{
  "best_metric": 10.300241470336914,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 1.9138755980861244,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.019138755980861243,
      "grad_norm": 0.4266333281993866,
      "learning_rate": 1e-05,
      "loss": 10.3784,
      "step": 1
    },
    {
      "epoch": 0.019138755980861243,
      "eval_loss": 10.377665519714355,
      "eval_runtime": 0.2079,
      "eval_samples_per_second": 423.375,
      "eval_steps_per_second": 105.844,
      "step": 1
    },
    {
      "epoch": 0.03827751196172249,
      "grad_norm": 0.4478803873062134,
      "learning_rate": 2e-05,
      "loss": 10.3778,
      "step": 2
    },
    {
      "epoch": 0.05741626794258373,
      "grad_norm": 0.41060081124305725,
      "learning_rate": 3e-05,
      "loss": 10.3799,
      "step": 3
    },
    {
      "epoch": 0.07655502392344497,
      "grad_norm": 0.3675904870033264,
      "learning_rate": 4e-05,
      "loss": 10.3776,
      "step": 4
    },
    {
      "epoch": 0.09569377990430622,
      "grad_norm": 0.3921853303909302,
      "learning_rate": 5e-05,
      "loss": 10.3772,
      "step": 5
    },
    {
      "epoch": 0.11483253588516747,
      "grad_norm": 0.4090043306350708,
      "learning_rate": 6e-05,
      "loss": 10.3755,
      "step": 6
    },
    {
      "epoch": 0.1339712918660287,
      "grad_norm": 0.39872977137565613,
      "learning_rate": 7e-05,
      "loss": 10.3738,
      "step": 7
    },
    {
      "epoch": 0.15311004784688995,
      "grad_norm": 0.38402482867240906,
      "learning_rate": 8e-05,
      "loss": 10.3735,
      "step": 8
    },
    {
      "epoch": 0.1722488038277512,
      "grad_norm": 0.3583473861217499,
      "learning_rate": 9e-05,
      "loss": 10.3738,
      "step": 9
    },
    {
      "epoch": 0.19138755980861244,
      "grad_norm": 0.3627314865589142,
      "learning_rate": 0.0001,
      "loss": 10.3702,
      "step": 10
    },
    {
      "epoch": 0.21052631578947367,
      "grad_norm": 0.42793917655944824,
      "learning_rate": 9.99885820390154e-05,
      "loss": 10.3661,
      "step": 11
    },
    {
      "epoch": 0.22966507177033493,
      "grad_norm": 0.39294254779815674,
      "learning_rate": 9.995433337085491e-05,
      "loss": 10.3655,
      "step": 12
    },
    {
      "epoch": 0.24880382775119617,
      "grad_norm": 0.3837736248970032,
      "learning_rate": 9.989726963751682e-05,
      "loss": 10.3663,
      "step": 13
    },
    {
      "epoch": 0.2679425837320574,
      "grad_norm": 0.5134721994400024,
      "learning_rate": 9.981741690106034e-05,
      "loss": 10.359,
      "step": 14
    },
    {
      "epoch": 0.28708133971291866,
      "grad_norm": 0.5079248547554016,
      "learning_rate": 9.971481163170268e-05,
      "loss": 10.3572,
      "step": 15
    },
    {
      "epoch": 0.3062200956937799,
      "grad_norm": 0.5069385766983032,
      "learning_rate": 9.95895006911623e-05,
      "loss": 10.3597,
      "step": 16
    },
    {
      "epoch": 0.3253588516746411,
      "grad_norm": 0.47848770022392273,
      "learning_rate": 9.944154131125642e-05,
      "loss": 10.355,
      "step": 17
    },
    {
      "epoch": 0.3444976076555024,
      "grad_norm": 0.5119503140449524,
      "learning_rate": 9.927100106776212e-05,
      "loss": 10.353,
      "step": 18
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 0.46988987922668457,
      "learning_rate": 9.907795784955327e-05,
      "loss": 10.3484,
      "step": 19
    },
    {
      "epoch": 0.3827751196172249,
      "grad_norm": 0.5642258524894714,
      "learning_rate": 9.88624998230272e-05,
      "loss": 10.3472,
      "step": 20
    },
    {
      "epoch": 0.4019138755980861,
      "grad_norm": 0.47275394201278687,
      "learning_rate": 9.862472539183756e-05,
      "loss": 10.3452,
      "step": 21
    },
    {
      "epoch": 0.42105263157894735,
      "grad_norm": 0.4831475019454956,
      "learning_rate": 9.836474315195147e-05,
      "loss": 10.342,
      "step": 22
    },
    {
      "epoch": 0.44019138755980863,
      "grad_norm": 0.4092586636543274,
      "learning_rate": 9.808267184205183e-05,
      "loss": 10.3422,
      "step": 23
    },
    {
      "epoch": 0.45933014354066987,
      "grad_norm": 0.46105170249938965,
      "learning_rate": 9.777864028930705e-05,
      "loss": 10.336,
      "step": 24
    },
    {
      "epoch": 0.4784688995215311,
      "grad_norm": 0.4268898069858551,
      "learning_rate": 9.745278735053343e-05,
      "loss": 10.333,
      "step": 25
    },
    {
      "epoch": 0.49760765550239233,
      "grad_norm": 0.3566943109035492,
      "learning_rate": 9.710526184877667e-05,
      "loss": 10.335,
      "step": 26
    },
    {
      "epoch": 0.5167464114832536,
      "grad_norm": 0.40495947003364563,
      "learning_rate": 9.673622250534156e-05,
      "loss": 10.3247,
      "step": 27
    },
    {
      "epoch": 0.5358851674641149,
      "grad_norm": 0.38109859824180603,
      "learning_rate": 9.63458378673011e-05,
      "loss": 10.3239,
      "step": 28
    },
    {
      "epoch": 0.5550239234449761,
      "grad_norm": 0.36544325947761536,
      "learning_rate": 9.593428623051792e-05,
      "loss": 10.3227,
      "step": 29
    },
    {
      "epoch": 0.5741626794258373,
      "grad_norm": 0.36144474148750305,
      "learning_rate": 9.550175555821333e-05,
      "loss": 10.3243,
      "step": 30
    },
    {
      "epoch": 0.5933014354066986,
      "grad_norm": 0.3017820715904236,
      "learning_rate": 9.504844339512095e-05,
      "loss": 10.3222,
      "step": 31
    },
    {
      "epoch": 0.6124401913875598,
      "grad_norm": 0.25235190987586975,
      "learning_rate": 9.457455677726448e-05,
      "loss": 10.3197,
      "step": 32
    },
    {
      "epoch": 0.631578947368421,
      "grad_norm": 0.270778626203537,
      "learning_rate": 9.408031213740045e-05,
      "loss": 10.3177,
      "step": 33
    },
    {
      "epoch": 0.6507177033492823,
      "grad_norm": 0.22615878283977509,
      "learning_rate": 9.356593520616948e-05,
      "loss": 10.3199,
      "step": 34
    },
    {
      "epoch": 0.6698564593301436,
      "grad_norm": 0.18281053006649017,
      "learning_rate": 9.303166090900082e-05,
      "loss": 10.319,
      "step": 35
    },
    {
      "epoch": 0.6889952153110048,
      "grad_norm": 0.1660808026790619,
      "learning_rate": 9.24777332588177e-05,
      "loss": 10.3191,
      "step": 36
    },
    {
      "epoch": 0.7081339712918661,
      "grad_norm": 0.19208800792694092,
      "learning_rate": 9.190440524459203e-05,
      "loss": 10.3193,
      "step": 37
    },
    {
      "epoch": 0.7272727272727273,
      "grad_norm": 0.1481315642595291,
      "learning_rate": 9.131193871579975e-05,
      "loss": 10.316,
      "step": 38
    },
    {
      "epoch": 0.7464114832535885,
      "grad_norm": 0.10044525563716888,
      "learning_rate": 9.070060426282925e-05,
      "loss": 10.3234,
      "step": 39
    },
    {
      "epoch": 0.7655502392344498,
      "grad_norm": 0.1636795997619629,
      "learning_rate": 9.007068109339784e-05,
      "loss": 10.3094,
      "step": 40
    },
    {
      "epoch": 0.784688995215311,
      "grad_norm": 0.1244809702038765,
      "learning_rate": 8.942245690503239e-05,
      "loss": 10.3069,
      "step": 41
    },
    {
      "epoch": 0.8038277511961722,
      "grad_norm": 0.1734219640493393,
      "learning_rate": 8.87562277536726e-05,
      "loss": 10.3117,
      "step": 42
    },
    {
      "epoch": 0.8229665071770335,
      "grad_norm": 0.12269428372383118,
      "learning_rate": 8.807229791845673e-05,
      "loss": 10.3143,
      "step": 43
    },
    {
      "epoch": 0.8421052631578947,
      "grad_norm": 0.1280500292778015,
      "learning_rate": 8.737097976275178e-05,
      "loss": 10.3103,
      "step": 44
    },
    {
      "epoch": 0.861244019138756,
      "grad_norm": 0.11635402590036392,
      "learning_rate": 8.665259359149132e-05,
      "loss": 10.3126,
      "step": 45
    },
    {
      "epoch": 0.8803827751196173,
      "grad_norm": 0.14325037598609924,
      "learning_rate": 8.591746750488639e-05,
      "loss": 10.3113,
      "step": 46
    },
    {
      "epoch": 0.8995215311004785,
      "grad_norm": 0.08365687727928162,
      "learning_rate": 8.516593724857598e-05,
      "loss": 10.3121,
      "step": 47
    },
    {
      "epoch": 0.9186602870813397,
      "grad_norm": 0.08075929433107376,
      "learning_rate": 8.439834606028594e-05,
      "loss": 10.3117,
      "step": 48
    },
    {
      "epoch": 0.937799043062201,
      "grad_norm": 0.09325200319290161,
      "learning_rate": 8.361504451306585e-05,
      "loss": 10.3172,
      "step": 49
    },
    {
      "epoch": 0.9569377990430622,
      "grad_norm": 0.07876553386449814,
      "learning_rate": 8.28163903551759e-05,
      "loss": 10.3132,
      "step": 50
    },
    {
      "epoch": 0.9569377990430622,
      "eval_loss": 10.310466766357422,
      "eval_runtime": 0.2053,
      "eval_samples_per_second": 428.635,
      "eval_steps_per_second": 107.159,
      "step": 50
    },
    {
      "epoch": 0.9760765550239234,
      "grad_norm": 0.08856772631406784,
      "learning_rate": 8.200274834669675e-05,
      "loss": 10.3106,
      "step": 51
    },
    {
      "epoch": 0.9952153110047847,
      "grad_norm": 0.09694826602935791,
      "learning_rate": 8.117449009293668e-05,
      "loss": 10.3171,
      "step": 52
    },
    {
      "epoch": 1.014354066985646,
      "grad_norm": 0.15517449378967285,
      "learning_rate": 8.033199387471277e-05,
      "loss": 18.3693,
      "step": 53
    },
    {
      "epoch": 1.0334928229665072,
      "grad_norm": 0.0667949989438057,
      "learning_rate": 7.9475644475583e-05,
      "loss": 10.0332,
      "step": 54
    },
    {
      "epoch": 1.0526315789473684,
      "grad_norm": 0.0705876350402832,
      "learning_rate": 7.860583300610849e-05,
      "loss": 10.3075,
      "step": 55
    },
    {
      "epoch": 1.0717703349282297,
      "grad_norm": 0.08071315288543701,
      "learning_rate": 7.772295672522615e-05,
      "loss": 10.3503,
      "step": 56
    },
    {
      "epoch": 1.0909090909090908,
      "grad_norm": 0.060574401170015335,
      "learning_rate": 7.682741885881315e-05,
      "loss": 10.2436,
      "step": 57
    },
    {
      "epoch": 1.1100478468899522,
      "grad_norm": 0.06491580605506897,
      "learning_rate": 7.591962841552627e-05,
      "loss": 10.377,
      "step": 58
    },
    {
      "epoch": 1.1291866028708135,
      "grad_norm": 0.08106613159179688,
      "learning_rate": 7.500000000000001e-05,
      "loss": 10.2996,
      "step": 59
    },
    {
      "epoch": 1.1483253588516746,
      "grad_norm": 0.08917899429798126,
      "learning_rate": 7.406895362348916e-05,
      "loss": 10.2626,
      "step": 60
    },
    {
      "epoch": 1.167464114832536,
      "grad_norm": 0.10297100991010666,
      "learning_rate": 7.312691451204178e-05,
      "loss": 10.3349,
      "step": 61
    },
    {
      "epoch": 1.186602870813397,
      "grad_norm": 0.07042112201452255,
      "learning_rate": 7.217431291229067e-05,
      "loss": 10.3964,
      "step": 62
    },
    {
      "epoch": 1.2057416267942584,
      "grad_norm": 0.07486451417207718,
      "learning_rate": 7.121158389495186e-05,
      "loss": 10.1931,
      "step": 63
    },
    {
      "epoch": 1.2248803827751196,
      "grad_norm": 0.09859184175729752,
      "learning_rate": 7.023916715611969e-05,
      "loss": 10.3828,
      "step": 64
    },
    {
      "epoch": 1.244019138755981,
      "grad_norm": 0.07667276263237,
      "learning_rate": 6.925750681644953e-05,
      "loss": 10.7305,
      "step": 65
    },
    {
      "epoch": 1.263157894736842,
      "grad_norm": 0.07506383955478668,
      "learning_rate": 6.826705121831976e-05,
      "loss": 10.1215,
      "step": 66
    },
    {
      "epoch": 1.2822966507177034,
      "grad_norm": 0.06321374326944351,
      "learning_rate": 6.726825272106538e-05,
      "loss": 10.0464,
      "step": 67
    },
    {
      "epoch": 1.3014354066985647,
      "grad_norm": 0.07606147229671478,
      "learning_rate": 6.626156749437736e-05,
      "loss": 10.3409,
      "step": 68
    },
    {
      "epoch": 1.3205741626794258,
      "grad_norm": 0.08716686069965363,
      "learning_rate": 6.524745530996137e-05,
      "loss": 10.3083,
      "step": 69
    },
    {
      "epoch": 1.339712918660287,
      "grad_norm": 0.07832231372594833,
      "learning_rate": 6.422637933155162e-05,
      "loss": 10.2791,
      "step": 70
    },
    {
      "epoch": 1.3588516746411483,
      "grad_norm": 0.09248408675193787,
      "learning_rate": 6.319880590337549e-05,
      "loss": 10.3614,
      "step": 71
    },
    {
      "epoch": 1.3779904306220097,
      "grad_norm": 0.08951514214277267,
      "learning_rate": 6.216520433716545e-05,
      "loss": 10.2633,
      "step": 72
    },
    {
      "epoch": 1.3971291866028708,
      "grad_norm": 0.08380934596061707,
      "learning_rate": 6.112604669781572e-05,
      "loss": 10.2203,
      "step": 73
    },
    {
      "epoch": 1.4162679425837321,
      "grad_norm": 0.08385058492422104,
      "learning_rate": 6.008180758778167e-05,
      "loss": 10.4143,
      "step": 74
    },
    {
      "epoch": 1.4354066985645932,
      "grad_norm": 0.07687491178512573,
      "learning_rate": 5.903296393031995e-05,
      "loss": 10.2941,
      "step": 75
    },
    {
      "epoch": 1.4545454545454546,
      "grad_norm": 0.07478059083223343,
      "learning_rate": 5.7979994751668964e-05,
      "loss": 10.2666,
      "step": 76
    },
    {
      "epoch": 1.4736842105263157,
      "grad_norm": 0.10892575234174728,
      "learning_rate": 5.69233809622687e-05,
      "loss": 10.3199,
      "step": 77
    },
    {
      "epoch": 1.492822966507177,
      "grad_norm": 0.09505303204059601,
      "learning_rate": 5.58636051371201e-05,
      "loss": 10.6274,
      "step": 78
    },
    {
      "epoch": 1.5119617224880382,
      "grad_norm": 0.09463223069906235,
      "learning_rate": 5.480115129538409e-05,
      "loss": 10.2876,
      "step": 79
    },
    {
      "epoch": 1.5311004784688995,
      "grad_norm": 0.08493571728467941,
      "learning_rate": 5.373650467932122e-05,
      "loss": 9.994,
      "step": 80
    },
    {
      "epoch": 1.5502392344497609,
      "grad_norm": 0.093894362449646,
      "learning_rate": 5.267015153267245e-05,
      "loss": 10.3278,
      "step": 81
    },
    {
      "epoch": 1.569377990430622,
      "grad_norm": 0.10776396840810776,
      "learning_rate": 5.1602578878582776e-05,
      "loss": 10.2704,
      "step": 82
    },
    {
      "epoch": 1.588516746411483,
      "grad_norm": 0.10382504016160965,
      "learning_rate": 5.053427429716867e-05,
      "loss": 10.2904,
      "step": 83
    },
    {
      "epoch": 1.6076555023923444,
      "grad_norm": 0.1062113493680954,
      "learning_rate": 4.9465725702831346e-05,
      "loss": 10.3657,
      "step": 84
    },
    {
      "epoch": 1.6267942583732058,
      "grad_norm": 0.12500600516796112,
      "learning_rate": 4.839742112141724e-05,
      "loss": 10.323,
      "step": 85
    },
    {
      "epoch": 1.6459330143540671,
      "grad_norm": 0.12947624921798706,
      "learning_rate": 4.732984846732755e-05,
      "loss": 10.2952,
      "step": 86
    },
    {
      "epoch": 1.6650717703349283,
      "grad_norm": 0.10035474598407745,
      "learning_rate": 4.626349532067879e-05,
      "loss": 10.2569,
      "step": 87
    },
    {
      "epoch": 1.6842105263157894,
      "grad_norm": 0.10493069142103195,
      "learning_rate": 4.5198848704615914e-05,
      "loss": 10.3804,
      "step": 88
    },
    {
      "epoch": 1.7033492822966507,
      "grad_norm": 0.09970294684171677,
      "learning_rate": 4.4136394862879914e-05,
      "loss": 10.2641,
      "step": 89
    },
    {
      "epoch": 1.722488038277512,
      "grad_norm": 0.1537674069404602,
      "learning_rate": 4.307661903773129e-05,
      "loss": 10.3269,
      "step": 90
    },
    {
      "epoch": 1.7416267942583732,
      "grad_norm": 0.1353168934583664,
      "learning_rate": 4.2020005248331054e-05,
      "loss": 10.7181,
      "step": 91
    },
    {
      "epoch": 1.7607655502392343,
      "grad_norm": 0.10454723984003067,
      "learning_rate": 4.096703606968006e-05,
      "loss": 10.1224,
      "step": 92
    },
    {
      "epoch": 1.7799043062200957,
      "grad_norm": 0.10816597938537598,
      "learning_rate": 3.991819241221835e-05,
      "loss": 10.0276,
      "step": 93
    },
    {
      "epoch": 1.799043062200957,
      "grad_norm": 0.12994703650474548,
      "learning_rate": 3.887395330218429e-05,
      "loss": 10.3349,
      "step": 94
    },
    {
      "epoch": 1.8181818181818183,
      "grad_norm": 0.1489221602678299,
      "learning_rate": 3.783479566283457e-05,
      "loss": 10.2663,
      "step": 95
    },
    {
      "epoch": 1.8373205741626795,
      "grad_norm": 0.11641079187393188,
      "learning_rate": 3.680119409662452e-05,
      "loss": 10.2685,
      "step": 96
    },
    {
      "epoch": 1.8564593301435406,
      "grad_norm": 0.13673876225948334,
      "learning_rate": 3.5773620668448384e-05,
      "loss": 10.3558,
      "step": 97
    },
    {
      "epoch": 1.875598086124402,
      "grad_norm": 0.1347990185022354,
      "learning_rate": 3.4752544690038647e-05,
      "loss": 10.2981,
      "step": 98
    },
    {
      "epoch": 1.8947368421052633,
      "grad_norm": 0.11974027007818222,
      "learning_rate": 3.373843250562265e-05,
      "loss": 10.2657,
      "step": 99
    },
    {
      "epoch": 1.9138755980861244,
      "grad_norm": 0.11552689224481583,
      "learning_rate": 3.273174727893463e-05,
      "loss": 10.3134,
      "step": 100
    },
    {
      "epoch": 1.9138755980861244,
      "eval_loss": 10.300241470336914,
      "eval_runtime": 0.2059,
      "eval_samples_per_second": 427.459,
      "eval_steps_per_second": 106.865,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 157,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "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": 11155066060800.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}