jonathanagustin's picture
Model save
c799181
raw
history blame
24.9 kB
{
"best_metric": 1.2616792917251587,
"best_model_checkpoint": "/content/drive/My Drive/Colab Notebooks/aai520-project/checkpoints/distilbert-finetuned-uncased/checkpoint-3900",
"epoch": 7.257416033341506,
"eval_steps": 100,
"global_step": 7400,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.39,
"learning_rate": 1.607843137254902e-05,
"loss": 3.6437,
"step": 100
},
{
"epoch": 0.39,
"eval_loss": 2.1780340671539307,
"eval_runtime": 8.4412,
"eval_samples_per_second": 1417.927,
"eval_steps_per_second": 11.136,
"step": 100
},
{
"epoch": 0.78,
"learning_rate": 1.215686274509804e-05,
"loss": 2.1596,
"step": 200
},
{
"epoch": 0.78,
"eval_loss": 1.6557185649871826,
"eval_runtime": 8.3581,
"eval_samples_per_second": 1432.022,
"eval_steps_per_second": 11.247,
"step": 200
},
{
"epoch": 1.18,
"learning_rate": 8.23529411764706e-06,
"loss": 1.8138,
"step": 300
},
{
"epoch": 1.18,
"eval_loss": 1.5682721138000488,
"eval_runtime": 8.4191,
"eval_samples_per_second": 1421.643,
"eval_steps_per_second": 11.165,
"step": 300
},
{
"epoch": 1.57,
"learning_rate": 4.313725490196079e-06,
"loss": 1.6987,
"step": 400
},
{
"epoch": 1.57,
"eval_loss": 1.5075817108154297,
"eval_runtime": 8.3595,
"eval_samples_per_second": 1431.779,
"eval_steps_per_second": 11.245,
"step": 400
},
{
"epoch": 1.96,
"learning_rate": 3.921568627450981e-07,
"loss": 1.6586,
"step": 500
},
{
"epoch": 1.96,
"eval_loss": 1.535025715827942,
"eval_runtime": 8.4289,
"eval_samples_per_second": 1419.991,
"eval_steps_per_second": 11.152,
"step": 500
},
{
"epoch": 1.18,
"learning_rate": 8.23529411764706e-06,
"loss": 1.5957,
"step": 600
},
{
"epoch": 1.18,
"eval_loss": 1.4431041479110718,
"eval_runtime": 8.5594,
"eval_samples_per_second": 1398.342,
"eval_steps_per_second": 21.964,
"step": 600
},
{
"epoch": 1.37,
"learning_rate": 6.274509803921569e-06,
"loss": 1.5825,
"step": 700
},
{
"epoch": 1.37,
"eval_loss": 1.495514154434204,
"eval_runtime": 8.5285,
"eval_samples_per_second": 1403.419,
"eval_steps_per_second": 22.044,
"step": 700
},
{
"epoch": 1.57,
"learning_rate": 4.313725490196079e-06,
"loss": 1.5523,
"step": 800
},
{
"epoch": 1.57,
"eval_loss": 1.4444433450698853,
"eval_runtime": 8.5112,
"eval_samples_per_second": 1406.272,
"eval_steps_per_second": 22.089,
"step": 800
},
{
"epoch": 1.76,
"learning_rate": 2.3529411764705885e-06,
"loss": 1.5346,
"step": 900
},
{
"epoch": 1.76,
"eval_loss": 1.393009066581726,
"eval_runtime": 8.5265,
"eval_samples_per_second": 1403.737,
"eval_steps_per_second": 22.049,
"step": 900
},
{
"epoch": 1.96,
"learning_rate": 3.921568627450981e-07,
"loss": 1.5098,
"step": 1000
},
{
"epoch": 1.96,
"eval_loss": 1.4284701347351074,
"eval_runtime": 8.5994,
"eval_samples_per_second": 1391.84,
"eval_steps_per_second": 21.862,
"step": 1000
},
{
"epoch": 2.16,
"learning_rate": 9.215686274509804e-06,
"loss": 1.4632,
"step": 1100
},
{
"epoch": 2.16,
"eval_loss": 1.3630493879318237,
"eval_runtime": 8.4807,
"eval_samples_per_second": 1411.328,
"eval_steps_per_second": 22.168,
"step": 1100
},
{
"epoch": 2.35,
"learning_rate": 8.23529411764706e-06,
"loss": 1.4468,
"step": 1200
},
{
"epoch": 2.35,
"eval_loss": 1.370953917503357,
"eval_runtime": 8.5147,
"eval_samples_per_second": 1405.685,
"eval_steps_per_second": 22.079,
"step": 1200
},
{
"epoch": 2.55,
"learning_rate": 7.2549019607843145e-06,
"loss": 1.4343,
"step": 1300
},
{
"epoch": 2.55,
"eval_loss": 1.3422259092330933,
"eval_runtime": 8.4859,
"eval_samples_per_second": 1410.461,
"eval_steps_per_second": 22.154,
"step": 1300
},
{
"epoch": 2.75,
"learning_rate": 6.274509803921569e-06,
"loss": 1.4225,
"step": 1400
},
{
"epoch": 2.75,
"eval_loss": 1.397080659866333,
"eval_runtime": 8.4725,
"eval_samples_per_second": 1412.689,
"eval_steps_per_second": 22.189,
"step": 1400
},
{
"epoch": 2.94,
"learning_rate": 5.294117647058824e-06,
"loss": 1.408,
"step": 1500
},
{
"epoch": 2.94,
"eval_loss": 1.435463547706604,
"eval_runtime": 8.4775,
"eval_samples_per_second": 1411.85,
"eval_steps_per_second": 22.176,
"step": 1500
},
{
"epoch": 3.14,
"learning_rate": 4.313725490196079e-06,
"loss": 1.3609,
"step": 1600
},
{
"epoch": 3.14,
"eval_loss": 1.3331981897354126,
"eval_runtime": 8.4786,
"eval_samples_per_second": 1411.679,
"eval_steps_per_second": 22.174,
"step": 1600
},
{
"epoch": 3.33,
"learning_rate": 3.3333333333333333e-06,
"loss": 1.3398,
"step": 1700
},
{
"epoch": 3.33,
"eval_loss": 1.3791619539260864,
"eval_runtime": 8.4678,
"eval_samples_per_second": 1413.466,
"eval_steps_per_second": 22.202,
"step": 1700
},
{
"epoch": 3.53,
"learning_rate": 2.3529411764705885e-06,
"loss": 1.3224,
"step": 1800
},
{
"epoch": 3.53,
"eval_loss": 1.41716730594635,
"eval_runtime": 8.4259,
"eval_samples_per_second": 1420.506,
"eval_steps_per_second": 22.312,
"step": 1800
},
{
"epoch": 3.73,
"learning_rate": 1.3725490196078434e-06,
"loss": 1.3152,
"step": 1900
},
{
"epoch": 3.73,
"eval_loss": 1.3955893516540527,
"eval_runtime": 8.444,
"eval_samples_per_second": 1417.453,
"eval_steps_per_second": 22.264,
"step": 1900
},
{
"epoch": 3.92,
"learning_rate": 3.921568627450981e-07,
"loss": 1.3141,
"step": 2000
},
{
"epoch": 3.92,
"eval_loss": 1.3748189210891724,
"eval_runtime": 8.4509,
"eval_samples_per_second": 1416.303,
"eval_steps_per_second": 22.246,
"step": 2000
},
{
"epoch": 2.06,
"learning_rate": 1.587831207065751e-05,
"loss": 1.3085,
"step": 2100
},
{
"epoch": 2.06,
"eval_loss": 1.3948506116867065,
"eval_runtime": 61.1737,
"eval_samples_per_second": 195.656,
"eval_steps_per_second": 6.13,
"step": 2100
},
{
"epoch": 2.16,
"learning_rate": 1.5682041216879295e-05,
"loss": 1.3325,
"step": 2200
},
{
"epoch": 2.16,
"eval_loss": 1.4869881868362427,
"eval_runtime": 61.232,
"eval_samples_per_second": 195.47,
"eval_steps_per_second": 6.124,
"step": 2200
},
{
"epoch": 2.26,
"learning_rate": 1.548577036310108e-05,
"loss": 1.3162,
"step": 2300
},
{
"epoch": 2.26,
"eval_loss": 1.4565335512161255,
"eval_runtime": 61.2209,
"eval_samples_per_second": 195.505,
"eval_steps_per_second": 6.125,
"step": 2300
},
{
"epoch": 2.35,
"learning_rate": 1.5289499509322867e-05,
"loss": 1.2936,
"step": 2400
},
{
"epoch": 2.35,
"eval_loss": 1.449613332748413,
"eval_runtime": 61.2023,
"eval_samples_per_second": 195.565,
"eval_steps_per_second": 6.127,
"step": 2400
},
{
"epoch": 2.45,
"learning_rate": 1.5093228655544654e-05,
"loss": 1.2648,
"step": 2500
},
{
"epoch": 2.45,
"eval_loss": 1.2867687940597534,
"eval_runtime": 61.2092,
"eval_samples_per_second": 195.542,
"eval_steps_per_second": 6.127,
"step": 2500
},
{
"epoch": 2.55,
"learning_rate": 1.4896957801766438e-05,
"loss": 1.2531,
"step": 2600
},
{
"epoch": 2.55,
"eval_loss": 1.5093618631362915,
"eval_runtime": 60.9769,
"eval_samples_per_second": 196.287,
"eval_steps_per_second": 6.15,
"step": 2600
},
{
"epoch": 2.65,
"learning_rate": 1.4700686947988226e-05,
"loss": 1.2599,
"step": 2700
},
{
"epoch": 2.65,
"eval_loss": 1.3450872898101807,
"eval_runtime": 61.0675,
"eval_samples_per_second": 195.996,
"eval_steps_per_second": 6.141,
"step": 2700
},
{
"epoch": 2.75,
"learning_rate": 1.4504416094210011e-05,
"loss": 1.2545,
"step": 2800
},
{
"epoch": 2.75,
"eval_loss": 1.407065749168396,
"eval_runtime": 61.1333,
"eval_samples_per_second": 195.785,
"eval_steps_per_second": 6.134,
"step": 2800
},
{
"epoch": 2.84,
"learning_rate": 1.4308145240431797e-05,
"loss": 1.2461,
"step": 2900
},
{
"epoch": 2.84,
"eval_loss": 1.3378450870513916,
"eval_runtime": 61.1961,
"eval_samples_per_second": 195.584,
"eval_steps_per_second": 6.128,
"step": 2900
},
{
"epoch": 2.94,
"learning_rate": 1.4111874386653583e-05,
"loss": 1.2038,
"step": 3000
},
{
"epoch": 2.94,
"eval_loss": 1.294646143913269,
"eval_runtime": 61.1636,
"eval_samples_per_second": 195.688,
"eval_steps_per_second": 6.131,
"step": 3000
},
{
"epoch": 3.04,
"learning_rate": 1.391560353287537e-05,
"loss": 1.1677,
"step": 3100
},
{
"epoch": 3.04,
"eval_loss": 1.480231761932373,
"eval_runtime": 61.0678,
"eval_samples_per_second": 195.995,
"eval_steps_per_second": 6.141,
"step": 3100
},
{
"epoch": 3.14,
"learning_rate": 1.3719332679097154e-05,
"loss": 1.103,
"step": 3200
},
{
"epoch": 3.14,
"eval_loss": 1.3580176830291748,
"eval_runtime": 61.18,
"eval_samples_per_second": 195.636,
"eval_steps_per_second": 6.129,
"step": 3200
},
{
"epoch": 3.24,
"learning_rate": 1.3523061825318942e-05,
"loss": 1.1205,
"step": 3300
},
{
"epoch": 3.24,
"eval_loss": 1.3818870782852173,
"eval_runtime": 60.9958,
"eval_samples_per_second": 196.227,
"eval_steps_per_second": 6.148,
"step": 3300
},
{
"epoch": 3.33,
"learning_rate": 1.3326790971540726e-05,
"loss": 1.095,
"step": 3400
},
{
"epoch": 3.33,
"eval_loss": 1.4335613250732422,
"eval_runtime": 61.1187,
"eval_samples_per_second": 195.832,
"eval_steps_per_second": 6.136,
"step": 3400
},
{
"epoch": 3.43,
"learning_rate": 1.3130520117762513e-05,
"loss": 1.0896,
"step": 3500
},
{
"epoch": 3.43,
"eval_loss": 1.4962539672851562,
"eval_runtime": 61.0543,
"eval_samples_per_second": 196.039,
"eval_steps_per_second": 6.142,
"step": 3500
},
{
"epoch": 3.53,
"learning_rate": 1.2934249263984299e-05,
"loss": 1.0856,
"step": 3600
},
{
"epoch": 3.53,
"eval_loss": 1.3384228944778442,
"eval_runtime": 61.1027,
"eval_samples_per_second": 195.883,
"eval_steps_per_second": 6.137,
"step": 3600
},
{
"epoch": 3.63,
"learning_rate": 1.2737978410206085e-05,
"loss": 1.0652,
"step": 3700
},
{
"epoch": 3.63,
"eval_loss": 1.3583240509033203,
"eval_runtime": 61.0826,
"eval_samples_per_second": 195.948,
"eval_steps_per_second": 6.139,
"step": 3700
},
{
"epoch": 3.73,
"learning_rate": 1.254170755642787e-05,
"loss": 1.0859,
"step": 3800
},
{
"epoch": 3.73,
"eval_loss": 1.414008378982544,
"eval_runtime": 61.0681,
"eval_samples_per_second": 195.994,
"eval_steps_per_second": 6.141,
"step": 3800
},
{
"epoch": 3.83,
"learning_rate": 1.2345436702649658e-05,
"loss": 1.058,
"step": 3900
},
{
"epoch": 3.83,
"eval_loss": 1.2616792917251587,
"eval_runtime": 61.1143,
"eval_samples_per_second": 195.846,
"eval_steps_per_second": 6.136,
"step": 3900
},
{
"epoch": 3.92,
"learning_rate": 1.2149165848871442e-05,
"loss": 1.0724,
"step": 4000
},
{
"epoch": 3.92,
"eval_loss": 1.3551816940307617,
"eval_runtime": 61.0974,
"eval_samples_per_second": 195.9,
"eval_steps_per_second": 6.138,
"step": 4000
},
{
"epoch": 4.02,
"learning_rate": 1.1954857703631012e-05,
"loss": 1.0509,
"step": 4100
},
{
"epoch": 4.02,
"eval_loss": 1.2970877885818481,
"eval_runtime": 61.0416,
"eval_samples_per_second": 196.079,
"eval_steps_per_second": 6.143,
"step": 4100
},
{
"epoch": 4.12,
"learning_rate": 1.1758586849852797e-05,
"loss": 0.97,
"step": 4200
},
{
"epoch": 4.12,
"eval_loss": 1.3268026113510132,
"eval_runtime": 61.0438,
"eval_samples_per_second": 196.072,
"eval_steps_per_second": 6.143,
"step": 4200
},
{
"epoch": 4.22,
"learning_rate": 1.1562315996074585e-05,
"loss": 0.95,
"step": 4300
},
{
"epoch": 4.22,
"eval_loss": 1.3753584623336792,
"eval_runtime": 61.1527,
"eval_samples_per_second": 195.723,
"eval_steps_per_second": 6.132,
"step": 4300
},
{
"epoch": 4.32,
"learning_rate": 1.1366045142296369e-05,
"loss": 0.9337,
"step": 4400
},
{
"epoch": 4.32,
"eval_loss": 1.3687292337417603,
"eval_runtime": 61.1591,
"eval_samples_per_second": 195.703,
"eval_steps_per_second": 6.132,
"step": 4400
},
{
"epoch": 4.41,
"learning_rate": 1.1169774288518156e-05,
"loss": 0.977,
"step": 4500
},
{
"epoch": 4.41,
"eval_loss": 1.3613475561141968,
"eval_runtime": 61.1865,
"eval_samples_per_second": 195.615,
"eval_steps_per_second": 6.129,
"step": 4500
},
{
"epoch": 4.51,
"learning_rate": 1.0973503434739942e-05,
"loss": 0.9484,
"step": 4600
},
{
"epoch": 4.51,
"eval_loss": 1.513939380645752,
"eval_runtime": 61.2246,
"eval_samples_per_second": 195.493,
"eval_steps_per_second": 6.125,
"step": 4600
},
{
"epoch": 4.61,
"learning_rate": 1.0777232580961728e-05,
"loss": 0.9739,
"step": 4700
},
{
"epoch": 4.61,
"eval_loss": 1.2861210107803345,
"eval_runtime": 61.1721,
"eval_samples_per_second": 195.661,
"eval_steps_per_second": 6.13,
"step": 4700
},
{
"epoch": 4.71,
"learning_rate": 1.0580961727183514e-05,
"loss": 0.955,
"step": 4800
},
{
"epoch": 4.71,
"eval_loss": 1.3666507005691528,
"eval_runtime": 61.1291,
"eval_samples_per_second": 195.799,
"eval_steps_per_second": 6.135,
"step": 4800
},
{
"epoch": 4.81,
"learning_rate": 1.0384690873405301e-05,
"loss": 0.9536,
"step": 4900
},
{
"epoch": 4.81,
"eval_loss": 1.3179610967636108,
"eval_runtime": 61.1785,
"eval_samples_per_second": 195.641,
"eval_steps_per_second": 6.13,
"step": 4900
},
{
"epoch": 4.9,
"learning_rate": 1.0188420019627085e-05,
"loss": 0.9541,
"step": 5000
},
{
"epoch": 4.9,
"eval_loss": 1.4610702991485596,
"eval_runtime": 61.0871,
"eval_samples_per_second": 195.933,
"eval_steps_per_second": 6.139,
"step": 5000
},
{
"epoch": 5.0,
"learning_rate": 9.992149165848873e-06,
"loss": 0.9462,
"step": 5100
},
{
"epoch": 5.0,
"eval_loss": 1.4066604375839233,
"eval_runtime": 61.1331,
"eval_samples_per_second": 195.786,
"eval_steps_per_second": 6.134,
"step": 5100
},
{
"epoch": 5.1,
"learning_rate": 9.795878312070658e-06,
"loss": 0.8728,
"step": 5200
},
{
"epoch": 5.1,
"eval_loss": 1.3490474224090576,
"eval_runtime": 61.0973,
"eval_samples_per_second": 195.901,
"eval_steps_per_second": 6.138,
"step": 5200
},
{
"epoch": 5.2,
"learning_rate": 9.599607458292444e-06,
"loss": 0.8646,
"step": 5300
},
{
"epoch": 5.2,
"eval_loss": 1.4630706310272217,
"eval_runtime": 61.0445,
"eval_samples_per_second": 196.07,
"eval_steps_per_second": 6.143,
"step": 5300
},
{
"epoch": 5.3,
"learning_rate": 9.40333660451423e-06,
"loss": 0.8683,
"step": 5400
},
{
"epoch": 5.3,
"eval_loss": 1.4977810382843018,
"eval_runtime": 61.0754,
"eval_samples_per_second": 195.971,
"eval_steps_per_second": 6.14,
"step": 5400
},
{
"epoch": 5.39,
"learning_rate": 9.207065750736016e-06,
"loss": 0.8571,
"step": 5500
},
{
"epoch": 5.39,
"eval_loss": 1.5814284086227417,
"eval_runtime": 61.0641,
"eval_samples_per_second": 196.007,
"eval_steps_per_second": 6.141,
"step": 5500
},
{
"epoch": 5.49,
"learning_rate": 9.010794896957803e-06,
"loss": 0.8475,
"step": 5600
},
{
"epoch": 5.49,
"eval_loss": 1.5535171031951904,
"eval_runtime": 61.1062,
"eval_samples_per_second": 195.872,
"eval_steps_per_second": 6.137,
"step": 5600
},
{
"epoch": 5.59,
"learning_rate": 8.814524043179589e-06,
"loss": 0.8653,
"step": 5700
},
{
"epoch": 5.59,
"eval_loss": 1.4938398599624634,
"eval_runtime": 61.1584,
"eval_samples_per_second": 195.705,
"eval_steps_per_second": 6.132,
"step": 5700
},
{
"epoch": 5.69,
"learning_rate": 8.618253189401375e-06,
"loss": 0.8664,
"step": 5800
},
{
"epoch": 5.69,
"eval_loss": 1.414058804512024,
"eval_runtime": 61.1886,
"eval_samples_per_second": 195.608,
"eval_steps_per_second": 6.129,
"step": 5800
},
{
"epoch": 5.79,
"learning_rate": 8.42198233562316e-06,
"loss": 0.889,
"step": 5900
},
{
"epoch": 5.79,
"eval_loss": 1.4486888647079468,
"eval_runtime": 61.1387,
"eval_samples_per_second": 195.768,
"eval_steps_per_second": 6.134,
"step": 5900
},
{
"epoch": 5.88,
"learning_rate": 8.225711481844946e-06,
"loss": 0.8601,
"step": 6000
},
{
"epoch": 5.88,
"eval_loss": 1.47215735912323,
"eval_runtime": 61.1249,
"eval_samples_per_second": 195.812,
"eval_steps_per_second": 6.135,
"step": 6000
},
{
"epoch": 5.98,
"learning_rate": 8.031403336604516e-06,
"loss": 0.8645,
"step": 6100
},
{
"epoch": 5.98,
"eval_loss": 1.5842609405517578,
"eval_runtime": 61.0783,
"eval_samples_per_second": 195.962,
"eval_steps_per_second": 6.14,
"step": 6100
},
{
"epoch": 6.08,
"learning_rate": 7.835132482826301e-06,
"loss": 0.785,
"step": 6200
},
{
"epoch": 6.08,
"eval_loss": 1.6027640104293823,
"eval_runtime": 61.1172,
"eval_samples_per_second": 195.837,
"eval_steps_per_second": 6.136,
"step": 6200
},
{
"epoch": 6.18,
"learning_rate": 7.638861629048087e-06,
"loss": 0.7711,
"step": 6300
},
{
"epoch": 6.18,
"eval_loss": 1.6270956993103027,
"eval_runtime": 61.0612,
"eval_samples_per_second": 196.016,
"eval_steps_per_second": 6.141,
"step": 6300
},
{
"epoch": 6.28,
"learning_rate": 7.442590775269874e-06,
"loss": 0.8056,
"step": 6400
},
{
"epoch": 6.28,
"eval_loss": 1.5399292707443237,
"eval_runtime": 61.1714,
"eval_samples_per_second": 195.663,
"eval_steps_per_second": 6.13,
"step": 6400
},
{
"epoch": 6.37,
"learning_rate": 7.246319921491659e-06,
"loss": 0.8087,
"step": 6500
},
{
"epoch": 6.37,
"eval_loss": 1.492693305015564,
"eval_runtime": 61.0261,
"eval_samples_per_second": 196.129,
"eval_steps_per_second": 6.145,
"step": 6500
},
{
"epoch": 6.47,
"learning_rate": 7.0500490677134445e-06,
"loss": 0.7859,
"step": 6600
},
{
"epoch": 6.47,
"eval_loss": 1.4677467346191406,
"eval_runtime": 61.0807,
"eval_samples_per_second": 195.954,
"eval_steps_per_second": 6.139,
"step": 6600
},
{
"epoch": 6.57,
"learning_rate": 6.853778213935232e-06,
"loss": 0.7896,
"step": 6700
},
{
"epoch": 6.57,
"eval_loss": 1.4780325889587402,
"eval_runtime": 61.0973,
"eval_samples_per_second": 195.901,
"eval_steps_per_second": 6.138,
"step": 6700
},
{
"epoch": 6.67,
"learning_rate": 6.657507360157017e-06,
"loss": 0.7971,
"step": 6800
},
{
"epoch": 6.67,
"eval_loss": 1.5110238790512085,
"eval_runtime": 61.1306,
"eval_samples_per_second": 195.794,
"eval_steps_per_second": 6.134,
"step": 6800
},
{
"epoch": 6.77,
"learning_rate": 6.461236506378803e-06,
"loss": 0.7952,
"step": 6900
},
{
"epoch": 6.77,
"eval_loss": 1.545872688293457,
"eval_runtime": 61.0099,
"eval_samples_per_second": 196.181,
"eval_steps_per_second": 6.147,
"step": 6900
},
{
"epoch": 6.87,
"learning_rate": 6.26496565260059e-06,
"loss": 0.7971,
"step": 7000
},
{
"epoch": 6.87,
"eval_loss": 1.5281697511672974,
"eval_runtime": 61.0816,
"eval_samples_per_second": 195.951,
"eval_steps_per_second": 6.139,
"step": 7000
},
{
"epoch": 6.96,
"learning_rate": 6.068694798822376e-06,
"loss": 0.7908,
"step": 7100
},
{
"epoch": 6.96,
"eval_loss": 1.4799116849899292,
"eval_runtime": 61.1305,
"eval_samples_per_second": 195.794,
"eval_steps_per_second": 6.134,
"step": 7100
},
{
"epoch": 7.06,
"learning_rate": 5.872423945044161e-06,
"loss": 0.7456,
"step": 7200
},
{
"epoch": 7.06,
"eval_loss": 1.6487486362457275,
"eval_runtime": 61.0413,
"eval_samples_per_second": 196.08,
"eval_steps_per_second": 6.143,
"step": 7200
},
{
"epoch": 7.16,
"learning_rate": 5.676153091265948e-06,
"loss": 0.7236,
"step": 7300
},
{
"epoch": 7.16,
"eval_loss": 1.654253602027893,
"eval_runtime": 61.1832,
"eval_samples_per_second": 195.626,
"eval_steps_per_second": 6.129,
"step": 7300
},
{
"epoch": 7.26,
"learning_rate": 5.479882237487734e-06,
"loss": 0.7484,
"step": 7400
},
{
"epoch": 7.26,
"eval_loss": 1.6202023029327393,
"eval_runtime": 61.1291,
"eval_samples_per_second": 195.799,
"eval_steps_per_second": 6.135,
"step": 7400
},
{
"epoch": 7.26,
"step": 7400,
"total_flos": 1.738708177538776e+17,
"train_loss": 0.0,
"train_runtime": 0.6152,
"train_samples_per_second": 2121277.112,
"train_steps_per_second": 8289.858
},
{
"epoch": 7.26,
"eval_loss": 1.261675477027893,
"eval_runtime": 63.7101,
"eval_samples_per_second": 187.867,
"eval_steps_per_second": 2.951,
"step": 7400
}
],
"logging_steps": 100,
"max_steps": 5100,
"num_train_epochs": 10,
"save_steps": 100,
"total_flos": 1.738708177538776e+17,
"trial_name": null,
"trial_params": null
}