last-checkpoint/trainer_state.json

{
  "best_metric": 1.6313807964324951,
  "best_model_checkpoint": "miner_id_24/checkpoint-10",
  "epoch": 0.007739938080495356,
  "eval_steps": 5,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0007739938080495357,
      "grad_norm": 0.6112090349197388,
      "learning_rate": 1e-05,
      "loss": 5.9449,
      "step": 1
    },
    {
      "epoch": 0.0007739938080495357,
      "eval_loss": 1.638183832168579,
      "eval_runtime": 123.6155,
      "eval_samples_per_second": 4.409,
      "eval_steps_per_second": 2.208,
      "step": 1
    },
    {
      "epoch": 0.0015479876160990713,
      "grad_norm": 0.7082736492156982,
      "learning_rate": 2e-05,
      "loss": 5.8472,
      "step": 2
    },
    {
      "epoch": 0.0023219814241486067,
      "grad_norm": 0.8556309938430786,
      "learning_rate": 3e-05,
      "loss": 6.6413,
      "step": 3
    },
    {
      "epoch": 0.0030959752321981426,
      "grad_norm": 1.0540803670883179,
      "learning_rate": 4e-05,
      "loss": 6.5789,
      "step": 4
    },
    {
      "epoch": 0.003869969040247678,
      "grad_norm": 0.5907458662986755,
      "learning_rate": 5e-05,
      "loss": 4.927,
      "step": 5
    },
    {
      "epoch": 0.003869969040247678,
      "eval_loss": 1.6376686096191406,
      "eval_runtime": 124.049,
      "eval_samples_per_second": 4.393,
      "eval_steps_per_second": 2.201,
      "step": 5
    },
    {
      "epoch": 0.0046439628482972135,
      "grad_norm": 0.6620371341705322,
      "learning_rate": 6e-05,
      "loss": 6.2809,
      "step": 6
    },
    {
      "epoch": 0.005417956656346749,
      "grad_norm": 0.5814986228942871,
      "learning_rate": 7e-05,
      "loss": 5.0479,
      "step": 7
    },
    {
      "epoch": 0.006191950464396285,
      "grad_norm": 0.6137049198150635,
      "learning_rate": 8e-05,
      "loss": 6.1478,
      "step": 8
    },
    {
      "epoch": 0.00696594427244582,
      "grad_norm": 0.6229683756828308,
      "learning_rate": 9e-05,
      "loss": 4.2841,
      "step": 9
    },
    {
      "epoch": 0.007739938080495356,
      "grad_norm": 0.8397112488746643,
      "learning_rate": 0.0001,
      "loss": 4.238,
      "step": 10
    },
    {
      "epoch": 0.007739938080495356,
      "eval_loss": 1.6313807964324951,
      "eval_runtime": 123.9718,
      "eval_samples_per_second": 4.396,
      "eval_steps_per_second": 2.202,
      "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": 2931748635672576.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}