last-checkpoint/trainer_state.json

{
  "best_metric": 1.2856680154800415,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.06983240223463687,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006983240223463687,
      "eval_loss": 1.370945930480957,
      "eval_runtime": 51.907,
      "eval_samples_per_second": 11.617,
      "eval_steps_per_second": 2.909,
      "step": 1
    },
    {
      "epoch": 0.006983240223463687,
      "grad_norm": 0.8086255788803101,
      "learning_rate": 4.34e-05,
      "loss": 1.074,
      "step": 10
    },
    {
      "epoch": 0.013966480446927373,
      "grad_norm": 0.5126949548721313,
      "learning_rate": 8.68e-05,
      "loss": 0.9041,
      "step": 20
    },
    {
      "epoch": 0.02094972067039106,
      "grad_norm": 0.6224434971809387,
      "learning_rate": 0.0001302,
      "loss": 0.9133,
      "step": 30
    },
    {
      "epoch": 0.027932960893854747,
      "grad_norm": 0.596337616443634,
      "learning_rate": 0.0001736,
      "loss": 0.8771,
      "step": 40
    },
    {
      "epoch": 0.034916201117318434,
      "grad_norm": 1.162047266960144,
      "learning_rate": 0.000217,
      "loss": 2.273,
      "step": 50
    },
    {
      "epoch": 0.034916201117318434,
      "eval_loss": 1.2856680154800415,
      "eval_runtime": 51.8319,
      "eval_samples_per_second": 11.634,
      "eval_steps_per_second": 2.913,
      "step": 50
    },
    {
      "epoch": 0.04189944134078212,
      "grad_norm": 0.47395944595336914,
      "learning_rate": 0.00021673569945319091,
      "loss": 0.9326,
      "step": 60
    },
    {
      "epoch": 0.04888268156424581,
      "grad_norm": 0.45159703493118286,
      "learning_rate": 0.00021594408545846038,
      "loss": 0.864,
      "step": 70
    },
    {
      "epoch": 0.055865921787709494,
      "grad_norm": 0.48672589659690857,
      "learning_rate": 0.0002146290146796179,
      "loss": 0.9053,
      "step": 80
    },
    {
      "epoch": 0.06284916201117319,
      "grad_norm": 0.6035557389259338,
      "learning_rate": 0.0002127968940093076,
      "loss": 0.9917,
      "step": 90
    },
    {
      "epoch": 0.06983240223463687,
      "grad_norm": 1.352277398109436,
      "learning_rate": 0.00021045664935527106,
      "loss": 2.3177,
      "step": 100
    },
    {
      "epoch": 0.06983240223463687,
      "eval_loss": 1.2862142324447632,
      "eval_runtime": 51.6109,
      "eval_samples_per_second": 11.684,
      "eval_steps_per_second": 2.926,
      "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": 2.817116957835264e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}