{
  "best_metric": 1.4572163820266724,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.021482277121374866,
  "eval_steps": 5,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0008592910848549946,
      "grad_norm": 0.1270437240600586,
      "learning_rate": 2e-05,
      "loss": 1.5391,
      "step": 1
    },
    {
      "epoch": 0.0008592910848549946,
      "eval_loss": 1.5906188488006592,
      "eval_runtime": 45.4207,
      "eval_samples_per_second": 10.788,
      "eval_steps_per_second": 5.394,
      "step": 1
    },
    {
      "epoch": 0.0017185821697099893,
      "grad_norm": 0.14911828935146332,
      "learning_rate": 4e-05,
      "loss": 1.5235,
      "step": 2
    },
    {
      "epoch": 0.0025778732545649837,
      "grad_norm": 0.13913476467132568,
      "learning_rate": 6e-05,
      "loss": 1.5497,
      "step": 3
    },
    {
      "epoch": 0.0034371643394199786,
      "grad_norm": 0.14412061870098114,
      "learning_rate": 8e-05,
      "loss": 1.6657,
      "step": 4
    },
    {
      "epoch": 0.004296455424274973,
      "grad_norm": 0.1414536088705063,
      "learning_rate": 0.0001,
      "loss": 1.6289,
      "step": 5
    },
    {
      "epoch": 0.004296455424274973,
      "eval_loss": 1.5890724658966064,
      "eval_runtime": 44.8032,
      "eval_samples_per_second": 10.937,
      "eval_steps_per_second": 5.468,
      "step": 5
    },
    {
      "epoch": 0.0051557465091299675,
      "grad_norm": 0.15352720022201538,
      "learning_rate": 0.00012,
      "loss": 1.6763,
      "step": 6
    },
    {
      "epoch": 0.006015037593984963,
      "grad_norm": 0.14356131851673126,
      "learning_rate": 0.00014,
      "loss": 1.4288,
      "step": 7
    },
    {
      "epoch": 0.006874328678839957,
      "grad_norm": 0.15954053401947021,
      "learning_rate": 0.00016,
      "loss": 1.591,
      "step": 8
    },
    {
      "epoch": 0.007733619763694952,
      "grad_norm": 0.1504104733467102,
      "learning_rate": 0.00018,
      "loss": 1.5244,
      "step": 9
    },
    {
      "epoch": 0.008592910848549946,
      "grad_norm": 0.16843052208423615,
      "learning_rate": 0.0002,
      "loss": 1.5883,
      "step": 10
    },
    {
      "epoch": 0.008592910848549946,
      "eval_loss": 1.558466911315918,
      "eval_runtime": 46.5267,
      "eval_samples_per_second": 10.532,
      "eval_steps_per_second": 5.266,
      "step": 10
    },
    {
      "epoch": 0.00945220193340494,
      "grad_norm": 0.17917290329933167,
      "learning_rate": 0.00019781476007338058,
      "loss": 1.5504,
      "step": 11
    },
    {
      "epoch": 0.010311493018259935,
      "grad_norm": 0.1752149611711502,
      "learning_rate": 0.0001913545457642601,
      "loss": 1.5564,
      "step": 12
    },
    {
      "epoch": 0.01117078410311493,
      "grad_norm": 0.18790920078754425,
      "learning_rate": 0.00018090169943749476,
      "loss": 1.578,
      "step": 13
    },
    {
      "epoch": 0.012030075187969926,
      "grad_norm": 0.17092998325824738,
      "learning_rate": 0.00016691306063588583,
      "loss": 1.3762,
      "step": 14
    },
    {
      "epoch": 0.01288936627282492,
      "grad_norm": 0.17537423968315125,
      "learning_rate": 0.00015000000000000001,
      "loss": 1.5093,
      "step": 15
    },
    {
      "epoch": 0.01288936627282492,
      "eval_loss": 1.4965424537658691,
      "eval_runtime": 44.9338,
      "eval_samples_per_second": 10.905,
      "eval_steps_per_second": 5.452,
      "step": 15
    },
    {
      "epoch": 0.013748657357679914,
      "grad_norm": 0.16586551070213318,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.4224,
      "step": 16
    },
    {
      "epoch": 0.014607948442534909,
      "grad_norm": 0.18348799645900726,
      "learning_rate": 0.00011045284632676536,
      "loss": 1.6179,
      "step": 17
    },
    {
      "epoch": 0.015467239527389903,
      "grad_norm": 0.19045992195606232,
      "learning_rate": 8.954715367323468e-05,
      "loss": 1.459,
      "step": 18
    },
    {
      "epoch": 0.0163265306122449,
      "grad_norm": 0.19004923105239868,
      "learning_rate": 6.909830056250527e-05,
      "loss": 1.4926,
      "step": 19
    },
    {
      "epoch": 0.017185821697099892,
      "grad_norm": 0.205982506275177,
      "learning_rate": 5.000000000000002e-05,
      "loss": 1.4912,
      "step": 20
    },
    {
      "epoch": 0.017185821697099892,
      "eval_loss": 1.4640228748321533,
      "eval_runtime": 44.5134,
      "eval_samples_per_second": 11.008,
      "eval_steps_per_second": 5.504,
      "step": 20
    },
    {
      "epoch": 0.01804511278195489,
      "grad_norm": 0.1899358034133911,
      "learning_rate": 3.308693936411421e-05,
      "loss": 1.3502,
      "step": 21
    },
    {
      "epoch": 0.01890440386680988,
      "grad_norm": 0.18288901448249817,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 1.4681,
      "step": 22
    },
    {
      "epoch": 0.019763694951664877,
      "grad_norm": 0.18912482261657715,
      "learning_rate": 8.645454235739903e-06,
      "loss": 1.4683,
      "step": 23
    },
    {
      "epoch": 0.02062298603651987,
      "grad_norm": 0.21653838455677032,
      "learning_rate": 2.1852399266194314e-06,
      "loss": 1.4228,
      "step": 24
    },
    {
      "epoch": 0.021482277121374866,
      "grad_norm": 0.20494642853736877,
      "learning_rate": 0.0,
      "loss": 1.4457,
      "step": 25
    },
    {
      "epoch": 0.021482277121374866,
      "eval_loss": 1.4572163820266724,
      "eval_runtime": 44.5699,
      "eval_samples_per_second": 10.994,
      "eval_steps_per_second": 5.497,
      "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": 1278959891251200.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}