last-checkpoint/trainer_state.json

{
  "best_metric": 0.26675283908843994,
  "best_model_checkpoint": "miner_id_24/checkpoint-500",
  "epoch": 0.24394706348722328,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00048789412697444653,
      "eval_loss": 0.41620752215385437,
      "eval_runtime": 378.5304,
      "eval_samples_per_second": 9.122,
      "eval_steps_per_second": 2.283,
      "step": 1
    },
    {
      "epoch": 0.024394706348722327,
      "grad_norm": 0.791959822177887,
      "learning_rate": 0.000109,
      "loss": 0.3028,
      "step": 50
    },
    {
      "epoch": 0.048789412697444655,
      "grad_norm": 0.7407991886138916,
      "learning_rate": 0.000218,
      "loss": 0.2629,
      "step": 100
    },
    {
      "epoch": 0.07318411904616698,
      "grad_norm": 0.8837946653366089,
      "learning_rate": 0.00020970286904373027,
      "loss": 0.2861,
      "step": 150
    },
    {
      "epoch": 0.09757882539488931,
      "grad_norm": 0.6867163181304932,
      "learning_rate": 0.00018607463914933369,
      "loss": 0.27,
      "step": 200
    },
    {
      "epoch": 0.12197353174361164,
      "grad_norm": 0.7695136070251465,
      "learning_rate": 0.0001507124941277948,
      "loss": 0.2802,
      "step": 250
    },
    {
      "epoch": 0.14636823809233396,
      "grad_norm": 0.796603798866272,
      "learning_rate": 0.000109,
      "loss": 0.2849,
      "step": 300
    },
    {
      "epoch": 0.1707629444410563,
      "grad_norm": 0.6176795363426208,
      "learning_rate": 6.728750587220522e-05,
      "loss": 0.2807,
      "step": 350
    },
    {
      "epoch": 0.19515765078977862,
      "grad_norm": 0.6259704828262329,
      "learning_rate": 3.192536085066633e-05,
      "loss": 0.2805,
      "step": 400
    },
    {
      "epoch": 0.21955235713850094,
      "grad_norm": 0.8086729049682617,
      "learning_rate": 8.297130956269746e-06,
      "loss": 0.2778,
      "step": 450
    },
    {
      "epoch": 0.24394706348722328,
      "grad_norm": 0.6864873170852661,
      "learning_rate": 0.0,
      "loss": 0.2724,
      "step": 500
    },
    {
      "epoch": 0.24394706348722328,
      "eval_loss": 0.26675283908843994,
      "eval_runtime": 378.5603,
      "eval_samples_per_second": 9.121,
      "eval_steps_per_second": 2.282,
      "step": 500
    }
  ],
  "logging_steps": 50,
  "max_steps": 500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 7.54269674274816e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}