{
  "best_metric": 0.8686741590499878,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.012683648662932036,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00042278828876440123,
      "eval_loss": 1.0198981761932373,
      "eval_runtime": 134.3255,
      "eval_samples_per_second": 7.415,
      "eval_steps_per_second": 3.707,
      "step": 1
    },
    {
      "epoch": 0.0012683648662932037,
      "grad_norm": 12.870140075683594,
      "learning_rate": 6e-05,
      "loss": 4.0089,
      "step": 3
    },
    {
      "epoch": 0.0021139414438220063,
      "eval_loss": 0.9453728795051575,
      "eval_runtime": 135.415,
      "eval_samples_per_second": 7.355,
      "eval_steps_per_second": 3.678,
      "step": 5
    },
    {
      "epoch": 0.0025367297325864075,
      "grad_norm": 13.533971786499023,
      "learning_rate": 0.00012,
      "loss": 3.7072,
      "step": 6
    },
    {
      "epoch": 0.003805094598879611,
      "grad_norm": 11.559992790222168,
      "learning_rate": 0.00018,
      "loss": 3.615,
      "step": 9
    },
    {
      "epoch": 0.004227882887644013,
      "eval_loss": 0.899836003780365,
      "eval_runtime": 135.6278,
      "eval_samples_per_second": 7.344,
      "eval_steps_per_second": 3.672,
      "step": 10
    },
    {
      "epoch": 0.005073459465172815,
      "grad_norm": 9.462875366210938,
      "learning_rate": 0.00019510565162951537,
      "loss": 3.1673,
      "step": 12
    },
    {
      "epoch": 0.006341824331466018,
      "grad_norm": 13.82746410369873,
      "learning_rate": 0.00017071067811865476,
      "loss": 3.3417,
      "step": 15
    },
    {
      "epoch": 0.006341824331466018,
      "eval_loss": 0.894367516040802,
      "eval_runtime": 135.3207,
      "eval_samples_per_second": 7.36,
      "eval_steps_per_second": 3.68,
      "step": 15
    },
    {
      "epoch": 0.007610189197759222,
      "grad_norm": 9.724739074707031,
      "learning_rate": 0.00013090169943749476,
      "loss": 3.4907,
      "step": 18
    },
    {
      "epoch": 0.008455765775288025,
      "eval_loss": 0.880286693572998,
      "eval_runtime": 135.3208,
      "eval_samples_per_second": 7.36,
      "eval_steps_per_second": 3.68,
      "step": 20
    },
    {
      "epoch": 0.008878554064052425,
      "grad_norm": 9.82568359375,
      "learning_rate": 8.435655349597689e-05,
      "loss": 3.5855,
      "step": 21
    },
    {
      "epoch": 0.01014691893034563,
      "grad_norm": 9.060408592224121,
      "learning_rate": 4.12214747707527e-05,
      "loss": 3.6996,
      "step": 24
    },
    {
      "epoch": 0.01056970721911003,
      "eval_loss": 0.8725765943527222,
      "eval_runtime": 135.8826,
      "eval_samples_per_second": 7.33,
      "eval_steps_per_second": 3.665,
      "step": 25
    },
    {
      "epoch": 0.011415283796638833,
      "grad_norm": 10.024374961853027,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 3.5561,
      "step": 27
    },
    {
      "epoch": 0.012683648662932036,
      "grad_norm": 8.599822998046875,
      "learning_rate": 0.0,
      "loss": 3.3725,
      "step": 30
    },
    {
      "epoch": 0.012683648662932036,
      "eval_loss": 0.8686741590499878,
      "eval_runtime": 136.0169,
      "eval_samples_per_second": 7.323,
      "eval_steps_per_second": 3.661,
      "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": 1.1250084863803392e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}