LLMSecurity350monoPython / trainer_state.json
MuhammedYahia's picture
Upload folder using huggingface_hub
150e2df
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.04,
"eval_steps": 50,
"global_step": 400,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 5.000000000000001e-07,
"loss": 1.424,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 1.0000000000000002e-06,
"loss": 0.9593,
"step": 2
},
{
"epoch": 0.0,
"learning_rate": 1.5e-06,
"loss": 0.8636,
"step": 3
},
{
"epoch": 0.0,
"learning_rate": 2.0000000000000003e-06,
"loss": 1.0751,
"step": 4
},
{
"epoch": 0.0,
"learning_rate": 2.5e-06,
"loss": 1.0284,
"step": 5
},
{
"epoch": 0.0,
"learning_rate": 3e-06,
"loss": 1.0424,
"step": 6
},
{
"epoch": 0.0,
"learning_rate": 3.5000000000000004e-06,
"loss": 1.154,
"step": 7
},
{
"epoch": 0.0,
"learning_rate": 4.000000000000001e-06,
"loss": 1.4715,
"step": 8
},
{
"epoch": 0.0,
"learning_rate": 4.5e-06,
"loss": 1.5074,
"step": 9
},
{
"epoch": 0.0,
"learning_rate": 5e-06,
"loss": 0.9633,
"step": 10
},
{
"epoch": 0.0,
"learning_rate": 5.500000000000001e-06,
"loss": 0.7885,
"step": 11
},
{
"epoch": 0.0,
"learning_rate": 6e-06,
"loss": 0.9121,
"step": 12
},
{
"epoch": 0.0,
"learning_rate": 6.5000000000000004e-06,
"loss": 1.0456,
"step": 13
},
{
"epoch": 0.0,
"learning_rate": 7.000000000000001e-06,
"loss": 0.8722,
"step": 14
},
{
"epoch": 0.0,
"learning_rate": 7.5e-06,
"loss": 1.0264,
"step": 15
},
{
"epoch": 0.0,
"learning_rate": 8.000000000000001e-06,
"loss": 1.2709,
"step": 16
},
{
"epoch": 0.0,
"learning_rate": 8.500000000000002e-06,
"loss": 1.1519,
"step": 17
},
{
"epoch": 0.0,
"learning_rate": 9e-06,
"loss": 0.9543,
"step": 18
},
{
"epoch": 0.0,
"learning_rate": 9.5e-06,
"loss": 0.7449,
"step": 19
},
{
"epoch": 0.0,
"learning_rate": 1e-05,
"loss": 1.0338,
"step": 20
},
{
"epoch": 0.0,
"learning_rate": 1.05e-05,
"loss": 1.3037,
"step": 21
},
{
"epoch": 0.0,
"learning_rate": 1.1000000000000001e-05,
"loss": 1.0368,
"step": 22
},
{
"epoch": 0.0,
"learning_rate": 1.1500000000000002e-05,
"loss": 1.076,
"step": 23
},
{
"epoch": 0.0,
"learning_rate": 1.2e-05,
"loss": 1.4172,
"step": 24
},
{
"epoch": 0.0,
"learning_rate": 1.25e-05,
"loss": 0.7517,
"step": 25
},
{
"epoch": 0.0,
"learning_rate": 1.3000000000000001e-05,
"loss": 1.0805,
"step": 26
},
{
"epoch": 0.0,
"learning_rate": 1.3500000000000001e-05,
"loss": 0.9719,
"step": 27
},
{
"epoch": 0.0,
"learning_rate": 1.4000000000000001e-05,
"loss": 0.8599,
"step": 28
},
{
"epoch": 0.0,
"learning_rate": 1.45e-05,
"loss": 1.0069,
"step": 29
},
{
"epoch": 0.0,
"learning_rate": 1.5e-05,
"loss": 0.8821,
"step": 30
},
{
"epoch": 0.0,
"learning_rate": 1.55e-05,
"loss": 1.324,
"step": 31
},
{
"epoch": 0.0,
"learning_rate": 1.6000000000000003e-05,
"loss": 0.7325,
"step": 32
},
{
"epoch": 0.0,
"learning_rate": 1.65e-05,
"loss": 0.9195,
"step": 33
},
{
"epoch": 0.0,
"learning_rate": 1.7000000000000003e-05,
"loss": 1.0733,
"step": 34
},
{
"epoch": 0.0,
"learning_rate": 1.75e-05,
"loss": 1.0441,
"step": 35
},
{
"epoch": 0.0,
"learning_rate": 1.8e-05,
"loss": 0.9961,
"step": 36
},
{
"epoch": 0.0,
"learning_rate": 1.85e-05,
"loss": 1.0976,
"step": 37
},
{
"epoch": 0.0,
"learning_rate": 1.9e-05,
"loss": 0.7981,
"step": 38
},
{
"epoch": 0.0,
"learning_rate": 1.9500000000000003e-05,
"loss": 0.9183,
"step": 39
},
{
"epoch": 0.0,
"learning_rate": 2e-05,
"loss": 1.2273,
"step": 40
},
{
"epoch": 0.0,
"learning_rate": 2.05e-05,
"loss": 1.0005,
"step": 41
},
{
"epoch": 0.0,
"learning_rate": 2.1e-05,
"loss": 1.2448,
"step": 42
},
{
"epoch": 0.0,
"learning_rate": 2.15e-05,
"loss": 1.4173,
"step": 43
},
{
"epoch": 0.0,
"learning_rate": 2.2000000000000003e-05,
"loss": 0.6956,
"step": 44
},
{
"epoch": 0.0,
"learning_rate": 2.25e-05,
"loss": 0.7313,
"step": 45
},
{
"epoch": 0.0,
"learning_rate": 2.3000000000000003e-05,
"loss": 0.9992,
"step": 46
},
{
"epoch": 0.0,
"learning_rate": 2.35e-05,
"loss": 1.0287,
"step": 47
},
{
"epoch": 0.0,
"learning_rate": 2.4e-05,
"loss": 1.3604,
"step": 48
},
{
"epoch": 0.0,
"learning_rate": 2.45e-05,
"loss": 0.7198,
"step": 49
},
{
"epoch": 0.01,
"learning_rate": 2.5e-05,
"loss": 0.2974,
"step": 50
},
{
"epoch": 0.01,
"eval_loss": 1.1389975547790527,
"eval_runtime": 71.831,
"eval_samples_per_second": 2.77,
"eval_steps_per_second": 0.696,
"step": 50
},
{
"epoch": 0.01,
"learning_rate": 2.5500000000000003e-05,
"loss": 0.5533,
"step": 51
},
{
"epoch": 0.01,
"learning_rate": 2.6000000000000002e-05,
"loss": 1.2819,
"step": 52
},
{
"epoch": 0.01,
"learning_rate": 2.6500000000000004e-05,
"loss": 1.4542,
"step": 53
},
{
"epoch": 0.01,
"learning_rate": 2.7000000000000002e-05,
"loss": 1.5254,
"step": 54
},
{
"epoch": 0.01,
"learning_rate": 2.7500000000000004e-05,
"loss": 1.1699,
"step": 55
},
{
"epoch": 0.01,
"learning_rate": 2.8000000000000003e-05,
"loss": 1.3209,
"step": 56
},
{
"epoch": 0.01,
"learning_rate": 2.8499999999999998e-05,
"loss": 0.659,
"step": 57
},
{
"epoch": 0.01,
"learning_rate": 2.9e-05,
"loss": 1.0342,
"step": 58
},
{
"epoch": 0.01,
"learning_rate": 2.95e-05,
"loss": 1.1414,
"step": 59
},
{
"epoch": 0.01,
"learning_rate": 3e-05,
"loss": 1.2102,
"step": 60
},
{
"epoch": 0.01,
"learning_rate": 3.05e-05,
"loss": 1.0656,
"step": 61
},
{
"epoch": 0.01,
"learning_rate": 3.1e-05,
"loss": 1.0089,
"step": 62
},
{
"epoch": 0.01,
"learning_rate": 3.15e-05,
"loss": 1.2177,
"step": 63
},
{
"epoch": 0.01,
"learning_rate": 3.2000000000000005e-05,
"loss": 0.965,
"step": 64
},
{
"epoch": 0.01,
"learning_rate": 3.2500000000000004e-05,
"loss": 0.8526,
"step": 65
},
{
"epoch": 0.01,
"learning_rate": 3.3e-05,
"loss": 0.9656,
"step": 66
},
{
"epoch": 0.01,
"learning_rate": 3.35e-05,
"loss": 1.0447,
"step": 67
},
{
"epoch": 0.01,
"learning_rate": 3.4000000000000007e-05,
"loss": 0.7947,
"step": 68
},
{
"epoch": 0.01,
"learning_rate": 3.45e-05,
"loss": 0.7962,
"step": 69
},
{
"epoch": 0.01,
"learning_rate": 3.5e-05,
"loss": 0.5062,
"step": 70
},
{
"epoch": 0.01,
"learning_rate": 3.55e-05,
"loss": 0.9352,
"step": 71
},
{
"epoch": 0.01,
"learning_rate": 3.6e-05,
"loss": 1.8548,
"step": 72
},
{
"epoch": 0.01,
"learning_rate": 3.65e-05,
"loss": 2.0769,
"step": 73
},
{
"epoch": 0.01,
"learning_rate": 3.7e-05,
"loss": 0.8846,
"step": 74
},
{
"epoch": 0.01,
"learning_rate": 3.7500000000000003e-05,
"loss": 0.864,
"step": 75
},
{
"epoch": 0.01,
"learning_rate": 3.8e-05,
"loss": 0.8684,
"step": 76
},
{
"epoch": 0.01,
"learning_rate": 3.85e-05,
"loss": 1.0395,
"step": 77
},
{
"epoch": 0.01,
"learning_rate": 3.9000000000000006e-05,
"loss": 1.1751,
"step": 78
},
{
"epoch": 0.01,
"learning_rate": 3.9500000000000005e-05,
"loss": 0.7136,
"step": 79
},
{
"epoch": 0.01,
"learning_rate": 4e-05,
"loss": 0.5699,
"step": 80
},
{
"epoch": 0.01,
"learning_rate": 4.05e-05,
"loss": 0.782,
"step": 81
},
{
"epoch": 0.01,
"learning_rate": 4.1e-05,
"loss": 1.4756,
"step": 82
},
{
"epoch": 0.01,
"learning_rate": 4.15e-05,
"loss": 1.3176,
"step": 83
},
{
"epoch": 0.01,
"learning_rate": 4.2e-05,
"loss": 1.2823,
"step": 84
},
{
"epoch": 0.01,
"learning_rate": 4.25e-05,
"loss": 1.3336,
"step": 85
},
{
"epoch": 0.01,
"learning_rate": 4.3e-05,
"loss": 1.3062,
"step": 86
},
{
"epoch": 0.01,
"learning_rate": 4.35e-05,
"loss": 1.2965,
"step": 87
},
{
"epoch": 0.01,
"learning_rate": 4.4000000000000006e-05,
"loss": 1.7232,
"step": 88
},
{
"epoch": 0.01,
"learning_rate": 4.4500000000000004e-05,
"loss": 1.0913,
"step": 89
},
{
"epoch": 0.01,
"learning_rate": 4.5e-05,
"loss": 1.3334,
"step": 90
},
{
"epoch": 0.01,
"learning_rate": 4.55e-05,
"loss": 1.1843,
"step": 91
},
{
"epoch": 0.01,
"learning_rate": 4.600000000000001e-05,
"loss": 0.9398,
"step": 92
},
{
"epoch": 0.01,
"learning_rate": 4.6500000000000005e-05,
"loss": 0.7859,
"step": 93
},
{
"epoch": 0.01,
"learning_rate": 4.7e-05,
"loss": 1.2015,
"step": 94
},
{
"epoch": 0.01,
"learning_rate": 4.75e-05,
"loss": 1.1383,
"step": 95
},
{
"epoch": 0.01,
"learning_rate": 4.8e-05,
"loss": 0.9095,
"step": 96
},
{
"epoch": 0.01,
"learning_rate": 4.85e-05,
"loss": 0.9644,
"step": 97
},
{
"epoch": 0.01,
"learning_rate": 4.9e-05,
"loss": 1.2399,
"step": 98
},
{
"epoch": 0.01,
"learning_rate": 4.9500000000000004e-05,
"loss": 0.8818,
"step": 99
},
{
"epoch": 0.01,
"learning_rate": 5e-05,
"loss": 0.9184,
"step": 100
},
{
"epoch": 0.01,
"eval_loss": 1.1290233135223389,
"eval_runtime": 72.0275,
"eval_samples_per_second": 2.763,
"eval_steps_per_second": 0.694,
"step": 100
},
{
"epoch": 0.01,
"learning_rate": 4.999999874125034e-05,
"loss": 0.4027,
"step": 101
},
{
"epoch": 0.01,
"learning_rate": 4.9999994965001495e-05,
"loss": 0.0226,
"step": 102
},
{
"epoch": 0.01,
"learning_rate": 4.999998867125384e-05,
"loss": 0.0269,
"step": 103
},
{
"epoch": 0.01,
"learning_rate": 4.9999979860008006e-05,
"loss": 0.025,
"step": 104
},
{
"epoch": 0.01,
"learning_rate": 4.999996853126489e-05,
"loss": 0.0204,
"step": 105
},
{
"epoch": 0.01,
"learning_rate": 4.999995468502562e-05,
"loss": 0.0263,
"step": 106
},
{
"epoch": 0.01,
"learning_rate": 4.9999938321291604e-05,
"loss": 0.0248,
"step": 107
},
{
"epoch": 0.01,
"learning_rate": 4.999991944006448e-05,
"loss": 0.0274,
"step": 108
},
{
"epoch": 0.01,
"learning_rate": 4.9999898041346155e-05,
"loss": 0.0218,
"step": 109
},
{
"epoch": 0.01,
"learning_rate": 4.999987412513878e-05,
"loss": 0.0182,
"step": 110
},
{
"epoch": 0.01,
"learning_rate": 4.999984769144476e-05,
"loss": 0.0205,
"step": 111
},
{
"epoch": 0.01,
"learning_rate": 4.9999818740266766e-05,
"loss": 0.0229,
"step": 112
},
{
"epoch": 0.01,
"learning_rate": 4.9999787271607714e-05,
"loss": 0.0416,
"step": 113
},
{
"epoch": 0.01,
"learning_rate": 4.999975328547076e-05,
"loss": 0.0191,
"step": 114
},
{
"epoch": 0.01,
"learning_rate": 4.999971678185933e-05,
"loss": 0.0205,
"step": 115
},
{
"epoch": 0.01,
"learning_rate": 4.9999677760777114e-05,
"loss": 0.0184,
"step": 116
},
{
"epoch": 0.01,
"learning_rate": 4.999963622222803e-05,
"loss": 0.018,
"step": 117
},
{
"epoch": 0.01,
"learning_rate": 4.9999592166216256e-05,
"loss": 0.0242,
"step": 118
},
{
"epoch": 0.01,
"learning_rate": 4.999954559274624e-05,
"loss": 0.4053,
"step": 119
},
{
"epoch": 0.01,
"learning_rate": 4.999949650182266e-05,
"loss": 0.5058,
"step": 120
},
{
"epoch": 0.01,
"learning_rate": 4.9999444893450476e-05,
"loss": 0.9192,
"step": 121
},
{
"epoch": 0.01,
"learning_rate": 4.999939076763487e-05,
"loss": 1.1211,
"step": 122
},
{
"epoch": 0.01,
"learning_rate": 4.99993341243813e-05,
"loss": 0.7105,
"step": 123
},
{
"epoch": 0.01,
"learning_rate": 4.999927496369547e-05,
"loss": 0.851,
"step": 124
},
{
"epoch": 0.01,
"learning_rate": 4.999921328558333e-05,
"loss": 0.763,
"step": 125
},
{
"epoch": 0.01,
"learning_rate": 4.99991490900511e-05,
"loss": 1.1325,
"step": 126
},
{
"epoch": 0.01,
"learning_rate": 4.999908237710523e-05,
"loss": 1.1006,
"step": 127
},
{
"epoch": 0.01,
"learning_rate": 4.999901314675246e-05,
"loss": 0.9444,
"step": 128
},
{
"epoch": 0.01,
"learning_rate": 4.9998941398999754e-05,
"loss": 1.0285,
"step": 129
},
{
"epoch": 0.01,
"learning_rate": 4.999886713385432e-05,
"loss": 0.9176,
"step": 130
},
{
"epoch": 0.01,
"learning_rate": 4.999879035132366e-05,
"loss": 1.2408,
"step": 131
},
{
"epoch": 0.01,
"learning_rate": 4.999871105141549e-05,
"loss": 1.0897,
"step": 132
},
{
"epoch": 0.01,
"learning_rate": 4.999862923413781e-05,
"loss": 0.6091,
"step": 133
},
{
"epoch": 0.01,
"learning_rate": 4.999854489949884e-05,
"loss": 1.1689,
"step": 134
},
{
"epoch": 0.01,
"learning_rate": 4.999845804750709e-05,
"loss": 1.5978,
"step": 135
},
{
"epoch": 0.01,
"learning_rate": 4.999836867817129e-05,
"loss": 1.4423,
"step": 136
},
{
"epoch": 0.01,
"learning_rate": 4.999827679150045e-05,
"loss": 0.9095,
"step": 137
},
{
"epoch": 0.01,
"learning_rate": 4.999818238750382e-05,
"loss": 0.7459,
"step": 138
},
{
"epoch": 0.01,
"learning_rate": 4.999808546619091e-05,
"loss": 0.8685,
"step": 139
},
{
"epoch": 0.01,
"learning_rate": 4.9997986027571485e-05,
"loss": 1.1481,
"step": 140
},
{
"epoch": 0.01,
"learning_rate": 4.9997884071655546e-05,
"loss": 2.5944,
"step": 141
},
{
"epoch": 0.01,
"learning_rate": 4.999777959845336e-05,
"loss": 0.8284,
"step": 142
},
{
"epoch": 0.01,
"learning_rate": 4.999767260797546e-05,
"loss": 1.0722,
"step": 143
},
{
"epoch": 0.01,
"learning_rate": 4.999756310023261e-05,
"loss": 1.0372,
"step": 144
},
{
"epoch": 0.01,
"learning_rate": 4.9997451075235834e-05,
"loss": 1.1565,
"step": 145
},
{
"epoch": 0.01,
"learning_rate": 4.9997336532996426e-05,
"loss": 1.1735,
"step": 146
},
{
"epoch": 0.01,
"learning_rate": 4.999721947352591e-05,
"loss": 0.861,
"step": 147
},
{
"epoch": 0.01,
"learning_rate": 4.999709989683607e-05,
"loss": 0.7458,
"step": 148
},
{
"epoch": 0.01,
"learning_rate": 4.999697780293897e-05,
"loss": 1.1438,
"step": 149
},
{
"epoch": 0.01,
"learning_rate": 4.9996853191846885e-05,
"loss": 0.8448,
"step": 150
},
{
"epoch": 0.01,
"eval_loss": 1.1207772493362427,
"eval_runtime": 72.9183,
"eval_samples_per_second": 2.729,
"eval_steps_per_second": 0.686,
"step": 150
},
{
"epoch": 0.02,
"learning_rate": 4.999672606357236e-05,
"loss": 0.4995,
"step": 151
},
{
"epoch": 0.02,
"learning_rate": 4.99965964181282e-05,
"loss": 0.2793,
"step": 152
},
{
"epoch": 0.02,
"learning_rate": 4.9996464255527475e-05,
"loss": 0.5865,
"step": 153
},
{
"epoch": 0.02,
"learning_rate": 4.999632957578349e-05,
"loss": 0.7137,
"step": 154
},
{
"epoch": 0.02,
"learning_rate": 4.9996192378909786e-05,
"loss": 0.495,
"step": 155
},
{
"epoch": 0.02,
"learning_rate": 4.9996052664920195e-05,
"loss": 0.9241,
"step": 156
},
{
"epoch": 0.02,
"learning_rate": 4.999591043382878e-05,
"loss": 2.3316,
"step": 157
},
{
"epoch": 0.02,
"learning_rate": 4.9995765685649885e-05,
"loss": 1.1994,
"step": 158
},
{
"epoch": 0.02,
"learning_rate": 4.999561842039806e-05,
"loss": 0.6486,
"step": 159
},
{
"epoch": 0.02,
"learning_rate": 4.999546863808815e-05,
"loss": 0.6252,
"step": 160
},
{
"epoch": 0.02,
"learning_rate": 4.999531633873522e-05,
"loss": 1.0976,
"step": 161
},
{
"epoch": 0.02,
"learning_rate": 4.9995161522354626e-05,
"loss": 0.8763,
"step": 162
},
{
"epoch": 0.02,
"learning_rate": 4.9995004188961954e-05,
"loss": 0.4891,
"step": 163
},
{
"epoch": 0.02,
"learning_rate": 4.9994844338573047e-05,
"loss": 0.7395,
"step": 164
},
{
"epoch": 0.02,
"learning_rate": 4.9994681971203985e-05,
"loss": 0.9335,
"step": 165
},
{
"epoch": 0.02,
"learning_rate": 4.999451708687114e-05,
"loss": 0.8835,
"step": 166
},
{
"epoch": 0.02,
"learning_rate": 4.999434968559111e-05,
"loss": 0.7375,
"step": 167
},
{
"epoch": 0.02,
"learning_rate": 4.9994179767380746e-05,
"loss": 1.1447,
"step": 168
},
{
"epoch": 0.02,
"learning_rate": 4.9994007332257166e-05,
"loss": 1.0092,
"step": 169
},
{
"epoch": 0.02,
"learning_rate": 4.9993832380237735e-05,
"loss": 1.2002,
"step": 170
},
{
"epoch": 0.02,
"learning_rate": 4.999365491134006e-05,
"loss": 1.1527,
"step": 171
},
{
"epoch": 0.02,
"learning_rate": 4.999347492558202e-05,
"loss": 0.8259,
"step": 172
},
{
"epoch": 0.02,
"learning_rate": 4.9993292422981744e-05,
"loss": 0.7446,
"step": 173
},
{
"epoch": 0.02,
"learning_rate": 4.9993107403557606e-05,
"loss": 0.8483,
"step": 174
},
{
"epoch": 0.02,
"learning_rate": 4.999291986732823e-05,
"loss": 0.9139,
"step": 175
},
{
"epoch": 0.02,
"learning_rate": 4.999272981431251e-05,
"loss": 1.1312,
"step": 176
},
{
"epoch": 0.02,
"learning_rate": 4.999253724452958e-05,
"loss": 1.0392,
"step": 177
},
{
"epoch": 0.02,
"learning_rate": 4.999234215799884e-05,
"loss": 0.9711,
"step": 178
},
{
"epoch": 0.02,
"learning_rate": 4.9992144554739915e-05,
"loss": 0.0736,
"step": 179
},
{
"epoch": 0.02,
"learning_rate": 4.9991944434772734e-05,
"loss": 0.0228,
"step": 180
},
{
"epoch": 0.02,
"learning_rate": 4.999174179811742e-05,
"loss": 0.0183,
"step": 181
},
{
"epoch": 0.02,
"learning_rate": 4.9991536644794394e-05,
"loss": 0.0135,
"step": 182
},
{
"epoch": 0.02,
"learning_rate": 4.9991328974824314e-05,
"loss": 0.0189,
"step": 183
},
{
"epoch": 0.02,
"learning_rate": 4.9991118788228084e-05,
"loss": 0.0138,
"step": 184
},
{
"epoch": 0.02,
"learning_rate": 4.999090608502688e-05,
"loss": 0.0177,
"step": 185
},
{
"epoch": 0.02,
"learning_rate": 4.999069086524212e-05,
"loss": 0.0161,
"step": 186
},
{
"epoch": 0.02,
"learning_rate": 4.999047312889547e-05,
"loss": 0.0227,
"step": 187
},
{
"epoch": 0.02,
"learning_rate": 4.999025287600886e-05,
"loss": 0.0161,
"step": 188
},
{
"epoch": 0.02,
"learning_rate": 4.9990030106604466e-05,
"loss": 0.0178,
"step": 189
},
{
"epoch": 0.02,
"learning_rate": 4.9989804820704735e-05,
"loss": 0.0351,
"step": 190
},
{
"epoch": 0.02,
"learning_rate": 4.998957701833233e-05,
"loss": 0.0169,
"step": 191
},
{
"epoch": 0.02,
"learning_rate": 4.998934669951021e-05,
"loss": 0.0152,
"step": 192
},
{
"epoch": 0.02,
"learning_rate": 4.998911386426156e-05,
"loss": 0.0116,
"step": 193
},
{
"epoch": 0.02,
"learning_rate": 4.998887851260983e-05,
"loss": 0.015,
"step": 194
},
{
"epoch": 0.02,
"learning_rate": 4.998864064457871e-05,
"loss": 0.021,
"step": 195
},
{
"epoch": 0.02,
"learning_rate": 4.998840026019217e-05,
"loss": 0.017,
"step": 196
},
{
"epoch": 0.02,
"learning_rate": 4.99881573594744e-05,
"loss": 0.4376,
"step": 197
},
{
"epoch": 0.02,
"learning_rate": 4.9987911942449874e-05,
"loss": 0.5764,
"step": 198
},
{
"epoch": 0.02,
"learning_rate": 4.998766400914329e-05,
"loss": 1.0406,
"step": 199
},
{
"epoch": 0.02,
"learning_rate": 4.9987413559579636e-05,
"loss": 1.2413,
"step": 200
},
{
"epoch": 0.02,
"eval_loss": 1.1171025037765503,
"eval_runtime": 71.816,
"eval_samples_per_second": 2.771,
"eval_steps_per_second": 0.696,
"step": 200
},
{
"epoch": 0.02,
"learning_rate": 4.998716059378411e-05,
"loss": 0.9615,
"step": 201
},
{
"epoch": 0.02,
"learning_rate": 4.99869051117822e-05,
"loss": 0.9232,
"step": 202
},
{
"epoch": 0.02,
"learning_rate": 4.998664711359963e-05,
"loss": 1.3542,
"step": 203
},
{
"epoch": 0.02,
"learning_rate": 4.9986386599262374e-05,
"loss": 0.7679,
"step": 204
},
{
"epoch": 0.02,
"learning_rate": 4.998612356879667e-05,
"loss": 0.9539,
"step": 205
},
{
"epoch": 0.02,
"learning_rate": 4.9985858022229015e-05,
"loss": 1.3759,
"step": 206
},
{
"epoch": 0.02,
"learning_rate": 4.998558995958614e-05,
"loss": 0.9567,
"step": 207
},
{
"epoch": 0.02,
"learning_rate": 4.998531938089503e-05,
"loss": 0.8245,
"step": 208
},
{
"epoch": 0.02,
"learning_rate": 4.998504628618296e-05,
"loss": 0.8987,
"step": 209
},
{
"epoch": 0.02,
"learning_rate": 4.99847706754774e-05,
"loss": 0.9503,
"step": 210
},
{
"epoch": 0.02,
"learning_rate": 4.998449254880612e-05,
"loss": 0.9907,
"step": 211
},
{
"epoch": 0.02,
"learning_rate": 4.998421190619711e-05,
"loss": 1.1336,
"step": 212
},
{
"epoch": 0.02,
"learning_rate": 4.9983928747678663e-05,
"loss": 1.3901,
"step": 213
},
{
"epoch": 0.02,
"learning_rate": 4.998364307327927e-05,
"loss": 1.5705,
"step": 214
},
{
"epoch": 0.02,
"learning_rate": 4.99833548830277e-05,
"loss": 0.8125,
"step": 215
},
{
"epoch": 0.02,
"learning_rate": 4.9983064176952976e-05,
"loss": 0.82,
"step": 216
},
{
"epoch": 0.02,
"learning_rate": 4.9982770955084376e-05,
"loss": 0.7146,
"step": 217
},
{
"epoch": 0.02,
"learning_rate": 4.9982475217451426e-05,
"loss": 1.0612,
"step": 218
},
{
"epoch": 0.02,
"learning_rate": 4.998217696408391e-05,
"loss": 0.7297,
"step": 219
},
{
"epoch": 0.02,
"learning_rate": 4.9981876195011844e-05,
"loss": 0.9502,
"step": 220
},
{
"epoch": 0.02,
"learning_rate": 4.998157291026553e-05,
"loss": 1.1155,
"step": 221
},
{
"epoch": 0.02,
"learning_rate": 4.998126710987552e-05,
"loss": 1.1281,
"step": 222
},
{
"epoch": 0.02,
"learning_rate": 4.9980958793872577e-05,
"loss": 0.848,
"step": 223
},
{
"epoch": 0.02,
"learning_rate": 4.998064796228779e-05,
"loss": 0.6496,
"step": 224
},
{
"epoch": 0.02,
"learning_rate": 4.998033461515242e-05,
"loss": 0.9489,
"step": 225
},
{
"epoch": 0.02,
"learning_rate": 4.9980018752498035e-05,
"loss": 1.1667,
"step": 226
},
{
"epoch": 0.02,
"learning_rate": 4.9979700374356455e-05,
"loss": 1.0077,
"step": 227
},
{
"epoch": 0.02,
"learning_rate": 4.997937948075973e-05,
"loss": 0.8891,
"step": 228
},
{
"epoch": 0.02,
"learning_rate": 4.997905607174017e-05,
"loss": 1.2342,
"step": 229
},
{
"epoch": 0.02,
"learning_rate": 4.9978730147330355e-05,
"loss": 0.7439,
"step": 230
},
{
"epoch": 0.02,
"learning_rate": 4.9978401707563096e-05,
"loss": 0.8864,
"step": 231
},
{
"epoch": 0.02,
"learning_rate": 4.997807075247146e-05,
"loss": 0.8909,
"step": 232
},
{
"epoch": 0.02,
"learning_rate": 4.997773728208879e-05,
"loss": 0.928,
"step": 233
},
{
"epoch": 0.02,
"learning_rate": 4.997740129644865e-05,
"loss": 0.8764,
"step": 234
},
{
"epoch": 0.02,
"learning_rate": 4.9977062795584893e-05,
"loss": 0.8078,
"step": 235
},
{
"epoch": 0.02,
"learning_rate": 4.99767217795316e-05,
"loss": 1.2065,
"step": 236
},
{
"epoch": 0.02,
"learning_rate": 4.9976378248323095e-05,
"loss": 0.6946,
"step": 237
},
{
"epoch": 0.02,
"learning_rate": 4.997603220199399e-05,
"loss": 0.8255,
"step": 238
},
{
"epoch": 0.02,
"learning_rate": 4.9975683640579126e-05,
"loss": 0.9762,
"step": 239
},
{
"epoch": 0.02,
"learning_rate": 4.99753325641136e-05,
"loss": 0.9771,
"step": 240
},
{
"epoch": 0.02,
"learning_rate": 4.997497897263277e-05,
"loss": 0.8766,
"step": 241
},
{
"epoch": 0.02,
"learning_rate": 4.997462286617224e-05,
"loss": 1.03,
"step": 242
},
{
"epoch": 0.02,
"learning_rate": 4.997426424476787e-05,
"loss": 0.7792,
"step": 243
},
{
"epoch": 0.02,
"learning_rate": 4.997390310845578e-05,
"loss": 0.7772,
"step": 244
},
{
"epoch": 0.02,
"learning_rate": 4.997353945727232e-05,
"loss": 0.9822,
"step": 245
},
{
"epoch": 0.02,
"learning_rate": 4.9973173291254126e-05,
"loss": 0.9403,
"step": 246
},
{
"epoch": 0.02,
"learning_rate": 4.997280461043806e-05,
"loss": 1.117,
"step": 247
},
{
"epoch": 0.02,
"learning_rate": 4.997243341486127e-05,
"loss": 1.3156,
"step": 248
},
{
"epoch": 0.02,
"learning_rate": 4.9972059704561094e-05,
"loss": 0.7289,
"step": 249
},
{
"epoch": 0.03,
"learning_rate": 4.99716834795752e-05,
"loss": 0.7193,
"step": 250
},
{
"epoch": 0.03,
"eval_loss": 1.108275294303894,
"eval_runtime": 72.6609,
"eval_samples_per_second": 2.739,
"eval_steps_per_second": 0.688,
"step": 250
},
{
"epoch": 0.03,
"learning_rate": 4.9971304739941465e-05,
"loss": 0.8273,
"step": 251
},
{
"epoch": 0.03,
"learning_rate": 4.9970923485698025e-05,
"loss": 0.8979,
"step": 252
},
{
"epoch": 0.03,
"learning_rate": 4.997053971688327e-05,
"loss": 1.1935,
"step": 253
},
{
"epoch": 0.03,
"learning_rate": 4.997015343353585e-05,
"loss": 0.6769,
"step": 254
},
{
"epoch": 0.03,
"learning_rate": 4.996976463569467e-05,
"loss": 0.1888,
"step": 255
},
{
"epoch": 0.03,
"learning_rate": 4.996937332339887e-05,
"loss": 0.6274,
"step": 256
},
{
"epoch": 0.03,
"learning_rate": 4.996897949668785e-05,
"loss": 1.1241,
"step": 257
},
{
"epoch": 0.03,
"learning_rate": 4.996858315560129e-05,
"loss": 1.4104,
"step": 258
},
{
"epoch": 0.03,
"learning_rate": 4.996818430017908e-05,
"loss": 1.5033,
"step": 259
},
{
"epoch": 0.03,
"learning_rate": 4.996778293046141e-05,
"loss": 0.9864,
"step": 260
},
{
"epoch": 0.03,
"learning_rate": 4.996737904648866e-05,
"loss": 1.2575,
"step": 261
},
{
"epoch": 0.03,
"learning_rate": 4.9966972648301536e-05,
"loss": 0.4235,
"step": 262
},
{
"epoch": 0.03,
"learning_rate": 4.996656373594095e-05,
"loss": 0.9705,
"step": 263
},
{
"epoch": 0.03,
"learning_rate": 4.9966152309448076e-05,
"loss": 1.1265,
"step": 264
},
{
"epoch": 0.03,
"learning_rate": 4.996573836886435e-05,
"loss": 1.0598,
"step": 265
},
{
"epoch": 0.03,
"learning_rate": 4.996532191423145e-05,
"loss": 0.9536,
"step": 266
},
{
"epoch": 0.03,
"learning_rate": 4.996490294559132e-05,
"loss": 0.936,
"step": 267
},
{
"epoch": 0.03,
"learning_rate": 4.996448146298614e-05,
"loss": 1.1793,
"step": 268
},
{
"epoch": 0.03,
"learning_rate": 4.996405746645837e-05,
"loss": 0.8472,
"step": 269
},
{
"epoch": 0.03,
"learning_rate": 4.996363095605069e-05,
"loss": 0.861,
"step": 270
},
{
"epoch": 0.03,
"learning_rate": 4.996320193180606e-05,
"loss": 0.7457,
"step": 271
},
{
"epoch": 0.03,
"learning_rate": 4.996277039376767e-05,
"loss": 0.9936,
"step": 272
},
{
"epoch": 0.03,
"learning_rate": 4.996233634197899e-05,
"loss": 0.6526,
"step": 273
},
{
"epoch": 0.03,
"learning_rate": 4.996189977648372e-05,
"loss": 0.6052,
"step": 274
},
{
"epoch": 0.03,
"learning_rate": 4.996146069732583e-05,
"loss": 0.3457,
"step": 275
},
{
"epoch": 0.03,
"learning_rate": 4.996101910454953e-05,
"loss": 0.8991,
"step": 276
},
{
"epoch": 0.03,
"learning_rate": 4.9960574998199285e-05,
"loss": 2.1928,
"step": 277
},
{
"epoch": 0.03,
"learning_rate": 4.9960128378319825e-05,
"loss": 1.5278,
"step": 278
},
{
"epoch": 0.03,
"learning_rate": 4.995967924495611e-05,
"loss": 0.7869,
"step": 279
},
{
"epoch": 0.03,
"learning_rate": 4.995922759815339e-05,
"loss": 0.75,
"step": 280
},
{
"epoch": 0.03,
"learning_rate": 4.995877343795714e-05,
"loss": 0.8104,
"step": 281
},
{
"epoch": 0.03,
"learning_rate": 4.995831676441307e-05,
"loss": 0.9529,
"step": 282
},
{
"epoch": 0.03,
"learning_rate": 4.9957857577567197e-05,
"loss": 0.9996,
"step": 283
},
{
"epoch": 0.03,
"learning_rate": 4.995739587746574e-05,
"loss": 0.6799,
"step": 284
},
{
"epoch": 0.03,
"learning_rate": 4.995693166415521e-05,
"loss": 0.3521,
"step": 285
},
{
"epoch": 0.03,
"learning_rate": 4.995646493768234e-05,
"loss": 0.7761,
"step": 286
},
{
"epoch": 0.03,
"learning_rate": 4.995599569809414e-05,
"loss": 1.4368,
"step": 287
},
{
"epoch": 0.03,
"learning_rate": 4.995552394543784e-05,
"loss": 1.2596,
"step": 288
},
{
"epoch": 0.03,
"learning_rate": 4.995504967976098e-05,
"loss": 1.2384,
"step": 289
},
{
"epoch": 0.03,
"learning_rate": 4.9954572901111286e-05,
"loss": 1.2618,
"step": 290
},
{
"epoch": 0.03,
"learning_rate": 4.995409360953679e-05,
"loss": 1.1813,
"step": 291
},
{
"epoch": 0.03,
"learning_rate": 4.995361180508575e-05,
"loss": 1.2225,
"step": 292
},
{
"epoch": 0.03,
"learning_rate": 4.995312748780668e-05,
"loss": 1.6035,
"step": 293
},
{
"epoch": 0.03,
"learning_rate": 4.995264065774836e-05,
"loss": 1.0326,
"step": 294
},
{
"epoch": 0.03,
"learning_rate": 4.995215131495981e-05,
"loss": 1.1068,
"step": 295
},
{
"epoch": 0.03,
"learning_rate": 4.9951659459490294e-05,
"loss": 1.1749,
"step": 296
},
{
"epoch": 0.03,
"learning_rate": 4.995116509138936e-05,
"loss": 0.7934,
"step": 297
},
{
"epoch": 0.03,
"learning_rate": 4.995066821070679e-05,
"loss": 0.7168,
"step": 298
},
{
"epoch": 0.03,
"learning_rate": 4.995016881749261e-05,
"loss": 1.1443,
"step": 299
},
{
"epoch": 0.03,
"learning_rate": 4.994966691179711e-05,
"loss": 1.0016,
"step": 300
},
{
"epoch": 0.03,
"eval_loss": 1.1079908609390259,
"eval_runtime": 72.0399,
"eval_samples_per_second": 2.762,
"eval_steps_per_second": 0.694,
"step": 300
},
{
"epoch": 0.03,
"learning_rate": 4.994916249367084e-05,
"loss": 0.8799,
"step": 301
},
{
"epoch": 0.03,
"learning_rate": 4.994865556316458e-05,
"loss": 0.7981,
"step": 302
},
{
"epoch": 0.03,
"learning_rate": 4.9948146120329395e-05,
"loss": 1.1415,
"step": 303
},
{
"epoch": 0.03,
"learning_rate": 4.9947634165216584e-05,
"loss": 0.7678,
"step": 304
},
{
"epoch": 0.03,
"learning_rate": 4.994711969787769e-05,
"loss": 0.6894,
"step": 305
},
{
"epoch": 0.03,
"learning_rate": 4.9946602718364515e-05,
"loss": 0.2112,
"step": 306
},
{
"epoch": 0.03,
"learning_rate": 4.994608322672914e-05,
"loss": 0.0144,
"step": 307
},
{
"epoch": 0.03,
"learning_rate": 4.994556122302386e-05,
"loss": 0.0126,
"step": 308
},
{
"epoch": 0.03,
"learning_rate": 4.994503670730125e-05,
"loss": 0.0285,
"step": 309
},
{
"epoch": 0.03,
"learning_rate": 4.994450967961413e-05,
"loss": 0.0182,
"step": 310
},
{
"epoch": 0.03,
"learning_rate": 4.994398014001557e-05,
"loss": 0.0169,
"step": 311
},
{
"epoch": 0.03,
"learning_rate": 4.994344808855888e-05,
"loss": 0.0094,
"step": 312
},
{
"epoch": 0.03,
"learning_rate": 4.9942913525297655e-05,
"loss": 0.0169,
"step": 313
},
{
"epoch": 0.03,
"learning_rate": 4.994237645028572e-05,
"loss": 0.0135,
"step": 314
},
{
"epoch": 0.03,
"learning_rate": 4.994183686357717e-05,
"loss": 0.0131,
"step": 315
},
{
"epoch": 0.03,
"learning_rate": 4.994129476522632e-05,
"loss": 0.0138,
"step": 316
},
{
"epoch": 0.03,
"learning_rate": 4.9940750155287775e-05,
"loss": 0.0172,
"step": 317
},
{
"epoch": 0.03,
"learning_rate": 4.994020303381636e-05,
"loss": 0.0196,
"step": 318
},
{
"epoch": 0.03,
"learning_rate": 4.993965340086719e-05,
"loss": 0.0103,
"step": 319
},
{
"epoch": 0.03,
"learning_rate": 4.993910125649561e-05,
"loss": 0.018,
"step": 320
},
{
"epoch": 0.03,
"learning_rate": 4.9938546600757205e-05,
"loss": 0.0128,
"step": 321
},
{
"epoch": 0.03,
"learning_rate": 4.993798943370785e-05,
"loss": 0.0112,
"step": 322
},
{
"epoch": 0.03,
"learning_rate": 4.9937429755403634e-05,
"loss": 0.0176,
"step": 323
},
{
"epoch": 0.03,
"learning_rate": 4.993686756590093e-05,
"loss": 0.371,
"step": 324
},
{
"epoch": 0.03,
"learning_rate": 4.993630286525634e-05,
"loss": 0.5097,
"step": 325
},
{
"epoch": 0.03,
"learning_rate": 4.993573565352674e-05,
"loss": 0.8996,
"step": 326
},
{
"epoch": 0.03,
"learning_rate": 4.9935165930769235e-05,
"loss": 0.9685,
"step": 327
},
{
"epoch": 0.03,
"learning_rate": 4.99345936970412e-05,
"loss": 0.5462,
"step": 328
},
{
"epoch": 0.03,
"learning_rate": 4.993401895240027e-05,
"loss": 0.8048,
"step": 329
},
{
"epoch": 0.03,
"learning_rate": 4.993344169690431e-05,
"loss": 0.7428,
"step": 330
},
{
"epoch": 0.03,
"learning_rate": 4.9932861930611454e-05,
"loss": 0.9778,
"step": 331
},
{
"epoch": 0.03,
"learning_rate": 4.993227965358008e-05,
"loss": 0.9751,
"step": 332
},
{
"epoch": 0.03,
"learning_rate": 4.993169486586884e-05,
"loss": 0.8585,
"step": 333
},
{
"epoch": 0.03,
"learning_rate": 4.99311075675366e-05,
"loss": 1.0175,
"step": 334
},
{
"epoch": 0.03,
"learning_rate": 4.9930517758642503e-05,
"loss": 0.7355,
"step": 335
},
{
"epoch": 0.03,
"learning_rate": 4.992992543924596e-05,
"loss": 1.1919,
"step": 336
},
{
"epoch": 0.03,
"learning_rate": 4.992933060940661e-05,
"loss": 0.9677,
"step": 337
},
{
"epoch": 0.03,
"learning_rate": 4.992873326918434e-05,
"loss": 0.4328,
"step": 338
},
{
"epoch": 0.03,
"learning_rate": 4.9928133418639316e-05,
"loss": 1.2334,
"step": 339
},
{
"epoch": 0.03,
"learning_rate": 4.992753105783194e-05,
"loss": 1.3437,
"step": 340
},
{
"epoch": 0.03,
"learning_rate": 4.992692618682286e-05,
"loss": 1.3923,
"step": 341
},
{
"epoch": 0.03,
"learning_rate": 4.992631880567301e-05,
"loss": 0.747,
"step": 342
},
{
"epoch": 0.03,
"learning_rate": 4.9925708914443526e-05,
"loss": 0.7077,
"step": 343
},
{
"epoch": 0.03,
"learning_rate": 4.9925096513195846e-05,
"loss": 0.8386,
"step": 344
},
{
"epoch": 0.03,
"learning_rate": 4.992448160199162e-05,
"loss": 1.0766,
"step": 345
},
{
"epoch": 0.03,
"learning_rate": 4.992386418089279e-05,
"loss": 2.5327,
"step": 346
},
{
"epoch": 0.03,
"learning_rate": 4.992324424996151e-05,
"loss": 0.669,
"step": 347
},
{
"epoch": 0.03,
"learning_rate": 4.992262180926022e-05,
"loss": 1.1023,
"step": 348
},
{
"epoch": 0.03,
"learning_rate": 4.992199685885159e-05,
"loss": 0.9316,
"step": 349
},
{
"epoch": 0.04,
"learning_rate": 4.992136939879856e-05,
"loss": 1.0181,
"step": 350
},
{
"epoch": 0.04,
"eval_loss": 1.1037520170211792,
"eval_runtime": 72.8274,
"eval_samples_per_second": 2.732,
"eval_steps_per_second": 0.687,
"step": 350
},
{
"epoch": 0.04,
"learning_rate": 4.992073942916432e-05,
"loss": 1.1855,
"step": 351
},
{
"epoch": 0.04,
"learning_rate": 4.992010695001229e-05,
"loss": 0.7205,
"step": 352
},
{
"epoch": 0.04,
"learning_rate": 4.991947196140618e-05,
"loss": 0.7094,
"step": 353
},
{
"epoch": 0.04,
"learning_rate": 4.991883446340992e-05,
"loss": 1.0553,
"step": 354
},
{
"epoch": 0.04,
"learning_rate": 4.991819445608772e-05,
"loss": 0.8234,
"step": 355
},
{
"epoch": 0.04,
"learning_rate": 4.991755193950401e-05,
"loss": 0.3084,
"step": 356
},
{
"epoch": 0.04,
"learning_rate": 4.991690691372352e-05,
"loss": 0.1456,
"step": 357
},
{
"epoch": 0.04,
"learning_rate": 4.991625937881116e-05,
"loss": 0.5623,
"step": 358
},
{
"epoch": 0.04,
"learning_rate": 4.991560933483218e-05,
"loss": 0.5258,
"step": 359
},
{
"epoch": 0.04,
"learning_rate": 4.991495678185202e-05,
"loss": 0.5237,
"step": 360
},
{
"epoch": 0.04,
"learning_rate": 4.9914301719936386e-05,
"loss": 0.9311,
"step": 361
},
{
"epoch": 0.04,
"learning_rate": 4.9913644149151256e-05,
"loss": 2.1465,
"step": 362
},
{
"epoch": 0.04,
"learning_rate": 4.991298406956284e-05,
"loss": 1.0485,
"step": 363
},
{
"epoch": 0.04,
"learning_rate": 4.991232148123761e-05,
"loss": 0.5495,
"step": 364
},
{
"epoch": 0.04,
"learning_rate": 4.991165638424229e-05,
"loss": 0.5886,
"step": 365
},
{
"epoch": 0.04,
"learning_rate": 4.991098877864385e-05,
"loss": 0.9717,
"step": 366
},
{
"epoch": 0.04,
"learning_rate": 4.991031866450953e-05,
"loss": 0.6979,
"step": 367
},
{
"epoch": 0.04,
"learning_rate": 4.990964604190679e-05,
"loss": 0.3933,
"step": 368
},
{
"epoch": 0.04,
"learning_rate": 4.990897091090338e-05,
"loss": 0.7745,
"step": 369
},
{
"epoch": 0.04,
"learning_rate": 4.9908293271567286e-05,
"loss": 0.7866,
"step": 370
},
{
"epoch": 0.04,
"learning_rate": 4.990761312396673e-05,
"loss": 0.7686,
"step": 371
},
{
"epoch": 0.04,
"learning_rate": 4.990693046817023e-05,
"loss": 0.7124,
"step": 372
},
{
"epoch": 0.04,
"learning_rate": 4.99062453042465e-05,
"loss": 1.1124,
"step": 373
},
{
"epoch": 0.04,
"learning_rate": 4.990555763226455e-05,
"loss": 0.8905,
"step": 374
},
{
"epoch": 0.04,
"learning_rate": 4.990486745229364e-05,
"loss": 1.0419,
"step": 375
},
{
"epoch": 0.04,
"learning_rate": 4.9904174764403255e-05,
"loss": 1.1019,
"step": 376
},
{
"epoch": 0.04,
"learning_rate": 4.990347956866315e-05,
"loss": 0.6797,
"step": 377
},
{
"epoch": 0.04,
"learning_rate": 4.9902781865143326e-05,
"loss": 0.522,
"step": 378
},
{
"epoch": 0.04,
"learning_rate": 4.9902081653914056e-05,
"loss": 0.8258,
"step": 379
},
{
"epoch": 0.04,
"learning_rate": 4.990137893504585e-05,
"loss": 0.8358,
"step": 380
},
{
"epoch": 0.04,
"learning_rate": 4.9900673708609455e-05,
"loss": 1.0822,
"step": 381
},
{
"epoch": 0.04,
"learning_rate": 4.989996597467591e-05,
"loss": 0.8717,
"step": 382
},
{
"epoch": 0.04,
"learning_rate": 4.9899255733316465e-05,
"loss": 0.8567,
"step": 383
},
{
"epoch": 0.04,
"learning_rate": 4.9898542984602656e-05,
"loss": 0.0489,
"step": 384
},
{
"epoch": 0.04,
"learning_rate": 4.989782772860624e-05,
"loss": 0.0117,
"step": 385
},
{
"epoch": 0.04,
"learning_rate": 4.989710996539926e-05,
"loss": 0.0183,
"step": 386
},
{
"epoch": 0.04,
"learning_rate": 4.989638969505399e-05,
"loss": 0.0143,
"step": 387
},
{
"epoch": 0.04,
"learning_rate": 4.989566691764295e-05,
"loss": 0.0117,
"step": 388
},
{
"epoch": 0.04,
"learning_rate": 4.989494163323894e-05,
"loss": 0.0188,
"step": 389
},
{
"epoch": 0.04,
"learning_rate": 4.989421384191499e-05,
"loss": 0.0138,
"step": 390
},
{
"epoch": 0.04,
"learning_rate": 4.989348354374438e-05,
"loss": 0.0138,
"step": 391
},
{
"epoch": 0.04,
"learning_rate": 4.9892750738800664e-05,
"loss": 0.0121,
"step": 392
},
{
"epoch": 0.04,
"learning_rate": 4.989201542715762e-05,
"loss": 0.014,
"step": 393
},
{
"epoch": 0.04,
"learning_rate": 4.989127760888932e-05,
"loss": 0.0112,
"step": 394
},
{
"epoch": 0.04,
"learning_rate": 4.9890537284070037e-05,
"loss": 0.0236,
"step": 395
},
{
"epoch": 0.04,
"learning_rate": 4.988979445277433e-05,
"loss": 0.0129,
"step": 396
},
{
"epoch": 0.04,
"learning_rate": 4.9889049115077005e-05,
"loss": 0.0129,
"step": 397
},
{
"epoch": 0.04,
"learning_rate": 4.988830127105311e-05,
"loss": 0.0204,
"step": 398
},
{
"epoch": 0.04,
"learning_rate": 4.9887550920777956e-05,
"loss": 0.02,
"step": 399
},
{
"epoch": 0.04,
"learning_rate": 4.988679806432712e-05,
"loss": 0.0099,
"step": 400
},
{
"epoch": 0.04,
"eval_loss": 1.1065870523452759,
"eval_runtime": 71.8543,
"eval_samples_per_second": 2.769,
"eval_steps_per_second": 0.696,
"step": 400
}
],
"logging_steps": 1,
"max_steps": 10000,
"num_train_epochs": 9223372036854775807,
"save_steps": 100,
"total_flos": 6460489806643200.0,
"trial_name": null,
"trial_params": null
}