last-checkpoint/trainer_state.json

{
  "best_metric": NaN,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 1.7665198237885462,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07048458149779736,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 904.6357,
      "step": 1
    },
    {
      "epoch": 0.07048458149779736,
      "eval_loss": NaN,
      "eval_runtime": 4.7727,
      "eval_samples_per_second": 10.476,
      "eval_steps_per_second": 2.724,
      "step": 1
    },
    {
      "epoch": 0.14096916299559473,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.21145374449339208,
      "grad_norm": NaN,
      "learning_rate": 9.986796105326832e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.28193832599118945,
      "grad_norm": NaN,
      "learning_rate": 9.947261907011569e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.3524229074889868,
      "grad_norm": NaN,
      "learning_rate": 9.881629407450006e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.42290748898678415,
      "grad_norm": NaN,
      "learning_rate": 9.790283764247188e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.4933920704845815,
      "grad_norm": NaN,
      "learning_rate": 9.673761029959427e-05,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.5638766519823789,
      "grad_norm": NaN,
      "learning_rate": 9.53274500632475e-05,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.6343612334801763,
      "grad_norm": NaN,
      "learning_rate": 9.368063231442406e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.7048458149779736,
      "grad_norm": NaN,
      "learning_rate": 9.18068212345023e-05,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.775330396475771,
      "grad_norm": NaN,
      "learning_rate": 8.971701309198744e-05,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.8458149779735683,
      "grad_norm": NaN,
      "learning_rate": 8.742347171203542e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.9162995594713657,
      "grad_norm": NaN,
      "learning_rate": 8.493965650745043e-05,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.986784140969163,
      "grad_norm": NaN,
      "learning_rate": 8.228014349349872e-05,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 1.0616740088105727,
      "grad_norm": NaN,
      "learning_rate": 7.946053975005496e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 1.13215859030837,
      "grad_norm": NaN,
      "learning_rate": 7.649739183305184e-05,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 1.2026431718061674,
      "grad_norm": NaN,
      "learning_rate": 7.34080886727103e-05,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 1.2731277533039647,
      "grad_norm": NaN,
      "learning_rate": 7.021075952838262e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 1.3436123348017621,
      "grad_norm": NaN,
      "learning_rate": 6.692416759884978e-05,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 1.4140969162995596,
      "grad_norm": NaN,
      "learning_rate": 6.356759991241008e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 1.4845814977973568,
      "grad_norm": NaN,
      "learning_rate": 6.016075414292803e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 1.555066079295154,
      "grad_norm": NaN,
      "learning_rate": 5.6723623016051596e-05,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 1.6255506607929515,
      "grad_norm": NaN,
      "learning_rate": 5.3276376983948415e-05,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 1.696035242290749,
      "grad_norm": NaN,
      "learning_rate": 4.9839245857071994e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 1.7665198237885462,
      "grad_norm": NaN,
      "learning_rate": 4.643240008758992e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 1.7665198237885462,
      "eval_loss": NaN,
      "eval_runtime": 3.6192,
      "eval_samples_per_second": 13.815,
      "eval_steps_per_second": 3.592,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 43,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 25,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.0677119162279526e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}