last-checkpoint/trainer_state.json

{
  "best_metric": 0.839118242263794,
  "best_model_checkpoint": "miner_id_24/checkpoint-20",
  "epoch": 0.0006499573465491328,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.249786732745664e-05,
      "eval_loss": 1.712390422821045,
      "eval_runtime": 2336.6809,
      "eval_samples_per_second": 5.545,
      "eval_steps_per_second": 2.773,
      "step": 1
    },
    {
      "epoch": 9.74936019823699e-05,
      "grad_norm": 15.106966018676758,
      "learning_rate": 6e-05,
      "loss": 6.4014,
      "step": 3
    },
    {
      "epoch": 0.0001624893366372832,
      "eval_loss": 1.3558801412582397,
      "eval_runtime": 2348.1344,
      "eval_samples_per_second": 5.518,
      "eval_steps_per_second": 2.759,
      "step": 5
    },
    {
      "epoch": 0.0001949872039647398,
      "grad_norm": 13.26583480834961,
      "learning_rate": 0.00012,
      "loss": 4.4171,
      "step": 6
    },
    {
      "epoch": 0.00029248080594710974,
      "grad_norm": 9.484980583190918,
      "learning_rate": 0.00018,
      "loss": 4.265,
      "step": 9
    },
    {
      "epoch": 0.0003249786732745664,
      "eval_loss": 1.0520634651184082,
      "eval_runtime": 2344.7233,
      "eval_samples_per_second": 5.526,
      "eval_steps_per_second": 2.763,
      "step": 10
    },
    {
      "epoch": 0.0003899744079294796,
      "grad_norm": 12.171273231506348,
      "learning_rate": 0.00019510565162951537,
      "loss": 3.9456,
      "step": 12
    },
    {
      "epoch": 0.0004874680099118495,
      "grad_norm": 10.046751022338867,
      "learning_rate": 0.00017071067811865476,
      "loss": 3.8244,
      "step": 15
    },
    {
      "epoch": 0.0004874680099118495,
      "eval_loss": 0.897432267665863,
      "eval_runtime": 2348.5492,
      "eval_samples_per_second": 5.517,
      "eval_steps_per_second": 2.759,
      "step": 15
    },
    {
      "epoch": 0.0005849616118942195,
      "grad_norm": 7.874410629272461,
      "learning_rate": 0.00013090169943749476,
      "loss": 3.3084,
      "step": 18
    },
    {
      "epoch": 0.0006499573465491328,
      "eval_loss": 0.839118242263794,
      "eval_runtime": 2346.33,
      "eval_samples_per_second": 5.522,
      "eval_steps_per_second": 2.761,
      "step": 20
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 8525445171511296.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}