{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 20,
  "global_step": 1180,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0,
      "eval_accuracy": 0.7546099290780142,
      "eval_f1": 0.36162361623616235,
      "eval_loss": 0.49413058161735535,
      "eval_precision": 0.6363636363636364,
      "eval_recall": 0.25257731958762886,
      "eval_runtime": 51.7135,
      "eval_samples_per_second": 5.646,
      "eval_steps_per_second": 0.193,
      "step": 0
    },
    {
      "epoch": 0.000847457627118644,
      "grad_norm": 1.8022950887680054,
      "learning_rate": 1.6949152542372883e-07,
      "loss": 0.4871,
      "step": 1
    },
    {
      "epoch": 0.001694915254237288,
      "grad_norm": 1.6145427227020264,
      "learning_rate": 3.3898305084745766e-07,
      "loss": 0.443,
      "step": 2
    },
    {
      "epoch": 0.002542372881355932,
      "grad_norm": 2.0260508060455322,
      "learning_rate": 5.084745762711865e-07,
      "loss": 0.5426,
      "step": 3
    },
    {
      "epoch": 0.003389830508474576,
      "grad_norm": 1.438798427581787,
      "learning_rate": 6.779661016949153e-07,
      "loss": 0.4559,
      "step": 4
    },
    {
      "epoch": 0.00423728813559322,
      "grad_norm": 2.0105838775634766,
      "learning_rate": 8.474576271186441e-07,
      "loss": 0.4625,
      "step": 5
    },
    {
      "epoch": 0.005084745762711864,
      "grad_norm": 1.818857192993164,
      "learning_rate": 1.016949152542373e-06,
      "loss": 0.5044,
      "step": 6
    },
    {
      "epoch": 0.005932203389830509,
      "grad_norm": 3.1182994842529297,
      "learning_rate": 1.186440677966102e-06,
      "loss": 0.6415,
      "step": 7
    },
    {
      "epoch": 0.006779661016949152,
      "grad_norm": 1.8738701343536377,
      "learning_rate": 1.3559322033898307e-06,
      "loss": 0.5268,
      "step": 8
    },
    {
      "epoch": 0.007627118644067797,
      "grad_norm": 2.299548864364624,
      "learning_rate": 1.5254237288135596e-06,
      "loss": 0.4975,
      "step": 9
    },
    {
      "epoch": 0.00847457627118644,
      "grad_norm": 2.331179141998291,
      "learning_rate": 1.6949152542372882e-06,
      "loss": 0.5234,
      "step": 10
    },
    {
      "epoch": 0.009322033898305085,
      "grad_norm": 1.9474170207977295,
      "learning_rate": 1.8644067796610171e-06,
      "loss": 0.4841,
      "step": 11
    },
    {
      "epoch": 0.010169491525423728,
      "grad_norm": 1.6214301586151123,
      "learning_rate": 2.033898305084746e-06,
      "loss": 0.4232,
      "step": 12
    },
    {
      "epoch": 0.011016949152542373,
      "grad_norm": 2.3513247966766357,
      "learning_rate": 2.203389830508475e-06,
      "loss": 0.6045,
      "step": 13
    },
    {
      "epoch": 0.011864406779661017,
      "grad_norm": 1.8450990915298462,
      "learning_rate": 2.372881355932204e-06,
      "loss": 0.5038,
      "step": 14
    },
    {
      "epoch": 0.012711864406779662,
      "grad_norm": 1.9837912321090698,
      "learning_rate": 2.5423728813559323e-06,
      "loss": 0.4716,
      "step": 15
    },
    {
      "epoch": 0.013559322033898305,
      "grad_norm": 1.9894237518310547,
      "learning_rate": 2.7118644067796613e-06,
      "loss": 0.4758,
      "step": 16
    },
    {
      "epoch": 0.01440677966101695,
      "grad_norm": 2.0753157138824463,
      "learning_rate": 2.8813559322033903e-06,
      "loss": 0.4984,
      "step": 17
    },
    {
      "epoch": 0.015254237288135594,
      "grad_norm": 2.442741632461548,
      "learning_rate": 3.0508474576271192e-06,
      "loss": 0.5174,
      "step": 18
    },
    {
      "epoch": 0.016101694915254237,
      "grad_norm": 1.9772732257843018,
      "learning_rate": 3.2203389830508473e-06,
      "loss": 0.5237,
      "step": 19
    },
    {
      "epoch": 0.01694915254237288,
      "grad_norm": 1.8191900253295898,
      "learning_rate": 3.3898305084745763e-06,
      "loss": 0.483,
      "step": 20
    },
    {
      "epoch": 0.01694915254237288,
      "eval_accuracy": 0.7645390070921986,
      "eval_f1": 0.3712121212121212,
      "eval_loss": 0.489811509847641,
      "eval_precision": 0.7,
      "eval_recall": 0.25257731958762886,
      "eval_runtime": 51.7942,
      "eval_samples_per_second": 5.638,
      "eval_steps_per_second": 0.193,
      "step": 20
    },
    {
      "epoch": 0.017796610169491526,
      "grad_norm": 1.6104735136032104,
      "learning_rate": 3.5593220338983053e-06,
      "loss": 0.4962,
      "step": 21
    },
    {
      "epoch": 0.01864406779661017,
      "grad_norm": 4.9892897605896,
      "learning_rate": 3.7288135593220342e-06,
      "loss": 0.4929,
      "step": 22
    },
    {
      "epoch": 0.019491525423728815,
      "grad_norm": 1.9893275499343872,
      "learning_rate": 3.898305084745763e-06,
      "loss": 0.4361,
      "step": 23
    },
    {
      "epoch": 0.020338983050847456,
      "grad_norm": 1.6889193058013916,
      "learning_rate": 4.067796610169492e-06,
      "loss": 0.4808,
      "step": 24
    },
    {
      "epoch": 0.0211864406779661,
      "grad_norm": 2.095546245574951,
      "learning_rate": 4.23728813559322e-06,
      "loss": 0.5017,
      "step": 25
    },
    {
      "epoch": 0.022033898305084745,
      "grad_norm": 1.7155216932296753,
      "learning_rate": 4.40677966101695e-06,
      "loss": 0.4901,
      "step": 26
    },
    {
      "epoch": 0.02288135593220339,
      "grad_norm": 1.7803897857666016,
      "learning_rate": 4.576271186440678e-06,
      "loss": 0.4776,
      "step": 27
    },
    {
      "epoch": 0.023728813559322035,
      "grad_norm": 1.9448434114456177,
      "learning_rate": 4.745762711864408e-06,
      "loss": 0.463,
      "step": 28
    },
    {
      "epoch": 0.02457627118644068,
      "grad_norm": 1.8458937406539917,
      "learning_rate": 4.915254237288136e-06,
      "loss": 0.5081,
      "step": 29
    },
    {
      "epoch": 0.025423728813559324,
      "grad_norm": 1.8070677518844604,
      "learning_rate": 5.084745762711865e-06,
      "loss": 0.4508,
      "step": 30
    },
    {
      "epoch": 0.026271186440677965,
      "grad_norm": 1.8023436069488525,
      "learning_rate": 5.254237288135594e-06,
      "loss": 0.4382,
      "step": 31
    },
    {
      "epoch": 0.02711864406779661,
      "grad_norm": 2.1084094047546387,
      "learning_rate": 5.423728813559323e-06,
      "loss": 0.5103,
      "step": 32
    },
    {
      "epoch": 0.027966101694915254,
      "grad_norm": 2.0315449237823486,
      "learning_rate": 5.593220338983051e-06,
      "loss": 0.4936,
      "step": 33
    },
    {
      "epoch": 0.0288135593220339,
      "grad_norm": 1.6474404335021973,
      "learning_rate": 5.7627118644067805e-06,
      "loss": 0.4135,
      "step": 34
    },
    {
      "epoch": 0.029661016949152543,
      "grad_norm": 1.6273308992385864,
      "learning_rate": 5.932203389830509e-06,
      "loss": 0.4333,
      "step": 35
    },
    {
      "epoch": 0.030508474576271188,
      "grad_norm": 1.7373437881469727,
      "learning_rate": 6.1016949152542385e-06,
      "loss": 0.4807,
      "step": 36
    },
    {
      "epoch": 0.03135593220338983,
      "grad_norm": 1.7728058099746704,
      "learning_rate": 6.271186440677966e-06,
      "loss": 0.4788,
      "step": 37
    },
    {
      "epoch": 0.03220338983050847,
      "grad_norm": 1.839632511138916,
      "learning_rate": 6.440677966101695e-06,
      "loss": 0.5109,
      "step": 38
    },
    {
      "epoch": 0.03305084745762712,
      "grad_norm": 2.0971577167510986,
      "learning_rate": 6.610169491525424e-06,
      "loss": 0.3893,
      "step": 39
    },
    {
      "epoch": 0.03389830508474576,
      "grad_norm": 1.9932570457458496,
      "learning_rate": 6.779661016949153e-06,
      "loss": 0.5491,
      "step": 40
    },
    {
      "epoch": 0.03389830508474576,
      "eval_accuracy": 0.7716312056737589,
      "eval_f1": 0.3686274509803922,
      "eval_loss": 0.4646168649196625,
      "eval_precision": 0.7704918032786885,
      "eval_recall": 0.2422680412371134,
      "eval_runtime": 50.3457,
      "eval_samples_per_second": 5.8,
      "eval_steps_per_second": 0.199,
      "step": 40
    },
    {
      "epoch": 0.03474576271186441,
      "grad_norm": 2.155245780944824,
      "learning_rate": 6.949152542372882e-06,
      "loss": 0.5208,
      "step": 41
    },
    {
      "epoch": 0.03559322033898305,
      "grad_norm": 2.139366626739502,
      "learning_rate": 7.1186440677966106e-06,
      "loss": 0.4249,
      "step": 42
    },
    {
      "epoch": 0.036440677966101696,
      "grad_norm": 1.818919062614441,
      "learning_rate": 7.288135593220339e-06,
      "loss": 0.3855,
      "step": 43
    },
    {
      "epoch": 0.03728813559322034,
      "grad_norm": 1.7183736562728882,
      "learning_rate": 7.4576271186440685e-06,
      "loss": 0.4531,
      "step": 44
    },
    {
      "epoch": 0.038135593220338986,
      "grad_norm": 1.7476608753204346,
      "learning_rate": 7.627118644067797e-06,
      "loss": 0.4361,
      "step": 45
    },
    {
      "epoch": 0.03898305084745763,
      "grad_norm": 1.6213011741638184,
      "learning_rate": 7.796610169491526e-06,
      "loss": 0.4214,
      "step": 46
    },
    {
      "epoch": 0.03983050847457627,
      "grad_norm": 2.0858964920043945,
      "learning_rate": 7.966101694915255e-06,
      "loss": 0.4487,
      "step": 47
    },
    {
      "epoch": 0.04067796610169491,
      "grad_norm": 1.9192991256713867,
      "learning_rate": 8.135593220338983e-06,
      "loss": 0.3855,
      "step": 48
    },
    {
      "epoch": 0.04152542372881356,
      "grad_norm": 2.8907480239868164,
      "learning_rate": 8.305084745762712e-06,
      "loss": 0.5793,
      "step": 49
    },
    {
      "epoch": 0.0423728813559322,
      "grad_norm": 2.0093941688537598,
      "learning_rate": 8.47457627118644e-06,
      "loss": 0.4369,
      "step": 50
    },
    {
      "epoch": 0.043220338983050846,
      "grad_norm": 1.8551487922668457,
      "learning_rate": 8.64406779661017e-06,
      "loss": 0.3609,
      "step": 51
    },
    {
      "epoch": 0.04406779661016949,
      "grad_norm": 2.578389883041382,
      "learning_rate": 8.8135593220339e-06,
      "loss": 0.4005,
      "step": 52
    },
    {
      "epoch": 0.044915254237288135,
      "grad_norm": 1.8454015254974365,
      "learning_rate": 8.983050847457628e-06,
      "loss": 0.3813,
      "step": 53
    },
    {
      "epoch": 0.04576271186440678,
      "grad_norm": 1.8623127937316895,
      "learning_rate": 9.152542372881356e-06,
      "loss": 0.371,
      "step": 54
    },
    {
      "epoch": 0.046610169491525424,
      "grad_norm": 1.5980563163757324,
      "learning_rate": 9.322033898305085e-06,
      "loss": 0.3526,
      "step": 55
    },
    {
      "epoch": 0.04745762711864407,
      "grad_norm": 1.9545420408248901,
      "learning_rate": 9.491525423728815e-06,
      "loss": 0.3964,
      "step": 56
    },
    {
      "epoch": 0.048305084745762714,
      "grad_norm": 2.28120493888855,
      "learning_rate": 9.661016949152544e-06,
      "loss": 0.4318,
      "step": 57
    },
    {
      "epoch": 0.04915254237288136,
      "grad_norm": 2.028052568435669,
      "learning_rate": 9.830508474576272e-06,
      "loss": 0.3738,
      "step": 58
    },
    {
      "epoch": 0.05,
      "grad_norm": 1.778688669204712,
      "learning_rate": 1e-05,
      "loss": 0.356,
      "step": 59
    },
    {
      "epoch": 0.05084745762711865,
      "grad_norm": 1.9434354305267334,
      "learning_rate": 1.016949152542373e-05,
      "loss": 0.3868,
      "step": 60
    },
    {
      "epoch": 0.05084745762711865,
      "eval_accuracy": 0.8014184397163121,
      "eval_f1": 0.4852941176470588,
      "eval_loss": 0.39268842339515686,
      "eval_precision": 0.8461538461538461,
      "eval_recall": 0.3402061855670103,
      "eval_runtime": 51.5844,
      "eval_samples_per_second": 5.661,
      "eval_steps_per_second": 0.194,
      "step": 60
    },
    {
      "epoch": 0.051694915254237285,
      "grad_norm": 2.865485429763794,
      "learning_rate": 1.0338983050847458e-05,
      "loss": 0.4346,
      "step": 61
    },
    {
      "epoch": 0.05254237288135593,
      "grad_norm": 1.7954847812652588,
      "learning_rate": 1.0508474576271188e-05,
      "loss": 0.3288,
      "step": 62
    },
    {
      "epoch": 0.053389830508474574,
      "grad_norm": 1.9036914110183716,
      "learning_rate": 1.0677966101694917e-05,
      "loss": 0.345,
      "step": 63
    },
    {
      "epoch": 0.05423728813559322,
      "grad_norm": 1.8734129667282104,
      "learning_rate": 1.0847457627118645e-05,
      "loss": 0.3011,
      "step": 64
    },
    {
      "epoch": 0.05508474576271186,
      "grad_norm": 1.7967445850372314,
      "learning_rate": 1.1016949152542374e-05,
      "loss": 0.3054,
      "step": 65
    },
    {
      "epoch": 0.05593220338983051,
      "grad_norm": 2.14163875579834,
      "learning_rate": 1.1186440677966102e-05,
      "loss": 0.3151,
      "step": 66
    },
    {
      "epoch": 0.05677966101694915,
      "grad_norm": 2.054262399673462,
      "learning_rate": 1.1355932203389833e-05,
      "loss": 0.3112,
      "step": 67
    },
    {
      "epoch": 0.0576271186440678,
      "grad_norm": 2.427635669708252,
      "learning_rate": 1.1525423728813561e-05,
      "loss": 0.3375,
      "step": 68
    },
    {
      "epoch": 0.05847457627118644,
      "grad_norm": 2.156615972518921,
      "learning_rate": 1.169491525423729e-05,
      "loss": 0.2858,
      "step": 69
    },
    {
      "epoch": 0.059322033898305086,
      "grad_norm": 1.882498860359192,
      "learning_rate": 1.1864406779661018e-05,
      "loss": 0.2763,
      "step": 70
    },
    {
      "epoch": 0.06016949152542373,
      "grad_norm": 2.2266876697540283,
      "learning_rate": 1.2033898305084745e-05,
      "loss": 0.2747,
      "step": 71
    },
    {
      "epoch": 0.061016949152542375,
      "grad_norm": 2.385572671890259,
      "learning_rate": 1.2203389830508477e-05,
      "loss": 0.2908,
      "step": 72
    },
    {
      "epoch": 0.06186440677966102,
      "grad_norm": 3.370197057723999,
      "learning_rate": 1.2372881355932205e-05,
      "loss": 0.3021,
      "step": 73
    },
    {
      "epoch": 0.06271186440677966,
      "grad_norm": 2.4264488220214844,
      "learning_rate": 1.2542372881355932e-05,
      "loss": 0.2979,
      "step": 74
    },
    {
      "epoch": 0.0635593220338983,
      "grad_norm": 2.0098724365234375,
      "learning_rate": 1.2711864406779661e-05,
      "loss": 0.2354,
      "step": 75
    },
    {
      "epoch": 0.06440677966101695,
      "grad_norm": 1.5533535480499268,
      "learning_rate": 1.288135593220339e-05,
      "loss": 0.1868,
      "step": 76
    },
    {
      "epoch": 0.06525423728813559,
      "grad_norm": 2.51094651222229,
      "learning_rate": 1.305084745762712e-05,
      "loss": 0.2803,
      "step": 77
    },
    {
      "epoch": 0.06610169491525424,
      "grad_norm": 2.6391665935516357,
      "learning_rate": 1.3220338983050848e-05,
      "loss": 0.2686,
      "step": 78
    },
    {
      "epoch": 0.06694915254237288,
      "grad_norm": 1.9863828420639038,
      "learning_rate": 1.3389830508474577e-05,
      "loss": 0.232,
      "step": 79
    },
    {
      "epoch": 0.06779661016949153,
      "grad_norm": 3.283465623855591,
      "learning_rate": 1.3559322033898305e-05,
      "loss": 0.2752,
      "step": 80
    },
    {
      "epoch": 0.06779661016949153,
      "eval_accuracy": 0.9148936170212766,
      "eval_f1": 0.8235294117647058,
      "eval_loss": 0.24302659928798676,
      "eval_precision": 0.958904109589041,
      "eval_recall": 0.7216494845360825,
      "eval_runtime": 50.3657,
      "eval_samples_per_second": 5.798,
      "eval_steps_per_second": 0.199,
      "step": 80
    },
    {
      "epoch": 0.06864406779661017,
      "grad_norm": 4.136785507202148,
      "learning_rate": 1.3728813559322034e-05,
      "loss": 0.2669,
      "step": 81
    },
    {
      "epoch": 0.06949152542372881,
      "grad_norm": 2.905684471130371,
      "learning_rate": 1.3898305084745764e-05,
      "loss": 0.2977,
      "step": 82
    },
    {
      "epoch": 0.07033898305084746,
      "grad_norm": 3.484105110168457,
      "learning_rate": 1.4067796610169493e-05,
      "loss": 0.2463,
      "step": 83
    },
    {
      "epoch": 0.0711864406779661,
      "grad_norm": 2.0514471530914307,
      "learning_rate": 1.4237288135593221e-05,
      "loss": 0.189,
      "step": 84
    },
    {
      "epoch": 0.07203389830508475,
      "grad_norm": 3.3227920532226562,
      "learning_rate": 1.440677966101695e-05,
      "loss": 0.3301,
      "step": 85
    },
    {
      "epoch": 0.07288135593220339,
      "grad_norm": 4.558714866638184,
      "learning_rate": 1.4576271186440678e-05,
      "loss": 0.2356,
      "step": 86
    },
    {
      "epoch": 0.07372881355932204,
      "grad_norm": 3.302720069885254,
      "learning_rate": 1.4745762711864408e-05,
      "loss": 0.1992,
      "step": 87
    },
    {
      "epoch": 0.07457627118644068,
      "grad_norm": 2.9582176208496094,
      "learning_rate": 1.4915254237288137e-05,
      "loss": 0.2135,
      "step": 88
    },
    {
      "epoch": 0.07542372881355933,
      "grad_norm": 2.0440144538879395,
      "learning_rate": 1.5084745762711865e-05,
      "loss": 0.1561,
      "step": 89
    },
    {
      "epoch": 0.07627118644067797,
      "grad_norm": 3.5674586296081543,
      "learning_rate": 1.5254237288135594e-05,
      "loss": 0.2177,
      "step": 90
    },
    {
      "epoch": 0.07711864406779662,
      "grad_norm": 5.187112808227539,
      "learning_rate": 1.5423728813559326e-05,
      "loss": 0.2427,
      "step": 91
    },
    {
      "epoch": 0.07796610169491526,
      "grad_norm": 5.343093395233154,
      "learning_rate": 1.5593220338983053e-05,
      "loss": 0.1792,
      "step": 92
    },
    {
      "epoch": 0.0788135593220339,
      "grad_norm": 7.031548500061035,
      "learning_rate": 1.576271186440678e-05,
      "loss": 0.1923,
      "step": 93
    },
    {
      "epoch": 0.07966101694915254,
      "grad_norm": 4.42516565322876,
      "learning_rate": 1.593220338983051e-05,
      "loss": 0.2155,
      "step": 94
    },
    {
      "epoch": 0.08050847457627118,
      "grad_norm": 4.800620079040527,
      "learning_rate": 1.6101694915254237e-05,
      "loss": 0.1527,
      "step": 95
    },
    {
      "epoch": 0.08135593220338982,
      "grad_norm": 1.2162249088287354,
      "learning_rate": 1.6271186440677967e-05,
      "loss": 0.0701,
      "step": 96
    },
    {
      "epoch": 0.08220338983050847,
      "grad_norm": 3.083869218826294,
      "learning_rate": 1.6440677966101697e-05,
      "loss": 0.1733,
      "step": 97
    },
    {
      "epoch": 0.08305084745762711,
      "grad_norm": 4.925241470336914,
      "learning_rate": 1.6610169491525424e-05,
      "loss": 0.2633,
      "step": 98
    },
    {
      "epoch": 0.08389830508474576,
      "grad_norm": 8.311452865600586,
      "learning_rate": 1.6779661016949154e-05,
      "loss": 0.1714,
      "step": 99
    },
    {
      "epoch": 0.0847457627118644,
      "grad_norm": 3.1740920543670654,
      "learning_rate": 1.694915254237288e-05,
      "loss": 0.1319,
      "step": 100
    },
    {
      "epoch": 0.0847457627118644,
      "eval_accuracy": 0.9716312056737588,
      "eval_f1": 0.9481865284974094,
      "eval_loss": 0.09902569651603699,
      "eval_precision": 0.953125,
      "eval_recall": 0.9432989690721649,
      "eval_runtime": 49.823,
      "eval_samples_per_second": 5.861,
      "eval_steps_per_second": 0.201,
      "step": 100
    },
    {
      "epoch": 0.08559322033898305,
      "grad_norm": 3.773057222366333,
      "learning_rate": 1.711864406779661e-05,
      "loss": 0.1186,
      "step": 101
    },
    {
      "epoch": 0.08644067796610169,
      "grad_norm": 1.8200677633285522,
      "learning_rate": 1.728813559322034e-05,
      "loss": 0.0917,
      "step": 102
    },
    {
      "epoch": 0.08728813559322034,
      "grad_norm": 5.035698890686035,
      "learning_rate": 1.745762711864407e-05,
      "loss": 0.1199,
      "step": 103
    },
    {
      "epoch": 0.08813559322033898,
      "grad_norm": 4.666184425354004,
      "learning_rate": 1.76271186440678e-05,
      "loss": 0.1286,
      "step": 104
    },
    {
      "epoch": 0.08898305084745763,
      "grad_norm": 2.4662208557128906,
      "learning_rate": 1.7796610169491526e-05,
      "loss": 0.0845,
      "step": 105
    },
    {
      "epoch": 0.08983050847457627,
      "grad_norm": 2.8939261436462402,
      "learning_rate": 1.7966101694915256e-05,
      "loss": 0.0989,
      "step": 106
    },
    {
      "epoch": 0.09067796610169492,
      "grad_norm": 4.854353904724121,
      "learning_rate": 1.8135593220338986e-05,
      "loss": 0.1092,
      "step": 107
    },
    {
      "epoch": 0.09152542372881356,
      "grad_norm": 3.3702521324157715,
      "learning_rate": 1.8305084745762713e-05,
      "loss": 0.1564,
      "step": 108
    },
    {
      "epoch": 0.0923728813559322,
      "grad_norm": 4.387780666351318,
      "learning_rate": 1.8474576271186443e-05,
      "loss": 0.1399,
      "step": 109
    },
    {
      "epoch": 0.09322033898305085,
      "grad_norm": 4.5151495933532715,
      "learning_rate": 1.864406779661017e-05,
      "loss": 0.0979,
      "step": 110
    },
    {
      "epoch": 0.0940677966101695,
      "grad_norm": 3.65556001663208,
      "learning_rate": 1.88135593220339e-05,
      "loss": 0.1338,
      "step": 111
    },
    {
      "epoch": 0.09491525423728814,
      "grad_norm": 2.1862547397613525,
      "learning_rate": 1.898305084745763e-05,
      "loss": 0.0791,
      "step": 112
    },
    {
      "epoch": 0.09576271186440678,
      "grad_norm": 5.004955291748047,
      "learning_rate": 1.9152542372881357e-05,
      "loss": 0.0972,
      "step": 113
    },
    {
      "epoch": 0.09661016949152543,
      "grad_norm": 3.057615041732788,
      "learning_rate": 1.9322033898305087e-05,
      "loss": 0.0611,
      "step": 114
    },
    {
      "epoch": 0.09745762711864407,
      "grad_norm": 5.858815670013428,
      "learning_rate": 1.9491525423728814e-05,
      "loss": 0.1005,
      "step": 115
    },
    {
      "epoch": 0.09830508474576272,
      "grad_norm": 3.9090657234191895,
      "learning_rate": 1.9661016949152545e-05,
      "loss": 0.1294,
      "step": 116
    },
    {
      "epoch": 0.09915254237288136,
      "grad_norm": 2.838143825531006,
      "learning_rate": 1.9830508474576275e-05,
      "loss": 0.089,
      "step": 117
    },
    {
      "epoch": 0.1,
      "grad_norm": 6.167634963989258,
      "learning_rate": 2e-05,
      "loss": 0.1497,
      "step": 118
    },
    {
      "epoch": 0.10084745762711865,
      "grad_norm": 2.7352752685546875,
      "learning_rate": 1.9999956245734325e-05,
      "loss": 0.0708,
      "step": 119
    },
    {
      "epoch": 0.1016949152542373,
      "grad_norm": 5.203207969665527,
      "learning_rate": 1.9999824983320176e-05,
      "loss": 0.0971,
      "step": 120
    },
    {
      "epoch": 0.1016949152542373,
      "eval_accuracy": 0.9914893617021276,
      "eval_f1": 0.9846938775510204,
      "eval_loss": 0.04216673597693443,
      "eval_precision": 0.9747474747474747,
      "eval_recall": 0.9948453608247423,
      "eval_runtime": 50.369,
      "eval_samples_per_second": 5.797,
      "eval_steps_per_second": 0.199,
      "step": 120
    },
    {
      "epoch": 0.10254237288135593,
      "grad_norm": 3.716186046600342,
      "learning_rate": 1.999960621390622e-05,
      "loss": 0.0875,
      "step": 121
    },
    {
      "epoch": 0.10338983050847457,
      "grad_norm": 3.5088372230529785,
      "learning_rate": 1.9999299939406875e-05,
      "loss": 0.0642,
      "step": 122
    },
    {
      "epoch": 0.10423728813559321,
      "grad_norm": 3.1328420639038086,
      "learning_rate": 1.9998906162502298e-05,
      "loss": 0.0559,
      "step": 123
    },
    {
      "epoch": 0.10508474576271186,
      "grad_norm": 1.2235671281814575,
      "learning_rate": 1.9998424886638382e-05,
      "loss": 0.0267,
      "step": 124
    },
    {
      "epoch": 0.1059322033898305,
      "grad_norm": 2.749112129211426,
      "learning_rate": 1.9997856116026692e-05,
      "loss": 0.0547,
      "step": 125
    },
    {
      "epoch": 0.10677966101694915,
      "grad_norm": 1.985463261604309,
      "learning_rate": 1.999719985564446e-05,
      "loss": 0.0422,
      "step": 126
    },
    {
      "epoch": 0.10762711864406779,
      "grad_norm": 1.806302785873413,
      "learning_rate": 1.999645611123453e-05,
      "loss": 0.0311,
      "step": 127
    },
    {
      "epoch": 0.10847457627118644,
      "grad_norm": 1.514439582824707,
      "learning_rate": 1.9995624889305286e-05,
      "loss": 0.0303,
      "step": 128
    },
    {
      "epoch": 0.10932203389830508,
      "grad_norm": 4.151468276977539,
      "learning_rate": 1.9994706197130645e-05,
      "loss": 0.0615,
      "step": 129
    },
    {
      "epoch": 0.11016949152542373,
      "grad_norm": 4.021677494049072,
      "learning_rate": 1.9993700042749937e-05,
      "loss": 0.0374,
      "step": 130
    },
    {
      "epoch": 0.11101694915254237,
      "grad_norm": 4.167133331298828,
      "learning_rate": 1.9992606434967877e-05,
      "loss": 0.0969,
      "step": 131
    },
    {
      "epoch": 0.11186440677966102,
      "grad_norm": 2.3483352661132812,
      "learning_rate": 1.9991425383354462e-05,
      "loss": 0.0587,
      "step": 132
    },
    {
      "epoch": 0.11271186440677966,
      "grad_norm": 3.196880340576172,
      "learning_rate": 1.99901568982449e-05,
      "loss": 0.0665,
      "step": 133
    },
    {
      "epoch": 0.1135593220338983,
      "grad_norm": 1.4003562927246094,
      "learning_rate": 1.998880099073952e-05,
      "loss": 0.0287,
      "step": 134
    },
    {
      "epoch": 0.11440677966101695,
      "grad_norm": 6.164405822753906,
      "learning_rate": 1.9987357672703674e-05,
      "loss": 0.0557,
      "step": 135
    },
    {
      "epoch": 0.1152542372881356,
      "grad_norm": 4.226889133453369,
      "learning_rate": 1.998582695676762e-05,
      "loss": 0.0575,
      "step": 136
    },
    {
      "epoch": 0.11610169491525424,
      "grad_norm": 3.4632186889648438,
      "learning_rate": 1.9984208856326433e-05,
      "loss": 0.0405,
      "step": 137
    },
    {
      "epoch": 0.11694915254237288,
      "grad_norm": 1.7408661842346191,
      "learning_rate": 1.9982503385539865e-05,
      "loss": 0.0208,
      "step": 138
    },
    {
      "epoch": 0.11779661016949153,
      "grad_norm": 4.273019790649414,
      "learning_rate": 1.9980710559332248e-05,
      "loss": 0.0439,
      "step": 139
    },
    {
      "epoch": 0.11864406779661017,
      "grad_norm": 2.678131341934204,
      "learning_rate": 1.9978830393392338e-05,
      "loss": 0.0478,
      "step": 140
    },
    {
      "epoch": 0.11864406779661017,
      "eval_accuracy": 0.9985815602836879,
      "eval_f1": 0.9974160206718347,
      "eval_loss": 0.0119753647595644,
      "eval_precision": 1.0,
      "eval_recall": 0.9948453608247423,
      "eval_runtime": 49.8796,
      "eval_samples_per_second": 5.854,
      "eval_steps_per_second": 0.2,
      "step": 140
    },
    {
      "epoch": 0.11949152542372882,
      "grad_norm": 3.534904718399048,
      "learning_rate": 1.997686290417319e-05,
      "loss": 0.0676,
      "step": 141
    },
    {
      "epoch": 0.12033898305084746,
      "grad_norm": 2.0324580669403076,
      "learning_rate": 1.9974808108892017e-05,
      "loss": 0.0522,
      "step": 142
    },
    {
      "epoch": 0.1211864406779661,
      "grad_norm": 1.198857069015503,
      "learning_rate": 1.9972666025530027e-05,
      "loss": 0.0296,
      "step": 143
    },
    {
      "epoch": 0.12203389830508475,
      "grad_norm": 3.2384731769561768,
      "learning_rate": 1.9970436672832276e-05,
      "loss": 0.0295,
      "step": 144
    },
    {
      "epoch": 0.1228813559322034,
      "grad_norm": 2.0026895999908447,
      "learning_rate": 1.9968120070307503e-05,
      "loss": 0.0426,
      "step": 145
    },
    {
      "epoch": 0.12372881355932204,
      "grad_norm": 0.9530765414237976,
      "learning_rate": 1.996571623822796e-05,
      "loss": 0.0192,
      "step": 146
    },
    {
      "epoch": 0.12457627118644068,
      "grad_norm": 4.019771575927734,
      "learning_rate": 1.9963225197629223e-05,
      "loss": 0.0693,
      "step": 147
    },
    {
      "epoch": 0.12542372881355932,
      "grad_norm": 2.6940274238586426,
      "learning_rate": 1.9960646970310027e-05,
      "loss": 0.032,
      "step": 148
    },
    {
      "epoch": 0.12627118644067797,
      "grad_norm": 1.5307412147521973,
      "learning_rate": 1.995798157883206e-05,
      "loss": 0.0238,
      "step": 149
    },
    {
      "epoch": 0.1271186440677966,
      "grad_norm": 2.437249183654785,
      "learning_rate": 1.995522904651977e-05,
      "loss": 0.0348,
      "step": 150
    },
    {
      "epoch": 0.12796610169491526,
      "grad_norm": 1.985588550567627,
      "learning_rate": 1.995238939746016e-05,
      "loss": 0.0441,
      "step": 151
    },
    {
      "epoch": 0.1288135593220339,
      "grad_norm": 1.3132153749465942,
      "learning_rate": 1.9949462656502588e-05,
      "loss": 0.0146,
      "step": 152
    },
    {
      "epoch": 0.12966101694915255,
      "grad_norm": 2.7921226024627686,
      "learning_rate": 1.994644884925853e-05,
      "loss": 0.0445,
      "step": 153
    },
    {
      "epoch": 0.13050847457627118,
      "grad_norm": 4.007246017456055,
      "learning_rate": 1.9943348002101374e-05,
      "loss": 0.0593,
      "step": 154
    },
    {
      "epoch": 0.13135593220338984,
      "grad_norm": 5.683608531951904,
      "learning_rate": 1.9940160142166172e-05,
      "loss": 0.0705,
      "step": 155
    },
    {
      "epoch": 0.13220338983050847,
      "grad_norm": 3.090878963470459,
      "learning_rate": 1.9936885297349426e-05,
      "loss": 0.0516,
      "step": 156
    },
    {
      "epoch": 0.13305084745762713,
      "grad_norm": 1.8990111351013184,
      "learning_rate": 1.993352349630882e-05,
      "loss": 0.0218,
      "step": 157
    },
    {
      "epoch": 0.13389830508474576,
      "grad_norm": 2.009877920150757,
      "learning_rate": 1.9930074768462974e-05,
      "loss": 0.0294,
      "step": 158
    },
    {
      "epoch": 0.13474576271186442,
      "grad_norm": 5.6568193435668945,
      "learning_rate": 1.992653914399121e-05,
      "loss": 0.0532,
      "step": 159
    },
    {
      "epoch": 0.13559322033898305,
      "grad_norm": 1.7055613994598389,
      "learning_rate": 1.992291665383325e-05,
      "loss": 0.0373,
      "step": 160
    },
    {
      "epoch": 0.13559322033898305,
      "eval_accuracy": 0.9985815602836879,
      "eval_f1": 0.9974160206718347,
      "eval_loss": 0.009858837351202965,
      "eval_precision": 1.0,
      "eval_recall": 0.9948453608247423,
      "eval_runtime": 49.8997,
      "eval_samples_per_second": 5.852,
      "eval_steps_per_second": 0.2,
      "step": 160
    },
    {
      "epoch": 0.13644067796610168,
      "grad_norm": 4.821517467498779,
      "learning_rate": 1.9919207329688974e-05,
      "loss": 0.0473,
      "step": 161
    },
    {
      "epoch": 0.13728813559322034,
      "grad_norm": 3.094421863555908,
      "learning_rate": 1.9915411204018137e-05,
      "loss": 0.0347,
      "step": 162
    },
    {
      "epoch": 0.13813559322033897,
      "grad_norm": 2.942777156829834,
      "learning_rate": 1.9911528310040073e-05,
      "loss": 0.0534,
      "step": 163
    },
    {
      "epoch": 0.13898305084745763,
      "grad_norm": 1.5976642370224,
      "learning_rate": 1.990755868173342e-05,
      "loss": 0.0214,
      "step": 164
    },
    {
      "epoch": 0.13983050847457626,
      "grad_norm": 1.8799856901168823,
      "learning_rate": 1.9903502353835812e-05,
      "loss": 0.0335,
      "step": 165
    },
    {
      "epoch": 0.14067796610169492,
      "grad_norm": 1.2853425741195679,
      "learning_rate": 1.989935936184358e-05,
      "loss": 0.0168,
      "step": 166
    },
    {
      "epoch": 0.14152542372881355,
      "grad_norm": 0.8122027516365051,
      "learning_rate": 1.9895129742011434e-05,
      "loss": 0.0137,
      "step": 167
    },
    {
      "epoch": 0.1423728813559322,
      "grad_norm": 3.085028886795044,
      "learning_rate": 1.989081353135216e-05,
      "loss": 0.0671,
      "step": 168
    },
    {
      "epoch": 0.14322033898305084,
      "grad_norm": 2.514724016189575,
      "learning_rate": 1.9886410767636284e-05,
      "loss": 0.0641,
      "step": 169
    },
    {
      "epoch": 0.1440677966101695,
      "grad_norm": 1.2149631977081299,
      "learning_rate": 1.9881921489391738e-05,
      "loss": 0.024,
      "step": 170
    },
    {
      "epoch": 0.14491525423728813,
      "grad_norm": 4.677899360656738,
      "learning_rate": 1.9877345735903546e-05,
      "loss": 0.0553,
      "step": 171
    },
    {
      "epoch": 0.14576271186440679,
      "grad_norm": 0.9889124631881714,
      "learning_rate": 1.9872683547213446e-05,
      "loss": 0.025,
      "step": 172
    },
    {
      "epoch": 0.14661016949152542,
      "grad_norm": 1.9920752048492432,
      "learning_rate": 1.9867934964119575e-05,
      "loss": 0.0254,
      "step": 173
    },
    {
      "epoch": 0.14745762711864407,
      "grad_norm": 1.7707115411758423,
      "learning_rate": 1.986310002817608e-05,
      "loss": 0.0258,
      "step": 174
    },
    {
      "epoch": 0.1483050847457627,
      "grad_norm": 1.0819811820983887,
      "learning_rate": 1.9858178781692777e-05,
      "loss": 0.021,
      "step": 175
    },
    {
      "epoch": 0.14915254237288136,
      "grad_norm": 1.0780267715454102,
      "learning_rate": 1.985317126773477e-05,
      "loss": 0.0194,
      "step": 176
    },
    {
      "epoch": 0.15,
      "grad_norm": 2.7838480472564697,
      "learning_rate": 1.9848077530122083e-05,
      "loss": 0.0543,
      "step": 177
    },
    {
      "epoch": 0.15084745762711865,
      "grad_norm": 1.6005308628082275,
      "learning_rate": 1.984289761342926e-05,
      "loss": 0.0216,
      "step": 178
    },
    {
      "epoch": 0.15169491525423728,
      "grad_norm": 1.7227445840835571,
      "learning_rate": 1.9837631562984995e-05,
      "loss": 0.0232,
      "step": 179
    },
    {
      "epoch": 0.15254237288135594,
      "grad_norm": 2.9609763622283936,
      "learning_rate": 1.983227942487172e-05,
      "loss": 0.0357,
      "step": 180
    },
    {
      "epoch": 0.15254237288135594,
      "eval_accuracy": 0.9971631205673759,
      "eval_f1": 0.9948453608247423,
      "eval_loss": 0.007280215620994568,
      "eval_precision": 0.9948453608247423,
      "eval_recall": 0.9948453608247423,
      "eval_runtime": 50.033,
      "eval_samples_per_second": 5.836,
      "eval_steps_per_second": 0.2,
      "step": 180
    },
    {
      "epoch": 0.15338983050847457,
      "grad_norm": 1.3586597442626953,
      "learning_rate": 1.982684124592521e-05,
      "loss": 0.0248,
      "step": 181
    },
    {
      "epoch": 0.15423728813559323,
      "grad_norm": 2.4621241092681885,
      "learning_rate": 1.9821317073734173e-05,
      "loss": 0.0244,
      "step": 182
    },
    {
      "epoch": 0.15508474576271186,
      "grad_norm": 1.4555177688598633,
      "learning_rate": 1.9815706956639824e-05,
      "loss": 0.0252,
      "step": 183
    },
    {
      "epoch": 0.15593220338983052,
      "grad_norm": 3.31247878074646,
      "learning_rate": 1.981001094373548e-05,
      "loss": 0.029,
      "step": 184
    },
    {
      "epoch": 0.15677966101694915,
      "grad_norm": 1.3305749893188477,
      "learning_rate": 1.9804229084866103e-05,
      "loss": 0.0071,
      "step": 185
    },
    {
      "epoch": 0.1576271186440678,
      "grad_norm": 2.1134912967681885,
      "learning_rate": 1.9798361430627898e-05,
      "loss": 0.0223,
      "step": 186
    },
    {
      "epoch": 0.15847457627118644,
      "grad_norm": 2.255300521850586,
      "learning_rate": 1.979240803236785e-05,
      "loss": 0.0165,
      "step": 187
    },
    {
      "epoch": 0.15932203389830507,
      "grad_norm": 1.72796630859375,
      "learning_rate": 1.9786368942183262e-05,
      "loss": 0.0216,
      "step": 188
    },
    {
      "epoch": 0.16016949152542373,
      "grad_norm": 3.4896645545959473,
      "learning_rate": 1.9780244212921333e-05,
      "loss": 0.0188,
      "step": 189
    },
    {
      "epoch": 0.16101694915254236,
      "grad_norm": 8.25186538696289,
      "learning_rate": 1.9774033898178668e-05,
      "loss": 0.0585,
      "step": 190
    },
    {
      "epoch": 0.16186440677966102,
      "grad_norm": 2.215669870376587,
      "learning_rate": 1.9767738052300816e-05,
      "loss": 0.015,
      "step": 191
    },
    {
      "epoch": 0.16271186440677965,
      "grad_norm": 1.952848196029663,
      "learning_rate": 1.9761356730381806e-05,
      "loss": 0.023,
      "step": 192
    },
    {
      "epoch": 0.1635593220338983,
      "grad_norm": 2.2259209156036377,
      "learning_rate": 1.975488998826364e-05,
      "loss": 0.0186,
      "step": 193
    },
    {
      "epoch": 0.16440677966101694,
      "grad_norm": 2.9435532093048096,
      "learning_rate": 1.974833788253584e-05,
      "loss": 0.0237,
      "step": 194
    },
    {
      "epoch": 0.1652542372881356,
      "grad_norm": 3.2941129207611084,
      "learning_rate": 1.9741700470534904e-05,
      "loss": 0.0168,
      "step": 195
    },
    {
      "epoch": 0.16610169491525423,
      "grad_norm": 2.563314437866211,
      "learning_rate": 1.9734977810343868e-05,
      "loss": 0.0245,
      "step": 196
    },
    {
      "epoch": 0.1669491525423729,
      "grad_norm": 5.807168006896973,
      "learning_rate": 1.9728169960791736e-05,
      "loss": 0.0526,
      "step": 197
    },
    {
      "epoch": 0.16779661016949152,
      "grad_norm": 2.7468652725219727,
      "learning_rate": 1.9721276981452995e-05,
      "loss": 0.03,
      "step": 198
    },
    {
      "epoch": 0.16864406779661018,
      "grad_norm": 7.025511741638184,
      "learning_rate": 1.97142989326471e-05,
      "loss": 0.0794,
      "step": 199
    },
    {
      "epoch": 0.1694915254237288,
      "grad_norm": 1.384521722793579,
      "learning_rate": 1.9707235875437932e-05,
      "loss": 0.0147,
      "step": 200
    },
    {
      "epoch": 0.1694915254237288,
      "eval_accuracy": 0.9985815602836879,
      "eval_f1": 0.9974160206718347,
      "eval_loss": 0.010543613694608212,
      "eval_precision": 1.0,
      "eval_recall": 0.9948453608247423,
      "eval_runtime": 50.7835,
      "eval_samples_per_second": 5.75,
      "eval_steps_per_second": 0.197,
      "step": 200
    },
    {
      "epoch": 0.17033898305084746,
      "grad_norm": 2.295042037963867,
      "learning_rate": 1.9700087871633267e-05,
      "loss": 0.0225,
      "step": 201
    },
    {
      "epoch": 0.1711864406779661,
      "grad_norm": 1.9021865129470825,
      "learning_rate": 1.9692854983784235e-05,
      "loss": 0.0282,
      "step": 202
    },
    {
      "epoch": 0.17203389830508475,
      "grad_norm": 6.971744060516357,
      "learning_rate": 1.9685537275184776e-05,
      "loss": 0.0743,
      "step": 203
    },
    {
      "epoch": 0.17288135593220338,
      "grad_norm": 3.0627219676971436,
      "learning_rate": 1.9678134809871085e-05,
      "loss": 0.0305,
      "step": 204
    },
    {
      "epoch": 0.17372881355932204,
      "grad_norm": 2.7916667461395264,
      "learning_rate": 1.9670647652621044e-05,
      "loss": 0.0407,
      "step": 205
    },
    {
      "epoch": 0.17457627118644067,
      "grad_norm": 0.5132026076316833,
      "learning_rate": 1.966307586895367e-05,
      "loss": 0.0058,
      "step": 206
    },
    {
      "epoch": 0.17542372881355933,
      "grad_norm": 2.076672077178955,
      "learning_rate": 1.9655419525128528e-05,
      "loss": 0.0275,
      "step": 207
    },
    {
      "epoch": 0.17627118644067796,
      "grad_norm": 1.9575265645980835,
      "learning_rate": 1.9647678688145163e-05,
      "loss": 0.0178,
      "step": 208
    },
    {
      "epoch": 0.17711864406779662,
      "grad_norm": 2.161008358001709,
      "learning_rate": 1.9639853425742496e-05,
      "loss": 0.0262,
      "step": 209
    },
    {
      "epoch": 0.17796610169491525,
      "grad_norm": 2.026916742324829,
      "learning_rate": 1.963194380639825e-05,
      "loss": 0.0257,
      "step": 210
    },
    {
      "epoch": 0.1788135593220339,
      "grad_norm": 1.033382773399353,
      "learning_rate": 1.9623949899328352e-05,
      "loss": 0.017,
      "step": 211
    },
    {
      "epoch": 0.17966101694915254,
      "grad_norm": 1.5789072513580322,
      "learning_rate": 1.9615871774486293e-05,
      "loss": 0.0241,
      "step": 212
    },
    {
      "epoch": 0.1805084745762712,
      "grad_norm": 1.8820958137512207,
      "learning_rate": 1.960770950256257e-05,
      "loss": 0.031,
      "step": 213
    },
    {
      "epoch": 0.18135593220338983,
      "grad_norm": 3.501945734024048,
      "learning_rate": 1.959946315498402e-05,
      "loss": 0.0479,
      "step": 214
    },
    {
      "epoch": 0.18220338983050846,
      "grad_norm": 1.3452684879302979,
      "learning_rate": 1.959113280391322e-05,
      "loss": 0.0158,
      "step": 215
    },
    {
      "epoch": 0.18305084745762712,
      "grad_norm": 2.5982766151428223,
      "learning_rate": 1.9582718522247854e-05,
      "loss": 0.0331,
      "step": 216
    },
    {
      "epoch": 0.18389830508474575,
      "grad_norm": 3.8872103691101074,
      "learning_rate": 1.9574220383620054e-05,
      "loss": 0.023,
      "step": 217
    },
    {
      "epoch": 0.1847457627118644,
      "grad_norm": 1.6585066318511963,
      "learning_rate": 1.9565638462395796e-05,
      "loss": 0.0235,
      "step": 218
    },
    {
      "epoch": 0.18559322033898304,
      "grad_norm": 1.910556435585022,
      "learning_rate": 1.95569728336742e-05,
      "loss": 0.0249,
      "step": 219
    },
    {
      "epoch": 0.1864406779661017,
      "grad_norm": 2.956751823425293,
      "learning_rate": 1.954822357328692e-05,
      "loss": 0.0271,
      "step": 220
    },
    {
      "epoch": 0.1864406779661017,
      "eval_accuracy": 0.9985815602836879,
      "eval_f1": 0.9974160206718347,
      "eval_loss": 0.007490006275475025,
      "eval_precision": 1.0,
      "eval_recall": 0.9948453608247423,
      "eval_runtime": 50.7062,
      "eval_samples_per_second": 5.759,
      "eval_steps_per_second": 0.197,
      "step": 220
    },
    {
      "epoch": 0.18728813559322033,
      "grad_norm": 3.494168281555176,
      "learning_rate": 1.9539390757797444e-05,
      "loss": 0.0706,
      "step": 221
    },
    {
      "epoch": 0.188135593220339,
      "grad_norm": 2.3897652626037598,
      "learning_rate": 1.9530474464500445e-05,
      "loss": 0.0252,
      "step": 222
    },
    {
      "epoch": 0.18898305084745762,
      "grad_norm": 2.2590034008026123,
      "learning_rate": 1.9521474771421093e-05,
      "loss": 0.033,
      "step": 223
    },
    {
      "epoch": 0.18983050847457628,
      "grad_norm": 3.1695659160614014,
      "learning_rate": 1.9512391757314382e-05,
      "loss": 0.0475,
      "step": 224
    },
    {
      "epoch": 0.1906779661016949,
      "grad_norm": 0.6561757922172546,
      "learning_rate": 1.950322550166444e-05,
      "loss": 0.0089,
      "step": 225
    },
    {
      "epoch": 0.19152542372881357,
      "grad_norm": 0.832501232624054,
      "learning_rate": 1.9493976084683814e-05,
      "loss": 0.0064,
      "step": 226
    },
    {
      "epoch": 0.1923728813559322,
      "grad_norm": 2.210726022720337,
      "learning_rate": 1.94846435873128e-05,
      "loss": 0.0372,
      "step": 227
    },
    {
      "epoch": 0.19322033898305085,
      "grad_norm": 1.805579662322998,
      "learning_rate": 1.9475228091218712e-05,
      "loss": 0.0288,
      "step": 228
    },
    {
      "epoch": 0.19406779661016949,
      "grad_norm": 1.477453351020813,
      "learning_rate": 1.946572967879517e-05,
      "loss": 0.01,
      "step": 229
    },
    {
      "epoch": 0.19491525423728814,
      "grad_norm": 1.16657555103302,
      "learning_rate": 1.9456148433161387e-05,
      "loss": 0.0183,
      "step": 230
    },
    {
      "epoch": 0.19576271186440677,
      "grad_norm": 6.658266544342041,
      "learning_rate": 1.944648443816144e-05,
      "loss": 0.0464,
      "step": 231
    },
    {
      "epoch": 0.19661016949152543,
      "grad_norm": 1.6691462993621826,
      "learning_rate": 1.9436737778363526e-05,
      "loss": 0.014,
      "step": 232
    },
    {
      "epoch": 0.19745762711864406,
      "grad_norm": 1.3182052373886108,
      "learning_rate": 1.942690853905924e-05,
      "loss": 0.0092,
      "step": 233
    },
    {
      "epoch": 0.19830508474576272,
      "grad_norm": 0.46388718485832214,
      "learning_rate": 1.94169968062628e-05,
      "loss": 0.004,
      "step": 234
    },
    {
      "epoch": 0.19915254237288135,
      "grad_norm": 3.9312496185302734,
      "learning_rate": 1.9407002666710334e-05,
      "loss": 0.0451,
      "step": 235
    },
    {
      "epoch": 0.2,
      "grad_norm": 1.5306397676467896,
      "learning_rate": 1.9396926207859085e-05,
      "loss": 0.0169,
      "step": 236
    },
    {
      "epoch": 0.20084745762711864,
      "grad_norm": 1.4190640449523926,
      "learning_rate": 1.9386767517886666e-05,
      "loss": 0.0248,
      "step": 237
    },
    {
      "epoch": 0.2016949152542373,
      "grad_norm": 2.2406575679779053,
      "learning_rate": 1.937652668569028e-05,
      "loss": 0.0259,
      "step": 238
    },
    {
      "epoch": 0.20254237288135593,
      "grad_norm": 0.8504940867424011,
      "learning_rate": 1.9366203800885944e-05,
      "loss": 0.0076,
      "step": 239
    },
    {
      "epoch": 0.2033898305084746,
      "grad_norm": 1.1296645402908325,
      "learning_rate": 1.9355798953807715e-05,
      "loss": 0.0071,
      "step": 240
    },
    {
      "epoch": 0.2033898305084746,
      "eval_accuracy": 0.9985815602836879,
      "eval_f1": 0.9974160206718347,
      "eval_loss": 0.007261006161570549,
      "eval_precision": 1.0,
      "eval_recall": 0.9948453608247423,
      "eval_runtime": 50.5554,
      "eval_samples_per_second": 5.776,
      "eval_steps_per_second": 0.198,
      "step": 240
    },
    {
      "epoch": 0.20423728813559322,
      "grad_norm": 2.6094491481781006,
      "learning_rate": 1.934531223550687e-05,
      "loss": 0.0298,
      "step": 241
    },
    {
      "epoch": 0.20508474576271185,
      "grad_norm": 3.385869264602661,
      "learning_rate": 1.933474373775115e-05,
      "loss": 0.0282,
      "step": 242
    },
    {
      "epoch": 0.2059322033898305,
      "grad_norm": 3.9192473888397217,
      "learning_rate": 1.932409355302392e-05,
      "loss": 0.0514,
      "step": 243
    },
    {
      "epoch": 0.20677966101694914,
      "grad_norm": 2.312788724899292,
      "learning_rate": 1.9313361774523387e-05,
      "loss": 0.029,
      "step": 244
    },
    {
      "epoch": 0.2076271186440678,
      "grad_norm": 1.603360891342163,
      "learning_rate": 1.9302548496161765e-05,
      "loss": 0.0193,
      "step": 245
    },
    {
      "epoch": 0.20847457627118643,
      "grad_norm": 3.1534547805786133,
      "learning_rate": 1.9291653812564468e-05,
      "loss": 0.0516,
      "step": 246
    },
    {
      "epoch": 0.2093220338983051,
      "grad_norm": 0.8444193005561829,
      "learning_rate": 1.9280677819069273e-05,
      "loss": 0.0084,
      "step": 247
    },
    {
      "epoch": 0.21016949152542372,
      "grad_norm": 1.4498813152313232,
      "learning_rate": 1.926962061172548e-05,
      "loss": 0.012,
      "step": 248
    },
    {
      "epoch": 0.21101694915254238,
      "grad_norm": 4.520916938781738,
      "learning_rate": 1.9258482287293097e-05,
      "loss": 0.0292,
      "step": 249
    },
    {
      "epoch": 0.211864406779661,
      "grad_norm": 4.337013244628906,
      "learning_rate": 1.924726294324196e-05,
      "loss": 0.0285,
      "step": 250
    },
    {
      "epoch": 0.21271186440677967,
      "grad_norm": 3.2843096256256104,
      "learning_rate": 1.9235962677750898e-05,
      "loss": 0.0424,
      "step": 251
    },
    {
      "epoch": 0.2135593220338983,
      "grad_norm": 2.163046360015869,
      "learning_rate": 1.922458158970688e-05,
      "loss": 0.0235,
      "step": 252
    },
    {
      "epoch": 0.21440677966101696,
      "grad_norm": 0.903529167175293,
      "learning_rate": 1.921311977870413e-05,
      "loss": 0.0111,
      "step": 253
    },
    {
      "epoch": 0.21525423728813559,
      "grad_norm": 0.9559667110443115,
      "learning_rate": 1.9201577345043282e-05,
      "loss": 0.0097,
      "step": 254
    },
    {
      "epoch": 0.21610169491525424,
      "grad_norm": 2.765850782394409,
      "learning_rate": 1.918995438973047e-05,
      "loss": 0.0173,
      "step": 255
    },
    {
      "epoch": 0.21694915254237288,
      "grad_norm": 1.1641409397125244,
      "learning_rate": 1.917825101447647e-05,
      "loss": 0.0073,
      "step": 256
    },
    {
      "epoch": 0.21779661016949153,
      "grad_norm": 1.1337021589279175,
      "learning_rate": 1.91664673216958e-05,
      "loss": 0.0129,
      "step": 257
    },
    {
      "epoch": 0.21864406779661016,
      "grad_norm": 2.058060646057129,
      "learning_rate": 1.9154603414505825e-05,
      "loss": 0.0418,
      "step": 258
    },
    {
      "epoch": 0.21949152542372882,
      "grad_norm": 2.029142379760742,
      "learning_rate": 1.9142659396725862e-05,
      "loss": 0.0289,
      "step": 259
    },
    {
      "epoch": 0.22033898305084745,
      "grad_norm": 1.0298879146575928,
      "learning_rate": 1.9130635372876245e-05,
      "loss": 0.009,
      "step": 260
    },
    {
      "epoch": 0.22033898305084745,
      "eval_accuracy": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.002083389787003398,
      "eval_precision": 1.0,
      "eval_recall": 1.0,
      "eval_runtime": 50.0162,
      "eval_samples_per_second": 5.838,
      "eval_steps_per_second": 0.2,
      "step": 260
    },
    {
      "epoch": 0.2211864406779661,
      "grad_norm": 1.038118839263916,
      "learning_rate": 1.9118531448177446e-05,
      "loss": 0.0065,
      "step": 261
    },
    {
      "epoch": 0.22203389830508474,
      "grad_norm": 1.853901743888855,
      "learning_rate": 1.9106347728549134e-05,
      "loss": 0.0317,
      "step": 262
    },
    {
      "epoch": 0.2228813559322034,
      "grad_norm": 1.197831392288208,
      "learning_rate": 1.909408432060925e-05,
      "loss": 0.0067,
      "step": 263
    },
    {
      "epoch": 0.22372881355932203,
      "grad_norm": 1.2054872512817383,
      "learning_rate": 1.908174133167307e-05,
      "loss": 0.0105,
      "step": 264
    },
    {
      "epoch": 0.2245762711864407,
      "grad_norm": 2.5519094467163086,
      "learning_rate": 1.906931886975228e-05,
      "loss": 0.0241,
      "step": 265
    },
    {
      "epoch": 0.22542372881355932,
      "grad_norm": 1.8726714849472046,
      "learning_rate": 1.9056817043554024e-05,
      "loss": 0.0144,
      "step": 266
    },
    {
      "epoch": 0.22627118644067798,
      "grad_norm": 3.216784715652466,
      "learning_rate": 1.9044235962479945e-05,
      "loss": 0.0338,
      "step": 267
    },
    {
      "epoch": 0.2271186440677966,
      "grad_norm": 2.3170483112335205,
      "learning_rate": 1.903157573662524e-05,
      "loss": 0.0178,
      "step": 268
    },
    {
      "epoch": 0.22796610169491524,
      "grad_norm": 3.330758571624756,
      "learning_rate": 1.9018836476777675e-05,
      "loss": 0.0404,
      "step": 269
    },
    {
      "epoch": 0.2288135593220339,
      "grad_norm": 3.121005058288574,
      "learning_rate": 1.9006018294416648e-05,
      "loss": 0.0286,
      "step": 270
    },
    {
      "epoch": 0.22966101694915253,
      "grad_norm": 0.9276627898216248,
      "learning_rate": 1.8993121301712194e-05,
      "loss": 0.0084,
      "step": 271
    },
    {
      "epoch": 0.2305084745762712,
      "grad_norm": 0.7775290012359619,
      "learning_rate": 1.8980145611523996e-05,
      "loss": 0.0053,
      "step": 272
    },
    {
      "epoch": 0.23135593220338982,
      "grad_norm": 3.8352859020233154,
      "learning_rate": 1.8967091337400418e-05,
      "loss": 0.0281,
      "step": 273
    },
    {
      "epoch": 0.23220338983050848,
      "grad_norm": 1.0906392335891724,
      "learning_rate": 1.895395859357749e-05,
      "loss": 0.0128,
      "step": 274
    },
    {
      "epoch": 0.2330508474576271,
      "grad_norm": 1.1791564226150513,
      "learning_rate": 1.894074749497793e-05,
      "loss": 0.0124,
      "step": 275
    },
    {
      "epoch": 0.23389830508474577,
      "grad_norm": 1.4967304468154907,
      "learning_rate": 1.8927458157210125e-05,
      "loss": 0.015,
      "step": 276
    },
    {
      "epoch": 0.2347457627118644,
      "grad_norm": 1.3809508085250854,
      "learning_rate": 1.8914090696567104e-05,
      "loss": 0.0089,
      "step": 277
    },
    {
      "epoch": 0.23559322033898306,
      "grad_norm": 1.202942132949829,
      "learning_rate": 1.8900645230025566e-05,
      "loss": 0.0113,
      "step": 278
    },
    {
      "epoch": 0.2364406779661017,
      "grad_norm": 1.3019424676895142,
      "learning_rate": 1.8887121875244804e-05,
      "loss": 0.008,
      "step": 279
    },
    {
      "epoch": 0.23728813559322035,
      "grad_norm": 1.8381810188293457,
      "learning_rate": 1.8873520750565716e-05,
      "loss": 0.0288,
      "step": 280
    },
    {
      "epoch": 0.23728813559322035,
      "eval_accuracy": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.0014825169928371906,
      "eval_precision": 1.0,
      "eval_recall": 1.0,
      "eval_runtime": 49.7093,
      "eval_samples_per_second": 5.874,
      "eval_steps_per_second": 0.201,
      "step": 280
    },
    {
      "epoch": 0.23813559322033898,
      "grad_norm": 0.7632168531417847,
      "learning_rate": 1.8859841975009747e-05,
      "loss": 0.0062,
      "step": 281
    },
    {
      "epoch": 0.23898305084745763,
      "grad_norm": 2.5059711933135986,
      "learning_rate": 1.884608566827785e-05,
      "loss": 0.0304,
      "step": 282
    },
    {
      "epoch": 0.23983050847457626,
      "grad_norm": 2.896942138671875,
      "learning_rate": 1.8832251950749443e-05,
      "loss": 0.0271,
      "step": 283
    },
    {
      "epoch": 0.24067796610169492,
      "grad_norm": 2.438624620437622,
      "learning_rate": 1.8818340943481362e-05,
      "loss": 0.0236,
      "step": 284
    },
    {
      "epoch": 0.24152542372881355,
      "grad_norm": 3.87087082862854,
      "learning_rate": 1.880435276820678e-05,
      "loss": 0.0337,
      "step": 285
    },
    {
      "epoch": 0.2423728813559322,
      "grad_norm": 1.3031063079833984,
      "learning_rate": 1.8790287547334178e-05,
      "loss": 0.009,
      "step": 286
    },
    {
      "epoch": 0.24322033898305084,
      "grad_norm": 2.244393825531006,
      "learning_rate": 1.8776145403946226e-05,
      "loss": 0.0331,
      "step": 287
    },
    {
      "epoch": 0.2440677966101695,
      "grad_norm": 1.3984683752059937,
      "learning_rate": 1.8761926461798743e-05,
      "loss": 0.0095,
      "step": 288
    },
    {
      "epoch": 0.24491525423728813,
      "grad_norm": 0.9854875206947327,
      "learning_rate": 1.874763084531961e-05,
      "loss": 0.0076,
      "step": 289
    },
    {
      "epoch": 0.2457627118644068,
      "grad_norm": 1.9005022048950195,
      "learning_rate": 1.8733258679607674e-05,
      "loss": 0.0169,
      "step": 290
    },
    {
      "epoch": 0.24661016949152542,
      "grad_norm": 2.174389600753784,
      "learning_rate": 1.871881009043163e-05,
      "loss": 0.0357,
      "step": 291
    },
    {
      "epoch": 0.24745762711864408,
      "grad_norm": 3.0177578926086426,
      "learning_rate": 1.8704285204228973e-05,
      "loss": 0.0373,
      "step": 292
    },
    {
      "epoch": 0.2483050847457627,
      "grad_norm": 2.5867350101470947,
      "learning_rate": 1.868968414810484e-05,
      "loss": 0.035,
      "step": 293
    },
    {
      "epoch": 0.24915254237288137,
      "grad_norm": 1.4265027046203613,
      "learning_rate": 1.8675007049830937e-05,
      "loss": 0.0138,
      "step": 294
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.97405606508255,
      "learning_rate": 1.866025403784439e-05,
      "loss": 0.0102,
      "step": 295
    },
    {
      "epoch": 0.25084745762711863,
      "grad_norm": 3.0567164421081543,
      "learning_rate": 1.8645425241246636e-05,
      "loss": 0.067,
      "step": 296
    },
    {
      "epoch": 0.25169491525423726,
      "grad_norm": 1.839958667755127,
      "learning_rate": 1.8630520789802308e-05,
      "loss": 0.0252,
      "step": 297
    },
    {
      "epoch": 0.25254237288135595,
      "grad_norm": 1.2445701360702515,
      "learning_rate": 1.8615540813938063e-05,
      "loss": 0.0391,
      "step": 298
    },
    {
      "epoch": 0.2533898305084746,
      "grad_norm": 2.647850275039673,
      "learning_rate": 1.860048544474147e-05,
      "loss": 0.0212,
      "step": 299
    },
    {
      "epoch": 0.2542372881355932,
      "grad_norm": 2.123107433319092,
      "learning_rate": 1.858535481395986e-05,
      "loss": 0.0236,
      "step": 300
    },
    {
      "epoch": 0.2542372881355932,
      "eval_accuracy": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.0011347213294357061,
      "eval_precision": 1.0,
      "eval_recall": 1.0,
      "eval_runtime": 52.457,
      "eval_samples_per_second": 5.566,
      "eval_steps_per_second": 0.191,
      "step": 300
    },
    {
      "epoch": 0.25508474576271184,
      "grad_norm": 0.9495724439620972,
      "learning_rate": 1.8570149053999154e-05,
      "loss": 0.0102,
      "step": 301
    },
    {
      "epoch": 0.2559322033898305,
      "grad_norm": 1.3956694602966309,
      "learning_rate": 1.8554868297922728e-05,
      "loss": 0.0094,
      "step": 302
    },
    {
      "epoch": 0.25677966101694916,
      "grad_norm": 2.1316022872924805,
      "learning_rate": 1.853951267945023e-05,
      "loss": 0.0169,
      "step": 303
    },
    {
      "epoch": 0.2576271186440678,
      "grad_norm": 1.0728296041488647,
      "learning_rate": 1.852408233295643e-05,
      "loss": 0.0131,
      "step": 304
    },
    {
      "epoch": 0.2584745762711864,
      "grad_norm": 1.8492826223373413,
      "learning_rate": 1.8508577393470014e-05,
      "loss": 0.0292,
      "step": 305
    },
    {
      "epoch": 0.2593220338983051,
      "grad_norm": 1.082140564918518,
      "learning_rate": 1.8492997996672436e-05,
      "loss": 0.0094,
      "step": 306
    },
    {
      "epoch": 0.26016949152542374,
      "grad_norm": 2.817040205001831,
      "learning_rate": 1.8477344278896708e-05,
      "loss": 0.0222,
      "step": 307
    },
    {
      "epoch": 0.26101694915254237,
      "grad_norm": 1.3377786874771118,
      "learning_rate": 1.846161637712622e-05,
      "loss": 0.0183,
      "step": 308
    },
    {
      "epoch": 0.261864406779661,
      "grad_norm": 2.062629222869873,
      "learning_rate": 1.8445814428993528e-05,
      "loss": 0.028,
      "step": 309
    },
    {
      "epoch": 0.2627118644067797,
      "grad_norm": 2.208967447280884,
      "learning_rate": 1.8429938572779154e-05,
      "loss": 0.0267,
      "step": 310
    },
    {
      "epoch": 0.2635593220338983,
      "grad_norm": 1.015850305557251,
      "learning_rate": 1.8413988947410388e-05,
      "loss": 0.0112,
      "step": 311
    },
    {
      "epoch": 0.26440677966101694,
      "grad_norm": 1.2069474458694458,
      "learning_rate": 1.839796569246006e-05,
      "loss": 0.0122,
      "step": 312
    },
    {
      "epoch": 0.2652542372881356,
      "grad_norm": 1.5780760049819946,
      "learning_rate": 1.8381868948145317e-05,
      "loss": 0.0197,
      "step": 313
    },
    {
      "epoch": 0.26610169491525426,
      "grad_norm": 0.7285755276679993,
      "learning_rate": 1.836569885532641e-05,
      "loss": 0.0064,
      "step": 314
    },
    {
      "epoch": 0.2669491525423729,
      "grad_norm": 2.682543992996216,
      "learning_rate": 1.8349455555505445e-05,
      "loss": 0.0285,
      "step": 315
    },
    {
      "epoch": 0.2677966101694915,
      "grad_norm": 1.949136734008789,
      "learning_rate": 1.833313919082515e-05,
      "loss": 0.0232,
      "step": 316
    },
    {
      "epoch": 0.26864406779661015,
      "grad_norm": 3.491502285003662,
      "learning_rate": 1.8316749904067637e-05,
      "loss": 0.0264,
      "step": 317
    },
    {
      "epoch": 0.26949152542372884,
      "grad_norm": 0.8317990303039551,
      "learning_rate": 1.8300287838653155e-05,
      "loss": 0.0048,
      "step": 318
    },
    {
      "epoch": 0.27033898305084747,
      "grad_norm": 1.39896821975708,
      "learning_rate": 1.828375313863881e-05,
      "loss": 0.0149,
      "step": 319
    },
    {
      "epoch": 0.2711864406779661,
      "grad_norm": 1.3299435377120972,
      "learning_rate": 1.8267145948717338e-05,
      "loss": 0.0053,
      "step": 320
    },
    {
      "epoch": 0.2711864406779661,
      "eval_accuracy": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.0007786459173075855,
      "eval_precision": 1.0,
      "eval_recall": 1.0,
      "eval_runtime": 52.8212,
      "eval_samples_per_second": 5.528,
      "eval_steps_per_second": 0.189,
      "step": 320
    },
    {
      "epoch": 0.27203389830508473,
      "grad_norm": 0.4707522392272949,
      "learning_rate": 1.8250466414215816e-05,
      "loss": 0.0044,
      "step": 321
    },
    {
      "epoch": 0.27288135593220336,
      "grad_norm": 2.0582358837127686,
      "learning_rate": 1.8233714681094405e-05,
      "loss": 0.0194,
      "step": 322
    },
    {
      "epoch": 0.27372881355932205,
      "grad_norm": 2.306215286254883,
      "learning_rate": 1.8216890895945062e-05,
      "loss": 0.0157,
      "step": 323
    },
    {
      "epoch": 0.2745762711864407,
      "grad_norm": 0.5328612923622131,
      "learning_rate": 1.8199995205990256e-05,
      "loss": 0.0025,
      "step": 324
    },
    {
      "epoch": 0.2754237288135593,
      "grad_norm": 1.3948057889938354,
      "learning_rate": 1.818302775908169e-05,
      "loss": 0.0114,
      "step": 325
    },
    {
      "epoch": 0.27627118644067794,
      "grad_norm": 0.7532712817192078,
      "learning_rate": 1.8165988703699003e-05,
      "loss": 0.0047,
      "step": 326
    },
    {
      "epoch": 0.2771186440677966,
      "grad_norm": 1.3939229249954224,
      "learning_rate": 1.814887818894846e-05,
      "loss": 0.0169,
      "step": 327
    },
    {
      "epoch": 0.27796610169491526,
      "grad_norm": 1.9840660095214844,
      "learning_rate": 1.813169636456167e-05,
      "loss": 0.0139,
      "step": 328
    },
    {
      "epoch": 0.2788135593220339,
      "grad_norm": 3.3618903160095215,
      "learning_rate": 1.8114443380894248e-05,
      "loss": 0.0212,
      "step": 329
    },
    {
      "epoch": 0.2796610169491525,
      "grad_norm": 1.521863579750061,
      "learning_rate": 1.8097119388924524e-05,
      "loss": 0.0063,
      "step": 330
    },
    {
      "epoch": 0.2805084745762712,
      "grad_norm": 2.661334991455078,
      "learning_rate": 1.8079724540252204e-05,
      "loss": 0.0212,
      "step": 331
    },
    {
      "epoch": 0.28135593220338984,
      "grad_norm": 0.9505246877670288,
      "learning_rate": 1.8062258987097062e-05,
      "loss": 0.0044,
      "step": 332
    },
    {
      "epoch": 0.28220338983050847,
      "grad_norm": 2.677922010421753,
      "learning_rate": 1.8044722882297582e-05,
      "loss": 0.0323,
      "step": 333
    },
    {
      "epoch": 0.2830508474576271,
      "grad_norm": 2.3942182064056396,
      "learning_rate": 1.8027116379309637e-05,
      "loss": 0.0173,
      "step": 334
    },
    {
      "epoch": 0.2838983050847458,
      "grad_norm": 5.396221160888672,
      "learning_rate": 1.8009439632205162e-05,
      "loss": 0.0445,
      "step": 335
    },
    {
      "epoch": 0.2847457627118644,
      "grad_norm": 3.2957260608673096,
      "learning_rate": 1.7991692795670764e-05,
      "loss": 0.0344,
      "step": 336
    },
    {
      "epoch": 0.28559322033898304,
      "grad_norm": 2.7046103477478027,
      "learning_rate": 1.7973876025006407e-05,
      "loss": 0.0119,
      "step": 337
    },
    {
      "epoch": 0.2864406779661017,
      "grad_norm": 2.09260630607605,
      "learning_rate": 1.7955989476124035e-05,
      "loss": 0.0191,
      "step": 338
    },
    {
      "epoch": 0.28728813559322036,
      "grad_norm": 1.4881995916366577,
      "learning_rate": 1.7938033305546208e-05,
      "loss": 0.0198,
      "step": 339
    },
    {
      "epoch": 0.288135593220339,
      "grad_norm": 0.29988396167755127,
      "learning_rate": 1.7920007670404738e-05,
      "loss": 0.0028,
      "step": 340
    },
    {
      "epoch": 0.288135593220339,
      "eval_accuracy": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.0003622370131779462,
      "eval_precision": 1.0,
      "eval_recall": 1.0,
      "eval_runtime": 51.8576,
      "eval_samples_per_second": 5.631,
      "eval_steps_per_second": 0.193,
      "step": 340
    },
    {
      "epoch": 0.2889830508474576,
      "grad_norm": 1.238132357597351,
      "learning_rate": 1.7901912728439317e-05,
      "loss": 0.0105,
      "step": 341
    },
    {
      "epoch": 0.28983050847457625,
      "grad_norm": 5.88295316696167,
      "learning_rate": 1.7883748637996113e-05,
      "loss": 0.0363,
      "step": 342
    },
    {
      "epoch": 0.29067796610169494,
      "grad_norm": 1.8744484186172485,
      "learning_rate": 1.786551555802643e-05,
      "loss": 0.014,
      "step": 343
    },
    {
      "epoch": 0.29152542372881357,
      "grad_norm": 0.7737008333206177,
      "learning_rate": 1.7847213648085257e-05,
      "loss": 0.0071,
      "step": 344
    },
    {
      "epoch": 0.2923728813559322,
      "grad_norm": 1.2532923221588135,
      "learning_rate": 1.7828843068329923e-05,
      "loss": 0.015,
      "step": 345
    },
    {
      "epoch": 0.29322033898305083,
      "grad_norm": 1.273977279663086,
      "learning_rate": 1.781040397951868e-05,
      "loss": 0.0071,
      "step": 346
    },
    {
      "epoch": 0.2940677966101695,
      "grad_norm": 1.9330259561538696,
      "learning_rate": 1.7791896543009282e-05,
      "loss": 0.0245,
      "step": 347
    },
    {
      "epoch": 0.29491525423728815,
      "grad_norm": 1.0898295640945435,
      "learning_rate": 1.7773320920757597e-05,
      "loss": 0.0099,
      "step": 348
    },
    {
      "epoch": 0.2957627118644068,
      "grad_norm": 2.295070171356201,
      "learning_rate": 1.775467727531615e-05,
      "loss": 0.0212,
      "step": 349
    },
    {
      "epoch": 0.2966101694915254,
      "grad_norm": 2.575789213180542,
      "learning_rate": 1.7735965769832754e-05,
      "loss": 0.0204,
      "step": 350
    },
    {
      "epoch": 0.29745762711864404,
      "grad_norm": 0.6911354660987854,
      "learning_rate": 1.7717186568049048e-05,
      "loss": 0.0045,
      "step": 351
    },
    {
      "epoch": 0.2983050847457627,
      "grad_norm": 2.2805356979370117,
      "learning_rate": 1.7698339834299064e-05,
      "loss": 0.0148,
      "step": 352
    },
    {
      "epoch": 0.29915254237288136,
      "grad_norm": 2.1223855018615723,
      "learning_rate": 1.7679425733507802e-05,
      "loss": 0.0291,
      "step": 353
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.93767911195755,
      "learning_rate": 1.766044443118978e-05,
      "loss": 0.0048,
      "step": 354
    },
    {
      "epoch": 0.3008474576271186,
      "grad_norm": 1.8879729509353638,
      "learning_rate": 1.764139609344759e-05,
      "loss": 0.0196,
      "step": 355
    },
    {
      "epoch": 0.3016949152542373,
      "grad_norm": 1.6808807849884033,
      "learning_rate": 1.7622280886970436e-05,
      "loss": 0.0116,
      "step": 356
    },
    {
      "epoch": 0.30254237288135594,
      "grad_norm": 2.692596912384033,
      "learning_rate": 1.7603098979032683e-05,
      "loss": 0.0215,
      "step": 357
    },
    {
      "epoch": 0.30338983050847457,
      "grad_norm": 0.6760978698730469,
      "learning_rate": 1.7583850537492386e-05,
      "loss": 0.0053,
      "step": 358
    },
    {
      "epoch": 0.3042372881355932,
      "grad_norm": 0.8519519567489624,
      "learning_rate": 1.7564535730789835e-05,
      "loss": 0.0057,
      "step": 359
    },
    {
      "epoch": 0.3050847457627119,
      "grad_norm": 2.1830923557281494,
      "learning_rate": 1.7545154727946065e-05,
      "loss": 0.015,
      "step": 360
    },
    {
      "epoch": 0.3050847457627119,
      "eval_accuracy": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.00035791730624623597,
      "eval_precision": 1.0,
      "eval_recall": 1.0,
      "eval_runtime": 51.4513,
      "eval_samples_per_second": 5.675,
      "eval_steps_per_second": 0.194,
      "step": 360
    },
    {
      "epoch": 0.3059322033898305,
      "grad_norm": 1.3546723127365112,
      "learning_rate": 1.7525707698561383e-05,
      "loss": 0.0152,
      "step": 361
    },
    {
      "epoch": 0.30677966101694915,
      "grad_norm": 2.3119301795959473,
      "learning_rate": 1.7506194812813896e-05,
      "loss": 0.031,
      "step": 362
    },
    {
      "epoch": 0.3076271186440678,
      "grad_norm": 2.6761271953582764,
      "learning_rate": 1.7486616241457994e-05,
      "loss": 0.0133,
      "step": 363
    },
    {
      "epoch": 0.30847457627118646,
      "grad_norm": 1.6576277017593384,
      "learning_rate": 1.746697215582288e-05,
      "loss": 0.0095,
      "step": 364
    },
    {
      "epoch": 0.3093220338983051,
      "grad_norm": 2.716494083404541,
      "learning_rate": 1.7447262727811062e-05,
      "loss": 0.0229,
      "step": 365
    },
    {
      "epoch": 0.3101694915254237,
      "grad_norm": 2.4295156002044678,
      "learning_rate": 1.7427488129896852e-05,
      "loss": 0.0245,
      "step": 366
    },
    {
      "epoch": 0.31101694915254235,
      "grad_norm": 1.3123137950897217,
      "learning_rate": 1.740764853512485e-05,
      "loss": 0.0066,
      "step": 367
    },
    {
      "epoch": 0.31186440677966104,
      "grad_norm": 1.4011317491531372,
      "learning_rate": 1.738774411710844e-05,
      "loss": 0.0215,
      "step": 368
    },
    {
      "epoch": 0.31271186440677967,
      "grad_norm": 1.852777361869812,
      "learning_rate": 1.7367775050028254e-05,
      "loss": 0.0119,
      "step": 369
    },
    {
      "epoch": 0.3135593220338983,
      "grad_norm": 1.4631356000900269,
      "learning_rate": 1.7347741508630673e-05,
      "loss": 0.0142,
      "step": 370
    },
    {
      "epoch": 0.31440677966101693,
      "grad_norm": 2.603271961212158,
      "learning_rate": 1.732764366822627e-05,
      "loss": 0.0218,
      "step": 371
    },
    {
      "epoch": 0.3152542372881356,
      "grad_norm": 1.0737484693527222,
      "learning_rate": 1.73074817046883e-05,
      "loss": 0.0087,
      "step": 372
    },
    {
      "epoch": 0.31610169491525425,
      "grad_norm": 3.7462353706359863,
      "learning_rate": 1.728725579445114e-05,
      "loss": 0.0573,
      "step": 373
    },
    {
      "epoch": 0.3169491525423729,
      "grad_norm": 1.9481991529464722,
      "learning_rate": 1.7266966114508764e-05,
      "loss": 0.011,
      "step": 374
    },
    {
      "epoch": 0.3177966101694915,
      "grad_norm": 0.9563993811607361,
      "learning_rate": 1.7246612842413177e-05,
      "loss": 0.0073,
      "step": 375
    },
    {
      "epoch": 0.31864406779661014,
      "grad_norm": 4.024267196655273,
      "learning_rate": 1.7226196156272873e-05,
      "loss": 0.0278,
      "step": 376
    },
    {
      "epoch": 0.31949152542372883,
      "grad_norm": 2.5183022022247314,
      "learning_rate": 1.720571623475128e-05,
      "loss": 0.0349,
      "step": 377
    },
    {
      "epoch": 0.32033898305084746,
      "grad_norm": 1.7995777130126953,
      "learning_rate": 1.7185173257065178e-05,
      "loss": 0.0097,
      "step": 378
    },
    {
      "epoch": 0.3211864406779661,
      "grad_norm": 1.5496909618377686,
      "learning_rate": 1.7164567402983153e-05,
      "loss": 0.0133,
      "step": 379
    },
    {
      "epoch": 0.3220338983050847,
      "grad_norm": 2.2646713256835938,
      "learning_rate": 1.7143898852824005e-05,
      "loss": 0.0446,
      "step": 380
    },
    {
      "epoch": 0.3220338983050847,
      "eval_accuracy": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.0006280901725403965,
      "eval_precision": 1.0,
      "eval_recall": 1.0,
      "eval_runtime": 51.0586,
      "eval_samples_per_second": 5.719,
      "eval_steps_per_second": 0.196,
      "step": 380
    },
    {
      "epoch": 0.3228813559322034,
      "grad_norm": 2.7952117919921875,
      "learning_rate": 1.7123167787455176e-05,
      "loss": 0.021,
      "step": 381
    },
    {
      "epoch": 0.32372881355932204,
      "grad_norm": 1.8368139266967773,
      "learning_rate": 1.7102374388291182e-05,
      "loss": 0.0117,
      "step": 382
    },
    {
      "epoch": 0.32457627118644067,
      "grad_norm": 1.9440964460372925,
      "learning_rate": 1.7081518837292006e-05,
      "loss": 0.0113,
      "step": 383
    },
    {
      "epoch": 0.3254237288135593,
      "grad_norm": 1.4448236227035522,
      "learning_rate": 1.7060601316961504e-05,
      "loss": 0.0097,
      "step": 384
    },
    {
      "epoch": 0.326271186440678,
      "grad_norm": 1.075166940689087,
      "learning_rate": 1.7039622010345832e-05,
      "loss": 0.0087,
      "step": 385
    },
    {
      "epoch": 0.3271186440677966,
      "grad_norm": 1.9080896377563477,
      "learning_rate": 1.7018581101031814e-05,
      "loss": 0.014,
      "step": 386
    },
    {
      "epoch": 0.32796610169491525,
      "grad_norm": 0.934737503528595,
      "learning_rate": 1.6997478773145363e-05,
      "loss": 0.0074,
      "step": 387
    },
    {
      "epoch": 0.3288135593220339,
      "grad_norm": 1.9116491079330444,
      "learning_rate": 1.6976315211349848e-05,
      "loss": 0.024,
      "step": 388
    },
    {
      "epoch": 0.32966101694915256,
      "grad_norm": 0.9697662591934204,
      "learning_rate": 1.6955090600844494e-05,
      "loss": 0.0058,
      "step": 389
    },
    {
      "epoch": 0.3305084745762712,
      "grad_norm": 2.447063446044922,
      "learning_rate": 1.6933805127362744e-05,
      "loss": 0.0205,
      "step": 390
    },
    {
      "epoch": 0.3313559322033898,
      "grad_norm": 1.4310107231140137,
      "learning_rate": 1.6912458977170655e-05,
      "loss": 0.0289,
      "step": 391
    },
    {
      "epoch": 0.33220338983050846,
      "grad_norm": 1.9119633436203003,
      "learning_rate": 1.6891052337065256e-05,
      "loss": 0.0095,
      "step": 392
    },
    {
      "epoch": 0.33305084745762714,
      "grad_norm": 1.6527955532073975,
      "learning_rate": 1.68695853943729e-05,
      "loss": 0.0147,
      "step": 393
    },
    {
      "epoch": 0.3338983050847458,
      "grad_norm": 0.6647539138793945,
      "learning_rate": 1.6848058336947657e-05,
      "loss": 0.0045,
      "step": 394
    },
    {
      "epoch": 0.3347457627118644,
      "grad_norm": 2.0844597816467285,
      "learning_rate": 1.682647135316965e-05,
      "loss": 0.0057,
      "step": 395
    },
    {
      "epoch": 0.33559322033898303,
      "grad_norm": 1.3205703496932983,
      "learning_rate": 1.6804824631943385e-05,
      "loss": 0.0074,
      "step": 396
    },
    {
      "epoch": 0.3364406779661017,
      "grad_norm": 1.966313362121582,
      "learning_rate": 1.6783118362696162e-05,
      "loss": 0.0199,
      "step": 397
    },
    {
      "epoch": 0.33728813559322035,
      "grad_norm": 1.4938113689422607,
      "learning_rate": 1.6761352735376343e-05,
      "loss": 0.0098,
      "step": 398
    },
    {
      "epoch": 0.338135593220339,
      "grad_norm": 1.2858011722564697,
      "learning_rate": 1.6739527940451742e-05,
      "loss": 0.0055,
      "step": 399
    },
    {
      "epoch": 0.3389830508474576,
      "grad_norm": 2.423365592956543,
      "learning_rate": 1.671764416890793e-05,
      "loss": 0.0261,
      "step": 400
    },
    {
      "epoch": 0.3389830508474576,
      "eval_accuracy": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.00033162630279548466,
      "eval_precision": 1.0,
      "eval_recall": 1.0,
      "eval_runtime": 51.2242,
      "eval_samples_per_second": 5.7,
      "eval_steps_per_second": 0.195,
      "step": 400
    },
    {
      "epoch": 0.3398305084745763,
      "grad_norm": 1.8987358808517456,
      "learning_rate": 1.6695701612246578e-05,
      "loss": 0.0087,
      "step": 401
    },
    {
      "epoch": 0.34067796610169493,
      "grad_norm": 2.600064277648926,
      "learning_rate": 1.6673700462483776e-05,
      "loss": 0.0215,
      "step": 402
    },
    {
      "epoch": 0.34152542372881356,
      "grad_norm": 0.21410588920116425,
      "learning_rate": 1.6651640912148362e-05,
      "loss": 0.0013,
      "step": 403
    },
    {
      "epoch": 0.3423728813559322,
      "grad_norm": 2.80786395072937,
      "learning_rate": 1.662952315428021e-05,
      "loss": 0.0257,
      "step": 404
    },
    {
      "epoch": 0.3432203389830508,
      "grad_norm": 2.0962929725646973,
      "learning_rate": 1.6607347382428577e-05,
      "loss": 0.0106,
      "step": 405
    },
    {
      "epoch": 0.3440677966101695,
      "grad_norm": 1.8939802646636963,
      "learning_rate": 1.658511379065039e-05,
      "loss": 0.0211,
      "step": 406
    },
    {
      "epoch": 0.34491525423728814,
      "grad_norm": 1.2169216871261597,
      "learning_rate": 1.6562822573508533e-05,
      "loss": 0.0056,
      "step": 407
    },
    {
      "epoch": 0.34576271186440677,
      "grad_norm": 1.3260303735733032,
      "learning_rate": 1.6540473926070183e-05,
      "loss": 0.0137,
      "step": 408
    },
    {
      "epoch": 0.3466101694915254,
      "grad_norm": 2.0518648624420166,
      "learning_rate": 1.6518068043905075e-05,
      "loss": 0.0104,
      "step": 409
    },
    {
      "epoch": 0.3474576271186441,
      "grad_norm": 0.49681225419044495,
      "learning_rate": 1.649560512308378e-05,
      "loss": 0.0037,
      "step": 410
    },
    {
      "epoch": 0.3483050847457627,
      "grad_norm": 1.43990957736969,
      "learning_rate": 1.647308536017603e-05,
      "loss": 0.0086,
      "step": 411
    },
    {
      "epoch": 0.34915254237288135,
      "grad_norm": 1.290264368057251,
      "learning_rate": 1.6450508952248957e-05,
      "loss": 0.0159,
      "step": 412
    },
    {
      "epoch": 0.35,
      "grad_norm": 0.9707666039466858,
      "learning_rate": 1.6427876096865394e-05,
      "loss": 0.0074,
      "step": 413
    },
    {
      "epoch": 0.35084745762711866,
      "grad_norm": 2.03999924659729,
      "learning_rate": 1.6405186992082134e-05,
      "loss": 0.0144,
      "step": 414
    },
    {
      "epoch": 0.3516949152542373,
      "grad_norm": 0.5716383457183838,
      "learning_rate": 1.6382441836448203e-05,
      "loss": 0.0053,
      "step": 415
    },
    {
      "epoch": 0.3525423728813559,
      "grad_norm": 0.6597254276275635,
      "learning_rate": 1.635964082900311e-05,
      "loss": 0.0033,
      "step": 416
    },
    {
      "epoch": 0.35338983050847456,
      "grad_norm": 0.7216088175773621,
      "learning_rate": 1.6336784169275132e-05,
      "loss": 0.0039,
      "step": 417
    },
    {
      "epoch": 0.35423728813559324,
      "grad_norm": 2.028721570968628,
      "learning_rate": 1.6313872057279536e-05,
      "loss": 0.0229,
      "step": 418
    },
    {
      "epoch": 0.3550847457627119,
      "grad_norm": 3.6218316555023193,
      "learning_rate": 1.6290904693516853e-05,
      "loss": 0.0318,
      "step": 419
    },
    {
      "epoch": 0.3559322033898305,
      "grad_norm": 0.5219744443893433,
      "learning_rate": 1.6267882278971102e-05,
      "loss": 0.0032,
      "step": 420
    },
    {
      "epoch": 0.3559322033898305,
      "eval_accuracy": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.00023322339984588325,
      "eval_precision": 1.0,
      "eval_recall": 1.0,
      "eval_runtime": 51.4367,
      "eval_samples_per_second": 5.677,
      "eval_steps_per_second": 0.194,
      "step": 420
    },
    {
      "epoch": 0.35677966101694913,
      "grad_norm": 1.2915095090866089,
      "learning_rate": 1.624480501510806e-05,
      "loss": 0.0086,
      "step": 421
    },
    {
      "epoch": 0.3576271186440678,
      "grad_norm": 1.938812255859375,
      "learning_rate": 1.6221673103873474e-05,
      "loss": 0.0181,
      "step": 422
    },
    {
      "epoch": 0.35847457627118645,
      "grad_norm": 2.0729336738586426,
      "learning_rate": 1.6198486747691293e-05,
      "loss": 0.0119,
      "step": 423
    },
    {
      "epoch": 0.3593220338983051,
      "grad_norm": 1.3602229356765747,
      "learning_rate": 1.617524614946192e-05,
      "loss": 0.0121,
      "step": 424
    },
    {
      "epoch": 0.3601694915254237,
      "grad_norm": 0.6615320444107056,
      "learning_rate": 1.615195151256042e-05,
      "loss": 0.0051,
      "step": 425
    },
    {
      "epoch": 0.3610169491525424,
      "grad_norm": 1.0828938484191895,
      "learning_rate": 1.6128603040834735e-05,
      "loss": 0.0136,
      "step": 426
    },
    {
      "epoch": 0.36186440677966103,
      "grad_norm": 1.0993672609329224,
      "learning_rate": 1.6105200938603917e-05,
      "loss": 0.0071,
      "step": 427
    },
    {
      "epoch": 0.36271186440677966,
      "grad_norm": 1.2687034606933594,
      "learning_rate": 1.608174541065632e-05,
      "loss": 0.0124,
      "step": 428
    },
    {
      "epoch": 0.3635593220338983,
      "grad_norm": 0.7331047654151917,
      "learning_rate": 1.6058236662247827e-05,
      "loss": 0.0042,
      "step": 429
    },
    {
      "epoch": 0.3644067796610169,
      "grad_norm": 0.8685011863708496,
      "learning_rate": 1.603467489910004e-05,
      "loss": 0.0065,
      "step": 430
    },
    {
      "epoch": 0.3652542372881356,
      "grad_norm": 0.4545860290527344,
      "learning_rate": 1.6011060327398492e-05,
      "loss": 0.0035,
      "step": 431
    },
    {
      "epoch": 0.36610169491525424,
      "grad_norm": 1.2493585348129272,
      "learning_rate": 1.5987393153790832e-05,
      "loss": 0.0104,
      "step": 432
    },
    {
      "epoch": 0.36694915254237287,
      "grad_norm": 0.7078704237937927,
      "learning_rate": 1.5963673585385016e-05,
      "loss": 0.0061,
      "step": 433
    },
    {
      "epoch": 0.3677966101694915,
      "grad_norm": 1.4348129034042358,
      "learning_rate": 1.5939901829747508e-05,
      "loss": 0.0082,
      "step": 434
    },
    {
      "epoch": 0.3686440677966102,
      "grad_norm": 1.2969249486923218,
      "learning_rate": 1.5916078094901448e-05,
      "loss": 0.0049,
      "step": 435
    },
    {
      "epoch": 0.3694915254237288,
      "grad_norm": 0.5477801561355591,
      "learning_rate": 1.5892202589324835e-05,
      "loss": 0.0043,
      "step": 436
    },
    {
      "epoch": 0.37033898305084745,
      "grad_norm": 1.7194287776947021,
      "learning_rate": 1.5868275521948726e-05,
      "loss": 0.0148,
      "step": 437
    },
    {
      "epoch": 0.3711864406779661,
      "grad_norm": 1.6770473718643188,
      "learning_rate": 1.5844297102155364e-05,
      "loss": 0.0198,
      "step": 438
    },
    {
      "epoch": 0.37203389830508476,
      "grad_norm": 2.6121509075164795,
      "learning_rate": 1.582026753977638e-05,
      "loss": 0.0135,
      "step": 439
    },
    {
      "epoch": 0.3728813559322034,
      "grad_norm": 2.6553170680999756,
      "learning_rate": 1.5796187045090943e-05,
      "loss": 0.0413,
      "step": 440
    },
    {
      "epoch": 0.3728813559322034,
      "eval_accuracy": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.00017413182649761438,
      "eval_precision": 1.0,
      "eval_recall": 1.0,
      "eval_runtime": 51.5352,
      "eval_samples_per_second": 5.666,
      "eval_steps_per_second": 0.194,
      "step": 440
    },
    {
      "epoch": 0.373728813559322,
      "grad_norm": 1.9083479642868042,
      "learning_rate": 1.577205582882393e-05,
      "loss": 0.0052,
      "step": 441
    },
    {
      "epoch": 0.37457627118644066,
      "grad_norm": 1.9797714948654175,
      "learning_rate": 1.5747874102144073e-05,
      "loss": 0.0103,
      "step": 442
    },
    {
      "epoch": 0.37542372881355934,
      "grad_norm": 3.449254035949707,
      "learning_rate": 1.57236420766621e-05,
      "loss": 0.0396,
      "step": 443
    },
    {
      "epoch": 0.376271186440678,
      "grad_norm": 1.179081916809082,
      "learning_rate": 1.5699359964428917e-05,
      "loss": 0.0054,
      "step": 444
    },
    {
      "epoch": 0.3771186440677966,
      "grad_norm": 2.9331607818603516,
      "learning_rate": 1.567502797793372e-05,
      "loss": 0.0207,
      "step": 445
    },
    {
      "epoch": 0.37796610169491524,
      "grad_norm": 2.226416826248169,
      "learning_rate": 1.5650646330102144e-05,
      "loss": 0.0225,
      "step": 446
    },
    {
      "epoch": 0.3788135593220339,
      "grad_norm": 1.9515255689620972,
      "learning_rate": 1.5626215234294416e-05,
      "loss": 0.0122,
      "step": 447
    },
    {
      "epoch": 0.37966101694915255,
      "grad_norm": 2.8020267486572266,
      "learning_rate": 1.560173490430346e-05,
      "loss": 0.0113,
      "step": 448
    },
    {
      "epoch": 0.3805084745762712,
      "grad_norm": 2.073023557662964,
      "learning_rate": 1.5577205554353056e-05,
      "loss": 0.0083,
      "step": 449
    },
    {
      "epoch": 0.3813559322033898,
      "grad_norm": 1.7509485483169556,
      "learning_rate": 1.5552627399095943e-05,
      "loss": 0.0146,
      "step": 450
    },
    {
      "epoch": 0.3822033898305085,
      "grad_norm": 1.0263633728027344,
      "learning_rate": 1.5528000653611935e-05,
      "loss": 0.0048,
      "step": 451
    },
    {
      "epoch": 0.38305084745762713,
      "grad_norm": 0.847665011882782,
      "learning_rate": 1.5503325533406076e-05,
      "loss": 0.0096,
      "step": 452
    },
    {
      "epoch": 0.38389830508474576,
      "grad_norm": 1.1132762432098389,
      "learning_rate": 1.5478602254406722e-05,
      "loss": 0.0046,
      "step": 453
    },
    {
      "epoch": 0.3847457627118644,
      "grad_norm": 0.4251544177532196,
      "learning_rate": 1.5453831032963648e-05,
      "loss": 0.0034,
      "step": 454
    },
    {
      "epoch": 0.3855932203389831,
      "grad_norm": 1.9715460538864136,
      "learning_rate": 1.5429012085846183e-05,
      "loss": 0.0159,
      "step": 455
    },
    {
      "epoch": 0.3864406779661017,
      "grad_norm": 2.9356298446655273,
      "learning_rate": 1.5404145630241275e-05,
      "loss": 0.0379,
      "step": 456
    },
    {
      "epoch": 0.38728813559322034,
      "grad_norm": 0.7249993085861206,
      "learning_rate": 1.537923188375164e-05,
      "loss": 0.0025,
      "step": 457
    },
    {
      "epoch": 0.38813559322033897,
      "grad_norm": 1.8938612937927246,
      "learning_rate": 1.535427106439381e-05,
      "loss": 0.0096,
      "step": 458
    },
    {
      "epoch": 0.3889830508474576,
      "grad_norm": 3.1911001205444336,
      "learning_rate": 1.5329263390596245e-05,
      "loss": 0.0448,
      "step": 459
    },
    {
      "epoch": 0.3898305084745763,
      "grad_norm": 2.0256171226501465,
      "learning_rate": 1.5304209081197425e-05,
      "loss": 0.0189,
      "step": 460
    },
    {
      "epoch": 0.3898305084745763,
      "eval_accuracy": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.0003800760896410793,
      "eval_precision": 1.0,
      "eval_recall": 1.0,
      "eval_runtime": 51.2193,
      "eval_samples_per_second": 5.701,
      "eval_steps_per_second": 0.195,
      "step": 460
    },
    {
      "epoch": 0.3906779661016949,
      "grad_norm": 1.5554085969924927,
      "learning_rate": 1.5279108355443942e-05,
      "loss": 0.0094,
      "step": 461
    },
    {
      "epoch": 0.39152542372881355,
      "grad_norm": 1.625154972076416,
      "learning_rate": 1.5253961432988548e-05,
      "loss": 0.0218,
      "step": 462
    },
    {
      "epoch": 0.3923728813559322,
      "grad_norm": 1.304267406463623,
      "learning_rate": 1.5228768533888278e-05,
      "loss": 0.0065,
      "step": 463
    },
    {
      "epoch": 0.39322033898305087,
      "grad_norm": 2.61993408203125,
      "learning_rate": 1.5203529878602484e-05,
      "loss": 0.0283,
      "step": 464
    },
    {
      "epoch": 0.3940677966101695,
      "grad_norm": 0.5497863292694092,
      "learning_rate": 1.5178245687990937e-05,
      "loss": 0.0034,
      "step": 465
    },
    {
      "epoch": 0.3949152542372881,
      "grad_norm": 0.8741781711578369,
      "learning_rate": 1.5152916183311881e-05,
      "loss": 0.0034,
      "step": 466
    },
    {
      "epoch": 0.39576271186440676,
      "grad_norm": 2.4400858879089355,
      "learning_rate": 1.5127541586220077e-05,
      "loss": 0.0174,
      "step": 467
    },
    {
      "epoch": 0.39661016949152544,
      "grad_norm": 2.425032138824463,
      "learning_rate": 1.510212211876491e-05,
      "loss": 0.014,
      "step": 468
    },
    {
      "epoch": 0.3974576271186441,
      "grad_norm": 1.969048261642456,
      "learning_rate": 1.50766580033884e-05,
      "loss": 0.0231,
      "step": 469
    },
    {
      "epoch": 0.3983050847457627,
      "grad_norm": 3.7651619911193848,
      "learning_rate": 1.5051149462923285e-05,
      "loss": 0.036,
      "step": 470
    },
    {
      "epoch": 0.39915254237288134,
      "grad_norm": 1.2159584760665894,
      "learning_rate": 1.5025596720591052e-05,
      "loss": 0.0068,
      "step": 471
    },
    {
      "epoch": 0.4,
      "grad_norm": 1.8400602340698242,
      "learning_rate": 1.5000000000000002e-05,
      "loss": 0.0111,
      "step": 472
    },
    {
      "epoch": 0.40084745762711865,
      "grad_norm": 0.26205798983573914,
      "learning_rate": 1.4974359525143275e-05,
      "loss": 0.0017,
      "step": 473
    },
    {
      "epoch": 0.4016949152542373,
      "grad_norm": 1.555829405784607,
      "learning_rate": 1.4948675520396893e-05,
      "loss": 0.0209,
      "step": 474
    },
    {
      "epoch": 0.4025423728813559,
      "grad_norm": 0.8700111508369446,
      "learning_rate": 1.4922948210517822e-05,
      "loss": 0.0037,
      "step": 475
    },
    {
      "epoch": 0.4033898305084746,
      "grad_norm": 2.0976297855377197,
      "learning_rate": 1.4897177820641966e-05,
      "loss": 0.0134,
      "step": 476
    },
    {
      "epoch": 0.40423728813559323,
      "grad_norm": 1.7627066373825073,
      "learning_rate": 1.4871364576282223e-05,
      "loss": 0.008,
      "step": 477
    },
    {
      "epoch": 0.40508474576271186,
      "grad_norm": 0.7504107356071472,
      "learning_rate": 1.4845508703326504e-05,
      "loss": 0.0102,
      "step": 478
    },
    {
      "epoch": 0.4059322033898305,
      "grad_norm": 1.8525331020355225,
      "learning_rate": 1.4819610428035754e-05,
      "loss": 0.019,
      "step": 479
    },
    {
      "epoch": 0.4067796610169492,
      "grad_norm": 0.5475234985351562,
      "learning_rate": 1.4793669977041978e-05,
      "loss": 0.003,
      "step": 480
    },
    {
      "epoch": 0.4067796610169492,
      "eval_accuracy": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.0002279380423715338,
      "eval_precision": 1.0,
      "eval_recall": 1.0,
      "eval_runtime": 51.1012,
      "eval_samples_per_second": 5.714,
      "eval_steps_per_second": 0.196,
      "step": 480
    },
    {
      "epoch": 0.4076271186440678,
      "grad_norm": 0.4113156199455261,
      "learning_rate": 1.4767687577346253e-05,
      "loss": 0.0031,
      "step": 481
    },
    {
      "epoch": 0.40847457627118644,
      "grad_norm": 1.466239094734192,
      "learning_rate": 1.4741663456316742e-05,
      "loss": 0.0096,
      "step": 482
    },
    {
      "epoch": 0.40932203389830507,
      "grad_norm": 1.421286702156067,
      "learning_rate": 1.4715597841686708e-05,
      "loss": 0.0119,
      "step": 483
    },
    {
      "epoch": 0.4101694915254237,
      "grad_norm": 1.6936863660812378,
      "learning_rate": 1.4689490961552513e-05,
      "loss": 0.0191,
      "step": 484
    },
    {
      "epoch": 0.4110169491525424,
      "grad_norm": 2.2526814937591553,
      "learning_rate": 1.4663343044371635e-05,
      "loss": 0.018,
      "step": 485
    },
    {
      "epoch": 0.411864406779661,
      "grad_norm": 0.3923169672489166,
      "learning_rate": 1.4637154318960653e-05,
      "loss": 0.002,
      "step": 486
    },
    {
      "epoch": 0.41271186440677965,
      "grad_norm": 1.785679578781128,
      "learning_rate": 1.461092501449326e-05,
      "loss": 0.0066,
      "step": 487
    },
    {
      "epoch": 0.4135593220338983,
      "grad_norm": 4.866019248962402,
      "learning_rate": 1.4584655360498245e-05,
      "loss": 0.0307,
      "step": 488
    },
    {
      "epoch": 0.41440677966101697,
      "grad_norm": 3.334535598754883,
      "learning_rate": 1.4558345586857496e-05,
      "loss": 0.0293,
      "step": 489
    },
    {
      "epoch": 0.4152542372881356,
      "grad_norm": 1.5165126323699951,
      "learning_rate": 1.4531995923803974e-05,
      "loss": 0.0156,
      "step": 490
    },
    {
      "epoch": 0.4161016949152542,
      "grad_norm": 0.1444772481918335,
      "learning_rate": 1.450560660191971e-05,
      "loss": 0.001,
      "step": 491
    },
    {
      "epoch": 0.41694915254237286,
      "grad_norm": 1.8422871828079224,
      "learning_rate": 1.4479177852133787e-05,
      "loss": 0.0237,
      "step": 492
    },
    {
      "epoch": 0.41779661016949154,
      "grad_norm": 0.7579980492591858,
      "learning_rate": 1.4452709905720314e-05,
      "loss": 0.0036,
      "step": 493
    },
    {
      "epoch": 0.4186440677966102,
      "grad_norm": 0.8799729943275452,
      "learning_rate": 1.4426202994296401e-05,
      "loss": 0.0069,
      "step": 494
    },
    {
      "epoch": 0.4194915254237288,
      "grad_norm": 0.6293562054634094,
      "learning_rate": 1.4399657349820136e-05,
      "loss": 0.0038,
      "step": 495
    },
    {
      "epoch": 0.42033898305084744,
      "grad_norm": 0.24156221747398376,
      "learning_rate": 1.4373073204588556e-05,
      "loss": 0.0017,
      "step": 496
    },
    {
      "epoch": 0.4211864406779661,
      "grad_norm": 0.5691763758659363,
      "learning_rate": 1.4346450791235611e-05,
      "loss": 0.0037,
      "step": 497
    },
    {
      "epoch": 0.42203389830508475,
      "grad_norm": 1.91914963722229,
      "learning_rate": 1.4319790342730131e-05,
      "loss": 0.0214,
      "step": 498
    },
    {
      "epoch": 0.4228813559322034,
      "grad_norm": 3.101850748062134,
      "learning_rate": 1.4293092092373786e-05,
      "loss": 0.0217,
      "step": 499
    },
    {
      "epoch": 0.423728813559322,
      "grad_norm": 1.2713143825531006,
      "learning_rate": 1.4266356273799044e-05,
      "loss": 0.0071,
      "step": 500
    },
    {
      "epoch": 0.423728813559322,
      "eval_accuracy": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.0003793275391217321,
      "eval_precision": 1.0,
      "eval_recall": 1.0,
      "eval_runtime": 52.145,
      "eval_samples_per_second": 5.6,
      "eval_steps_per_second": 0.192,
      "step": 500
    },
    {
      "epoch": 0.4245762711864407,
      "grad_norm": 3.1827445030212402,
      "learning_rate": 1.4239583120967125e-05,
      "loss": 0.0485,
      "step": 501
    },
    {
      "epoch": 0.42542372881355933,
      "grad_norm": 1.7482115030288696,
      "learning_rate": 1.4212772868165957e-05,
      "loss": 0.0151,
      "step": 502
    },
    {
      "epoch": 0.42627118644067796,
      "grad_norm": 1.0564489364624023,
      "learning_rate": 1.418592575000813e-05,
      "loss": 0.007,
      "step": 503
    },
    {
      "epoch": 0.4271186440677966,
      "grad_norm": 1.7804484367370605,
      "learning_rate": 1.4159042001428827e-05,
      "loss": 0.0103,
      "step": 504
    },
    {
      "epoch": 0.4279661016949153,
      "grad_norm": 0.9321497082710266,
      "learning_rate": 1.4132121857683782e-05,
      "loss": 0.0152,
      "step": 505
    },
    {
      "epoch": 0.4288135593220339,
      "grad_norm": 0.712197482585907,
      "learning_rate": 1.4105165554347227e-05,
      "loss": 0.0035,
      "step": 506
    },
    {
      "epoch": 0.42966101694915254,
      "grad_norm": 0.5874913930892944,
      "learning_rate": 1.4078173327309807e-05,
      "loss": 0.0045,
      "step": 507
    },
    {
      "epoch": 0.43050847457627117,
      "grad_norm": 1.6754646301269531,
      "learning_rate": 1.4051145412776536e-05,
      "loss": 0.0134,
      "step": 508
    },
    {
      "epoch": 0.43135593220338986,
      "grad_norm": 0.6901799440383911,
      "learning_rate": 1.4024082047264729e-05,
      "loss": 0.0049,
      "step": 509
    },
    {
      "epoch": 0.4322033898305085,
      "grad_norm": 1.6095439195632935,
      "learning_rate": 1.3996983467601921e-05,
      "loss": 0.0113,
      "step": 510
    },
    {
      "epoch": 0.4330508474576271,
      "grad_norm": 2.4264211654663086,
      "learning_rate": 1.3969849910923803e-05,
      "loss": 0.0281,
      "step": 511
    },
    {
      "epoch": 0.43389830508474575,
      "grad_norm": 0.8501647114753723,
      "learning_rate": 1.3942681614672144e-05,
      "loss": 0.0042,
      "step": 512
    },
    {
      "epoch": 0.4347457627118644,
      "grad_norm": 1.2504135370254517,
      "learning_rate": 1.3915478816592715e-05,
      "loss": 0.0069,
      "step": 513
    },
    {
      "epoch": 0.43559322033898307,
      "grad_norm": 0.24446320533752441,
      "learning_rate": 1.388824175473321e-05,
      "loss": 0.0013,
      "step": 514
    },
    {
      "epoch": 0.4364406779661017,
      "grad_norm": 2.65307354927063,
      "learning_rate": 1.3860970667441147e-05,
      "loss": 0.0194,
      "step": 515
    },
    {
      "epoch": 0.43728813559322033,
      "grad_norm": 1.6779959201812744,
      "learning_rate": 1.3833665793361816e-05,
      "loss": 0.0159,
      "step": 516
    },
    {
      "epoch": 0.43813559322033896,
      "grad_norm": 1.3321099281311035,
      "learning_rate": 1.3806327371436159e-05,
      "loss": 0.0118,
      "step": 517
    },
    {
      "epoch": 0.43898305084745765,
      "grad_norm": 0.5509894490242004,
      "learning_rate": 1.3778955640898686e-05,
      "loss": 0.0026,
      "step": 518
    },
    {
      "epoch": 0.4398305084745763,
      "grad_norm": 1.3254811763763428,
      "learning_rate": 1.3751550841275394e-05,
      "loss": 0.0135,
      "step": 519
    },
    {
      "epoch": 0.4406779661016949,
      "grad_norm": 1.8219112157821655,
      "learning_rate": 1.372411321238166e-05,
      "loss": 0.0139,
      "step": 520
    },
    {
      "epoch": 0.4406779661016949,
      "eval_accuracy": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.0005393382161855698,
      "eval_precision": 1.0,
      "eval_recall": 1.0,
      "eval_runtime": 50.6981,
      "eval_samples_per_second": 5.76,
      "eval_steps_per_second": 0.197,
      "step": 520
    },
    {
      "epoch": 0.44152542372881354,
      "grad_norm": 1.3557311296463013,
      "learning_rate": 1.3696642994320146e-05,
      "loss": 0.0138,
      "step": 521
    },
    {
      "epoch": 0.4423728813559322,
      "grad_norm": 0.22216911613941193,
      "learning_rate": 1.3669140427478693e-05,
      "loss": 0.0015,
      "step": 522
    },
    {
      "epoch": 0.44322033898305085,
      "grad_norm": 0.794339120388031,
      "learning_rate": 1.3641605752528225e-05,
      "loss": 0.0082,
      "step": 523
    },
    {
      "epoch": 0.4440677966101695,
      "grad_norm": 1.4078831672668457,
      "learning_rate": 1.3614039210420638e-05,
      "loss": 0.0057,
      "step": 524
    },
    {
      "epoch": 0.4449152542372881,
      "grad_norm": 2.3533213138580322,
      "learning_rate": 1.3586441042386694e-05,
      "loss": 0.0198,
      "step": 525
    },
    {
      "epoch": 0.4457627118644068,
      "grad_norm": 3.0721018314361572,
      "learning_rate": 1.3558811489933909e-05,
      "loss": 0.0254,
      "step": 526
    },
    {
      "epoch": 0.44661016949152543,
      "grad_norm": 1.831836223602295,
      "learning_rate": 1.353115079484444e-05,
      "loss": 0.0169,
      "step": 527
    },
    {
      "epoch": 0.44745762711864406,
      "grad_norm": 1.5127922296524048,
      "learning_rate": 1.3503459199172969e-05,
      "loss": 0.0075,
      "step": 528
    },
    {
      "epoch": 0.4483050847457627,
      "grad_norm": 2.0667357444763184,
      "learning_rate": 1.3475736945244575e-05,
      "loss": 0.0122,
      "step": 529
    },
    {
      "epoch": 0.4491525423728814,
      "grad_norm": 0.386496365070343,
      "learning_rate": 1.3447984275652638e-05,
      "loss": 0.0023,
      "step": 530
    },
    {
      "epoch": 0.45,
      "grad_norm": 0.4718012511730194,
      "learning_rate": 1.342020143325669e-05,
      "loss": 0.0034,
      "step": 531
    },
    {
      "epoch": 0.45084745762711864,
      "grad_norm": 2.439950466156006,
      "learning_rate": 1.3392388661180303e-05,
      "loss": 0.0186,
      "step": 532
    },
    {
      "epoch": 0.4516949152542373,
      "grad_norm": 0.8340148329734802,
      "learning_rate": 1.3364546202808966e-05,
      "loss": 0.0067,
      "step": 533
    },
    {
      "epoch": 0.45254237288135596,
      "grad_norm": 2.2126450538635254,
      "learning_rate": 1.3336674301787942e-05,
      "loss": 0.0187,
      "step": 534
    },
    {
      "epoch": 0.4533898305084746,
      "grad_norm": 0.4377054274082184,
      "learning_rate": 1.330877320202014e-05,
      "loss": 0.0028,
      "step": 535
    },
    {
      "epoch": 0.4542372881355932,
      "grad_norm": 1.3909966945648193,
      "learning_rate": 1.3280843147663988e-05,
      "loss": 0.0131,
      "step": 536
    },
    {
      "epoch": 0.45508474576271185,
      "grad_norm": 0.3523927330970764,
      "learning_rate": 1.325288438313129e-05,
      "loss": 0.0016,
      "step": 537
    },
    {
      "epoch": 0.4559322033898305,
      "grad_norm": 3.0238094329833984,
      "learning_rate": 1.322489715308509e-05,
      "loss": 0.0175,
      "step": 538
    },
    {
      "epoch": 0.45677966101694917,
      "grad_norm": 1.9963982105255127,
      "learning_rate": 1.3196881702437525e-05,
      "loss": 0.0181,
      "step": 539
    },
    {
      "epoch": 0.4576271186440678,
      "grad_norm": 1.146183729171753,
      "learning_rate": 1.3168838276347691e-05,
      "loss": 0.0161,
      "step": 540
    },
    {
      "epoch": 0.4576271186440678,
      "eval_accuracy": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.0002900932158809155,
      "eval_precision": 1.0,
      "eval_recall": 1.0,
      "eval_runtime": 51.127,
      "eval_samples_per_second": 5.711,
      "eval_steps_per_second": 0.196,
      "step": 540
    },
    {
      "epoch": 0.45847457627118643,
      "grad_norm": 1.0082005262374878,
      "learning_rate": 1.314076712021949e-05,
      "loss": 0.0081,
      "step": 541
    },
    {
      "epoch": 0.45932203389830506,
      "grad_norm": 0.8905977606773376,
      "learning_rate": 1.3112668479699486e-05,
      "loss": 0.0037,
      "step": 542
    },
    {
      "epoch": 0.46016949152542375,
      "grad_norm": 1.1065611839294434,
      "learning_rate": 1.3084542600674756e-05,
      "loss": 0.0048,
      "step": 543
    },
    {
      "epoch": 0.4610169491525424,
      "grad_norm": 1.939026951789856,
      "learning_rate": 1.305638972927074e-05,
      "loss": 0.009,
      "step": 544
    },
    {
      "epoch": 0.461864406779661,
      "grad_norm": 2.5424704551696777,
      "learning_rate": 1.3028210111849079e-05,
      "loss": 0.0121,
      "step": 545
    },
    {
      "epoch": 0.46271186440677964,
      "grad_norm": 0.8510853052139282,
      "learning_rate": 1.3000003995005462e-05,
      "loss": 0.0053,
      "step": 546
    },
    {
      "epoch": 0.4635593220338983,
      "grad_norm": 4.978145599365234,
      "learning_rate": 1.297177162556748e-05,
      "loss": 0.0365,
      "step": 547
    },
    {
      "epoch": 0.46440677966101696,
      "grad_norm": 1.0519256591796875,
      "learning_rate": 1.294351325059245e-05,
      "loss": 0.0046,
      "step": 548
    },
    {
      "epoch": 0.4652542372881356,
      "grad_norm": 2.549281120300293,
      "learning_rate": 1.291522911736526e-05,
      "loss": 0.0192,
      "step": 549
    },
    {
      "epoch": 0.4661016949152542,
      "grad_norm": 1.8708372116088867,
      "learning_rate": 1.2886919473396212e-05,
      "loss": 0.0121,
      "step": 550
    },
    {
      "epoch": 0.4669491525423729,
      "grad_norm": 3.6299774646759033,
      "learning_rate": 1.2858584566418837e-05,
      "loss": 0.0233,
      "step": 551
    },
    {
      "epoch": 0.46779661016949153,
      "grad_norm": 1.1099425554275513,
      "learning_rate": 1.2830224644387742e-05,
      "loss": 0.0084,
      "step": 552
    },
    {
      "epoch": 0.46864406779661016,
      "grad_norm": 3.3964803218841553,
      "learning_rate": 1.2801839955476444e-05,
      "loss": 0.0413,
      "step": 553
    },
    {
      "epoch": 0.4694915254237288,
      "grad_norm": 2.0021309852600098,
      "learning_rate": 1.277343074807519e-05,
      "loss": 0.0144,
      "step": 554
    },
    {
      "epoch": 0.4703389830508475,
      "grad_norm": 2.881606340408325,
      "learning_rate": 1.2744997270788777e-05,
      "loss": 0.0354,
      "step": 555
    },
    {
      "epoch": 0.4711864406779661,
      "grad_norm": 0.47970932722091675,
      "learning_rate": 1.2716539772434389e-05,
      "loss": 0.0022,
      "step": 556
    },
    {
      "epoch": 0.47203389830508474,
      "grad_norm": 0.41695287823677063,
      "learning_rate": 1.2688058502039416e-05,
      "loss": 0.0023,
      "step": 557
    },
    {
      "epoch": 0.4728813559322034,
      "grad_norm": 2.176729440689087,
      "learning_rate": 1.2659553708839273e-05,
      "loss": 0.0271,
      "step": 558
    },
    {
      "epoch": 0.47372881355932206,
      "grad_norm": 0.9656859636306763,
      "learning_rate": 1.2631025642275212e-05,
      "loss": 0.0075,
      "step": 559
    },
    {
      "epoch": 0.4745762711864407,
      "grad_norm": 0.5131775140762329,
      "learning_rate": 1.2602474551992165e-05,
      "loss": 0.0027,
      "step": 560
    },
    {
      "epoch": 0.4745762711864407,
      "eval_accuracy": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.0001880442287074402,
      "eval_precision": 1.0,
      "eval_recall": 1.0,
      "eval_runtime": 50.0747,
      "eval_samples_per_second": 5.831,
      "eval_steps_per_second": 0.2,
      "step": 560
    },
    {
      "epoch": 0.4754237288135593,
      "grad_norm": 1.1515014171600342,
      "learning_rate": 1.2573900687836525e-05,
      "loss": 0.0114,
      "step": 561
    },
    {
      "epoch": 0.47627118644067795,
      "grad_norm": 0.5253351926803589,
      "learning_rate": 1.2545304299853977e-05,
      "loss": 0.0038,
      "step": 562
    },
    {
      "epoch": 0.47711864406779664,
      "grad_norm": 0.9620082378387451,
      "learning_rate": 1.2516685638287318e-05,
      "loss": 0.0053,
      "step": 563
    },
    {
      "epoch": 0.47796610169491527,
      "grad_norm": 0.7079916596412659,
      "learning_rate": 1.248804495357425e-05,
      "loss": 0.0038,
      "step": 564
    },
    {
      "epoch": 0.4788135593220339,
      "grad_norm": 1.2482668161392212,
      "learning_rate": 1.2459382496345199e-05,
      "loss": 0.0042,
      "step": 565
    },
    {
      "epoch": 0.47966101694915253,
      "grad_norm": 0.6608754992485046,
      "learning_rate": 1.2430698517421117e-05,
      "loss": 0.006,
      "step": 566
    },
    {
      "epoch": 0.48050847457627116,
      "grad_norm": 0.9836096167564392,
      "learning_rate": 1.2401993267811293e-05,
      "loss": 0.0087,
      "step": 567
    },
    {
      "epoch": 0.48135593220338985,
      "grad_norm": 2.097402334213257,
      "learning_rate": 1.2373266998711152e-05,
      "loss": 0.0165,
      "step": 568
    },
    {
      "epoch": 0.4822033898305085,
      "grad_norm": 0.6762765645980835,
      "learning_rate": 1.2344519961500048e-05,
      "loss": 0.0038,
      "step": 569
    },
    {
      "epoch": 0.4830508474576271,
      "grad_norm": 0.8983291983604431,
      "learning_rate": 1.2315752407739093e-05,
      "loss": 0.0044,
      "step": 570
    },
    {
      "epoch": 0.48389830508474574,
      "grad_norm": 1.4723248481750488,
      "learning_rate": 1.2286964589168917e-05,
      "loss": 0.0062,
      "step": 571
    },
    {
      "epoch": 0.4847457627118644,
      "grad_norm": 1.0354115962982178,
      "learning_rate": 1.2258156757707496e-05,
      "loss": 0.0098,
      "step": 572
    },
    {
      "epoch": 0.48559322033898306,
      "grad_norm": 0.8155727982521057,
      "learning_rate": 1.2229329165447931e-05,
      "loss": 0.0124,
      "step": 573
    },
    {
      "epoch": 0.4864406779661017,
      "grad_norm": 2.297771692276001,
      "learning_rate": 1.220048206465625e-05,
      "loss": 0.0094,
      "step": 574
    },
    {
      "epoch": 0.4872881355932203,
      "grad_norm": 1.3691686391830444,
      "learning_rate": 1.217161570776919e-05,
      "loss": 0.0039,
      "step": 575
    },
    {
      "epoch": 0.488135593220339,
      "grad_norm": 2.56219744682312,
      "learning_rate": 1.2142730347392007e-05,
      "loss": 0.0088,
      "step": 576
    },
    {
      "epoch": 0.48898305084745763,
      "grad_norm": 1.2534739971160889,
      "learning_rate": 1.2113826236296245e-05,
      "loss": 0.0046,
      "step": 577
    },
    {
      "epoch": 0.48983050847457626,
      "grad_norm": 0.3140455186367035,
      "learning_rate": 1.2084903627417535e-05,
      "loss": 0.001,
      "step": 578
    },
    {
      "epoch": 0.4906779661016949,
      "grad_norm": 2.9673843383789062,
      "learning_rate": 1.2055962773853379e-05,
      "loss": 0.0261,
      "step": 579
    },
    {
      "epoch": 0.4915254237288136,
      "grad_norm": 1.1575368642807007,
      "learning_rate": 1.2027003928860936e-05,
      "loss": 0.0039,
      "step": 580
    },
    {
      "epoch": 0.4915254237288136,
      "eval_accuracy": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.00029336303123272955,
      "eval_precision": 1.0,
      "eval_recall": 1.0,
      "eval_runtime": 51.1721,
      "eval_samples_per_second": 5.706,
      "eval_steps_per_second": 0.195,
      "step": 580
    },
    {
      "epoch": 0.4923728813559322,
      "grad_norm": 0.5004251003265381,
      "learning_rate": 1.1998027345854811e-05,
      "loss": 0.002,
      "step": 581
    },
    {
      "epoch": 0.49322033898305084,
      "grad_norm": 1.6102720499038696,
      "learning_rate": 1.1969033278404816e-05,
      "loss": 0.0071,
      "step": 582
    },
    {
      "epoch": 0.4940677966101695,
      "grad_norm": 0.36238208413124084,
      "learning_rate": 1.1940021980233784e-05,
      "loss": 0.0021,
      "step": 583
    },
    {
      "epoch": 0.49491525423728816,
      "grad_norm": 1.1167278289794922,
      "learning_rate": 1.1910993705215323e-05,
      "loss": 0.0026,
      "step": 584
    },
    {
      "epoch": 0.4957627118644068,
      "grad_norm": 1.2431293725967407,
      "learning_rate": 1.1881948707371609e-05,
      "loss": 0.0186,
      "step": 585
    },
    {
      "epoch": 0.4966101694915254,
      "grad_norm": 2.63661789894104,
      "learning_rate": 1.1852887240871145e-05,
      "loss": 0.024,
      "step": 586
    },
    {
      "epoch": 0.49745762711864405,
      "grad_norm": 0.9267066717147827,
      "learning_rate": 1.1823809560026558e-05,
      "loss": 0.0055,
      "step": 587
    },
    {
      "epoch": 0.49830508474576274,
      "grad_norm": 2.153548240661621,
      "learning_rate": 1.1794715919292368e-05,
      "loss": 0.0189,
      "step": 588
    },
    {
      "epoch": 0.49915254237288137,
      "grad_norm": 1.1179004907608032,
      "learning_rate": 1.1765606573262745e-05,
      "loss": 0.0091,
      "step": 589
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.7604763507843018,
      "learning_rate": 1.1736481776669307e-05,
      "loss": 0.0038,
      "step": 590
    },
    {
      "epoch": 0.5008474576271187,
      "grad_norm": 1.1166861057281494,
      "learning_rate": 1.1707341784378865e-05,
      "loss": 0.004,
      "step": 591
    },
    {
      "epoch": 0.5016949152542373,
      "grad_norm": 2.1006617546081543,
      "learning_rate": 1.1678186851391218e-05,
      "loss": 0.0119,
      "step": 592
    },
    {
      "epoch": 0.502542372881356,
      "grad_norm": 0.9687687754631042,
      "learning_rate": 1.1649017232836899e-05,
      "loss": 0.0031,
      "step": 593
    },
    {
      "epoch": 0.5033898305084745,
      "grad_norm": 1.6780524253845215,
      "learning_rate": 1.1619833183974959e-05,
      "loss": 0.0095,
      "step": 594
    },
    {
      "epoch": 0.5042372881355932,
      "grad_norm": 1.265393614768982,
      "learning_rate": 1.1590634960190722e-05,
      "loss": 0.0113,
      "step": 595
    },
    {
      "epoch": 0.5050847457627119,
      "grad_norm": 2.153305768966675,
      "learning_rate": 1.1561422816993555e-05,
      "loss": 0.021,
      "step": 596
    },
    {
      "epoch": 0.5059322033898305,
      "grad_norm": 1.4506266117095947,
      "learning_rate": 1.1532197010014636e-05,
      "loss": 0.0091,
      "step": 597
    },
    {
      "epoch": 0.5067796610169492,
      "grad_norm": 2.4317758083343506,
      "learning_rate": 1.1502957795004706e-05,
      "loss": 0.0171,
      "step": 598
    },
    {
      "epoch": 0.5076271186440678,
      "grad_norm": 1.4479554891586304,
      "learning_rate": 1.1473705427831843e-05,
      "loss": 0.0055,
      "step": 599
    },
    {
      "epoch": 0.5084745762711864,
      "grad_norm": 1.9250199794769287,
      "learning_rate": 1.1444440164479215e-05,
      "loss": 0.0067,
      "step": 600
    },
    {
      "epoch": 0.5084745762711864,
      "eval_accuracy": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.00014447586727328598,
      "eval_precision": 1.0,
      "eval_recall": 1.0,
      "eval_runtime": 49.9263,
      "eval_samples_per_second": 5.849,
      "eval_steps_per_second": 0.2,
      "step": 600
    },
    {
      "epoch": 0.5093220338983051,
      "grad_norm": 2.220385789871216,
      "learning_rate": 1.1415162261042849e-05,
      "loss": 0.0195,
      "step": 601
    },
    {
      "epoch": 0.5101694915254237,
      "grad_norm": 2.395817279815674,
      "learning_rate": 1.138587197372937e-05,
      "loss": 0.0189,
      "step": 602
    },
    {
      "epoch": 0.5110169491525424,
      "grad_norm": 3.041154146194458,
      "learning_rate": 1.1356569558853783e-05,
      "loss": 0.0231,
      "step": 603
    },
    {
      "epoch": 0.511864406779661,
      "grad_norm": 2.976128339767456,
      "learning_rate": 1.1327255272837221e-05,
      "loss": 0.0335,
      "step": 604
    },
    {
      "epoch": 0.5127118644067796,
      "grad_norm": 1.8595855236053467,
      "learning_rate": 1.1297929372204692e-05,
      "loss": 0.0115,
      "step": 605
    },
    {
      "epoch": 0.5135593220338983,
      "grad_norm": 0.9439570307731628,
      "learning_rate": 1.1268592113582848e-05,
      "loss": 0.0045,
      "step": 606
    },
    {
      "epoch": 0.514406779661017,
      "grad_norm": 0.2880883514881134,
      "learning_rate": 1.1239243753697728e-05,
      "loss": 0.0026,
      "step": 607
    },
    {
      "epoch": 0.5152542372881356,
      "grad_norm": 3.2744438648223877,
      "learning_rate": 1.120988454937252e-05,
      "loss": 0.0315,
      "step": 608
    },
    {
      "epoch": 0.5161016949152543,
      "grad_norm": 0.40230241417884827,
      "learning_rate": 1.118051475752531e-05,
      "loss": 0.0024,
      "step": 609
    },
    {
      "epoch": 0.5169491525423728,
      "grad_norm": 1.0340898036956787,
      "learning_rate": 1.115113463516683e-05,
      "loss": 0.0022,
      "step": 610
    },
    {
      "epoch": 0.5177966101694915,
      "grad_norm": 1.4035919904708862,
      "learning_rate": 1.112174443939822e-05,
      "loss": 0.0084,
      "step": 611
    },
    {
      "epoch": 0.5186440677966102,
      "grad_norm": 1.525558590888977,
      "learning_rate": 1.1092344427408767e-05,
      "loss": 0.0205,
      "step": 612
    },
    {
      "epoch": 0.5194915254237288,
      "grad_norm": 0.6529274582862854,
      "learning_rate": 1.1062934856473655e-05,
      "loss": 0.0044,
      "step": 613
    },
    {
      "epoch": 0.5203389830508475,
      "grad_norm": 0.5694882273674011,
      "learning_rate": 1.1033515983951722e-05,
      "loss": 0.0066,
      "step": 614
    },
    {
      "epoch": 0.5211864406779662,
      "grad_norm": 0.8706492781639099,
      "learning_rate": 1.10040880672832e-05,
      "loss": 0.0042,
      "step": 615
    },
    {
      "epoch": 0.5220338983050847,
      "grad_norm": 1.458556056022644,
      "learning_rate": 1.0974651363987465e-05,
      "loss": 0.0052,
      "step": 616
    },
    {
      "epoch": 0.5228813559322034,
      "grad_norm": 2.5780954360961914,
      "learning_rate": 1.0945206131660787e-05,
      "loss": 0.0284,
      "step": 617
    },
    {
      "epoch": 0.523728813559322,
      "grad_norm": 1.741313099861145,
      "learning_rate": 1.0915752627974068e-05,
      "loss": 0.017,
      "step": 618
    },
    {
      "epoch": 0.5245762711864407,
      "grad_norm": 0.1626061648130417,
      "learning_rate": 1.0886291110670592e-05,
      "loss": 0.0012,
      "step": 619
    },
    {
      "epoch": 0.5254237288135594,
      "grad_norm": 1.2944737672805786,
      "learning_rate": 1.085682183756377e-05,
      "loss": 0.012,
      "step": 620
    },
    {
      "epoch": 0.5254237288135594,
      "eval_accuracy": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.00011476398503873497,
      "eval_precision": 1.0,
      "eval_recall": 1.0,
      "eval_runtime": 49.5926,
      "eval_samples_per_second": 5.888,
      "eval_steps_per_second": 0.202,
      "step": 620
    },
    {
      "epoch": 0.5262711864406779,
      "grad_norm": 0.913479208946228,
      "learning_rate": 1.0827345066534887e-05,
      "loss": 0.0033,
      "step": 621
    },
    {
      "epoch": 0.5271186440677966,
      "grad_norm": 1.1390260457992554,
      "learning_rate": 1.0797861055530832e-05,
      "loss": 0.0083,
      "step": 622
    },
    {
      "epoch": 0.5279661016949152,
      "grad_norm": 0.6345875263214111,
      "learning_rate": 1.076837006256186e-05,
      "loss": 0.0054,
      "step": 623
    },
    {
      "epoch": 0.5288135593220339,
      "grad_norm": 1.8191931247711182,
      "learning_rate": 1.0738872345699314e-05,
      "loss": 0.0087,
      "step": 624
    },
    {
      "epoch": 0.5296610169491526,
      "grad_norm": 0.6184027791023254,
      "learning_rate": 1.0709368163073385e-05,
      "loss": 0.0041,
      "step": 625
    },
    {
      "epoch": 0.5305084745762711,
      "grad_norm": 0.8594485521316528,
      "learning_rate": 1.0679857772870845e-05,
      "loss": 0.0101,
      "step": 626
    },
    {
      "epoch": 0.5313559322033898,
      "grad_norm": 1.234549880027771,
      "learning_rate": 1.0650341433332778e-05,
      "loss": 0.0075,
      "step": 627
    },
    {
      "epoch": 0.5322033898305085,
      "grad_norm": 0.6435002088546753,
      "learning_rate": 1.062081940275234e-05,
      "loss": 0.0061,
      "step": 628
    },
    {
      "epoch": 0.5330508474576271,
      "grad_norm": 2.0458498001098633,
      "learning_rate": 1.0591291939472487e-05,
      "loss": 0.0129,
      "step": 629
    },
    {
      "epoch": 0.5338983050847458,
      "grad_norm": 2.5087852478027344,
      "learning_rate": 1.0561759301883714e-05,
      "loss": 0.0246,
      "step": 630
    },
    {
      "epoch": 0.5347457627118644,
      "grad_norm": 1.4174385070800781,
      "learning_rate": 1.0532221748421786e-05,
      "loss": 0.0176,
      "step": 631
    },
    {
      "epoch": 0.535593220338983,
      "grad_norm": 1.510528802871704,
      "learning_rate": 1.0502679537565507e-05,
      "loss": 0.0134,
      "step": 632
    },
    {
      "epoch": 0.5364406779661017,
      "grad_norm": 1.4558008909225464,
      "learning_rate": 1.047313292783442e-05,
      "loss": 0.0092,
      "step": 633
    },
    {
      "epoch": 0.5372881355932203,
      "grad_norm": 0.5714721083641052,
      "learning_rate": 1.0443582177786564e-05,
      "loss": 0.0028,
      "step": 634
    },
    {
      "epoch": 0.538135593220339,
      "grad_norm": 0.8509529829025269,
      "learning_rate": 1.0414027546016223e-05,
      "loss": 0.0053,
      "step": 635
    },
    {
      "epoch": 0.5389830508474577,
      "grad_norm": 1.3928581476211548,
      "learning_rate": 1.0384469291151628e-05,
      "loss": 0.0048,
      "step": 636
    },
    {
      "epoch": 0.5398305084745763,
      "grad_norm": 1.8540736436843872,
      "learning_rate": 1.0354907671852733e-05,
      "loss": 0.0116,
      "step": 637
    },
    {
      "epoch": 0.5406779661016949,
      "grad_norm": 0.5891087651252747,
      "learning_rate": 1.0325342946808923e-05,
      "loss": 0.005,
      "step": 638
    },
    {
      "epoch": 0.5415254237288135,
      "grad_norm": 2.605158805847168,
      "learning_rate": 1.029577537473677e-05,
      "loss": 0.0089,
      "step": 639
    },
    {
      "epoch": 0.5423728813559322,
      "grad_norm": 1.4306203126907349,
      "learning_rate": 1.026620521437775e-05,
      "loss": 0.006,
      "step": 640
    },
    {
      "epoch": 0.5423728813559322,
      "eval_accuracy": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.00012067957868566737,
      "eval_precision": 1.0,
      "eval_recall": 1.0,
      "eval_runtime": 49.6065,
      "eval_samples_per_second": 5.886,
      "eval_steps_per_second": 0.202,
      "step": 640
    },
    {
      "epoch": 0.5432203389830509,
      "grad_norm": 2.7418384552001953,
      "learning_rate": 1.0236632724495995e-05,
      "loss": 0.0281,
      "step": 641
    },
    {
      "epoch": 0.5440677966101695,
      "grad_norm": 2.0800535678863525,
      "learning_rate": 1.0207058163876021e-05,
      "loss": 0.0117,
      "step": 642
    },
    {
      "epoch": 0.5449152542372881,
      "grad_norm": 1.9006716012954712,
      "learning_rate": 1.0177481791320463e-05,
      "loss": 0.0084,
      "step": 643
    },
    {
      "epoch": 0.5457627118644067,
      "grad_norm": 0.9068240523338318,
      "learning_rate": 1.0147903865647814e-05,
      "loss": 0.0073,
      "step": 644
    },
    {
      "epoch": 0.5466101694915254,
      "grad_norm": 0.5592976808547974,
      "learning_rate": 1.0118324645690161e-05,
      "loss": 0.004,
      "step": 645
    },
    {
      "epoch": 0.5474576271186441,
      "grad_norm": 1.2031232118606567,
      "learning_rate": 1.008874439029091e-05,
      "loss": 0.0031,
      "step": 646
    },
    {
      "epoch": 0.5483050847457627,
      "grad_norm": 1.0401791334152222,
      "learning_rate": 1.0059163358302537e-05,
      "loss": 0.0066,
      "step": 647
    },
    {
      "epoch": 0.5491525423728814,
      "grad_norm": 1.2891989946365356,
      "learning_rate": 1.0029581808584298e-05,
      "loss": 0.0113,
      "step": 648
    },
    {
      "epoch": 0.55,
      "grad_norm": 2.2454192638397217,
      "learning_rate": 1e-05,
      "loss": 0.0186,
      "step": 649
    },
    {
      "epoch": 0.5508474576271186,
      "grad_norm": 1.310914158821106,
      "learning_rate": 9.970418191415703e-06,
      "loss": 0.0076,
      "step": 650
    },
    {
      "epoch": 0.5516949152542373,
      "grad_norm": 1.0773290395736694,
      "learning_rate": 9.940836641697465e-06,
      "loss": 0.0064,
      "step": 651
    },
    {
      "epoch": 0.5525423728813559,
      "grad_norm": 1.1092021465301514,
      "learning_rate": 9.911255609709089e-06,
      "loss": 0.014,
      "step": 652
    },
    {
      "epoch": 0.5533898305084746,
      "grad_norm": 1.551621437072754,
      "learning_rate": 9.88167535430984e-06,
      "loss": 0.0138,
      "step": 653
    },
    {
      "epoch": 0.5542372881355933,
      "grad_norm": 0.6066732406616211,
      "learning_rate": 9.852096134352186e-06,
      "loss": 0.0036,
      "step": 654
    },
    {
      "epoch": 0.5550847457627118,
      "grad_norm": 1.743664026260376,
      "learning_rate": 9.822518208679542e-06,
      "loss": 0.0206,
      "step": 655
    },
    {
      "epoch": 0.5559322033898305,
      "grad_norm": 0.5602774620056152,
      "learning_rate": 9.792941836123984e-06,
      "loss": 0.002,
      "step": 656
    },
    {
      "epoch": 0.5567796610169492,
      "grad_norm": 0.8597205877304077,
      "learning_rate": 9.76336727550401e-06,
      "loss": 0.0057,
      "step": 657
    },
    {
      "epoch": 0.5576271186440678,
      "grad_norm": 1.2528083324432373,
      "learning_rate": 9.733794785622254e-06,
      "loss": 0.0095,
      "step": 658
    },
    {
      "epoch": 0.5584745762711865,
      "grad_norm": 2.5552995204925537,
      "learning_rate": 9.704224625263233e-06,
      "loss": 0.0174,
      "step": 659
    },
    {
      "epoch": 0.559322033898305,
      "grad_norm": 0.4139198362827301,
      "learning_rate": 9.674657053191079e-06,
      "loss": 0.0025,
      "step": 660
    },
    {
      "epoch": 0.559322033898305,
      "eval_accuracy": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.00013073084119241685,
      "eval_precision": 1.0,
      "eval_recall": 1.0,
      "eval_runtime": 52.9786,
      "eval_samples_per_second": 5.512,
      "eval_steps_per_second": 0.189,
      "step": 660
    },
    {
      "epoch": 0.5601694915254237,
      "grad_norm": 1.9302622079849243,
      "learning_rate": 9.64509232814727e-06,
      "loss": 0.0225,
      "step": 661
    },
    {
      "epoch": 0.5610169491525424,
      "grad_norm": 1.2856723070144653,
      "learning_rate": 9.615530708848373e-06,
      "loss": 0.0099,
      "step": 662
    },
    {
      "epoch": 0.561864406779661,
      "grad_norm": 2.7380619049072266,
      "learning_rate": 9.585972453983779e-06,
      "loss": 0.0136,
      "step": 663
    },
    {
      "epoch": 0.5627118644067797,
      "grad_norm": 1.488617181777954,
      "learning_rate": 9.556417822213436e-06,
      "loss": 0.0139,
      "step": 664
    },
    {
      "epoch": 0.5635593220338984,
      "grad_norm": 0.7547746300697327,
      "learning_rate": 9.52686707216558e-06,
      "loss": 0.0039,
      "step": 665
    },
    {
      "epoch": 0.5644067796610169,
      "grad_norm": 1.0919615030288696,
      "learning_rate": 9.497320462434498e-06,
      "loss": 0.0112,
      "step": 666
    },
    {
      "epoch": 0.5652542372881356,
      "grad_norm": 0.737077534198761,
      "learning_rate": 9.467778251578217e-06,
      "loss": 0.0054,
      "step": 667
    },
    {
      "epoch": 0.5661016949152542,
      "grad_norm": 0.8337336778640747,
      "learning_rate": 9.438240698116291e-06,
      "loss": 0.0073,
      "step": 668
    },
    {
      "epoch": 0.5669491525423729,
      "grad_norm": 0.32100099325180054,
      "learning_rate": 9.408708060527515e-06,
      "loss": 0.0014,
      "step": 669
    },
    {
      "epoch": 0.5677966101694916,
      "grad_norm": 3.1640625,
      "learning_rate": 9.379180597247661e-06,
      "loss": 0.0172,
      "step": 670
    },
    {
      "epoch": 0.5686440677966101,
      "grad_norm": 0.860525906085968,
      "learning_rate": 9.349658566667225e-06,
      "loss": 0.0055,
      "step": 671
    },
    {
      "epoch": 0.5694915254237288,
      "grad_norm": 1.1916359663009644,
      "learning_rate": 9.320142227129158e-06,
      "loss": 0.0115,
      "step": 672
    },
    {
      "epoch": 0.5703389830508474,
      "grad_norm": 0.5801283717155457,
      "learning_rate": 9.290631836926616e-06,
      "loss": 0.003,
      "step": 673
    },
    {
      "epoch": 0.5711864406779661,
      "grad_norm": 1.943459391593933,
      "learning_rate": 9.261127654300689e-06,
      "loss": 0.0193,
      "step": 674
    },
    {
      "epoch": 0.5720338983050848,
      "grad_norm": 0.7220546007156372,
      "learning_rate": 9.231629937438142e-06,
      "loss": 0.0039,
      "step": 675
    },
    {
      "epoch": 0.5728813559322034,
      "grad_norm": 2.289808511734009,
      "learning_rate": 9.202138944469168e-06,
      "loss": 0.0165,
      "step": 676
    },
    {
      "epoch": 0.573728813559322,
      "grad_norm": 0.4558367431163788,
      "learning_rate": 9.172654933465114e-06,
      "loss": 0.0028,
      "step": 677
    },
    {
      "epoch": 0.5745762711864407,
      "grad_norm": 0.68553626537323,
      "learning_rate": 9.143178162436232e-06,
      "loss": 0.0034,
      "step": 678
    },
    {
      "epoch": 0.5754237288135593,
      "grad_norm": 1.1303017139434814,
      "learning_rate": 9.113708889329413e-06,
      "loss": 0.0075,
      "step": 679
    },
    {
      "epoch": 0.576271186440678,
      "grad_norm": 0.9036606550216675,
      "learning_rate": 9.084247372025938e-06,
      "loss": 0.0055,
      "step": 680
    },
    {
      "epoch": 0.576271186440678,
      "eval_accuracy": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.0001349969388684258,
      "eval_precision": 1.0,
      "eval_recall": 1.0,
      "eval_runtime": 50.0561,
      "eval_samples_per_second": 5.833,
      "eval_steps_per_second": 0.2,
      "step": 680
    },
    {
      "epoch": 0.5771186440677966,
      "grad_norm": 1.685551404953003,
      "learning_rate": 9.054793868339218e-06,
      "loss": 0.0116,
      "step": 681
    },
    {
      "epoch": 0.5779661016949152,
      "grad_norm": 0.9484760761260986,
      "learning_rate": 9.025348636012537e-06,
      "loss": 0.0047,
      "step": 682
    },
    {
      "epoch": 0.5788135593220339,
      "grad_norm": 1.4319676160812378,
      "learning_rate": 8.995911932716803e-06,
      "loss": 0.0148,
      "step": 683
    },
    {
      "epoch": 0.5796610169491525,
      "grad_norm": 0.5585588812828064,
      "learning_rate": 8.966484016048282e-06,
      "loss": 0.0024,
      "step": 684
    },
    {
      "epoch": 0.5805084745762712,
      "grad_norm": 2.1300556659698486,
      "learning_rate": 8.937065143526349e-06,
      "loss": 0.0135,
      "step": 685
    },
    {
      "epoch": 0.5813559322033899,
      "grad_norm": 0.46091559529304504,
      "learning_rate": 8.907655572591235e-06,
      "loss": 0.0026,
      "step": 686
    },
    {
      "epoch": 0.5822033898305085,
      "grad_norm": 0.28531086444854736,
      "learning_rate": 8.878255560601781e-06,
      "loss": 0.0015,
      "step": 687
    },
    {
      "epoch": 0.5830508474576271,
      "grad_norm": 2.4347126483917236,
      "learning_rate": 8.84886536483317e-06,
      "loss": 0.0144,
      "step": 688
    },
    {
      "epoch": 0.5838983050847457,
      "grad_norm": 1.346192717552185,
      "learning_rate": 8.819485242474696e-06,
      "loss": 0.0037,
      "step": 689
    },
    {
      "epoch": 0.5847457627118644,
      "grad_norm": 1.6517138481140137,
      "learning_rate": 8.790115450627486e-06,
      "loss": 0.0151,
      "step": 690
    },
    {
      "epoch": 0.5855932203389831,
      "grad_norm": 1.451384425163269,
      "learning_rate": 8.760756246302277e-06,
      "loss": 0.0183,
      "step": 691
    },
    {
      "epoch": 0.5864406779661017,
      "grad_norm": 0.25365039706230164,
      "learning_rate": 8.731407886417155e-06,
      "loss": 0.0009,
      "step": 692
    },
    {
      "epoch": 0.5872881355932204,
      "grad_norm": 2.36940860748291,
      "learning_rate": 8.70207062779531e-06,
      "loss": 0.0259,
      "step": 693
    },
    {
      "epoch": 0.588135593220339,
      "grad_norm": 0.5836230516433716,
      "learning_rate": 8.672744727162782e-06,
      "loss": 0.0034,
      "step": 694
    },
    {
      "epoch": 0.5889830508474576,
      "grad_norm": 0.7795729637145996,
      "learning_rate": 8.64343044114622e-06,
      "loss": 0.005,
      "step": 695
    },
    {
      "epoch": 0.5898305084745763,
      "grad_norm": 0.3191084563732147,
      "learning_rate": 8.614128026270633e-06,
      "loss": 0.0014,
      "step": 696
    },
    {
      "epoch": 0.5906779661016949,
      "grad_norm": 0.7273288369178772,
      "learning_rate": 8.584837738957155e-06,
      "loss": 0.0025,
      "step": 697
    },
    {
      "epoch": 0.5915254237288136,
      "grad_norm": 1.6525626182556152,
      "learning_rate": 8.555559835520786e-06,
      "loss": 0.0059,
      "step": 698
    },
    {
      "epoch": 0.5923728813559322,
      "grad_norm": 0.7382212281227112,
      "learning_rate": 8.526294572168157e-06,
      "loss": 0.0026,
      "step": 699
    },
    {
      "epoch": 0.5932203389830508,
      "grad_norm": 3.2163925170898438,
      "learning_rate": 8.497042204995299e-06,
      "loss": 0.0116,
      "step": 700
    },
    {
      "epoch": 0.5932203389830508,
      "eval_accuracy": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 9.157847671303898e-05,
      "eval_precision": 1.0,
      "eval_recall": 1.0,
      "eval_runtime": 49.7798,
      "eval_samples_per_second": 5.866,
      "eval_steps_per_second": 0.201,
      "step": 700
    },
    {
      "epoch": 0.5940677966101695,
      "grad_norm": 1.3996844291687012,
      "learning_rate": 8.46780298998537e-06,
      "loss": 0.0051,
      "step": 701
    },
    {
      "epoch": 0.5949152542372881,
      "grad_norm": 1.469482421875,
      "learning_rate": 8.438577183006448e-06,
      "loss": 0.0096,
      "step": 702
    },
    {
      "epoch": 0.5957627118644068,
      "grad_norm": 0.796106219291687,
      "learning_rate": 8.409365039809282e-06,
      "loss": 0.006,
      "step": 703
    },
    {
      "epoch": 0.5966101694915255,
      "grad_norm": 1.5384269952774048,
      "learning_rate": 8.380166816025043e-06,
      "loss": 0.0144,
      "step": 704
    },
    {
      "epoch": 0.597457627118644,
      "grad_norm": 2.1261978149414062,
      "learning_rate": 8.350982767163105e-06,
      "loss": 0.0185,
      "step": 705
    },
    {
      "epoch": 0.5983050847457627,
      "grad_norm": 2.251471757888794,
      "learning_rate": 8.321813148608784e-06,
      "loss": 0.0158,
      "step": 706
    },
    {
      "epoch": 0.5991525423728814,
      "grad_norm": 0.6852215528488159,
      "learning_rate": 8.292658215621139e-06,
      "loss": 0.0025,
      "step": 707
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.9804059863090515,
      "learning_rate": 8.263518223330698e-06,
      "loss": 0.0028,
      "step": 708
    },
    {
      "epoch": 0.6008474576271187,
      "grad_norm": 1.716261863708496,
      "learning_rate": 8.234393426737258e-06,
      "loss": 0.0095,
      "step": 709
    },
    {
      "epoch": 0.6016949152542372,
      "grad_norm": 2.618445634841919,
      "learning_rate": 8.205284080707634e-06,
      "loss": 0.0172,
      "step": 710
    },
    {
      "epoch": 0.6025423728813559,
      "grad_norm": 0.9949232935905457,
      "learning_rate": 8.176190439973442e-06,
      "loss": 0.0044,
      "step": 711
    },
    {
      "epoch": 0.6033898305084746,
      "grad_norm": 0.9794982075691223,
      "learning_rate": 8.147112759128859e-06,
      "loss": 0.0046,
      "step": 712
    },
    {
      "epoch": 0.6042372881355932,
      "grad_norm": 1.576850414276123,
      "learning_rate": 8.118051292628394e-06,
      "loss": 0.0127,
      "step": 713
    },
    {
      "epoch": 0.6050847457627119,
      "grad_norm": 1.6285077333450317,
      "learning_rate": 8.089006294784679e-06,
      "loss": 0.0077,
      "step": 714
    },
    {
      "epoch": 0.6059322033898306,
      "grad_norm": 2.055169105529785,
      "learning_rate": 8.059978019766219e-06,
      "loss": 0.0078,
      "step": 715
    },
    {
      "epoch": 0.6067796610169491,
      "grad_norm": 1.1716010570526123,
      "learning_rate": 8.030966721595186e-06,
      "loss": 0.0042,
      "step": 716
    },
    {
      "epoch": 0.6076271186440678,
      "grad_norm": 0.2800714075565338,
      "learning_rate": 8.001972654145194e-06,
      "loss": 0.0012,
      "step": 717
    },
    {
      "epoch": 0.6084745762711864,
      "grad_norm": 1.2018545866012573,
      "learning_rate": 7.972996071139065e-06,
      "loss": 0.009,
      "step": 718
    },
    {
      "epoch": 0.6093220338983051,
      "grad_norm": 3.2295126914978027,
      "learning_rate": 7.944037226146623e-06,
      "loss": 0.0188,
      "step": 719
    },
    {
      "epoch": 0.6101694915254238,
      "grad_norm": 2.7130823135375977,
      "learning_rate": 7.915096372582467e-06,
      "loss": 0.014,
      "step": 720
    },
    {
      "epoch": 0.6101694915254238,
      "eval_accuracy": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 9.377366950502619e-05,
      "eval_precision": 1.0,
      "eval_recall": 1.0,
      "eval_runtime": 51.3568,
      "eval_samples_per_second": 5.686,
      "eval_steps_per_second": 0.195,
      "step": 720
    },
    {
      "epoch": 0.6110169491525423,
      "grad_norm": 0.14015014469623566,
      "learning_rate": 7.886173763703757e-06,
      "loss": 0.0007,
      "step": 721
    },
    {
      "epoch": 0.611864406779661,
      "grad_norm": 1.3559490442276,
      "learning_rate": 7.857269652607995e-06,
      "loss": 0.005,
      "step": 722
    },
    {
      "epoch": 0.6127118644067797,
      "grad_norm": 1.6353223323822021,
      "learning_rate": 7.828384292230814e-06,
      "loss": 0.0081,
      "step": 723
    },
    {
      "epoch": 0.6135593220338983,
      "grad_norm": 1.1183819770812988,
      "learning_rate": 7.799517935343757e-06,
      "loss": 0.0034,
      "step": 724
    },
    {
      "epoch": 0.614406779661017,
      "grad_norm": 1.9186286926269531,
      "learning_rate": 7.770670834552074e-06,
      "loss": 0.0153,
      "step": 725
    },
    {
      "epoch": 0.6152542372881356,
      "grad_norm": 1.465635895729065,
      "learning_rate": 7.741843242292508e-06,
      "loss": 0.0108,
      "step": 726
    },
    {
      "epoch": 0.6161016949152542,
      "grad_norm": 1.6631442308425903,
      "learning_rate": 7.713035410831086e-06,
      "loss": 0.0155,
      "step": 727
    },
    {
      "epoch": 0.6169491525423729,
      "grad_norm": 0.37416231632232666,
      "learning_rate": 7.68424759226091e-06,
      "loss": 0.0011,
      "step": 728
    },
    {
      "epoch": 0.6177966101694915,
      "grad_norm": 1.5809506177902222,
      "learning_rate": 7.655480038499953e-06,
      "loss": 0.0071,
      "step": 729
    },
    {
      "epoch": 0.6186440677966102,
      "grad_norm": 1.0575535297393799,
      "learning_rate": 7.626733001288852e-06,
      "loss": 0.003,
      "step": 730
    },
    {
      "epoch": 0.6194915254237288,
      "grad_norm": 1.1455744504928589,
      "learning_rate": 7.598006732188708e-06,
      "loss": 0.007,
      "step": 731
    },
    {
      "epoch": 0.6203389830508474,
      "grad_norm": 1.1559722423553467,
      "learning_rate": 7.569301482578885e-06,
      "loss": 0.0043,
      "step": 732
    },
    {
      "epoch": 0.6211864406779661,
      "grad_norm": 4.226150035858154,
      "learning_rate": 7.540617503654804e-06,
      "loss": 0.0244,
      "step": 733
    },
    {
      "epoch": 0.6220338983050847,
      "grad_norm": 1.66443932056427,
      "learning_rate": 7.511955046425754e-06,
      "loss": 0.0073,
      "step": 734
    },
    {
      "epoch": 0.6228813559322034,
      "grad_norm": 4.203097820281982,
      "learning_rate": 7.483314361712686e-06,
      "loss": 0.0236,
      "step": 735
    },
    {
      "epoch": 0.6237288135593221,
      "grad_norm": 3.4578402042388916,
      "learning_rate": 7.454695700146024e-06,
      "loss": 0.0224,
      "step": 736
    },
    {
      "epoch": 0.6245762711864407,
      "grad_norm": 2.495051383972168,
      "learning_rate": 7.42609931216348e-06,
      "loss": 0.0303,
      "step": 737
    },
    {
      "epoch": 0.6254237288135593,
      "grad_norm": 0.11093101650476456,
      "learning_rate": 7.397525448007838e-06,
      "loss": 0.0005,
      "step": 738
    },
    {
      "epoch": 0.6262711864406779,
      "grad_norm": 0.8444148302078247,
      "learning_rate": 7.368974357724789e-06,
      "loss": 0.0038,
      "step": 739
    },
    {
      "epoch": 0.6271186440677966,
      "grad_norm": 0.6768697500228882,
      "learning_rate": 7.3404462911607325e-06,
      "loss": 0.0042,
      "step": 740
    },
    {
      "epoch": 0.6271186440677966,
      "eval_accuracy": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 9.098863665712997e-05,
      "eval_precision": 1.0,
      "eval_recall": 1.0,
      "eval_runtime": 51.0217,
      "eval_samples_per_second": 5.723,
      "eval_steps_per_second": 0.196,
      "step": 740
    },
    {
      "epoch": 0.6279661016949153,
      "grad_norm": 0.5370987057685852,
      "learning_rate": 7.3119414979605865e-06,
      "loss": 0.0043,
      "step": 741
    },
    {
      "epoch": 0.6288135593220339,
      "grad_norm": 2.2939460277557373,
      "learning_rate": 7.283460227565614e-06,
      "loss": 0.0163,
      "step": 742
    },
    {
      "epoch": 0.6296610169491526,
      "grad_norm": 0.1840486228466034,
      "learning_rate": 7.255002729211227e-06,
      "loss": 0.0014,
      "step": 743
    },
    {
      "epoch": 0.6305084745762712,
      "grad_norm": 2.645730495452881,
      "learning_rate": 7.226569251924811e-06,
      "loss": 0.0305,
      "step": 744
    },
    {
      "epoch": 0.6313559322033898,
      "grad_norm": 2.7763075828552246,
      "learning_rate": 7.198160044523555e-06,
      "loss": 0.0297,
      "step": 745
    },
    {
      "epoch": 0.6322033898305085,
      "grad_norm": 1.471494436264038,
      "learning_rate": 7.169775355612261e-06,
      "loss": 0.0038,
      "step": 746
    },
    {
      "epoch": 0.6330508474576271,
      "grad_norm": 1.1910088062286377,
      "learning_rate": 7.141415433581169e-06,
      "loss": 0.0051,
      "step": 747
    },
    {
      "epoch": 0.6338983050847458,
      "grad_norm": 0.6888835430145264,
      "learning_rate": 7.113080526603793e-06,
      "loss": 0.0018,
      "step": 748
    },
    {
      "epoch": 0.6347457627118644,
      "grad_norm": 0.5418266654014587,
      "learning_rate": 7.0847708826347415e-06,
      "loss": 0.0023,
      "step": 749
    },
    {
      "epoch": 0.635593220338983,
      "grad_norm": 0.5402665138244629,
      "learning_rate": 7.056486749407552e-06,
      "loss": 0.0013,
      "step": 750
    },
    {
      "epoch": 0.6364406779661017,
      "grad_norm": 0.44419825077056885,
      "learning_rate": 7.028228374432523e-06,
      "loss": 0.0018,
      "step": 751
    },
    {
      "epoch": 0.6372881355932203,
      "grad_norm": 2.0415663719177246,
      "learning_rate": 6.9999960049945406e-06,
      "loss": 0.0136,
      "step": 752
    },
    {
      "epoch": 0.638135593220339,
      "grad_norm": 1.5157843828201294,
      "learning_rate": 6.971789888150926e-06,
      "loss": 0.0225,
      "step": 753
    },
    {
      "epoch": 0.6389830508474577,
      "grad_norm": 0.30365321040153503,
      "learning_rate": 6.943610270729261e-06,
      "loss": 0.0013,
      "step": 754
    },
    {
      "epoch": 0.6398305084745762,
      "grad_norm": 1.8797694444656372,
      "learning_rate": 6.915457399325243e-06,
      "loss": 0.0126,
      "step": 755
    },
    {
      "epoch": 0.6406779661016949,
      "grad_norm": 1.3082208633422852,
      "learning_rate": 6.8873315203005155e-06,
      "loss": 0.0186,
      "step": 756
    },
    {
      "epoch": 0.6415254237288136,
      "grad_norm": 0.4574929475784302,
      "learning_rate": 6.859232879780515e-06,
      "loss": 0.0033,
      "step": 757
    },
    {
      "epoch": 0.6423728813559322,
      "grad_norm": 1.4100733995437622,
      "learning_rate": 6.831161723652313e-06,
      "loss": 0.0054,
      "step": 758
    },
    {
      "epoch": 0.6432203389830509,
      "grad_norm": 0.8795613646507263,
      "learning_rate": 6.803118297562479e-06,
      "loss": 0.006,
      "step": 759
    },
    {
      "epoch": 0.6440677966101694,
      "grad_norm": 3.974163293838501,
      "learning_rate": 6.775102846914912e-06,
      "loss": 0.0418,
      "step": 760
    },
    {
      "epoch": 0.6440677966101694,
      "eval_accuracy": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.0002802866802085191,
      "eval_precision": 1.0,
      "eval_recall": 1.0,
      "eval_runtime": 50.7257,
      "eval_samples_per_second": 5.756,
      "eval_steps_per_second": 0.197,
      "step": 760
    },
    {
      "epoch": 0.6449152542372881,
      "grad_norm": 2.1430978775024414,
      "learning_rate": 6.747115616868711e-06,
      "loss": 0.0171,
      "step": 761
    },
    {
      "epoch": 0.6457627118644068,
      "grad_norm": 0.2186567485332489,
      "learning_rate": 6.719156852336015e-06,
      "loss": 0.0009,
      "step": 762
    },
    {
      "epoch": 0.6466101694915254,
      "grad_norm": 2.305494546890259,
      "learning_rate": 6.691226797979864e-06,
      "loss": 0.0223,
      "step": 763
    },
    {
      "epoch": 0.6474576271186441,
      "grad_norm": 0.28418537974357605,
      "learning_rate": 6.66332569821206e-06,
      "loss": 0.0013,
      "step": 764
    },
    {
      "epoch": 0.6483050847457628,
      "grad_norm": 0.9447827935218811,
      "learning_rate": 6.635453797191034e-06,
      "loss": 0.0048,
      "step": 765
    },
    {
      "epoch": 0.6491525423728813,
      "grad_norm": 1.4569226503372192,
      "learning_rate": 6.607611338819697e-06,
      "loss": 0.0032,
      "step": 766
    },
    {
      "epoch": 0.65,
      "grad_norm": 0.2803967297077179,
      "learning_rate": 6.579798566743314e-06,
      "loss": 0.0011,
      "step": 767
    },
    {
      "epoch": 0.6508474576271186,
      "grad_norm": 1.287703037261963,
      "learning_rate": 6.552015724347367e-06,
      "loss": 0.0057,
      "step": 768
    },
    {
      "epoch": 0.6516949152542373,
      "grad_norm": 1.7164057493209839,
      "learning_rate": 6.52426305475543e-06,
      "loss": 0.0123,
      "step": 769
    },
    {
      "epoch": 0.652542372881356,
      "grad_norm": 2.8528084754943848,
      "learning_rate": 6.4965408008270355e-06,
      "loss": 0.0127,
      "step": 770
    },
    {
      "epoch": 0.6533898305084745,
      "grad_norm": 2.0749473571777344,
      "learning_rate": 6.4688492051555604e-06,
      "loss": 0.0145,
      "step": 771
    },
    {
      "epoch": 0.6542372881355932,
      "grad_norm": 3.287358522415161,
      "learning_rate": 6.441188510066092e-06,
      "loss": 0.0254,
      "step": 772
    },
    {
      "epoch": 0.6550847457627119,
      "grad_norm": 0.4311177432537079,
      "learning_rate": 6.413558957613309e-06,
      "loss": 0.0012,
      "step": 773
    },
    {
      "epoch": 0.6559322033898305,
      "grad_norm": 1.6251966953277588,
      "learning_rate": 6.385960789579364e-06,
      "loss": 0.008,
      "step": 774
    },
    {
      "epoch": 0.6567796610169492,
      "grad_norm": 2.233088493347168,
      "learning_rate": 6.358394247471779e-06,
      "loss": 0.0203,
      "step": 775
    },
    {
      "epoch": 0.6576271186440678,
      "grad_norm": 0.6515169143676758,
      "learning_rate": 6.330859572521311e-06,
      "loss": 0.0032,
      "step": 776
    },
    {
      "epoch": 0.6584745762711864,
      "grad_norm": 0.9649152159690857,
      "learning_rate": 6.303357005679858e-06,
      "loss": 0.0057,
      "step": 777
    },
    {
      "epoch": 0.6593220338983051,
      "grad_norm": 0.40915530920028687,
      "learning_rate": 6.275886787618339e-06,
      "loss": 0.0017,
      "step": 778
    },
    {
      "epoch": 0.6601694915254237,
      "grad_norm": 2.0900630950927734,
      "learning_rate": 6.2484491587246096e-06,
      "loss": 0.0091,
      "step": 779
    },
    {
      "epoch": 0.6610169491525424,
      "grad_norm": 0.4685976803302765,
      "learning_rate": 6.221044359101317e-06,
      "loss": 0.0024,
      "step": 780
    },
    {
      "epoch": 0.6610169491525424,
      "eval_accuracy": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.00018300920783076435,
      "eval_precision": 1.0,
      "eval_recall": 1.0,
      "eval_runtime": 50.7091,
      "eval_samples_per_second": 5.758,
      "eval_steps_per_second": 0.197,
      "step": 780
    },
    {
      "epoch": 0.661864406779661,
      "grad_norm": 0.4373491108417511,
      "learning_rate": 6.193672628563845e-06,
      "loss": 0.0016,
      "step": 781
    },
    {
      "epoch": 0.6627118644067796,
      "grad_norm": 0.18425188958644867,
      "learning_rate": 6.166334206638186e-06,
      "loss": 0.0007,
      "step": 782
    },
    {
      "epoch": 0.6635593220338983,
      "grad_norm": 1.5032649040222168,
      "learning_rate": 6.139029332558855e-06,
      "loss": 0.0087,
      "step": 783
    },
    {
      "epoch": 0.6644067796610169,
      "grad_norm": 1.4531553983688354,
      "learning_rate": 6.111758245266795e-06,
      "loss": 0.0055,
      "step": 784
    },
    {
      "epoch": 0.6652542372881356,
      "grad_norm": 1.0665950775146484,
      "learning_rate": 6.084521183407286e-06,
      "loss": 0.0075,
      "step": 785
    },
    {
      "epoch": 0.6661016949152543,
      "grad_norm": 2.243398666381836,
      "learning_rate": 6.057318385327857e-06,
      "loss": 0.0172,
      "step": 786
    },
    {
      "epoch": 0.6669491525423729,
      "grad_norm": 1.1581579446792603,
      "learning_rate": 6.030150089076199e-06,
      "loss": 0.0046,
      "step": 787
    },
    {
      "epoch": 0.6677966101694915,
      "grad_norm": 2.128571033477783,
      "learning_rate": 6.0030165323980794e-06,
      "loss": 0.0052,
      "step": 788
    },
    {
      "epoch": 0.6686440677966101,
      "grad_norm": 3.439826011657715,
      "learning_rate": 5.975917952735272e-06,
      "loss": 0.0174,
      "step": 789
    },
    {
      "epoch": 0.6694915254237288,
      "grad_norm": 0.6685582995414734,
      "learning_rate": 5.948854587223465e-06,
      "loss": 0.0034,
      "step": 790
    },
    {
      "epoch": 0.6703389830508475,
      "grad_norm": 0.4205131530761719,
      "learning_rate": 5.921826672690199e-06,
      "loss": 0.0016,
      "step": 791
    },
    {
      "epoch": 0.6711864406779661,
      "grad_norm": 0.8802849650382996,
      "learning_rate": 5.894834445652777e-06,
      "loss": 0.0041,
      "step": 792
    },
    {
      "epoch": 0.6720338983050848,
      "grad_norm": 2.2352685928344727,
      "learning_rate": 5.867878142316221e-06,
      "loss": 0.0108,
      "step": 793
    },
    {
      "epoch": 0.6728813559322034,
      "grad_norm": 2.6779541969299316,
      "learning_rate": 5.840957998571177e-06,
      "loss": 0.0305,
      "step": 794
    },
    {
      "epoch": 0.673728813559322,
      "grad_norm": 2.999138116836548,
      "learning_rate": 5.814074249991876e-06,
      "loss": 0.0156,
      "step": 795
    },
    {
      "epoch": 0.6745762711864407,
      "grad_norm": 0.4623313546180725,
      "learning_rate": 5.787227131834043e-06,
      "loss": 0.0013,
      "step": 796
    },
    {
      "epoch": 0.6754237288135593,
      "grad_norm": 0.4670167863368988,
      "learning_rate": 5.7604168790328774e-06,
      "loss": 0.0016,
      "step": 797
    },
    {
      "epoch": 0.676271186440678,
      "grad_norm": 1.1071865558624268,
      "learning_rate": 5.733643726200958e-06,
      "loss": 0.0055,
      "step": 798
    },
    {
      "epoch": 0.6771186440677966,
      "grad_norm": 1.0425511598587036,
      "learning_rate": 5.706907907626216e-06,
      "loss": 0.0115,
      "step": 799
    },
    {
      "epoch": 0.6779661016949152,
      "grad_norm": 0.9477194547653198,
      "learning_rate": 5.680209657269871e-06,
      "loss": 0.0039,
      "step": 800
    },
    {
      "epoch": 0.6779661016949152,
      "eval_accuracy": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.0001500351936556399,
      "eval_precision": 1.0,
      "eval_recall": 1.0,
      "eval_runtime": 52.726,
      "eval_samples_per_second": 5.538,
      "eval_steps_per_second": 0.19,
      "step": 800
    },
    {
      "epoch": 0.6788135593220339,
      "grad_norm": 0.8634885549545288,
      "learning_rate": 5.6535492087643904e-06,
      "loss": 0.0026,
      "step": 801
    },
    {
      "epoch": 0.6796610169491526,
      "grad_norm": 2.032689094543457,
      "learning_rate": 5.626926795411447e-06,
      "loss": 0.01,
      "step": 802
    },
    {
      "epoch": 0.6805084745762712,
      "grad_norm": 0.10548463463783264,
      "learning_rate": 5.6003426501798665e-06,
      "loss": 0.0005,
      "step": 803
    },
    {
      "epoch": 0.6813559322033899,
      "grad_norm": 1.6854254007339478,
      "learning_rate": 5.573797005703601e-06,
      "loss": 0.0037,
      "step": 804
    },
    {
      "epoch": 0.6822033898305084,
      "grad_norm": 0.280429869890213,
      "learning_rate": 5.547290094279687e-06,
      "loss": 0.001,
      "step": 805
    },
    {
      "epoch": 0.6830508474576271,
      "grad_norm": 0.711410403251648,
      "learning_rate": 5.520822147866214e-06,
      "loss": 0.0033,
      "step": 806
    },
    {
      "epoch": 0.6838983050847458,
      "grad_norm": 0.2613879144191742,
      "learning_rate": 5.494393398080292e-06,
      "loss": 0.0011,
      "step": 807
    },
    {
      "epoch": 0.6847457627118644,
      "grad_norm": 0.8584437966346741,
      "learning_rate": 5.46800407619603e-06,
      "loss": 0.0023,
      "step": 808
    },
    {
      "epoch": 0.6855932203389831,
      "grad_norm": 3.826030731201172,
      "learning_rate": 5.441654413142508e-06,
      "loss": 0.0228,
      "step": 809
    },
    {
      "epoch": 0.6864406779661016,
      "grad_norm": 0.7557411193847656,
      "learning_rate": 5.415344639501754e-06,
      "loss": 0.0033,
      "step": 810
    },
    {
      "epoch": 0.6872881355932203,
      "grad_norm": 1.0392420291900635,
      "learning_rate": 5.38907498550674e-06,
      "loss": 0.0043,
      "step": 811
    },
    {
      "epoch": 0.688135593220339,
      "grad_norm": 2.502735137939453,
      "learning_rate": 5.362845681039348e-06,
      "loss": 0.0147,
      "step": 812
    },
    {
      "epoch": 0.6889830508474576,
      "grad_norm": 0.42259418964385986,
      "learning_rate": 5.336656955628371e-06,
      "loss": 0.0021,
      "step": 813
    },
    {
      "epoch": 0.6898305084745763,
      "grad_norm": 2.6665008068084717,
      "learning_rate": 5.310509038447492e-06,
      "loss": 0.0194,
      "step": 814
    },
    {
      "epoch": 0.690677966101695,
      "grad_norm": 2.9882800579071045,
      "learning_rate": 5.284402158313299e-06,
      "loss": 0.0415,
      "step": 815
    },
    {
      "epoch": 0.6915254237288135,
      "grad_norm": 0.5250701904296875,
      "learning_rate": 5.25833654368326e-06,
      "loss": 0.0027,
      "step": 816
    },
    {
      "epoch": 0.6923728813559322,
      "grad_norm": 0.46300551295280457,
      "learning_rate": 5.23231242265375e-06,
      "loss": 0.0013,
      "step": 817
    },
    {
      "epoch": 0.6932203389830508,
      "grad_norm": 0.7175685167312622,
      "learning_rate": 5.206330022958024e-06,
      "loss": 0.0037,
      "step": 818
    },
    {
      "epoch": 0.6940677966101695,
      "grad_norm": 0.36853301525115967,
      "learning_rate": 5.180389571964249e-06,
      "loss": 0.0016,
      "step": 819
    },
    {
      "epoch": 0.6949152542372882,
      "grad_norm": 0.713392436504364,
      "learning_rate": 5.1544912966735e-06,
      "loss": 0.0048,
      "step": 820
    },
    {
      "epoch": 0.6949152542372882,
      "eval_accuracy": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 9.25260319490917e-05,
      "eval_precision": 1.0,
      "eval_recall": 1.0,
      "eval_runtime": 51.5622,
      "eval_samples_per_second": 5.663,
      "eval_steps_per_second": 0.194,
      "step": 820
    },
    {
      "epoch": 0.6957627118644067,
      "grad_norm": 1.1480737924575806,
      "learning_rate": 5.1286354237177806e-06,
      "loss": 0.0071,
      "step": 821
    },
    {
      "epoch": 0.6966101694915254,
      "grad_norm": 1.0792937278747559,
      "learning_rate": 5.102822179358037e-06,
      "loss": 0.0062,
      "step": 822
    },
    {
      "epoch": 0.6974576271186441,
      "grad_norm": 2.4379987716674805,
      "learning_rate": 5.0770517894821815e-06,
      "loss": 0.0301,
      "step": 823
    },
    {
      "epoch": 0.6983050847457627,
      "grad_norm": 1.457727313041687,
      "learning_rate": 5.051324479603106e-06,
      "loss": 0.0199,
      "step": 824
    },
    {
      "epoch": 0.6991525423728814,
      "grad_norm": 0.9668751955032349,
      "learning_rate": 5.025640474856732e-06,
      "loss": 0.003,
      "step": 825
    },
    {
      "epoch": 0.7,
      "grad_norm": 0.48410564661026,
      "learning_rate": 5.000000000000003e-06,
      "loss": 0.0013,
      "step": 826
    },
    {
      "epoch": 0.7008474576271186,
      "grad_norm": 0.28067731857299805,
      "learning_rate": 4.97440327940895e-06,
      "loss": 0.0012,
      "step": 827
    },
    {
      "epoch": 0.7016949152542373,
      "grad_norm": 0.2483496367931366,
      "learning_rate": 4.948850537076719e-06,
      "loss": 0.0007,
      "step": 828
    },
    {
      "epoch": 0.7025423728813559,
      "grad_norm": 1.3155626058578491,
      "learning_rate": 4.923341996611604e-06,
      "loss": 0.0077,
      "step": 829
    },
    {
      "epoch": 0.7033898305084746,
      "grad_norm": 0.7930201888084412,
      "learning_rate": 4.897877881235091e-06,
      "loss": 0.0027,
      "step": 830
    },
    {
      "epoch": 0.7042372881355933,
      "grad_norm": 0.8325580954551697,
      "learning_rate": 4.8724584137799235e-06,
      "loss": 0.0081,
      "step": 831
    },
    {
      "epoch": 0.7050847457627119,
      "grad_norm": 2.1520488262176514,
      "learning_rate": 4.847083816688123e-06,
      "loss": 0.0172,
      "step": 832
    },
    {
      "epoch": 0.7059322033898305,
      "grad_norm": 0.5673890709877014,
      "learning_rate": 4.821754312009063e-06,
      "loss": 0.0019,
      "step": 833
    },
    {
      "epoch": 0.7067796610169491,
      "grad_norm": 2.460827350616455,
      "learning_rate": 4.796470121397518e-06,
      "loss": 0.0238,
      "step": 834
    },
    {
      "epoch": 0.7076271186440678,
      "grad_norm": 1.8376518487930298,
      "learning_rate": 4.771231466111725e-06,
      "loss": 0.0136,
      "step": 835
    },
    {
      "epoch": 0.7084745762711865,
      "grad_norm": 1.0489223003387451,
      "learning_rate": 4.746038567011454e-06,
      "loss": 0.0035,
      "step": 836
    },
    {
      "epoch": 0.7093220338983051,
      "grad_norm": 2.19427227973938,
      "learning_rate": 4.7208916445560625e-06,
      "loss": 0.0212,
      "step": 837
    },
    {
      "epoch": 0.7101694915254237,
      "grad_norm": 2.033280849456787,
      "learning_rate": 4.695790918802577e-06,
      "loss": 0.0033,
      "step": 838
    },
    {
      "epoch": 0.7110169491525423,
      "grad_norm": 1.6251804828643799,
      "learning_rate": 4.67073660940376e-06,
      "loss": 0.0187,
      "step": 839
    },
    {
      "epoch": 0.711864406779661,
      "grad_norm": 0.2912212610244751,
      "learning_rate": 4.645728935606194e-06,
      "loss": 0.0007,
      "step": 840
    },
    {
      "epoch": 0.711864406779661,
      "eval_accuracy": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.00012361357221379876,
      "eval_precision": 1.0,
      "eval_recall": 1.0,
      "eval_runtime": 51.0511,
      "eval_samples_per_second": 5.72,
      "eval_steps_per_second": 0.196,
      "step": 840
    },
    {
      "epoch": 0.7127118644067797,
      "grad_norm": 3.8638107776641846,
      "learning_rate": 4.620768116248362e-06,
      "loss": 0.0192,
      "step": 841
    },
    {
      "epoch": 0.7135593220338983,
      "grad_norm": 3.521618366241455,
      "learning_rate": 4.595854369758727e-06,
      "loss": 0.0239,
      "step": 842
    },
    {
      "epoch": 0.714406779661017,
      "grad_norm": 4.152134418487549,
      "learning_rate": 4.570987914153824e-06,
      "loss": 0.0344,
      "step": 843
    },
    {
      "epoch": 0.7152542372881356,
      "grad_norm": 1.025924801826477,
      "learning_rate": 4.546168967036352e-06,
      "loss": 0.0037,
      "step": 844
    },
    {
      "epoch": 0.7161016949152542,
      "grad_norm": 1.601256012916565,
      "learning_rate": 4.521397745593279e-06,
      "loss": 0.008,
      "step": 845
    },
    {
      "epoch": 0.7169491525423729,
      "grad_norm": 1.8692275285720825,
      "learning_rate": 4.4966744665939226e-06,
      "loss": 0.0072,
      "step": 846
    },
    {
      "epoch": 0.7177966101694915,
      "grad_norm": 2.0935654640197754,
      "learning_rate": 4.4719993463880695e-06,
      "loss": 0.0217,
      "step": 847
    },
    {
      "epoch": 0.7186440677966102,
      "grad_norm": 1.089236855506897,
      "learning_rate": 4.447372600904065e-06,
      "loss": 0.0095,
      "step": 848
    },
    {
      "epoch": 0.7194915254237289,
      "grad_norm": 1.3698294162750244,
      "learning_rate": 4.422794445646947e-06,
      "loss": 0.0075,
      "step": 849
    },
    {
      "epoch": 0.7203389830508474,
      "grad_norm": 1.4754582643508911,
      "learning_rate": 4.398265095696539e-06,
      "loss": 0.012,
      "step": 850
    },
    {
      "epoch": 0.7211864406779661,
      "grad_norm": 0.5242229104042053,
      "learning_rate": 4.373784765705586e-06,
      "loss": 0.0038,
      "step": 851
    },
    {
      "epoch": 0.7220338983050848,
      "grad_norm": 3.324636220932007,
      "learning_rate": 4.349353669897856e-06,
      "loss": 0.0299,
      "step": 852
    },
    {
      "epoch": 0.7228813559322034,
      "grad_norm": 1.4912688732147217,
      "learning_rate": 4.324972022066284e-06,
      "loss": 0.009,
      "step": 853
    },
    {
      "epoch": 0.7237288135593221,
      "grad_norm": 1.8088048696517944,
      "learning_rate": 4.300640035571085e-06,
      "loss": 0.0156,
      "step": 854
    },
    {
      "epoch": 0.7245762711864406,
      "grad_norm": 0.9810622930526733,
      "learning_rate": 4.276357923337903e-06,
      "loss": 0.0054,
      "step": 855
    },
    {
      "epoch": 0.7254237288135593,
      "grad_norm": 1.399301290512085,
      "learning_rate": 4.2521258978559324e-06,
      "loss": 0.0144,
      "step": 856
    },
    {
      "epoch": 0.726271186440678,
      "grad_norm": 1.4187586307525635,
      "learning_rate": 4.227944171176072e-06,
      "loss": 0.0111,
      "step": 857
    },
    {
      "epoch": 0.7271186440677966,
      "grad_norm": 1.7159850597381592,
      "learning_rate": 4.203812954909057e-06,
      "loss": 0.0124,
      "step": 858
    },
    {
      "epoch": 0.7279661016949153,
      "grad_norm": 1.37935471534729,
      "learning_rate": 4.179732460223626e-06,
      "loss": 0.0118,
      "step": 859
    },
    {
      "epoch": 0.7288135593220338,
      "grad_norm": 0.29636350274086,
      "learning_rate": 4.1557028978446415e-06,
      "loss": 0.0014,
      "step": 860
    },
    {
      "epoch": 0.7288135593220338,
      "eval_accuracy": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.00012519690790213645,
      "eval_precision": 1.0,
      "eval_recall": 1.0,
      "eval_runtime": 50.6172,
      "eval_samples_per_second": 5.769,
      "eval_steps_per_second": 0.198,
      "step": 860
    },
    {
      "epoch": 0.7296610169491525,
      "grad_norm": 0.8602759838104248,
      "learning_rate": 4.1317244780512775e-06,
      "loss": 0.0092,
      "step": 861
    },
    {
      "epoch": 0.7305084745762712,
      "grad_norm": 2.8475470542907715,
      "learning_rate": 4.107797410675166e-06,
      "loss": 0.0388,
      "step": 862
    },
    {
      "epoch": 0.7313559322033898,
      "grad_norm": 1.3523766994476318,
      "learning_rate": 4.083921905098559e-06,
      "loss": 0.0068,
      "step": 863
    },
    {
      "epoch": 0.7322033898305085,
      "grad_norm": 1.5425556898117065,
      "learning_rate": 4.060098170252495e-06,
      "loss": 0.0116,
      "step": 864
    },
    {
      "epoch": 0.7330508474576272,
      "grad_norm": 0.3472643494606018,
      "learning_rate": 4.036326414614985e-06,
      "loss": 0.0016,
      "step": 865
    },
    {
      "epoch": 0.7338983050847457,
      "grad_norm": 0.4821791648864746,
      "learning_rate": 4.0126068462091705e-06,
      "loss": 0.0022,
      "step": 866
    },
    {
      "epoch": 0.7347457627118644,
      "grad_norm": 0.49641525745391846,
      "learning_rate": 3.988939672601509e-06,
      "loss": 0.0018,
      "step": 867
    },
    {
      "epoch": 0.735593220338983,
      "grad_norm": 1.2695690393447876,
      "learning_rate": 3.9653251008999615e-06,
      "loss": 0.0189,
      "step": 868
    },
    {
      "epoch": 0.7364406779661017,
      "grad_norm": 0.7525699734687805,
      "learning_rate": 3.941763337752177e-06,
      "loss": 0.0027,
      "step": 869
    },
    {
      "epoch": 0.7372881355932204,
      "grad_norm": 1.9671075344085693,
      "learning_rate": 3.918254589343683e-06,
      "loss": 0.0161,
      "step": 870
    },
    {
      "epoch": 0.738135593220339,
      "grad_norm": 0.5608029365539551,
      "learning_rate": 3.894799061396086e-06,
      "loss": 0.002,
      "step": 871
    },
    {
      "epoch": 0.7389830508474576,
      "grad_norm": 2.967503309249878,
      "learning_rate": 3.871396959165267e-06,
      "loss": 0.0201,
      "step": 872
    },
    {
      "epoch": 0.7398305084745763,
      "grad_norm": 0.9887444972991943,
      "learning_rate": 3.848048487439583e-06,
      "loss": 0.0059,
      "step": 873
    },
    {
      "epoch": 0.7406779661016949,
      "grad_norm": 1.1107892990112305,
      "learning_rate": 3.824753850538082e-06,
      "loss": 0.0071,
      "step": 874
    },
    {
      "epoch": 0.7415254237288136,
      "grad_norm": 0.9307472705841064,
      "learning_rate": 3.801513252308712e-06,
      "loss": 0.0042,
      "step": 875
    },
    {
      "epoch": 0.7423728813559322,
      "grad_norm": 2.223409652709961,
      "learning_rate": 3.778326896126533e-06,
      "loss": 0.0084,
      "step": 876
    },
    {
      "epoch": 0.7432203389830508,
      "grad_norm": 0.8251433968544006,
      "learning_rate": 3.755194984891943e-06,
      "loss": 0.0042,
      "step": 877
    },
    {
      "epoch": 0.7440677966101695,
      "grad_norm": 1.5690832138061523,
      "learning_rate": 3.7321177210288974e-06,
      "loss": 0.0045,
      "step": 878
    },
    {
      "epoch": 0.7449152542372881,
      "grad_norm": 1.1555606126785278,
      "learning_rate": 3.709095306483149e-06,
      "loss": 0.009,
      "step": 879
    },
    {
      "epoch": 0.7457627118644068,
      "grad_norm": 0.7731421589851379,
      "learning_rate": 3.6861279427204634e-06,
      "loss": 0.0056,
      "step": 880
    },
    {
      "epoch": 0.7457627118644068,
      "eval_accuracy": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 9.962059266399592e-05,
      "eval_precision": 1.0,
      "eval_recall": 1.0,
      "eval_runtime": 52.1678,
      "eval_samples_per_second": 5.597,
      "eval_steps_per_second": 0.192,
      "step": 880
    },
    {
      "epoch": 0.7466101694915255,
      "grad_norm": 0.9392852783203125,
      "learning_rate": 3.6632158307248713e-06,
      "loss": 0.0043,
      "step": 881
    },
    {
      "epoch": 0.747457627118644,
      "grad_norm": 0.8620559573173523,
      "learning_rate": 3.6403591709968924e-06,
      "loss": 0.0049,
      "step": 882
    },
    {
      "epoch": 0.7483050847457627,
      "grad_norm": 1.7161260843276978,
      "learning_rate": 3.617558163551802e-06,
      "loss": 0.0101,
      "step": 883
    },
    {
      "epoch": 0.7491525423728813,
      "grad_norm": 0.5389106273651123,
      "learning_rate": 3.5948130079178666e-06,
      "loss": 0.0052,
      "step": 884
    },
    {
      "epoch": 0.75,
      "grad_norm": 1.6375874280929565,
      "learning_rate": 3.5721239031346067e-06,
      "loss": 0.0099,
      "step": 885
    },
    {
      "epoch": 0.7508474576271187,
      "grad_norm": 0.791953444480896,
      "learning_rate": 3.5494910477510445e-06,
      "loss": 0.0035,
      "step": 886
    },
    {
      "epoch": 0.7516949152542373,
      "grad_norm": 2.004249095916748,
      "learning_rate": 3.526914639823973e-06,
      "loss": 0.012,
      "step": 887
    },
    {
      "epoch": 0.752542372881356,
      "grad_norm": 0.7185747623443604,
      "learning_rate": 3.5043948769162227e-06,
      "loss": 0.0037,
      "step": 888
    },
    {
      "epoch": 0.7533898305084745,
      "grad_norm": 1.0839685201644897,
      "learning_rate": 3.4819319560949303e-06,
      "loss": 0.0043,
      "step": 889
    },
    {
      "epoch": 0.7542372881355932,
      "grad_norm": 1.8889586925506592,
      "learning_rate": 3.4595260739298174e-06,
      "loss": 0.0236,
      "step": 890
    },
    {
      "epoch": 0.7550847457627119,
      "grad_norm": 1.4316060543060303,
      "learning_rate": 3.437177426491468e-06,
      "loss": 0.0168,
      "step": 891
    },
    {
      "epoch": 0.7559322033898305,
      "grad_norm": 1.128692865371704,
      "learning_rate": 3.414886209349615e-06,
      "loss": 0.007,
      "step": 892
    },
    {
      "epoch": 0.7567796610169492,
      "grad_norm": 1.5015407800674438,
      "learning_rate": 3.3926526175714246e-06,
      "loss": 0.0063,
      "step": 893
    },
    {
      "epoch": 0.7576271186440678,
      "grad_norm": 0.8763653635978699,
      "learning_rate": 3.3704768457197933e-06,
      "loss": 0.0039,
      "step": 894
    },
    {
      "epoch": 0.7584745762711864,
      "grad_norm": 2.3314383029937744,
      "learning_rate": 3.3483590878516437e-06,
      "loss": 0.0201,
      "step": 895
    },
    {
      "epoch": 0.7593220338983051,
      "grad_norm": 1.774864912033081,
      "learning_rate": 3.3262995375162256e-06,
      "loss": 0.0058,
      "step": 896
    },
    {
      "epoch": 0.7601694915254237,
      "grad_norm": 0.5185796618461609,
      "learning_rate": 3.304298387753426e-06,
      "loss": 0.0022,
      "step": 897
    },
    {
      "epoch": 0.7610169491525424,
      "grad_norm": 1.1957974433898926,
      "learning_rate": 3.282355831092072e-06,
      "loss": 0.0046,
      "step": 898
    },
    {
      "epoch": 0.761864406779661,
      "grad_norm": 1.759142518043518,
      "learning_rate": 3.2604720595482598e-06,
      "loss": 0.0097,
      "step": 899
    },
    {
      "epoch": 0.7627118644067796,
      "grad_norm": 2.0010337829589844,
      "learning_rate": 3.2386472646236565e-06,
      "loss": 0.0107,
      "step": 900
    },
    {
      "epoch": 0.7627118644067796,
      "eval_accuracy": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 9.30224996409379e-05,
      "eval_precision": 1.0,
      "eval_recall": 1.0,
      "eval_runtime": 49.6959,
      "eval_samples_per_second": 5.876,
      "eval_steps_per_second": 0.201,
      "step": 900
    },
    {
      "epoch": 0.7635593220338983,
      "grad_norm": 1.5581014156341553,
      "learning_rate": 3.216881637303839e-06,
      "loss": 0.0083,
      "step": 901
    },
    {
      "epoch": 0.764406779661017,
      "grad_norm": 1.8738924264907837,
      "learning_rate": 3.1951753680566143e-06,
      "loss": 0.0215,
      "step": 902
    },
    {
      "epoch": 0.7652542372881356,
      "grad_norm": 0.4267842173576355,
      "learning_rate": 3.1735286468303563e-06,
      "loss": 0.0016,
      "step": 903
    },
    {
      "epoch": 0.7661016949152543,
      "grad_norm": 1.4631012678146362,
      "learning_rate": 3.151941663052345e-06,
      "loss": 0.0058,
      "step": 904
    },
    {
      "epoch": 0.7669491525423728,
      "grad_norm": 0.23579372465610504,
      "learning_rate": 3.130414605627102e-06,
      "loss": 0.0017,
      "step": 905
    },
    {
      "epoch": 0.7677966101694915,
      "grad_norm": 1.0443428754806519,
      "learning_rate": 3.1089476629347494e-06,
      "loss": 0.0078,
      "step": 906
    },
    {
      "epoch": 0.7686440677966102,
      "grad_norm": 0.8802245259284973,
      "learning_rate": 3.087541022829347e-06,
      "loss": 0.0052,
      "step": 907
    },
    {
      "epoch": 0.7694915254237288,
      "grad_norm": 0.9820923805236816,
      "learning_rate": 3.066194872637258e-06,
      "loss": 0.0022,
      "step": 908
    },
    {
      "epoch": 0.7703389830508475,
      "grad_norm": 0.40738704800605774,
      "learning_rate": 3.04490939915551e-06,
      "loss": 0.001,
      "step": 909
    },
    {
      "epoch": 0.7711864406779662,
      "grad_norm": 2.081660032272339,
      "learning_rate": 3.023684788650154e-06,
      "loss": 0.0101,
      "step": 910
    },
    {
      "epoch": 0.7720338983050847,
      "grad_norm": 1.3725014925003052,
      "learning_rate": 3.002521226854641e-06,
      "loss": 0.0069,
      "step": 911
    },
    {
      "epoch": 0.7728813559322034,
      "grad_norm": 2.1171929836273193,
      "learning_rate": 2.981418898968186e-06,
      "loss": 0.0139,
      "step": 912
    },
    {
      "epoch": 0.773728813559322,
      "grad_norm": 1.6483219861984253,
      "learning_rate": 2.9603779896541705e-06,
      "loss": 0.0092,
      "step": 913
    },
    {
      "epoch": 0.7745762711864407,
      "grad_norm": 0.36683687567710876,
      "learning_rate": 2.939398683038497e-06,
      "loss": 0.0012,
      "step": 914
    },
    {
      "epoch": 0.7754237288135594,
      "grad_norm": 1.9361350536346436,
      "learning_rate": 2.918481162707999e-06,
      "loss": 0.0093,
      "step": 915
    },
    {
      "epoch": 0.7762711864406779,
      "grad_norm": 0.6846543550491333,
      "learning_rate": 2.89762561170882e-06,
      "loss": 0.0035,
      "step": 916
    },
    {
      "epoch": 0.7771186440677966,
      "grad_norm": 1.052035927772522,
      "learning_rate": 2.8768322125448265e-06,
      "loss": 0.0123,
      "step": 917
    },
    {
      "epoch": 0.7779661016949152,
      "grad_norm": 0.6025975942611694,
      "learning_rate": 2.856101147175998e-06,
      "loss": 0.0035,
      "step": 918
    },
    {
      "epoch": 0.7788135593220339,
      "grad_norm": 1.8254081010818481,
      "learning_rate": 2.8354325970168483e-06,
      "loss": 0.0175,
      "step": 919
    },
    {
      "epoch": 0.7796610169491526,
      "grad_norm": 0.6324992179870605,
      "learning_rate": 2.814826742934823e-06,
      "loss": 0.0027,
      "step": 920
    },
    {
      "epoch": 0.7796610169491526,
      "eval_accuracy": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 7.932856533443555e-05,
      "eval_precision": 1.0,
      "eval_recall": 1.0,
      "eval_runtime": 50.5195,
      "eval_samples_per_second": 5.78,
      "eval_steps_per_second": 0.198,
      "step": 920
    },
    {
      "epoch": 0.7805084745762711,
      "grad_norm": 4.134251117706299,
      "learning_rate": 2.794283765248722e-06,
      "loss": 0.0218,
      "step": 921
    },
    {
      "epoch": 0.7813559322033898,
      "grad_norm": 1.057350754737854,
      "learning_rate": 2.7738038437271288e-06,
      "loss": 0.0032,
      "step": 922
    },
    {
      "epoch": 0.7822033898305085,
      "grad_norm": 0.7094781994819641,
      "learning_rate": 2.7533871575868275e-06,
      "loss": 0.0028,
      "step": 923
    },
    {
      "epoch": 0.7830508474576271,
      "grad_norm": 2.3617732524871826,
      "learning_rate": 2.733033885491241e-06,
      "loss": 0.0126,
      "step": 924
    },
    {
      "epoch": 0.7838983050847458,
      "grad_norm": 0.1944715678691864,
      "learning_rate": 2.7127442055488617e-06,
      "loss": 0.0007,
      "step": 925
    },
    {
      "epoch": 0.7847457627118644,
      "grad_norm": 0.6528817415237427,
      "learning_rate": 2.6925182953117022e-06,
      "loss": 0.0046,
      "step": 926
    },
    {
      "epoch": 0.785593220338983,
      "grad_norm": 0.31304916739463806,
      "learning_rate": 2.67235633177373e-06,
      "loss": 0.0016,
      "step": 927
    },
    {
      "epoch": 0.7864406779661017,
      "grad_norm": 0.75702303647995,
      "learning_rate": 2.6522584913693295e-06,
      "loss": 0.0047,
      "step": 928
    },
    {
      "epoch": 0.7872881355932203,
      "grad_norm": 1.600816011428833,
      "learning_rate": 2.6322249499717477e-06,
      "loss": 0.0062,
      "step": 929
    },
    {
      "epoch": 0.788135593220339,
      "grad_norm": 1.592640995979309,
      "learning_rate": 2.6122558828915647e-06,
      "loss": 0.0064,
      "step": 930
    },
    {
      "epoch": 0.7889830508474577,
      "grad_norm": 2.1126153469085693,
      "learning_rate": 2.5923514648751537e-06,
      "loss": 0.0265,
      "step": 931
    },
    {
      "epoch": 0.7898305084745763,
      "grad_norm": 1.4339178800582886,
      "learning_rate": 2.572511870103149e-06,
      "loss": 0.0054,
      "step": 932
    },
    {
      "epoch": 0.7906779661016949,
      "grad_norm": 2.253162145614624,
      "learning_rate": 2.55273727218894e-06,
      "loss": 0.0321,
      "step": 933
    },
    {
      "epoch": 0.7915254237288135,
      "grad_norm": 1.1612133979797363,
      "learning_rate": 2.533027844177123e-06,
      "loss": 0.0062,
      "step": 934
    },
    {
      "epoch": 0.7923728813559322,
      "grad_norm": 1.0363982915878296,
      "learning_rate": 2.5133837585420084e-06,
      "loss": 0.0053,
      "step": 935
    },
    {
      "epoch": 0.7932203389830509,
      "grad_norm": 1.3332302570343018,
      "learning_rate": 2.4938051871861046e-06,
      "loss": 0.0072,
      "step": 936
    },
    {
      "epoch": 0.7940677966101695,
      "grad_norm": 0.3061300218105316,
      "learning_rate": 2.4742923014386154e-06,
      "loss": 0.0015,
      "step": 937
    },
    {
      "epoch": 0.7949152542372881,
      "grad_norm": 2.649893045425415,
      "learning_rate": 2.4548452720539375e-06,
      "loss": 0.0238,
      "step": 938
    },
    {
      "epoch": 0.7957627118644067,
      "grad_norm": 0.9358623623847961,
      "learning_rate": 2.435464269210167e-06,
      "loss": 0.0036,
      "step": 939
    },
    {
      "epoch": 0.7966101694915254,
      "grad_norm": 1.4924583435058594,
      "learning_rate": 2.4161494625076164e-06,
      "loss": 0.0105,
      "step": 940
    },
    {
      "epoch": 0.7966101694915254,
      "eval_accuracy": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.00010792797547765076,
      "eval_precision": 1.0,
      "eval_recall": 1.0,
      "eval_runtime": 49.837,
      "eval_samples_per_second": 5.859,
      "eval_steps_per_second": 0.201,
      "step": 940
    },
    {
      "epoch": 0.7974576271186441,
      "grad_norm": 0.9415515661239624,
      "learning_rate": 2.3969010209673215e-06,
      "loss": 0.0031,
      "step": 941
    },
    {
      "epoch": 0.7983050847457627,
      "grad_norm": 1.4553923606872559,
      "learning_rate": 2.3777191130295673e-06,
      "loss": 0.008,
      "step": 942
    },
    {
      "epoch": 0.7991525423728814,
      "grad_norm": 0.9974135160446167,
      "learning_rate": 2.3586039065524113e-06,
      "loss": 0.0037,
      "step": 943
    },
    {
      "epoch": 0.8,
      "grad_norm": 1.052581548690796,
      "learning_rate": 2.339555568810221e-06,
      "loss": 0.0057,
      "step": 944
    },
    {
      "epoch": 0.8008474576271186,
      "grad_norm": 0.27318713068962097,
      "learning_rate": 2.3205742664922006e-06,
      "loss": 0.0011,
      "step": 945
    },
    {
      "epoch": 0.8016949152542373,
      "grad_norm": 2.6839377880096436,
      "learning_rate": 2.3016601657009364e-06,
      "loss": 0.0192,
      "step": 946
    },
    {
      "epoch": 0.8025423728813559,
      "grad_norm": 0.8619096279144287,
      "learning_rate": 2.282813431950952e-06,
      "loss": 0.0026,
      "step": 947
    },
    {
      "epoch": 0.8033898305084746,
      "grad_norm": 2.3613054752349854,
      "learning_rate": 2.264034230167246e-06,
      "loss": 0.0161,
      "step": 948
    },
    {
      "epoch": 0.8042372881355933,
      "grad_norm": 1.840660572052002,
      "learning_rate": 2.245322724683854e-06,
      "loss": 0.0191,
      "step": 949
    },
    {
      "epoch": 0.8050847457627118,
      "grad_norm": 1.5182996988296509,
      "learning_rate": 2.2266790792424096e-06,
      "loss": 0.0083,
      "step": 950
    },
    {
      "epoch": 0.8059322033898305,
      "grad_norm": 1.8400460481643677,
      "learning_rate": 2.208103456990719e-06,
      "loss": 0.0136,
      "step": 951
    },
    {
      "epoch": 0.8067796610169492,
      "grad_norm": 1.5054808855056763,
      "learning_rate": 2.1895960204813194e-06,
      "loss": 0.0101,
      "step": 952
    },
    {
      "epoch": 0.8076271186440678,
      "grad_norm": 1.5928698778152466,
      "learning_rate": 2.1711569316700774e-06,
      "loss": 0.0118,
      "step": 953
    },
    {
      "epoch": 0.8084745762711865,
      "grad_norm": 1.162479281425476,
      "learning_rate": 2.1527863519147474e-06,
      "loss": 0.0068,
      "step": 954
    },
    {
      "epoch": 0.809322033898305,
      "grad_norm": 1.07491135597229,
      "learning_rate": 2.1344844419735757e-06,
      "loss": 0.0025,
      "step": 955
    },
    {
      "epoch": 0.8101694915254237,
      "grad_norm": 0.22395382821559906,
      "learning_rate": 2.116251362003887e-06,
      "loss": 0.0007,
      "step": 956
    },
    {
      "epoch": 0.8110169491525424,
      "grad_norm": 0.4018426239490509,
      "learning_rate": 2.098087271560687e-06,
      "loss": 0.0026,
      "step": 957
    },
    {
      "epoch": 0.811864406779661,
      "grad_norm": 1.074708104133606,
      "learning_rate": 2.079992329595263e-06,
      "loss": 0.0035,
      "step": 958
    },
    {
      "epoch": 0.8127118644067797,
      "grad_norm": 1.0309704542160034,
      "learning_rate": 2.0619666944537954e-06,
      "loss": 0.0041,
      "step": 959
    },
    {
      "epoch": 0.8135593220338984,
      "grad_norm": 2.1775588989257812,
      "learning_rate": 2.044010523875969e-06,
      "loss": 0.0157,
      "step": 960
    },
    {
      "epoch": 0.8135593220338984,
      "eval_accuracy": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 9.212108125211671e-05,
      "eval_precision": 1.0,
      "eval_recall": 1.0,
      "eval_runtime": 49.5926,
      "eval_samples_per_second": 5.888,
      "eval_steps_per_second": 0.202,
      "step": 960
    },
    {
      "epoch": 0.8144067796610169,
      "grad_norm": 0.222603902220726,
      "learning_rate": 2.0261239749935966e-06,
      "loss": 0.0009,
      "step": 961
    },
    {
      "epoch": 0.8152542372881356,
      "grad_norm": 0.21753355860710144,
      "learning_rate": 2.0083072043292406e-06,
      "loss": 0.0007,
      "step": 962
    },
    {
      "epoch": 0.8161016949152542,
      "grad_norm": 1.3669072389602661,
      "learning_rate": 1.9905603677948425e-06,
      "loss": 0.0065,
      "step": 963
    },
    {
      "epoch": 0.8169491525423729,
      "grad_norm": 2.4227099418640137,
      "learning_rate": 1.972883620690366e-06,
      "loss": 0.0253,
      "step": 964
    },
    {
      "epoch": 0.8177966101694916,
      "grad_norm": 0.42630961537361145,
      "learning_rate": 1.955277117702424e-06,
      "loss": 0.0013,
      "step": 965
    },
    {
      "epoch": 0.8186440677966101,
      "grad_norm": 1.9701416492462158,
      "learning_rate": 1.9377410129029407e-06,
      "loss": 0.011,
      "step": 966
    },
    {
      "epoch": 0.8194915254237288,
      "grad_norm": 2.1445109844207764,
      "learning_rate": 1.920275459747796e-06,
      "loss": 0.0132,
      "step": 967
    },
    {
      "epoch": 0.8203389830508474,
      "grad_norm": 1.7752200365066528,
      "learning_rate": 1.902880611075477e-06,
      "loss": 0.0069,
      "step": 968
    },
    {
      "epoch": 0.8211864406779661,
      "grad_norm": 0.9991908669471741,
      "learning_rate": 1.8855566191057538e-06,
      "loss": 0.0043,
      "step": 969
    },
    {
      "epoch": 0.8220338983050848,
      "grad_norm": 1.4875959157943726,
      "learning_rate": 1.868303635438332e-06,
      "loss": 0.0118,
      "step": 970
    },
    {
      "epoch": 0.8228813559322034,
      "grad_norm": 0.8871830701828003,
      "learning_rate": 1.8511218110515428e-06,
      "loss": 0.0042,
      "step": 971
    },
    {
      "epoch": 0.823728813559322,
      "grad_norm": 1.4304015636444092,
      "learning_rate": 1.8340112963009993e-06,
      "loss": 0.0085,
      "step": 972
    },
    {
      "epoch": 0.8245762711864407,
      "grad_norm": 1.7509040832519531,
      "learning_rate": 1.81697224091831e-06,
      "loss": 0.0181,
      "step": 973
    },
    {
      "epoch": 0.8254237288135593,
      "grad_norm": 0.6783941388130188,
      "learning_rate": 1.8000047940097453e-06,
      "loss": 0.0039,
      "step": 974
    },
    {
      "epoch": 0.826271186440678,
      "grad_norm": 0.9287757873535156,
      "learning_rate": 1.7831091040549397e-06,
      "loss": 0.0097,
      "step": 975
    },
    {
      "epoch": 0.8271186440677966,
      "grad_norm": 1.7914001941680908,
      "learning_rate": 1.7662853189055951e-06,
      "loss": 0.0152,
      "step": 976
    },
    {
      "epoch": 0.8279661016949152,
      "grad_norm": 0.4140421450138092,
      "learning_rate": 1.7495335857841855e-06,
      "loss": 0.0023,
      "step": 977
    },
    {
      "epoch": 0.8288135593220339,
      "grad_norm": 0.8546230792999268,
      "learning_rate": 1.7328540512826664e-06,
      "loss": 0.0077,
      "step": 978
    },
    {
      "epoch": 0.8296610169491525,
      "grad_norm": 1.1925534009933472,
      "learning_rate": 1.7162468613611937e-06,
      "loss": 0.0077,
      "step": 979
    },
    {
      "epoch": 0.8305084745762712,
      "grad_norm": 1.0941600799560547,
      "learning_rate": 1.699712161346846e-06,
      "loss": 0.0082,
      "step": 980
    },
    {
      "epoch": 0.8305084745762712,
      "eval_accuracy": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.00011068069579778239,
      "eval_precision": 1.0,
      "eval_recall": 1.0,
      "eval_runtime": 49.9161,
      "eval_samples_per_second": 5.85,
      "eval_steps_per_second": 0.2,
      "step": 980
    },
    {
      "epoch": 0.8313559322033899,
      "grad_norm": 3.0363481044769287,
      "learning_rate": 1.6832500959323605e-06,
      "loss": 0.0313,
      "step": 981
    },
    {
      "epoch": 0.8322033898305085,
      "grad_norm": 1.8849022388458252,
      "learning_rate": 1.6668608091748495e-06,
      "loss": 0.007,
      "step": 982
    },
    {
      "epoch": 0.8330508474576271,
      "grad_norm": 0.2518068253993988,
      "learning_rate": 1.6505444444945584e-06,
      "loss": 0.0009,
      "step": 983
    },
    {
      "epoch": 0.8338983050847457,
      "grad_norm": 0.548155665397644,
      "learning_rate": 1.6343011446735925e-06,
      "loss": 0.0024,
      "step": 984
    },
    {
      "epoch": 0.8347457627118644,
      "grad_norm": 1.4121159315109253,
      "learning_rate": 1.6181310518546856e-06,
      "loss": 0.0082,
      "step": 985
    },
    {
      "epoch": 0.8355932203389831,
      "grad_norm": 3.7406160831451416,
      "learning_rate": 1.6020343075399425e-06,
      "loss": 0.0086,
      "step": 986
    },
    {
      "epoch": 0.8364406779661017,
      "grad_norm": 0.4382129907608032,
      "learning_rate": 1.5860110525896143e-06,
      "loss": 0.0032,
      "step": 987
    },
    {
      "epoch": 0.8372881355932204,
      "grad_norm": 1.0554977655410767,
      "learning_rate": 1.5700614272208492e-06,
      "loss": 0.0042,
      "step": 988
    },
    {
      "epoch": 0.838135593220339,
      "grad_norm": 0.5351442694664001,
      "learning_rate": 1.5541855710064757e-06,
      "loss": 0.0021,
      "step": 989
    },
    {
      "epoch": 0.8389830508474576,
      "grad_norm": 1.2155871391296387,
      "learning_rate": 1.5383836228737815e-06,
      "loss": 0.0059,
      "step": 990
    },
    {
      "epoch": 0.8398305084745763,
      "grad_norm": 1.8322945833206177,
      "learning_rate": 1.522655721103291e-06,
      "loss": 0.0069,
      "step": 991
    },
    {
      "epoch": 0.8406779661016949,
      "grad_norm": 1.3039281368255615,
      "learning_rate": 1.5070020033275655e-06,
      "loss": 0.0102,
      "step": 992
    },
    {
      "epoch": 0.8415254237288136,
      "grad_norm": 1.6748837232589722,
      "learning_rate": 1.4914226065299886e-06,
      "loss": 0.0059,
      "step": 993
    },
    {
      "epoch": 0.8423728813559322,
      "grad_norm": 0.4845666289329529,
      "learning_rate": 1.475917667043575e-06,
      "loss": 0.0019,
      "step": 994
    },
    {
      "epoch": 0.8432203389830508,
      "grad_norm": 0.8964245915412903,
      "learning_rate": 1.4604873205497727e-06,
      "loss": 0.002,
      "step": 995
    },
    {
      "epoch": 0.8440677966101695,
      "grad_norm": 1.370054841041565,
      "learning_rate": 1.445131702077277e-06,
      "loss": 0.0086,
      "step": 996
    },
    {
      "epoch": 0.8449152542372881,
      "grad_norm": 2.0046818256378174,
      "learning_rate": 1.4298509460008491e-06,
      "loss": 0.0311,
      "step": 997
    },
    {
      "epoch": 0.8457627118644068,
      "grad_norm": 1.3406736850738525,
      "learning_rate": 1.4146451860401445e-06,
      "loss": 0.0075,
      "step": 998
    },
    {
      "epoch": 0.8466101694915255,
      "grad_norm": 0.8433687090873718,
      "learning_rate": 1.3995145552585321e-06,
      "loss": 0.0047,
      "step": 999
    },
    {
      "epoch": 0.847457627118644,
      "grad_norm": 2.1373324394226074,
      "learning_rate": 1.3844591860619382e-06,
      "loss": 0.0084,
      "step": 1000
    },
    {
      "epoch": 0.847457627118644,
      "eval_accuracy": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.0001222841819981113,
      "eval_precision": 1.0,
      "eval_recall": 1.0,
      "eval_runtime": 50.0901,
      "eval_samples_per_second": 5.83,
      "eval_steps_per_second": 0.2,
      "step": 1000
    },
    {
      "epoch": 0.8483050847457627,
      "grad_norm": 1.054631233215332,
      "learning_rate": 1.3694792101976938e-06,
      "loss": 0.0064,
      "step": 1001
    },
    {
      "epoch": 0.8491525423728814,
      "grad_norm": 3.1577975749969482,
      "learning_rate": 1.354574758753363e-06,
      "loss": 0.0276,
      "step": 1002
    },
    {
      "epoch": 0.85,
      "grad_norm": 2.423903703689575,
      "learning_rate": 1.339745962155613e-06,
      "loss": 0.0236,
      "step": 1003
    },
    {
      "epoch": 0.8508474576271187,
      "grad_norm": 0.5103369951248169,
      "learning_rate": 1.324992950169065e-06,
      "loss": 0.0016,
      "step": 1004
    },
    {
      "epoch": 0.8516949152542372,
      "grad_norm": 2.461594343185425,
      "learning_rate": 1.310315851895162e-06,
      "loss": 0.0258,
      "step": 1005
    },
    {
      "epoch": 0.8525423728813559,
      "grad_norm": 0.4233887195587158,
      "learning_rate": 1.2957147957710292e-06,
      "loss": 0.0016,
      "step": 1006
    },
    {
      "epoch": 0.8533898305084746,
      "grad_norm": 1.1271721124649048,
      "learning_rate": 1.28118990956837e-06,
      "loss": 0.0051,
      "step": 1007
    },
    {
      "epoch": 0.8542372881355932,
      "grad_norm": 1.2144718170166016,
      "learning_rate": 1.2667413203923283e-06,
      "loss": 0.0059,
      "step": 1008
    },
    {
      "epoch": 0.8550847457627119,
      "grad_norm": 0.09200064092874527,
      "learning_rate": 1.2523691546803872e-06,
      "loss": 0.0003,
      "step": 1009
    },
    {
      "epoch": 0.8559322033898306,
      "grad_norm": 0.7451255917549133,
      "learning_rate": 1.2380735382012576e-06,
      "loss": 0.0047,
      "step": 1010
    },
    {
      "epoch": 0.8567796610169491,
      "grad_norm": 0.9666259288787842,
      "learning_rate": 1.2238545960537795e-06,
      "loss": 0.0044,
      "step": 1011
    },
    {
      "epoch": 0.8576271186440678,
      "grad_norm": 0.9461873769760132,
      "learning_rate": 1.2097124526658277e-06,
      "loss": 0.0052,
      "step": 1012
    },
    {
      "epoch": 0.8584745762711864,
      "grad_norm": 1.253847360610962,
      "learning_rate": 1.1956472317932211e-06,
      "loss": 0.0117,
      "step": 1013
    },
    {
      "epoch": 0.8593220338983051,
      "grad_norm": 2.8636152744293213,
      "learning_rate": 1.1816590565186414e-06,
      "loss": 0.0236,
      "step": 1014
    },
    {
      "epoch": 0.8601694915254238,
      "grad_norm": 0.7781552076339722,
      "learning_rate": 1.1677480492505589e-06,
      "loss": 0.0068,
      "step": 1015
    },
    {
      "epoch": 0.8610169491525423,
      "grad_norm": 2.7591519355773926,
      "learning_rate": 1.1539143317221524e-06,
      "loss": 0.0293,
      "step": 1016
    },
    {
      "epoch": 0.861864406779661,
      "grad_norm": 1.2667608261108398,
      "learning_rate": 1.1401580249902566e-06,
      "loss": 0.0135,
      "step": 1017
    },
    {
      "epoch": 0.8627118644067797,
      "grad_norm": 1.1776992082595825,
      "learning_rate": 1.1264792494342858e-06,
      "loss": 0.0072,
      "step": 1018
    },
    {
      "epoch": 0.8635593220338983,
      "grad_norm": 1.9288878440856934,
      "learning_rate": 1.112878124755199e-06,
      "loss": 0.0101,
      "step": 1019
    },
    {
      "epoch": 0.864406779661017,
      "grad_norm": 1.5513525009155273,
      "learning_rate": 1.0993547699744366e-06,
      "loss": 0.0182,
      "step": 1020
    },
    {
      "epoch": 0.864406779661017,
      "eval_accuracy": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.00010546201519900933,
      "eval_precision": 1.0,
      "eval_recall": 1.0,
      "eval_runtime": 51.2385,
      "eval_samples_per_second": 5.699,
      "eval_steps_per_second": 0.195,
      "step": 1020
    },
    {
      "epoch": 0.8652542372881356,
      "grad_norm": 1.8383911848068237,
      "learning_rate": 1.0859093034328972e-06,
      "loss": 0.0058,
      "step": 1021
    },
    {
      "epoch": 0.8661016949152542,
      "grad_norm": 0.7148596048355103,
      "learning_rate": 1.0725418427898792e-06,
      "loss": 0.0033,
      "step": 1022
    },
    {
      "epoch": 0.8669491525423729,
      "grad_norm": 0.8727383017539978,
      "learning_rate": 1.0592525050220692e-06,
      "loss": 0.006,
      "step": 1023
    },
    {
      "epoch": 0.8677966101694915,
      "grad_norm": 1.3725224733352661,
      "learning_rate": 1.0460414064225099e-06,
      "loss": 0.007,
      "step": 1024
    },
    {
      "epoch": 0.8686440677966102,
      "grad_norm": 0.29742565751075745,
      "learning_rate": 1.0329086625995843e-06,
      "loss": 0.0015,
      "step": 1025
    },
    {
      "epoch": 0.8694915254237288,
      "grad_norm": 1.752211332321167,
      "learning_rate": 1.0198543884760049e-06,
      "loss": 0.0151,
      "step": 1026
    },
    {
      "epoch": 0.8703389830508474,
      "grad_norm": 0.8796065449714661,
      "learning_rate": 1.0068786982878087e-06,
      "loss": 0.0052,
      "step": 1027
    },
    {
      "epoch": 0.8711864406779661,
      "grad_norm": 1.1921021938323975,
      "learning_rate": 9.939817055833534e-07,
      "loss": 0.0079,
      "step": 1028
    },
    {
      "epoch": 0.8720338983050847,
      "grad_norm": 3.8833506107330322,
      "learning_rate": 9.811635232223283e-07,
      "loss": 0.0188,
      "step": 1029
    },
    {
      "epoch": 0.8728813559322034,
      "grad_norm": 0.4924924969673157,
      "learning_rate": 9.684242633747642e-07,
      "loss": 0.0018,
      "step": 1030
    },
    {
      "epoch": 0.8737288135593221,
      "grad_norm": 0.3568030893802643,
      "learning_rate": 9.55764037520055e-07,
      "loss": 0.0021,
      "step": 1031
    },
    {
      "epoch": 0.8745762711864407,
      "grad_norm": 1.1321516036987305,
      "learning_rate": 9.43182956445976e-07,
      "loss": 0.0187,
      "step": 1032
    },
    {
      "epoch": 0.8754237288135593,
      "grad_norm": 1.1234910488128662,
      "learning_rate": 9.306811302477214e-07,
      "loss": 0.0054,
      "step": 1033
    },
    {
      "epoch": 0.8762711864406779,
      "grad_norm": 1.4271575212478638,
      "learning_rate": 9.182586683269323e-07,
      "loss": 0.0063,
      "step": 1034
    },
    {
      "epoch": 0.8771186440677966,
      "grad_norm": 1.43450129032135,
      "learning_rate": 9.059156793907542e-07,
      "loss": 0.0189,
      "step": 1035
    },
    {
      "epoch": 0.8779661016949153,
      "grad_norm": 1.4197413921356201,
      "learning_rate": 8.936522714508678e-07,
      "loss": 0.0058,
      "step": 1036
    },
    {
      "epoch": 0.8788135593220339,
      "grad_norm": 0.9812485575675964,
      "learning_rate": 8.814685518225552e-07,
      "loss": 0.0074,
      "step": 1037
    },
    {
      "epoch": 0.8796610169491526,
      "grad_norm": 1.7358640432357788,
      "learning_rate": 8.693646271237577e-07,
      "loss": 0.0099,
      "step": 1038
    },
    {
      "epoch": 0.8805084745762712,
      "grad_norm": 0.25579047203063965,
      "learning_rate": 8.573406032741438e-07,
      "loss": 0.0014,
      "step": 1039
    },
    {
      "epoch": 0.8813559322033898,
      "grad_norm": 0.7132051587104797,
      "learning_rate": 8.453965854941748e-07,
      "loss": 0.0053,
      "step": 1040
    },
    {
      "epoch": 0.8813559322033898,
      "eval_accuracy": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.00010203008423559368,
      "eval_precision": 1.0,
      "eval_recall": 1.0,
      "eval_runtime": 51.4316,
      "eval_samples_per_second": 5.677,
      "eval_steps_per_second": 0.194,
      "step": 1040
    },
    {
      "epoch": 0.8822033898305085,
      "grad_norm": 0.3814912736415863,
      "learning_rate": 8.33532678304203e-07,
      "loss": 0.0022,
      "step": 1041
    },
    {
      "epoch": 0.8830508474576271,
      "grad_norm": 0.48492759466171265,
      "learning_rate": 8.217489855235338e-07,
      "loss": 0.0026,
      "step": 1042
    },
    {
      "epoch": 0.8838983050847458,
      "grad_norm": 1.3368293046951294,
      "learning_rate": 8.100456102695342e-07,
      "loss": 0.0099,
      "step": 1043
    },
    {
      "epoch": 0.8847457627118644,
      "grad_norm": 0.33328455686569214,
      "learning_rate": 7.98422654956722e-07,
      "loss": 0.0014,
      "step": 1044
    },
    {
      "epoch": 0.885593220338983,
      "grad_norm": 2.369331121444702,
      "learning_rate": 7.868802212958704e-07,
      "loss": 0.0122,
      "step": 1045
    },
    {
      "epoch": 0.8864406779661017,
      "grad_norm": 1.2063324451446533,
      "learning_rate": 7.754184102931228e-07,
      "loss": 0.0174,
      "step": 1046
    },
    {
      "epoch": 0.8872881355932203,
      "grad_norm": 1.7367677688598633,
      "learning_rate": 7.640373222491038e-07,
      "loss": 0.0105,
      "step": 1047
    },
    {
      "epoch": 0.888135593220339,
      "grad_norm": 1.0690417289733887,
      "learning_rate": 7.527370567580416e-07,
      "loss": 0.0054,
      "step": 1048
    },
    {
      "epoch": 0.8889830508474577,
      "grad_norm": 2.0434165000915527,
      "learning_rate": 7.415177127069029e-07,
      "loss": 0.0161,
      "step": 1049
    },
    {
      "epoch": 0.8898305084745762,
      "grad_norm": 2.049274206161499,
      "learning_rate": 7.303793882745181e-07,
      "loss": 0.0097,
      "step": 1050
    },
    {
      "epoch": 0.8906779661016949,
      "grad_norm": 0.8351269960403442,
      "learning_rate": 7.193221809307304e-07,
      "loss": 0.0063,
      "step": 1051
    },
    {
      "epoch": 0.8915254237288136,
      "grad_norm": 0.6742042303085327,
      "learning_rate": 7.083461874355335e-07,
      "loss": 0.0047,
      "step": 1052
    },
    {
      "epoch": 0.8923728813559322,
      "grad_norm": 2.22886061668396,
      "learning_rate": 6.974515038382379e-07,
      "loss": 0.0125,
      "step": 1053
    },
    {
      "epoch": 0.8932203389830509,
      "grad_norm": 2.4455456733703613,
      "learning_rate": 6.866382254766158e-07,
      "loss": 0.0186,
      "step": 1054
    },
    {
      "epoch": 0.8940677966101694,
      "grad_norm": 2.354172945022583,
      "learning_rate": 6.759064469760823e-07,
      "loss": 0.0088,
      "step": 1055
    },
    {
      "epoch": 0.8949152542372881,
      "grad_norm": 0.5831468105316162,
      "learning_rate": 6.652562622488535e-07,
      "loss": 0.0033,
      "step": 1056
    },
    {
      "epoch": 0.8957627118644068,
      "grad_norm": 1.065117359161377,
      "learning_rate": 6.546877644931315e-07,
      "loss": 0.0129,
      "step": 1057
    },
    {
      "epoch": 0.8966101694915254,
      "grad_norm": 1.6987978219985962,
      "learning_rate": 6.442010461922888e-07,
      "loss": 0.0125,
      "step": 1058
    },
    {
      "epoch": 0.8974576271186441,
      "grad_norm": 0.6148873567581177,
      "learning_rate": 6.33796199114055e-07,
      "loss": 0.0027,
      "step": 1059
    },
    {
      "epoch": 0.8983050847457628,
      "grad_norm": 1.205604076385498,
      "learning_rate": 6.234733143097215e-07,
      "loss": 0.0087,
      "step": 1060
    },
    {
      "epoch": 0.8983050847457628,
      "eval_accuracy": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 9.550240793032572e-05,
      "eval_precision": 1.0,
      "eval_recall": 1.0,
      "eval_runtime": 51.1494,
      "eval_samples_per_second": 5.709,
      "eval_steps_per_second": 0.196,
      "step": 1060
    },
    {
      "epoch": 0.8991525423728813,
      "grad_norm": 3.041253089904785,
      "learning_rate": 6.132324821133362e-07,
      "loss": 0.0132,
      "step": 1061
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.2654479146003723,
      "learning_rate": 6.030737921409169e-07,
      "loss": 0.001,
      "step": 1062
    },
    {
      "epoch": 0.9008474576271186,
      "grad_norm": 0.14473998546600342,
      "learning_rate": 5.929973332896677e-07,
      "loss": 0.0009,
      "step": 1063
    },
    {
      "epoch": 0.9016949152542373,
      "grad_norm": 0.26278120279312134,
      "learning_rate": 5.830031937372005e-07,
      "loss": 0.001,
      "step": 1064
    },
    {
      "epoch": 0.902542372881356,
      "grad_norm": 1.2509464025497437,
      "learning_rate": 5.730914609407634e-07,
      "loss": 0.006,
      "step": 1065
    },
    {
      "epoch": 0.9033898305084745,
      "grad_norm": 0.7587932348251343,
      "learning_rate": 5.632622216364736e-07,
      "loss": 0.0052,
      "step": 1066
    },
    {
      "epoch": 0.9042372881355932,
      "grad_norm": 0.35142210125923157,
      "learning_rate": 5.535155618385612e-07,
      "loss": 0.0022,
      "step": 1067
    },
    {
      "epoch": 0.9050847457627119,
      "grad_norm": 1.582571268081665,
      "learning_rate": 5.438515668386124e-07,
      "loss": 0.0121,
      "step": 1068
    },
    {
      "epoch": 0.9059322033898305,
      "grad_norm": 0.8583706617355347,
      "learning_rate": 5.342703212048306e-07,
      "loss": 0.0033,
      "step": 1069
    },
    {
      "epoch": 0.9067796610169492,
      "grad_norm": 1.316669225692749,
      "learning_rate": 5.247719087812897e-07,
      "loss": 0.0052,
      "step": 1070
    },
    {
      "epoch": 0.9076271186440678,
      "grad_norm": 1.5841196775436401,
      "learning_rate": 5.153564126872002e-07,
      "loss": 0.0087,
      "step": 1071
    },
    {
      "epoch": 0.9084745762711864,
      "grad_norm": 0.39058223366737366,
      "learning_rate": 5.060239153161872e-07,
      "loss": 0.0013,
      "step": 1072
    },
    {
      "epoch": 0.9093220338983051,
      "grad_norm": 1.9693634510040283,
      "learning_rate": 4.967744983355638e-07,
      "loss": 0.0137,
      "step": 1073
    },
    {
      "epoch": 0.9101694915254237,
      "grad_norm": 0.7177203297615051,
      "learning_rate": 4.876082426856177e-07,
      "loss": 0.0027,
      "step": 1074
    },
    {
      "epoch": 0.9110169491525424,
      "grad_norm": 1.0042608976364136,
      "learning_rate": 4.785252285789077e-07,
      "loss": 0.021,
      "step": 1075
    },
    {
      "epoch": 0.911864406779661,
      "grad_norm": 1.2595585584640503,
      "learning_rate": 4.695255354995576e-07,
      "loss": 0.0072,
      "step": 1076
    },
    {
      "epoch": 0.9127118644067796,
      "grad_norm": 0.42359045147895813,
      "learning_rate": 4.6060924220255654e-07,
      "loss": 0.0029,
      "step": 1077
    },
    {
      "epoch": 0.9135593220338983,
      "grad_norm": 1.1068620681762695,
      "learning_rate": 4.5177642671308087e-07,
      "loss": 0.0053,
      "step": 1078
    },
    {
      "epoch": 0.9144067796610169,
      "grad_norm": 0.701837956905365,
      "learning_rate": 4.430271663258001e-07,
      "loss": 0.0047,
      "step": 1079
    },
    {
      "epoch": 0.9152542372881356,
      "grad_norm": 0.43353769183158875,
      "learning_rate": 4.343615376042065e-07,
      "loss": 0.0017,
      "step": 1080
    },
    {
      "epoch": 0.9152542372881356,
      "eval_accuracy": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 9.550563845550641e-05,
      "eval_precision": 1.0,
      "eval_recall": 1.0,
      "eval_runtime": 51.4172,
      "eval_samples_per_second": 5.679,
      "eval_steps_per_second": 0.194,
      "step": 1080
    },
    {
      "epoch": 0.9161016949152543,
      "grad_norm": 1.3469489812850952,
      "learning_rate": 4.2577961637994544e-07,
      "loss": 0.0116,
      "step": 1081
    },
    {
      "epoch": 0.9169491525423729,
      "grad_norm": 1.7352731227874756,
      "learning_rate": 4.172814777521483e-07,
      "loss": 0.012,
      "step": 1082
    },
    {
      "epoch": 0.9177966101694915,
      "grad_norm": 1.6800487041473389,
      "learning_rate": 4.088671960867785e-07,
      "loss": 0.0248,
      "step": 1083
    },
    {
      "epoch": 0.9186440677966101,
      "grad_norm": 1.4252413511276245,
      "learning_rate": 4.0053684501598076e-07,
      "loss": 0.0083,
      "step": 1084
    },
    {
      "epoch": 0.9194915254237288,
      "grad_norm": 2.737250804901123,
      "learning_rate": 3.9229049743743087e-07,
      "loss": 0.0172,
      "step": 1085
    },
    {
      "epoch": 0.9203389830508475,
      "grad_norm": 1.0084242820739746,
      "learning_rate": 3.8412822551370797e-07,
      "loss": 0.0093,
      "step": 1086
    },
    {
      "epoch": 0.9211864406779661,
      "grad_norm": 1.396519422531128,
      "learning_rate": 3.7605010067165216e-07,
      "loss": 0.016,
      "step": 1087
    },
    {
      "epoch": 0.9220338983050848,
      "grad_norm": 3.1301279067993164,
      "learning_rate": 3.68056193601749e-07,
      "loss": 0.0136,
      "step": 1088
    },
    {
      "epoch": 0.9228813559322034,
      "grad_norm": 1.233527421951294,
      "learning_rate": 3.601465742575061e-07,
      "loss": 0.0053,
      "step": 1089
    },
    {
      "epoch": 0.923728813559322,
      "grad_norm": 1.5494545698165894,
      "learning_rate": 3.5232131185484075e-07,
      "loss": 0.0119,
      "step": 1090
    },
    {
      "epoch": 0.9245762711864407,
      "grad_norm": 0.7201801538467407,
      "learning_rate": 3.445804748714732e-07,
      "loss": 0.0071,
      "step": 1091
    },
    {
      "epoch": 0.9254237288135593,
      "grad_norm": 2.4075450897216797,
      "learning_rate": 3.3692413104633226e-07,
      "loss": 0.0131,
      "step": 1092
    },
    {
      "epoch": 0.926271186440678,
      "grad_norm": 0.0901576578617096,
      "learning_rate": 3.2935234737895837e-07,
      "loss": 0.0005,
      "step": 1093
    },
    {
      "epoch": 0.9271186440677966,
      "grad_norm": 0.39205268025398254,
      "learning_rate": 3.2186519012891823e-07,
      "loss": 0.0027,
      "step": 1094
    },
    {
      "epoch": 0.9279661016949152,
      "grad_norm": 1.3817288875579834,
      "learning_rate": 3.1446272481522544e-07,
      "loss": 0.0158,
      "step": 1095
    },
    {
      "epoch": 0.9288135593220339,
      "grad_norm": 2.032911777496338,
      "learning_rate": 3.071450162157663e-07,
      "loss": 0.0121,
      "step": 1096
    },
    {
      "epoch": 0.9296610169491526,
      "grad_norm": 1.8076006174087524,
      "learning_rate": 2.999121283667339e-07,
      "loss": 0.0057,
      "step": 1097
    },
    {
      "epoch": 0.9305084745762712,
      "grad_norm": 1.118698000907898,
      "learning_rate": 2.9276412456206826e-07,
      "loss": 0.0037,
      "step": 1098
    },
    {
      "epoch": 0.9313559322033899,
      "grad_norm": 0.7791540026664734,
      "learning_rate": 2.857010673529015e-07,
      "loss": 0.0063,
      "step": 1099
    },
    {
      "epoch": 0.9322033898305084,
      "grad_norm": 1.4591788053512573,
      "learning_rate": 2.78723018547008e-07,
      "loss": 0.0058,
      "step": 1100
    },
    {
      "epoch": 0.9322033898305084,
      "eval_accuracy": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.00010077878687297925,
      "eval_precision": 1.0,
      "eval_recall": 1.0,
      "eval_runtime": 51.6426,
      "eval_samples_per_second": 5.654,
      "eval_steps_per_second": 0.194,
      "step": 1100
    },
    {
      "epoch": 0.9330508474576271,
      "grad_norm": 2.0700523853302,
      "learning_rate": 2.7183003920826846e-07,
      "loss": 0.015,
      "step": 1101
    },
    {
      "epoch": 0.9338983050847458,
      "grad_norm": 0.7995718717575073,
      "learning_rate": 2.6502218965613335e-07,
      "loss": 0.0059,
      "step": 1102
    },
    {
      "epoch": 0.9347457627118644,
      "grad_norm": 1.953245759010315,
      "learning_rate": 2.5829952946509585e-07,
      "loss": 0.0084,
      "step": 1103
    },
    {
      "epoch": 0.9355932203389831,
      "grad_norm": 1.5361946821212769,
      "learning_rate": 2.5166211746416534e-07,
      "loss": 0.0078,
      "step": 1104
    },
    {
      "epoch": 0.9364406779661016,
      "grad_norm": 1.721569299697876,
      "learning_rate": 2.451100117363603e-07,
      "loss": 0.0134,
      "step": 1105
    },
    {
      "epoch": 0.9372881355932203,
      "grad_norm": 0.24595603346824646,
      "learning_rate": 2.386432696181973e-07,
      "loss": 0.0011,
      "step": 1106
    },
    {
      "epoch": 0.938135593220339,
      "grad_norm": 0.49296998977661133,
      "learning_rate": 2.3226194769918497e-07,
      "loss": 0.0035,
      "step": 1107
    },
    {
      "epoch": 0.9389830508474576,
      "grad_norm": 0.35648539662361145,
      "learning_rate": 2.2596610182133328e-07,
      "loss": 0.0014,
      "step": 1108
    },
    {
      "epoch": 0.9398305084745763,
      "grad_norm": 0.42918694019317627,
      "learning_rate": 2.1975578707866818e-07,
      "loss": 0.0037,
      "step": 1109
    },
    {
      "epoch": 0.940677966101695,
      "grad_norm": 0.3251606822013855,
      "learning_rate": 2.1363105781673888e-07,
      "loss": 0.0015,
      "step": 1110
    },
    {
      "epoch": 0.9415254237288135,
      "grad_norm": 1.1148656606674194,
      "learning_rate": 2.0759196763215362e-07,
      "loss": 0.0024,
      "step": 1111
    },
    {
      "epoch": 0.9423728813559322,
      "grad_norm": 1.0703065395355225,
      "learning_rate": 2.0163856937210236e-07,
      "loss": 0.0057,
      "step": 1112
    },
    {
      "epoch": 0.9432203389830508,
      "grad_norm": 0.5219106078147888,
      "learning_rate": 1.9577091513389933e-07,
      "loss": 0.0019,
      "step": 1113
    },
    {
      "epoch": 0.9440677966101695,
      "grad_norm": 1.2193870544433594,
      "learning_rate": 1.8998905626452568e-07,
      "loss": 0.0039,
      "step": 1114
    },
    {
      "epoch": 0.9449152542372882,
      "grad_norm": 0.7670567035675049,
      "learning_rate": 1.842930433601775e-07,
      "loss": 0.0023,
      "step": 1115
    },
    {
      "epoch": 0.9457627118644067,
      "grad_norm": 1.6820135116577148,
      "learning_rate": 1.7868292626582851e-07,
      "loss": 0.0066,
      "step": 1116
    },
    {
      "epoch": 0.9466101694915254,
      "grad_norm": 0.2756711542606354,
      "learning_rate": 1.731587540747903e-07,
      "loss": 0.0018,
      "step": 1117
    },
    {
      "epoch": 0.9474576271186441,
      "grad_norm": 0.09309152513742447,
      "learning_rate": 1.6772057512828178e-07,
      "loss": 0.0005,
      "step": 1118
    },
    {
      "epoch": 0.9483050847457627,
      "grad_norm": 0.9462043642997742,
      "learning_rate": 1.6236843701500692e-07,
      "loss": 0.0045,
      "step": 1119
    },
    {
      "epoch": 0.9491525423728814,
      "grad_norm": 0.3377615213394165,
      "learning_rate": 1.5710238657074218e-07,
      "loss": 0.0015,
      "step": 1120
    },
    {
      "epoch": 0.9491525423728814,
      "eval_accuracy": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.00010440533515065908,
      "eval_precision": 1.0,
      "eval_recall": 1.0,
      "eval_runtime": 50.0065,
      "eval_samples_per_second": 5.839,
      "eval_steps_per_second": 0.2,
      "step": 1120
    },
    {
      "epoch": 0.95,
      "grad_norm": 1.3986833095550537,
      "learning_rate": 1.519224698779198e-07,
      "loss": 0.0143,
      "step": 1121
    },
    {
      "epoch": 0.9508474576271186,
      "grad_norm": 2.198768377304077,
      "learning_rate": 1.4682873226523064e-07,
      "loss": 0.0134,
      "step": 1122
    },
    {
      "epoch": 0.9516949152542373,
      "grad_norm": 3.4906070232391357,
      "learning_rate": 1.418212183072254e-07,
      "loss": 0.023,
      "step": 1123
    },
    {
      "epoch": 0.9525423728813559,
      "grad_norm": 2.3907110691070557,
      "learning_rate": 1.3689997182392278e-07,
      "loss": 0.0341,
      "step": 1124
    },
    {
      "epoch": 0.9533898305084746,
      "grad_norm": 1.1482832431793213,
      "learning_rate": 1.3206503588042762e-07,
      "loss": 0.0046,
      "step": 1125
    },
    {
      "epoch": 0.9542372881355933,
      "grad_norm": 0.41303661465644836,
      "learning_rate": 1.2731645278655448e-07,
      "loss": 0.0015,
      "step": 1126
    },
    {
      "epoch": 0.9550847457627119,
      "grad_norm": 2.1115567684173584,
      "learning_rate": 1.2265426409645676e-07,
      "loss": 0.0193,
      "step": 1127
    },
    {
      "epoch": 0.9559322033898305,
      "grad_norm": 0.9733043909072876,
      "learning_rate": 1.180785106082627e-07,
      "loss": 0.0063,
      "step": 1128
    },
    {
      "epoch": 0.9567796610169491,
      "grad_norm": 1.6615018844604492,
      "learning_rate": 1.1358923236371888e-07,
      "loss": 0.0143,
      "step": 1129
    },
    {
      "epoch": 0.9576271186440678,
      "grad_norm": 2.9333720207214355,
      "learning_rate": 1.0918646864784166e-07,
      "loss": 0.0204,
      "step": 1130
    },
    {
      "epoch": 0.9584745762711865,
      "grad_norm": 0.4009217619895935,
      "learning_rate": 1.0487025798856632e-07,
      "loss": 0.0019,
      "step": 1131
    },
    {
      "epoch": 0.9593220338983051,
      "grad_norm": 0.5355218052864075,
      "learning_rate": 1.0064063815642178e-07,
      "loss": 0.0024,
      "step": 1132
    },
    {
      "epoch": 0.9601694915254237,
      "grad_norm": 1.6377936601638794,
      "learning_rate": 9.649764616418866e-08,
      "loss": 0.018,
      "step": 1133
    },
    {
      "epoch": 0.9610169491525423,
      "grad_norm": 1.1204107999801636,
      "learning_rate": 9.244131826658065e-08,
      "loss": 0.0128,
      "step": 1134
    },
    {
      "epoch": 0.961864406779661,
      "grad_norm": 1.4632524251937866,
      "learning_rate": 8.847168995992916e-08,
      "loss": 0.0098,
      "step": 1135
    },
    {
      "epoch": 0.9627118644067797,
      "grad_norm": 0.7185283303260803,
      "learning_rate": 8.458879598186586e-08,
      "loss": 0.0023,
      "step": 1136
    },
    {
      "epoch": 0.9635593220338983,
      "grad_norm": 2.070397138595581,
      "learning_rate": 8.079267031102844e-08,
      "loss": 0.014,
      "step": 1137
    },
    {
      "epoch": 0.964406779661017,
      "grad_norm": 2.4648094177246094,
      "learning_rate": 7.708334616675417e-08,
      "loss": 0.0103,
      "step": 1138
    },
    {
      "epoch": 0.9652542372881356,
      "grad_norm": 1.3357059955596924,
      "learning_rate": 7.34608560087946e-08,
      "loss": 0.0114,
      "step": 1139
    },
    {
      "epoch": 0.9661016949152542,
      "grad_norm": 0.8426046371459961,
      "learning_rate": 6.99252315370269e-08,
      "loss": 0.0059,
      "step": 1140
    },
    {
      "epoch": 0.9661016949152542,
      "eval_accuracy": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.00011169948993483558,
      "eval_precision": 1.0,
      "eval_recall": 1.0,
      "eval_runtime": 50.2826,
      "eval_samples_per_second": 5.807,
      "eval_steps_per_second": 0.199,
      "step": 1140
    },
    {
      "epoch": 0.9669491525423729,
      "grad_norm": 0.7774562835693359,
      "learning_rate": 6.647650369118408e-08,
      "loss": 0.0078,
      "step": 1141
    },
    {
      "epoch": 0.9677966101694915,
      "grad_norm": 2.7641003131866455,
      "learning_rate": 6.311470265057518e-08,
      "loss": 0.0138,
      "step": 1142
    },
    {
      "epoch": 0.9686440677966102,
      "grad_norm": 2.618208885192871,
      "learning_rate": 5.983985783382773e-08,
      "loss": 0.0202,
      "step": 1143
    },
    {
      "epoch": 0.9694915254237289,
      "grad_norm": 1.5658472776412964,
      "learning_rate": 5.665199789862907e-08,
      "loss": 0.0201,
      "step": 1144
    },
    {
      "epoch": 0.9703389830508474,
      "grad_norm": 0.43462297320365906,
      "learning_rate": 5.3551150741472104e-08,
      "loss": 0.002,
      "step": 1145
    },
    {
      "epoch": 0.9711864406779661,
      "grad_norm": 1.4689350128173828,
      "learning_rate": 5.0537343497414346e-08,
      "loss": 0.009,
      "step": 1146
    },
    {
      "epoch": 0.9720338983050848,
      "grad_norm": 2.49544620513916,
      "learning_rate": 4.761060253984151e-08,
      "loss": 0.0279,
      "step": 1147
    },
    {
      "epoch": 0.9728813559322034,
      "grad_norm": 1.6884862184524536,
      "learning_rate": 4.47709534802343e-08,
      "loss": 0.0078,
      "step": 1148
    },
    {
      "epoch": 0.9737288135593221,
      "grad_norm": 0.37377646565437317,
      "learning_rate": 4.201842116794308e-08,
      "loss": 0.0023,
      "step": 1149
    },
    {
      "epoch": 0.9745762711864406,
      "grad_norm": 0.7765163779258728,
      "learning_rate": 3.9353029689974676e-08,
      "loss": 0.0038,
      "step": 1150
    },
    {
      "epoch": 0.9754237288135593,
      "grad_norm": 0.513041615486145,
      "learning_rate": 3.677480237077813e-08,
      "loss": 0.0016,
      "step": 1151
    },
    {
      "epoch": 0.976271186440678,
      "grad_norm": 0.7876710891723633,
      "learning_rate": 3.4283761772042623e-08,
      "loss": 0.0056,
      "step": 1152
    },
    {
      "epoch": 0.9771186440677966,
      "grad_norm": 0.6897133588790894,
      "learning_rate": 3.187992969249876e-08,
      "loss": 0.0034,
      "step": 1153
    },
    {
      "epoch": 0.9779661016949153,
      "grad_norm": 1.7506352663040161,
      "learning_rate": 2.9563327167727585e-08,
      "loss": 0.0099,
      "step": 1154
    },
    {
      "epoch": 0.9788135593220338,
      "grad_norm": 2.4349284172058105,
      "learning_rate": 2.733397446997632e-08,
      "loss": 0.0097,
      "step": 1155
    },
    {
      "epoch": 0.9796610169491525,
      "grad_norm": 1.168368935585022,
      "learning_rate": 2.5191891107985143e-08,
      "loss": 0.0082,
      "step": 1156
    },
    {
      "epoch": 0.9805084745762712,
      "grad_norm": 1.3423504829406738,
      "learning_rate": 2.3137095826809564e-08,
      "loss": 0.0091,
      "step": 1157
    },
    {
      "epoch": 0.9813559322033898,
      "grad_norm": 0.42089366912841797,
      "learning_rate": 2.1169606607662764e-08,
      "loss": 0.0024,
      "step": 1158
    },
    {
      "epoch": 0.9822033898305085,
      "grad_norm": 1.1868031024932861,
      "learning_rate": 1.92894406677524e-08,
      "loss": 0.0064,
      "step": 1159
    },
    {
      "epoch": 0.9830508474576272,
      "grad_norm": 1.4910340309143066,
      "learning_rate": 1.7496614460135174e-08,
      "loss": 0.0069,
      "step": 1160
    },
    {
      "epoch": 0.9830508474576272,
      "eval_accuracy": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.0001118536019930616,
      "eval_precision": 1.0,
      "eval_recall": 1.0,
      "eval_runtime": 50.1342,
      "eval_samples_per_second": 5.824,
      "eval_steps_per_second": 0.199,
      "step": 1160
    },
    {
      "epoch": 0.9838983050847457,
      "grad_norm": 1.986571192741394,
      "learning_rate": 1.5791143673570263e-08,
      "loss": 0.0193,
      "step": 1161
    },
    {
      "epoch": 0.9847457627118644,
      "grad_norm": 2.655247688293457,
      "learning_rate": 1.4173043232380557e-08,
      "loss": 0.0257,
      "step": 1162
    },
    {
      "epoch": 0.985593220338983,
      "grad_norm": 1.0046510696411133,
      "learning_rate": 1.2642327296327194e-08,
      "loss": 0.003,
      "step": 1163
    },
    {
      "epoch": 0.9864406779661017,
      "grad_norm": 1.124706745147705,
      "learning_rate": 1.1199009260479676e-08,
      "loss": 0.0157,
      "step": 1164
    },
    {
      "epoch": 0.9872881355932204,
      "grad_norm": 1.0634783506393433,
      "learning_rate": 9.843101755101503e-09,
      "loss": 0.0046,
      "step": 1165
    },
    {
      "epoch": 0.988135593220339,
      "grad_norm": 1.6343358755111694,
      "learning_rate": 8.574616645541377e-09,
      "loss": 0.0113,
      "step": 1166
    },
    {
      "epoch": 0.9889830508474576,
      "grad_norm": 0.2569604814052582,
      "learning_rate": 7.3935650321255156e-09,
      "loss": 0.0015,
      "step": 1167
    },
    {
      "epoch": 0.9898305084745763,
      "grad_norm": 0.6046754717826843,
      "learning_rate": 6.299957250064381e-09,
      "loss": 0.0024,
      "step": 1168
    },
    {
      "epoch": 0.9906779661016949,
      "grad_norm": 0.760793149471283,
      "learning_rate": 5.293802869357212e-09,
      "loss": 0.0026,
      "step": 1169
    },
    {
      "epoch": 0.9915254237288136,
      "grad_norm": 1.5352802276611328,
      "learning_rate": 4.375110694713192e-09,
      "loss": 0.0089,
      "step": 1170
    },
    {
      "epoch": 0.9923728813559322,
      "grad_norm": 1.066978931427002,
      "learning_rate": 3.5438887654737355e-09,
      "loss": 0.0054,
      "step": 1171
    },
    {
      "epoch": 0.9932203389830508,
      "grad_norm": 0.2690616846084595,
      "learning_rate": 2.800144355540324e-09,
      "loss": 0.0012,
      "step": 1172
    },
    {
      "epoch": 0.9940677966101695,
      "grad_norm": 0.24727602303028107,
      "learning_rate": 2.1438839733101125e-09,
      "loss": 0.0012,
      "step": 1173
    },
    {
      "epoch": 0.9949152542372881,
      "grad_norm": 0.8187950849533081,
      "learning_rate": 1.5751133616215276e-09,
      "loss": 0.0028,
      "step": 1174
    },
    {
      "epoch": 0.9957627118644068,
      "grad_norm": 5.176650047302246,
      "learning_rate": 1.0938374977020882e-09,
      "loss": 0.0332,
      "step": 1175
    },
    {
      "epoch": 0.9966101694915255,
      "grad_norm": 1.1245023012161255,
      "learning_rate": 7.000605931273274e-10,
      "loss": 0.0031,
      "step": 1176
    },
    {
      "epoch": 0.997457627118644,
      "grad_norm": 0.7511110901832581,
      "learning_rate": 3.9378609377971335e-10,
      "loss": 0.0033,
      "step": 1177
    },
    {
      "epoch": 0.9983050847457627,
      "grad_norm": 0.6101163029670715,
      "learning_rate": 1.7501667982311454e-10,
      "loss": 0.0029,
      "step": 1178
    },
    {
      "epoch": 0.9991525423728813,
      "grad_norm": 1.6641690731048584,
      "learning_rate": 4.375426567726493e-11,
      "loss": 0.0074,
      "step": 1179
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.8142516016960144,
      "learning_rate": 0.0,
      "loss": 0.0058,
      "step": 1180
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.0001048951453412883,
      "eval_precision": 1.0,
      "eval_recall": 1.0,
      "eval_runtime": 49.7666,
      "eval_samples_per_second": 5.867,
      "eval_steps_per_second": 0.201,
      "step": 1180
    }
  ],
  "logging_steps": 1,
  "max_steps": 1180,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.6331250614114714e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}