no-robots-y34b-lora / checkpoint-210 /trainer_state.json
Doctor-Shotgun's picture
Upload folder using huggingface_hub
7831acd
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.0145278450363193,
"eval_steps": 500,
"global_step": 210,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.01,
"learning_rate": 8.000000000000001e-06,
"loss": 1.6073,
"step": 1
},
{
"epoch": 0.02,
"learning_rate": 1.6000000000000003e-05,
"loss": 1.701,
"step": 2
},
{
"epoch": 0.03,
"learning_rate": 2.4e-05,
"loss": 1.6232,
"step": 3
},
{
"epoch": 0.04,
"learning_rate": 3.2000000000000005e-05,
"loss": 1.705,
"step": 4
},
{
"epoch": 0.05,
"learning_rate": 4e-05,
"loss": 1.6552,
"step": 5
},
{
"epoch": 0.06,
"learning_rate": 4.8e-05,
"loss": 1.7611,
"step": 6
},
{
"epoch": 0.07,
"learning_rate": 5.6e-05,
"loss": 1.6008,
"step": 7
},
{
"epoch": 0.08,
"learning_rate": 6.400000000000001e-05,
"loss": 1.6468,
"step": 8
},
{
"epoch": 0.09,
"learning_rate": 7.2e-05,
"loss": 1.6148,
"step": 9
},
{
"epoch": 0.1,
"learning_rate": 8e-05,
"loss": 1.6125,
"step": 10
},
{
"epoch": 0.11,
"learning_rate": 7.999779207981935e-05,
"loss": 1.6532,
"step": 11
},
{
"epoch": 0.12,
"learning_rate": 7.999116856302298e-05,
"loss": 1.528,
"step": 12
},
{
"epoch": 0.13,
"learning_rate": 7.998013018082072e-05,
"loss": 1.5758,
"step": 13
},
{
"epoch": 0.14,
"learning_rate": 7.996467815180588e-05,
"loss": 1.6549,
"step": 14
},
{
"epoch": 0.15,
"learning_rate": 7.994481418182082e-05,
"loss": 1.3725,
"step": 15
},
{
"epoch": 0.15,
"learning_rate": 7.992054046376854e-05,
"loss": 1.6324,
"step": 16
},
{
"epoch": 0.16,
"learning_rate": 7.989185967737066e-05,
"loss": 1.5984,
"step": 17
},
{
"epoch": 0.17,
"learning_rate": 7.985877498887149e-05,
"loss": 1.7095,
"step": 18
},
{
"epoch": 0.18,
"learning_rate": 7.982129005068865e-05,
"loss": 1.4843,
"step": 19
},
{
"epoch": 0.19,
"learning_rate": 7.977940900100967e-05,
"loss": 1.6701,
"step": 20
},
{
"epoch": 0.2,
"learning_rate": 7.973313646333532e-05,
"loss": 1.6216,
"step": 21
},
{
"epoch": 0.21,
"learning_rate": 7.968247754596908e-05,
"loss": 1.6616,
"step": 22
},
{
"epoch": 0.22,
"learning_rate": 7.962743784145323e-05,
"loss": 1.5737,
"step": 23
},
{
"epoch": 0.23,
"learning_rate": 7.956802342595152e-05,
"loss": 1.5716,
"step": 24
},
{
"epoch": 0.24,
"learning_rate": 7.950424085857827e-05,
"loss": 1.4727,
"step": 25
},
{
"epoch": 0.25,
"learning_rate": 7.943609718067437e-05,
"loss": 1.676,
"step": 26
},
{
"epoch": 0.26,
"learning_rate": 7.936359991502993e-05,
"loss": 1.5953,
"step": 27
},
{
"epoch": 0.27,
"learning_rate": 7.92867570650537e-05,
"loss": 1.5233,
"step": 28
},
{
"epoch": 0.28,
"learning_rate": 7.920557711388967e-05,
"loss": 1.7087,
"step": 29
},
{
"epoch": 0.29,
"learning_rate": 7.912006902348045e-05,
"loss": 1.6314,
"step": 30
},
{
"epoch": 0.3,
"learning_rate": 7.903024223357797e-05,
"loss": 1.5763,
"step": 31
},
{
"epoch": 0.31,
"learning_rate": 7.893610666070134e-05,
"loss": 1.7077,
"step": 32
},
{
"epoch": 0.32,
"learning_rate": 7.883767269704209e-05,
"loss": 1.5335,
"step": 33
},
{
"epoch": 0.33,
"learning_rate": 7.873495120931697e-05,
"loss": 1.6053,
"step": 34
},
{
"epoch": 0.34,
"learning_rate": 7.86279535375683e-05,
"loss": 1.3602,
"step": 35
},
{
"epoch": 0.35,
"learning_rate": 7.851669149391198e-05,
"loss": 1.3493,
"step": 36
},
{
"epoch": 0.36,
"learning_rate": 7.84011773612336e-05,
"loss": 1.5459,
"step": 37
},
{
"epoch": 0.37,
"learning_rate": 7.828142389183239e-05,
"loss": 1.5918,
"step": 38
},
{
"epoch": 0.38,
"learning_rate": 7.815744430601344e-05,
"loss": 1.4649,
"step": 39
},
{
"epoch": 0.39,
"learning_rate": 7.802925229062823e-05,
"loss": 1.5555,
"step": 40
},
{
"epoch": 0.4,
"learning_rate": 7.789686199756365e-05,
"loss": 1.6162,
"step": 41
},
{
"epoch": 0.41,
"learning_rate": 7.776028804217968e-05,
"loss": 1.5508,
"step": 42
},
{
"epoch": 0.42,
"learning_rate": 7.761954550169593e-05,
"loss": 1.7089,
"step": 43
},
{
"epoch": 0.43,
"learning_rate": 7.74746499135272e-05,
"loss": 1.6471,
"step": 44
},
{
"epoch": 0.44,
"learning_rate": 7.732561727356811e-05,
"loss": 1.5361,
"step": 45
},
{
"epoch": 0.45,
"learning_rate": 7.717246403442735e-05,
"loss": 1.4333,
"step": 46
},
{
"epoch": 0.46,
"learning_rate": 7.701520710361129e-05,
"loss": 1.5406,
"step": 47
},
{
"epoch": 0.46,
"learning_rate": 7.685386384165748e-05,
"loss": 1.6056,
"step": 48
},
{
"epoch": 0.47,
"learning_rate": 7.668845206021812e-05,
"loss": 1.5945,
"step": 49
},
{
"epoch": 0.48,
"learning_rate": 7.651899002009375e-05,
"loss": 1.6727,
"step": 50
},
{
"epoch": 0.49,
"learning_rate": 7.634549642921725e-05,
"loss": 1.6352,
"step": 51
},
{
"epoch": 0.5,
"learning_rate": 7.616799044058867e-05,
"loss": 1.5127,
"step": 52
},
{
"epoch": 0.51,
"learning_rate": 7.598649165016073e-05,
"loss": 1.5696,
"step": 53
},
{
"epoch": 0.52,
"learning_rate": 7.58010200946755e-05,
"loss": 1.5987,
"step": 54
},
{
"epoch": 0.53,
"learning_rate": 7.561159624945257e-05,
"loss": 1.5007,
"step": 55
},
{
"epoch": 0.54,
"learning_rate": 7.541824102612839e-05,
"loss": 1.697,
"step": 56
},
{
"epoch": 0.55,
"learning_rate": 7.5220975770348e-05,
"loss": 1.5062,
"step": 57
},
{
"epoch": 0.56,
"learning_rate": 7.501982225940833e-05,
"loss": 1.6713,
"step": 58
},
{
"epoch": 0.57,
"learning_rate": 7.48148026998542e-05,
"loss": 1.5913,
"step": 59
},
{
"epoch": 0.58,
"learning_rate": 7.460593972502674e-05,
"loss": 1.5841,
"step": 60
},
{
"epoch": 0.59,
"learning_rate": 7.439325639256483e-05,
"loss": 1.5459,
"step": 61
},
{
"epoch": 0.6,
"learning_rate": 7.417677618185955e-05,
"loss": 1.5911,
"step": 62
},
{
"epoch": 0.61,
"learning_rate": 7.39565229914622e-05,
"loss": 1.5862,
"step": 63
},
{
"epoch": 0.62,
"learning_rate": 7.373252113644596e-05,
"loss": 1.6381,
"step": 64
},
{
"epoch": 0.63,
"learning_rate": 7.350479534572166e-05,
"loss": 1.5476,
"step": 65
},
{
"epoch": 0.64,
"learning_rate": 7.327337075930775e-05,
"loss": 1.579,
"step": 66
},
{
"epoch": 0.65,
"learning_rate": 7.303827292555495e-05,
"loss": 1.6105,
"step": 67
},
{
"epoch": 0.66,
"learning_rate": 7.279952779832584e-05,
"loss": 1.5728,
"step": 68
},
{
"epoch": 0.67,
"learning_rate": 7.255716173412966e-05,
"loss": 1.6509,
"step": 69
},
{
"epoch": 0.68,
"learning_rate": 7.23112014892126e-05,
"loss": 1.5586,
"step": 70
},
{
"epoch": 0.69,
"learning_rate": 7.20616742166041e-05,
"loss": 1.3865,
"step": 71
},
{
"epoch": 0.7,
"learning_rate": 7.180860746311917e-05,
"loss": 1.5214,
"step": 72
},
{
"epoch": 0.71,
"learning_rate": 7.155202916631743e-05,
"loss": 1.5699,
"step": 73
},
{
"epoch": 0.72,
"learning_rate": 7.129196765141886e-05,
"loss": 1.388,
"step": 74
},
{
"epoch": 0.73,
"learning_rate": 7.10284516281768e-05,
"loss": 1.5735,
"step": 75
},
{
"epoch": 0.74,
"learning_rate": 7.076151018770854e-05,
"loss": 1.6245,
"step": 76
},
{
"epoch": 0.75,
"learning_rate": 7.049117279928374e-05,
"loss": 1.6489,
"step": 77
},
{
"epoch": 0.76,
"learning_rate": 7.021746930707117e-05,
"loss": 1.5712,
"step": 78
},
{
"epoch": 0.77,
"learning_rate": 6.994042992684406e-05,
"loss": 1.6359,
"step": 79
},
{
"epoch": 0.77,
"learning_rate": 6.966008524264429e-05,
"loss": 1.6452,
"step": 80
},
{
"epoch": 0.78,
"learning_rate": 6.937646620340618e-05,
"loss": 1.5655,
"step": 81
},
{
"epoch": 0.79,
"learning_rate": 6.908960411953973e-05,
"loss": 1.5791,
"step": 82
},
{
"epoch": 0.8,
"learning_rate": 6.879953065947416e-05,
"loss": 1.685,
"step": 83
},
{
"epoch": 0.81,
"learning_rate": 6.850627784616178e-05,
"loss": 1.5755,
"step": 84
},
{
"epoch": 0.82,
"learning_rate": 6.82098780535428e-05,
"loss": 1.5878,
"step": 85
},
{
"epoch": 0.83,
"learning_rate": 6.791036400297142e-05,
"loss": 1.6273,
"step": 86
},
{
"epoch": 0.84,
"learning_rate": 6.760776875960347e-05,
"loss": 1.625,
"step": 87
},
{
"epoch": 0.85,
"learning_rate": 6.730212572874618e-05,
"loss": 1.6891,
"step": 88
},
{
"epoch": 0.86,
"learning_rate": 6.699346865217031e-05,
"loss": 1.5593,
"step": 89
},
{
"epoch": 0.87,
"learning_rate": 6.668183160438531e-05,
"loss": 1.6518,
"step": 90
},
{
"epoch": 0.88,
"learning_rate": 6.636724898887751e-05,
"loss": 1.6314,
"step": 91
},
{
"epoch": 0.89,
"learning_rate": 6.604975553431219e-05,
"loss": 1.6267,
"step": 92
},
{
"epoch": 0.9,
"learning_rate": 6.572938629069959e-05,
"loss": 1.5465,
"step": 93
},
{
"epoch": 0.91,
"learning_rate": 6.540617662552565e-05,
"loss": 1.6302,
"step": 94
},
{
"epoch": 0.92,
"learning_rate": 6.508016221984747e-05,
"loss": 1.5039,
"step": 95
},
{
"epoch": 0.93,
"learning_rate": 6.475137906435435e-05,
"loss": 1.6879,
"step": 96
},
{
"epoch": 0.94,
"learning_rate": 6.441986345539446e-05,
"loss": 1.5822,
"step": 97
},
{
"epoch": 0.95,
"learning_rate": 6.408565199096798e-05,
"loss": 1.5612,
"step": 98
},
{
"epoch": 0.96,
"learning_rate": 6.374878156668676e-05,
"loss": 1.6022,
"step": 99
},
{
"epoch": 0.97,
"learning_rate": 6.340928937170118e-05,
"loss": 1.6292,
"step": 100
},
{
"epoch": 0.98,
"learning_rate": 6.30672128845947e-05,
"loss": 1.6783,
"step": 101
},
{
"epoch": 0.99,
"learning_rate": 6.272258986924624e-05,
"loss": 1.5995,
"step": 102
},
{
"epoch": 1.0,
"learning_rate": 6.237545837066133e-05,
"loss": 1.5811,
"step": 103
},
{
"epoch": 1.01,
"learning_rate": 6.202585671077204e-05,
"loss": 1.5029,
"step": 104
},
{
"epoch": 1.02,
"learning_rate": 6.167382348420637e-05,
"loss": 1.5067,
"step": 105
},
{
"epoch": 1.01,
"learning_rate": 6.131939755402755e-05,
"loss": 1.4932,
"step": 106
},
{
"epoch": 1.02,
"learning_rate": 6.09626180474438e-05,
"loss": 1.6286,
"step": 107
},
{
"epoch": 1.03,
"learning_rate": 6.060352435148874e-05,
"loss": 1.5934,
"step": 108
},
{
"epoch": 1.04,
"learning_rate": 6.024215610867327e-05,
"loss": 1.5562,
"step": 109
},
{
"epoch": 1.05,
"learning_rate": 5.9878553212609184e-05,
"loss": 1.5332,
"step": 110
},
{
"epoch": 1.06,
"learning_rate": 5.95127558036051e-05,
"loss": 1.604,
"step": 111
},
{
"epoch": 1.07,
"learning_rate": 5.9144804264235066e-05,
"loss": 1.4745,
"step": 112
},
{
"epoch": 1.08,
"learning_rate": 5.8774739214880554e-05,
"loss": 1.4254,
"step": 113
},
{
"epoch": 1.08,
"learning_rate": 5.840260150924609e-05,
"loss": 1.6039,
"step": 114
},
{
"epoch": 1.09,
"learning_rate": 5.802843222984919e-05,
"loss": 1.6403,
"step": 115
},
{
"epoch": 1.1,
"learning_rate": 5.765227268348501e-05,
"loss": 1.6617,
"step": 116
},
{
"epoch": 1.11,
"learning_rate": 5.727416439666622e-05,
"loss": 1.5826,
"step": 117
},
{
"epoch": 1.12,
"learning_rate": 5.689414911103867e-05,
"loss": 1.4698,
"step": 118
},
{
"epoch": 1.13,
"learning_rate": 5.651226877877326e-05,
"loss": 1.3276,
"step": 119
},
{
"epoch": 1.14,
"learning_rate": 5.612856555793459e-05,
"loss": 1.4114,
"step": 120
},
{
"epoch": 1.15,
"learning_rate": 5.574308180782693e-05,
"loss": 1.583,
"step": 121
},
{
"epoch": 1.16,
"learning_rate": 5.5355860084317787e-05,
"loss": 1.684,
"step": 122
},
{
"epoch": 1.17,
"learning_rate": 5.496694313514009e-05,
"loss": 1.6231,
"step": 123
},
{
"epoch": 1.18,
"learning_rate": 5.457637389517285e-05,
"loss": 1.5874,
"step": 124
},
{
"epoch": 1.19,
"learning_rate": 5.4184195481701425e-05,
"loss": 1.4062,
"step": 125
},
{
"epoch": 1.2,
"learning_rate": 5.3790451189657486e-05,
"loss": 1.3867,
"step": 126
},
{
"epoch": 1.21,
"learning_rate": 5.339518448683945e-05,
"loss": 1.5874,
"step": 127
},
{
"epoch": 1.22,
"learning_rate": 5.2998439009113814e-05,
"loss": 1.6856,
"step": 128
},
{
"epoch": 1.23,
"learning_rate": 5.260025855559792e-05,
"loss": 1.5057,
"step": 129
},
{
"epoch": 1.24,
"learning_rate": 5.2200687083824706e-05,
"loss": 1.5815,
"step": 130
},
{
"epoch": 1.25,
"learning_rate": 5.179976870488999e-05,
"loss": 1.4807,
"step": 131
},
{
"epoch": 1.26,
"learning_rate": 5.1397547678582745e-05,
"loss": 1.542,
"step": 132
},
{
"epoch": 1.27,
"learning_rate": 5.099406840849902e-05,
"loss": 1.5297,
"step": 133
},
{
"epoch": 1.28,
"learning_rate": 5.058937543713999e-05,
"loss": 1.461,
"step": 134
},
{
"epoch": 1.29,
"learning_rate": 5.018351344099453e-05,
"loss": 1.5576,
"step": 135
},
{
"epoch": 1.3,
"learning_rate": 4.9776527225607274e-05,
"loss": 1.4301,
"step": 136
},
{
"epoch": 1.31,
"learning_rate": 4.93684617206321e-05,
"loss": 1.6082,
"step": 137
},
{
"epoch": 1.32,
"learning_rate": 4.89593619748722e-05,
"loss": 1.6474,
"step": 138
},
{
"epoch": 1.33,
"learning_rate": 4.8549273151306795e-05,
"loss": 1.5037,
"step": 139
},
{
"epoch": 1.34,
"learning_rate": 4.8138240522105365e-05,
"loss": 1.5476,
"step": 140
},
{
"epoch": 1.35,
"learning_rate": 4.7726309463629733e-05,
"loss": 1.5466,
"step": 141
},
{
"epoch": 1.36,
"learning_rate": 4.731352545142478e-05,
"loss": 1.6127,
"step": 142
},
{
"epoch": 1.37,
"learning_rate": 4.689993405519802e-05,
"loss": 1.6105,
"step": 143
},
{
"epoch": 1.38,
"learning_rate": 4.648558093378899e-05,
"loss": 1.492,
"step": 144
},
{
"epoch": 1.38,
"learning_rate": 4.607051183012862e-05,
"loss": 1.5909,
"step": 145
},
{
"epoch": 1.39,
"learning_rate": 4.5654772566189415e-05,
"loss": 1.5474,
"step": 146
},
{
"epoch": 1.4,
"learning_rate": 4.5238409037926905e-05,
"loss": 1.6371,
"step": 147
},
{
"epoch": 1.41,
"learning_rate": 4.4821467210212924e-05,
"loss": 1.4939,
"step": 148
},
{
"epoch": 1.42,
"learning_rate": 4.4403993111761265e-05,
"loss": 1.5418,
"step": 149
},
{
"epoch": 1.43,
"learning_rate": 4.398603283004626e-05,
"loss": 1.5505,
"step": 150
},
{
"epoch": 1.44,
"learning_rate": 4.356763250621496e-05,
"loss": 1.4928,
"step": 151
},
{
"epoch": 1.45,
"learning_rate": 4.314883832999326e-05,
"loss": 1.4589,
"step": 152
},
{
"epoch": 1.46,
"learning_rate": 4.272969653458685e-05,
"loss": 1.5522,
"step": 153
},
{
"epoch": 1.47,
"learning_rate": 4.231025339157714e-05,
"loss": 1.5325,
"step": 154
},
{
"epoch": 1.48,
"learning_rate": 4.189055520581315e-05,
"loss": 1.4912,
"step": 155
},
{
"epoch": 1.49,
"learning_rate": 4.147064831029959e-05,
"loss": 1.5292,
"step": 156
},
{
"epoch": 1.5,
"learning_rate": 4.105057906108189e-05,
"loss": 1.4766,
"step": 157
},
{
"epoch": 1.51,
"learning_rate": 4.063039383212866e-05,
"loss": 1.6332,
"step": 158
},
{
"epoch": 1.52,
"learning_rate": 4.021013901021225e-05,
"loss": 1.5232,
"step": 159
},
{
"epoch": 1.53,
"learning_rate": 3.978986098978777e-05,
"loss": 1.5639,
"step": 160
},
{
"epoch": 1.54,
"learning_rate": 3.936960616787135e-05,
"loss": 1.6731,
"step": 161
},
{
"epoch": 1.55,
"learning_rate": 3.8949420938918124e-05,
"loss": 1.5748,
"step": 162
},
{
"epoch": 1.56,
"learning_rate": 3.852935168970042e-05,
"loss": 1.4529,
"step": 163
},
{
"epoch": 1.57,
"learning_rate": 3.810944479418686e-05,
"loss": 1.5499,
"step": 164
},
{
"epoch": 1.58,
"learning_rate": 3.768974660842287e-05,
"loss": 1.4416,
"step": 165
},
{
"epoch": 1.59,
"learning_rate": 3.727030346541317e-05,
"loss": 1.4857,
"step": 166
},
{
"epoch": 1.6,
"learning_rate": 3.685116167000675e-05,
"loss": 1.6612,
"step": 167
},
{
"epoch": 1.61,
"learning_rate": 3.6432367493785056e-05,
"loss": 1.6123,
"step": 168
},
{
"epoch": 1.62,
"learning_rate": 3.601396716995375e-05,
"loss": 1.4952,
"step": 169
},
{
"epoch": 1.63,
"learning_rate": 3.559600688823875e-05,
"loss": 1.5899,
"step": 170
},
{
"epoch": 1.64,
"learning_rate": 3.517853278978708e-05,
"loss": 1.5784,
"step": 171
},
{
"epoch": 1.65,
"learning_rate": 3.4761590962073115e-05,
"loss": 1.6251,
"step": 172
},
{
"epoch": 1.66,
"learning_rate": 3.434522743381061e-05,
"loss": 1.6478,
"step": 173
},
{
"epoch": 1.67,
"learning_rate": 3.39294881698714e-05,
"loss": 1.5043,
"step": 174
},
{
"epoch": 1.68,
"learning_rate": 3.3514419066211025e-05,
"loss": 1.6968,
"step": 175
},
{
"epoch": 1.69,
"learning_rate": 3.310006594480199e-05,
"loss": 1.395,
"step": 176
},
{
"epoch": 1.69,
"learning_rate": 3.268647454857524e-05,
"loss": 1.6285,
"step": 177
},
{
"epoch": 1.7,
"learning_rate": 3.227369053637028e-05,
"loss": 1.4827,
"step": 178
},
{
"epoch": 1.71,
"learning_rate": 3.1861759477894656e-05,
"loss": 1.3457,
"step": 179
},
{
"epoch": 1.72,
"learning_rate": 3.145072684869322e-05,
"loss": 1.4998,
"step": 180
},
{
"epoch": 1.73,
"learning_rate": 3.104063802512782e-05,
"loss": 1.536,
"step": 181
},
{
"epoch": 1.74,
"learning_rate": 3.063153827936792e-05,
"loss": 1.5633,
"step": 182
},
{
"epoch": 1.75,
"learning_rate": 3.0223472774392753e-05,
"loss": 1.7605,
"step": 183
},
{
"epoch": 1.76,
"learning_rate": 2.9816486559005482e-05,
"loss": 1.5604,
"step": 184
},
{
"epoch": 1.77,
"learning_rate": 2.9410624562860026e-05,
"loss": 1.5909,
"step": 185
},
{
"epoch": 1.78,
"learning_rate": 2.9005931591500974e-05,
"loss": 1.4833,
"step": 186
},
{
"epoch": 1.79,
"learning_rate": 2.860245232141726e-05,
"loss": 1.551,
"step": 187
},
{
"epoch": 1.8,
"learning_rate": 2.8200231295110012e-05,
"loss": 1.5279,
"step": 188
},
{
"epoch": 1.81,
"learning_rate": 2.7799312916175294e-05,
"loss": 1.5564,
"step": 189
},
{
"epoch": 1.82,
"learning_rate": 2.7399741444402087e-05,
"loss": 1.4859,
"step": 190
},
{
"epoch": 1.83,
"learning_rate": 2.7001560990886196e-05,
"loss": 1.5372,
"step": 191
},
{
"epoch": 1.84,
"learning_rate": 2.6604815513160556e-05,
"loss": 1.4932,
"step": 192
},
{
"epoch": 1.85,
"learning_rate": 2.6209548810342517e-05,
"loss": 1.5412,
"step": 193
},
{
"epoch": 1.86,
"learning_rate": 2.5815804518298575e-05,
"loss": 1.4758,
"step": 194
},
{
"epoch": 1.87,
"learning_rate": 2.542362610482715e-05,
"loss": 1.715,
"step": 195
},
{
"epoch": 1.88,
"learning_rate": 2.503305686485991e-05,
"loss": 1.5454,
"step": 196
},
{
"epoch": 1.89,
"learning_rate": 2.464413991568222e-05,
"loss": 1.43,
"step": 197
},
{
"epoch": 1.9,
"learning_rate": 2.4256918192173088e-05,
"loss": 1.5798,
"step": 198
},
{
"epoch": 1.91,
"learning_rate": 2.3871434442065414e-05,
"loss": 1.4315,
"step": 199
},
{
"epoch": 1.92,
"learning_rate": 2.3487731221226754e-05,
"loss": 1.6566,
"step": 200
},
{
"epoch": 1.93,
"learning_rate": 2.3105850888961348e-05,
"loss": 1.5944,
"step": 201
},
{
"epoch": 1.94,
"learning_rate": 2.272583560333379e-05,
"loss": 1.5169,
"step": 202
},
{
"epoch": 1.95,
"learning_rate": 2.2347727316515e-05,
"loss": 1.6553,
"step": 203
},
{
"epoch": 1.96,
"learning_rate": 2.1971567770150814e-05,
"loss": 1.6193,
"step": 204
},
{
"epoch": 1.97,
"learning_rate": 2.1597398490753917e-05,
"loss": 1.6137,
"step": 205
},
{
"epoch": 1.98,
"learning_rate": 2.1225260785119456e-05,
"loss": 1.459,
"step": 206
},
{
"epoch": 1.99,
"learning_rate": 2.0855195735764947e-05,
"loss": 1.6145,
"step": 207
},
{
"epoch": 2.0,
"learning_rate": 2.0487244196394912e-05,
"loss": 1.607,
"step": 208
},
{
"epoch": 2.0,
"learning_rate": 2.0121446787390822e-05,
"loss": 1.5978,
"step": 209
},
{
"epoch": 2.01,
"learning_rate": 1.9757843891326736e-05,
"loss": 1.4527,
"step": 210
}
],
"logging_steps": 1,
"max_steps": 309,
"num_train_epochs": 3,
"save_steps": 500,
"total_flos": 1.4076450105049743e+18,
"trial_name": null,
"trial_params": null
}