{
  "best_metric": 1.0137192010879517,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.6329113924050633,
  "eval_steps": 5,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02531645569620253,
      "grad_norm": 20.915555953979492,
      "learning_rate": 2e-05,
      "loss": 7.1044,
      "step": 1
    },
    {
      "epoch": 0.02531645569620253,
      "eval_loss": 1.9238215684890747,
      "eval_runtime": 3.8238,
      "eval_samples_per_second": 4.446,
      "eval_steps_per_second": 2.354,
      "step": 1
    },
    {
      "epoch": 0.05063291139240506,
      "grad_norm": 24.20079803466797,
      "learning_rate": 4e-05,
      "loss": 7.3347,
      "step": 2
    },
    {
      "epoch": 0.0759493670886076,
      "grad_norm": 21.937389373779297,
      "learning_rate": 6e-05,
      "loss": 7.3178,
      "step": 3
    },
    {
      "epoch": 0.10126582278481013,
      "grad_norm": 21.61054801940918,
      "learning_rate": 8e-05,
      "loss": 6.998,
      "step": 4
    },
    {
      "epoch": 0.12658227848101267,
      "grad_norm": 26.70899772644043,
      "learning_rate": 0.0001,
      "loss": 6.628,
      "step": 5
    },
    {
      "epoch": 0.12658227848101267,
      "eval_loss": 1.5685361623764038,
      "eval_runtime": 3.7721,
      "eval_samples_per_second": 4.507,
      "eval_steps_per_second": 2.386,
      "step": 5
    },
    {
      "epoch": 0.1518987341772152,
      "grad_norm": 20.493154525756836,
      "learning_rate": 0.00012,
      "loss": 5.6093,
      "step": 6
    },
    {
      "epoch": 0.17721518987341772,
      "grad_norm": 17.29804801940918,
      "learning_rate": 0.00014,
      "loss": 4.6879,
      "step": 7
    },
    {
      "epoch": 0.20253164556962025,
      "grad_norm": 19.611940383911133,
      "learning_rate": 0.00016,
      "loss": 4.7622,
      "step": 8
    },
    {
      "epoch": 0.22784810126582278,
      "grad_norm": 20.298032760620117,
      "learning_rate": 0.00018,
      "loss": 4.7463,
      "step": 9
    },
    {
      "epoch": 0.25316455696202533,
      "grad_norm": 15.746353149414062,
      "learning_rate": 0.0002,
      "loss": 4.2088,
      "step": 10
    },
    {
      "epoch": 0.25316455696202533,
      "eval_loss": 1.0953528881072998,
      "eval_runtime": 3.7313,
      "eval_samples_per_second": 4.556,
      "eval_steps_per_second": 2.412,
      "step": 10
    },
    {
      "epoch": 0.27848101265822783,
      "grad_norm": 26.16781997680664,
      "learning_rate": 0.00019781476007338058,
      "loss": 5.3184,
      "step": 11
    },
    {
      "epoch": 0.3037974683544304,
      "grad_norm": 15.420275688171387,
      "learning_rate": 0.0001913545457642601,
      "loss": 4.2233,
      "step": 12
    },
    {
      "epoch": 0.3291139240506329,
      "grad_norm": 22.992372512817383,
      "learning_rate": 0.00018090169943749476,
      "loss": 3.7317,
      "step": 13
    },
    {
      "epoch": 0.35443037974683544,
      "grad_norm": 17.611976623535156,
      "learning_rate": 0.00016691306063588583,
      "loss": 5.165,
      "step": 14
    },
    {
      "epoch": 0.379746835443038,
      "grad_norm": 13.892826080322266,
      "learning_rate": 0.00015000000000000001,
      "loss": 3.9094,
      "step": 15
    },
    {
      "epoch": 0.379746835443038,
      "eval_loss": 1.0695868730545044,
      "eval_runtime": 3.8815,
      "eval_samples_per_second": 4.38,
      "eval_steps_per_second": 2.319,
      "step": 15
    },
    {
      "epoch": 0.4050632911392405,
      "grad_norm": 12.855504989624023,
      "learning_rate": 0.00013090169943749476,
      "loss": 3.6685,
      "step": 16
    },
    {
      "epoch": 0.43037974683544306,
      "grad_norm": 17.538185119628906,
      "learning_rate": 0.00011045284632676536,
      "loss": 4.4205,
      "step": 17
    },
    {
      "epoch": 0.45569620253164556,
      "grad_norm": 16.913982391357422,
      "learning_rate": 8.954715367323468e-05,
      "loss": 3.9638,
      "step": 18
    },
    {
      "epoch": 0.4810126582278481,
      "grad_norm": 14.760642051696777,
      "learning_rate": 6.909830056250527e-05,
      "loss": 4.1546,
      "step": 19
    },
    {
      "epoch": 0.5063291139240507,
      "grad_norm": 16.046525955200195,
      "learning_rate": 5.000000000000002e-05,
      "loss": 3.607,
      "step": 20
    },
    {
      "epoch": 0.5063291139240507,
      "eval_loss": 1.0186785459518433,
      "eval_runtime": 3.8623,
      "eval_samples_per_second": 4.402,
      "eval_steps_per_second": 2.33,
      "step": 20
    },
    {
      "epoch": 0.5316455696202531,
      "grad_norm": 16.88188362121582,
      "learning_rate": 3.308693936411421e-05,
      "loss": 4.3946,
      "step": 21
    },
    {
      "epoch": 0.5569620253164557,
      "grad_norm": 15.035842895507812,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 4.1136,
      "step": 22
    },
    {
      "epoch": 0.5822784810126582,
      "grad_norm": 15.598001480102539,
      "learning_rate": 8.645454235739903e-06,
      "loss": 4.5961,
      "step": 23
    },
    {
      "epoch": 0.6075949367088608,
      "grad_norm": 13.525558471679688,
      "learning_rate": 2.1852399266194314e-06,
      "loss": 3.6972,
      "step": 24
    },
    {
      "epoch": 0.6329113924050633,
      "grad_norm": 11.98470687866211,
      "learning_rate": 0.0,
      "loss": 3.5662,
      "step": 25
    },
    {
      "epoch": 0.6329113924050633,
      "eval_loss": 1.0137192010879517,
      "eval_runtime": 3.7701,
      "eval_samples_per_second": 4.509,
      "eval_steps_per_second": 2.387,
      "step": 25
    }
  ],
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4381674464870400.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}