{
  "best_metric": 0.9635820582698403,
  "best_model_checkpoint": "./distilbert_multilingual_cased_greek_latin_classifiergreek/checkpoint-14160",
  "epoch": 8.0,
  "eval_steps": 500,
  "global_step": 14160,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05649717514124294,
      "grad_norm": 9.908761978149414,
      "learning_rate": 4.9858757062146896e-05,
      "loss": 0.4326,
      "step": 100
    },
    {
      "epoch": 0.11299435028248588,
      "grad_norm": 0.47730961441993713,
      "learning_rate": 4.971751412429379e-05,
      "loss": 0.2915,
      "step": 200
    },
    {
      "epoch": 0.1694915254237288,
      "grad_norm": 5.969715595245361,
      "learning_rate": 4.957627118644068e-05,
      "loss": 0.2426,
      "step": 300
    },
    {
      "epoch": 0.22598870056497175,
      "grad_norm": 2.764862537384033,
      "learning_rate": 4.9435028248587575e-05,
      "loss": 0.256,
      "step": 400
    },
    {
      "epoch": 0.2824858757062147,
      "grad_norm": 12.726994514465332,
      "learning_rate": 4.929378531073446e-05,
      "loss": 0.2165,
      "step": 500
    },
    {
      "epoch": 0.3389830508474576,
      "grad_norm": 1.1394743919372559,
      "learning_rate": 4.915254237288136e-05,
      "loss": 0.2168,
      "step": 600
    },
    {
      "epoch": 0.3954802259887006,
      "grad_norm": 4.321178913116455,
      "learning_rate": 4.9011299435028255e-05,
      "loss": 0.2059,
      "step": 700
    },
    {
      "epoch": 0.4519774011299435,
      "grad_norm": 18.238351821899414,
      "learning_rate": 4.887005649717514e-05,
      "loss": 0.2294,
      "step": 800
    },
    {
      "epoch": 0.5084745762711864,
      "grad_norm": 7.210486888885498,
      "learning_rate": 4.8728813559322034e-05,
      "loss": 0.1904,
      "step": 900
    },
    {
      "epoch": 0.5649717514124294,
      "grad_norm": 1.240628719329834,
      "learning_rate": 4.8587570621468934e-05,
      "loss": 0.1668,
      "step": 1000
    },
    {
      "epoch": 0.6214689265536724,
      "grad_norm": 9.029092788696289,
      "learning_rate": 4.844632768361582e-05,
      "loss": 0.18,
      "step": 1100
    },
    {
      "epoch": 0.6779661016949152,
      "grad_norm": 4.866886615753174,
      "learning_rate": 4.8305084745762714e-05,
      "loss": 0.2082,
      "step": 1200
    },
    {
      "epoch": 0.7344632768361582,
      "grad_norm": 7.6279778480529785,
      "learning_rate": 4.816384180790961e-05,
      "loss": 0.1818,
      "step": 1300
    },
    {
      "epoch": 0.7909604519774012,
      "grad_norm": 8.820233345031738,
      "learning_rate": 4.80225988700565e-05,
      "loss": 0.1853,
      "step": 1400
    },
    {
      "epoch": 0.847457627118644,
      "grad_norm": 22.571056365966797,
      "learning_rate": 4.788135593220339e-05,
      "loss": 0.1638,
      "step": 1500
    },
    {
      "epoch": 0.903954802259887,
      "grad_norm": 4.86266565322876,
      "learning_rate": 4.7740112994350286e-05,
      "loss": 0.1761,
      "step": 1600
    },
    {
      "epoch": 0.96045197740113,
      "grad_norm": 2.2481741905212402,
      "learning_rate": 4.759887005649718e-05,
      "loss": 0.1481,
      "step": 1700
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9473554127533367,
      "eval_f1": 0.9471867274372374,
      "eval_loss": 0.15506704151630402,
      "eval_runtime": 0.99,
      "eval_samples_per_second": 4086.911,
      "eval_steps_per_second": 64.647,
      "step": 1770
    },
    {
      "epoch": 1.0169491525423728,
      "grad_norm": 0.16318374872207642,
      "learning_rate": 4.745762711864407e-05,
      "loss": 0.1303,
      "step": 1800
    },
    {
      "epoch": 1.073446327683616,
      "grad_norm": 2.8574020862579346,
      "learning_rate": 4.7316384180790966e-05,
      "loss": 0.0916,
      "step": 1900
    },
    {
      "epoch": 1.1299435028248588,
      "grad_norm": 7.220451831817627,
      "learning_rate": 4.717514124293785e-05,
      "loss": 0.1214,
      "step": 2000
    },
    {
      "epoch": 1.1864406779661016,
      "grad_norm": 0.23234207928180695,
      "learning_rate": 4.703389830508475e-05,
      "loss": 0.1005,
      "step": 2100
    },
    {
      "epoch": 1.2429378531073447,
      "grad_norm": 5.788926124572754,
      "learning_rate": 4.689265536723164e-05,
      "loss": 0.106,
      "step": 2200
    },
    {
      "epoch": 1.2994350282485876,
      "grad_norm": 14.127985954284668,
      "learning_rate": 4.675141242937853e-05,
      "loss": 0.1002,
      "step": 2300
    },
    {
      "epoch": 1.3559322033898304,
      "grad_norm": 8.628386497497559,
      "learning_rate": 4.6610169491525425e-05,
      "loss": 0.1228,
      "step": 2400
    },
    {
      "epoch": 1.4124293785310735,
      "grad_norm": 3.4723896980285645,
      "learning_rate": 4.646892655367232e-05,
      "loss": 0.1193,
      "step": 2500
    },
    {
      "epoch": 1.4689265536723164,
      "grad_norm": 5.112296104431152,
      "learning_rate": 4.632768361581921e-05,
      "loss": 0.0989,
      "step": 2600
    },
    {
      "epoch": 1.5254237288135593,
      "grad_norm": 8.718145370483398,
      "learning_rate": 4.6186440677966104e-05,
      "loss": 0.1291,
      "step": 2700
    },
    {
      "epoch": 1.5819209039548023,
      "grad_norm": 0.052204638719558716,
      "learning_rate": 4.6045197740113e-05,
      "loss": 0.0987,
      "step": 2800
    },
    {
      "epoch": 1.6384180790960452,
      "grad_norm": 11.152572631835938,
      "learning_rate": 4.590395480225989e-05,
      "loss": 0.113,
      "step": 2900
    },
    {
      "epoch": 1.694915254237288,
      "grad_norm": 3.002537965774536,
      "learning_rate": 4.5762711864406784e-05,
      "loss": 0.1215,
      "step": 3000
    },
    {
      "epoch": 1.7514124293785311,
      "grad_norm": 16.578323364257812,
      "learning_rate": 4.562146892655367e-05,
      "loss": 0.0998,
      "step": 3100
    },
    {
      "epoch": 1.807909604519774,
      "grad_norm": 4.660722255706787,
      "learning_rate": 4.548022598870056e-05,
      "loss": 0.1015,
      "step": 3200
    },
    {
      "epoch": 1.8644067796610169,
      "grad_norm": 0.32472193241119385,
      "learning_rate": 4.533898305084746e-05,
      "loss": 0.0982,
      "step": 3300
    },
    {
      "epoch": 1.92090395480226,
      "grad_norm": 12.544636726379395,
      "learning_rate": 4.519774011299435e-05,
      "loss": 0.1151,
      "step": 3400
    },
    {
      "epoch": 1.9774011299435028,
      "grad_norm": 0.20591090619564056,
      "learning_rate": 4.505649717514124e-05,
      "loss": 0.1109,
      "step": 3500
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9540286702916461,
      "eval_f1": 0.9542995811514169,
      "eval_loss": 0.17088210582733154,
      "eval_runtime": 0.9919,
      "eval_samples_per_second": 4078.94,
      "eval_steps_per_second": 64.521,
      "step": 3540
    },
    {
      "epoch": 2.0338983050847457,
      "grad_norm": 1.156205177307129,
      "learning_rate": 4.491525423728814e-05,
      "loss": 0.0764,
      "step": 3600
    },
    {
      "epoch": 2.0903954802259888,
      "grad_norm": 4.644138336181641,
      "learning_rate": 4.477401129943503e-05,
      "loss": 0.0603,
      "step": 3700
    },
    {
      "epoch": 2.146892655367232,
      "grad_norm": 0.0709792822599411,
      "learning_rate": 4.463276836158192e-05,
      "loss": 0.0649,
      "step": 3800
    },
    {
      "epoch": 2.2033898305084745,
      "grad_norm": 0.13090333342552185,
      "learning_rate": 4.4491525423728816e-05,
      "loss": 0.076,
      "step": 3900
    },
    {
      "epoch": 2.2598870056497176,
      "grad_norm": 39.72850799560547,
      "learning_rate": 4.435028248587571e-05,
      "loss": 0.0827,
      "step": 4000
    },
    {
      "epoch": 2.3163841807909606,
      "grad_norm": 0.29564905166625977,
      "learning_rate": 4.42090395480226e-05,
      "loss": 0.0701,
      "step": 4100
    },
    {
      "epoch": 2.3728813559322033,
      "grad_norm": 0.23284725844860077,
      "learning_rate": 4.4067796610169495e-05,
      "loss": 0.0697,
      "step": 4200
    },
    {
      "epoch": 2.4293785310734464,
      "grad_norm": 0.059655264019966125,
      "learning_rate": 4.392655367231638e-05,
      "loss": 0.0803,
      "step": 4300
    },
    {
      "epoch": 2.4858757062146895,
      "grad_norm": 0.01876319944858551,
      "learning_rate": 4.378531073446328e-05,
      "loss": 0.0796,
      "step": 4400
    },
    {
      "epoch": 2.542372881355932,
      "grad_norm": 0.07363492995500565,
      "learning_rate": 4.3644067796610175e-05,
      "loss": 0.0573,
      "step": 4500
    },
    {
      "epoch": 2.598870056497175,
      "grad_norm": 0.26911139488220215,
      "learning_rate": 4.350282485875706e-05,
      "loss": 0.0732,
      "step": 4600
    },
    {
      "epoch": 2.655367231638418,
      "grad_norm": 0.045297879725694656,
      "learning_rate": 4.3361581920903954e-05,
      "loss": 0.0645,
      "step": 4700
    },
    {
      "epoch": 2.711864406779661,
      "grad_norm": 0.24285119771957397,
      "learning_rate": 4.3220338983050854e-05,
      "loss": 0.0852,
      "step": 4800
    },
    {
      "epoch": 2.768361581920904,
      "grad_norm": 70.39765930175781,
      "learning_rate": 4.307909604519774e-05,
      "loss": 0.0763,
      "step": 4900
    },
    {
      "epoch": 2.824858757062147,
      "grad_norm": 3.1160919666290283,
      "learning_rate": 4.2937853107344634e-05,
      "loss": 0.0618,
      "step": 5000
    },
    {
      "epoch": 2.8813559322033897,
      "grad_norm": 0.14466217160224915,
      "learning_rate": 4.279661016949153e-05,
      "loss": 0.0628,
      "step": 5100
    },
    {
      "epoch": 2.937853107344633,
      "grad_norm": 11.605415344238281,
      "learning_rate": 4.265536723163842e-05,
      "loss": 0.0539,
      "step": 5200
    },
    {
      "epoch": 2.994350282485876,
      "grad_norm": 0.03261380270123482,
      "learning_rate": 4.251412429378531e-05,
      "loss": 0.0349,
      "step": 5300
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9574888779041029,
      "eval_f1": 0.9573208648613947,
      "eval_loss": 0.20843710005283356,
      "eval_runtime": 0.9688,
      "eval_samples_per_second": 4176.286,
      "eval_steps_per_second": 66.061,
      "step": 5310
    },
    {
      "epoch": 3.0508474576271185,
      "grad_norm": 0.007287267595529556,
      "learning_rate": 4.2372881355932206e-05,
      "loss": 0.0575,
      "step": 5400
    },
    {
      "epoch": 3.1073446327683616,
      "grad_norm": 19.718822479248047,
      "learning_rate": 4.22316384180791e-05,
      "loss": 0.0423,
      "step": 5500
    },
    {
      "epoch": 3.1638418079096047,
      "grad_norm": 78.35333251953125,
      "learning_rate": 4.209039548022599e-05,
      "loss": 0.0349,
      "step": 5600
    },
    {
      "epoch": 3.2203389830508473,
      "grad_norm": 0.025877630338072777,
      "learning_rate": 4.1949152542372886e-05,
      "loss": 0.0632,
      "step": 5700
    },
    {
      "epoch": 3.2768361581920904,
      "grad_norm": 14.864492416381836,
      "learning_rate": 4.180790960451977e-05,
      "loss": 0.0651,
      "step": 5800
    },
    {
      "epoch": 3.3333333333333335,
      "grad_norm": 0.002800008049234748,
      "learning_rate": 4.166666666666667e-05,
      "loss": 0.0225,
      "step": 5900
    },
    {
      "epoch": 3.389830508474576,
      "grad_norm": 0.10183978080749512,
      "learning_rate": 4.152542372881356e-05,
      "loss": 0.0467,
      "step": 6000
    },
    {
      "epoch": 3.446327683615819,
      "grad_norm": 30.69606590270996,
      "learning_rate": 4.138418079096045e-05,
      "loss": 0.0509,
      "step": 6100
    },
    {
      "epoch": 3.5028248587570623,
      "grad_norm": 0.43340635299682617,
      "learning_rate": 4.1242937853107345e-05,
      "loss": 0.0366,
      "step": 6200
    },
    {
      "epoch": 3.559322033898305,
      "grad_norm": 3.5696895122528076,
      "learning_rate": 4.110169491525424e-05,
      "loss": 0.0576,
      "step": 6300
    },
    {
      "epoch": 3.615819209039548,
      "grad_norm": 3.981534481048584,
      "learning_rate": 4.096045197740113e-05,
      "loss": 0.0574,
      "step": 6400
    },
    {
      "epoch": 3.672316384180791,
      "grad_norm": 0.020425381138920784,
      "learning_rate": 4.0819209039548024e-05,
      "loss": 0.0582,
      "step": 6500
    },
    {
      "epoch": 3.7288135593220337,
      "grad_norm": 1.6137280464172363,
      "learning_rate": 4.067796610169492e-05,
      "loss": 0.037,
      "step": 6600
    },
    {
      "epoch": 3.785310734463277,
      "grad_norm": 0.41225990653038025,
      "learning_rate": 4.053672316384181e-05,
      "loss": 0.039,
      "step": 6700
    },
    {
      "epoch": 3.84180790960452,
      "grad_norm": 0.02651926688849926,
      "learning_rate": 4.0395480225988704e-05,
      "loss": 0.052,
      "step": 6800
    },
    {
      "epoch": 3.898305084745763,
      "grad_norm": 4.174577713012695,
      "learning_rate": 4.025423728813559e-05,
      "loss": 0.0746,
      "step": 6900
    },
    {
      "epoch": 3.9548022598870056,
      "grad_norm": 0.06549729406833649,
      "learning_rate": 4.011299435028249e-05,
      "loss": 0.0682,
      "step": 7000
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9619377162629758,
      "eval_f1": 0.961922353652765,
      "eval_loss": 0.19074885547161102,
      "eval_runtime": 0.9577,
      "eval_samples_per_second": 4224.832,
      "eval_steps_per_second": 66.829,
      "step": 7080
    },
    {
      "epoch": 4.011299435028248,
      "grad_norm": 0.09852942079305649,
      "learning_rate": 3.997175141242938e-05,
      "loss": 0.0573,
      "step": 7100
    },
    {
      "epoch": 4.067796610169491,
      "grad_norm": 0.010253222659230232,
      "learning_rate": 3.983050847457627e-05,
      "loss": 0.0268,
      "step": 7200
    },
    {
      "epoch": 4.124293785310734,
      "grad_norm": 0.05561167746782303,
      "learning_rate": 3.968926553672316e-05,
      "loss": 0.041,
      "step": 7300
    },
    {
      "epoch": 4.1807909604519775,
      "grad_norm": 0.020777329802513123,
      "learning_rate": 3.954802259887006e-05,
      "loss": 0.0428,
      "step": 7400
    },
    {
      "epoch": 4.237288135593221,
      "grad_norm": 0.011439072899520397,
      "learning_rate": 3.940677966101695e-05,
      "loss": 0.0281,
      "step": 7500
    },
    {
      "epoch": 4.293785310734464,
      "grad_norm": 0.29063406586647034,
      "learning_rate": 3.926553672316384e-05,
      "loss": 0.0347,
      "step": 7600
    },
    {
      "epoch": 4.350282485875706,
      "grad_norm": 0.008078676648437977,
      "learning_rate": 3.9124293785310735e-05,
      "loss": 0.0427,
      "step": 7700
    },
    {
      "epoch": 4.406779661016949,
      "grad_norm": 0.0378178134560585,
      "learning_rate": 3.898305084745763e-05,
      "loss": 0.0448,
      "step": 7800
    },
    {
      "epoch": 4.463276836158192,
      "grad_norm": 0.09035930037498474,
      "learning_rate": 3.884180790960452e-05,
      "loss": 0.0328,
      "step": 7900
    },
    {
      "epoch": 4.519774011299435,
      "grad_norm": 0.05402543023228645,
      "learning_rate": 3.8700564971751415e-05,
      "loss": 0.0345,
      "step": 8000
    },
    {
      "epoch": 4.576271186440678,
      "grad_norm": 0.01713019795715809,
      "learning_rate": 3.855932203389831e-05,
      "loss": 0.0358,
      "step": 8100
    },
    {
      "epoch": 4.632768361581921,
      "grad_norm": 0.0475781112909317,
      "learning_rate": 3.84180790960452e-05,
      "loss": 0.0532,
      "step": 8200
    },
    {
      "epoch": 4.6892655367231635,
      "grad_norm": 0.006405588239431381,
      "learning_rate": 3.8276836158192094e-05,
      "loss": 0.0324,
      "step": 8300
    },
    {
      "epoch": 4.745762711864407,
      "grad_norm": 4.002650260925293,
      "learning_rate": 3.813559322033898e-05,
      "loss": 0.0526,
      "step": 8400
    },
    {
      "epoch": 4.80225988700565,
      "grad_norm": 0.010295218788087368,
      "learning_rate": 3.799435028248588e-05,
      "loss": 0.0428,
      "step": 8500
    },
    {
      "epoch": 4.858757062146893,
      "grad_norm": 25.15464973449707,
      "learning_rate": 3.7853107344632774e-05,
      "loss": 0.0513,
      "step": 8600
    },
    {
      "epoch": 4.915254237288136,
      "grad_norm": 0.018476568162441254,
      "learning_rate": 3.771186440677966e-05,
      "loss": 0.0627,
      "step": 8700
    },
    {
      "epoch": 4.971751412429379,
      "grad_norm": 0.02234013006091118,
      "learning_rate": 3.7570621468926554e-05,
      "loss": 0.0436,
      "step": 8800
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9594661393969353,
      "eval_f1": 0.9595618588245926,
      "eval_loss": 0.24679133296012878,
      "eval_runtime": 0.9625,
      "eval_samples_per_second": 4203.719,
      "eval_steps_per_second": 66.495,
      "step": 8850
    },
    {
      "epoch": 5.028248587570621,
      "grad_norm": 0.007325501646846533,
      "learning_rate": 3.7429378531073453e-05,
      "loss": 0.011,
      "step": 8900
    },
    {
      "epoch": 5.084745762711864,
      "grad_norm": 0.015004786662757397,
      "learning_rate": 3.728813559322034e-05,
      "loss": 0.0239,
      "step": 9000
    },
    {
      "epoch": 5.141242937853107,
      "grad_norm": 0.02809782139956951,
      "learning_rate": 3.714689265536723e-05,
      "loss": 0.0468,
      "step": 9100
    },
    {
      "epoch": 5.19774011299435,
      "grad_norm": 0.061971381306648254,
      "learning_rate": 3.7005649717514126e-05,
      "loss": 0.0369,
      "step": 9200
    },
    {
      "epoch": 5.254237288135593,
      "grad_norm": 0.028554769232869148,
      "learning_rate": 3.686440677966102e-05,
      "loss": 0.0254,
      "step": 9300
    },
    {
      "epoch": 5.3107344632768365,
      "grad_norm": 0.049820106476545334,
      "learning_rate": 3.672316384180791e-05,
      "loss": 0.0371,
      "step": 9400
    },
    {
      "epoch": 5.367231638418079,
      "grad_norm": 0.016609592363238335,
      "learning_rate": 3.6581920903954806e-05,
      "loss": 0.0184,
      "step": 9500
    },
    {
      "epoch": 5.423728813559322,
      "grad_norm": 0.05181876942515373,
      "learning_rate": 3.644067796610169e-05,
      "loss": 0.0414,
      "step": 9600
    },
    {
      "epoch": 5.480225988700565,
      "grad_norm": 0.05821879953145981,
      "learning_rate": 3.629943502824859e-05,
      "loss": 0.0308,
      "step": 9700
    },
    {
      "epoch": 5.536723163841808,
      "grad_norm": 0.010366985574364662,
      "learning_rate": 3.6158192090395485e-05,
      "loss": 0.0278,
      "step": 9800
    },
    {
      "epoch": 5.593220338983051,
      "grad_norm": 0.019191740080714226,
      "learning_rate": 3.601694915254237e-05,
      "loss": 0.0435,
      "step": 9900
    },
    {
      "epoch": 5.649717514124294,
      "grad_norm": 0.06532129645347595,
      "learning_rate": 3.587570621468927e-05,
      "loss": 0.0237,
      "step": 10000
    },
    {
      "epoch": 5.706214689265536,
      "grad_norm": 0.009392981417477131,
      "learning_rate": 3.573446327683616e-05,
      "loss": 0.0334,
      "step": 10100
    },
    {
      "epoch": 5.762711864406779,
      "grad_norm": 0.023171979933977127,
      "learning_rate": 3.559322033898305e-05,
      "loss": 0.0487,
      "step": 10200
    },
    {
      "epoch": 5.8192090395480225,
      "grad_norm": 0.055124878883361816,
      "learning_rate": 3.5451977401129944e-05,
      "loss": 0.0412,
      "step": 10300
    },
    {
      "epoch": 5.875706214689266,
      "grad_norm": 0.015424055978655815,
      "learning_rate": 3.531073446327684e-05,
      "loss": 0.0292,
      "step": 10400
    },
    {
      "epoch": 5.932203389830509,
      "grad_norm": 0.6497403979301453,
      "learning_rate": 3.516949152542373e-05,
      "loss": 0.039,
      "step": 10500
    },
    {
      "epoch": 5.988700564971752,
      "grad_norm": 18.98410415649414,
      "learning_rate": 3.5028248587570624e-05,
      "loss": 0.0322,
      "step": 10600
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9614434008897677,
      "eval_f1": 0.9615565973130906,
      "eval_loss": 0.2411661297082901,
      "eval_runtime": 0.9629,
      "eval_samples_per_second": 4201.762,
      "eval_steps_per_second": 66.464,
      "step": 10620
    },
    {
      "epoch": 6.045197740112994,
      "grad_norm": 0.013564531691372395,
      "learning_rate": 3.488700564971752e-05,
      "loss": 0.0254,
      "step": 10700
    },
    {
      "epoch": 6.101694915254237,
      "grad_norm": 33.3035888671875,
      "learning_rate": 3.474576271186441e-05,
      "loss": 0.0295,
      "step": 10800
    },
    {
      "epoch": 6.15819209039548,
      "grad_norm": 0.12126260250806808,
      "learning_rate": 3.46045197740113e-05,
      "loss": 0.0275,
      "step": 10900
    },
    {
      "epoch": 6.214689265536723,
      "grad_norm": 0.03739802539348602,
      "learning_rate": 3.446327683615819e-05,
      "loss": 0.0267,
      "step": 11000
    },
    {
      "epoch": 6.271186440677966,
      "grad_norm": 0.03359340503811836,
      "learning_rate": 3.432203389830508e-05,
      "loss": 0.0389,
      "step": 11100
    },
    {
      "epoch": 6.327683615819209,
      "grad_norm": 0.003635927801951766,
      "learning_rate": 3.418079096045198e-05,
      "loss": 0.0255,
      "step": 11200
    },
    {
      "epoch": 6.3841807909604515,
      "grad_norm": 0.06124364957213402,
      "learning_rate": 3.403954802259887e-05,
      "loss": 0.0229,
      "step": 11300
    },
    {
      "epoch": 6.440677966101695,
      "grad_norm": 0.026170525699853897,
      "learning_rate": 3.389830508474576e-05,
      "loss": 0.0319,
      "step": 11400
    },
    {
      "epoch": 6.497175141242938,
      "grad_norm": 0.013875061646103859,
      "learning_rate": 3.375706214689266e-05,
      "loss": 0.0276,
      "step": 11500
    },
    {
      "epoch": 6.553672316384181,
      "grad_norm": 0.009600764140486717,
      "learning_rate": 3.361581920903955e-05,
      "loss": 0.0182,
      "step": 11600
    },
    {
      "epoch": 6.610169491525424,
      "grad_norm": 0.02147483266890049,
      "learning_rate": 3.347457627118644e-05,
      "loss": 0.0277,
      "step": 11700
    },
    {
      "epoch": 6.666666666666667,
      "grad_norm": 0.007301884237676859,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.0268,
      "step": 11800
    },
    {
      "epoch": 6.72316384180791,
      "grad_norm": 0.008684027940034866,
      "learning_rate": 3.319209039548023e-05,
      "loss": 0.0244,
      "step": 11900
    },
    {
      "epoch": 6.779661016949152,
      "grad_norm": 0.0058201453648507595,
      "learning_rate": 3.305084745762712e-05,
      "loss": 0.018,
      "step": 12000
    },
    {
      "epoch": 6.836158192090395,
      "grad_norm": 0.015645477920770645,
      "learning_rate": 3.2909604519774014e-05,
      "loss": 0.0389,
      "step": 12100
    },
    {
      "epoch": 6.892655367231638,
      "grad_norm": 0.013589623384177685,
      "learning_rate": 3.27683615819209e-05,
      "loss": 0.0271,
      "step": 12200
    },
    {
      "epoch": 6.9491525423728815,
      "grad_norm": 0.004052096512168646,
      "learning_rate": 3.26271186440678e-05,
      "loss": 0.012,
      "step": 12300
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.963173504695996,
      "eval_f1": 0.9631919351432553,
      "eval_loss": 0.22085699439048767,
      "eval_runtime": 0.9623,
      "eval_samples_per_second": 4204.299,
      "eval_steps_per_second": 66.504,
      "step": 12390
    },
    {
      "epoch": 7.005649717514125,
      "grad_norm": 0.06705684214830399,
      "learning_rate": 3.2485875706214694e-05,
      "loss": 0.0309,
      "step": 12400
    },
    {
      "epoch": 7.062146892655368,
      "grad_norm": 0.006240461952984333,
      "learning_rate": 3.234463276836158e-05,
      "loss": 0.0084,
      "step": 12500
    },
    {
      "epoch": 7.11864406779661,
      "grad_norm": 0.020344626158475876,
      "learning_rate": 3.2203389830508473e-05,
      "loss": 0.0168,
      "step": 12600
    },
    {
      "epoch": 7.175141242937853,
      "grad_norm": 0.003926662262529135,
      "learning_rate": 3.2062146892655373e-05,
      "loss": 0.022,
      "step": 12700
    },
    {
      "epoch": 7.231638418079096,
      "grad_norm": 0.0025492089334875345,
      "learning_rate": 3.192090395480226e-05,
      "loss": 0.0133,
      "step": 12800
    },
    {
      "epoch": 7.288135593220339,
      "grad_norm": 0.005623087752610445,
      "learning_rate": 3.177966101694915e-05,
      "loss": 0.0164,
      "step": 12900
    },
    {
      "epoch": 7.344632768361582,
      "grad_norm": 0.0032459620852023363,
      "learning_rate": 3.1638418079096046e-05,
      "loss": 0.0272,
      "step": 13000
    },
    {
      "epoch": 7.401129943502825,
      "grad_norm": 1.1293178796768188,
      "learning_rate": 3.149717514124294e-05,
      "loss": 0.0148,
      "step": 13100
    },
    {
      "epoch": 7.4576271186440675,
      "grad_norm": 0.0017996145179495215,
      "learning_rate": 3.135593220338983e-05,
      "loss": 0.0132,
      "step": 13200
    },
    {
      "epoch": 7.5141242937853105,
      "grad_norm": 0.008758709765970707,
      "learning_rate": 3.1214689265536726e-05,
      "loss": 0.0152,
      "step": 13300
    },
    {
      "epoch": 7.570621468926554,
      "grad_norm": 0.0038798090536147356,
      "learning_rate": 3.107344632768362e-05,
      "loss": 0.0106,
      "step": 13400
    },
    {
      "epoch": 7.627118644067797,
      "grad_norm": 0.005076746456325054,
      "learning_rate": 3.093220338983051e-05,
      "loss": 0.0158,
      "step": 13500
    },
    {
      "epoch": 7.68361581920904,
      "grad_norm": 0.003670661011710763,
      "learning_rate": 3.0790960451977405e-05,
      "loss": 0.0093,
      "step": 13600
    },
    {
      "epoch": 7.740112994350282,
      "grad_norm": 0.003522429848089814,
      "learning_rate": 3.064971751412429e-05,
      "loss": 0.0183,
      "step": 13700
    },
    {
      "epoch": 7.796610169491525,
      "grad_norm": 0.06700780242681503,
      "learning_rate": 3.050847457627119e-05,
      "loss": 0.0398,
      "step": 13800
    },
    {
      "epoch": 7.853107344632768,
      "grad_norm": 0.01462018396705389,
      "learning_rate": 3.036723163841808e-05,
      "loss": 0.0286,
      "step": 13900
    },
    {
      "epoch": 7.909604519774011,
      "grad_norm": 0.025290269404649734,
      "learning_rate": 3.022598870056497e-05,
      "loss": 0.037,
      "step": 14000
    },
    {
      "epoch": 7.966101694915254,
      "grad_norm": 0.011192042380571365,
      "learning_rate": 3.0084745762711864e-05,
      "loss": 0.0147,
      "step": 14100
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9636678200692042,
      "eval_f1": 0.9635820582698403,
      "eval_loss": 0.24865780770778656,
      "eval_runtime": 0.9484,
      "eval_samples_per_second": 4266.086,
      "eval_steps_per_second": 67.481,
      "step": 14160
    }
  ],
  "logging_steps": 100,
  "max_steps": 35400,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 20,
  "save_steps": 500,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1172336478105600.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}