last-checkpoint/trainer_state.json

{
  "best_metric": 1.9829720258712769,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.042811273635390654,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0014270424545130217,
      "eval_loss": 2.0832698345184326,
      "eval_runtime": 65.6797,
      "eval_samples_per_second": 8.983,
      "eval_steps_per_second": 2.253,
      "step": 1
    },
    {
      "epoch": 0.004281127363539065,
      "grad_norm": 0.8814626932144165,
      "learning_rate": 0.00012,
      "loss": 8.1138,
      "step": 3
    },
    {
      "epoch": 0.007135212272565109,
      "eval_loss": 2.065013885498047,
      "eval_runtime": 66.1087,
      "eval_samples_per_second": 8.925,
      "eval_steps_per_second": 2.239,
      "step": 5
    },
    {
      "epoch": 0.00856225472707813,
      "grad_norm": 0.7059219479560852,
      "learning_rate": 0.0001992114701314478,
      "loss": 7.9036,
      "step": 6
    },
    {
      "epoch": 0.012843382090617196,
      "grad_norm": 0.9905046820640564,
      "learning_rate": 0.00018763066800438636,
      "loss": 8.0913,
      "step": 9
    },
    {
      "epoch": 0.014270424545130217,
      "eval_loss": 2.0186400413513184,
      "eval_runtime": 66.11,
      "eval_samples_per_second": 8.925,
      "eval_steps_per_second": 2.239,
      "step": 10
    },
    {
      "epoch": 0.01712450945415626,
      "grad_norm": 0.8391133546829224,
      "learning_rate": 0.000163742398974869,
      "loss": 8.3792,
      "step": 12
    },
    {
      "epoch": 0.021405636817695327,
      "grad_norm": 0.5525553226470947,
      "learning_rate": 0.00013090169943749476,
      "loss": 8.1928,
      "step": 15
    },
    {
      "epoch": 0.021405636817695327,
      "eval_loss": 1.9936939477920532,
      "eval_runtime": 66.5146,
      "eval_samples_per_second": 8.87,
      "eval_steps_per_second": 2.225,
      "step": 15
    },
    {
      "epoch": 0.025686764181234393,
      "grad_norm": 0.9312046766281128,
      "learning_rate": 9.372094804706867e-05,
      "loss": 8.188,
      "step": 18
    },
    {
      "epoch": 0.028540849090260435,
      "eval_loss": 1.9905468225479126,
      "eval_runtime": 66.4999,
      "eval_samples_per_second": 8.872,
      "eval_steps_per_second": 2.226,
      "step": 20
    },
    {
      "epoch": 0.029967891544773455,
      "grad_norm": 4.579926490783691,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 8.4023,
      "step": 21
    },
    {
      "epoch": 0.03424901890831252,
      "grad_norm": 0.5020058751106262,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 8.322,
      "step": 24
    },
    {
      "epoch": 0.03567606136282554,
      "eval_loss": 1.984390139579773,
      "eval_runtime": 66.1126,
      "eval_samples_per_second": 8.924,
      "eval_steps_per_second": 2.239,
      "step": 25
    },
    {
      "epoch": 0.038530146271851584,
      "grad_norm": 0.5804142951965332,
      "learning_rate": 7.022351411174866e-06,
      "loss": 8.2736,
      "step": 27
    },
    {
      "epoch": 0.042811273635390654,
      "grad_norm": 0.5896081328392029,
      "learning_rate": 0.0,
      "loss": 7.9687,
      "step": 30
    },
    {
      "epoch": 0.042811273635390654,
      "eval_loss": 1.9829720258712769,
      "eval_runtime": 66.1241,
      "eval_samples_per_second": 8.923,
      "eval_steps_per_second": 2.238,
      "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": 3.5450456956207104e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}