last-checkpoint/trainer_state.json

{
  "best_metric": 3.5841777324676514,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.014904980747733202,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0004968326915911067,
      "eval_loss": 5.553887844085693,
      "eval_runtime": 77.054,
      "eval_samples_per_second": 11.005,
      "eval_steps_per_second": 5.503,
      "step": 1
    },
    {
      "epoch": 0.0014904980747733202,
      "grad_norm": 17.217065811157227,
      "learning_rate": 6e-05,
      "loss": 21.1239,
      "step": 3
    },
    {
      "epoch": 0.0024841634579555335,
      "eval_loss": 5.122373104095459,
      "eval_runtime": 77.8988,
      "eval_samples_per_second": 10.886,
      "eval_steps_per_second": 5.443,
      "step": 5
    },
    {
      "epoch": 0.0029809961495466403,
      "grad_norm": 16.843305587768555,
      "learning_rate": 9.96057350657239e-05,
      "loss": 21.1989,
      "step": 6
    },
    {
      "epoch": 0.0044714942243199605,
      "grad_norm": 16.498064041137695,
      "learning_rate": 9.381533400219318e-05,
      "loss": 19.2642,
      "step": 9
    },
    {
      "epoch": 0.004968326915911067,
      "eval_loss": 4.2596354484558105,
      "eval_runtime": 77.9927,
      "eval_samples_per_second": 10.873,
      "eval_steps_per_second": 5.436,
      "step": 10
    },
    {
      "epoch": 0.005961992299093281,
      "grad_norm": 13.716416358947754,
      "learning_rate": 8.18711994874345e-05,
      "loss": 17.5391,
      "step": 12
    },
    {
      "epoch": 0.007452490373866601,
      "grad_norm": 13.025663375854492,
      "learning_rate": 6.545084971874738e-05,
      "loss": 15.9514,
      "step": 15
    },
    {
      "epoch": 0.007452490373866601,
      "eval_loss": 3.834385633468628,
      "eval_runtime": 77.4146,
      "eval_samples_per_second": 10.954,
      "eval_steps_per_second": 5.477,
      "step": 15
    },
    {
      "epoch": 0.008942988448639921,
      "grad_norm": 13.887004852294922,
      "learning_rate": 4.6860474023534335e-05,
      "loss": 15.5808,
      "step": 18
    },
    {
      "epoch": 0.009936653831822134,
      "eval_loss": 3.6557891368865967,
      "eval_runtime": 77.3554,
      "eval_samples_per_second": 10.962,
      "eval_steps_per_second": 5.481,
      "step": 20
    },
    {
      "epoch": 0.01043348652341324,
      "grad_norm": 11.381671905517578,
      "learning_rate": 2.8711035421746367e-05,
      "loss": 14.3006,
      "step": 21
    },
    {
      "epoch": 0.011923984598186561,
      "grad_norm": 12.137283325195312,
      "learning_rate": 1.3551568628929434e-05,
      "loss": 14.4807,
      "step": 24
    },
    {
      "epoch": 0.012420817289777668,
      "eval_loss": 3.590764284133911,
      "eval_runtime": 77.337,
      "eval_samples_per_second": 10.965,
      "eval_steps_per_second": 5.482,
      "step": 25
    },
    {
      "epoch": 0.01341448267295988,
      "grad_norm": 12.388276100158691,
      "learning_rate": 3.511175705587433e-06,
      "loss": 14.1514,
      "step": 27
    },
    {
      "epoch": 0.014904980747733202,
      "grad_norm": 13.344575881958008,
      "learning_rate": 0.0,
      "loss": 15.1692,
      "step": 30
    },
    {
      "epoch": 0.014904980747733202,
      "eval_loss": 3.5841777324676514,
      "eval_runtime": 77.5415,
      "eval_samples_per_second": 10.936,
      "eval_steps_per_second": 5.468,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "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": 910112965263360.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}