Hugging Face's logo

lll2343
/
seqdlm

TensorBoard
Safetensors
Model card Files
xet
 Metrics Community
seqdlm / mask_block_v1114_bs8_3b_main /checkpoint-800 /trainer_state.json
lll2343's picture
lll2343
Upload folder using huggingface_hub
58aa287 verified
raw
history blame contribute delete
83.4 kB
{
 "best_metric": null,
 "best_model_checkpoint": null,
 "epoch": 0.05839842324257245,
 "eval_steps": 500,
 "global_step": 800,
 "is_hyper_param_search": false,
 "is_local_process_zero": true,
 "is_world_process_zero": true,
 "log_history": [
 {
 "epoch": 0.0,
 "learning_rate": 5e-06,
 "loss": 11.6243,
 "step": 1
 },
 {
 "epoch": 0.0,
 "learning_rate": 5e-06,
 "loss": 10.8031,
 "step": 2
 },
 {
 "epoch": 0.0,
 "learning_rate": 5e-06,
 "loss": 9.0961,
 "step": 3
 },
 {
 "epoch": 0.0,
 "learning_rate": 5e-06,
 "loss": 8.751,
 "step": 4
 },
 {
 "epoch": 0.0,
 "learning_rate": 5e-06,
 "loss": 6.9251,
 "step": 5
 },
 {
 "epoch": 0.0,
 "learning_rate": 5e-06,
 "loss": 6.5065,
 "step": 6
 },
 {
 "epoch": 0.0,
 "learning_rate": 5e-06,
 "loss": 6.2688,
 "step": 7
 },
 {
 "epoch": 0.0,
 "learning_rate": 5e-06,
 "loss": 5.344,
 "step": 8
 },
 {
 "epoch": 0.0,
 "learning_rate": 5e-06,
 "loss": 5.1358,
 "step": 9
 },
 {
 "epoch": 0.0,
 "learning_rate": 5e-06,
 "loss": 5.2283,
 "step": 10
 },
 {
 "epoch": 0.0,
 "learning_rate": 5e-06,
 "loss": 4.9726,
 "step": 11
 },
 {
 "epoch": 0.0,
 "learning_rate": 5e-06,
 "loss": 4.9962,
 "step": 12
 },
 {
 "epoch": 0.0,
 "learning_rate": 5e-06,
 "loss": 4.837,
 "step": 13
 },
 {
 "epoch": 0.0,
 "learning_rate": 5e-06,
 "loss": 4.6785,
 "step": 14
 },
 {
 "epoch": 0.0,
 "learning_rate": 5e-06,
 "loss": 4.5521,
 "step": 15
 },
 {
 "epoch": 0.0,
 "learning_rate": 5e-06,
 "loss": 4.4392,
 "step": 16
 },
 {
 "epoch": 0.0,
 "learning_rate": 5e-06,
 "loss": 4.2529,
 "step": 17
 },
 {
 "epoch": 0.0,
 "learning_rate": 5e-06,
 "loss": 4.0991,
 "step": 18
 },
 {
 "epoch": 0.0,
 "learning_rate": 5e-06,
 "loss": 4.0167,
 "step": 19
 },
 {
 "epoch": 0.0,
 "learning_rate": 5e-06,
 "loss": 4.0012,
 "step": 20
 },
 {
 "epoch": 0.0,
 "learning_rate": 5e-06,
 "loss": 3.9013,
 "step": 21
 },
 {
 "epoch": 0.0,
 "learning_rate": 5e-06,
 "loss": 3.8921,
 "step": 22
 },
 {
 "epoch": 0.0,
 "learning_rate": 5e-06,
 "loss": 3.8821,
 "step": 23
 },
 {
 "epoch": 0.0,
 "learning_rate": 5e-06,
 "loss": 3.8247,
 "step": 24
 },
 {
 "epoch": 0.0,
 "learning_rate": 5e-06,
 "loss": 3.7794,
 "step": 25
 },
 {
 "epoch": 0.0,
 "learning_rate": 5e-06,
 "loss": 3.8643,
 "step": 26
 },
 {
 "epoch": 0.0,
 "learning_rate": 5e-06,
 "loss": 3.78,
 "step": 27
 },
 {
 "epoch": 0.0,
 "learning_rate": 5e-06,
 "loss": 3.7055,
 "step": 28
 },
 {
 "epoch": 0.0,
 "learning_rate": 5e-06,
 "loss": 3.5667,
 "step": 29
 },
 {
 "epoch": 0.0,
 "learning_rate": 5e-06,
 "loss": 3.5302,
 "step": 30
 },
 {
 "epoch": 0.0,
 "learning_rate": 5e-06,
 "loss": 3.4729,
 "step": 31
 },
 {
 "epoch": 0.0,
 "learning_rate": 5e-06,
 "loss": 3.5958,
 "step": 32
 },
 {
 "epoch": 0.0,
 "learning_rate": 5e-06,
 "loss": 3.4481,
 "step": 33
 },
 {
 "epoch": 0.0,
 "learning_rate": 5e-06,
 "loss": 3.4567,
 "step": 34
 },
 {
 "epoch": 0.0,
 "learning_rate": 5e-06,
 "loss": 3.4172,
 "step": 35
 },
 {
 "epoch": 0.0,
 "learning_rate": 5e-06,
 "loss": 3.4287,
 "step": 36
 },
 {
 "epoch": 0.0,
 "learning_rate": 5e-06,
 "loss": 3.3519,
 "step": 37
 },
 {
 "epoch": 0.0,
 "learning_rate": 5e-06,
 "loss": 3.3259,
 "step": 38
 },
 {
 "epoch": 0.0,
 "learning_rate": 5e-06,
 "loss": 3.3288,
 "step": 39
 },
 {
 "epoch": 0.0,
 "learning_rate": 5e-06,
 "loss": 3.2049,
 "step": 40
 },
 {
 "epoch": 0.0,
 "learning_rate": 5e-06,
 "loss": 3.3316,
 "step": 41
 },
 {
 "epoch": 0.0,
 "learning_rate": 5e-06,
 "loss": 3.217,
 "step": 42
 },
 {
 "epoch": 0.0,
 "learning_rate": 5e-06,
 "loss": 3.2825,
 "step": 43
 },
 {
 "epoch": 0.0,
 "learning_rate": 5e-06,
 "loss": 3.0773,
 "step": 44
 },
 {
 "epoch": 0.0,
 "learning_rate": 5e-06,
 "loss": 3.065,
 "step": 45
 },
 {
 "epoch": 0.0,
 "learning_rate": 5e-06,
 "loss": 3.1438,
 "step": 46
 },
 {
 "epoch": 0.0,
 "learning_rate": 5e-06,
 "loss": 3.2048,
 "step": 47
 },
 {
 "epoch": 0.0,
 "learning_rate": 5e-06,
 "loss": 3.2364,
 "step": 48
 },
 {
 "epoch": 0.0,
 "learning_rate": 5e-06,
 "loss": 3.094,
 "step": 49
 },
 {
 "epoch": 0.0,
 "learning_rate": 5e-06,
 "loss": 3.164,
 "step": 50
 },
 {
 "epoch": 0.0,
 "learning_rate": 5e-06,
 "loss": 3.243,
 "step": 51
 },
 {
 "epoch": 0.0,
 "learning_rate": 5e-06,
 "loss": 3.0207,
 "step": 52
 },
 {
 "epoch": 0.0,
 "learning_rate": 5e-06,
 "loss": 3.1562,
 "step": 53
 },
 {
 "epoch": 0.0,
 "learning_rate": 5e-06,
 "loss": 3.1492,
 "step": 54
 },
 {
 "epoch": 0.0,
 "learning_rate": 5e-06,
 "loss": 3.1319,
 "step": 55
 },
 {
 "epoch": 0.0,
 "learning_rate": 5e-06,
 "loss": 2.9655,
 "step": 56
 },
 {
 "epoch": 0.0,
 "learning_rate": 5e-06,
 "loss": 2.939,
 "step": 57
 },
 {
 "epoch": 0.0,
 "learning_rate": 5e-06,
 "loss": 3.0842,
 "step": 58
 },
 {
 "epoch": 0.0,
 "learning_rate": 5e-06,
 "loss": 3.1599,
 "step": 59
 },
 {
 "epoch": 0.0,
 "learning_rate": 5e-06,
 "loss": 3.1353,
 "step": 60
 },
 {
 "epoch": 0.0,
 "learning_rate": 5e-06,
 "loss": 3.0907,
 "step": 61
 },
 {
 "epoch": 0.0,
 "learning_rate": 5e-06,
 "loss": 3.0175,
 "step": 62
 },
 {
 "epoch": 0.0,
 "learning_rate": 5e-06,
 "loss": 2.9857,
 "step": 63
 },
 {
 "epoch": 0.0,
 "learning_rate": 5e-06,
 "loss": 2.9647,
 "step": 64
 },
 {
 "epoch": 0.0,
 "learning_rate": 5e-06,
 "loss": 3.0053,
 "step": 65
 },
 {
 "epoch": 0.0,
 "learning_rate": 5e-06,
 "loss": 2.938,
 "step": 66
 },
 {
 "epoch": 0.0,
 "learning_rate": 5e-06,
 "loss": 3.0491,
 "step": 67
 },
 {
 "epoch": 0.0,
 "learning_rate": 5e-06,
 "loss": 2.9659,
 "step": 68
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.9964,
 "step": 69
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.9787,
 "step": 70
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 3.0239,
 "step": 71
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.9521,
 "step": 72
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.9255,
 "step": 73
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.9615,
 "step": 74
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.9989,
 "step": 75
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.94,
 "step": 76
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 3.0828,
 "step": 77
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.8718,
 "step": 78
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 3.0277,
 "step": 79
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.9993,
 "step": 80
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.8636,
 "step": 81
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.8424,
 "step": 82
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.8559,
 "step": 83
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.9295,
 "step": 84
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.9318,
 "step": 85
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.9764,
 "step": 86
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.7651,
 "step": 87
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.8445,
 "step": 88
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.7054,
 "step": 89
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.8985,
 "step": 90
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.8135,
 "step": 91
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.9246,
 "step": 92
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.8542,
 "step": 93
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.7713,
 "step": 94
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.9579,
 "step": 95
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.8579,
 "step": 96
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.8539,
 "step": 97
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.8201,
 "step": 98
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.7599,
 "step": 99
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.9535,
 "step": 100
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.8019,
 "step": 101
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.7506,
 "step": 102
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.7784,
 "step": 103
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.7484,
 "step": 104
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.7125,
 "step": 105
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.8713,
 "step": 106
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.7539,
 "step": 107
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.9135,
 "step": 108
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.6295,
 "step": 109
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.7716,
 "step": 110
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.7639,
 "step": 111
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.9206,
 "step": 112
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.5896,
 "step": 113
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.741,
 "step": 114
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.7554,
 "step": 115
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.6613,
 "step": 116
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.6461,
 "step": 117
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.7501,
 "step": 118
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.8243,
 "step": 119
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.9344,
 "step": 120
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.6621,
 "step": 121
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.5778,
 "step": 122
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.6881,
 "step": 123
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.6494,
 "step": 124
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.7286,
 "step": 125
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.7195,
 "step": 126
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.6477,
 "step": 127
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.8487,
 "step": 128
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.6896,
 "step": 129
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.5985,
 "step": 130
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.5715,
 "step": 131
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.7832,
 "step": 132
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.8698,
 "step": 133
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.5528,
 "step": 134
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.7677,
 "step": 135
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.6543,
 "step": 136
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.4845,
 "step": 137
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.5369,
 "step": 138
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.6431,
 "step": 139
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.6443,
 "step": 140
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.5306,
 "step": 141
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.5494,
 "step": 142
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.5574,
 "step": 143
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.6736,
 "step": 144
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.5946,
 "step": 145
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.6373,
 "step": 146
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.5626,
 "step": 147
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.7473,
 "step": 148
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.4872,
 "step": 149
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.6176,
 "step": 150
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.4197,
 "step": 151
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.8597,
 "step": 152
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.6606,
 "step": 153
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.6396,
 "step": 154
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.6494,
 "step": 155
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.557,
 "step": 156
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.5562,
 "step": 157
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.6402,
 "step": 158
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.6436,
 "step": 159
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.4905,
 "step": 160
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.5803,
 "step": 161
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.4443,
 "step": 162
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.5771,
 "step": 163
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.578,
 "step": 164
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.4754,
 "step": 165
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.6536,
 "step": 166
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.8153,
 "step": 167
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.6334,
 "step": 168
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.6698,
 "step": 169
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.5996,
 "step": 170
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.5661,
 "step": 171
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.6083,
 "step": 172
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.462,
 "step": 173
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.4469,
 "step": 174
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.6956,
 "step": 175
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.381,
 "step": 176
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.4819,
 "step": 177
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.5509,
 "step": 178
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.7101,
 "step": 179
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.5195,
 "step": 180
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.5533,
 "step": 181
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.4747,
 "step": 182
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.6185,
 "step": 183
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.6152,
 "step": 184
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.6366,
 "step": 185
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.6714,
 "step": 186
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.6231,
 "step": 187
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.6722,
 "step": 188
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.4526,
 "step": 189
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.7384,
 "step": 190
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.6559,
 "step": 191
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.586,
 "step": 192
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.3873,
 "step": 193
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.4916,
 "step": 194
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.5987,
 "step": 195
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.5041,
 "step": 196
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.5214,
 "step": 197
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.6548,
 "step": 198
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.585,
 "step": 199
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.5355,
 "step": 200
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.5228,
 "step": 201
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.6359,
 "step": 202
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.4445,
 "step": 203
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.5417,
 "step": 204
 },
 {
 "epoch": 0.01,
 "learning_rate": 5e-06,
 "loss": 2.4911,
 "step": 205
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.6637,
 "step": 206
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.599,
 "step": 207
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.6797,
 "step": 208
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.5976,
 "step": 209
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.4958,
 "step": 210
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.3943,
 "step": 211
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.44,
 "step": 212
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.5112,
 "step": 213
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.5165,
 "step": 214
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.5767,
 "step": 215
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.4932,
 "step": 216
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.4602,
 "step": 217
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.4062,
 "step": 218
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.4689,
 "step": 219
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.5566,
 "step": 220
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.5065,
 "step": 221
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.5052,
 "step": 222
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.59,
 "step": 223
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.42,
 "step": 224
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.5565,
 "step": 225
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.4942,
 "step": 226
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.5012,
 "step": 227
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.4658,
 "step": 228
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.4984,
 "step": 229
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.6537,
 "step": 230
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.5348,
 "step": 231
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.5583,
 "step": 232
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.528,
 "step": 233
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.4035,
 "step": 234
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.6399,
 "step": 235
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.4256,
 "step": 236
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.5387,
 "step": 237
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.4162,
 "step": 238
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.5594,
 "step": 239
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.4394,
 "step": 240
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.6122,
 "step": 241
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.4346,
 "step": 242
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.4073,
 "step": 243
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.4437,
 "step": 244
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.49,
 "step": 245
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.436,
 "step": 246
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.4399,
 "step": 247
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.3343,
 "step": 248
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.5765,
 "step": 249
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.4001,
 "step": 250
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.5959,
 "step": 251
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.5728,
 "step": 252
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.6113,
 "step": 253
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.3282,
 "step": 254
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.4478,
 "step": 255
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.3353,
 "step": 256
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.5998,
 "step": 257
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.4375,
 "step": 258
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.4199,
 "step": 259
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.4328,
 "step": 260
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.5407,
 "step": 261
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.2606,
 "step": 262
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.5056,
 "step": 263
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.4713,
 "step": 264
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.3771,
 "step": 265
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.5766,
 "step": 266
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.339,
 "step": 267
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.4035,
 "step": 268
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.438,
 "step": 269
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.6428,
 "step": 270
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.5192,
 "step": 271
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.3811,
 "step": 272
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.3672,
 "step": 273
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.5212,
 "step": 274
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.5846,
 "step": 275
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.4354,
 "step": 276
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.3809,
 "step": 277
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.4245,
 "step": 278
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.3002,
 "step": 279
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.4916,
 "step": 280
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.4493,
 "step": 281
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.5236,
 "step": 282
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.3049,
 "step": 283
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.5782,
 "step": 284
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.4589,
 "step": 285
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.4921,
 "step": 286
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.3741,
 "step": 287
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.3035,
 "step": 288
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.5289,
 "step": 289
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.3893,
 "step": 290
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.3984,
 "step": 291
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.4267,
 "step": 292
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.4201,
 "step": 293
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.2952,
 "step": 294
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.5155,
 "step": 295
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.2813,
 "step": 296
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.3606,
 "step": 297
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.473,
 "step": 298
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.3668,
 "step": 299
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.4038,
 "step": 300
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.4567,
 "step": 301
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.3533,
 "step": 302
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.4434,
 "step": 303
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.3037,
 "step": 304
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.49,
 "step": 305
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.5606,
 "step": 306
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.334,
 "step": 307
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.5926,
 "step": 308
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.6084,
 "step": 309
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.4274,
 "step": 310
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.3999,
 "step": 311
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.4386,
 "step": 312
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.2882,
 "step": 313
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.4737,
 "step": 314
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.4087,
 "step": 315
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.3979,
 "step": 316
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.4174,
 "step": 317
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.3294,
 "step": 318
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.409,
 "step": 319
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.4144,
 "step": 320
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.6311,
 "step": 321
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.4711,
 "step": 322
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.3509,
 "step": 323
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.4037,
 "step": 324
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.4688,
 "step": 325
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.4573,
 "step": 326
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.2451,
 "step": 327
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.3223,
 "step": 328
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.2768,
 "step": 329
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.4538,
 "step": 330
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.4078,
 "step": 331
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.4188,
 "step": 332
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.3864,
 "step": 333
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.3327,
 "step": 334
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.3103,
 "step": 335
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.3625,
 "step": 336
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.3586,
 "step": 337
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.3639,
 "step": 338
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.3828,
 "step": 339
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.352,
 "step": 340
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.3199,
 "step": 341
 },
 {
 "epoch": 0.02,
 "learning_rate": 5e-06,
 "loss": 2.3379,
 "step": 342
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.5431,
 "step": 343
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.3285,
 "step": 344
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.5247,
 "step": 345
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.4093,
 "step": 346
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.4002,
 "step": 347
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.3856,
 "step": 348
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.2884,
 "step": 349
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.2656,
 "step": 350
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.2942,
 "step": 351
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.3438,
 "step": 352
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.4258,
 "step": 353
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.492,
 "step": 354
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.4193,
 "step": 355
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.1842,
 "step": 356
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.4666,
 "step": 357
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.3804,
 "step": 358
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.3235,
 "step": 359
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.4474,
 "step": 360
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.3337,
 "step": 361
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.4204,
 "step": 362
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.3564,
 "step": 363
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.4102,
 "step": 364
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.3959,
 "step": 365
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.5135,
 "step": 366
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.4559,
 "step": 367
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.3929,
 "step": 368
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.4304,
 "step": 369
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.2383,
 "step": 370
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.3116,
 "step": 371
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.4058,
 "step": 372
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.129,
 "step": 373
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.222,
 "step": 374
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.0865,
 "step": 375
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.4229,
 "step": 376
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.3515,
 "step": 377
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.2382,
 "step": 378
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.4002,
 "step": 379
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.3593,
 "step": 380
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.4797,
 "step": 381
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.2068,
 "step": 382
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.3053,
 "step": 383
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.3749,
 "step": 384
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.3414,
 "step": 385
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.324,
 "step": 386
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.3991,
 "step": 387
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.334,
 "step": 388
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.2266,
 "step": 389
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.3956,
 "step": 390
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.3382,
 "step": 391
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.2861,
 "step": 392
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.361,
 "step": 393
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.362,
 "step": 394
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.3787,
 "step": 395
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.2466,
 "step": 396
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.242,
 "step": 397
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.4188,
 "step": 398
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.4505,
 "step": 399
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.2417,
 "step": 400
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.4674,
 "step": 401
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.4241,
 "step": 402
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.4395,
 "step": 403
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.1007,
 "step": 404
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.3334,
 "step": 405
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.2629,
 "step": 406
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.3649,
 "step": 407
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.4357,
 "step": 408
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.3871,
 "step": 409
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.3774,
 "step": 410
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.436,
 "step": 411
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.41,
 "step": 412
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.2928,
 "step": 413
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.273,
 "step": 414
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.1439,
 "step": 415
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.2155,
 "step": 416
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.435,
 "step": 417
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.3334,
 "step": 418
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.2998,
 "step": 419
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.2297,
 "step": 420
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.3031,
 "step": 421
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.2057,
 "step": 422
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.4307,
 "step": 423
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.3086,
 "step": 424
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.3757,
 "step": 425
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.2866,
 "step": 426
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.2531,
 "step": 427
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.2498,
 "step": 428
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.328,
 "step": 429
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.2989,
 "step": 430
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.2262,
 "step": 431
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.3834,
 "step": 432
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.2916,
 "step": 433
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.3017,
 "step": 434
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.321,
 "step": 435
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.3299,
 "step": 436
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.3741,
 "step": 437
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.2994,
 "step": 438
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.3326,
 "step": 439
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.3245,
 "step": 440
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.3005,
 "step": 441
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.2355,
 "step": 442
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.3688,
 "step": 443
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.3327,
 "step": 444
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.3421,
 "step": 445
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.3625,
 "step": 446
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.1771,
 "step": 447
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.3608,
 "step": 448
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.2887,
 "step": 449
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.2824,
 "step": 450
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.2585,
 "step": 451
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.3508,
 "step": 452
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.2106,
 "step": 453
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.2993,
 "step": 454
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.2442,
 "step": 455
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.2128,
 "step": 456
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.3994,
 "step": 457
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.2651,
 "step": 458
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.3396,
 "step": 459
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.249,
 "step": 460
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.1616,
 "step": 461
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.2997,
 "step": 462
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.4295,
 "step": 463
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.2785,
 "step": 464
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.3247,
 "step": 465
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.3932,
 "step": 466
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.2094,
 "step": 467
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.3563,
 "step": 468
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.4192,
 "step": 469
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.2554,
 "step": 470
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.2965,
 "step": 471
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.2807,
 "step": 472
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.0843,
 "step": 473
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.2973,
 "step": 474
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.2276,
 "step": 475
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.2649,
 "step": 476
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.4174,
 "step": 477
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.3409,
 "step": 478
 },
 {
 "epoch": 0.03,
 "learning_rate": 5e-06,
 "loss": 2.3994,
 "step": 479
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.3197,
 "step": 480
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.1879,
 "step": 481
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.2375,
 "step": 482
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.205,
 "step": 483
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.3538,
 "step": 484
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.2691,
 "step": 485
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.2389,
 "step": 486
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.2522,
 "step": 487
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.2241,
 "step": 488
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.291,
 "step": 489
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.3417,
 "step": 490
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.2723,
 "step": 491
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.255,
 "step": 492
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.272,
 "step": 493
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.2328,
 "step": 494
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.2335,
 "step": 495
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.3181,
 "step": 496
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.4039,
 "step": 497
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.3684,
 "step": 498
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.3547,
 "step": 499
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.2805,
 "step": 500
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.3682,
 "step": 501
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.3655,
 "step": 502
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.1753,
 "step": 503
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.2609,
 "step": 504
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.2362,
 "step": 505
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.1753,
 "step": 506
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.3172,
 "step": 507
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.3005,
 "step": 508
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.1617,
 "step": 509
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.2692,
 "step": 510
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.2409,
 "step": 511
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.3036,
 "step": 512
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.2643,
 "step": 513
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.1754,
 "step": 514
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.2657,
 "step": 515
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.3146,
 "step": 516
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.2148,
 "step": 517
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.2063,
 "step": 518
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.1886,
 "step": 519
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.2478,
 "step": 520
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.301,
 "step": 521
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.1773,
 "step": 522
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.1678,
 "step": 523
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.4945,
 "step": 524
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.1524,
 "step": 525
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.434,
 "step": 526
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.2696,
 "step": 527
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.2781,
 "step": 528
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.0438,
 "step": 529
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.2034,
 "step": 530
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.3268,
 "step": 531
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.1514,
 "step": 532
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.3219,
 "step": 533
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.3067,
 "step": 534
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.1166,
 "step": 535
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.2664,
 "step": 536
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.2855,
 "step": 537
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.2451,
 "step": 538
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.2199,
 "step": 539
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.1773,
 "step": 540
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.1842,
 "step": 541
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.4004,
 "step": 542
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.2502,
 "step": 543
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.3524,
 "step": 544
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.3295,
 "step": 545
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.1994,
 "step": 546
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.2618,
 "step": 547
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.3195,
 "step": 548
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.2457,
 "step": 549
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.244,
 "step": 550
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.284,
 "step": 551
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.3249,
 "step": 552
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.2361,
 "step": 553
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.2633,
 "step": 554
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.3222,
 "step": 555
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.2015,
 "step": 556
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.2338,
 "step": 557
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.3515,
 "step": 558
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.2573,
 "step": 559
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.3614,
 "step": 560
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.2731,
 "step": 561
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.2712,
 "step": 562
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.2383,
 "step": 563
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.1763,
 "step": 564
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.2481,
 "step": 565
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.2288,
 "step": 566
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.1605,
 "step": 567
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.3264,
 "step": 568
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.3742,
 "step": 569
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.4745,
 "step": 570
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.2066,
 "step": 571
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.2045,
 "step": 572
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.2278,
 "step": 573
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.3434,
 "step": 574
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.2345,
 "step": 575
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.2188,
 "step": 576
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.2338,
 "step": 577
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.2529,
 "step": 578
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.1843,
 "step": 579
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.3591,
 "step": 580
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.4078,
 "step": 581
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.1554,
 "step": 582
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.3483,
 "step": 583
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.2998,
 "step": 584
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.2683,
 "step": 585
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.1864,
 "step": 586
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.1914,
 "step": 587
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.1801,
 "step": 588
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.1201,
 "step": 589
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.1239,
 "step": 590
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.2476,
 "step": 591
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.2376,
 "step": 592
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.2214,
 "step": 593
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.1813,
 "step": 594
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.2263,
 "step": 595
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.2287,
 "step": 596
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.2707,
 "step": 597
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.2916,
 "step": 598
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.3861,
 "step": 599
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.3033,
 "step": 600
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.2953,
 "step": 601
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.1112,
 "step": 602
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.321,
 "step": 603
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.2917,
 "step": 604
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.0078,
 "step": 605
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.187,
 "step": 606
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.1913,
 "step": 607
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.1619,
 "step": 608
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.3647,
 "step": 609
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.3575,
 "step": 610
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.1744,
 "step": 611
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.2569,
 "step": 612
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.1844,
 "step": 613
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.2062,
 "step": 614
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.2458,
 "step": 615
 },
 {
 "epoch": 0.04,
 "learning_rate": 5e-06,
 "loss": 2.2573,
 "step": 616
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.3622,
 "step": 617
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.1643,
 "step": 618
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.3098,
 "step": 619
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.3771,
 "step": 620
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.3758,
 "step": 621
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.2323,
 "step": 622
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.1375,
 "step": 623
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.2017,
 "step": 624
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.2073,
 "step": 625
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.2575,
 "step": 626
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.2798,
 "step": 627
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.1912,
 "step": 628
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.2217,
 "step": 629
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.1462,
 "step": 630
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.3194,
 "step": 631
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.1854,
 "step": 632
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.0951,
 "step": 633
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.1063,
 "step": 634
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.1629,
 "step": 635
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.2903,
 "step": 636
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.0397,
 "step": 637
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.0962,
 "step": 638
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.2192,
 "step": 639
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.1281,
 "step": 640
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.1983,
 "step": 641
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.339,
 "step": 642
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.2111,
 "step": 643
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.0054,
 "step": 644
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.2629,
 "step": 645
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.2389,
 "step": 646
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.2019,
 "step": 647
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.2796,
 "step": 648
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.2478,
 "step": 649
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.3493,
 "step": 650
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.2706,
 "step": 651
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.3583,
 "step": 652
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.0723,
 "step": 653
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.3235,
 "step": 654
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.2284,
 "step": 655
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.2282,
 "step": 656
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.2596,
 "step": 657
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.2352,
 "step": 658
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.203,
 "step": 659
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.2811,
 "step": 660
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.2728,
 "step": 661
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.0994,
 "step": 662
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.0213,
 "step": 663
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.2741,
 "step": 664
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.1986,
 "step": 665
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.2591,
 "step": 666
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.0232,
 "step": 667
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.1402,
 "step": 668
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.2598,
 "step": 669
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.1985,
 "step": 670
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.3841,
 "step": 671
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.2087,
 "step": 672
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.1717,
 "step": 673
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.213,
 "step": 674
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.0074,
 "step": 675
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.1754,
 "step": 676
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.154,
 "step": 677
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.2367,
 "step": 678
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.3127,
 "step": 679
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.3635,
 "step": 680
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.1103,
 "step": 681
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.0653,
 "step": 682
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.1558,
 "step": 683
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.3271,
 "step": 684
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.3628,
 "step": 685
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.0855,
 "step": 686
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.3204,
 "step": 687
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.4032,
 "step": 688
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.3049,
 "step": 689
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.1401,
 "step": 690
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.1734,
 "step": 691
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.2938,
 "step": 692
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.2818,
 "step": 693
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.2178,
 "step": 694
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.1375,
 "step": 695
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.247,
 "step": 696
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.2241,
 "step": 697
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.1636,
 "step": 698
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.284,
 "step": 699
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.179,
 "step": 700
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.2628,
 "step": 701
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.2762,
 "step": 702
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.2877,
 "step": 703
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.005,
 "step": 704
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.1381,
 "step": 705
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.2092,
 "step": 706
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.3192,
 "step": 707
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.2556,
 "step": 708
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.3928,
 "step": 709
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.0413,
 "step": 710
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.1713,
 "step": 711
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.1591,
 "step": 712
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.2034,
 "step": 713
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.0603,
 "step": 714
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.1113,
 "step": 715
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.1562,
 "step": 716
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.1369,
 "step": 717
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.2655,
 "step": 718
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.347,
 "step": 719
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.3423,
 "step": 720
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.2628,
 "step": 721
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.1909,
 "step": 722
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.1432,
 "step": 723
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.1165,
 "step": 724
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.226,
 "step": 725
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.2618,
 "step": 726
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.2137,
 "step": 727
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.1223,
 "step": 728
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.2031,
 "step": 729
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.2553,
 "step": 730
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.251,
 "step": 731
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.0894,
 "step": 732
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.1818,
 "step": 733
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.3629,
 "step": 734
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.2736,
 "step": 735
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.3052,
 "step": 736
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.2613,
 "step": 737
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.1589,
 "step": 738
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.0418,
 "step": 739
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.2337,
 "step": 740
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.3636,
 "step": 741
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.2663,
 "step": 742
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.2256,
 "step": 743
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.294,
 "step": 744
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.3789,
 "step": 745
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.1306,
 "step": 746
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.3467,
 "step": 747
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.1293,
 "step": 748
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.2108,
 "step": 749
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.0935,
 "step": 750
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.1714,
 "step": 751
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.1777,
 "step": 752
 },
 {
 "epoch": 0.05,
 "learning_rate": 5e-06,
 "loss": 2.3676,
 "step": 753
 },
 {
 "epoch": 0.06,
 "learning_rate": 5e-06,
 "loss": 2.1214,
 "step": 754
 },
 {
 "epoch": 0.06,
 "learning_rate": 5e-06,
 "loss": 2.1325,
 "step": 755
 },
 {
 "epoch": 0.06,
 "learning_rate": 5e-06,
 "loss": 2.209,
 "step": 756
 },
 {
 "epoch": 0.06,
 "learning_rate": 5e-06,
 "loss": 2.2387,
 "step": 757
 },
 {
 "epoch": 0.06,
 "learning_rate": 5e-06,
 "loss": 2.3381,
 "step": 758
 },
 {
 "epoch": 0.06,
 "learning_rate": 5e-06,
 "loss": 2.2048,
 "step": 759
 },
 {
 "epoch": 0.06,
 "learning_rate": 5e-06,
 "loss": 1.9196,
 "step": 760
 },
 {
 "epoch": 0.06,
 "learning_rate": 5e-06,
 "loss": 2.2138,
 "step": 761
 },
 {
 "epoch": 0.06,
 "learning_rate": 5e-06,
 "loss": 2.0882,
 "step": 762
 },
 {
 "epoch": 0.06,
 "learning_rate": 5e-06,
 "loss": 2.3105,
 "step": 763
 },
 {
 "epoch": 0.06,
 "learning_rate": 5e-06,
 "loss": 2.2885,
 "step": 764
 },
 {
 "epoch": 0.06,
 "learning_rate": 5e-06,
 "loss": 2.1353,
 "step": 765
 },
 {
 "epoch": 0.06,
 "learning_rate": 5e-06,
 "loss": 2.1896,
 "step": 766
 },
 {
 "epoch": 0.06,
 "learning_rate": 5e-06,
 "loss": 2.2285,
 "step": 767
 },
 {
 "epoch": 0.06,
 "learning_rate": 5e-06,
 "loss": 2.2358,
 "step": 768
 },
 {
 "epoch": 0.06,
 "learning_rate": 5e-06,
 "loss": 2.1389,
 "step": 769
 },
 {
 "epoch": 0.06,
 "learning_rate": 5e-06,
 "loss": 2.0973,
 "step": 770
 },
 {
 "epoch": 0.06,
 "learning_rate": 5e-06,
 "loss": 2.1618,
 "step": 771
 },
 {
 "epoch": 0.06,
 "learning_rate": 5e-06,
 "loss": 2.172,
 "step": 772
 },
 {
 "epoch": 0.06,
 "learning_rate": 5e-06,
 "loss": 2.0853,
 "step": 773
 },
 {
 "epoch": 0.06,
 "learning_rate": 5e-06,
 "loss": 2.3629,
 "step": 774
 },
 {
 "epoch": 0.06,
 "learning_rate": 5e-06,
 "loss": 2.1363,
 "step": 775
 },
 {
 "epoch": 0.06,
 "learning_rate": 5e-06,
 "loss": 2.2508,
 "step": 776
 },
 {
 "epoch": 0.06,
 "learning_rate": 5e-06,
 "loss": 2.2474,
 "step": 777
 },
 {
 "epoch": 0.06,
 "learning_rate": 5e-06,
 "loss": 2.4388,
 "step": 778
 },
 {
 "epoch": 0.06,
 "learning_rate": 5e-06,
 "loss": 2.15,
 "step": 779
 },
 {
 "epoch": 0.06,
 "learning_rate": 5e-06,
 "loss": 2.1308,
 "step": 780
 },
 {
 "epoch": 0.06,
 "learning_rate": 5e-06,
 "loss": 2.1943,
 "step": 781
 },
 {
 "epoch": 0.06,
 "learning_rate": 5e-06,
 "loss": 2.1406,
 "step": 782
 },
 {
 "epoch": 0.06,
 "learning_rate": 5e-06,
 "loss": 2.1965,
 "step": 783
 },
 {
 "epoch": 0.06,
 "learning_rate": 5e-06,
 "loss": 2.0482,
 "step": 784
 },
 {
 "epoch": 0.06,
 "learning_rate": 5e-06,
 "loss": 2.1726,
 "step": 785
 },
 {
 "epoch": 0.06,
 "learning_rate": 5e-06,
 "loss": 2.2678,
 "step": 786
 },
 {
 "epoch": 0.06,
 "learning_rate": 5e-06,
 "loss": 2.1922,
 "step": 787
 },
 {
 "epoch": 0.06,
 "learning_rate": 5e-06,
 "loss": 2.1322,
 "step": 788
 },
 {
 "epoch": 0.06,
 "learning_rate": 5e-06,
 "loss": 2.2166,
 "step": 789
 },
 {
 "epoch": 0.06,
 "learning_rate": 5e-06,
 "loss": 2.123,
 "step": 790
 },
 {
 "epoch": 0.06,
 "learning_rate": 5e-06,
 "loss": 2.1716,
 "step": 791
 },
 {
 "epoch": 0.06,
 "learning_rate": 5e-06,
 "loss": 2.1954,
 "step": 792
 },
 {
 "epoch": 0.06,
 "learning_rate": 5e-06,
 "loss": 2.2643,
 "step": 793
 },
 {
 "epoch": 0.06,
 "learning_rate": 5e-06,
 "loss": 2.1578,
 "step": 794
 },
 {
 "epoch": 0.06,
 "learning_rate": 5e-06,
 "loss": 2.1701,
 "step": 795
 },
 {
 "epoch": 0.06,
 "learning_rate": 5e-06,
 "loss": 2.313,
 "step": 796
 },
 {
 "epoch": 0.06,
 "learning_rate": 5e-06,
 "loss": 1.9838,
 "step": 797
 },
 {
 "epoch": 0.06,
 "learning_rate": 5e-06,
 "loss": 2.1982,
 "step": 798
 },
 {
 "epoch": 0.06,
 "learning_rate": 5e-06,
 "loss": 2.2363,
 "step": 799
 },
 {
 "epoch": 0.06,
 "learning_rate": 5e-06,
 "loss": 2.1595,
 "step": 800
 }
 ],
 "logging_steps": 1.0,
 "max_steps": 13699,
 "num_input_tokens_seen": 0,
 "num_train_epochs": 1,
 "save_steps": 800,
 "total_flos": 9.560584163522773e+18,
 "train_batch_size": 2,
 "trial_name": null,
 "trial_params": null
}