Llama-2-13b-chat-dutch / trainer_state.json
Bram Vanroy
init adapters
280f9ff
{
"best_metric": 1.0847766399383545,
"best_model_checkpoint": "results/llama2-13b-chat-dutch/2e-4lr+64tbs+32a+4r/checkpoint-440",
"epoch": 1.9978189749182116,
"global_step": 458,
"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": 1.4904,
"step": 1
},
{
"epoch": 0.01,
"learning_rate": 5.252990700743872e-05,
"loss": 1.4765,
"step": 2
},
{
"epoch": 0.01,
"learning_rate": 8.325793277315987e-05,
"loss": 1.4205,
"step": 3
},
{
"epoch": 0.02,
"learning_rate": 0.00010505981401487743,
"loss": 1.4166,
"step": 4
},
{
"epoch": 0.02,
"learning_rate": 0.00012197066690239247,
"loss": 1.4086,
"step": 5
},
{
"epoch": 0.03,
"learning_rate": 0.00013578783978059858,
"loss": 1.3382,
"step": 6
},
{
"epoch": 0.03,
"learning_rate": 0.00014747009299256132,
"loss": 1.3148,
"step": 7
},
{
"epoch": 0.03,
"learning_rate": 0.00015758972102231612,
"loss": 1.2409,
"step": 8
},
{
"epoch": 0.04,
"learning_rate": 0.00016651586554631973,
"loss": 1.1946,
"step": 9
},
{
"epoch": 0.04,
"learning_rate": 0.0001745005739098312,
"loss": 1.1482,
"step": 10
},
{
"epoch": 0.05,
"learning_rate": 0.00018172362122561043,
"loss": 1.1234,
"step": 11
},
{
"epoch": 0.05,
"learning_rate": 0.0001883177467880373,
"loss": 1.0852,
"step": 12
},
{
"epoch": 0.06,
"learning_rate": 0.00019438375428058432,
"loss": 1.0612,
"step": 13
},
{
"epoch": 0.06,
"learning_rate": 0.0002,
"loss": 1.0247,
"step": 14
},
{
"epoch": 0.07,
"learning_rate": 0.0002,
"loss": 1.0447,
"step": 15
},
{
"epoch": 0.07,
"learning_rate": 0.0002,
"loss": 1.041,
"step": 16
},
{
"epoch": 0.07,
"learning_rate": 0.0002,
"loss": 1.04,
"step": 17
},
{
"epoch": 0.08,
"learning_rate": 0.0002,
"loss": 1.0725,
"step": 18
},
{
"epoch": 0.08,
"learning_rate": 0.0002,
"loss": 1.029,
"step": 19
},
{
"epoch": 0.09,
"learning_rate": 0.0002,
"loss": 1.0193,
"step": 20
},
{
"epoch": 0.09,
"eval_loss": 1.1583425998687744,
"eval_runtime": 298.1348,
"eval_samples_per_second": 2.113,
"eval_steps_per_second": 0.265,
"step": 20
},
{
"epoch": 0.09,
"learning_rate": 0.0002,
"loss": 0.9944,
"step": 21
},
{
"epoch": 0.1,
"learning_rate": 0.0002,
"loss": 0.9873,
"step": 22
},
{
"epoch": 0.1,
"learning_rate": 0.0002,
"loss": 0.9825,
"step": 23
},
{
"epoch": 0.1,
"learning_rate": 0.0002,
"loss": 0.9769,
"step": 24
},
{
"epoch": 0.11,
"learning_rate": 0.0002,
"loss": 0.9831,
"step": 25
},
{
"epoch": 0.11,
"learning_rate": 0.0002,
"loss": 1.0092,
"step": 26
},
{
"epoch": 0.12,
"learning_rate": 0.0002,
"loss": 0.9596,
"step": 27
},
{
"epoch": 0.12,
"learning_rate": 0.0002,
"loss": 0.9955,
"step": 28
},
{
"epoch": 0.13,
"learning_rate": 0.0002,
"loss": 1.0027,
"step": 29
},
{
"epoch": 0.13,
"learning_rate": 0.0002,
"loss": 1.0067,
"step": 30
},
{
"epoch": 0.14,
"learning_rate": 0.0002,
"loss": 1.0138,
"step": 31
},
{
"epoch": 0.14,
"learning_rate": 0.0002,
"loss": 0.9738,
"step": 32
},
{
"epoch": 0.14,
"learning_rate": 0.0002,
"loss": 0.9592,
"step": 33
},
{
"epoch": 0.15,
"learning_rate": 0.0002,
"loss": 0.9431,
"step": 34
},
{
"epoch": 0.15,
"learning_rate": 0.0002,
"loss": 0.9516,
"step": 35
},
{
"epoch": 0.16,
"learning_rate": 0.0002,
"loss": 0.9499,
"step": 36
},
{
"epoch": 0.16,
"learning_rate": 0.0002,
"loss": 0.944,
"step": 37
},
{
"epoch": 0.17,
"learning_rate": 0.0002,
"loss": 0.9629,
"step": 38
},
{
"epoch": 0.17,
"learning_rate": 0.0002,
"loss": 0.9571,
"step": 39
},
{
"epoch": 0.17,
"learning_rate": 0.0002,
"loss": 0.9743,
"step": 40
},
{
"epoch": 0.17,
"eval_loss": 1.133877158164978,
"eval_runtime": 297.7759,
"eval_samples_per_second": 2.116,
"eval_steps_per_second": 0.265,
"step": 40
},
{
"epoch": 0.18,
"learning_rate": 0.0002,
"loss": 0.9651,
"step": 41
},
{
"epoch": 0.18,
"learning_rate": 0.0002,
"loss": 0.9941,
"step": 42
},
{
"epoch": 0.19,
"learning_rate": 0.0002,
"loss": 0.9723,
"step": 43
},
{
"epoch": 0.19,
"learning_rate": 0.0002,
"loss": 0.9519,
"step": 44
},
{
"epoch": 0.2,
"learning_rate": 0.0002,
"loss": 0.9648,
"step": 45
},
{
"epoch": 0.2,
"learning_rate": 0.0002,
"loss": 0.9492,
"step": 46
},
{
"epoch": 0.21,
"learning_rate": 0.0002,
"loss": 0.9334,
"step": 47
},
{
"epoch": 0.21,
"learning_rate": 0.0002,
"loss": 0.919,
"step": 48
},
{
"epoch": 0.21,
"learning_rate": 0.0002,
"loss": 0.9349,
"step": 49
},
{
"epoch": 0.22,
"learning_rate": 0.0002,
"loss": 0.9197,
"step": 50
},
{
"epoch": 0.22,
"learning_rate": 0.0002,
"loss": 0.9145,
"step": 51
},
{
"epoch": 0.23,
"learning_rate": 0.0002,
"loss": 0.9302,
"step": 52
},
{
"epoch": 0.23,
"learning_rate": 0.0002,
"loss": 0.9731,
"step": 53
},
{
"epoch": 0.24,
"learning_rate": 0.0002,
"loss": 0.936,
"step": 54
},
{
"epoch": 0.24,
"learning_rate": 0.0002,
"loss": 0.9397,
"step": 55
},
{
"epoch": 0.24,
"learning_rate": 0.0002,
"loss": 0.9505,
"step": 56
},
{
"epoch": 0.25,
"learning_rate": 0.0002,
"loss": 0.949,
"step": 57
},
{
"epoch": 0.25,
"learning_rate": 0.0002,
"loss": 0.9316,
"step": 58
},
{
"epoch": 0.26,
"learning_rate": 0.0002,
"loss": 0.9262,
"step": 59
},
{
"epoch": 0.26,
"learning_rate": 0.0002,
"loss": 0.9159,
"step": 60
},
{
"epoch": 0.26,
"eval_loss": 1.121756672859192,
"eval_runtime": 297.6872,
"eval_samples_per_second": 2.116,
"eval_steps_per_second": 0.265,
"step": 60
},
{
"epoch": 0.27,
"learning_rate": 0.0002,
"loss": 0.9076,
"step": 61
},
{
"epoch": 0.27,
"learning_rate": 0.0002,
"loss": 0.9051,
"step": 62
},
{
"epoch": 0.27,
"learning_rate": 0.0002,
"loss": 0.9352,
"step": 63
},
{
"epoch": 0.28,
"learning_rate": 0.0002,
"loss": 0.906,
"step": 64
},
{
"epoch": 0.28,
"learning_rate": 0.0002,
"loss": 0.9356,
"step": 65
},
{
"epoch": 0.29,
"learning_rate": 0.0002,
"loss": 0.948,
"step": 66
},
{
"epoch": 0.29,
"learning_rate": 0.0002,
"loss": 0.921,
"step": 67
},
{
"epoch": 0.3,
"learning_rate": 0.0002,
"loss": 0.9628,
"step": 68
},
{
"epoch": 0.3,
"learning_rate": 0.0002,
"loss": 0.9477,
"step": 69
},
{
"epoch": 0.31,
"learning_rate": 0.0002,
"loss": 0.9122,
"step": 70
},
{
"epoch": 0.31,
"learning_rate": 0.0002,
"loss": 0.9098,
"step": 71
},
{
"epoch": 0.31,
"learning_rate": 0.0002,
"loss": 0.9112,
"step": 72
},
{
"epoch": 0.32,
"learning_rate": 0.0002,
"loss": 0.8882,
"step": 73
},
{
"epoch": 0.32,
"learning_rate": 0.0002,
"loss": 0.91,
"step": 74
},
{
"epoch": 0.33,
"learning_rate": 0.0002,
"loss": 0.9064,
"step": 75
},
{
"epoch": 0.33,
"learning_rate": 0.0002,
"loss": 0.9316,
"step": 76
},
{
"epoch": 0.34,
"learning_rate": 0.0002,
"loss": 0.9428,
"step": 77
},
{
"epoch": 0.34,
"learning_rate": 0.0002,
"loss": 0.9356,
"step": 78
},
{
"epoch": 0.34,
"learning_rate": 0.0002,
"loss": 0.9339,
"step": 79
},
{
"epoch": 0.35,
"learning_rate": 0.0002,
"loss": 0.9131,
"step": 80
},
{
"epoch": 0.35,
"eval_loss": 1.1153171062469482,
"eval_runtime": 297.6868,
"eval_samples_per_second": 2.116,
"eval_steps_per_second": 0.265,
"step": 80
},
{
"epoch": 0.35,
"learning_rate": 0.0002,
"loss": 0.9159,
"step": 81
},
{
"epoch": 0.36,
"learning_rate": 0.0002,
"loss": 0.9209,
"step": 82
},
{
"epoch": 0.36,
"learning_rate": 0.0002,
"loss": 0.8699,
"step": 83
},
{
"epoch": 0.37,
"learning_rate": 0.0002,
"loss": 0.9065,
"step": 84
},
{
"epoch": 0.37,
"learning_rate": 0.0002,
"loss": 0.8701,
"step": 85
},
{
"epoch": 0.38,
"learning_rate": 0.0002,
"loss": 0.8946,
"step": 86
},
{
"epoch": 0.38,
"learning_rate": 0.0002,
"loss": 0.8842,
"step": 87
},
{
"epoch": 0.38,
"learning_rate": 0.0002,
"loss": 0.8917,
"step": 88
},
{
"epoch": 0.39,
"learning_rate": 0.0002,
"loss": 0.9398,
"step": 89
},
{
"epoch": 0.39,
"learning_rate": 0.0002,
"loss": 0.9401,
"step": 90
},
{
"epoch": 0.4,
"learning_rate": 0.0002,
"loss": 0.8967,
"step": 91
},
{
"epoch": 0.4,
"learning_rate": 0.0002,
"loss": 0.8977,
"step": 92
},
{
"epoch": 0.41,
"learning_rate": 0.0002,
"loss": 0.9036,
"step": 93
},
{
"epoch": 0.41,
"learning_rate": 0.0002,
"loss": 0.8899,
"step": 94
},
{
"epoch": 0.41,
"learning_rate": 0.0002,
"loss": 0.8838,
"step": 95
},
{
"epoch": 0.42,
"learning_rate": 0.0002,
"loss": 0.8804,
"step": 96
},
{
"epoch": 0.42,
"learning_rate": 0.0002,
"loss": 0.8876,
"step": 97
},
{
"epoch": 0.43,
"learning_rate": 0.0002,
"loss": 0.8782,
"step": 98
},
{
"epoch": 0.43,
"learning_rate": 0.0002,
"loss": 0.8816,
"step": 99
},
{
"epoch": 0.44,
"learning_rate": 0.0002,
"loss": 0.8816,
"step": 100
},
{
"epoch": 0.44,
"eval_loss": 1.112991452217102,
"eval_runtime": 297.8676,
"eval_samples_per_second": 2.115,
"eval_steps_per_second": 0.265,
"step": 100
},
{
"epoch": 0.44,
"learning_rate": 0.0002,
"loss": 0.88,
"step": 101
},
{
"epoch": 0.44,
"learning_rate": 0.0002,
"loss": 0.8939,
"step": 102
},
{
"epoch": 0.45,
"learning_rate": 0.0002,
"loss": 0.9273,
"step": 103
},
{
"epoch": 0.45,
"learning_rate": 0.0002,
"loss": 0.9136,
"step": 104
},
{
"epoch": 0.46,
"learning_rate": 0.0002,
"loss": 0.9192,
"step": 105
},
{
"epoch": 0.46,
"learning_rate": 0.0002,
"loss": 0.8791,
"step": 106
},
{
"epoch": 0.47,
"learning_rate": 0.0002,
"loss": 0.9207,
"step": 107
},
{
"epoch": 0.47,
"learning_rate": 0.0002,
"loss": 0.8998,
"step": 108
},
{
"epoch": 0.48,
"learning_rate": 0.0002,
"loss": 0.8755,
"step": 109
},
{
"epoch": 0.48,
"learning_rate": 0.0002,
"loss": 0.8818,
"step": 110
},
{
"epoch": 0.48,
"learning_rate": 0.0002,
"loss": 0.8722,
"step": 111
},
{
"epoch": 0.49,
"learning_rate": 0.0002,
"loss": 0.8757,
"step": 112
},
{
"epoch": 0.49,
"learning_rate": 0.0002,
"loss": 0.8659,
"step": 113
},
{
"epoch": 0.5,
"learning_rate": 0.0002,
"loss": 0.8987,
"step": 114
},
{
"epoch": 0.5,
"learning_rate": 0.0002,
"loss": 0.8804,
"step": 115
},
{
"epoch": 0.51,
"learning_rate": 0.0002,
"loss": 0.9229,
"step": 116
},
{
"epoch": 0.51,
"learning_rate": 0.0002,
"loss": 0.9001,
"step": 117
},
{
"epoch": 0.51,
"learning_rate": 0.0002,
"loss": 0.8914,
"step": 118
},
{
"epoch": 0.52,
"learning_rate": 0.0002,
"loss": 0.9071,
"step": 119
},
{
"epoch": 0.52,
"learning_rate": 0.0002,
"loss": 0.8977,
"step": 120
},
{
"epoch": 0.52,
"eval_loss": 1.1069496870040894,
"eval_runtime": 297.5004,
"eval_samples_per_second": 2.118,
"eval_steps_per_second": 0.266,
"step": 120
},
{
"epoch": 0.53,
"learning_rate": 0.0002,
"loss": 0.8685,
"step": 121
},
{
"epoch": 0.53,
"learning_rate": 0.0002,
"loss": 0.8927,
"step": 122
},
{
"epoch": 0.54,
"learning_rate": 0.0002,
"loss": 0.8651,
"step": 123
},
{
"epoch": 0.54,
"learning_rate": 0.0002,
"loss": 0.8823,
"step": 124
},
{
"epoch": 0.55,
"learning_rate": 0.0002,
"loss": 0.8796,
"step": 125
},
{
"epoch": 0.55,
"learning_rate": 0.0002,
"loss": 0.8596,
"step": 126
},
{
"epoch": 0.55,
"learning_rate": 0.0002,
"loss": 0.8977,
"step": 127
},
{
"epoch": 0.56,
"learning_rate": 0.0002,
"loss": 0.8899,
"step": 128
},
{
"epoch": 0.56,
"learning_rate": 0.0002,
"loss": 0.9151,
"step": 129
},
{
"epoch": 0.57,
"learning_rate": 0.0002,
"loss": 0.8835,
"step": 130
},
{
"epoch": 0.57,
"learning_rate": 0.0002,
"loss": 0.8944,
"step": 131
},
{
"epoch": 0.58,
"learning_rate": 0.0002,
"loss": 0.8659,
"step": 132
},
{
"epoch": 0.58,
"learning_rate": 0.0002,
"loss": 0.8684,
"step": 133
},
{
"epoch": 0.58,
"learning_rate": 0.0002,
"loss": 0.8703,
"step": 134
},
{
"epoch": 0.59,
"learning_rate": 0.0002,
"loss": 0.8574,
"step": 135
},
{
"epoch": 0.59,
"learning_rate": 0.0002,
"loss": 0.8688,
"step": 136
},
{
"epoch": 0.6,
"learning_rate": 0.0002,
"loss": 0.8708,
"step": 137
},
{
"epoch": 0.6,
"learning_rate": 0.0002,
"loss": 0.8764,
"step": 138
},
{
"epoch": 0.61,
"learning_rate": 0.0002,
"loss": 0.8288,
"step": 139
},
{
"epoch": 0.61,
"learning_rate": 0.0002,
"loss": 0.9061,
"step": 140
},
{
"epoch": 0.61,
"eval_loss": 1.1024621725082397,
"eval_runtime": 297.9932,
"eval_samples_per_second": 2.114,
"eval_steps_per_second": 0.265,
"step": 140
},
{
"epoch": 0.62,
"learning_rate": 0.0002,
"loss": 0.8807,
"step": 141
},
{
"epoch": 0.62,
"learning_rate": 0.0002,
"loss": 0.9187,
"step": 142
},
{
"epoch": 0.62,
"learning_rate": 0.0002,
"loss": 0.8921,
"step": 143
},
{
"epoch": 0.63,
"learning_rate": 0.0002,
"loss": 0.8807,
"step": 144
},
{
"epoch": 0.63,
"learning_rate": 0.0002,
"loss": 0.8599,
"step": 145
},
{
"epoch": 0.64,
"learning_rate": 0.0002,
"loss": 0.869,
"step": 146
},
{
"epoch": 0.64,
"learning_rate": 0.0002,
"loss": 0.8795,
"step": 147
},
{
"epoch": 0.65,
"learning_rate": 0.0002,
"loss": 0.862,
"step": 148
},
{
"epoch": 0.65,
"learning_rate": 0.0002,
"loss": 0.8768,
"step": 149
},
{
"epoch": 0.65,
"learning_rate": 0.0002,
"loss": 0.8791,
"step": 150
},
{
"epoch": 0.66,
"learning_rate": 0.0002,
"loss": 0.902,
"step": 151
},
{
"epoch": 0.66,
"learning_rate": 0.0002,
"loss": 0.8899,
"step": 152
},
{
"epoch": 0.67,
"learning_rate": 0.0002,
"loss": 0.8686,
"step": 153
},
{
"epoch": 0.67,
"learning_rate": 0.0002,
"loss": 0.8884,
"step": 154
},
{
"epoch": 0.68,
"learning_rate": 0.0002,
"loss": 0.893,
"step": 155
},
{
"epoch": 0.68,
"learning_rate": 0.0002,
"loss": 0.8922,
"step": 156
},
{
"epoch": 0.68,
"learning_rate": 0.0002,
"loss": 0.8948,
"step": 157
},
{
"epoch": 0.69,
"learning_rate": 0.0002,
"loss": 0.8631,
"step": 158
},
{
"epoch": 0.69,
"learning_rate": 0.0002,
"loss": 0.8568,
"step": 159
},
{
"epoch": 0.7,
"learning_rate": 0.0002,
"loss": 0.8672,
"step": 160
},
{
"epoch": 0.7,
"eval_loss": 1.1024175882339478,
"eval_runtime": 298.1369,
"eval_samples_per_second": 2.113,
"eval_steps_per_second": 0.265,
"step": 160
},
{
"epoch": 0.7,
"learning_rate": 0.0002,
"loss": 0.8472,
"step": 161
},
{
"epoch": 0.71,
"learning_rate": 0.0002,
"loss": 0.8579,
"step": 162
},
{
"epoch": 0.71,
"learning_rate": 0.0002,
"loss": 0.8437,
"step": 163
},
{
"epoch": 0.72,
"learning_rate": 0.0002,
"loss": 0.8959,
"step": 164
},
{
"epoch": 0.72,
"learning_rate": 0.0002,
"loss": 0.8763,
"step": 165
},
{
"epoch": 0.72,
"learning_rate": 0.0002,
"loss": 0.8989,
"step": 166
},
{
"epoch": 0.73,
"learning_rate": 0.0002,
"loss": 0.8782,
"step": 167
},
{
"epoch": 0.73,
"learning_rate": 0.0002,
"loss": 0.8828,
"step": 168
},
{
"epoch": 0.74,
"learning_rate": 0.0002,
"loss": 0.8883,
"step": 169
},
{
"epoch": 0.74,
"learning_rate": 0.0002,
"loss": 0.8548,
"step": 170
},
{
"epoch": 0.75,
"learning_rate": 0.0002,
"loss": 0.8543,
"step": 171
},
{
"epoch": 0.75,
"learning_rate": 0.0002,
"loss": 0.826,
"step": 172
},
{
"epoch": 0.75,
"learning_rate": 0.0002,
"loss": 0.8505,
"step": 173
},
{
"epoch": 0.76,
"learning_rate": 0.0002,
"loss": 0.8534,
"step": 174
},
{
"epoch": 0.76,
"learning_rate": 0.0002,
"loss": 0.8521,
"step": 175
},
{
"epoch": 0.77,
"learning_rate": 0.0002,
"loss": 0.8476,
"step": 176
},
{
"epoch": 0.77,
"learning_rate": 0.0002,
"loss": 0.8975,
"step": 177
},
{
"epoch": 0.78,
"learning_rate": 0.0002,
"loss": 0.8728,
"step": 178
},
{
"epoch": 0.78,
"learning_rate": 0.0002,
"loss": 0.8631,
"step": 179
},
{
"epoch": 0.79,
"learning_rate": 0.0002,
"loss": 0.8956,
"step": 180
},
{
"epoch": 0.79,
"eval_loss": 1.09708833694458,
"eval_runtime": 298.3175,
"eval_samples_per_second": 2.112,
"eval_steps_per_second": 0.265,
"step": 180
},
{
"epoch": 0.79,
"learning_rate": 0.0002,
"loss": 0.8851,
"step": 181
},
{
"epoch": 0.79,
"learning_rate": 0.0002,
"loss": 0.8677,
"step": 182
},
{
"epoch": 0.8,
"learning_rate": 0.0002,
"loss": 0.8857,
"step": 183
},
{
"epoch": 0.8,
"learning_rate": 0.0002,
"loss": 0.8622,
"step": 184
},
{
"epoch": 0.81,
"learning_rate": 0.0002,
"loss": 0.8537,
"step": 185
},
{
"epoch": 0.81,
"learning_rate": 0.0002,
"loss": 0.8628,
"step": 186
},
{
"epoch": 0.82,
"learning_rate": 0.0002,
"loss": 0.8539,
"step": 187
},
{
"epoch": 0.82,
"learning_rate": 0.0002,
"loss": 0.85,
"step": 188
},
{
"epoch": 0.82,
"learning_rate": 0.0002,
"loss": 0.8637,
"step": 189
},
{
"epoch": 0.83,
"learning_rate": 0.0002,
"loss": 0.9028,
"step": 190
},
{
"epoch": 0.83,
"learning_rate": 0.0002,
"loss": 0.8614,
"step": 191
},
{
"epoch": 0.84,
"learning_rate": 0.0002,
"loss": 0.875,
"step": 192
},
{
"epoch": 0.84,
"learning_rate": 0.0002,
"loss": 0.8749,
"step": 193
},
{
"epoch": 0.85,
"learning_rate": 0.0002,
"loss": 0.8707,
"step": 194
},
{
"epoch": 0.85,
"learning_rate": 0.0002,
"loss": 0.8543,
"step": 195
},
{
"epoch": 0.85,
"learning_rate": 0.0002,
"loss": 0.8314,
"step": 196
},
{
"epoch": 0.86,
"learning_rate": 0.0002,
"loss": 0.8487,
"step": 197
},
{
"epoch": 0.86,
"learning_rate": 0.0002,
"loss": 0.837,
"step": 198
},
{
"epoch": 0.87,
"learning_rate": 0.0002,
"loss": 0.8422,
"step": 199
},
{
"epoch": 0.87,
"learning_rate": 0.0002,
"loss": 0.8514,
"step": 200
},
{
"epoch": 0.87,
"eval_loss": 1.0995315313339233,
"eval_runtime": 298.0972,
"eval_samples_per_second": 2.113,
"eval_steps_per_second": 0.265,
"step": 200
},
{
"epoch": 0.88,
"learning_rate": 0.0002,
"loss": 0.8633,
"step": 201
},
{
"epoch": 0.88,
"learning_rate": 0.0002,
"loss": 0.8679,
"step": 202
},
{
"epoch": 0.89,
"learning_rate": 0.0002,
"loss": 0.8875,
"step": 203
},
{
"epoch": 0.89,
"learning_rate": 0.0002,
"loss": 0.8816,
"step": 204
},
{
"epoch": 0.89,
"learning_rate": 0.0002,
"loss": 0.9009,
"step": 205
},
{
"epoch": 0.9,
"learning_rate": 0.0002,
"loss": 0.8899,
"step": 206
},
{
"epoch": 0.9,
"learning_rate": 0.0002,
"loss": 0.8638,
"step": 207
},
{
"epoch": 0.91,
"learning_rate": 0.0002,
"loss": 0.8558,
"step": 208
},
{
"epoch": 0.91,
"learning_rate": 0.0002,
"loss": 0.8313,
"step": 209
},
{
"epoch": 0.92,
"learning_rate": 0.0002,
"loss": 0.8379,
"step": 210
},
{
"epoch": 0.92,
"learning_rate": 0.0002,
"loss": 0.8323,
"step": 211
},
{
"epoch": 0.92,
"learning_rate": 0.0002,
"loss": 0.8417,
"step": 212
},
{
"epoch": 0.93,
"learning_rate": 0.0002,
"loss": 0.8317,
"step": 213
},
{
"epoch": 0.93,
"learning_rate": 0.0002,
"loss": 0.8711,
"step": 214
},
{
"epoch": 0.94,
"learning_rate": 0.0002,
"loss": 0.8699,
"step": 215
},
{
"epoch": 0.94,
"learning_rate": 0.0002,
"loss": 0.8802,
"step": 216
},
{
"epoch": 0.95,
"learning_rate": 0.0002,
"loss": 0.8947,
"step": 217
},
{
"epoch": 0.95,
"learning_rate": 0.0002,
"loss": 0.8655,
"step": 218
},
{
"epoch": 0.96,
"learning_rate": 0.0002,
"loss": 0.841,
"step": 219
},
{
"epoch": 0.96,
"learning_rate": 0.0002,
"loss": 0.8357,
"step": 220
},
{
"epoch": 0.96,
"eval_loss": 1.0951653718948364,
"eval_runtime": 298.5564,
"eval_samples_per_second": 2.11,
"eval_steps_per_second": 0.265,
"step": 220
},
{
"epoch": 0.96,
"learning_rate": 0.0002,
"loss": 0.8738,
"step": 221
},
{
"epoch": 0.97,
"learning_rate": 0.0002,
"loss": 0.8402,
"step": 222
},
{
"epoch": 0.97,
"learning_rate": 0.0002,
"loss": 0.8445,
"step": 223
},
{
"epoch": 0.98,
"learning_rate": 0.0002,
"loss": 0.8529,
"step": 224
},
{
"epoch": 0.98,
"learning_rate": 0.0002,
"loss": 0.8205,
"step": 225
},
{
"epoch": 0.99,
"learning_rate": 0.0002,
"loss": 0.8445,
"step": 226
},
{
"epoch": 0.99,
"learning_rate": 0.0002,
"loss": 0.8892,
"step": 227
},
{
"epoch": 0.99,
"learning_rate": 0.0002,
"loss": 0.8501,
"step": 228
},
{
"epoch": 1.0,
"learning_rate": 0.0002,
"loss": 0.8445,
"step": 229
},
{
"epoch": 1.0,
"learning_rate": 0.0002,
"loss": 0.8308,
"step": 230
},
{
"epoch": 1.01,
"learning_rate": 0.0002,
"loss": 0.8321,
"step": 231
},
{
"epoch": 1.01,
"learning_rate": 0.0002,
"loss": 0.8585,
"step": 232
},
{
"epoch": 1.02,
"learning_rate": 0.0002,
"loss": 0.8467,
"step": 233
},
{
"epoch": 1.02,
"learning_rate": 0.0002,
"loss": 0.8528,
"step": 234
},
{
"epoch": 1.03,
"learning_rate": 0.0002,
"loss": 0.8851,
"step": 235
},
{
"epoch": 1.03,
"learning_rate": 0.0002,
"loss": 0.8431,
"step": 236
},
{
"epoch": 1.03,
"learning_rate": 0.0002,
"loss": 0.8478,
"step": 237
},
{
"epoch": 1.04,
"learning_rate": 0.0002,
"loss": 0.8204,
"step": 238
},
{
"epoch": 1.04,
"learning_rate": 0.0002,
"loss": 0.845,
"step": 239
},
{
"epoch": 1.05,
"learning_rate": 0.0002,
"loss": 0.8294,
"step": 240
},
{
"epoch": 1.05,
"eval_loss": 1.096376895904541,
"eval_runtime": 298.2089,
"eval_samples_per_second": 2.113,
"eval_steps_per_second": 0.265,
"step": 240
},
{
"epoch": 1.05,
"learning_rate": 0.0002,
"loss": 0.8248,
"step": 241
},
{
"epoch": 1.06,
"learning_rate": 0.0002,
"loss": 0.8481,
"step": 242
},
{
"epoch": 1.06,
"learning_rate": 0.0002,
"loss": 0.8774,
"step": 243
},
{
"epoch": 1.06,
"learning_rate": 0.0002,
"loss": 0.8699,
"step": 244
},
{
"epoch": 1.07,
"learning_rate": 0.0002,
"loss": 0.8682,
"step": 245
},
{
"epoch": 1.07,
"learning_rate": 0.0002,
"loss": 0.8883,
"step": 246
},
{
"epoch": 1.08,
"learning_rate": 0.0002,
"loss": 0.8709,
"step": 247
},
{
"epoch": 1.08,
"learning_rate": 0.0002,
"loss": 0.8781,
"step": 248
},
{
"epoch": 1.09,
"learning_rate": 0.0002,
"loss": 0.8291,
"step": 249
},
{
"epoch": 1.09,
"learning_rate": 0.0002,
"loss": 0.8422,
"step": 250
},
{
"epoch": 1.09,
"learning_rate": 0.0002,
"loss": 0.8313,
"step": 251
},
{
"epoch": 1.1,
"learning_rate": 0.0002,
"loss": 0.8416,
"step": 252
},
{
"epoch": 1.1,
"learning_rate": 0.0002,
"loss": 0.827,
"step": 253
},
{
"epoch": 1.11,
"learning_rate": 0.0002,
"loss": 0.8364,
"step": 254
},
{
"epoch": 1.11,
"learning_rate": 0.0002,
"loss": 0.8291,
"step": 255
},
{
"epoch": 1.12,
"learning_rate": 0.0002,
"loss": 0.8607,
"step": 256
},
{
"epoch": 1.12,
"learning_rate": 0.0002,
"loss": 0.8381,
"step": 257
},
{
"epoch": 1.13,
"learning_rate": 0.0002,
"loss": 0.8488,
"step": 258
},
{
"epoch": 1.13,
"learning_rate": 0.0002,
"loss": 0.8552,
"step": 259
},
{
"epoch": 1.13,
"learning_rate": 0.0002,
"loss": 0.8531,
"step": 260
},
{
"epoch": 1.13,
"eval_loss": 1.094660997390747,
"eval_runtime": 298.1616,
"eval_samples_per_second": 2.113,
"eval_steps_per_second": 0.265,
"step": 260
},
{
"epoch": 1.14,
"learning_rate": 0.0002,
"loss": 0.8684,
"step": 261
},
{
"epoch": 1.14,
"learning_rate": 0.0002,
"loss": 0.8439,
"step": 262
},
{
"epoch": 1.15,
"learning_rate": 0.0002,
"loss": 0.8287,
"step": 263
},
{
"epoch": 1.15,
"learning_rate": 0.0002,
"loss": 0.8302,
"step": 264
},
{
"epoch": 1.16,
"learning_rate": 0.0002,
"loss": 0.8302,
"step": 265
},
{
"epoch": 1.16,
"learning_rate": 0.0002,
"loss": 0.8412,
"step": 266
},
{
"epoch": 1.16,
"learning_rate": 0.0002,
"loss": 0.8323,
"step": 267
},
{
"epoch": 1.17,
"learning_rate": 0.0002,
"loss": 0.8542,
"step": 268
},
{
"epoch": 1.17,
"learning_rate": 0.0002,
"loss": 0.8818,
"step": 269
},
{
"epoch": 1.18,
"learning_rate": 0.0002,
"loss": 0.8726,
"step": 270
},
{
"epoch": 1.18,
"learning_rate": 0.0002,
"loss": 0.8815,
"step": 271
},
{
"epoch": 1.19,
"learning_rate": 0.0002,
"loss": 0.868,
"step": 272
},
{
"epoch": 1.19,
"learning_rate": 0.0002,
"loss": 0.8517,
"step": 273
},
{
"epoch": 1.2,
"learning_rate": 0.0002,
"loss": 0.8478,
"step": 274
},
{
"epoch": 1.2,
"learning_rate": 0.0002,
"loss": 0.839,
"step": 275
},
{
"epoch": 1.2,
"learning_rate": 0.0002,
"loss": 0.8322,
"step": 276
},
{
"epoch": 1.21,
"learning_rate": 0.0002,
"loss": 0.841,
"step": 277
},
{
"epoch": 1.21,
"learning_rate": 0.0002,
"loss": 0.836,
"step": 278
},
{
"epoch": 1.22,
"learning_rate": 0.0002,
"loss": 0.8241,
"step": 279
},
{
"epoch": 1.22,
"learning_rate": 0.0002,
"loss": 0.8321,
"step": 280
},
{
"epoch": 1.22,
"eval_loss": 1.0951038599014282,
"eval_runtime": 297.7475,
"eval_samples_per_second": 2.116,
"eval_steps_per_second": 0.265,
"step": 280
},
{
"epoch": 1.23,
"learning_rate": 0.0002,
"loss": 0.8181,
"step": 281
},
{
"epoch": 1.23,
"learning_rate": 0.0002,
"loss": 0.8765,
"step": 282
},
{
"epoch": 1.23,
"learning_rate": 0.0002,
"loss": 0.8836,
"step": 283
},
{
"epoch": 1.24,
"learning_rate": 0.0002,
"loss": 0.862,
"step": 284
},
{
"epoch": 1.24,
"learning_rate": 0.0002,
"loss": 0.8687,
"step": 285
},
{
"epoch": 1.25,
"learning_rate": 0.0002,
"loss": 0.8548,
"step": 286
},
{
"epoch": 1.25,
"learning_rate": 0.0002,
"loss": 0.8491,
"step": 287
},
{
"epoch": 1.26,
"learning_rate": 0.0002,
"loss": 0.8327,
"step": 288
},
{
"epoch": 1.26,
"learning_rate": 0.0002,
"loss": 0.8421,
"step": 289
},
{
"epoch": 1.26,
"learning_rate": 0.0002,
"loss": 0.8333,
"step": 290
},
{
"epoch": 1.27,
"learning_rate": 0.0002,
"loss": 0.8171,
"step": 291
},
{
"epoch": 1.27,
"learning_rate": 0.0002,
"loss": 0.8594,
"step": 292
},
{
"epoch": 1.28,
"learning_rate": 0.0002,
"loss": 0.8226,
"step": 293
},
{
"epoch": 1.28,
"learning_rate": 0.0002,
"loss": 0.8744,
"step": 294
},
{
"epoch": 1.29,
"learning_rate": 0.0002,
"loss": 0.8613,
"step": 295
},
{
"epoch": 1.29,
"learning_rate": 0.0002,
"loss": 0.8846,
"step": 296
},
{
"epoch": 1.3,
"learning_rate": 0.0002,
"loss": 0.8651,
"step": 297
},
{
"epoch": 1.3,
"learning_rate": 0.0002,
"loss": 0.8453,
"step": 298
},
{
"epoch": 1.3,
"learning_rate": 0.0002,
"loss": 0.8536,
"step": 299
},
{
"epoch": 1.31,
"learning_rate": 0.0002,
"loss": 0.8365,
"step": 300
},
{
"epoch": 1.31,
"eval_loss": 1.0909942388534546,
"eval_runtime": 297.8185,
"eval_samples_per_second": 2.115,
"eval_steps_per_second": 0.265,
"step": 300
},
{
"epoch": 1.31,
"learning_rate": 0.0002,
"loss": 0.8077,
"step": 301
},
{
"epoch": 1.32,
"learning_rate": 0.0002,
"loss": 0.8255,
"step": 302
},
{
"epoch": 1.32,
"learning_rate": 0.0002,
"loss": 0.82,
"step": 303
},
{
"epoch": 1.33,
"learning_rate": 0.0002,
"loss": 0.8365,
"step": 304
},
{
"epoch": 1.33,
"learning_rate": 0.0002,
"loss": 0.8231,
"step": 305
},
{
"epoch": 1.33,
"learning_rate": 0.0002,
"loss": 0.8583,
"step": 306
},
{
"epoch": 1.34,
"learning_rate": 0.0002,
"loss": 0.8452,
"step": 307
},
{
"epoch": 1.34,
"learning_rate": 0.0002,
"loss": 0.8562,
"step": 308
},
{
"epoch": 1.35,
"learning_rate": 0.0002,
"loss": 0.8659,
"step": 309
},
{
"epoch": 1.35,
"learning_rate": 0.0002,
"loss": 0.8614,
"step": 310
},
{
"epoch": 1.36,
"learning_rate": 0.0002,
"loss": 0.8329,
"step": 311
},
{
"epoch": 1.36,
"learning_rate": 0.0002,
"loss": 0.8334,
"step": 312
},
{
"epoch": 1.37,
"learning_rate": 0.0002,
"loss": 0.8345,
"step": 313
},
{
"epoch": 1.37,
"learning_rate": 0.0002,
"loss": 0.8401,
"step": 314
},
{
"epoch": 1.37,
"learning_rate": 0.0002,
"loss": 0.8349,
"step": 315
},
{
"epoch": 1.38,
"learning_rate": 0.0002,
"loss": 0.8311,
"step": 316
},
{
"epoch": 1.38,
"learning_rate": 0.0002,
"loss": 0.8078,
"step": 317
},
{
"epoch": 1.39,
"learning_rate": 0.0002,
"loss": 0.8559,
"step": 318
},
{
"epoch": 1.39,
"learning_rate": 0.0002,
"loss": 0.8731,
"step": 319
},
{
"epoch": 1.4,
"learning_rate": 0.0002,
"loss": 0.8616,
"step": 320
},
{
"epoch": 1.4,
"eval_loss": 1.089436650276184,
"eval_runtime": 298.0608,
"eval_samples_per_second": 2.114,
"eval_steps_per_second": 0.265,
"step": 320
},
{
"epoch": 1.4,
"learning_rate": 0.0002,
"loss": 0.8545,
"step": 321
},
{
"epoch": 1.4,
"learning_rate": 0.0002,
"loss": 0.8385,
"step": 322
},
{
"epoch": 1.41,
"learning_rate": 0.0002,
"loss": 0.8277,
"step": 323
},
{
"epoch": 1.41,
"learning_rate": 0.0002,
"loss": 0.8422,
"step": 324
},
{
"epoch": 1.42,
"learning_rate": 0.0002,
"loss": 0.8162,
"step": 325
},
{
"epoch": 1.42,
"learning_rate": 0.0002,
"loss": 0.8114,
"step": 326
},
{
"epoch": 1.43,
"learning_rate": 0.0002,
"loss": 0.8168,
"step": 327
},
{
"epoch": 1.43,
"learning_rate": 0.0002,
"loss": 0.8231,
"step": 328
},
{
"epoch": 1.44,
"learning_rate": 0.0002,
"loss": 0.8127,
"step": 329
},
{
"epoch": 1.44,
"learning_rate": 0.0002,
"loss": 0.8229,
"step": 330
},
{
"epoch": 1.44,
"learning_rate": 0.0002,
"loss": 0.8331,
"step": 331
},
{
"epoch": 1.45,
"learning_rate": 0.0002,
"loss": 0.8635,
"step": 332
},
{
"epoch": 1.45,
"learning_rate": 0.0002,
"loss": 0.8342,
"step": 333
},
{
"epoch": 1.46,
"learning_rate": 0.0002,
"loss": 0.8705,
"step": 334
},
{
"epoch": 1.46,
"learning_rate": 0.0002,
"loss": 0.8483,
"step": 335
},
{
"epoch": 1.47,
"learning_rate": 0.0002,
"loss": 0.8388,
"step": 336
},
{
"epoch": 1.47,
"learning_rate": 0.0002,
"loss": 0.8364,
"step": 337
},
{
"epoch": 1.47,
"learning_rate": 0.0002,
"loss": 0.8306,
"step": 338
},
{
"epoch": 1.48,
"learning_rate": 0.0002,
"loss": 0.8305,
"step": 339
},
{
"epoch": 1.48,
"learning_rate": 0.0002,
"loss": 0.8397,
"step": 340
},
{
"epoch": 1.48,
"eval_loss": 1.0903966426849365,
"eval_runtime": 298.1209,
"eval_samples_per_second": 2.113,
"eval_steps_per_second": 0.265,
"step": 340
},
{
"epoch": 1.49,
"learning_rate": 0.0002,
"loss": 0.8328,
"step": 341
},
{
"epoch": 1.49,
"learning_rate": 0.0002,
"loss": 0.8353,
"step": 342
},
{
"epoch": 1.5,
"learning_rate": 0.0002,
"loss": 0.8663,
"step": 343
},
{
"epoch": 1.5,
"learning_rate": 0.0002,
"loss": 0.8582,
"step": 344
},
{
"epoch": 1.5,
"learning_rate": 0.0002,
"loss": 0.8661,
"step": 345
},
{
"epoch": 1.51,
"learning_rate": 0.0002,
"loss": 0.8546,
"step": 346
},
{
"epoch": 1.51,
"learning_rate": 0.0002,
"loss": 0.8525,
"step": 347
},
{
"epoch": 1.52,
"learning_rate": 0.0002,
"loss": 0.8425,
"step": 348
},
{
"epoch": 1.52,
"learning_rate": 0.0002,
"loss": 0.8116,
"step": 349
},
{
"epoch": 1.53,
"learning_rate": 0.0002,
"loss": 0.8456,
"step": 350
},
{
"epoch": 1.53,
"learning_rate": 0.0002,
"loss": 0.8106,
"step": 351
},
{
"epoch": 1.54,
"learning_rate": 0.0002,
"loss": 0.8191,
"step": 352
},
{
"epoch": 1.54,
"learning_rate": 0.0002,
"loss": 0.8156,
"step": 353
},
{
"epoch": 1.54,
"learning_rate": 0.0002,
"loss": 0.8321,
"step": 354
},
{
"epoch": 1.55,
"learning_rate": 0.0002,
"loss": 0.8194,
"step": 355
},
{
"epoch": 1.55,
"learning_rate": 0.0002,
"loss": 0.8641,
"step": 356
},
{
"epoch": 1.56,
"learning_rate": 0.0002,
"loss": 0.8666,
"step": 357
},
{
"epoch": 1.56,
"learning_rate": 0.0002,
"loss": 0.8662,
"step": 358
},
{
"epoch": 1.57,
"learning_rate": 0.0002,
"loss": 0.8461,
"step": 359
},
{
"epoch": 1.57,
"learning_rate": 0.0002,
"loss": 0.861,
"step": 360
},
{
"epoch": 1.57,
"eval_loss": 1.0879958868026733,
"eval_runtime": 298.0492,
"eval_samples_per_second": 2.114,
"eval_steps_per_second": 0.265,
"step": 360
},
{
"epoch": 1.57,
"learning_rate": 0.0002,
"loss": 0.8773,
"step": 361
},
{
"epoch": 1.58,
"learning_rate": 0.0002,
"loss": 0.8199,
"step": 362
},
{
"epoch": 1.58,
"learning_rate": 0.0002,
"loss": 0.8329,
"step": 363
},
{
"epoch": 1.59,
"learning_rate": 0.0002,
"loss": 0.8143,
"step": 364
},
{
"epoch": 1.59,
"learning_rate": 0.0002,
"loss": 0.8151,
"step": 365
},
{
"epoch": 1.6,
"learning_rate": 0.0002,
"loss": 0.8122,
"step": 366
},
{
"epoch": 1.6,
"learning_rate": 0.0002,
"loss": 0.8562,
"step": 367
},
{
"epoch": 1.61,
"learning_rate": 0.0002,
"loss": 0.8411,
"step": 368
},
{
"epoch": 1.61,
"learning_rate": 0.0002,
"loss": 0.8237,
"step": 369
},
{
"epoch": 1.61,
"learning_rate": 0.0002,
"loss": 0.8748,
"step": 370
},
{
"epoch": 1.62,
"learning_rate": 0.0002,
"loss": 0.8464,
"step": 371
},
{
"epoch": 1.62,
"learning_rate": 0.0002,
"loss": 0.8524,
"step": 372
},
{
"epoch": 1.63,
"learning_rate": 0.0002,
"loss": 0.8209,
"step": 373
},
{
"epoch": 1.63,
"learning_rate": 0.0002,
"loss": 0.8239,
"step": 374
},
{
"epoch": 1.64,
"learning_rate": 0.0002,
"loss": 0.8362,
"step": 375
},
{
"epoch": 1.64,
"learning_rate": 0.0002,
"loss": 0.8157,
"step": 376
},
{
"epoch": 1.64,
"learning_rate": 0.0002,
"loss": 0.7831,
"step": 377
},
{
"epoch": 1.65,
"learning_rate": 0.0002,
"loss": 0.8309,
"step": 378
},
{
"epoch": 1.65,
"learning_rate": 0.0002,
"loss": 0.818,
"step": 379
},
{
"epoch": 1.66,
"learning_rate": 0.0002,
"loss": 0.8116,
"step": 380
},
{
"epoch": 1.66,
"eval_loss": 1.0871427059173584,
"eval_runtime": 298.1736,
"eval_samples_per_second": 2.113,
"eval_steps_per_second": 0.265,
"step": 380
},
{
"epoch": 1.66,
"learning_rate": 0.0002,
"loss": 0.8273,
"step": 381
},
{
"epoch": 1.67,
"learning_rate": 0.0002,
"loss": 0.8636,
"step": 382
},
{
"epoch": 1.67,
"learning_rate": 0.0002,
"loss": 0.858,
"step": 383
},
{
"epoch": 1.68,
"learning_rate": 0.0002,
"loss": 0.8523,
"step": 384
},
{
"epoch": 1.68,
"learning_rate": 0.0002,
"loss": 0.8535,
"step": 385
},
{
"epoch": 1.68,
"learning_rate": 0.0002,
"loss": 0.8519,
"step": 386
},
{
"epoch": 1.69,
"learning_rate": 0.0002,
"loss": 0.8279,
"step": 387
},
{
"epoch": 1.69,
"learning_rate": 0.0002,
"loss": 0.837,
"step": 388
},
{
"epoch": 1.7,
"learning_rate": 0.0002,
"loss": 0.8256,
"step": 389
},
{
"epoch": 1.7,
"learning_rate": 0.0002,
"loss": 0.8365,
"step": 390
},
{
"epoch": 1.71,
"learning_rate": 0.0002,
"loss": 0.823,
"step": 391
},
{
"epoch": 1.71,
"learning_rate": 0.0002,
"loss": 0.8234,
"step": 392
},
{
"epoch": 1.71,
"learning_rate": 0.0002,
"loss": 0.8425,
"step": 393
},
{
"epoch": 1.72,
"learning_rate": 0.0002,
"loss": 0.8596,
"step": 394
},
{
"epoch": 1.72,
"learning_rate": 0.0002,
"loss": 0.8767,
"step": 395
},
{
"epoch": 1.73,
"learning_rate": 0.0002,
"loss": 0.8755,
"step": 396
},
{
"epoch": 1.73,
"learning_rate": 0.0002,
"loss": 0.8251,
"step": 397
},
{
"epoch": 1.74,
"learning_rate": 0.0002,
"loss": 0.8438,
"step": 398
},
{
"epoch": 1.74,
"learning_rate": 0.0002,
"loss": 0.8215,
"step": 399
},
{
"epoch": 1.74,
"learning_rate": 0.0002,
"loss": 0.8285,
"step": 400
},
{
"epoch": 1.74,
"eval_loss": 1.0855315923690796,
"eval_runtime": 298.3211,
"eval_samples_per_second": 2.112,
"eval_steps_per_second": 0.265,
"step": 400
},
{
"epoch": 1.75,
"learning_rate": 0.0002,
"loss": 0.8268,
"step": 401
},
{
"epoch": 1.75,
"learning_rate": 0.0002,
"loss": 0.8275,
"step": 402
},
{
"epoch": 1.76,
"learning_rate": 0.0002,
"loss": 0.8348,
"step": 403
},
{
"epoch": 1.76,
"learning_rate": 0.0002,
"loss": 0.8155,
"step": 404
},
{
"epoch": 1.77,
"learning_rate": 0.0002,
"loss": 0.84,
"step": 405
},
{
"epoch": 1.77,
"learning_rate": 0.0002,
"loss": 0.8336,
"step": 406
},
{
"epoch": 1.78,
"learning_rate": 0.0002,
"loss": 0.8544,
"step": 407
},
{
"epoch": 1.78,
"learning_rate": 0.0002,
"loss": 0.8468,
"step": 408
},
{
"epoch": 1.78,
"learning_rate": 0.0002,
"loss": 0.8536,
"step": 409
},
{
"epoch": 1.79,
"learning_rate": 0.0002,
"loss": 0.8433,
"step": 410
},
{
"epoch": 1.79,
"learning_rate": 0.0002,
"loss": 0.8736,
"step": 411
},
{
"epoch": 1.8,
"learning_rate": 0.0002,
"loss": 0.8354,
"step": 412
},
{
"epoch": 1.8,
"learning_rate": 0.0002,
"loss": 0.8277,
"step": 413
},
{
"epoch": 1.81,
"learning_rate": 0.0002,
"loss": 0.8204,
"step": 414
},
{
"epoch": 1.81,
"learning_rate": 0.0002,
"loss": 0.8158,
"step": 415
},
{
"epoch": 1.81,
"learning_rate": 0.0002,
"loss": 0.8141,
"step": 416
},
{
"epoch": 1.82,
"learning_rate": 0.0002,
"loss": 0.8159,
"step": 417
},
{
"epoch": 1.82,
"learning_rate": 0.0002,
"loss": 0.8492,
"step": 418
},
{
"epoch": 1.83,
"learning_rate": 0.0002,
"loss": 0.8456,
"step": 419
},
{
"epoch": 1.83,
"learning_rate": 0.0002,
"loss": 0.8603,
"step": 420
},
{
"epoch": 1.83,
"eval_loss": 1.08558189868927,
"eval_runtime": 298.4008,
"eval_samples_per_second": 2.111,
"eval_steps_per_second": 0.265,
"step": 420
},
{
"epoch": 1.84,
"learning_rate": 0.0002,
"loss": 0.8401,
"step": 421
},
{
"epoch": 1.84,
"learning_rate": 0.0002,
"loss": 0.8639,
"step": 422
},
{
"epoch": 1.85,
"learning_rate": 0.0002,
"loss": 0.8543,
"step": 423
},
{
"epoch": 1.85,
"learning_rate": 0.0002,
"loss": 0.8312,
"step": 424
},
{
"epoch": 1.85,
"learning_rate": 0.0002,
"loss": 0.8327,
"step": 425
},
{
"epoch": 1.86,
"learning_rate": 0.0002,
"loss": 0.8259,
"step": 426
},
{
"epoch": 1.86,
"learning_rate": 0.0002,
"loss": 0.8123,
"step": 427
},
{
"epoch": 1.87,
"learning_rate": 0.0002,
"loss": 0.804,
"step": 428
},
{
"epoch": 1.87,
"learning_rate": 0.0002,
"loss": 0.8198,
"step": 429
},
{
"epoch": 1.88,
"learning_rate": 0.0002,
"loss": 0.8305,
"step": 430
},
{
"epoch": 1.88,
"learning_rate": 0.0002,
"loss": 0.8795,
"step": 431
},
{
"epoch": 1.88,
"learning_rate": 0.0002,
"loss": 0.8395,
"step": 432
},
{
"epoch": 1.89,
"learning_rate": 0.0002,
"loss": 0.8869,
"step": 433
},
{
"epoch": 1.89,
"learning_rate": 0.0002,
"loss": 0.848,
"step": 434
},
{
"epoch": 1.9,
"learning_rate": 0.0002,
"loss": 0.8446,
"step": 435
},
{
"epoch": 1.9,
"learning_rate": 0.0002,
"loss": 0.829,
"step": 436
},
{
"epoch": 1.91,
"learning_rate": 0.0002,
"loss": 0.8339,
"step": 437
},
{
"epoch": 1.91,
"learning_rate": 0.0002,
"loss": 0.8216,
"step": 438
},
{
"epoch": 1.91,
"learning_rate": 0.0002,
"loss": 0.7943,
"step": 439
},
{
"epoch": 1.92,
"learning_rate": 0.0002,
"loss": 0.8126,
"step": 440
},
{
"epoch": 1.92,
"eval_loss": 1.0847766399383545,
"eval_runtime": 298.252,
"eval_samples_per_second": 2.112,
"eval_steps_per_second": 0.265,
"step": 440
},
{
"epoch": 1.92,
"learning_rate": 0.0002,
"loss": 0.8076,
"step": 441
},
{
"epoch": 1.93,
"learning_rate": 0.0002,
"loss": 0.8277,
"step": 442
},
{
"epoch": 1.93,
"learning_rate": 0.0002,
"loss": 0.862,
"step": 443
},
{
"epoch": 1.94,
"learning_rate": 0.0002,
"loss": 0.8258,
"step": 444
},
{
"epoch": 1.94,
"learning_rate": 0.0002,
"loss": 0.8648,
"step": 445
},
{
"epoch": 1.95,
"learning_rate": 0.0002,
"loss": 0.8652,
"step": 446
},
{
"epoch": 1.95,
"learning_rate": 0.0002,
"loss": 0.8295,
"step": 447
},
{
"epoch": 1.95,
"learning_rate": 0.0002,
"loss": 0.8466,
"step": 448
},
{
"epoch": 1.96,
"learning_rate": 0.0002,
"loss": 0.841,
"step": 449
},
{
"epoch": 1.96,
"learning_rate": 0.0002,
"loss": 0.8283,
"step": 450
},
{
"epoch": 1.97,
"learning_rate": 0.0002,
"loss": 0.8117,
"step": 451
},
{
"epoch": 1.97,
"learning_rate": 0.0002,
"loss": 0.8056,
"step": 452
},
{
"epoch": 1.98,
"learning_rate": 0.0002,
"loss": 0.8077,
"step": 453
},
{
"epoch": 1.98,
"learning_rate": 0.0002,
"loss": 0.804,
"step": 454
},
{
"epoch": 1.98,
"learning_rate": 0.0002,
"loss": 0.8635,
"step": 455
},
{
"epoch": 1.99,
"learning_rate": 0.0002,
"loss": 0.8385,
"step": 456
},
{
"epoch": 1.99,
"learning_rate": 0.0002,
"loss": 0.833,
"step": 457
},
{
"epoch": 2.0,
"learning_rate": 0.0002,
"loss": 0.8211,
"step": 458
},
{
"epoch": 2.0,
"step": 458,
"total_flos": 4.4708987267050373e+18,
"train_loss": 0.8817351038799536,
"train_runtime": 50140.2452,
"train_samples_per_second": 0.585,
"train_steps_per_second": 0.009
}
],
"max_steps": 458,
"num_train_epochs": 2,
"total_flos": 4.4708987267050373e+18,
"trial_name": null,
"trial_params": null
}