{
  "best_metric": 1.7055974006652832,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.01483019427554501,
  "eval_steps": 5,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005932077710218003,
      "grad_norm": 1.5604506731033325,
      "learning_rate": 2e-05,
      "loss": 7.2816,
      "step": 1
    },
    {
      "epoch": 0.0005932077710218003,
      "eval_loss": 1.8809071779251099,
      "eval_runtime": 51.1364,
      "eval_samples_per_second": 13.884,
      "eval_steps_per_second": 6.942,
      "step": 1
    },
    {
      "epoch": 0.0011864155420436007,
      "grad_norm": 1.3534035682678223,
      "learning_rate": 4e-05,
      "loss": 7.2367,
      "step": 2
    },
    {
      "epoch": 0.0017796233130654012,
      "grad_norm": 1.556756615638733,
      "learning_rate": 6e-05,
      "loss": 6.6101,
      "step": 3
    },
    {
      "epoch": 0.0023728310840872013,
      "grad_norm": 1.78481125831604,
      "learning_rate": 8e-05,
      "loss": 6.6512,
      "step": 4
    },
    {
      "epoch": 0.002966038855109002,
      "grad_norm": 1.6084747314453125,
      "learning_rate": 0.0001,
      "loss": 7.5114,
      "step": 5
    },
    {
      "epoch": 0.002966038855109002,
      "eval_loss": 1.8634954690933228,
      "eval_runtime": 47.8443,
      "eval_samples_per_second": 14.84,
      "eval_steps_per_second": 7.42,
      "step": 5
    },
    {
      "epoch": 0.0035592466261308024,
      "grad_norm": 1.8598929643630981,
      "learning_rate": 0.00012,
      "loss": 7.3005,
      "step": 6
    },
    {
      "epoch": 0.004152454397152602,
      "grad_norm": 1.7229331731796265,
      "learning_rate": 0.00014,
      "loss": 7.0142,
      "step": 7
    },
    {
      "epoch": 0.004745662168174403,
      "grad_norm": 1.9855549335479736,
      "learning_rate": 0.00016,
      "loss": 5.9546,
      "step": 8
    },
    {
      "epoch": 0.005338869939196204,
      "grad_norm": 2.6306424140930176,
      "learning_rate": 0.00018,
      "loss": 7.6557,
      "step": 9
    },
    {
      "epoch": 0.005932077710218004,
      "grad_norm": 4.312272071838379,
      "learning_rate": 0.0002,
      "loss": 8.7644,
      "step": 10
    },
    {
      "epoch": 0.005932077710218004,
      "eval_loss": 1.7866129875183105,
      "eval_runtime": 47.7519,
      "eval_samples_per_second": 14.869,
      "eval_steps_per_second": 7.434,
      "step": 10
    },
    {
      "epoch": 0.0065252854812398045,
      "grad_norm": 3.453673839569092,
      "learning_rate": 0.00019781476007338058,
      "loss": 8.4542,
      "step": 11
    },
    {
      "epoch": 0.007118493252261605,
      "grad_norm": 4.104527473449707,
      "learning_rate": 0.0001913545457642601,
      "loss": 8.2059,
      "step": 12
    },
    {
      "epoch": 0.007711701023283405,
      "grad_norm": 6.156380653381348,
      "learning_rate": 0.00018090169943749476,
      "loss": 8.3057,
      "step": 13
    },
    {
      "epoch": 0.008304908794305205,
      "grad_norm": 5.152556419372559,
      "learning_rate": 0.00016691306063588583,
      "loss": 5.8191,
      "step": 14
    },
    {
      "epoch": 0.008898116565327005,
      "grad_norm": 4.139110088348389,
      "learning_rate": 0.00015000000000000001,
      "loss": 6.4268,
      "step": 15
    },
    {
      "epoch": 0.008898116565327005,
      "eval_loss": 1.7479956150054932,
      "eval_runtime": 47.3405,
      "eval_samples_per_second": 14.998,
      "eval_steps_per_second": 7.499,
      "step": 15
    },
    {
      "epoch": 0.009491324336348805,
      "grad_norm": 5.199703216552734,
      "learning_rate": 0.00013090169943749476,
      "loss": 7.6062,
      "step": 16
    },
    {
      "epoch": 0.010084532107370607,
      "grad_norm": 5.312143325805664,
      "learning_rate": 0.00011045284632676536,
      "loss": 5.2735,
      "step": 17
    },
    {
      "epoch": 0.010677739878392408,
      "grad_norm": 5.719979286193848,
      "learning_rate": 8.954715367323468e-05,
      "loss": 6.2765,
      "step": 18
    },
    {
      "epoch": 0.011270947649414208,
      "grad_norm": 4.406425476074219,
      "learning_rate": 6.909830056250527e-05,
      "loss": 6.6895,
      "step": 19
    },
    {
      "epoch": 0.011864155420436008,
      "grad_norm": 6.59907865524292,
      "learning_rate": 5.000000000000002e-05,
      "loss": 7.4128,
      "step": 20
    },
    {
      "epoch": 0.011864155420436008,
      "eval_loss": 1.7100764513015747,
      "eval_runtime": 48.7502,
      "eval_samples_per_second": 14.564,
      "eval_steps_per_second": 7.282,
      "step": 20
    },
    {
      "epoch": 0.012457363191457809,
      "grad_norm": 4.8315749168396,
      "learning_rate": 3.308693936411421e-05,
      "loss": 6.5809,
      "step": 21
    },
    {
      "epoch": 0.013050570962479609,
      "grad_norm": 6.237402439117432,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 7.0893,
      "step": 22
    },
    {
      "epoch": 0.01364377873350141,
      "grad_norm": 3.9503602981567383,
      "learning_rate": 8.645454235739903e-06,
      "loss": 6.1072,
      "step": 23
    },
    {
      "epoch": 0.01423698650452321,
      "grad_norm": 4.370555400848389,
      "learning_rate": 2.1852399266194314e-06,
      "loss": 7.268,
      "step": 24
    },
    {
      "epoch": 0.01483019427554501,
      "grad_norm": 8.193671226501465,
      "learning_rate": 0.0,
      "loss": 7.2895,
      "step": 25
    },
    {
      "epoch": 0.01483019427554501,
      "eval_loss": 1.7055974006652832,
      "eval_runtime": 48.6257,
      "eval_samples_per_second": 14.601,
      "eval_steps_per_second": 7.301,
      "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": 828538324254720.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}