{
  "best_metric": 2.924403190612793,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.5215123859191656,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.020860495436766623,
      "grad_norm": 9.733530044555664,
      "learning_rate": 5e-05,
      "loss": 6.9458,
      "step": 1
    },
    {
      "epoch": 0.020860495436766623,
      "eval_loss": 9.503127098083496,
      "eval_runtime": 2.0464,
      "eval_samples_per_second": 24.433,
      "eval_steps_per_second": 6.353,
      "step": 1
    },
    {
      "epoch": 0.041720990873533245,
      "grad_norm": 10.49179744720459,
      "learning_rate": 0.0001,
      "loss": 7.877,
      "step": 2
    },
    {
      "epoch": 0.06258148631029987,
      "grad_norm": 9.120818138122559,
      "learning_rate": 9.990365154573717e-05,
      "loss": 7.3715,
      "step": 3
    },
    {
      "epoch": 0.08344198174706649,
      "grad_norm": 6.438422203063965,
      "learning_rate": 9.961501876182148e-05,
      "loss": 6.5731,
      "step": 4
    },
    {
      "epoch": 0.10430247718383312,
      "grad_norm": 6.40809965133667,
      "learning_rate": 9.913533761814537e-05,
      "loss": 6.0948,
      "step": 5
    },
    {
      "epoch": 0.12516297262059975,
      "grad_norm": 7.464506149291992,
      "learning_rate": 9.846666218300807e-05,
      "loss": 5.9117,
      "step": 6
    },
    {
      "epoch": 0.14602346805736635,
      "grad_norm": 7.578457832336426,
      "learning_rate": 9.761185582727977e-05,
      "loss": 5.5103,
      "step": 7
    },
    {
      "epoch": 0.16688396349413298,
      "grad_norm": 6.015934944152832,
      "learning_rate": 9.657457896300791e-05,
      "loss": 5.5119,
      "step": 8
    },
    {
      "epoch": 0.1877444589308996,
      "grad_norm": 11.263550758361816,
      "learning_rate": 9.535927336897098e-05,
      "loss": 4.9997,
      "step": 9
    },
    {
      "epoch": 0.20860495436766624,
      "grad_norm": 12.682040214538574,
      "learning_rate": 9.397114317029975e-05,
      "loss": 3.9157,
      "step": 10
    },
    {
      "epoch": 0.22946544980443284,
      "grad_norm": 16.877872467041016,
      "learning_rate": 9.241613255361455e-05,
      "loss": 3.5108,
      "step": 11
    },
    {
      "epoch": 0.2503259452411995,
      "grad_norm": 20.40404510498047,
      "learning_rate": 9.070090031310558e-05,
      "loss": 5.0812,
      "step": 12
    },
    {
      "epoch": 0.2711864406779661,
      "grad_norm": 14.97578239440918,
      "learning_rate": 8.883279133655399e-05,
      "loss": 4.9984,
      "step": 13
    },
    {
      "epoch": 0.2920469361147327,
      "grad_norm": 6.86972713470459,
      "learning_rate": 8.681980515339464e-05,
      "loss": 4.5982,
      "step": 14
    },
    {
      "epoch": 0.31290743155149936,
      "grad_norm": 4.815412998199463,
      "learning_rate": 8.467056167950311e-05,
      "loss": 4.3926,
      "step": 15
    },
    {
      "epoch": 0.33376792698826596,
      "grad_norm": 4.70793342590332,
      "learning_rate": 8.239426430539243e-05,
      "loss": 4.336,
      "step": 16
    },
    {
      "epoch": 0.3546284224250326,
      "grad_norm": 4.900488376617432,
      "learning_rate": 8.000066048588211e-05,
      "loss": 3.998,
      "step": 17
    },
    {
      "epoch": 0.3754889178617992,
      "grad_norm": 4.3667521476745605,
      "learning_rate": 7.75e-05,
      "loss": 4.0995,
      "step": 18
    },
    {
      "epoch": 0.3963494132985658,
      "grad_norm": 3.6821374893188477,
      "learning_rate": 7.490299105985507e-05,
      "loss": 4.1878,
      "step": 19
    },
    {
      "epoch": 0.4172099087353325,
      "grad_norm": 3.6842868328094482,
      "learning_rate": 7.222075445642904e-05,
      "loss": 3.901,
      "step": 20
    },
    {
      "epoch": 0.4380704041720991,
      "grad_norm": 3.5541388988494873,
      "learning_rate": 6.946477593864228e-05,
      "loss": 2.8489,
      "step": 21
    },
    {
      "epoch": 0.4589308996088657,
      "grad_norm": 4.352834701538086,
      "learning_rate": 6.664685702961344e-05,
      "loss": 0.6377,
      "step": 22
    },
    {
      "epoch": 0.47979139504563234,
      "grad_norm": 4.775582790374756,
      "learning_rate": 6.377906449072578e-05,
      "loss": 0.4793,
      "step": 23
    },
    {
      "epoch": 0.500651890482399,
      "grad_norm": 4.74364709854126,
      "learning_rate": 6.087367864990233e-05,
      "loss": 3.8634,
      "step": 24
    },
    {
      "epoch": 0.5215123859191656,
      "grad_norm": 4.812182426452637,
      "learning_rate": 5.794314081535644e-05,
      "loss": 3.4721,
      "step": 25
    },
    {
      "epoch": 0.5215123859191656,
      "eval_loss": 2.924403190612793,
      "eval_runtime": 2.0621,
      "eval_samples_per_second": 24.248,
      "eval_steps_per_second": 6.304,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 25,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 8.1240447254528e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}