last-checkpoint/trainer_state.json

{
  "best_metric": NaN,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.1984988524285094,
  "eval_steps": 100,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.001984988524285094,
      "eval_loss": NaN,
      "eval_runtime": 148.8478,
      "eval_samples_per_second": 5.704,
      "eval_steps_per_second": 5.704,
      "step": 1
    },
    {
      "epoch": 0.01984988524285094,
      "grad_norm": NaN,
      "learning_rate": 2.5e-06,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.03969977048570188,
      "grad_norm": NaN,
      "learning_rate": 5e-06,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.05954965572855282,
      "grad_norm": NaN,
      "learning_rate": 7.5e-06,
      "loss": 38369407795.2,
      "step": 30
    },
    {
      "epoch": 0.07939954097140375,
      "grad_norm": NaN,
      "learning_rate": 1e-05,
      "loss": 58802034861670.4,
      "step": 40
    },
    {
      "epoch": 0.0992494262142547,
      "grad_norm": NaN,
      "learning_rate": 1.25e-05,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 0.11909931145710564,
      "grad_norm": NaN,
      "learning_rate": 1.5e-05,
      "loss": 1.836556713023085e+18,
      "step": 60
    },
    {
      "epoch": 0.1389491966999566,
      "grad_norm": NaN,
      "learning_rate": 1.75e-05,
      "loss": 168.6052,
      "step": 70
    },
    {
      "epoch": 0.1587990819428075,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 80
    },
    {
      "epoch": 0.17864896718565845,
      "grad_norm": NaN,
      "learning_rate": 2.25e-05,
      "loss": 1.0724476961752798e+21,
      "step": 90
    },
    {
      "epoch": 0.1984988524285094,
      "grad_norm": NaN,
      "learning_rate": 2.5e-05,
      "loss": 4.1393,
      "step": 100
    },
    {
      "epoch": 0.1984988524285094,
      "eval_loss": NaN,
      "eval_runtime": 148.5823,
      "eval_samples_per_second": 5.714,
      "eval_steps_per_second": 5.714,
      "step": 100
    }
  ],
  "logging_steps": 10,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "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": 2.6446728217912934e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}