last-checkpoint/trainer_state.json

{
  "best_metric": 0.6163225173950195,
  "best_model_checkpoint": "miner_id_24/checkpoint-150",
  "epoch": 0.05687203791469194,
  "eval_steps": 150,
  "global_step": 150,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0003791469194312796,
      "eval_loss": 1.7795168161392212,
      "eval_runtime": 209.8549,
      "eval_samples_per_second": 21.167,
      "eval_steps_per_second": 5.294,
      "step": 1
    },
    {
      "epoch": 0.0037914691943127963,
      "grad_norm": 2.3918707370758057,
      "learning_rate": 2e-05,
      "loss": 2.1878,
      "step": 10
    },
    {
      "epoch": 0.007582938388625593,
      "grad_norm": 1.775721788406372,
      "learning_rate": 4e-05,
      "loss": 1.257,
      "step": 20
    },
    {
      "epoch": 0.011374407582938388,
      "grad_norm": 1.3155328035354614,
      "learning_rate": 6e-05,
      "loss": 0.7683,
      "step": 30
    },
    {
      "epoch": 0.015165876777251185,
      "grad_norm": 1.3514695167541504,
      "learning_rate": 8e-05,
      "loss": 0.5549,
      "step": 40
    },
    {
      "epoch": 0.018957345971563982,
      "grad_norm": 1.1452535390853882,
      "learning_rate": 0.0001,
      "loss": 0.3957,
      "step": 50
    },
    {
      "epoch": 0.022748815165876776,
      "grad_norm": 1.4056144952774048,
      "learning_rate": 9.999631611658893e-05,
      "loss": 1.3166,
      "step": 60
    },
    {
      "epoch": 0.026540284360189573,
      "grad_norm": 1.0476895570755005,
      "learning_rate": 9.998526500919558e-05,
      "loss": 0.6856,
      "step": 70
    },
    {
      "epoch": 0.03033175355450237,
      "grad_norm": 1.057721495628357,
      "learning_rate": 9.996684830625961e-05,
      "loss": 0.5876,
      "step": 80
    },
    {
      "epoch": 0.034123222748815164,
      "grad_norm": 0.8883450627326965,
      "learning_rate": 9.99410687215805e-05,
      "loss": 0.5092,
      "step": 90
    },
    {
      "epoch": 0.037914691943127965,
      "grad_norm": 1.0792176723480225,
      "learning_rate": 9.990793005391757e-05,
      "loss": 0.3727,
      "step": 100
    },
    {
      "epoch": 0.04170616113744076,
      "grad_norm": 0.9899026155471802,
      "learning_rate": 9.986743718643037e-05,
      "loss": 1.0962,
      "step": 110
    },
    {
      "epoch": 0.04549763033175355,
      "grad_norm": 0.9852607250213623,
      "learning_rate": 9.981959608595904e-05,
      "loss": 0.6074,
      "step": 120
    },
    {
      "epoch": 0.04928909952606635,
      "grad_norm": 0.8935758471488953,
      "learning_rate": 9.976441380214499e-05,
      "loss": 0.5443,
      "step": 130
    },
    {
      "epoch": 0.05308056872037915,
      "grad_norm": 0.8601885437965393,
      "learning_rate": 9.970189846639224e-05,
      "loss": 0.4588,
      "step": 140
    },
    {
      "epoch": 0.05687203791469194,
      "grad_norm": 0.8278557658195496,
      "learning_rate": 9.963205929066912e-05,
      "loss": 0.3571,
      "step": 150
    },
    {
      "epoch": 0.05687203791469194,
      "eval_loss": 0.6163225173950195,
      "eval_runtime": 211.3771,
      "eval_samples_per_second": 21.015,
      "eval_steps_per_second": 5.256,
      "step": 150
    }
  ],
  "logging_steps": 10,
  "max_steps": 2638,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 150,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 2,
        "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": 1.3274919492963533e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}