guru1984-v2 / metrics.json
emdemor's picture
Training in progress, step 3800
6d16c73 verified
{"Step":50,"eval_loss":3.8617525101,"eval_runtime":29.4492,"eval_samples_per_second":3.396,"eval_steps_per_second":0.441,"epoch":0.0392772977}
{"Step":100,"eval_loss":2.5934023857,"eval_runtime":29.4336,"eval_samples_per_second":3.397,"eval_steps_per_second":0.442,"epoch":0.0785545954}
{"Step":150,"eval_loss":2.2559566498,"eval_runtime":29.4433,"eval_samples_per_second":3.396,"eval_steps_per_second":0.442,"epoch":0.1178318932}
{"Step":200,"eval_loss":2.1369433403,"eval_runtime":29.6429,"eval_samples_per_second":3.373,"eval_steps_per_second":0.439,"epoch":0.1571091909}
{"Step":250,"eval_loss":2.0804655552,"eval_runtime":29.5575,"eval_samples_per_second":3.383,"eval_steps_per_second":0.44,"epoch":0.1963864886}
{"Step":300,"eval_loss":2.0563046932,"eval_runtime":29.4932,"eval_samples_per_second":3.391,"eval_steps_per_second":0.441,"epoch":0.2356637863}
{"Step":350,"eval_loss":2.0286335945,"eval_runtime":29.3134,"eval_samples_per_second":3.411,"eval_steps_per_second":0.443,"epoch":0.2749410841}
{"Step":400,"eval_loss":2.0177054405,"eval_runtime":29.516,"eval_samples_per_second":3.388,"eval_steps_per_second":0.44,"epoch":0.3142183818}
{"Step":450,"eval_loss":2.001973629,"eval_runtime":29.578,"eval_samples_per_second":3.381,"eval_steps_per_second":0.44,"epoch":0.3534956795}
{"Step":500,"eval_loss":1.9914397001,"eval_runtime":29.3577,"eval_samples_per_second":3.406,"eval_steps_per_second":0.443,"epoch":0.3927729772}
{"Step":550,"eval_loss":1.9789185524,"eval_runtime":29.5883,"eval_samples_per_second":3.38,"eval_steps_per_second":0.439,"epoch":0.4320502749}
{"Step":600,"eval_loss":1.9679882526,"eval_runtime":29.7136,"eval_samples_per_second":3.365,"eval_steps_per_second":0.438,"epoch":0.4713275727}
{"Step":650,"eval_loss":1.9631274939,"eval_runtime":29.8472,"eval_samples_per_second":3.35,"eval_steps_per_second":0.436,"epoch":0.5106048704}
{"Step":700,"eval_loss":1.9546252489,"eval_runtime":29.5017,"eval_samples_per_second":3.39,"eval_steps_per_second":0.441,"epoch":0.5498821681}
{"Step":750,"eval_loss":1.9469780922,"eval_runtime":29.8753,"eval_samples_per_second":3.347,"eval_steps_per_second":0.435,"epoch":0.5891594658}
{"Step":800,"eval_loss":1.9397352934,"eval_runtime":29.4107,"eval_samples_per_second":3.4,"eval_steps_per_second":0.442,"epoch":0.6284367636}
{"Step":850,"eval_loss":1.9425079823,"eval_runtime":29.4898,"eval_samples_per_second":3.391,"eval_steps_per_second":0.441,"epoch":0.6677140613}
{"Step":900,"eval_loss":1.9176784754,"eval_runtime":29.544,"eval_samples_per_second":3.385,"eval_steps_per_second":0.44,"epoch":0.706991359}
{"Step":950,"eval_loss":1.9149932861,"eval_runtime":29.4076,"eval_samples_per_second":3.4,"eval_steps_per_second":0.442,"epoch":0.7462686567}
{"Step":1000,"eval_loss":1.9071648121,"eval_runtime":29.4527,"eval_samples_per_second":3.395,"eval_steps_per_second":0.441,"epoch":0.7855459544}
{"Step":1050,"eval_loss":1.8993133307,"eval_runtime":29.5512,"eval_samples_per_second":3.384,"eval_steps_per_second":0.44,"epoch":0.8248232522}
{"Step":1100,"eval_loss":1.9054021835,"eval_runtime":29.3876,"eval_samples_per_second":3.403,"eval_steps_per_second":0.442,"epoch":0.8641005499}
{"Step":1150,"eval_loss":1.8948385715,"eval_runtime":29.428,"eval_samples_per_second":3.398,"eval_steps_per_second":0.442,"epoch":0.9033778476}
{"Step":1200,"eval_loss":1.8822929859,"eval_runtime":29.4891,"eval_samples_per_second":3.391,"eval_steps_per_second":0.441,"epoch":0.9426551453}
{"Step":1250,"eval_loss":1.8784922361,"eval_runtime":29.4313,"eval_samples_per_second":3.398,"eval_steps_per_second":0.442,"epoch":0.981932443}
{"Step":1300,"eval_loss":1.8769853115,"eval_runtime":29.4816,"eval_samples_per_second":3.392,"eval_steps_per_second":0.441,"epoch":1.0212097408}
{"Step":1350,"eval_loss":1.8668268919,"eval_runtime":29.5392,"eval_samples_per_second":3.385,"eval_steps_per_second":0.44,"epoch":1.0604870385}
{"Step":1400,"eval_loss":1.8661786318,"eval_runtime":29.4511,"eval_samples_per_second":3.395,"eval_steps_per_second":0.441,"epoch":1.0997643362}
{"Step":1450,"eval_loss":1.8573988676,"eval_runtime":29.4384,"eval_samples_per_second":3.397,"eval_steps_per_second":0.442,"epoch":1.1390416339}
{"Step":1500,"eval_loss":1.8574242592,"eval_runtime":29.4845,"eval_samples_per_second":3.392,"eval_steps_per_second":0.441,"epoch":1.1783189317}
{"Step":1550,"eval_loss":1.8602547646,"eval_runtime":29.5084,"eval_samples_per_second":3.389,"eval_steps_per_second":0.441,"epoch":1.2175962294}
{"Step":1600,"eval_loss":1.8516952991,"eval_runtime":29.539,"eval_samples_per_second":3.385,"eval_steps_per_second":0.44,"epoch":1.2568735271}
{"Step":1650,"eval_loss":1.8447459936,"eval_runtime":29.4621,"eval_samples_per_second":3.394,"eval_steps_per_second":0.441,"epoch":1.2961508248}
{"Step":1700,"eval_loss":1.8399604559,"eval_runtime":29.4709,"eval_samples_per_second":3.393,"eval_steps_per_second":0.441,"epoch":1.3354281225}
{"Step":1750,"eval_loss":1.8384497166,"eval_runtime":29.4803,"eval_samples_per_second":3.392,"eval_steps_per_second":0.441,"epoch":1.3747054203}
{"Step":1800,"eval_loss":1.8313938379,"eval_runtime":29.4965,"eval_samples_per_second":3.39,"eval_steps_per_second":0.441,"epoch":1.413982718}
{"Step":1850,"eval_loss":1.8278540373,"eval_runtime":29.4535,"eval_samples_per_second":3.395,"eval_steps_per_second":0.441,"epoch":1.4532600157}
{"Step":1900,"eval_loss":1.8285325766,"eval_runtime":29.5818,"eval_samples_per_second":3.38,"eval_steps_per_second":0.439,"epoch":1.4925373134}
{"Step":1950,"eval_loss":1.8242964745,"eval_runtime":29.4834,"eval_samples_per_second":3.392,"eval_steps_per_second":0.441,"epoch":1.5318146112}
{"Step":2000,"eval_loss":1.8210265636,"eval_runtime":29.5979,"eval_samples_per_second":3.379,"eval_steps_per_second":0.439,"epoch":1.5710919089}
{"Step":2050,"eval_loss":1.8052531481,"eval_runtime":29.6699,"eval_samples_per_second":3.37,"eval_steps_per_second":0.438,"epoch":1.6103692066}
{"Step":2100,"eval_loss":1.8001557589,"eval_runtime":29.4349,"eval_samples_per_second":3.397,"eval_steps_per_second":0.442,"epoch":1.6496465043}
{"Step":2150,"eval_loss":1.8008465767,"eval_runtime":29.3948,"eval_samples_per_second":3.402,"eval_steps_per_second":0.442,"epoch":1.688923802}
{"Step":2200,"eval_loss":1.7969157696,"eval_runtime":29.4741,"eval_samples_per_second":3.393,"eval_steps_per_second":0.441,"epoch":1.7282010998}
{"Step":2250,"eval_loss":1.7962598801,"eval_runtime":29.3661,"eval_samples_per_second":3.405,"eval_steps_per_second":0.443,"epoch":1.7674783975}
{"Step":2300,"eval_loss":1.7972977161,"eval_runtime":29.4909,"eval_samples_per_second":3.391,"eval_steps_per_second":0.441,"epoch":1.8067556952}
{"Step":2350,"eval_loss":1.7902172804,"eval_runtime":29.5667,"eval_samples_per_second":3.382,"eval_steps_per_second":0.44,"epoch":1.8460329929}
{"Step":2400,"eval_loss":1.7889854908,"eval_runtime":29.5198,"eval_samples_per_second":3.388,"eval_steps_per_second":0.44,"epoch":1.8853102907}
{"Step":2450,"eval_loss":1.7838914394,"eval_runtime":29.4874,"eval_samples_per_second":3.391,"eval_steps_per_second":0.441,"epoch":1.9245875884}
{"Step":2500,"eval_loss":1.7779937983,"eval_runtime":29.5562,"eval_samples_per_second":3.383,"eval_steps_per_second":0.44,"epoch":1.9638648861}
{"Step":2550,"eval_loss":1.7793732882,"eval_runtime":29.5808,"eval_samples_per_second":3.381,"eval_steps_per_second":0.439,"epoch":2.0031421838}
{"Step":2600,"eval_loss":1.7732738256,"eval_runtime":29.4165,"eval_samples_per_second":3.399,"eval_steps_per_second":0.442,"epoch":2.0424194815}
{"Step":2650,"eval_loss":1.7721085548,"eval_runtime":29.5171,"eval_samples_per_second":3.388,"eval_steps_per_second":0.44,"epoch":2.0816967793}
{"Step":2700,"eval_loss":1.7694271803,"eval_runtime":29.9036,"eval_samples_per_second":3.344,"eval_steps_per_second":0.435,"epoch":2.120974077}
{"Step":2750,"eval_loss":1.7644474506,"eval_runtime":29.5003,"eval_samples_per_second":3.39,"eval_steps_per_second":0.441,"epoch":2.1602513747}
{"Step":2800,"eval_loss":1.76300776,"eval_runtime":29.3837,"eval_samples_per_second":3.403,"eval_steps_per_second":0.442,"epoch":2.1995286724}
{"Step":2850,"eval_loss":1.760255456,"eval_runtime":29.4586,"eval_samples_per_second":3.395,"eval_steps_per_second":0.441,"epoch":2.2388059701}
{"Step":2900,"eval_loss":1.7579619884,"eval_runtime":29.3692,"eval_samples_per_second":3.405,"eval_steps_per_second":0.443,"epoch":2.2780832679}
{"Step":2950,"eval_loss":1.7549589872,"eval_runtime":29.4284,"eval_samples_per_second":3.398,"eval_steps_per_second":0.442,"epoch":2.3173605656}
{"Step":3000,"eval_loss":1.7528626919,"eval_runtime":29.4272,"eval_samples_per_second":3.398,"eval_steps_per_second":0.442,"epoch":2.3566378633}
{"Step":3050,"eval_loss":1.7513557673,"eval_runtime":29.577,"eval_samples_per_second":3.381,"eval_steps_per_second":0.44,"epoch":2.395915161}
{"Step":3100,"eval_loss":1.7509515285,"eval_runtime":29.3774,"eval_samples_per_second":3.404,"eval_steps_per_second":0.443,"epoch":2.4351924588}
{"Step":3150,"eval_loss":1.7521715164,"eval_runtime":29.4311,"eval_samples_per_second":3.398,"eval_steps_per_second":0.442,"epoch":2.4744697565}
{"Step":3200,"eval_loss":1.7496337891,"eval_runtime":29.4486,"eval_samples_per_second":3.396,"eval_steps_per_second":0.441,"epoch":2.5137470542}
{"Step":3250,"eval_loss":1.7441329956,"eval_runtime":29.3681,"eval_samples_per_second":3.405,"eval_steps_per_second":0.443,"epoch":2.5530243519}
{"Step":3300,"eval_loss":1.7436232567,"eval_runtime":29.5214,"eval_samples_per_second":3.387,"eval_steps_per_second":0.44,"epoch":2.5923016496}
{"Step":3350,"eval_loss":1.7433184385,"eval_runtime":29.6962,"eval_samples_per_second":3.367,"eval_steps_per_second":0.438,"epoch":2.6315789474}
{"Step":3400,"eval_loss":1.7429870367,"eval_runtime":29.4333,"eval_samples_per_second":3.398,"eval_steps_per_second":0.442,"epoch":2.6708562451}
{"Step":3450,"eval_loss":1.7402327061,"eval_runtime":29.6244,"eval_samples_per_second":3.376,"eval_steps_per_second":0.439,"epoch":2.7101335428}
{"Step":3500,"eval_loss":1.7408081293,"eval_runtime":29.3534,"eval_samples_per_second":3.407,"eval_steps_per_second":0.443,"epoch":2.7494108405}
{"Step":3550,"eval_loss":1.7384474277,"eval_runtime":29.4245,"eval_samples_per_second":3.399,"eval_steps_per_second":0.442,"epoch":2.7886881383}
{"Step":3600,"eval_loss":1.7396867275,"eval_runtime":29.4237,"eval_samples_per_second":3.399,"eval_steps_per_second":0.442,"epoch":2.827965436}
{"Step":3650,"eval_loss":1.74048388,"eval_runtime":29.3962,"eval_samples_per_second":3.402,"eval_steps_per_second":0.442,"epoch":2.8672427337}
{"Step":3700,"eval_loss":1.7404457331,"eval_runtime":29.4897,"eval_samples_per_second":3.391,"eval_steps_per_second":0.441,"epoch":2.9065200314}
{"Step":3750,"eval_loss":1.7380776405,"eval_runtime":29.4462,"eval_samples_per_second":3.396,"eval_steps_per_second":0.441,"epoch":2.9457973291}
{"Step":3800,"eval_loss":1.7374665737,"eval_runtime":29.4954,"eval_samples_per_second":3.39,"eval_steps_per_second":0.441,"epoch":2.9850746269}