last-checkpoint/trainer_state.json

{
  "best_metric": 1.566378116607666,
  "best_model_checkpoint": "miner_id_24/checkpoint-10",
  "epoch": 0.00018862852912188705,
  "eval_steps": 5,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.8862852912188704e-05,
      "grad_norm": 4.201507091522217,
      "learning_rate": 2e-05,
      "loss": 9.2904,
      "step": 1
    },
    {
      "epoch": 1.8862852912188704e-05,
      "eval_loss": 2.357879400253296,
      "eval_runtime": 3343.2684,
      "eval_samples_per_second": 6.677,
      "eval_steps_per_second": 3.338,
      "step": 1
    },
    {
      "epoch": 3.772570582437741e-05,
      "grad_norm": 4.2625226974487305,
      "learning_rate": 4e-05,
      "loss": 8.986,
      "step": 2
    },
    {
      "epoch": 5.658855873656611e-05,
      "grad_norm": 4.74202823638916,
      "learning_rate": 6e-05,
      "loss": 11.7277,
      "step": 3
    },
    {
      "epoch": 7.545141164875482e-05,
      "grad_norm": 4.6647796630859375,
      "learning_rate": 8e-05,
      "loss": 10.482,
      "step": 4
    },
    {
      "epoch": 9.431426456094352e-05,
      "grad_norm": 5.054591178894043,
      "learning_rate": 0.0001,
      "loss": 8.7356,
      "step": 5
    },
    {
      "epoch": 9.431426456094352e-05,
      "eval_loss": 2.2210323810577393,
      "eval_runtime": 3335.248,
      "eval_samples_per_second": 6.693,
      "eval_steps_per_second": 3.346,
      "step": 5
    },
    {
      "epoch": 0.00011317711747313222,
      "grad_norm": 5.291041851043701,
      "learning_rate": 0.00012,
      "loss": 9.9723,
      "step": 6
    },
    {
      "epoch": 0.00013203997038532093,
      "grad_norm": 6.159406661987305,
      "learning_rate": 0.00014,
      "loss": 8.599,
      "step": 7
    },
    {
      "epoch": 0.00015090282329750963,
      "grad_norm": 6.752080917358398,
      "learning_rate": 0.00016,
      "loss": 8.2687,
      "step": 8
    },
    {
      "epoch": 0.00016976567620969834,
      "grad_norm": 6.00890588760376,
      "learning_rate": 0.00018,
      "loss": 8.3068,
      "step": 9
    },
    {
      "epoch": 0.00018862852912188705,
      "grad_norm": 5.494807243347168,
      "learning_rate": 0.0002,
      "loss": 7.4516,
      "step": 10
    },
    {
      "epoch": 0.00018862852912188705,
      "eval_loss": 1.566378116607666,
      "eval_runtime": 3362.0639,
      "eval_samples_per_second": 6.639,
      "eval_steps_per_second": 3.32,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 25,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "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": 1656448963203072.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}