Llama-3-LongVILA-8B-1024Frames / trainer_state.json
Ligeng-Zhu's picture
Upload files with huggingface_hub
7b51e24 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 5.913669064748202,
"eval_steps": 500,
"global_step": 204,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.03,
"learning_rate": 7.142857142857143e-06,
"loss": 3.7385,
"step": 1
},
{
"epoch": 0.06,
"learning_rate": 1.4285714285714285e-05,
"loss": 2.9618,
"step": 2
},
{
"epoch": 0.09,
"learning_rate": 2.1428571428571428e-05,
"loss": 3.7649,
"step": 3
},
{
"epoch": 0.12,
"learning_rate": 2.857142857142857e-05,
"loss": 2.5575,
"step": 4
},
{
"epoch": 0.14,
"learning_rate": 3.571428571428572e-05,
"loss": 3.2366,
"step": 5
},
{
"epoch": 0.17,
"learning_rate": 4.2857142857142856e-05,
"loss": 3.7946,
"step": 6
},
{
"epoch": 0.2,
"learning_rate": 5e-05,
"loss": 3.4406,
"step": 7
},
{
"epoch": 0.23,
"learning_rate": 4.999682116415026e-05,
"loss": 3.254,
"step": 8
},
{
"epoch": 0.26,
"learning_rate": 4.998728546500082e-05,
"loss": 3.2319,
"step": 9
},
{
"epoch": 0.29,
"learning_rate": 4.9971395327545466e-05,
"loss": 3.8141,
"step": 10
},
{
"epoch": 0.32,
"learning_rate": 4.9949154792755286e-05,
"loss": 2.9063,
"step": 11
},
{
"epoch": 0.35,
"learning_rate": 4.992056951655103e-05,
"loss": 2.4719,
"step": 12
},
{
"epoch": 0.37,
"learning_rate": 4.988564676836475e-05,
"loss": 2.3808,
"step": 13
},
{
"epoch": 0.4,
"learning_rate": 4.984439542929117e-05,
"loss": 2.312,
"step": 14
},
{
"epoch": 0.43,
"learning_rate": 4.979682598982912e-05,
"loss": 2.8406,
"step": 15
},
{
"epoch": 0.46,
"learning_rate": 4.974295054721377e-05,
"loss": 3.0506,
"step": 16
},
{
"epoch": 0.49,
"learning_rate": 4.9682782802340184e-05,
"loss": 2.7309,
"step": 17
},
{
"epoch": 0.52,
"learning_rate": 4.9616338056279124e-05,
"loss": 2.8111,
"step": 18
},
{
"epoch": 0.55,
"learning_rate": 4.9543633206385834e-05,
"loss": 3.6213,
"step": 19
},
{
"epoch": 0.58,
"learning_rate": 4.9464686742003006e-05,
"loss": 3.5676,
"step": 20
},
{
"epoch": 0.6,
"learning_rate": 4.937951873975871e-05,
"loss": 2.8303,
"step": 21
},
{
"epoch": 0.63,
"learning_rate": 4.928815085846087e-05,
"loss": 3.3833,
"step": 22
},
{
"epoch": 0.66,
"learning_rate": 4.9190606333589194e-05,
"loss": 2.9999,
"step": 23
},
{
"epoch": 0.69,
"learning_rate": 4.9086909971386305e-05,
"loss": 3.1962,
"step": 24
},
{
"epoch": 0.72,
"learning_rate": 4.8977088142549285e-05,
"loss": 2.6578,
"step": 25
},
{
"epoch": 0.75,
"learning_rate": 4.886116877552347e-05,
"loss": 3.2361,
"step": 26
},
{
"epoch": 0.78,
"learning_rate": 4.873918134940002e-05,
"loss": 4.1256,
"step": 27
},
{
"epoch": 0.81,
"learning_rate": 4.8611156886419206e-05,
"loss": 2.683,
"step": 28
},
{
"epoch": 0.83,
"learning_rate": 4.847712794408124e-05,
"loss": 3.4159,
"step": 29
},
{
"epoch": 0.86,
"learning_rate": 4.833712860686666e-05,
"loss": 3.918,
"step": 30
},
{
"epoch": 0.89,
"learning_rate": 4.8191194477568435e-05,
"loss": 3.1473,
"step": 31
},
{
"epoch": 0.92,
"learning_rate": 4.803936266823792e-05,
"loss": 3.9101,
"step": 32
},
{
"epoch": 0.95,
"learning_rate": 4.7881671790747e-05,
"loss": 3.0017,
"step": 33
},
{
"epoch": 0.98,
"learning_rate": 4.7718161946968835e-05,
"loss": 2.9023,
"step": 34
},
{
"epoch": 1.01,
"learning_rate": 4.754887471857969e-05,
"loss": 2.7649,
"step": 35
},
{
"epoch": 1.04,
"learning_rate": 4.7373853156484406e-05,
"loss": 2.9823,
"step": 36
},
{
"epoch": 1.06,
"learning_rate": 4.7193141769868265e-05,
"loss": 2.9701,
"step": 37
},
{
"epoch": 1.09,
"learning_rate": 4.7006786514877997e-05,
"loss": 2.5226,
"step": 38
},
{
"epoch": 1.12,
"learning_rate": 4.6814834782934844e-05,
"loss": 2.3836,
"step": 39
},
{
"epoch": 1.15,
"learning_rate": 4.6617335388682556e-05,
"loss": 3.2099,
"step": 40
},
{
"epoch": 1.18,
"learning_rate": 4.641433855757351e-05,
"loss": 3.3312,
"step": 41
},
{
"epoch": 1.21,
"learning_rate": 4.620589591309603e-05,
"loss": 2.9884,
"step": 42
},
{
"epoch": 1.24,
"learning_rate": 4.59920604636462e-05,
"loss": 2.4634,
"step": 43
},
{
"epoch": 1.27,
"learning_rate": 4.577288658904741e-05,
"loss": 2.8223,
"step": 44
},
{
"epoch": 1.29,
"learning_rate": 4.554843002672129e-05,
"loss": 4.1285,
"step": 45
},
{
"epoch": 1.32,
"learning_rate": 4.531874785751317e-05,
"loss": 3.5577,
"step": 46
},
{
"epoch": 1.35,
"learning_rate": 4.5083898491176136e-05,
"loss": 3.3524,
"step": 47
},
{
"epoch": 1.38,
"learning_rate": 4.4843941651517e-05,
"loss": 2.518,
"step": 48
},
{
"epoch": 1.41,
"learning_rate": 4.4598938361208095e-05,
"loss": 2.948,
"step": 49
},
{
"epoch": 1.44,
"learning_rate": 4.434895092626883e-05,
"loss": 2.4119,
"step": 50
},
{
"epoch": 1.49,
"learning_rate": 4.409404292022081e-05,
"loss": 1.5223,
"step": 51
},
{
"epoch": 1.52,
"learning_rate": 4.38342791679207e-05,
"loss": 1.6446,
"step": 52
},
{
"epoch": 1.55,
"learning_rate": 4.356972572907473e-05,
"loss": 2.1176,
"step": 53
},
{
"epoch": 1.58,
"learning_rate": 4.3300449881439375e-05,
"loss": 2.3363,
"step": 54
},
{
"epoch": 1.6,
"learning_rate": 4.302652010371205e-05,
"loss": 1.4723,
"step": 55
},
{
"epoch": 1.63,
"learning_rate": 4.274800605811658e-05,
"loss": 1.7024,
"step": 56
},
{
"epoch": 1.66,
"learning_rate": 4.246497857268759e-05,
"loss": 1.7637,
"step": 57
},
{
"epoch": 1.69,
"learning_rate": 4.2177509623258456e-05,
"loss": 1.6597,
"step": 58
},
{
"epoch": 1.72,
"learning_rate": 4.1885672315157346e-05,
"loss": 1.3964,
"step": 59
},
{
"epoch": 1.75,
"learning_rate": 4.1589540864616025e-05,
"loss": 1.7824,
"step": 60
},
{
"epoch": 1.78,
"learning_rate": 4.128919057989622e-05,
"loss": 2.6526,
"step": 61
},
{
"epoch": 1.81,
"learning_rate": 4.098469784213812e-05,
"loss": 1.5922,
"step": 62
},
{
"epoch": 1.83,
"learning_rate": 4.0676140085936186e-05,
"loss": 1.863,
"step": 63
},
{
"epoch": 1.86,
"learning_rate": 4.0363595779647e-05,
"loss": 1.9858,
"step": 64
},
{
"epoch": 1.89,
"learning_rate": 4.0047144405434175e-05,
"loss": 1.7664,
"step": 65
},
{
"epoch": 1.92,
"learning_rate": 3.972686643905558e-05,
"loss": 2.3141,
"step": 66
},
{
"epoch": 1.95,
"learning_rate": 3.940284332939771e-05,
"loss": 1.2004,
"step": 67
},
{
"epoch": 1.98,
"learning_rate": 3.9075157477762744e-05,
"loss": 1.5104,
"step": 68
},
{
"epoch": 2.01,
"learning_rate": 3.874389221691329e-05,
"loss": 1.6063,
"step": 69
},
{
"epoch": 2.04,
"learning_rate": 3.84091317898803e-05,
"loss": 1.3248,
"step": 70
},
{
"epoch": 2.06,
"learning_rate": 3.8070961328539525e-05,
"loss": 1.5846,
"step": 71
},
{
"epoch": 2.09,
"learning_rate": 3.772946683196179e-05,
"loss": 1.1226,
"step": 72
},
{
"epoch": 2.12,
"learning_rate": 3.738473514454297e-05,
"loss": 1.3365,
"step": 73
},
{
"epoch": 2.15,
"learning_rate": 3.7036853933918784e-05,
"loss": 1.863,
"step": 74
},
{
"epoch": 2.18,
"learning_rate": 3.668591166867035e-05,
"loss": 1.3578,
"step": 75
},
{
"epoch": 2.21,
"learning_rate": 3.633199759582596e-05,
"loss": 1.3557,
"step": 76
},
{
"epoch": 2.24,
"learning_rate": 3.597520171816503e-05,
"loss": 1.414,
"step": 77
},
{
"epoch": 2.27,
"learning_rate": 3.5615614771329706e-05,
"loss": 1.5178,
"step": 78
},
{
"epoch": 2.29,
"learning_rate": 3.5253328200750224e-05,
"loss": 2.2556,
"step": 79
},
{
"epoch": 2.32,
"learning_rate": 3.488843413838963e-05,
"loss": 1.9742,
"step": 80
},
{
"epoch": 2.35,
"learning_rate": 3.452102537931408e-05,
"loss": 2.1719,
"step": 81
},
{
"epoch": 2.38,
"learning_rate": 3.4151195358094365e-05,
"loss": 1.1524,
"step": 82
},
{
"epoch": 2.41,
"learning_rate": 3.377903812504487e-05,
"loss": 1.7081,
"step": 83
},
{
"epoch": 2.44,
"learning_rate": 3.340464832230592e-05,
"loss": 1.2862,
"step": 84
},
{
"epoch": 2.47,
"learning_rate": 3.3028121159775656e-05,
"loss": 3.1442,
"step": 85
},
{
"epoch": 2.5,
"learning_rate": 3.2649552390897494e-05,
"loss": 3.1724,
"step": 86
},
{
"epoch": 2.53,
"learning_rate": 3.226903828830935e-05,
"loss": 2.821,
"step": 87
},
{
"epoch": 2.55,
"learning_rate": 3.1886675619360885e-05,
"loss": 3.2655,
"step": 88
},
{
"epoch": 2.58,
"learning_rate": 3.1502561621504874e-05,
"loss": 3.2369,
"step": 89
},
{
"epoch": 2.61,
"learning_rate": 3.111679397756906e-05,
"loss": 2.6636,
"step": 90
},
{
"epoch": 2.64,
"learning_rate": 3.072947079091472e-05,
"loss": 2.289,
"step": 91
},
{
"epoch": 2.67,
"learning_rate": 3.034069056048837e-05,
"loss": 2.9397,
"step": 92
},
{
"epoch": 2.7,
"learning_rate": 2.9950552155772743e-05,
"loss": 3.18,
"step": 93
},
{
"epoch": 2.73,
"learning_rate": 2.95591547916436e-05,
"loss": 2.362,
"step": 94
},
{
"epoch": 2.76,
"learning_rate": 2.9166598003138766e-05,
"loss": 3.0609,
"step": 95
},
{
"epoch": 2.78,
"learning_rate": 2.8772981620145623e-05,
"loss": 3.0864,
"step": 96
},
{
"epoch": 2.81,
"learning_rate": 2.8378405742013713e-05,
"loss": 2.7795,
"step": 97
},
{
"epoch": 2.84,
"learning_rate": 2.7982970712098794e-05,
"loss": 3.1472,
"step": 98
},
{
"epoch": 2.87,
"learning_rate": 2.7586777092244804e-05,
"loss": 3.9248,
"step": 99
},
{
"epoch": 2.9,
"learning_rate": 2.7189925637210323e-05,
"loss": 3.9677,
"step": 100
},
{
"epoch": 2.95,
"learning_rate": 2.6792517269045943e-05,
"loss": 1.1242,
"step": 101
},
{
"epoch": 2.98,
"learning_rate": 2.6394653051429064e-05,
"loss": 1.2223,
"step": 102
},
{
"epoch": 3.01,
"learning_rate": 2.5996434163962763e-05,
"loss": 1.2138,
"step": 103
},
{
"epoch": 3.04,
"learning_rate": 2.5597961876445077e-05,
"loss": 0.9312,
"step": 104
},
{
"epoch": 3.06,
"learning_rate": 2.5199337523115418e-05,
"loss": 1.0011,
"step": 105
},
{
"epoch": 3.09,
"learning_rate": 2.480066247688459e-05,
"loss": 0.6636,
"step": 106
},
{
"epoch": 3.12,
"learning_rate": 2.4402038123554933e-05,
"loss": 0.6459,
"step": 107
},
{
"epoch": 3.15,
"learning_rate": 2.4003565836037246e-05,
"loss": 1.0171,
"step": 108
},
{
"epoch": 3.18,
"learning_rate": 2.360534694857094e-05,
"loss": 0.6442,
"step": 109
},
{
"epoch": 3.21,
"learning_rate": 2.3207482730954063e-05,
"loss": 0.6365,
"step": 110
},
{
"epoch": 3.24,
"learning_rate": 2.2810074362789676e-05,
"loss": 0.7385,
"step": 111
},
{
"epoch": 3.27,
"learning_rate": 2.2413222907755195e-05,
"loss": 0.6871,
"step": 112
},
{
"epoch": 3.29,
"learning_rate": 2.2017029287901212e-05,
"loss": 0.9302,
"step": 113
},
{
"epoch": 3.32,
"learning_rate": 2.162159425798629e-05,
"loss": 0.8288,
"step": 114
},
{
"epoch": 3.35,
"learning_rate": 2.1227018379854383e-05,
"loss": 0.8842,
"step": 115
},
{
"epoch": 3.38,
"learning_rate": 2.083340199686124e-05,
"loss": 0.431,
"step": 116
},
{
"epoch": 3.41,
"learning_rate": 2.0440845208356402e-05,
"loss": 0.8126,
"step": 117
},
{
"epoch": 3.44,
"learning_rate": 2.0049447844227266e-05,
"loss": 0.5205,
"step": 118
},
{
"epoch": 3.47,
"learning_rate": 1.9659309439511628e-05,
"loss": 0.8926,
"step": 119
},
{
"epoch": 3.5,
"learning_rate": 1.927052920908528e-05,
"loss": 1.1858,
"step": 120
},
{
"epoch": 3.53,
"learning_rate": 1.8883206022430956e-05,
"loss": 1.3177,
"step": 121
},
{
"epoch": 3.55,
"learning_rate": 1.849743837849513e-05,
"loss": 1.3189,
"step": 122
},
{
"epoch": 3.58,
"learning_rate": 1.8113324380639117e-05,
"loss": 1.7173,
"step": 123
},
{
"epoch": 3.61,
"learning_rate": 1.7730961711690655e-05,
"loss": 1.2899,
"step": 124
},
{
"epoch": 3.64,
"learning_rate": 1.735044760910251e-05,
"loss": 1.3921,
"step": 125
},
{
"epoch": 3.67,
"learning_rate": 1.6971878840224346e-05,
"loss": 1.913,
"step": 126
},
{
"epoch": 3.7,
"learning_rate": 1.6595351677694083e-05,
"loss": 2.1296,
"step": 127
},
{
"epoch": 3.73,
"learning_rate": 1.6220961874955134e-05,
"loss": 1.4972,
"step": 128
},
{
"epoch": 3.76,
"learning_rate": 1.5848804641905634e-05,
"loss": 1.9327,
"step": 129
},
{
"epoch": 3.78,
"learning_rate": 1.547897462068592e-05,
"loss": 1.7836,
"step": 130
},
{
"epoch": 3.81,
"learning_rate": 1.5111565861610378e-05,
"loss": 1.4168,
"step": 131
},
{
"epoch": 3.84,
"learning_rate": 1.4746671799249784e-05,
"loss": 1.8149,
"step": 132
},
{
"epoch": 3.87,
"learning_rate": 1.4384385228670288e-05,
"loss": 2.3297,
"step": 133
},
{
"epoch": 3.9,
"learning_rate": 1.4024798281834966e-05,
"loss": 2.8803,
"step": 134
},
{
"epoch": 3.93,
"learning_rate": 1.3668002404174047e-05,
"loss": 4.1083,
"step": 135
},
{
"epoch": 3.96,
"learning_rate": 1.331408833132966e-05,
"loss": 3.8829,
"step": 136
},
{
"epoch": 3.99,
"learning_rate": 1.2963146066081217e-05,
"loss": 3.0687,
"step": 137
},
{
"epoch": 4.01,
"learning_rate": 1.2615264855457038e-05,
"loss": 3.2044,
"step": 138
},
{
"epoch": 4.04,
"learning_rate": 1.2270533168038217e-05,
"loss": 2.6155,
"step": 139
},
{
"epoch": 4.07,
"learning_rate": 1.1929038671460486e-05,
"loss": 3.357,
"step": 140
},
{
"epoch": 4.1,
"learning_rate": 1.1590868210119692e-05,
"loss": 3.2517,
"step": 141
},
{
"epoch": 4.13,
"learning_rate": 1.125610778308672e-05,
"loss": 3.5836,
"step": 142
},
{
"epoch": 4.16,
"learning_rate": 1.0924842522237267e-05,
"loss": 3.9635,
"step": 143
},
{
"epoch": 4.19,
"learning_rate": 1.0597156670602299e-05,
"loss": 3.369,
"step": 144
},
{
"epoch": 4.22,
"learning_rate": 1.027313356094443e-05,
"loss": 3.3562,
"step": 145
},
{
"epoch": 4.24,
"learning_rate": 9.95285559456583e-06,
"loss": 2.6965,
"step": 146
},
{
"epoch": 4.27,
"learning_rate": 9.636404220353013e-06,
"loss": 3.0411,
"step": 147
},
{
"epoch": 4.3,
"learning_rate": 9.323859914063814e-06,
"loss": 3.3667,
"step": 148
},
{
"epoch": 4.33,
"learning_rate": 9.015302157861883e-06,
"loss": 2.4606,
"step": 149
},
{
"epoch": 4.36,
"learning_rate": 8.710809420103789e-06,
"loss": 3.3676,
"step": 150
},
{
"epoch": 4.39,
"learning_rate": 8.41045913538398e-06,
"loss": 3.3801,
"step": 151
},
{
"epoch": 4.42,
"learning_rate": 8.11432768484267e-06,
"loss": 3.2172,
"step": 152
},
{
"epoch": 4.45,
"learning_rate": 7.822490376741554e-06,
"loss": 2.8255,
"step": 153
},
{
"epoch": 4.47,
"learning_rate": 7.535021427312417e-06,
"loss": 2.1001,
"step": 154
},
{
"epoch": 4.5,
"learning_rate": 7.251993941883428e-06,
"loss": 3.0872,
"step": 155
},
{
"epoch": 4.53,
"learning_rate": 6.9734798962879575e-06,
"loss": 3.0398,
"step": 156
},
{
"epoch": 4.56,
"learning_rate": 6.699550118560632e-06,
"loss": 2.4247,
"step": 157
},
{
"epoch": 4.59,
"learning_rate": 6.430274270925271e-06,
"loss": 3.318,
"step": 158
},
{
"epoch": 4.62,
"learning_rate": 6.1657208320793054e-06,
"loss": 2.9561,
"step": 159
},
{
"epoch": 4.65,
"learning_rate": 5.905957079779187e-06,
"loss": 4.0259,
"step": 160
},
{
"epoch": 4.68,
"learning_rate": 5.6510490737311735e-06,
"loss": 3.2479,
"step": 161
},
{
"epoch": 4.71,
"learning_rate": 5.4010616387919095e-06,
"loss": 2.8332,
"step": 162
},
{
"epoch": 4.73,
"learning_rate": 5.156058348483006e-06,
"loss": 3.157,
"step": 163
},
{
"epoch": 4.76,
"learning_rate": 4.916101508823873e-06,
"loss": 2.7395,
"step": 164
},
{
"epoch": 4.79,
"learning_rate": 4.681252142486841e-06,
"loss": 2.4334,
"step": 165
},
{
"epoch": 4.82,
"learning_rate": 4.451569973278719e-06,
"loss": 2.7141,
"step": 166
},
{
"epoch": 4.85,
"learning_rate": 4.227113410952585e-06,
"loss": 3.8611,
"step": 167
},
{
"epoch": 4.88,
"learning_rate": 4.007939536353805e-06,
"loss": 2.5086,
"step": 168
},
{
"epoch": 4.91,
"learning_rate": 3.7941040869039714e-06,
"loss": 3.7843,
"step": 169
},
{
"epoch": 4.94,
"learning_rate": 3.585661442426494e-06,
"loss": 3.5859,
"step": 170
},
{
"epoch": 4.96,
"learning_rate": 3.382664611317446e-06,
"loss": 4.9826,
"step": 171
},
{
"epoch": 4.99,
"learning_rate": 3.1851652170651584e-06,
"loss": 2.6905,
"step": 172
},
{
"epoch": 5.02,
"learning_rate": 2.9932134851220038e-06,
"loss": 3.2184,
"step": 173
},
{
"epoch": 5.05,
"learning_rate": 2.8068582301317425e-06,
"loss": 3.0139,
"step": 174
},
{
"epoch": 5.08,
"learning_rate": 2.6261468435155978e-06,
"loss": 2.9526,
"step": 175
},
{
"epoch": 5.11,
"learning_rate": 2.4511252814203107e-06,
"loss": 2.4834,
"step": 176
},
{
"epoch": 5.14,
"learning_rate": 2.2818380530311655e-06,
"loss": 4.3975,
"step": 177
},
{
"epoch": 5.17,
"learning_rate": 2.1183282092530065e-06,
"loss": 3.4159,
"step": 178
},
{
"epoch": 5.19,
"learning_rate": 1.960637331762091e-06,
"loss": 3.2516,
"step": 179
},
{
"epoch": 5.22,
"learning_rate": 1.8088055224315697e-06,
"loss": 2.7591,
"step": 180
},
{
"epoch": 5.25,
"learning_rate": 1.6628713931333445e-06,
"loss": 2.6279,
"step": 181
},
{
"epoch": 5.28,
"learning_rate": 1.5228720559187642e-06,
"loss": 2.847,
"step": 182
},
{
"epoch": 5.31,
"learning_rate": 1.3888431135807956e-06,
"loss": 2.089,
"step": 183
},
{
"epoch": 5.34,
"learning_rate": 1.2608186505999847e-06,
"loss": 3.5639,
"step": 184
},
{
"epoch": 5.37,
"learning_rate": 1.138831224476533e-06,
"loss": 3.0349,
"step": 185
},
{
"epoch": 5.4,
"learning_rate": 1.0229118574507174e-06,
"loss": 3.6886,
"step": 186
},
{
"epoch": 5.42,
"learning_rate": 9.130900286137001e-07,
"loss": 2.7077,
"step": 187
},
{
"epoch": 5.45,
"learning_rate": 8.093936664108071e-07,
"loss": 2.3523,
"step": 188
},
{
"epoch": 5.48,
"learning_rate": 7.118491415391337e-07,
"loss": 3.7049,
"step": 189
},
{
"epoch": 5.51,
"learning_rate": 6.204812602412902e-07,
"loss": 5.1024,
"step": 190
},
{
"epoch": 5.54,
"learning_rate": 5.353132579969972e-07,
"loss": 3.0828,
"step": 191
},
{
"epoch": 5.57,
"learning_rate": 4.56366793614163e-07,
"loss": 2.5269,
"step": 192
},
{
"epoch": 5.6,
"learning_rate": 3.8366194372088384e-07,
"loss": 2.7201,
"step": 193
},
{
"epoch": 5.63,
"learning_rate": 3.1721719765981926e-07,
"loss": 2.9555,
"step": 194
},
{
"epoch": 5.65,
"learning_rate": 2.5704945278623436e-07,
"loss": 3.5292,
"step": 195
},
{
"epoch": 5.68,
"learning_rate": 2.0317401017088122e-07,
"loss": 2.9735,
"step": 196
},
{
"epoch": 5.71,
"learning_rate": 1.5560457070883105e-07,
"loss": 3.2746,
"step": 197
},
{
"epoch": 5.74,
"learning_rate": 1.1435323163525025e-07,
"loss": 2.8847,
"step": 198
},
{
"epoch": 5.77,
"learning_rate": 7.94304834489723e-08,
"loss": 2.6234,
"step": 199
},
{
"epoch": 5.8,
"learning_rate": 5.0845207244715196e-08,
"loss": 3.2828,
"step": 200
},
{
"epoch": 5.83,
"learning_rate": 2.8604672454538018e-08,
"loss": 2.3275,
"step": 201
},
{
"epoch": 5.86,
"learning_rate": 1.2714534999183625e-08,
"loss": 3.3622,
"step": 202
},
{
"epoch": 5.88,
"learning_rate": 3.1788358497431005e-09,
"loss": 3.235,
"step": 203
},
{
"epoch": 5.91,
"learning_rate": 0.0,
"loss": 2.0377,
"step": 204
},
{
"epoch": 5.91,
"step": 204,
"total_flos": 0.0,
"train_loss": 1.2812642963493572,
"train_runtime": 30830.0379,
"train_samples_per_second": 13.815,
"train_steps_per_second": 0.007
}
],
"logging_steps": 1.0,
"max_steps": 204,
"num_input_tokens_seen": 0,
"num_train_epochs": 6,
"save_steps": 50,
"total_flos": 0.0,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}