{
  "best_metric": 1.0175485610961914,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 3.077625570776256,
  "eval_steps": 25,
  "global_step": 41,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0730593607305936,
      "grad_norm": 0.29548144340515137,
      "learning_rate": 5e-05,
      "loss": 1.3786,
      "step": 1
    },
    {
      "epoch": 0.0730593607305936,
      "eval_loss": 1.349356770515442,
      "eval_runtime": 1.0825,
      "eval_samples_per_second": 85.91,
      "eval_steps_per_second": 11.085,
      "step": 1
    },
    {
      "epoch": 0.1461187214611872,
      "grad_norm": 0.35044535994529724,
      "learning_rate": 0.0001,
      "loss": 1.4178,
      "step": 2
    },
    {
      "epoch": 0.2191780821917808,
      "grad_norm": 0.41287845373153687,
      "learning_rate": 9.983786540671051e-05,
      "loss": 1.3877,
      "step": 3
    },
    {
      "epoch": 0.2922374429223744,
      "grad_norm": 0.2790428400039673,
      "learning_rate": 9.935251313189564e-05,
      "loss": 1.369,
      "step": 4
    },
    {
      "epoch": 0.365296803652968,
      "grad_norm": 0.2401568740606308,
      "learning_rate": 9.85470908713026e-05,
      "loss": 1.2693,
      "step": 5
    },
    {
      "epoch": 0.4383561643835616,
      "grad_norm": 0.2623854875564575,
      "learning_rate": 9.742682209735727e-05,
      "loss": 1.2273,
      "step": 6
    },
    {
      "epoch": 0.5114155251141552,
      "grad_norm": 0.21658743917942047,
      "learning_rate": 9.599897218294122e-05,
      "loss": 1.2046,
      "step": 7
    },
    {
      "epoch": 0.5844748858447488,
      "grad_norm": 0.1891045868396759,
      "learning_rate": 9.42728012826605e-05,
      "loss": 1.2187,
      "step": 8
    },
    {
      "epoch": 0.6575342465753424,
      "grad_norm": 0.19009070098400116,
      "learning_rate": 9.225950427718975e-05,
      "loss": 1.1461,
      "step": 9
    },
    {
      "epoch": 0.730593607305936,
      "grad_norm": 0.17477785050868988,
      "learning_rate": 8.997213817017507e-05,
      "loss": 1.1226,
      "step": 10
    },
    {
      "epoch": 0.8036529680365296,
      "grad_norm": 0.14510700106620789,
      "learning_rate": 8.742553740855506e-05,
      "loss": 1.1622,
      "step": 11
    },
    {
      "epoch": 0.8767123287671232,
      "grad_norm": 0.15029433369636536,
      "learning_rate": 8.463621767547998e-05,
      "loss": 1.0546,
      "step": 12
    },
    {
      "epoch": 0.9497716894977168,
      "grad_norm": 0.17502561211585999,
      "learning_rate": 8.162226877976887e-05,
      "loss": 1.029,
      "step": 13
    },
    {
      "epoch": 1.0502283105022832,
      "grad_norm": 0.29605159163475037,
      "learning_rate": 7.840323733655778e-05,
      "loss": 2.01,
      "step": 14
    },
    {
      "epoch": 1.1232876712328768,
      "grad_norm": 0.19562408328056335,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.0572,
      "step": 15
    },
    {
      "epoch": 1.1963470319634704,
      "grad_norm": 0.20722578465938568,
      "learning_rate": 7.143462807015271e-05,
      "loss": 1.0049,
      "step": 16
    },
    {
      "epoch": 1.269406392694064,
      "grad_norm": 0.17433689534664154,
      "learning_rate": 6.773024435212678e-05,
      "loss": 1.0219,
      "step": 17
    },
    {
      "epoch": 1.3424657534246576,
      "grad_norm": 0.1956247240304947,
      "learning_rate": 6.391087319582264e-05,
      "loss": 1.1233,
      "step": 18
    },
    {
      "epoch": 1.4155251141552512,
      "grad_norm": 0.1997087448835373,
      "learning_rate": 6.0001284688802226e-05,
      "loss": 1.0518,
      "step": 19
    },
    {
      "epoch": 1.4885844748858448,
      "grad_norm": 0.18689264357089996,
      "learning_rate": 5.602683401276615e-05,
      "loss": 0.927,
      "step": 20
    },
    {
      "epoch": 1.5616438356164384,
      "grad_norm": 0.19745905697345734,
      "learning_rate": 5.201329700547076e-05,
      "loss": 1.2331,
      "step": 21
    },
    {
      "epoch": 1.634703196347032,
      "grad_norm": 0.20087485015392303,
      "learning_rate": 4.798670299452926e-05,
      "loss": 1.0406,
      "step": 22
    },
    {
      "epoch": 1.7077625570776256,
      "grad_norm": 0.2027587890625,
      "learning_rate": 4.397316598723385e-05,
      "loss": 0.8635,
      "step": 23
    },
    {
      "epoch": 1.7808219178082192,
      "grad_norm": 0.19199872016906738,
      "learning_rate": 3.9998715311197785e-05,
      "loss": 1.256,
      "step": 24
    },
    {
      "epoch": 1.8538812785388128,
      "grad_norm": 0.19371041655540466,
      "learning_rate": 3.608912680417737e-05,
      "loss": 1.0406,
      "step": 25
    },
    {
      "epoch": 1.8538812785388128,
      "eval_loss": 1.0175485610961914,
      "eval_runtime": 1.0826,
      "eval_samples_per_second": 85.902,
      "eval_steps_per_second": 11.084,
      "step": 25
    },
    {
      "epoch": 1.9269406392694064,
      "grad_norm": 0.22027455270290375,
      "learning_rate": 3.226975564787322e-05,
      "loss": 1.0663,
      "step": 26
    },
    {
      "epoch": 2.0273972602739727,
      "grad_norm": 0.2542748749256134,
      "learning_rate": 2.8565371929847284e-05,
      "loss": 1.821,
      "step": 27
    },
    {
      "epoch": 2.1004566210045663,
      "grad_norm": 0.15314239263534546,
      "learning_rate": 2.500000000000001e-05,
      "loss": 1.0119,
      "step": 28
    },
    {
      "epoch": 2.17351598173516,
      "grad_norm": 0.16169950366020203,
      "learning_rate": 2.1596762663442218e-05,
      "loss": 1.0286,
      "step": 29
    },
    {
      "epoch": 2.2465753424657535,
      "grad_norm": 0.1641775369644165,
      "learning_rate": 1.837773122023114e-05,
      "loss": 0.9043,
      "step": 30
    },
    {
      "epoch": 2.319634703196347,
      "grad_norm": 0.16621926426887512,
      "learning_rate": 1.536378232452003e-05,
      "loss": 1.2029,
      "step": 31
    },
    {
      "epoch": 2.3926940639269407,
      "grad_norm": 0.1616508662700653,
      "learning_rate": 1.257446259144494e-05,
      "loss": 1.0547,
      "step": 32
    },
    {
      "epoch": 2.4657534246575343,
      "grad_norm": 0.1510113924741745,
      "learning_rate": 1.0027861829824952e-05,
      "loss": 0.8809,
      "step": 33
    },
    {
      "epoch": 2.538812785388128,
      "grad_norm": 0.1720770299434662,
      "learning_rate": 7.740495722810271e-06,
      "loss": 1.2133,
      "step": 34
    },
    {
      "epoch": 2.6118721461187215,
      "grad_norm": 0.1738651543855667,
      "learning_rate": 5.727198717339511e-06,
      "loss": 1.0364,
      "step": 35
    },
    {
      "epoch": 2.684931506849315,
      "grad_norm": 0.16424569487571716,
      "learning_rate": 4.001027817058789e-06,
      "loss": 0.9136,
      "step": 36
    },
    {
      "epoch": 2.7579908675799087,
      "grad_norm": 0.1603696048259735,
      "learning_rate": 2.573177902642726e-06,
      "loss": 1.1305,
      "step": 37
    },
    {
      "epoch": 2.8310502283105023,
      "grad_norm": 0.1709257960319519,
      "learning_rate": 1.4529091286973995e-06,
      "loss": 1.0569,
      "step": 38
    },
    {
      "epoch": 2.904109589041096,
      "grad_norm": 0.17874523997306824,
      "learning_rate": 6.474868681043578e-07,
      "loss": 1.0163,
      "step": 39
    },
    {
      "epoch": 3.0045662100456623,
      "grad_norm": 0.21786744892597198,
      "learning_rate": 1.6213459328950352e-07,
      "loss": 1.7187,
      "step": 40
    },
    {
      "epoch": 3.077625570776256,
      "grad_norm": 0.12653082609176636,
      "learning_rate": 0.0,
      "loss": 1.0884,
      "step": 41
    }
  ],
  "logging_steps": 1,
  "max_steps": 41,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 8.688198101866906e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}