yi-34b-rm-900 / trainer_state.json
banghua's picture
Upload folder using huggingface_hub
96e0485 verified
{
"best_metric": 1.0441503524780273,
"best_model_checkpoint": "rm-ckpt-reward-p100-s0/checkpoint-400",
"epoch": 0.9369144284821986,
"eval_steps": 50,
"global_step": 900,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 0.0,
"loss": 1.447,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 7.525749891599529e-06,
"loss": 1.4166,
"step": 2
},
{
"epoch": 0.0,
"learning_rate": 1.192803136799156e-05,
"loss": 1.417,
"step": 3
},
{
"epoch": 0.0,
"learning_rate": 1.5051499783199057e-05,
"loss": 1.3947,
"step": 4
},
{
"epoch": 0.0,
"learning_rate": 1.7474250108400467e-05,
"loss": 1.3739,
"step": 5
},
{
"epoch": 0.01,
"learning_rate": 1.945378125959109e-05,
"loss": 1.3352,
"step": 6
},
{
"epoch": 0.01,
"learning_rate": 2.1127451000356418e-05,
"loss": 1.3181,
"step": 7
},
{
"epoch": 0.01,
"learning_rate": 2.2577249674798584e-05,
"loss": 1.3712,
"step": 8
},
{
"epoch": 0.01,
"learning_rate": 2.385606273598312e-05,
"loss": 1.3858,
"step": 9
},
{
"epoch": 0.01,
"learning_rate": 2.4999999999999998e-05,
"loss": 1.4424,
"step": 10
},
{
"epoch": 0.01,
"learning_rate": 2.6034817128955623e-05,
"loss": 1.3381,
"step": 11
},
{
"epoch": 0.01,
"learning_rate": 2.6979531151190617e-05,
"loss": 1.2937,
"step": 12
},
{
"epoch": 0.01,
"learning_rate": 2.7848583807670913e-05,
"loss": 1.3021,
"step": 13
},
{
"epoch": 0.01,
"learning_rate": 2.8653200891955945e-05,
"loss": 1.274,
"step": 14
},
{
"epoch": 0.01,
"learning_rate": 2.940228147639203e-05,
"loss": 1.2896,
"step": 15
},
{
"epoch": 0.01,
"learning_rate": 3.0102999566398115e-05,
"loss": 1.19,
"step": 16
},
{
"epoch": 0.02,
"learning_rate": 3.076122303445685e-05,
"loss": 1.1889,
"step": 17
},
{
"epoch": 0.02,
"learning_rate": 3.1381812627582646e-05,
"loss": 1.2028,
"step": 18
},
{
"epoch": 0.02,
"learning_rate": 3.1968840023820715e-05,
"loss": 1.2259,
"step": 19
},
{
"epoch": 0.02,
"learning_rate": 3.2525749891599525e-05,
"loss": 1.1971,
"step": 20
},
{
"epoch": 0.02,
"learning_rate": 3.305548236834798e-05,
"loss": 1.1972,
"step": 21
},
{
"epoch": 0.02,
"learning_rate": 3.3560567020555153e-05,
"loss": 1.2193,
"step": 22
},
{
"epoch": 0.02,
"learning_rate": 3.404319590043982e-05,
"loss": 1.1354,
"step": 23
},
{
"epoch": 0.02,
"learning_rate": 3.450528104279015e-05,
"loss": 1.1434,
"step": 24
},
{
"epoch": 0.02,
"learning_rate": 3.4948500216800935e-05,
"loss": 1.1237,
"step": 25
},
{
"epoch": 0.02,
"learning_rate": 3.537433369927044e-05,
"loss": 1.1227,
"step": 26
},
{
"epoch": 0.02,
"learning_rate": 3.578409410397468e-05,
"loss": 1.1554,
"step": 27
},
{
"epoch": 0.03,
"learning_rate": 3.6178950783555475e-05,
"loss": 1.131,
"step": 28
},
{
"epoch": 0.03,
"learning_rate": 3.65599499474739e-05,
"loss": 1.2016,
"step": 29
},
{
"epoch": 0.03,
"learning_rate": 3.6928031367991554e-05,
"loss": 1.0968,
"step": 30
},
{
"epoch": 0.03,
"learning_rate": 3.728404234585681e-05,
"loss": 1.0713,
"step": 31
},
{
"epoch": 0.03,
"learning_rate": 3.762874945799765e-05,
"loss": 1.1537,
"step": 32
},
{
"epoch": 0.03,
"learning_rate": 3.796284849694718e-05,
"loss": 1.0856,
"step": 33
},
{
"epoch": 0.03,
"learning_rate": 3.8286972926056376e-05,
"loss": 1.08,
"step": 34
},
{
"epoch": 0.03,
"learning_rate": 3.8601701108756885e-05,
"loss": 1.067,
"step": 35
},
{
"epoch": 0.03,
"learning_rate": 3.890756251918218e-05,
"loss": 1.1298,
"step": 36
},
{
"epoch": 0.03,
"learning_rate": 3.920504310167487e-05,
"loss": 1.0986,
"step": 37
},
{
"epoch": 0.03,
"learning_rate": 3.949458991542025e-05,
"loss": 1.0649,
"step": 38
},
{
"epoch": 0.04,
"learning_rate": 3.977661517566247e-05,
"loss": 1.0582,
"step": 39
},
{
"epoch": 0.04,
"learning_rate": 4.005149978319905e-05,
"loss": 1.1037,
"step": 40
},
{
"epoch": 0.04,
"learning_rate": 4.031959641799338e-05,
"loss": 1.052,
"step": 41
},
{
"epoch": 0.04,
"learning_rate": 4.058123225994751e-05,
"loss": 1.1048,
"step": 42
},
{
"epoch": 0.04,
"learning_rate": 4.0836711389489654e-05,
"loss": 1.0817,
"step": 43
},
{
"epoch": 0.04,
"learning_rate": 4.108631691215468e-05,
"loss": 1.0712,
"step": 44
},
{
"epoch": 0.04,
"learning_rate": 4.133031284438358e-05,
"loss": 1.0865,
"step": 45
},
{
"epoch": 0.04,
"learning_rate": 4.156894579203935e-05,
"loss": 1.0837,
"step": 46
},
{
"epoch": 0.04,
"learning_rate": 4.180244644839293e-05,
"loss": 1.0915,
"step": 47
},
{
"epoch": 0.04,
"learning_rate": 4.203103093438968e-05,
"loss": 1.0845,
"step": 48
},
{
"epoch": 0.04,
"learning_rate": 4.2254902000712836e-05,
"loss": 1.0425,
"step": 49
},
{
"epoch": 0.05,
"learning_rate": 4.247425010840046e-05,
"loss": 1.0479,
"step": 50
},
{
"epoch": 0.05,
"eval_val_accuracy": 0.6191666666666666,
"eval_val_loss": 1.1118515729904175,
"eval_val_runtime": 913.0126,
"eval_val_samples_per_second": 1.095,
"eval_val_steps_per_second": 0.137,
"step": 50
},
{
"epoch": 0.05,
"learning_rate": 4.2689254402448405e-05,
"loss": 1.079,
"step": 51
},
{
"epoch": 0.05,
"learning_rate": 4.290008359086998e-05,
"loss": 1.0855,
"step": 52
},
{
"epoch": 0.05,
"learning_rate": 4.310689674001973e-05,
"loss": 1.084,
"step": 53
},
{
"epoch": 0.05,
"learning_rate": 4.330984399557421e-05,
"loss": 1.0787,
"step": 54
},
{
"epoch": 0.05,
"learning_rate": 4.350906723735609e-05,
"loss": 1.1333,
"step": 55
},
{
"epoch": 0.05,
"learning_rate": 4.370470067515501e-05,
"loss": 1.1016,
"step": 56
},
{
"epoch": 0.06,
"learning_rate": 4.3896871391812285e-05,
"loss": 1.0716,
"step": 57
},
{
"epoch": 0.06,
"learning_rate": 4.408569983907343e-05,
"loss": 1.0861,
"step": 58
},
{
"epoch": 0.06,
"learning_rate": 4.42713002910536e-05,
"loss": 1.0583,
"step": 59
},
{
"epoch": 0.06,
"learning_rate": 4.445378125959108e-05,
"loss": 1.0793,
"step": 60
},
{
"epoch": 0.06,
"learning_rate": 4.463324587526917e-05,
"loss": 1.0761,
"step": 61
},
{
"epoch": 0.06,
"learning_rate": 4.4809792237456346e-05,
"loss": 1.0995,
"step": 62
},
{
"epoch": 0.06,
"learning_rate": 4.498351373633954e-05,
"loss": 1.0915,
"step": 63
},
{
"epoch": 0.06,
"learning_rate": 4.515449934959717e-05,
"loss": 1.0415,
"step": 64
},
{
"epoch": 0.06,
"learning_rate": 4.532283391607138e-05,
"loss": 1.0429,
"step": 65
},
{
"epoch": 0.06,
"learning_rate": 4.548859838854671e-05,
"loss": 1.0886,
"step": 66
},
{
"epoch": 0.07,
"learning_rate": 4.565187006752065e-05,
"loss": 1.0332,
"step": 67
},
{
"epoch": 0.07,
"learning_rate": 4.581272281765591e-05,
"loss": 1.0271,
"step": 68
},
{
"epoch": 0.07,
"learning_rate": 4.597122726843138e-05,
"loss": 1.0591,
"step": 69
},
{
"epoch": 0.07,
"learning_rate": 4.612745100035642e-05,
"loss": 1.023,
"step": 70
},
{
"epoch": 0.07,
"learning_rate": 4.628145871797688e-05,
"loss": 1.0665,
"step": 71
},
{
"epoch": 0.07,
"learning_rate": 4.643331241078171e-05,
"loss": 1.064,
"step": 72
},
{
"epoch": 0.07,
"learning_rate": 4.658307150301139e-05,
"loss": 1.1339,
"step": 73
},
{
"epoch": 0.07,
"learning_rate": 4.67307929932744e-05,
"loss": 1.0609,
"step": 74
},
{
"epoch": 0.07,
"learning_rate": 4.687653158479249e-05,
"loss": 1.1128,
"step": 75
},
{
"epoch": 0.07,
"learning_rate": 4.702033980701978e-05,
"loss": 1.0733,
"step": 76
},
{
"epoch": 0.07,
"learning_rate": 4.716226812931204e-05,
"loss": 1.0761,
"step": 77
},
{
"epoch": 0.08,
"learning_rate": 4.7302365067262006e-05,
"loss": 1.0609,
"step": 78
},
{
"epoch": 0.08,
"learning_rate": 4.744067728226103e-05,
"loss": 1.0306,
"step": 79
},
{
"epoch": 0.08,
"learning_rate": 4.757724967479858e-05,
"loss": 1.0882,
"step": 80
},
{
"epoch": 0.08,
"learning_rate": 4.771212547196624e-05,
"loss": 1.0556,
"step": 81
},
{
"epoch": 0.08,
"learning_rate": 4.7845346309592914e-05,
"loss": 1.0455,
"step": 82
},
{
"epoch": 0.08,
"learning_rate": 4.7976952309401844e-05,
"loss": 1.0653,
"step": 83
},
{
"epoch": 0.08,
"learning_rate": 4.810698215154703e-05,
"loss": 1.0128,
"step": 84
},
{
"epoch": 0.08,
"learning_rate": 4.823547314285732e-05,
"loss": 1.0739,
"step": 85
},
{
"epoch": 0.08,
"learning_rate": 4.836246128108918e-05,
"loss": 1.161,
"step": 86
},
{
"epoch": 0.08,
"learning_rate": 4.8487981315465456e-05,
"loss": 1.0686,
"step": 87
},
{
"epoch": 0.09,
"learning_rate": 4.8612066803754214e-05,
"loss": 1.0785,
"step": 88
},
{
"epoch": 0.09,
"learning_rate": 4.873475016612281e-05,
"loss": 1.0362,
"step": 89
},
{
"epoch": 0.09,
"learning_rate": 4.885606273598312e-05,
"loss": 1.0775,
"step": 90
},
{
"epoch": 0.09,
"learning_rate": 4.897603480802733e-05,
"loss": 1.0445,
"step": 91
},
{
"epoch": 0.09,
"learning_rate": 4.909469568363888e-05,
"loss": 1.0452,
"step": 92
},
{
"epoch": 0.09,
"learning_rate": 4.9212073713848375e-05,
"loss": 1.0687,
"step": 93
},
{
"epoch": 0.09,
"learning_rate": 4.932819633999246e-05,
"loss": 1.0775,
"step": 94
},
{
"epoch": 0.09,
"learning_rate": 4.9443090132221186e-05,
"loss": 1.0239,
"step": 95
},
{
"epoch": 0.09,
"learning_rate": 4.9556780825989205e-05,
"loss": 1.0532,
"step": 96
},
{
"epoch": 0.09,
"learning_rate": 4.9669293356656114e-05,
"loss": 1.0628,
"step": 97
},
{
"epoch": 0.1,
"learning_rate": 4.978065189231237e-05,
"loss": 1.0562,
"step": 98
},
{
"epoch": 0.1,
"learning_rate": 4.989087986493874e-05,
"loss": 1.0404,
"step": 99
},
{
"epoch": 0.1,
"learning_rate": 4.9999999999999996e-05,
"loss": 1.0711,
"step": 100
},
{
"epoch": 0.1,
"eval_val_accuracy": 0.6268333333333334,
"eval_val_loss": 1.0909922122955322,
"eval_val_runtime": 906.1076,
"eval_val_samples_per_second": 1.104,
"eval_val_steps_per_second": 0.138,
"step": 100
},
{
"epoch": 0.1,
"learning_rate": 1e-05,
"loss": 1.0378,
"step": 101
},
{
"epoch": 0.1,
"learning_rate": 1e-05,
"loss": 1.0447,
"step": 102
},
{
"epoch": 0.1,
"learning_rate": 1e-05,
"loss": 1.0323,
"step": 103
},
{
"epoch": 0.1,
"learning_rate": 1e-05,
"loss": 1.0135,
"step": 104
},
{
"epoch": 0.1,
"learning_rate": 1e-05,
"loss": 1.0168,
"step": 105
},
{
"epoch": 0.1,
"learning_rate": 1e-05,
"loss": 1.0689,
"step": 106
},
{
"epoch": 0.1,
"learning_rate": 1e-05,
"loss": 1.0389,
"step": 107
},
{
"epoch": 0.1,
"learning_rate": 1e-05,
"loss": 1.0665,
"step": 108
},
{
"epoch": 0.11,
"learning_rate": 1e-05,
"loss": 1.0668,
"step": 109
},
{
"epoch": 0.11,
"learning_rate": 1e-05,
"loss": 1.0728,
"step": 110
},
{
"epoch": 0.11,
"learning_rate": 1e-05,
"loss": 1.0747,
"step": 111
},
{
"epoch": 0.11,
"learning_rate": 1e-05,
"loss": 1.0314,
"step": 112
},
{
"epoch": 0.11,
"learning_rate": 1e-05,
"loss": 1.1075,
"step": 113
},
{
"epoch": 0.11,
"learning_rate": 1e-05,
"loss": 1.0645,
"step": 114
},
{
"epoch": 0.11,
"learning_rate": 1e-05,
"loss": 1.0528,
"step": 115
},
{
"epoch": 0.11,
"learning_rate": 1e-05,
"loss": 1.0783,
"step": 116
},
{
"epoch": 0.11,
"learning_rate": 1e-05,
"loss": 1.0524,
"step": 117
},
{
"epoch": 0.11,
"learning_rate": 1e-05,
"loss": 1.0451,
"step": 118
},
{
"epoch": 0.12,
"learning_rate": 1e-05,
"loss": 1.0281,
"step": 119
},
{
"epoch": 0.12,
"learning_rate": 1e-05,
"loss": 1.0829,
"step": 120
},
{
"epoch": 0.12,
"learning_rate": 1e-05,
"loss": 1.0088,
"step": 121
},
{
"epoch": 0.12,
"learning_rate": 1e-05,
"loss": 1.0634,
"step": 122
},
{
"epoch": 0.12,
"learning_rate": 1e-05,
"loss": 1.0836,
"step": 123
},
{
"epoch": 0.12,
"learning_rate": 1e-05,
"loss": 1.08,
"step": 124
},
{
"epoch": 0.12,
"learning_rate": 1e-05,
"loss": 1.0523,
"step": 125
},
{
"epoch": 0.12,
"learning_rate": 1e-05,
"loss": 1.0564,
"step": 126
},
{
"epoch": 0.12,
"learning_rate": 1e-05,
"loss": 1.038,
"step": 127
},
{
"epoch": 0.12,
"learning_rate": 1e-05,
"loss": 1.0494,
"step": 128
},
{
"epoch": 0.13,
"learning_rate": 1e-05,
"loss": 1.0329,
"step": 129
},
{
"epoch": 0.13,
"learning_rate": 1e-05,
"loss": 1.0806,
"step": 130
},
{
"epoch": 0.13,
"learning_rate": 1e-05,
"loss": 1.0763,
"step": 131
},
{
"epoch": 0.13,
"learning_rate": 1e-05,
"loss": 1.0504,
"step": 132
},
{
"epoch": 0.13,
"learning_rate": 1e-05,
"loss": 1.044,
"step": 133
},
{
"epoch": 0.13,
"learning_rate": 1e-05,
"loss": 0.9895,
"step": 134
},
{
"epoch": 0.13,
"learning_rate": 1e-05,
"loss": 1.0688,
"step": 135
},
{
"epoch": 0.13,
"learning_rate": 1e-05,
"loss": 1.0471,
"step": 136
},
{
"epoch": 0.13,
"learning_rate": 1e-05,
"loss": 1.0711,
"step": 137
},
{
"epoch": 0.13,
"learning_rate": 1e-05,
"loss": 1.0506,
"step": 138
},
{
"epoch": 0.14,
"learning_rate": 1e-05,
"loss": 1.0789,
"step": 139
},
{
"epoch": 0.14,
"learning_rate": 1e-05,
"loss": 1.0888,
"step": 140
},
{
"epoch": 0.14,
"learning_rate": 1e-05,
"loss": 1.0746,
"step": 141
},
{
"epoch": 0.14,
"learning_rate": 1e-05,
"loss": 1.1229,
"step": 142
},
{
"epoch": 0.14,
"learning_rate": 1e-05,
"loss": 1.0826,
"step": 143
},
{
"epoch": 0.14,
"learning_rate": 1e-05,
"loss": 1.0504,
"step": 144
},
{
"epoch": 0.14,
"learning_rate": 1e-05,
"loss": 1.0311,
"step": 145
},
{
"epoch": 0.14,
"learning_rate": 1e-05,
"loss": 1.0456,
"step": 146
},
{
"epoch": 0.14,
"learning_rate": 1e-05,
"loss": 1.0097,
"step": 147
},
{
"epoch": 0.14,
"learning_rate": 1e-05,
"loss": 1.0282,
"step": 148
},
{
"epoch": 0.14,
"learning_rate": 1e-05,
"loss": 1.0507,
"step": 149
},
{
"epoch": 0.15,
"learning_rate": 1e-05,
"loss": 1.054,
"step": 150
},
{
"epoch": 0.15,
"eval_val_accuracy": 0.626,
"eval_val_loss": 1.0630038976669312,
"eval_val_runtime": 907.7978,
"eval_val_samples_per_second": 1.102,
"eval_val_steps_per_second": 0.138,
"step": 150
},
{
"epoch": 0.15,
"learning_rate": 1e-05,
"loss": 1.0165,
"step": 151
},
{
"epoch": 0.15,
"learning_rate": 1e-05,
"loss": 0.9992,
"step": 152
},
{
"epoch": 0.15,
"learning_rate": 1e-05,
"loss": 1.045,
"step": 153
},
{
"epoch": 0.15,
"learning_rate": 1e-05,
"loss": 1.0378,
"step": 154
},
{
"epoch": 0.15,
"learning_rate": 1e-05,
"loss": 1.0502,
"step": 155
},
{
"epoch": 0.15,
"learning_rate": 1e-05,
"loss": 0.9911,
"step": 156
},
{
"epoch": 0.15,
"learning_rate": 1e-05,
"loss": 1.063,
"step": 157
},
{
"epoch": 0.15,
"learning_rate": 1e-05,
"loss": 1.0383,
"step": 158
},
{
"epoch": 0.15,
"learning_rate": 1e-05,
"loss": 1.0511,
"step": 159
},
{
"epoch": 0.16,
"learning_rate": 1e-05,
"loss": 1.0204,
"step": 160
},
{
"epoch": 0.16,
"learning_rate": 1e-05,
"loss": 1.084,
"step": 161
},
{
"epoch": 0.16,
"learning_rate": 1e-05,
"loss": 1.0873,
"step": 162
},
{
"epoch": 0.16,
"learning_rate": 1e-05,
"loss": 1.0304,
"step": 163
},
{
"epoch": 0.16,
"learning_rate": 1e-05,
"loss": 1.0118,
"step": 164
},
{
"epoch": 0.16,
"learning_rate": 1e-05,
"loss": 1.04,
"step": 165
},
{
"epoch": 0.16,
"learning_rate": 1e-05,
"loss": 1.0018,
"step": 166
},
{
"epoch": 0.16,
"learning_rate": 1e-05,
"loss": 1.0432,
"step": 167
},
{
"epoch": 0.16,
"learning_rate": 1e-05,
"loss": 1.0116,
"step": 168
},
{
"epoch": 0.16,
"learning_rate": 1e-05,
"loss": 1.0647,
"step": 169
},
{
"epoch": 0.17,
"learning_rate": 1e-05,
"loss": 1.091,
"step": 170
},
{
"epoch": 0.17,
"learning_rate": 1e-05,
"loss": 1.0167,
"step": 171
},
{
"epoch": 0.17,
"learning_rate": 1e-05,
"loss": 1.0952,
"step": 172
},
{
"epoch": 0.17,
"learning_rate": 1e-05,
"loss": 1.0423,
"step": 173
},
{
"epoch": 0.17,
"learning_rate": 1e-05,
"loss": 1.0198,
"step": 174
},
{
"epoch": 0.17,
"learning_rate": 1e-05,
"loss": 1.0341,
"step": 175
},
{
"epoch": 0.17,
"learning_rate": 1e-05,
"loss": 1.0657,
"step": 176
},
{
"epoch": 0.17,
"learning_rate": 1e-05,
"loss": 1.0084,
"step": 177
},
{
"epoch": 0.17,
"learning_rate": 1e-05,
"loss": 1.0483,
"step": 178
},
{
"epoch": 0.17,
"learning_rate": 1e-05,
"loss": 1.0493,
"step": 179
},
{
"epoch": 0.17,
"learning_rate": 1e-05,
"loss": 1.0328,
"step": 180
},
{
"epoch": 0.18,
"learning_rate": 1e-05,
"loss": 1.0585,
"step": 181
},
{
"epoch": 0.18,
"learning_rate": 1e-05,
"loss": 0.9869,
"step": 182
},
{
"epoch": 0.18,
"learning_rate": 1e-05,
"loss": 1.0266,
"step": 183
},
{
"epoch": 0.18,
"learning_rate": 1e-05,
"loss": 1.0462,
"step": 184
},
{
"epoch": 0.18,
"learning_rate": 1e-05,
"loss": 1.0306,
"step": 185
},
{
"epoch": 0.18,
"learning_rate": 1e-05,
"loss": 1.0459,
"step": 186
},
{
"epoch": 0.18,
"learning_rate": 1e-05,
"loss": 1.0004,
"step": 187
},
{
"epoch": 0.18,
"learning_rate": 1e-05,
"loss": 1.0417,
"step": 188
},
{
"epoch": 0.18,
"learning_rate": 1e-05,
"loss": 1.0712,
"step": 189
},
{
"epoch": 0.18,
"learning_rate": 1e-05,
"loss": 1.0228,
"step": 190
},
{
"epoch": 0.19,
"learning_rate": 1e-05,
"loss": 0.9888,
"step": 191
},
{
"epoch": 0.19,
"learning_rate": 1e-05,
"loss": 0.9393,
"step": 192
},
{
"epoch": 0.19,
"learning_rate": 1e-05,
"loss": 1.052,
"step": 193
},
{
"epoch": 0.19,
"learning_rate": 1e-05,
"loss": 1.0751,
"step": 194
},
{
"epoch": 0.19,
"learning_rate": 1e-05,
"loss": 1.0468,
"step": 195
},
{
"epoch": 0.19,
"learning_rate": 1e-05,
"loss": 1.0235,
"step": 196
},
{
"epoch": 0.19,
"learning_rate": 1e-05,
"loss": 1.0428,
"step": 197
},
{
"epoch": 0.19,
"learning_rate": 1e-05,
"loss": 1.0408,
"step": 198
},
{
"epoch": 0.19,
"learning_rate": 1e-05,
"loss": 1.0112,
"step": 199
},
{
"epoch": 0.19,
"learning_rate": 1e-05,
"loss": 1.0329,
"step": 200
},
{
"epoch": 0.19,
"eval_val_accuracy": 0.6278333333333334,
"eval_val_loss": 1.0557304620742798,
"eval_val_runtime": 906.1331,
"eval_val_samples_per_second": 1.104,
"eval_val_steps_per_second": 0.138,
"step": 200
},
{
"epoch": 0.2,
"learning_rate": 1e-05,
"loss": 1.0219,
"step": 201
},
{
"epoch": 0.2,
"learning_rate": 1e-05,
"loss": 1.0479,
"step": 202
},
{
"epoch": 0.2,
"learning_rate": 1e-05,
"loss": 0.9808,
"step": 203
},
{
"epoch": 0.21,
"learning_rate": 1e-05,
"loss": 1.0404,
"step": 204
},
{
"epoch": 0.21,
"learning_rate": 1e-05,
"loss": 1.0214,
"step": 205
},
{
"epoch": 0.21,
"learning_rate": 1e-05,
"loss": 0.9991,
"step": 206
},
{
"epoch": 0.21,
"learning_rate": 1e-05,
"loss": 0.9435,
"step": 207
},
{
"epoch": 0.21,
"learning_rate": 1e-05,
"loss": 1.0083,
"step": 208
},
{
"epoch": 0.21,
"learning_rate": 1e-05,
"loss": 1.0187,
"step": 209
},
{
"epoch": 0.21,
"learning_rate": 1e-05,
"loss": 1.0493,
"step": 210
},
{
"epoch": 0.21,
"learning_rate": 1e-05,
"loss": 0.9925,
"step": 211
},
{
"epoch": 0.21,
"learning_rate": 1e-05,
"loss": 1.0142,
"step": 212
},
{
"epoch": 0.21,
"learning_rate": 1e-05,
"loss": 1.0131,
"step": 213
},
{
"epoch": 0.22,
"learning_rate": 1e-05,
"loss": 1.0041,
"step": 214
},
{
"epoch": 0.22,
"learning_rate": 1e-05,
"loss": 1.0187,
"step": 215
},
{
"epoch": 0.22,
"learning_rate": 1e-05,
"loss": 1.0551,
"step": 216
},
{
"epoch": 0.22,
"learning_rate": 1e-05,
"loss": 1.0224,
"step": 217
},
{
"epoch": 0.22,
"learning_rate": 1e-05,
"loss": 1.0654,
"step": 218
},
{
"epoch": 0.22,
"learning_rate": 1e-05,
"loss": 1.0472,
"step": 219
},
{
"epoch": 0.22,
"learning_rate": 1e-05,
"loss": 0.9667,
"step": 220
},
{
"epoch": 0.22,
"learning_rate": 1e-05,
"loss": 0.9944,
"step": 221
},
{
"epoch": 0.22,
"learning_rate": 1e-05,
"loss": 1.0283,
"step": 222
},
{
"epoch": 0.22,
"learning_rate": 1e-05,
"loss": 1.0047,
"step": 223
},
{
"epoch": 0.23,
"learning_rate": 1e-05,
"loss": 0.9781,
"step": 224
},
{
"epoch": 0.23,
"learning_rate": 1e-05,
"loss": 1.0127,
"step": 225
},
{
"epoch": 0.23,
"learning_rate": 1e-05,
"loss": 1.035,
"step": 226
},
{
"epoch": 0.23,
"learning_rate": 1e-05,
"loss": 0.9573,
"step": 227
},
{
"epoch": 0.23,
"learning_rate": 1e-05,
"loss": 1.0365,
"step": 228
},
{
"epoch": 0.23,
"learning_rate": 1e-05,
"loss": 1.0508,
"step": 229
},
{
"epoch": 0.23,
"learning_rate": 1e-05,
"loss": 1.0138,
"step": 230
},
{
"epoch": 0.23,
"learning_rate": 1e-05,
"loss": 1.0037,
"step": 231
},
{
"epoch": 0.23,
"learning_rate": 1e-05,
"loss": 1.013,
"step": 232
},
{
"epoch": 0.23,
"learning_rate": 1e-05,
"loss": 1.0025,
"step": 233
},
{
"epoch": 0.24,
"learning_rate": 1e-05,
"loss": 1.0309,
"step": 234
},
{
"epoch": 0.24,
"learning_rate": 1e-05,
"loss": 0.9718,
"step": 235
},
{
"epoch": 0.24,
"learning_rate": 1e-05,
"loss": 0.9968,
"step": 236
},
{
"epoch": 0.24,
"learning_rate": 1e-05,
"loss": 1.024,
"step": 237
},
{
"epoch": 0.24,
"learning_rate": 1e-05,
"loss": 1.0028,
"step": 238
},
{
"epoch": 0.24,
"learning_rate": 1e-05,
"loss": 1.0701,
"step": 239
},
{
"epoch": 0.24,
"learning_rate": 1e-05,
"loss": 1.0428,
"step": 240
},
{
"epoch": 0.24,
"learning_rate": 1e-05,
"loss": 0.9651,
"step": 241
},
{
"epoch": 0.24,
"learning_rate": 1e-05,
"loss": 1.0095,
"step": 242
},
{
"epoch": 0.24,
"learning_rate": 1e-05,
"loss": 1.0495,
"step": 243
},
{
"epoch": 0.25,
"learning_rate": 1e-05,
"loss": 1.0441,
"step": 244
},
{
"epoch": 0.25,
"learning_rate": 1e-05,
"loss": 1.0412,
"step": 245
},
{
"epoch": 0.25,
"learning_rate": 1e-05,
"loss": 1.0335,
"step": 246
},
{
"epoch": 0.25,
"learning_rate": 1e-05,
"loss": 1.0092,
"step": 247
},
{
"epoch": 0.25,
"learning_rate": 1e-05,
"loss": 1.0408,
"step": 248
},
{
"epoch": 0.25,
"learning_rate": 1e-05,
"loss": 0.993,
"step": 249
},
{
"epoch": 0.25,
"learning_rate": 1e-05,
"loss": 0.9546,
"step": 250
},
{
"epoch": 0.25,
"eval_val_accuracy": 0.6341666666666667,
"eval_val_loss": 1.053076148033142,
"eval_val_runtime": 906.4123,
"eval_val_samples_per_second": 1.103,
"eval_val_steps_per_second": 0.138,
"step": 250
},
{
"epoch": 0.25,
"learning_rate": 1e-05,
"loss": 1.043,
"step": 251
},
{
"epoch": 0.25,
"learning_rate": 1e-05,
"loss": 1.0082,
"step": 252
},
{
"epoch": 0.25,
"learning_rate": 1e-05,
"loss": 1.0281,
"step": 253
},
{
"epoch": 0.26,
"learning_rate": 1e-05,
"loss": 0.9779,
"step": 254
},
{
"epoch": 0.26,
"learning_rate": 1e-05,
"loss": 1.0074,
"step": 255
},
{
"epoch": 0.26,
"learning_rate": 1e-05,
"loss": 0.9639,
"step": 256
},
{
"epoch": 0.26,
"learning_rate": 1e-05,
"loss": 1.0121,
"step": 257
},
{
"epoch": 0.26,
"learning_rate": 1e-05,
"loss": 1.036,
"step": 258
},
{
"epoch": 0.26,
"learning_rate": 1e-05,
"loss": 1.0143,
"step": 259
},
{
"epoch": 0.26,
"learning_rate": 1e-05,
"loss": 1.0407,
"step": 260
},
{
"epoch": 0.26,
"learning_rate": 1e-05,
"loss": 1.0202,
"step": 261
},
{
"epoch": 0.26,
"learning_rate": 1e-05,
"loss": 1.0099,
"step": 262
},
{
"epoch": 0.26,
"learning_rate": 1e-05,
"loss": 1.0226,
"step": 263
},
{
"epoch": 0.27,
"learning_rate": 1e-05,
"loss": 1.02,
"step": 264
},
{
"epoch": 0.27,
"learning_rate": 1e-05,
"loss": 1.0197,
"step": 265
},
{
"epoch": 0.27,
"learning_rate": 1e-05,
"loss": 1.0621,
"step": 266
},
{
"epoch": 0.27,
"learning_rate": 1e-05,
"loss": 1.0261,
"step": 267
},
{
"epoch": 0.27,
"learning_rate": 1e-05,
"loss": 1.0392,
"step": 268
},
{
"epoch": 0.27,
"learning_rate": 1e-05,
"loss": 0.9644,
"step": 269
},
{
"epoch": 0.27,
"learning_rate": 1e-05,
"loss": 0.9943,
"step": 270
},
{
"epoch": 0.27,
"learning_rate": 1e-05,
"loss": 1.0354,
"step": 271
},
{
"epoch": 0.27,
"learning_rate": 1e-05,
"loss": 0.9826,
"step": 272
},
{
"epoch": 0.27,
"learning_rate": 1e-05,
"loss": 0.9934,
"step": 273
},
{
"epoch": 0.28,
"learning_rate": 1e-05,
"loss": 1.0222,
"step": 274
},
{
"epoch": 0.28,
"learning_rate": 1e-05,
"loss": 1.0752,
"step": 275
},
{
"epoch": 0.28,
"learning_rate": 1e-05,
"loss": 1.0337,
"step": 276
},
{
"epoch": 0.28,
"learning_rate": 1e-05,
"loss": 0.976,
"step": 277
},
{
"epoch": 0.28,
"learning_rate": 1e-05,
"loss": 1.051,
"step": 278
},
{
"epoch": 0.28,
"learning_rate": 1e-05,
"loss": 1.0338,
"step": 279
},
{
"epoch": 0.28,
"learning_rate": 1e-05,
"loss": 1.0026,
"step": 280
},
{
"epoch": 0.28,
"learning_rate": 1e-05,
"loss": 1.0118,
"step": 281
},
{
"epoch": 0.28,
"learning_rate": 1e-05,
"loss": 0.9982,
"step": 282
},
{
"epoch": 0.28,
"learning_rate": 1e-05,
"loss": 1.0136,
"step": 283
},
{
"epoch": 0.29,
"learning_rate": 1e-05,
"loss": 0.9613,
"step": 284
},
{
"epoch": 0.29,
"learning_rate": 1e-05,
"loss": 1.0122,
"step": 285
},
{
"epoch": 0.29,
"learning_rate": 1e-05,
"loss": 1.049,
"step": 286
},
{
"epoch": 0.29,
"learning_rate": 1e-05,
"loss": 1.0164,
"step": 287
},
{
"epoch": 0.29,
"learning_rate": 1e-05,
"loss": 1.0052,
"step": 288
},
{
"epoch": 0.29,
"learning_rate": 1e-05,
"loss": 1.0244,
"step": 289
},
{
"epoch": 0.29,
"learning_rate": 1e-05,
"loss": 0.9886,
"step": 290
},
{
"epoch": 0.29,
"learning_rate": 1e-05,
"loss": 1.0039,
"step": 291
},
{
"epoch": 0.29,
"learning_rate": 1e-05,
"loss": 1.0088,
"step": 292
},
{
"epoch": 0.29,
"learning_rate": 1e-05,
"loss": 1.0003,
"step": 293
},
{
"epoch": 0.3,
"learning_rate": 1e-05,
"loss": 0.9984,
"step": 294
},
{
"epoch": 0.3,
"learning_rate": 1e-05,
"loss": 1.0288,
"step": 295
},
{
"epoch": 0.3,
"learning_rate": 1e-05,
"loss": 0.9928,
"step": 296
},
{
"epoch": 0.3,
"learning_rate": 1e-05,
"loss": 0.992,
"step": 297
},
{
"epoch": 0.3,
"learning_rate": 1e-05,
"loss": 0.9863,
"step": 298
},
{
"epoch": 0.3,
"learning_rate": 1e-05,
"loss": 0.9959,
"step": 299
},
{
"epoch": 0.3,
"learning_rate": 1e-05,
"loss": 1.0094,
"step": 300
},
{
"epoch": 0.3,
"eval_val_accuracy": 0.6303333333333334,
"eval_val_loss": 1.0518085956573486,
"eval_val_runtime": 905.7847,
"eval_val_samples_per_second": 1.104,
"eval_val_steps_per_second": 0.138,
"step": 300
},
{
"epoch": 0.3,
"learning_rate": 1e-05,
"loss": 1.0049,
"step": 301
},
{
"epoch": 0.3,
"learning_rate": 1e-05,
"loss": 1.005,
"step": 302
},
{
"epoch": 0.3,
"learning_rate": 1e-05,
"loss": 1.0033,
"step": 303
},
{
"epoch": 0.31,
"learning_rate": 1e-05,
"loss": 1.054,
"step": 304
},
{
"epoch": 0.31,
"learning_rate": 1e-05,
"loss": 0.9742,
"step": 305
},
{
"epoch": 0.31,
"learning_rate": 1e-05,
"loss": 1.0061,
"step": 306
},
{
"epoch": 0.31,
"learning_rate": 1e-05,
"loss": 1.015,
"step": 307
},
{
"epoch": 0.31,
"learning_rate": 1e-05,
"loss": 1.0414,
"step": 308
},
{
"epoch": 0.31,
"learning_rate": 1e-05,
"loss": 0.9995,
"step": 309
},
{
"epoch": 0.31,
"learning_rate": 1e-05,
"loss": 0.9901,
"step": 310
},
{
"epoch": 0.31,
"learning_rate": 1e-05,
"loss": 0.9936,
"step": 311
},
{
"epoch": 0.31,
"learning_rate": 1e-05,
"loss": 1.0476,
"step": 312
},
{
"epoch": 0.31,
"learning_rate": 1e-05,
"loss": 0.9987,
"step": 313
},
{
"epoch": 0.32,
"learning_rate": 1e-05,
"loss": 1.0564,
"step": 314
},
{
"epoch": 0.32,
"learning_rate": 1e-05,
"loss": 1.0129,
"step": 315
},
{
"epoch": 0.32,
"learning_rate": 1e-05,
"loss": 0.9667,
"step": 316
},
{
"epoch": 0.32,
"learning_rate": 1e-05,
"loss": 1.0264,
"step": 317
},
{
"epoch": 0.32,
"learning_rate": 1e-05,
"loss": 0.9835,
"step": 318
},
{
"epoch": 0.32,
"learning_rate": 1e-05,
"loss": 1.0199,
"step": 319
},
{
"epoch": 0.32,
"learning_rate": 1e-05,
"loss": 0.9652,
"step": 320
},
{
"epoch": 0.32,
"learning_rate": 1e-05,
"loss": 0.9874,
"step": 321
},
{
"epoch": 0.32,
"learning_rate": 1e-05,
"loss": 1.0079,
"step": 322
},
{
"epoch": 0.32,
"learning_rate": 1e-05,
"loss": 1.0858,
"step": 323
},
{
"epoch": 0.33,
"learning_rate": 1e-05,
"loss": 1.015,
"step": 324
},
{
"epoch": 0.33,
"learning_rate": 1e-05,
"loss": 0.9782,
"step": 325
},
{
"epoch": 0.33,
"learning_rate": 1e-05,
"loss": 1.0589,
"step": 326
},
{
"epoch": 0.33,
"learning_rate": 1e-05,
"loss": 1.0152,
"step": 327
},
{
"epoch": 0.33,
"learning_rate": 1e-05,
"loss": 0.9639,
"step": 328
},
{
"epoch": 0.33,
"learning_rate": 1e-05,
"loss": 1.0089,
"step": 329
},
{
"epoch": 0.33,
"learning_rate": 1e-05,
"loss": 1.056,
"step": 330
},
{
"epoch": 0.33,
"learning_rate": 1e-05,
"loss": 0.985,
"step": 331
},
{
"epoch": 0.33,
"learning_rate": 1e-05,
"loss": 1.027,
"step": 332
},
{
"epoch": 0.33,
"learning_rate": 1e-05,
"loss": 1.0565,
"step": 333
},
{
"epoch": 0.34,
"learning_rate": 1e-05,
"loss": 1.0337,
"step": 334
},
{
"epoch": 0.34,
"learning_rate": 1e-05,
"loss": 1.0453,
"step": 335
},
{
"epoch": 0.34,
"learning_rate": 1e-05,
"loss": 1.0108,
"step": 336
},
{
"epoch": 0.34,
"learning_rate": 1e-05,
"loss": 1.0289,
"step": 337
},
{
"epoch": 0.34,
"learning_rate": 1e-05,
"loss": 1.0096,
"step": 338
},
{
"epoch": 0.34,
"learning_rate": 1e-05,
"loss": 1.0241,
"step": 339
},
{
"epoch": 0.34,
"learning_rate": 1e-05,
"loss": 0.9743,
"step": 340
},
{
"epoch": 0.34,
"learning_rate": 1e-05,
"loss": 1.0387,
"step": 341
},
{
"epoch": 0.34,
"learning_rate": 1e-05,
"loss": 1.0023,
"step": 342
},
{
"epoch": 0.34,
"learning_rate": 1e-05,
"loss": 1.0257,
"step": 343
},
{
"epoch": 0.35,
"learning_rate": 1e-05,
"loss": 0.9827,
"step": 344
},
{
"epoch": 0.35,
"learning_rate": 1e-05,
"loss": 1.0269,
"step": 345
},
{
"epoch": 0.35,
"learning_rate": 1e-05,
"loss": 1.0017,
"step": 346
},
{
"epoch": 0.35,
"learning_rate": 1e-05,
"loss": 0.994,
"step": 347
},
{
"epoch": 0.35,
"learning_rate": 1e-05,
"loss": 1.0285,
"step": 348
},
{
"epoch": 0.35,
"learning_rate": 1e-05,
"loss": 1.0634,
"step": 349
},
{
"epoch": 0.35,
"learning_rate": 1e-05,
"loss": 1.0224,
"step": 350
},
{
"epoch": 0.35,
"eval_val_accuracy": 0.6265,
"eval_val_loss": 1.0556230545043945,
"eval_val_runtime": 905.4395,
"eval_val_samples_per_second": 1.104,
"eval_val_steps_per_second": 0.138,
"step": 350
},
{
"epoch": 0.35,
"learning_rate": 1e-05,
"loss": 0.9755,
"step": 351
},
{
"epoch": 0.35,
"learning_rate": 1e-05,
"loss": 1.0004,
"step": 352
},
{
"epoch": 0.35,
"learning_rate": 1e-05,
"loss": 1.0171,
"step": 353
},
{
"epoch": 0.36,
"learning_rate": 1e-05,
"loss": 1.0,
"step": 354
},
{
"epoch": 0.36,
"learning_rate": 1e-05,
"loss": 0.9887,
"step": 355
},
{
"epoch": 0.36,
"learning_rate": 1e-05,
"loss": 1.0387,
"step": 356
},
{
"epoch": 0.36,
"learning_rate": 1e-05,
"loss": 0.9966,
"step": 357
},
{
"epoch": 0.36,
"learning_rate": 1e-05,
"loss": 1.0213,
"step": 358
},
{
"epoch": 0.36,
"learning_rate": 1e-05,
"loss": 1.0168,
"step": 359
},
{
"epoch": 0.36,
"learning_rate": 1e-05,
"loss": 1.0332,
"step": 360
},
{
"epoch": 0.36,
"learning_rate": 1e-05,
"loss": 1.039,
"step": 361
},
{
"epoch": 0.36,
"learning_rate": 1e-05,
"loss": 1.0034,
"step": 362
},
{
"epoch": 0.36,
"learning_rate": 1e-05,
"loss": 0.9631,
"step": 363
},
{
"epoch": 0.37,
"learning_rate": 1e-05,
"loss": 1.0406,
"step": 364
},
{
"epoch": 0.37,
"learning_rate": 1e-05,
"loss": 0.9821,
"step": 365
},
{
"epoch": 0.37,
"learning_rate": 1e-05,
"loss": 1.0231,
"step": 366
},
{
"epoch": 0.37,
"learning_rate": 1e-05,
"loss": 1.0272,
"step": 367
},
{
"epoch": 0.37,
"learning_rate": 1e-05,
"loss": 1.0231,
"step": 368
},
{
"epoch": 0.37,
"learning_rate": 1e-05,
"loss": 0.9833,
"step": 369
},
{
"epoch": 0.37,
"learning_rate": 1e-05,
"loss": 1.0219,
"step": 370
},
{
"epoch": 0.37,
"learning_rate": 1e-05,
"loss": 0.9647,
"step": 371
},
{
"epoch": 0.37,
"learning_rate": 1e-05,
"loss": 1.0044,
"step": 372
},
{
"epoch": 0.37,
"learning_rate": 1e-05,
"loss": 0.9968,
"step": 373
},
{
"epoch": 0.38,
"learning_rate": 1e-05,
"loss": 0.9956,
"step": 374
},
{
"epoch": 0.38,
"learning_rate": 1e-05,
"loss": 1.0278,
"step": 375
},
{
"epoch": 0.38,
"learning_rate": 1e-05,
"loss": 0.9908,
"step": 376
},
{
"epoch": 0.38,
"learning_rate": 1e-05,
"loss": 1.0058,
"step": 377
},
{
"epoch": 0.38,
"learning_rate": 1e-05,
"loss": 1.0185,
"step": 378
},
{
"epoch": 0.38,
"learning_rate": 1e-05,
"loss": 0.97,
"step": 379
},
{
"epoch": 0.38,
"learning_rate": 1e-05,
"loss": 0.9491,
"step": 380
},
{
"epoch": 0.38,
"learning_rate": 1e-05,
"loss": 1.0639,
"step": 381
},
{
"epoch": 0.38,
"learning_rate": 1e-05,
"loss": 1.0,
"step": 382
},
{
"epoch": 0.38,
"learning_rate": 1e-05,
"loss": 0.9812,
"step": 383
},
{
"epoch": 0.39,
"learning_rate": 1e-05,
"loss": 1.0691,
"step": 384
},
{
"epoch": 0.39,
"learning_rate": 1e-05,
"loss": 1.0074,
"step": 385
},
{
"epoch": 0.39,
"learning_rate": 1e-05,
"loss": 0.9924,
"step": 386
},
{
"epoch": 0.39,
"learning_rate": 1e-05,
"loss": 0.9976,
"step": 387
},
{
"epoch": 0.39,
"learning_rate": 1e-05,
"loss": 1.0217,
"step": 388
},
{
"epoch": 0.39,
"learning_rate": 1e-05,
"loss": 0.9745,
"step": 389
},
{
"epoch": 0.39,
"learning_rate": 1e-05,
"loss": 1.0014,
"step": 390
},
{
"epoch": 0.39,
"learning_rate": 1e-05,
"loss": 1.0192,
"step": 391
},
{
"epoch": 0.39,
"learning_rate": 1e-05,
"loss": 0.9825,
"step": 392
},
{
"epoch": 0.4,
"learning_rate": 1e-05,
"loss": 1.007,
"step": 393
},
{
"epoch": 0.4,
"learning_rate": 1e-05,
"loss": 1.0288,
"step": 394
},
{
"epoch": 0.4,
"learning_rate": 1e-05,
"loss": 1.0342,
"step": 395
},
{
"epoch": 0.4,
"learning_rate": 1e-05,
"loss": 1.0183,
"step": 396
},
{
"epoch": 0.4,
"learning_rate": 1e-05,
"loss": 0.9884,
"step": 397
},
{
"epoch": 0.4,
"learning_rate": 1e-05,
"loss": 0.9674,
"step": 398
},
{
"epoch": 0.4,
"learning_rate": 1e-05,
"loss": 0.9795,
"step": 399
},
{
"epoch": 0.4,
"learning_rate": 1e-05,
"loss": 0.9885,
"step": 400
},
{
"epoch": 0.4,
"eval_val_accuracy": 0.627,
"eval_val_loss": 1.0441503524780273,
"eval_val_runtime": 905.3415,
"eval_val_samples_per_second": 1.105,
"eval_val_steps_per_second": 0.138,
"step": 400
},
{
"epoch": 0.42,
"learning_rate": 1e-05,
"loss": 0.9416,
"step": 401
},
{
"epoch": 0.42,
"learning_rate": 1e-05,
"loss": 0.9981,
"step": 402
},
{
"epoch": 0.42,
"learning_rate": 1e-05,
"loss": 0.9836,
"step": 403
},
{
"epoch": 0.42,
"learning_rate": 1e-05,
"loss": 1.0321,
"step": 404
},
{
"epoch": 0.42,
"learning_rate": 1e-05,
"loss": 0.9656,
"step": 405
},
{
"epoch": 0.42,
"learning_rate": 1e-05,
"loss": 0.9036,
"step": 406
},
{
"epoch": 0.42,
"learning_rate": 1e-05,
"loss": 1.0229,
"step": 407
},
{
"epoch": 0.42,
"learning_rate": 1e-05,
"loss": 0.9579,
"step": 408
},
{
"epoch": 0.43,
"learning_rate": 1e-05,
"loss": 0.9381,
"step": 409
},
{
"epoch": 0.43,
"learning_rate": 1e-05,
"loss": 0.9351,
"step": 410
},
{
"epoch": 0.43,
"learning_rate": 1e-05,
"loss": 0.9767,
"step": 411
},
{
"epoch": 0.43,
"learning_rate": 1e-05,
"loss": 0.9715,
"step": 412
},
{
"epoch": 0.43,
"learning_rate": 1e-05,
"loss": 1.0075,
"step": 413
},
{
"epoch": 0.43,
"learning_rate": 1e-05,
"loss": 0.9632,
"step": 414
},
{
"epoch": 0.43,
"learning_rate": 1e-05,
"loss": 0.9996,
"step": 415
},
{
"epoch": 0.43,
"learning_rate": 1e-05,
"loss": 0.9225,
"step": 416
},
{
"epoch": 0.43,
"learning_rate": 1e-05,
"loss": 0.9681,
"step": 417
},
{
"epoch": 0.44,
"learning_rate": 1e-05,
"loss": 0.9389,
"step": 418
},
{
"epoch": 0.44,
"learning_rate": 1e-05,
"loss": 0.9275,
"step": 419
},
{
"epoch": 0.44,
"learning_rate": 1e-05,
"loss": 1.0225,
"step": 420
},
{
"epoch": 0.44,
"learning_rate": 1e-05,
"loss": 0.9046,
"step": 421
},
{
"epoch": 0.44,
"learning_rate": 1e-05,
"loss": 0.9884,
"step": 422
},
{
"epoch": 0.44,
"learning_rate": 1e-05,
"loss": 0.953,
"step": 423
},
{
"epoch": 0.44,
"learning_rate": 1e-05,
"loss": 1.0088,
"step": 424
},
{
"epoch": 0.44,
"learning_rate": 1e-05,
"loss": 0.9869,
"step": 425
},
{
"epoch": 0.44,
"learning_rate": 1e-05,
"loss": 0.9564,
"step": 426
},
{
"epoch": 0.44,
"learning_rate": 1e-05,
"loss": 0.9082,
"step": 427
},
{
"epoch": 0.45,
"learning_rate": 1e-05,
"loss": 0.9805,
"step": 428
},
{
"epoch": 0.45,
"learning_rate": 1e-05,
"loss": 0.9287,
"step": 429
},
{
"epoch": 0.45,
"learning_rate": 1e-05,
"loss": 0.9369,
"step": 430
},
{
"epoch": 0.45,
"learning_rate": 1e-05,
"loss": 0.9573,
"step": 431
},
{
"epoch": 0.45,
"learning_rate": 1e-05,
"loss": 0.9908,
"step": 432
},
{
"epoch": 0.45,
"learning_rate": 1e-05,
"loss": 0.9144,
"step": 433
},
{
"epoch": 0.45,
"learning_rate": 1e-05,
"loss": 0.9815,
"step": 434
},
{
"epoch": 0.45,
"learning_rate": 1e-05,
"loss": 0.9538,
"step": 435
},
{
"epoch": 0.45,
"learning_rate": 1e-05,
"loss": 1.0009,
"step": 436
},
{
"epoch": 0.45,
"learning_rate": 1e-05,
"loss": 0.9467,
"step": 437
},
{
"epoch": 0.46,
"learning_rate": 1e-05,
"loss": 0.9538,
"step": 438
},
{
"epoch": 0.46,
"learning_rate": 1e-05,
"loss": 0.9999,
"step": 439
},
{
"epoch": 0.46,
"learning_rate": 1e-05,
"loss": 0.9813,
"step": 440
},
{
"epoch": 0.46,
"learning_rate": 1e-05,
"loss": 0.9678,
"step": 441
},
{
"epoch": 0.46,
"learning_rate": 1e-05,
"loss": 0.992,
"step": 442
},
{
"epoch": 0.46,
"learning_rate": 1e-05,
"loss": 0.9991,
"step": 443
},
{
"epoch": 0.46,
"learning_rate": 1e-05,
"loss": 0.9756,
"step": 444
},
{
"epoch": 0.46,
"learning_rate": 1e-05,
"loss": 0.9439,
"step": 445
},
{
"epoch": 0.46,
"learning_rate": 1e-05,
"loss": 0.989,
"step": 446
},
{
"epoch": 0.47,
"learning_rate": 1e-05,
"loss": 0.9636,
"step": 447
},
{
"epoch": 0.47,
"learning_rate": 1e-05,
"loss": 0.9632,
"step": 448
},
{
"epoch": 0.47,
"learning_rate": 1e-05,
"loss": 0.9537,
"step": 449
},
{
"epoch": 0.47,
"learning_rate": 1e-05,
"loss": 0.9655,
"step": 450
},
{
"epoch": 0.47,
"eval_val_accuracy": 0.6243333333333334,
"eval_val_loss": 1.0594570636749268,
"eval_val_runtime": 906.8468,
"eval_val_samples_per_second": 1.103,
"eval_val_steps_per_second": 0.138,
"step": 450
},
{
"epoch": 0.47,
"learning_rate": 1e-05,
"loss": 0.9335,
"step": 451
},
{
"epoch": 0.47,
"learning_rate": 1e-05,
"loss": 0.9177,
"step": 452
},
{
"epoch": 0.47,
"learning_rate": 1e-05,
"loss": 1.0279,
"step": 453
},
{
"epoch": 0.47,
"learning_rate": 1e-05,
"loss": 0.9097,
"step": 454
},
{
"epoch": 0.47,
"learning_rate": 1e-05,
"loss": 1.025,
"step": 455
},
{
"epoch": 0.47,
"learning_rate": 1e-05,
"loss": 1.0042,
"step": 456
},
{
"epoch": 0.48,
"learning_rate": 1e-05,
"loss": 0.9836,
"step": 457
},
{
"epoch": 0.48,
"learning_rate": 1e-05,
"loss": 0.9366,
"step": 458
},
{
"epoch": 0.48,
"learning_rate": 1e-05,
"loss": 0.9492,
"step": 459
},
{
"epoch": 0.48,
"learning_rate": 1e-05,
"loss": 0.9956,
"step": 460
},
{
"epoch": 0.48,
"learning_rate": 1e-05,
"loss": 0.9625,
"step": 461
},
{
"epoch": 0.48,
"learning_rate": 1e-05,
"loss": 0.9146,
"step": 462
},
{
"epoch": 0.48,
"learning_rate": 1e-05,
"loss": 0.9767,
"step": 463
},
{
"epoch": 0.48,
"learning_rate": 1e-05,
"loss": 0.9612,
"step": 464
},
{
"epoch": 0.48,
"learning_rate": 1e-05,
"loss": 0.992,
"step": 465
},
{
"epoch": 0.49,
"learning_rate": 1e-05,
"loss": 0.9644,
"step": 466
},
{
"epoch": 0.49,
"learning_rate": 1e-05,
"loss": 0.9097,
"step": 467
},
{
"epoch": 0.49,
"learning_rate": 1e-05,
"loss": 0.9477,
"step": 468
},
{
"epoch": 0.49,
"learning_rate": 1e-05,
"loss": 0.9671,
"step": 469
},
{
"epoch": 0.49,
"learning_rate": 1e-05,
"loss": 0.9971,
"step": 470
},
{
"epoch": 0.49,
"learning_rate": 1e-05,
"loss": 0.9939,
"step": 471
},
{
"epoch": 0.49,
"learning_rate": 1e-05,
"loss": 0.9472,
"step": 472
},
{
"epoch": 0.49,
"learning_rate": 1e-05,
"loss": 0.9817,
"step": 473
},
{
"epoch": 0.49,
"learning_rate": 1e-05,
"loss": 1.0082,
"step": 474
},
{
"epoch": 0.49,
"learning_rate": 1e-05,
"loss": 0.9859,
"step": 475
},
{
"epoch": 0.5,
"learning_rate": 1e-05,
"loss": 0.9696,
"step": 476
},
{
"epoch": 0.5,
"learning_rate": 1e-05,
"loss": 0.9433,
"step": 477
},
{
"epoch": 0.5,
"learning_rate": 1e-05,
"loss": 1.0012,
"step": 478
},
{
"epoch": 0.5,
"learning_rate": 1e-05,
"loss": 0.9384,
"step": 479
},
{
"epoch": 0.5,
"learning_rate": 1e-05,
"loss": 0.9514,
"step": 480
},
{
"epoch": 0.5,
"learning_rate": 1e-05,
"loss": 0.9709,
"step": 481
},
{
"epoch": 0.5,
"learning_rate": 1e-05,
"loss": 0.9696,
"step": 482
},
{
"epoch": 0.5,
"learning_rate": 1e-05,
"loss": 0.9857,
"step": 483
},
{
"epoch": 0.5,
"learning_rate": 1e-05,
"loss": 0.9572,
"step": 484
},
{
"epoch": 0.5,
"learning_rate": 1e-05,
"loss": 0.9296,
"step": 485
},
{
"epoch": 0.51,
"learning_rate": 1e-05,
"loss": 1.0209,
"step": 486
},
{
"epoch": 0.51,
"learning_rate": 1e-05,
"loss": 0.9674,
"step": 487
},
{
"epoch": 0.51,
"learning_rate": 1e-05,
"loss": 0.9613,
"step": 488
},
{
"epoch": 0.51,
"learning_rate": 1e-05,
"loss": 0.9458,
"step": 489
},
{
"epoch": 0.51,
"learning_rate": 1e-05,
"loss": 0.9964,
"step": 490
},
{
"epoch": 0.51,
"learning_rate": 1e-05,
"loss": 0.9724,
"step": 491
},
{
"epoch": 0.51,
"learning_rate": 1e-05,
"loss": 0.9573,
"step": 492
},
{
"epoch": 0.51,
"learning_rate": 1e-05,
"loss": 0.9417,
"step": 493
},
{
"epoch": 0.51,
"learning_rate": 1e-05,
"loss": 1.0275,
"step": 494
},
{
"epoch": 0.52,
"learning_rate": 1e-05,
"loss": 0.9586,
"step": 495
},
{
"epoch": 0.52,
"learning_rate": 1e-05,
"loss": 0.9532,
"step": 496
},
{
"epoch": 0.52,
"learning_rate": 1e-05,
"loss": 0.979,
"step": 497
},
{
"epoch": 0.52,
"learning_rate": 1e-05,
"loss": 0.9598,
"step": 498
},
{
"epoch": 0.52,
"learning_rate": 1e-05,
"loss": 0.95,
"step": 499
},
{
"epoch": 0.52,
"learning_rate": 1e-05,
"loss": 0.9544,
"step": 500
},
{
"epoch": 0.52,
"eval_val_accuracy": 0.6228333333333333,
"eval_val_loss": 1.0580956935882568,
"eval_val_runtime": 905.1466,
"eval_val_samples_per_second": 1.105,
"eval_val_steps_per_second": 0.138,
"step": 500
},
{
"epoch": 0.52,
"learning_rate": 1e-05,
"loss": 1.0475,
"step": 501
},
{
"epoch": 0.52,
"learning_rate": 1e-05,
"loss": 0.9581,
"step": 502
},
{
"epoch": 0.52,
"learning_rate": 1e-05,
"loss": 0.9469,
"step": 503
},
{
"epoch": 0.52,
"learning_rate": 1e-05,
"loss": 0.9878,
"step": 504
},
{
"epoch": 0.53,
"learning_rate": 1e-05,
"loss": 0.9809,
"step": 505
},
{
"epoch": 0.53,
"learning_rate": 1e-05,
"loss": 0.9931,
"step": 506
},
{
"epoch": 0.53,
"learning_rate": 1e-05,
"loss": 0.9174,
"step": 507
},
{
"epoch": 0.53,
"learning_rate": 1e-05,
"loss": 0.9835,
"step": 508
},
{
"epoch": 0.53,
"learning_rate": 1e-05,
"loss": 0.9774,
"step": 509
},
{
"epoch": 0.53,
"learning_rate": 1e-05,
"loss": 0.978,
"step": 510
},
{
"epoch": 0.53,
"learning_rate": 1e-05,
"loss": 1.0193,
"step": 511
},
{
"epoch": 0.53,
"learning_rate": 1e-05,
"loss": 0.9259,
"step": 512
},
{
"epoch": 0.53,
"learning_rate": 1e-05,
"loss": 0.9589,
"step": 513
},
{
"epoch": 0.54,
"learning_rate": 1e-05,
"loss": 0.9863,
"step": 514
},
{
"epoch": 0.54,
"learning_rate": 1e-05,
"loss": 0.9849,
"step": 515
},
{
"epoch": 0.54,
"learning_rate": 1e-05,
"loss": 0.9962,
"step": 516
},
{
"epoch": 0.54,
"learning_rate": 1e-05,
"loss": 1.0303,
"step": 517
},
{
"epoch": 0.54,
"learning_rate": 1e-05,
"loss": 0.955,
"step": 518
},
{
"epoch": 0.54,
"learning_rate": 1e-05,
"loss": 0.9303,
"step": 519
},
{
"epoch": 0.54,
"learning_rate": 1e-05,
"loss": 0.9984,
"step": 520
},
{
"epoch": 0.54,
"learning_rate": 1e-05,
"loss": 0.983,
"step": 521
},
{
"epoch": 0.54,
"learning_rate": 1e-05,
"loss": 0.9693,
"step": 522
},
{
"epoch": 0.54,
"learning_rate": 1e-05,
"loss": 0.9412,
"step": 523
},
{
"epoch": 0.55,
"learning_rate": 1e-05,
"loss": 0.9857,
"step": 524
},
{
"epoch": 0.55,
"learning_rate": 1e-05,
"loss": 0.9433,
"step": 525
},
{
"epoch": 0.55,
"learning_rate": 1e-05,
"loss": 0.93,
"step": 526
},
{
"epoch": 0.55,
"learning_rate": 1e-05,
"loss": 0.9552,
"step": 527
},
{
"epoch": 0.55,
"learning_rate": 1e-05,
"loss": 0.9732,
"step": 528
},
{
"epoch": 0.55,
"learning_rate": 1e-05,
"loss": 0.9607,
"step": 529
},
{
"epoch": 0.55,
"learning_rate": 1e-05,
"loss": 0.9272,
"step": 530
},
{
"epoch": 0.55,
"learning_rate": 1e-05,
"loss": 0.994,
"step": 531
},
{
"epoch": 0.55,
"learning_rate": 1e-05,
"loss": 0.997,
"step": 532
},
{
"epoch": 0.55,
"learning_rate": 1e-05,
"loss": 0.9765,
"step": 533
},
{
"epoch": 0.56,
"learning_rate": 1e-05,
"loss": 0.9352,
"step": 534
},
{
"epoch": 0.56,
"learning_rate": 1e-05,
"loss": 1.0216,
"step": 535
},
{
"epoch": 0.56,
"learning_rate": 1e-05,
"loss": 0.9468,
"step": 536
},
{
"epoch": 0.56,
"learning_rate": 1e-05,
"loss": 0.9694,
"step": 537
},
{
"epoch": 0.56,
"learning_rate": 1e-05,
"loss": 0.9532,
"step": 538
},
{
"epoch": 0.56,
"learning_rate": 1e-05,
"loss": 0.9131,
"step": 539
},
{
"epoch": 0.56,
"learning_rate": 1e-05,
"loss": 1.017,
"step": 540
},
{
"epoch": 0.56,
"learning_rate": 1e-05,
"loss": 0.9356,
"step": 541
},
{
"epoch": 0.56,
"learning_rate": 1e-05,
"loss": 0.9673,
"step": 542
},
{
"epoch": 0.57,
"learning_rate": 1e-05,
"loss": 0.9573,
"step": 543
},
{
"epoch": 0.57,
"learning_rate": 1e-05,
"loss": 0.9472,
"step": 544
},
{
"epoch": 0.57,
"learning_rate": 1e-05,
"loss": 0.9883,
"step": 545
},
{
"epoch": 0.57,
"learning_rate": 1e-05,
"loss": 0.9956,
"step": 546
},
{
"epoch": 0.57,
"learning_rate": 1e-05,
"loss": 0.9234,
"step": 547
},
{
"epoch": 0.57,
"learning_rate": 1e-05,
"loss": 0.971,
"step": 548
},
{
"epoch": 0.57,
"learning_rate": 1e-05,
"loss": 0.9854,
"step": 549
},
{
"epoch": 0.57,
"learning_rate": 1e-05,
"loss": 0.9471,
"step": 550
},
{
"epoch": 0.57,
"eval_val_accuracy": 0.6206666666666666,
"eval_val_loss": 1.0513691902160645,
"eval_val_runtime": 904.4909,
"eval_val_samples_per_second": 1.106,
"eval_val_steps_per_second": 0.138,
"step": 550
},
{
"epoch": 0.57,
"learning_rate": 1e-05,
"loss": 0.9958,
"step": 551
},
{
"epoch": 0.57,
"learning_rate": 1e-05,
"loss": 0.9491,
"step": 552
},
{
"epoch": 0.58,
"learning_rate": 1e-05,
"loss": 0.9851,
"step": 553
},
{
"epoch": 0.58,
"learning_rate": 1e-05,
"loss": 0.9735,
"step": 554
},
{
"epoch": 0.58,
"learning_rate": 1e-05,
"loss": 0.9548,
"step": 555
},
{
"epoch": 0.58,
"learning_rate": 1e-05,
"loss": 0.9787,
"step": 556
},
{
"epoch": 0.58,
"learning_rate": 1e-05,
"loss": 1.0088,
"step": 557
},
{
"epoch": 0.58,
"learning_rate": 1e-05,
"loss": 0.9727,
"step": 558
},
{
"epoch": 0.58,
"learning_rate": 1e-05,
"loss": 0.9834,
"step": 559
},
{
"epoch": 0.58,
"learning_rate": 1e-05,
"loss": 0.9348,
"step": 560
},
{
"epoch": 0.58,
"learning_rate": 1e-05,
"loss": 0.9432,
"step": 561
},
{
"epoch": 0.59,
"learning_rate": 1e-05,
"loss": 0.9581,
"step": 562
},
{
"epoch": 0.59,
"learning_rate": 1e-05,
"loss": 0.9728,
"step": 563
},
{
"epoch": 0.59,
"learning_rate": 1e-05,
"loss": 1.0173,
"step": 564
},
{
"epoch": 0.59,
"learning_rate": 1e-05,
"loss": 0.9541,
"step": 565
},
{
"epoch": 0.59,
"learning_rate": 1e-05,
"loss": 1.0142,
"step": 566
},
{
"epoch": 0.59,
"learning_rate": 1e-05,
"loss": 1.021,
"step": 567
},
{
"epoch": 0.59,
"learning_rate": 1e-05,
"loss": 0.9934,
"step": 568
},
{
"epoch": 0.59,
"learning_rate": 1e-05,
"loss": 0.9692,
"step": 569
},
{
"epoch": 0.59,
"learning_rate": 1e-05,
"loss": 0.9979,
"step": 570
},
{
"epoch": 0.59,
"learning_rate": 1e-05,
"loss": 1.0031,
"step": 571
},
{
"epoch": 0.6,
"learning_rate": 1e-05,
"loss": 0.9836,
"step": 572
},
{
"epoch": 0.6,
"learning_rate": 1e-05,
"loss": 0.9701,
"step": 573
},
{
"epoch": 0.6,
"learning_rate": 1e-05,
"loss": 0.9289,
"step": 574
},
{
"epoch": 0.6,
"learning_rate": 1e-05,
"loss": 0.9135,
"step": 575
},
{
"epoch": 0.6,
"learning_rate": 1e-05,
"loss": 0.9226,
"step": 576
},
{
"epoch": 0.6,
"learning_rate": 1e-05,
"loss": 1.0005,
"step": 577
},
{
"epoch": 0.6,
"learning_rate": 1e-05,
"loss": 1.0153,
"step": 578
},
{
"epoch": 0.6,
"learning_rate": 1e-05,
"loss": 0.9625,
"step": 579
},
{
"epoch": 0.6,
"learning_rate": 1e-05,
"loss": 1.0364,
"step": 580
},
{
"epoch": 0.6,
"learning_rate": 1e-05,
"loss": 0.9613,
"step": 581
},
{
"epoch": 0.61,
"learning_rate": 1e-05,
"loss": 0.9285,
"step": 582
},
{
"epoch": 0.61,
"learning_rate": 1e-05,
"loss": 0.9561,
"step": 583
},
{
"epoch": 0.61,
"learning_rate": 1e-05,
"loss": 0.9584,
"step": 584
},
{
"epoch": 0.61,
"learning_rate": 1e-05,
"loss": 0.9744,
"step": 585
},
{
"epoch": 0.61,
"learning_rate": 1e-05,
"loss": 0.9739,
"step": 586
},
{
"epoch": 0.61,
"learning_rate": 1e-05,
"loss": 0.9664,
"step": 587
},
{
"epoch": 0.61,
"learning_rate": 1e-05,
"loss": 0.9662,
"step": 588
},
{
"epoch": 0.61,
"learning_rate": 1e-05,
"loss": 0.9938,
"step": 589
},
{
"epoch": 0.61,
"learning_rate": 1e-05,
"loss": 0.9287,
"step": 590
},
{
"epoch": 0.62,
"learning_rate": 1e-05,
"loss": 0.9549,
"step": 591
},
{
"epoch": 0.62,
"learning_rate": 1e-05,
"loss": 0.9885,
"step": 592
},
{
"epoch": 0.62,
"learning_rate": 1e-05,
"loss": 0.955,
"step": 593
},
{
"epoch": 0.62,
"learning_rate": 1e-05,
"loss": 0.967,
"step": 594
},
{
"epoch": 0.62,
"learning_rate": 1e-05,
"loss": 0.9143,
"step": 595
},
{
"epoch": 0.62,
"learning_rate": 1e-05,
"loss": 0.9997,
"step": 596
},
{
"epoch": 0.62,
"learning_rate": 1e-05,
"loss": 0.9506,
"step": 597
},
{
"epoch": 0.62,
"learning_rate": 1e-05,
"loss": 1.0507,
"step": 598
},
{
"epoch": 0.62,
"learning_rate": 1e-05,
"loss": 0.9492,
"step": 599
},
{
"epoch": 0.62,
"learning_rate": 1e-05,
"loss": 0.9629,
"step": 600
},
{
"epoch": 0.62,
"eval_val_accuracy": 0.6141666666666666,
"eval_val_loss": 1.0531094074249268,
"eval_val_runtime": 904.5104,
"eval_val_samples_per_second": 1.106,
"eval_val_steps_per_second": 0.138,
"step": 600
},
{
"epoch": 0.63,
"learning_rate": 1e-05,
"loss": 0.9857,
"step": 601
},
{
"epoch": 0.63,
"learning_rate": 1e-05,
"loss": 0.9886,
"step": 602
},
{
"epoch": 0.63,
"learning_rate": 1e-05,
"loss": 0.9898,
"step": 603
},
{
"epoch": 0.63,
"learning_rate": 1e-05,
"loss": 0.925,
"step": 604
},
{
"epoch": 0.63,
"learning_rate": 1e-05,
"loss": 0.9068,
"step": 605
},
{
"epoch": 0.63,
"learning_rate": 1e-05,
"loss": 0.9958,
"step": 606
},
{
"epoch": 0.63,
"learning_rate": 1e-05,
"loss": 0.9036,
"step": 607
},
{
"epoch": 0.63,
"learning_rate": 1e-05,
"loss": 0.9981,
"step": 608
},
{
"epoch": 0.63,
"learning_rate": 1e-05,
"loss": 0.9873,
"step": 609
},
{
"epoch": 0.64,
"learning_rate": 1e-05,
"loss": 0.9963,
"step": 610
},
{
"epoch": 0.64,
"learning_rate": 1e-05,
"loss": 0.9671,
"step": 611
},
{
"epoch": 0.64,
"learning_rate": 1e-05,
"loss": 0.9984,
"step": 612
},
{
"epoch": 0.64,
"learning_rate": 1e-05,
"loss": 0.9496,
"step": 613
},
{
"epoch": 0.64,
"learning_rate": 1e-05,
"loss": 0.961,
"step": 614
},
{
"epoch": 0.64,
"learning_rate": 1e-05,
"loss": 0.9723,
"step": 615
},
{
"epoch": 0.64,
"learning_rate": 1e-05,
"loss": 0.9951,
"step": 616
},
{
"epoch": 0.64,
"learning_rate": 1e-05,
"loss": 0.9422,
"step": 617
},
{
"epoch": 0.64,
"learning_rate": 1e-05,
"loss": 0.9832,
"step": 618
},
{
"epoch": 0.64,
"learning_rate": 1e-05,
"loss": 0.9792,
"step": 619
},
{
"epoch": 0.65,
"learning_rate": 1e-05,
"loss": 0.9742,
"step": 620
},
{
"epoch": 0.65,
"learning_rate": 1e-05,
"loss": 0.975,
"step": 621
},
{
"epoch": 0.65,
"learning_rate": 1e-05,
"loss": 1.0171,
"step": 622
},
{
"epoch": 0.65,
"learning_rate": 1e-05,
"loss": 0.9126,
"step": 623
},
{
"epoch": 0.65,
"learning_rate": 1e-05,
"loss": 0.9729,
"step": 624
},
{
"epoch": 0.65,
"learning_rate": 1e-05,
"loss": 0.9259,
"step": 625
},
{
"epoch": 0.65,
"learning_rate": 1e-05,
"loss": 1.037,
"step": 626
},
{
"epoch": 0.65,
"learning_rate": 1e-05,
"loss": 0.9489,
"step": 627
},
{
"epoch": 0.65,
"learning_rate": 1e-05,
"loss": 0.937,
"step": 628
},
{
"epoch": 0.65,
"learning_rate": 1e-05,
"loss": 1.0059,
"step": 629
},
{
"epoch": 0.66,
"learning_rate": 1e-05,
"loss": 1.0169,
"step": 630
},
{
"epoch": 0.66,
"learning_rate": 1e-05,
"loss": 0.952,
"step": 631
},
{
"epoch": 0.66,
"learning_rate": 1e-05,
"loss": 0.9882,
"step": 632
},
{
"epoch": 0.66,
"learning_rate": 1e-05,
"loss": 0.9361,
"step": 633
},
{
"epoch": 0.66,
"learning_rate": 1e-05,
"loss": 0.963,
"step": 634
},
{
"epoch": 0.66,
"learning_rate": 1e-05,
"loss": 0.9822,
"step": 635
},
{
"epoch": 0.66,
"learning_rate": 1e-05,
"loss": 0.9746,
"step": 636
},
{
"epoch": 0.66,
"learning_rate": 1e-05,
"loss": 0.966,
"step": 637
},
{
"epoch": 0.66,
"learning_rate": 1e-05,
"loss": 0.9303,
"step": 638
},
{
"epoch": 0.67,
"learning_rate": 1e-05,
"loss": 0.9507,
"step": 639
},
{
"epoch": 0.67,
"learning_rate": 1e-05,
"loss": 0.9927,
"step": 640
},
{
"epoch": 0.67,
"learning_rate": 1e-05,
"loss": 0.9693,
"step": 641
},
{
"epoch": 0.67,
"learning_rate": 1e-05,
"loss": 0.9611,
"step": 642
},
{
"epoch": 0.67,
"learning_rate": 1e-05,
"loss": 0.9868,
"step": 643
},
{
"epoch": 0.67,
"learning_rate": 1e-05,
"loss": 0.9299,
"step": 644
},
{
"epoch": 0.67,
"learning_rate": 1e-05,
"loss": 1.0052,
"step": 645
},
{
"epoch": 0.67,
"learning_rate": 1e-05,
"loss": 0.961,
"step": 646
},
{
"epoch": 0.67,
"learning_rate": 1e-05,
"loss": 0.9739,
"step": 647
},
{
"epoch": 0.67,
"learning_rate": 1e-05,
"loss": 0.9625,
"step": 648
},
{
"epoch": 0.68,
"learning_rate": 1e-05,
"loss": 0.9993,
"step": 649
},
{
"epoch": 0.68,
"learning_rate": 1e-05,
"loss": 0.9742,
"step": 650
},
{
"epoch": 0.68,
"eval_val_accuracy": 0.6171666666666666,
"eval_val_loss": 1.0519297122955322,
"eval_val_runtime": 904.949,
"eval_val_samples_per_second": 1.105,
"eval_val_steps_per_second": 0.138,
"step": 650
},
{
"epoch": 0.68,
"learning_rate": 1e-05,
"loss": 0.9833,
"step": 651
},
{
"epoch": 0.68,
"learning_rate": 1e-05,
"loss": 1.0026,
"step": 652
},
{
"epoch": 0.68,
"learning_rate": 1e-05,
"loss": 0.975,
"step": 653
},
{
"epoch": 0.68,
"learning_rate": 1e-05,
"loss": 0.9832,
"step": 654
},
{
"epoch": 0.68,
"learning_rate": 1e-05,
"loss": 1.0068,
"step": 655
},
{
"epoch": 0.68,
"learning_rate": 1e-05,
"loss": 0.9977,
"step": 656
},
{
"epoch": 0.68,
"learning_rate": 1e-05,
"loss": 1.0076,
"step": 657
},
{
"epoch": 0.68,
"learning_rate": 1e-05,
"loss": 0.9801,
"step": 658
},
{
"epoch": 0.69,
"learning_rate": 1e-05,
"loss": 1.001,
"step": 659
},
{
"epoch": 0.69,
"learning_rate": 1e-05,
"loss": 0.9578,
"step": 660
},
{
"epoch": 0.69,
"learning_rate": 1e-05,
"loss": 0.9078,
"step": 661
},
{
"epoch": 0.69,
"learning_rate": 1e-05,
"loss": 0.9509,
"step": 662
},
{
"epoch": 0.69,
"learning_rate": 1e-05,
"loss": 1.0073,
"step": 663
},
{
"epoch": 0.69,
"learning_rate": 1e-05,
"loss": 0.9515,
"step": 664
},
{
"epoch": 0.69,
"learning_rate": 1e-05,
"loss": 0.9781,
"step": 665
},
{
"epoch": 0.69,
"learning_rate": 1e-05,
"loss": 0.9942,
"step": 666
},
{
"epoch": 0.69,
"learning_rate": 1e-05,
"loss": 0.9915,
"step": 667
},
{
"epoch": 0.7,
"learning_rate": 1e-05,
"loss": 0.9366,
"step": 668
},
{
"epoch": 0.7,
"learning_rate": 1e-05,
"loss": 0.9966,
"step": 669
},
{
"epoch": 0.7,
"learning_rate": 1e-05,
"loss": 0.9971,
"step": 670
},
{
"epoch": 0.7,
"learning_rate": 1e-05,
"loss": 0.9982,
"step": 671
},
{
"epoch": 0.7,
"learning_rate": 1e-05,
"loss": 0.9739,
"step": 672
},
{
"epoch": 0.7,
"learning_rate": 1e-05,
"loss": 0.9667,
"step": 673
},
{
"epoch": 0.7,
"learning_rate": 1e-05,
"loss": 0.9501,
"step": 674
},
{
"epoch": 0.7,
"learning_rate": 1e-05,
"loss": 0.9503,
"step": 675
},
{
"epoch": 0.7,
"learning_rate": 1e-05,
"loss": 0.9912,
"step": 676
},
{
"epoch": 0.7,
"learning_rate": 1e-05,
"loss": 0.9387,
"step": 677
},
{
"epoch": 0.71,
"learning_rate": 1e-05,
"loss": 0.9116,
"step": 678
},
{
"epoch": 0.71,
"learning_rate": 1e-05,
"loss": 0.9936,
"step": 679
},
{
"epoch": 0.71,
"learning_rate": 1e-05,
"loss": 0.9653,
"step": 680
},
{
"epoch": 0.71,
"learning_rate": 1e-05,
"loss": 0.9474,
"step": 681
},
{
"epoch": 0.71,
"learning_rate": 1e-05,
"loss": 0.9737,
"step": 682
},
{
"epoch": 0.71,
"learning_rate": 1e-05,
"loss": 0.9769,
"step": 683
},
{
"epoch": 0.71,
"learning_rate": 1e-05,
"loss": 0.9874,
"step": 684
},
{
"epoch": 0.71,
"learning_rate": 1e-05,
"loss": 0.9332,
"step": 685
},
{
"epoch": 0.71,
"learning_rate": 1e-05,
"loss": 0.9686,
"step": 686
},
{
"epoch": 0.72,
"learning_rate": 1e-05,
"loss": 0.9706,
"step": 687
},
{
"epoch": 0.72,
"learning_rate": 1e-05,
"loss": 0.9703,
"step": 688
},
{
"epoch": 0.72,
"learning_rate": 1e-05,
"loss": 0.9746,
"step": 689
},
{
"epoch": 0.72,
"learning_rate": 1e-05,
"loss": 0.9607,
"step": 690
},
{
"epoch": 0.72,
"learning_rate": 1e-05,
"loss": 0.9543,
"step": 691
},
{
"epoch": 0.72,
"learning_rate": 1e-05,
"loss": 0.9667,
"step": 692
},
{
"epoch": 0.72,
"learning_rate": 1e-05,
"loss": 0.9366,
"step": 693
},
{
"epoch": 0.72,
"learning_rate": 1e-05,
"loss": 0.974,
"step": 694
},
{
"epoch": 0.72,
"learning_rate": 1e-05,
"loss": 0.994,
"step": 695
},
{
"epoch": 0.72,
"learning_rate": 1e-05,
"loss": 1.0005,
"step": 696
},
{
"epoch": 0.73,
"learning_rate": 1e-05,
"loss": 0.9076,
"step": 697
},
{
"epoch": 0.73,
"learning_rate": 1e-05,
"loss": 0.9653,
"step": 698
},
{
"epoch": 0.73,
"learning_rate": 1e-05,
"loss": 0.9189,
"step": 699
},
{
"epoch": 0.73,
"learning_rate": 1e-05,
"loss": 0.9946,
"step": 700
},
{
"epoch": 0.73,
"eval_val_accuracy": 0.6118333333333333,
"eval_val_loss": 1.0596308708190918,
"eval_val_runtime": 904.3023,
"eval_val_samples_per_second": 1.106,
"eval_val_steps_per_second": 0.138,
"step": 700
},
{
"epoch": 0.73,
"learning_rate": 1e-05,
"loss": 0.9833,
"step": 701
},
{
"epoch": 0.73,
"learning_rate": 1e-05,
"loss": 1.0002,
"step": 702
},
{
"epoch": 0.73,
"learning_rate": 1e-05,
"loss": 0.951,
"step": 703
},
{
"epoch": 0.73,
"learning_rate": 1e-05,
"loss": 0.9562,
"step": 704
},
{
"epoch": 0.73,
"learning_rate": 1e-05,
"loss": 0.9742,
"step": 705
},
{
"epoch": 0.73,
"learning_rate": 1e-05,
"loss": 0.9855,
"step": 706
},
{
"epoch": 0.74,
"learning_rate": 1e-05,
"loss": 0.942,
"step": 707
},
{
"epoch": 0.74,
"learning_rate": 1e-05,
"loss": 0.9907,
"step": 708
},
{
"epoch": 0.74,
"learning_rate": 1e-05,
"loss": 1.0228,
"step": 709
},
{
"epoch": 0.74,
"learning_rate": 1e-05,
"loss": 0.9461,
"step": 710
},
{
"epoch": 0.74,
"learning_rate": 1e-05,
"loss": 0.9462,
"step": 711
},
{
"epoch": 0.74,
"learning_rate": 1e-05,
"loss": 0.8869,
"step": 712
},
{
"epoch": 0.74,
"learning_rate": 1e-05,
"loss": 0.9543,
"step": 713
},
{
"epoch": 0.74,
"learning_rate": 1e-05,
"loss": 0.993,
"step": 714
},
{
"epoch": 0.74,
"learning_rate": 1e-05,
"loss": 0.9302,
"step": 715
},
{
"epoch": 0.75,
"learning_rate": 1e-05,
"loss": 1.045,
"step": 716
},
{
"epoch": 0.75,
"learning_rate": 1e-05,
"loss": 0.9636,
"step": 717
},
{
"epoch": 0.75,
"learning_rate": 1e-05,
"loss": 0.92,
"step": 718
},
{
"epoch": 0.75,
"learning_rate": 1e-05,
"loss": 0.9985,
"step": 719
},
{
"epoch": 0.75,
"learning_rate": 1e-05,
"loss": 0.9946,
"step": 720
},
{
"epoch": 0.75,
"learning_rate": 1e-05,
"loss": 0.9762,
"step": 721
},
{
"epoch": 0.75,
"learning_rate": 1e-05,
"loss": 0.9889,
"step": 722
},
{
"epoch": 0.75,
"learning_rate": 1e-05,
"loss": 0.9953,
"step": 723
},
{
"epoch": 0.75,
"learning_rate": 1e-05,
"loss": 0.9753,
"step": 724
},
{
"epoch": 0.75,
"learning_rate": 1e-05,
"loss": 0.9366,
"step": 725
},
{
"epoch": 0.76,
"learning_rate": 1e-05,
"loss": 1.021,
"step": 726
},
{
"epoch": 0.76,
"learning_rate": 1e-05,
"loss": 0.9809,
"step": 727
},
{
"epoch": 0.76,
"learning_rate": 1e-05,
"loss": 0.9644,
"step": 728
},
{
"epoch": 0.76,
"learning_rate": 1e-05,
"loss": 1.0002,
"step": 729
},
{
"epoch": 0.76,
"learning_rate": 1e-05,
"loss": 1.0045,
"step": 730
},
{
"epoch": 0.76,
"learning_rate": 1e-05,
"loss": 0.9519,
"step": 731
},
{
"epoch": 0.76,
"learning_rate": 1e-05,
"loss": 1.0066,
"step": 732
},
{
"epoch": 0.76,
"learning_rate": 1e-05,
"loss": 0.9723,
"step": 733
},
{
"epoch": 0.76,
"learning_rate": 1e-05,
"loss": 0.9447,
"step": 734
},
{
"epoch": 0.77,
"learning_rate": 1e-05,
"loss": 1.0052,
"step": 735
},
{
"epoch": 0.77,
"learning_rate": 1e-05,
"loss": 0.9309,
"step": 736
},
{
"epoch": 0.77,
"learning_rate": 1e-05,
"loss": 1.03,
"step": 737
},
{
"epoch": 0.77,
"learning_rate": 1e-05,
"loss": 1.0368,
"step": 738
},
{
"epoch": 0.77,
"learning_rate": 1e-05,
"loss": 1.0325,
"step": 739
},
{
"epoch": 0.77,
"learning_rate": 1e-05,
"loss": 0.975,
"step": 740
},
{
"epoch": 0.77,
"learning_rate": 1e-05,
"loss": 0.9406,
"step": 741
},
{
"epoch": 0.77,
"learning_rate": 1e-05,
"loss": 0.9795,
"step": 742
},
{
"epoch": 0.77,
"learning_rate": 1e-05,
"loss": 0.9628,
"step": 743
},
{
"epoch": 0.77,
"learning_rate": 1e-05,
"loss": 0.9707,
"step": 744
},
{
"epoch": 0.78,
"learning_rate": 1e-05,
"loss": 1.0462,
"step": 745
},
{
"epoch": 0.78,
"learning_rate": 1e-05,
"loss": 0.9723,
"step": 746
},
{
"epoch": 0.78,
"learning_rate": 1e-05,
"loss": 1.0194,
"step": 747
},
{
"epoch": 0.78,
"learning_rate": 1e-05,
"loss": 1.0038,
"step": 748
},
{
"epoch": 0.78,
"learning_rate": 1e-05,
"loss": 0.9149,
"step": 749
},
{
"epoch": 0.78,
"learning_rate": 1e-05,
"loss": 1.0181,
"step": 750
},
{
"epoch": 0.78,
"eval_val_accuracy": 0.608,
"eval_val_loss": 1.0550117492675781,
"eval_val_runtime": 904.5982,
"eval_val_samples_per_second": 1.105,
"eval_val_steps_per_second": 0.138,
"step": 750
},
{
"epoch": 0.78,
"learning_rate": 1e-05,
"loss": 0.9871,
"step": 751
},
{
"epoch": 0.78,
"learning_rate": 1e-05,
"loss": 0.9801,
"step": 752
},
{
"epoch": 0.78,
"learning_rate": 1e-05,
"loss": 0.9612,
"step": 753
},
{
"epoch": 0.78,
"learning_rate": 1e-05,
"loss": 0.9322,
"step": 754
},
{
"epoch": 0.79,
"learning_rate": 1e-05,
"loss": 0.9503,
"step": 755
},
{
"epoch": 0.79,
"learning_rate": 1e-05,
"loss": 0.9504,
"step": 756
},
{
"epoch": 0.79,
"learning_rate": 1e-05,
"loss": 0.9818,
"step": 757
},
{
"epoch": 0.79,
"learning_rate": 1e-05,
"loss": 0.9809,
"step": 758
},
{
"epoch": 0.79,
"learning_rate": 1e-05,
"loss": 0.9915,
"step": 759
},
{
"epoch": 0.79,
"learning_rate": 1e-05,
"loss": 0.9752,
"step": 760
},
{
"epoch": 0.79,
"learning_rate": 1e-05,
"loss": 0.9669,
"step": 761
},
{
"epoch": 0.79,
"learning_rate": 1e-05,
"loss": 1.0111,
"step": 762
},
{
"epoch": 0.79,
"learning_rate": 1e-05,
"loss": 0.929,
"step": 763
},
{
"epoch": 0.8,
"learning_rate": 1e-05,
"loss": 1.0079,
"step": 764
},
{
"epoch": 0.8,
"learning_rate": 1e-05,
"loss": 0.9454,
"step": 765
},
{
"epoch": 0.8,
"learning_rate": 1e-05,
"loss": 1.0133,
"step": 766
},
{
"epoch": 0.8,
"learning_rate": 1e-05,
"loss": 0.9691,
"step": 767
},
{
"epoch": 0.8,
"learning_rate": 1e-05,
"loss": 0.9478,
"step": 768
},
{
"epoch": 0.8,
"learning_rate": 1e-05,
"loss": 0.9852,
"step": 769
},
{
"epoch": 0.8,
"learning_rate": 1e-05,
"loss": 0.9884,
"step": 770
},
{
"epoch": 0.8,
"learning_rate": 1e-05,
"loss": 0.9346,
"step": 771
},
{
"epoch": 0.8,
"learning_rate": 1e-05,
"loss": 0.9926,
"step": 772
},
{
"epoch": 0.8,
"learning_rate": 1e-05,
"loss": 0.9691,
"step": 773
},
{
"epoch": 0.81,
"learning_rate": 1e-05,
"loss": 1.0028,
"step": 774
},
{
"epoch": 0.81,
"learning_rate": 1e-05,
"loss": 0.9706,
"step": 775
},
{
"epoch": 0.81,
"learning_rate": 1e-05,
"loss": 1.0258,
"step": 776
},
{
"epoch": 0.81,
"learning_rate": 1e-05,
"loss": 1.0111,
"step": 777
},
{
"epoch": 0.81,
"learning_rate": 1e-05,
"loss": 0.9496,
"step": 778
},
{
"epoch": 0.81,
"learning_rate": 1e-05,
"loss": 0.9753,
"step": 779
},
{
"epoch": 0.81,
"learning_rate": 1e-05,
"loss": 0.9635,
"step": 780
},
{
"epoch": 0.81,
"learning_rate": 1e-05,
"loss": 0.999,
"step": 781
},
{
"epoch": 0.81,
"learning_rate": 1e-05,
"loss": 1.0179,
"step": 782
},
{
"epoch": 0.82,
"learning_rate": 1e-05,
"loss": 0.9676,
"step": 783
},
{
"epoch": 0.82,
"learning_rate": 1e-05,
"loss": 1.0341,
"step": 784
},
{
"epoch": 0.82,
"learning_rate": 1e-05,
"loss": 1.0066,
"step": 785
},
{
"epoch": 0.82,
"learning_rate": 1e-05,
"loss": 1.0282,
"step": 786
},
{
"epoch": 0.82,
"learning_rate": 1e-05,
"loss": 1.0045,
"step": 787
},
{
"epoch": 0.82,
"learning_rate": 1e-05,
"loss": 0.9533,
"step": 788
},
{
"epoch": 0.82,
"learning_rate": 1e-05,
"loss": 1.0035,
"step": 789
},
{
"epoch": 0.82,
"learning_rate": 1e-05,
"loss": 0.9372,
"step": 790
},
{
"epoch": 0.82,
"learning_rate": 1e-05,
"loss": 1.0203,
"step": 791
},
{
"epoch": 0.82,
"learning_rate": 1e-05,
"loss": 0.9933,
"step": 792
},
{
"epoch": 0.83,
"learning_rate": 1e-05,
"loss": 0.9798,
"step": 793
},
{
"epoch": 0.83,
"learning_rate": 1e-05,
"loss": 0.9624,
"step": 794
},
{
"epoch": 0.83,
"learning_rate": 1e-05,
"loss": 1.0192,
"step": 795
},
{
"epoch": 0.83,
"learning_rate": 1e-05,
"loss": 0.9683,
"step": 796
},
{
"epoch": 0.83,
"learning_rate": 1e-05,
"loss": 0.9809,
"step": 797
},
{
"epoch": 0.83,
"learning_rate": 1e-05,
"loss": 1.0397,
"step": 798
},
{
"epoch": 0.83,
"learning_rate": 1e-05,
"loss": 0.9886,
"step": 799
},
{
"epoch": 0.83,
"learning_rate": 1e-05,
"loss": 0.9904,
"step": 800
},
{
"epoch": 0.83,
"eval_val_accuracy": 0.5953333333333334,
"eval_val_loss": 1.050798773765564,
"eval_val_runtime": 904.4369,
"eval_val_samples_per_second": 1.106,
"eval_val_steps_per_second": 0.138,
"step": 800
},
{
"epoch": 0.83,
"learning_rate": 1e-05,
"loss": 0.941,
"step": 801
},
{
"epoch": 0.83,
"learning_rate": 1e-05,
"loss": 0.9543,
"step": 802
},
{
"epoch": 0.84,
"learning_rate": 1e-05,
"loss": 0.9783,
"step": 803
},
{
"epoch": 0.84,
"learning_rate": 1e-05,
"loss": 0.9603,
"step": 804
},
{
"epoch": 0.84,
"learning_rate": 1e-05,
"loss": 0.9458,
"step": 805
},
{
"epoch": 0.84,
"learning_rate": 1e-05,
"loss": 0.9714,
"step": 806
},
{
"epoch": 0.84,
"learning_rate": 1e-05,
"loss": 0.942,
"step": 807
},
{
"epoch": 0.84,
"learning_rate": 1e-05,
"loss": 0.9459,
"step": 808
},
{
"epoch": 0.84,
"learning_rate": 1e-05,
"loss": 0.9504,
"step": 809
},
{
"epoch": 0.84,
"learning_rate": 1e-05,
"loss": 1.0117,
"step": 810
},
{
"epoch": 0.84,
"learning_rate": 1e-05,
"loss": 0.976,
"step": 811
},
{
"epoch": 0.85,
"learning_rate": 1e-05,
"loss": 0.9376,
"step": 812
},
{
"epoch": 0.85,
"learning_rate": 1e-05,
"loss": 0.975,
"step": 813
},
{
"epoch": 0.85,
"learning_rate": 1e-05,
"loss": 0.941,
"step": 814
},
{
"epoch": 0.85,
"learning_rate": 1e-05,
"loss": 0.9337,
"step": 815
},
{
"epoch": 0.85,
"learning_rate": 1e-05,
"loss": 0.9397,
"step": 816
},
{
"epoch": 0.85,
"learning_rate": 1e-05,
"loss": 0.949,
"step": 817
},
{
"epoch": 0.85,
"learning_rate": 1e-05,
"loss": 0.9503,
"step": 818
},
{
"epoch": 0.85,
"learning_rate": 1e-05,
"loss": 0.9631,
"step": 819
},
{
"epoch": 0.85,
"learning_rate": 1e-05,
"loss": 0.9582,
"step": 820
},
{
"epoch": 0.85,
"learning_rate": 1e-05,
"loss": 0.9762,
"step": 821
},
{
"epoch": 0.86,
"learning_rate": 1e-05,
"loss": 0.9581,
"step": 822
},
{
"epoch": 0.86,
"learning_rate": 1e-05,
"loss": 0.9998,
"step": 823
},
{
"epoch": 0.86,
"learning_rate": 1e-05,
"loss": 0.9814,
"step": 824
},
{
"epoch": 0.86,
"learning_rate": 1e-05,
"loss": 0.9546,
"step": 825
},
{
"epoch": 0.86,
"learning_rate": 1e-05,
"loss": 1.0128,
"step": 826
},
{
"epoch": 0.86,
"learning_rate": 1e-05,
"loss": 1.0044,
"step": 827
},
{
"epoch": 0.86,
"learning_rate": 1e-05,
"loss": 0.9734,
"step": 828
},
{
"epoch": 0.86,
"learning_rate": 1e-05,
"loss": 1.0091,
"step": 829
},
{
"epoch": 0.86,
"learning_rate": 1e-05,
"loss": 0.9782,
"step": 830
},
{
"epoch": 0.87,
"learning_rate": 1e-05,
"loss": 0.9747,
"step": 831
},
{
"epoch": 0.87,
"learning_rate": 1e-05,
"loss": 0.9303,
"step": 832
},
{
"epoch": 0.87,
"learning_rate": 1e-05,
"loss": 1.0246,
"step": 833
},
{
"epoch": 0.87,
"learning_rate": 1e-05,
"loss": 1.0,
"step": 834
},
{
"epoch": 0.87,
"learning_rate": 1e-05,
"loss": 0.9484,
"step": 835
},
{
"epoch": 0.87,
"learning_rate": 1e-05,
"loss": 0.9661,
"step": 836
},
{
"epoch": 0.87,
"learning_rate": 1e-05,
"loss": 0.9849,
"step": 837
},
{
"epoch": 0.87,
"learning_rate": 1e-05,
"loss": 1.0212,
"step": 838
},
{
"epoch": 0.87,
"learning_rate": 1e-05,
"loss": 1.0011,
"step": 839
},
{
"epoch": 0.87,
"learning_rate": 1e-05,
"loss": 1.0095,
"step": 840
},
{
"epoch": 0.88,
"learning_rate": 1e-05,
"loss": 0.9702,
"step": 841
},
{
"epoch": 0.88,
"learning_rate": 1e-05,
"loss": 0.9716,
"step": 842
},
{
"epoch": 0.88,
"learning_rate": 1e-05,
"loss": 0.9694,
"step": 843
},
{
"epoch": 0.88,
"learning_rate": 1e-05,
"loss": 0.9333,
"step": 844
},
{
"epoch": 0.88,
"learning_rate": 1e-05,
"loss": 0.9397,
"step": 845
},
{
"epoch": 0.88,
"learning_rate": 1e-05,
"loss": 0.9429,
"step": 846
},
{
"epoch": 0.88,
"learning_rate": 1e-05,
"loss": 0.9868,
"step": 847
},
{
"epoch": 0.88,
"learning_rate": 1e-05,
"loss": 0.951,
"step": 848
},
{
"epoch": 0.88,
"learning_rate": 1e-05,
"loss": 0.9835,
"step": 849
},
{
"epoch": 0.88,
"learning_rate": 1e-05,
"loss": 0.9954,
"step": 850
},
{
"epoch": 0.88,
"eval_val_accuracy": 0.5976666666666667,
"eval_val_loss": 1.0566874742507935,
"eval_val_runtime": 904.0696,
"eval_val_samples_per_second": 1.106,
"eval_val_steps_per_second": 0.138,
"step": 850
},
{
"epoch": 0.89,
"learning_rate": 1e-05,
"loss": 1.017,
"step": 851
},
{
"epoch": 0.89,
"learning_rate": 1e-05,
"loss": 0.9553,
"step": 852
},
{
"epoch": 0.89,
"learning_rate": 1e-05,
"loss": 1.0106,
"step": 853
},
{
"epoch": 0.89,
"learning_rate": 1e-05,
"loss": 0.918,
"step": 854
},
{
"epoch": 0.89,
"learning_rate": 1e-05,
"loss": 0.9538,
"step": 855
},
{
"epoch": 0.89,
"learning_rate": 1e-05,
"loss": 0.9326,
"step": 856
},
{
"epoch": 0.89,
"learning_rate": 1e-05,
"loss": 0.9897,
"step": 857
},
{
"epoch": 0.89,
"learning_rate": 1e-05,
"loss": 0.9297,
"step": 858
},
{
"epoch": 0.89,
"learning_rate": 1e-05,
"loss": 1.0215,
"step": 859
},
{
"epoch": 0.9,
"learning_rate": 1e-05,
"loss": 0.9503,
"step": 860
},
{
"epoch": 0.9,
"learning_rate": 1e-05,
"loss": 0.9823,
"step": 861
},
{
"epoch": 0.9,
"learning_rate": 1e-05,
"loss": 0.9815,
"step": 862
},
{
"epoch": 0.9,
"learning_rate": 1e-05,
"loss": 0.9887,
"step": 863
},
{
"epoch": 0.9,
"learning_rate": 1e-05,
"loss": 0.9911,
"step": 864
},
{
"epoch": 0.9,
"learning_rate": 1e-05,
"loss": 0.9807,
"step": 865
},
{
"epoch": 0.9,
"learning_rate": 1e-05,
"loss": 0.9201,
"step": 866
},
{
"epoch": 0.9,
"learning_rate": 1e-05,
"loss": 0.923,
"step": 867
},
{
"epoch": 0.9,
"learning_rate": 1e-05,
"loss": 0.9777,
"step": 868
},
{
"epoch": 0.9,
"learning_rate": 1e-05,
"loss": 0.9341,
"step": 869
},
{
"epoch": 0.91,
"learning_rate": 1e-05,
"loss": 0.9796,
"step": 870
},
{
"epoch": 0.91,
"learning_rate": 1e-05,
"loss": 1.0324,
"step": 871
},
{
"epoch": 0.91,
"learning_rate": 1e-05,
"loss": 0.9594,
"step": 872
},
{
"epoch": 0.91,
"learning_rate": 1e-05,
"loss": 0.9859,
"step": 873
},
{
"epoch": 0.91,
"learning_rate": 1e-05,
"loss": 0.987,
"step": 874
},
{
"epoch": 0.91,
"learning_rate": 1e-05,
"loss": 0.9794,
"step": 875
},
{
"epoch": 0.91,
"learning_rate": 1e-05,
"loss": 0.9081,
"step": 876
},
{
"epoch": 0.91,
"learning_rate": 1e-05,
"loss": 0.9958,
"step": 877
},
{
"epoch": 0.91,
"learning_rate": 1e-05,
"loss": 1.002,
"step": 878
},
{
"epoch": 0.92,
"learning_rate": 1e-05,
"loss": 0.9767,
"step": 879
},
{
"epoch": 0.92,
"learning_rate": 1e-05,
"loss": 0.9215,
"step": 880
},
{
"epoch": 0.92,
"learning_rate": 1e-05,
"loss": 0.9615,
"step": 881
},
{
"epoch": 0.92,
"learning_rate": 1e-05,
"loss": 0.9993,
"step": 882
},
{
"epoch": 0.92,
"learning_rate": 1e-05,
"loss": 0.9763,
"step": 883
},
{
"epoch": 0.92,
"learning_rate": 1e-05,
"loss": 1.0334,
"step": 884
},
{
"epoch": 0.92,
"learning_rate": 1e-05,
"loss": 0.9357,
"step": 885
},
{
"epoch": 0.92,
"learning_rate": 1e-05,
"loss": 0.9554,
"step": 886
},
{
"epoch": 0.92,
"learning_rate": 1e-05,
"loss": 0.9705,
"step": 887
},
{
"epoch": 0.92,
"learning_rate": 1e-05,
"loss": 0.9872,
"step": 888
},
{
"epoch": 0.93,
"learning_rate": 1e-05,
"loss": 0.9289,
"step": 889
},
{
"epoch": 0.93,
"learning_rate": 1e-05,
"loss": 0.9917,
"step": 890
},
{
"epoch": 0.93,
"learning_rate": 1e-05,
"loss": 0.9909,
"step": 891
},
{
"epoch": 0.93,
"learning_rate": 1e-05,
"loss": 1.013,
"step": 892
},
{
"epoch": 0.93,
"learning_rate": 1e-05,
"loss": 0.9916,
"step": 893
},
{
"epoch": 0.93,
"learning_rate": 1e-05,
"loss": 0.9638,
"step": 894
},
{
"epoch": 0.93,
"learning_rate": 1e-05,
"loss": 0.9642,
"step": 895
},
{
"epoch": 0.93,
"learning_rate": 1e-05,
"loss": 0.9633,
"step": 896
},
{
"epoch": 0.93,
"learning_rate": 1e-05,
"loss": 0.9375,
"step": 897
},
{
"epoch": 0.93,
"learning_rate": 1e-05,
"loss": 1.0361,
"step": 898
},
{
"epoch": 0.94,
"learning_rate": 1e-05,
"loss": 0.9908,
"step": 899
},
{
"epoch": 0.94,
"learning_rate": 1e-05,
"loss": 0.9618,
"step": 900
},
{
"epoch": 0.94,
"eval_val_accuracy": 0.5931666666666666,
"eval_val_loss": 1.0555800199508667,
"eval_val_runtime": 904.3634,
"eval_val_samples_per_second": 1.106,
"eval_val_steps_per_second": 0.138,
"step": 900
}
],
"logging_steps": 1,
"max_steps": 1920,
"num_input_tokens_seen": 0,
"num_train_epochs": 2,
"save_steps": 50,
"total_flos": 0.0,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}