last-checkpoint/trainer_state.json

{
  "best_metric": 1.7774372100830078,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.0007216135278482687,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.4053784261608958e-05,
      "eval_loss": 3.604696750640869,
      "eval_runtime": 2235.6462,
      "eval_samples_per_second": 15.66,
      "eval_steps_per_second": 3.915,
      "step": 1
    },
    {
      "epoch": 7.216135278482687e-05,
      "grad_norm": 21.76235580444336,
      "learning_rate": 0.00012,
      "loss": 10.3252,
      "step": 3
    },
    {
      "epoch": 0.00012026892130804478,
      "eval_loss": 3.373138666152954,
      "eval_runtime": 2235.6131,
      "eval_samples_per_second": 15.66,
      "eval_steps_per_second": 3.915,
      "step": 5
    },
    {
      "epoch": 0.00014432270556965373,
      "grad_norm": 12.278535842895508,
      "learning_rate": 0.0001992114701314478,
      "loss": 10.0076,
      "step": 6
    },
    {
      "epoch": 0.0002164840583544806,
      "grad_norm": 6.428678512573242,
      "learning_rate": 0.00018763066800438636,
      "loss": 9.4451,
      "step": 9
    },
    {
      "epoch": 0.00024053784261608956,
      "eval_loss": 2.6429617404937744,
      "eval_runtime": 2235.5851,
      "eval_samples_per_second": 15.66,
      "eval_steps_per_second": 3.915,
      "step": 10
    },
    {
      "epoch": 0.00028864541113930747,
      "grad_norm": 6.507843971252441,
      "learning_rate": 0.000163742398974869,
      "loss": 8.2763,
      "step": 12
    },
    {
      "epoch": 0.0003608067639241344,
      "grad_norm": 16.41105079650879,
      "learning_rate": 0.00013090169943749476,
      "loss": 7.6064,
      "step": 15
    },
    {
      "epoch": 0.0003608067639241344,
      "eval_loss": 2.160693407058716,
      "eval_runtime": 2235.7553,
      "eval_samples_per_second": 15.659,
      "eval_steps_per_second": 3.915,
      "step": 15
    },
    {
      "epoch": 0.0004329681167089612,
      "grad_norm": 5.645549297332764,
      "learning_rate": 9.372094804706867e-05,
      "loss": 7.2956,
      "step": 18
    },
    {
      "epoch": 0.00048107568523217913,
      "eval_loss": 1.9027982950210571,
      "eval_runtime": 2235.6324,
      "eval_samples_per_second": 15.66,
      "eval_steps_per_second": 3.915,
      "step": 20
    },
    {
      "epoch": 0.0005051294694937881,
      "grad_norm": 5.871511459350586,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 6.5545,
      "step": 21
    },
    {
      "epoch": 0.0005772908222786149,
      "grad_norm": 5.881715774536133,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 6.5465,
      "step": 24
    },
    {
      "epoch": 0.0006013446065402239,
      "eval_loss": 1.795774221420288,
      "eval_runtime": 2235.8074,
      "eval_samples_per_second": 15.659,
      "eval_steps_per_second": 3.915,
      "step": 25
    },
    {
      "epoch": 0.0006494521750634418,
      "grad_norm": 11.0554780960083,
      "learning_rate": 7.022351411174866e-06,
      "loss": 6.722,
      "step": 27
    },
    {
      "epoch": 0.0007216135278482687,
      "grad_norm": 13.766908645629883,
      "learning_rate": 0.0,
      "loss": 6.8375,
      "step": 30
    },
    {
      "epoch": 0.0007216135278482687,
      "eval_loss": 1.7774372100830078,
      "eval_runtime": 2235.4123,
      "eval_samples_per_second": 15.662,
      "eval_steps_per_second": 3.916,
      "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": 1.960393933062144e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}