avsolatorio/01-600-11-1-2-2-0-0-cls-normed-384-512_ASYM_BAAI_bge-small-en-v1.5-20240415163943-best
{"loss": 0.4083, "grad_norm": 7.204779624938965, "learning_rate": 8.280179334427121e-07, "epoch": 0.66, "step": 75500}
{"loss": 0.4168, "grad_norm": 13.862287521362305, "learning_rate": 6.580274967756653e-07, "epoch": 0.53, "step": 60000}
{"loss": 0.4329, "grad_norm": 15.365026473999023, "learning_rate": 5.922247470980988e-07, "epoch": 0.47, "step": 54000}
{"loss": 0.4479, "grad_norm": 15.81151008605957, "learning_rate": 5.757740596787072e-07, "epoch": 0.46, "step": 52500}
{"loss": 0.4615, "grad_norm": 0.5671650171279907, "learning_rate": 4.825534976354879e-07, "epoch": 0.39, "step": 44000}
{"loss": 0.4654, "grad_norm": 18.632034301757812, "learning_rate": 4.2771787290418245e-07, "epoch": 0.34, "step": 39000}
{"loss": 0.4881, "grad_norm": 23.602489471435547, "learning_rate": 4.1126718548479085e-07, "epoch": 0.33, "step": 37500}
{"loss": 0.5052, "grad_norm": 0.03971646726131439, "learning_rate": 3.1804662344157156e-07, "epoch": 0.25, "step": 29000}
{"loss": 0.5069, "grad_norm": 31.315715789794922, "learning_rate": 3.0707949849531046e-07, "epoch": 0.25, "step": 28000}
{"loss": 0.5485, "grad_norm": 4.49229621887207, "learning_rate": 2.6869456118339664e-07, "epoch": 0.21, "step": 24500}
{"loss": 0.5548, "grad_norm": 21.46637535095215, "learning_rate": 2.4127674881774393e-07, "epoch": 0.19, "step": 22000}
{"loss": 0.5623, "grad_norm": 23.116634368896484, "learning_rate": 2.1385893645209122e-07, "epoch": 0.17, "step": 19500}
{"loss": 0.6002, "grad_norm": 7.000210285186768, "learning_rate": 1.8095756161330794e-07, "epoch": 0.14, "step": 16500}
{"loss": 0.6176, "grad_norm": 32.07513427734375, "learning_rate": 1.5353974924765523e-07, "epoch": 0.12, "step": 14000}
{"loss": 0.6569, "grad_norm": 34.77505111694336, "learning_rate": 4.386849978504436e-08, "epoch": 0.04, "step": 4000}
{"loss": 0.7505, "grad_norm": 7.666896820068359, "learning_rate": 2.193424989252218e-08, "epoch": 0.02, "step": 2000}
{"loss": 0.7749, "grad_norm": 32.035709381103516, "learning_rate": 1.096712494626109e-08, "epoch": 0.01, "step": 1000}
{"loss": 0.987, "grad_norm": 57.99082946777344, "learning_rate": 5.483562473130545e-09, "epoch": 0.0, "step": 500}
initial commit
