grad_norm": 0.4180082380771637,
      "learning_rate": 0.000163742398974869,
      "loss": 0.9673,
      "step": 12
    },
    {
      "epoch": 0.0010623605651758207,
      "grad_norm": 0.5116729736328125,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.9065,
      "step": 15
    },
    {
      "epoch": 0.0010623605651758207,
      "eval_loss": 1.0059510469436646,
      "eval_runtime": 751.9391,
      "eval_samples_per_second": 7.908,
      "eval_steps_per_second": 3.954,
      "step": 15
    },
    {
      "epoch": 0.0012748326782109848,
      "grad_norm": 0.5504330992698669,
      "learning_rate": 9.372094804706867e-05,
      "loss": 0.8902,
      "step": 18
    },
    {
      "epoch": 0.0014164807535677608,
      "eval_loss": 0.9824416041374207,
      "eval_runtime": 754.227,
      "eval_samples_per_second": 7.884,
      "eval_steps_per_second": 3.942,
      "step": 20
    },
    {
      "epoch": 0.001487304791246149,
      "grad_norm": 0.5774909257888794,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 0.8711,
      "step": 21
    },
    {
      "epoch": 0.001699776904281313,
      "grad_norm": 0.4347454905509949,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 0.917,
      "step": 24
    },
    {
      "epoch": 0.0017706009419597012,
      "eval_loss": 0.9743475914001465,
      "eval_runtime": 751.6939,
      "eval_samples_per_second": 7.91,
      "eval_steps_per_second": 3.955,
      "step": 25
    },
    {
      "epoch": 0.0019122490173164772,
      "grad_norm": 0.4491797387599945,
      "learning_rate": 7.022351411174866e-06,
      "loss": 0.9083,
      "step": 27
    },
    {
      "epoch": 0.0021247211303516414,
      "grad_norm": 0.6388364434242249,
      "learning_rate": 0.0,
      "loss": 1.058,
      "step": 30
    },
    {
      "epoch": 0.0021247211303516414,
      "eval_loss": 0.972604513168335,
      "eval_runtime": 752.3285,
      "eval_samples_per_second": 7.903,
      "eval_steps_per_second": 3.952,
      "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": 1.049486910554112e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}