{
  "best_metric": 1.3223226070404053,
  "best_model_checkpoint": "miner_id_24/checkpoint-500",
  "epoch": 0.18392495861688432,
  "eval_steps": 50,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0003678499172337686,
      "eval_loss": 2.6280200481414795,
      "eval_runtime": 65.3457,
      "eval_samples_per_second": 17.522,
      "eval_steps_per_second": 4.392,
      "step": 1
    },
    {
      "epoch": 0.0036784991723376862,
      "grad_norm": 1.1987358331680298,
      "learning_rate": 4.02e-05,
      "loss": 2.5141,
      "step": 10
    },
    {
      "epoch": 0.0073569983446753725,
      "grad_norm": 1.3015245199203491,
      "learning_rate": 8.04e-05,
      "loss": 1.9684,
      "step": 20
    },
    {
      "epoch": 0.011035497517013059,
      "grad_norm": 1.007439136505127,
      "learning_rate": 0.0001206,
      "loss": 1.6286,
      "step": 30
    },
    {
      "epoch": 0.014713996689350745,
      "grad_norm": 1.1959398984909058,
      "learning_rate": 0.0001608,
      "loss": 1.5259,
      "step": 40
    },
    {
      "epoch": 0.01839249586168843,
      "grad_norm": 1.1850124597549438,
      "learning_rate": 0.000201,
      "loss": 1.373,
      "step": 50
    },
    {
      "epoch": 0.01839249586168843,
      "eval_loss": 1.5826470851898193,
      "eval_runtime": 65.3579,
      "eval_samples_per_second": 17.519,
      "eval_steps_per_second": 4.391,
      "step": 50
    },
    {
      "epoch": 0.022070995034026118,
      "grad_norm": 0.9022707939147949,
      "learning_rate": 0.00020075518705111234,
      "loss": 1.6254,
      "step": 60
    },
    {
      "epoch": 0.025749494206363802,
      "grad_norm": 0.8804805874824524,
      "learning_rate": 0.00020002194090852784,
      "loss": 1.5379,
      "step": 70
    },
    {
      "epoch": 0.02942799337870149,
      "grad_norm": 0.9261283874511719,
      "learning_rate": 0.00019880383387374748,
      "loss": 1.4729,
      "step": 80
    },
    {
      "epoch": 0.033106492551039174,
      "grad_norm": 0.9060719013214111,
      "learning_rate": 0.00019710680044180106,
      "loss": 1.4268,
      "step": 90
    },
    {
      "epoch": 0.03678499172337686,
      "grad_norm": 1.1774567365646362,
      "learning_rate": 0.0001949391083889838,
      "loss": 1.383,
      "step": 100
    },
    {
      "epoch": 0.03678499172337686,
      "eval_loss": 1.49298894405365,
      "eval_runtime": 65.3303,
      "eval_samples_per_second": 17.526,
      "eval_steps_per_second": 4.393,
      "step": 100
    },
    {
      "epoch": 0.04046349089571455,
      "grad_norm": 0.8449574708938599,
      "learning_rate": 0.00019231131849308138,
      "loss": 1.5649,
      "step": 110
    },
    {
      "epoch": 0.044141990068052236,
      "grad_norm": 0.9605708718299866,
      "learning_rate": 0.00018923623308232218,
      "loss": 1.4462,
      "step": 120
    },
    {
      "epoch": 0.047820489240389924,
      "grad_norm": 0.93846595287323,
      "learning_rate": 0.00018572883366372081,
      "loss": 1.4542,
      "step": 130
    },
    {
      "epoch": 0.051498988412727605,
      "grad_norm": 0.9066504240036011,
      "learning_rate": 0.00018180620793468224,
      "loss": 1.3955,
      "step": 140
    },
    {
      "epoch": 0.05517748758506529,
      "grad_norm": 1.112593412399292,
      "learning_rate": 0.00017748746653345728,
      "loss": 1.3078,
      "step": 150
    },
    {
      "epoch": 0.05517748758506529,
      "eval_loss": 1.4784965515136719,
      "eval_runtime": 65.2041,
      "eval_samples_per_second": 17.56,
      "eval_steps_per_second": 4.402,
      "step": 150
    },
    {
      "epoch": 0.05885598675740298,
      "grad_norm": 0.8634781241416931,
      "learning_rate": 0.00017279364993403443,
      "loss": 1.5365,
      "step": 160
    },
    {
      "epoch": 0.06253448592974066,
      "grad_norm": 0.8469012975692749,
      "learning_rate": 0.00016774762593906525,
      "loss": 1.532,
      "step": 170
    },
    {
      "epoch": 0.06621298510207835,
      "grad_norm": 0.8828918933868408,
      "learning_rate": 0.00016237397827022866,
      "loss": 1.3797,
      "step": 180
    },
    {
      "epoch": 0.06989148427441604,
      "grad_norm": 0.946323037147522,
      "learning_rate": 0.00015669888679881007,
      "loss": 1.3311,
      "step": 190
    },
    {
      "epoch": 0.07356998344675372,
      "grad_norm": 1.0333322286605835,
      "learning_rate": 0.00015075,
      "loss": 1.2819,
      "step": 200
    },
    {
      "epoch": 0.07356998344675372,
      "eval_loss": 1.464486837387085,
      "eval_runtime": 65.2426,
      "eval_samples_per_second": 17.55,
      "eval_steps_per_second": 4.399,
      "step": 200
    },
    {
      "epoch": 0.07724848261909141,
      "grad_norm": 0.7752374410629272,
      "learning_rate": 0.00014455630025230227,
      "loss": 1.4851,
      "step": 210
    },
    {
      "epoch": 0.0809269817914291,
      "grad_norm": 0.8208135366439819,
      "learning_rate": 0.00013814796263829918,
      "loss": 1.4285,
      "step": 220
    },
    {
      "epoch": 0.08460548096376679,
      "grad_norm": 0.8817787766456604,
      "learning_rate": 0.00013155620793468223,
      "loss": 1.4044,
      "step": 230
    },
    {
      "epoch": 0.08828398013610447,
      "grad_norm": 0.9041736721992493,
      "learning_rate": 0.0001248131505077666,
      "loss": 1.3384,
      "step": 240
    },
    {
      "epoch": 0.09196247930844216,
      "grad_norm": 1.0417087078094482,
      "learning_rate": 0.00011795164185552652,
      "loss": 1.2472,
      "step": 250
    },
    {
      "epoch": 0.09196247930844216,
      "eval_loss": 1.4156577587127686,
      "eval_runtime": 65.2226,
      "eval_samples_per_second": 17.555,
      "eval_steps_per_second": 4.4,
      "step": 250
    },
    {
      "epoch": 0.09564097848077985,
      "grad_norm": 0.7598959803581238,
      "learning_rate": 0.00011100511055839919,
      "loss": 1.5345,
      "step": 260
    },
    {
      "epoch": 0.09931947765311752,
      "grad_norm": 0.8524409532546997,
      "learning_rate": 0.00010400739941860137,
      "loss": 1.4252,
      "step": 270
    },
    {
      "epoch": 0.10299797682545521,
      "grad_norm": 0.8304363489151001,
      "learning_rate": 9.699260058139868e-05,
      "loss": 1.3754,
      "step": 280
    },
    {
      "epoch": 0.1066764759977929,
      "grad_norm": 0.8965967893600464,
      "learning_rate": 8.999488944160085e-05,
      "loss": 1.3527,
      "step": 290
    },
    {
      "epoch": 0.11035497517013058,
      "grad_norm": 1.1299211978912354,
      "learning_rate": 8.30483581444735e-05,
      "loss": 1.2001,
      "step": 300
    },
    {
      "epoch": 0.11035497517013058,
      "eval_loss": 1.3858033418655396,
      "eval_runtime": 65.2702,
      "eval_samples_per_second": 17.542,
      "eval_steps_per_second": 4.397,
      "step": 300
    },
    {
      "epoch": 0.11403347434246827,
      "grad_norm": 0.7235912084579468,
      "learning_rate": 7.618684949223341e-05,
      "loss": 1.4786,
      "step": 310
    },
    {
      "epoch": 0.11771197351480596,
      "grad_norm": 0.7429346442222595,
      "learning_rate": 6.94437920653178e-05,
      "loss": 1.4647,
      "step": 320
    },
    {
      "epoch": 0.12139047268714365,
      "grad_norm": 0.7758382558822632,
      "learning_rate": 6.285203736170084e-05,
      "loss": 1.3835,
      "step": 330
    },
    {
      "epoch": 0.12506897185948132,
      "grad_norm": 0.7685598731040955,
      "learning_rate": 5.6443699747697714e-05,
      "loss": 1.2376,
      "step": 340
    },
    {
      "epoch": 0.12874747103181902,
      "grad_norm": 1.1454414129257202,
      "learning_rate": 5.025000000000002e-05,
      "loss": 1.2399,
      "step": 350
    },
    {
      "epoch": 0.12874747103181902,
      "eval_loss": 1.359244704246521,
      "eval_runtime": 65.2526,
      "eval_samples_per_second": 17.547,
      "eval_steps_per_second": 4.398,
      "step": 350
    },
    {
      "epoch": 0.1324259702041567,
      "grad_norm": 0.766905665397644,
      "learning_rate": 4.430111320118996e-05,
      "loss": 1.451,
      "step": 360
    },
    {
      "epoch": 0.1361044693764944,
      "grad_norm": 0.7716265916824341,
      "learning_rate": 3.862602172977134e-05,
      "loss": 1.4025,
      "step": 370
    },
    {
      "epoch": 0.13978296854883207,
      "grad_norm": 0.7445082664489746,
      "learning_rate": 3.325237406093478e-05,
      "loss": 1.2896,
      "step": 380
    },
    {
      "epoch": 0.14346146772116977,
      "grad_norm": 0.8825977444648743,
      "learning_rate": 2.820635006596558e-05,
      "loss": 1.3365,
      "step": 390
    },
    {
      "epoch": 0.14713996689350745,
      "grad_norm": 1.0006340742111206,
      "learning_rate": 2.351253346654272e-05,
      "loss": 1.2482,
      "step": 400
    },
    {
      "epoch": 0.14713996689350745,
      "eval_loss": 1.332943081855774,
      "eval_runtime": 65.309,
      "eval_samples_per_second": 17.532,
      "eval_steps_per_second": 4.394,
      "step": 400
    },
    {
      "epoch": 0.15081846606584515,
      "grad_norm": 0.7437165975570679,
      "learning_rate": 1.9193792065317794e-05,
      "loss": 1.4276,
      "step": 410
    },
    {
      "epoch": 0.15449696523818282,
      "grad_norm": 0.7779045701026917,
      "learning_rate": 1.5271166336279193e-05,
      "loss": 1.3726,
      "step": 420
    },
    {
      "epoch": 0.1581754644105205,
      "grad_norm": 0.8055436611175537,
      "learning_rate": 1.1763766917677837e-05,
      "loss": 1.3318,
      "step": 430
    },
    {
      "epoch": 0.1618539635828582,
      "grad_norm": 0.8085871338844299,
      "learning_rate": 8.688681506918602e-06,
      "loss": 1.2827,
      "step": 440
    },
    {
      "epoch": 0.16553246275519587,
      "grad_norm": 0.9300590753555298,
      "learning_rate": 6.060891611016215e-06,
      "loss": 1.2341,
      "step": 450
    },
    {
      "epoch": 0.16553246275519587,
      "eval_loss": 1.3241080045700073,
      "eval_runtime": 65.4316,
      "eval_samples_per_second": 17.499,
      "eval_steps_per_second": 4.386,
      "step": 450
    },
    {
      "epoch": 0.16921096192753357,
      "grad_norm": 0.7751836776733398,
      "learning_rate": 3.893199558198952e-06,
      "loss": 1.4373,
      "step": 460
    },
    {
      "epoch": 0.17288946109987124,
      "grad_norm": 0.7827539443969727,
      "learning_rate": 2.1961661262525285e-06,
      "loss": 1.3386,
      "step": 470
    },
    {
      "epoch": 0.17656796027220895,
      "grad_norm": 0.7729030847549438,
      "learning_rate": 9.780590914721787e-07,
      "loss": 1.3196,
      "step": 480
    },
    {
      "epoch": 0.18024645944454662,
      "grad_norm": 0.8775790333747864,
      "learning_rate": 2.4481294888766817e-07,
      "loss": 1.2671,
      "step": 490
    },
    {
      "epoch": 0.18392495861688432,
      "grad_norm": 1.0807873010635376,
      "learning_rate": 0.0,
      "loss": 1.2471,
      "step": 500
    },
    {
      "epoch": 0.18392495861688432,
      "eval_loss": 1.3223226070404053,
      "eval_runtime": 65.3468,
      "eval_samples_per_second": 17.522,
      "eval_steps_per_second": 4.392,
      "step": 500
    }
  ],
  "logging_steps": 10,
  "max_steps": 500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "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": 8.886804283392e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}