last-checkpoint/trainer_state.json

{
  "best_metric": 1.2860125303268433,
  "best_model_checkpoint": "miner_id_24/checkpoint-10",
  "epoch": 0.00038642116042274477,
  "eval_steps": 5,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.864211604227448e-05,
      "grad_norm": 12.773677825927734,
      "learning_rate": 2e-05,
      "loss": 20.5874,
      "step": 1
    },
    {
      "epoch": 3.864211604227448e-05,
      "eval_loss": 2.319946527481079,
      "eval_runtime": 1539.8566,
      "eval_samples_per_second": 7.077,
      "eval_steps_per_second": 3.539,
      "step": 1
    },
    {
      "epoch": 7.728423208454895e-05,
      "grad_norm": 18.113393783569336,
      "learning_rate": 4e-05,
      "loss": 22.2643,
      "step": 2
    },
    {
      "epoch": 0.00011592634812682343,
      "grad_norm": 13.806958198547363,
      "learning_rate": 6e-05,
      "loss": 20.4745,
      "step": 3
    },
    {
      "epoch": 0.0001545684641690979,
      "grad_norm": 11.016865730285645,
      "learning_rate": 8e-05,
      "loss": 16.2397,
      "step": 4
    },
    {
      "epoch": 0.00019321058021137238,
      "grad_norm": 16.108251571655273,
      "learning_rate": 0.0001,
      "loss": 23.7669,
      "step": 5
    },
    {
      "epoch": 0.00019321058021137238,
      "eval_loss": 2.2090024948120117,
      "eval_runtime": 1568.1097,
      "eval_samples_per_second": 6.949,
      "eval_steps_per_second": 3.475,
      "step": 5
    },
    {
      "epoch": 0.00023185269625364686,
      "grad_norm": 15.758869171142578,
      "learning_rate": 0.00012,
      "loss": 17.7131,
      "step": 6
    },
    {
      "epoch": 0.0002704948122959213,
      "grad_norm": 12.927544593811035,
      "learning_rate": 0.00014,
      "loss": 14.3283,
      "step": 7
    },
    {
      "epoch": 0.0003091369283381958,
      "grad_norm": 19.0375919342041,
      "learning_rate": 0.00016,
      "loss": 19.2132,
      "step": 8
    },
    {
      "epoch": 0.00034777904438047026,
      "grad_norm": 23.053707122802734,
      "learning_rate": 0.00018,
      "loss": 19.7064,
      "step": 9
    },
    {
      "epoch": 0.00038642116042274477,
      "grad_norm": 21.222137451171875,
      "learning_rate": 0.0002,
      "loss": 14.0825,
      "step": 10
    },
    {
      "epoch": 0.00038642116042274477,
      "eval_loss": 1.2860125303268433,
      "eval_runtime": 1546.3074,
      "eval_samples_per_second": 7.047,
      "eval_steps_per_second": 3.524,
      "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": 1119139626221568.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}