last-checkpoint/trainer_state.json

{
  "best_metric": 3.036409378051758,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 7.982018109602686e-05,
  "eval_steps": 5,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.1928072438410748e-06,
      "eval_loss": 3.5490143299102783,
      "eval_runtime": 1455.6339,
      "eval_samples_per_second": 22.649,
      "eval_steps_per_second": 11.325,
      "step": 1
    },
    {
      "epoch": 9.578421731523224e-06,
      "grad_norm": 1.1333973407745361,
      "learning_rate": 6e-05,
      "loss": 3.5516,
      "step": 3
    },
    {
      "epoch": 1.5964036219205374e-05,
      "eval_loss": 3.524850606918335,
      "eval_runtime": 947.5996,
      "eval_samples_per_second": 34.792,
      "eval_steps_per_second": 17.397,
      "step": 5
    },
    {
      "epoch": 1.9156843463046448e-05,
      "grad_norm": 1.2352288961410522,
      "learning_rate": 0.00012,
      "loss": 3.7464,
      "step": 6
    },
    {
      "epoch": 2.8735265194569675e-05,
      "grad_norm": 1.2148215770721436,
      "learning_rate": 0.00018,
      "loss": 3.4888,
      "step": 9
    },
    {
      "epoch": 3.192807243841075e-05,
      "eval_loss": 3.346342086791992,
      "eval_runtime": 951.8702,
      "eval_samples_per_second": 34.636,
      "eval_steps_per_second": 17.319,
      "step": 10
    },
    {
      "epoch": 3.8313686926092896e-05,
      "grad_norm": 1.2107754945755005,
      "learning_rate": 0.0001913545457642601,
      "loss": 3.2029,
      "step": 12
    },
    {
      "epoch": 4.789210865761612e-05,
      "grad_norm": 1.50534188747406,
      "learning_rate": 0.00015000000000000001,
      "loss": 3.1148,
      "step": 15
    },
    {
      "epoch": 4.789210865761612e-05,
      "eval_loss": 3.137223243713379,
      "eval_runtime": 933.6085,
      "eval_samples_per_second": 35.314,
      "eval_steps_per_second": 17.657,
      "step": 15
    },
    {
      "epoch": 5.747053038913935e-05,
      "grad_norm": 1.7882508039474487,
      "learning_rate": 8.954715367323468e-05,
      "loss": 3.3444,
      "step": 18
    },
    {
      "epoch": 6.38561448768215e-05,
      "eval_loss": 3.055253505706787,
      "eval_runtime": 940.5098,
      "eval_samples_per_second": 35.054,
      "eval_steps_per_second": 17.528,
      "step": 20
    },
    {
      "epoch": 6.704895212066257e-05,
      "grad_norm": 1.5259191989898682,
      "learning_rate": 3.308693936411421e-05,
      "loss": 3.1122,
      "step": 21
    },
    {
      "epoch": 7.662737385218579e-05,
      "grad_norm": 1.561505913734436,
      "learning_rate": 2.1852399266194314e-06,
      "loss": 2.9817,
      "step": 24
    },
    {
      "epoch": 7.982018109602686e-05,
      "eval_loss": 3.036409378051758,
      "eval_runtime": 937.4505,
      "eval_samples_per_second": 35.169,
      "eval_steps_per_second": 17.585,
      "step": 25
    }
  ],
  "logging_steps": 3,
  "max_steps": 25,
  "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": 43386745651200.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}