last-checkpoint/trainer_state.json

{
  "best_metric": 0.9622511267662048,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.012683648662932036,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00042278828876440123,
      "eval_loss": 1.1933761835098267,
      "eval_runtime": 135.4339,
      "eval_samples_per_second": 7.354,
      "eval_steps_per_second": 3.677,
      "step": 1
    },
    {
      "epoch": 0.0012683648662932037,
      "grad_norm": 11.284184455871582,
      "learning_rate": 6e-05,
      "loss": 4.4735,
      "step": 3
    },
    {
      "epoch": 0.0021139414438220063,
      "eval_loss": 1.0962536334991455,
      "eval_runtime": 136.7913,
      "eval_samples_per_second": 7.281,
      "eval_steps_per_second": 3.641,
      "step": 5
    },
    {
      "epoch": 0.0025367297325864075,
      "grad_norm": 10.291092872619629,
      "learning_rate": 0.00012,
      "loss": 4.5116,
      "step": 6
    },
    {
      "epoch": 0.003805094598879611,
      "grad_norm": 12.492044448852539,
      "learning_rate": 0.00018,
      "loss": 4.0044,
      "step": 9
    },
    {
      "epoch": 0.004227882887644013,
      "eval_loss": 1.0281891822814941,
      "eval_runtime": 136.8737,
      "eval_samples_per_second": 7.277,
      "eval_steps_per_second": 3.638,
      "step": 10
    },
    {
      "epoch": 0.005073459465172815,
      "grad_norm": 8.697997093200684,
      "learning_rate": 0.00019510565162951537,
      "loss": 3.8483,
      "step": 12
    },
    {
      "epoch": 0.006341824331466018,
      "grad_norm": 9.351025581359863,
      "learning_rate": 0.00017071067811865476,
      "loss": 3.9851,
      "step": 15
    },
    {
      "epoch": 0.006341824331466018,
      "eval_loss": 0.9977760910987854,
      "eval_runtime": 136.7759,
      "eval_samples_per_second": 7.282,
      "eval_steps_per_second": 3.641,
      "step": 15
    },
    {
      "epoch": 0.007610189197759222,
      "grad_norm": 8.28114128112793,
      "learning_rate": 0.00013090169943749476,
      "loss": 3.7435,
      "step": 18
    },
    {
      "epoch": 0.008455765775288025,
      "eval_loss": 0.98299241065979,
      "eval_runtime": 136.7944,
      "eval_samples_per_second": 7.281,
      "eval_steps_per_second": 3.64,
      "step": 20
    },
    {
      "epoch": 0.008878554064052425,
      "grad_norm": 7.331959247589111,
      "learning_rate": 8.435655349597689e-05,
      "loss": 4.228,
      "step": 21
    },
    {
      "epoch": 0.01014691893034563,
      "grad_norm": 5.93434476852417,
      "learning_rate": 4.12214747707527e-05,
      "loss": 3.9821,
      "step": 24
    },
    {
      "epoch": 0.01056970721911003,
      "eval_loss": 0.9660122394561768,
      "eval_runtime": 137.0324,
      "eval_samples_per_second": 7.268,
      "eval_steps_per_second": 3.634,
      "step": 25
    },
    {
      "epoch": 0.011415283796638833,
      "grad_norm": 7.390657424926758,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 3.8016,
      "step": 27
    },
    {
      "epoch": 0.012683648662932036,
      "grad_norm": 6.83233118057251,
      "learning_rate": 0.0,
      "loss": 3.8984,
      "step": 30
    },
    {
      "epoch": 0.012683648662932036,
      "eval_loss": 0.9622511267662048,
      "eval_runtime": 136.8086,
      "eval_samples_per_second": 7.28,
      "eval_steps_per_second": 3.64,
      "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": 1.1250084863803392e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}