| { | |
| "best_metric": 0.16174831986427307, | |
| "best_model_checkpoint": "checkpoints_commonvoice/checkpoint-543873", | |
| "epoch": 54.0, | |
| "global_step": 889974, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 1.9984922031430132e-05, | |
| "loss": 2.3359, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 1.996975304896548e-05, | |
| "loss": 1.5264, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 1.995458406650082e-05, | |
| "loss": 1.3191, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 1.9939415084036163e-05, | |
| "loss": 1.1985, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 1.9924246101571506e-05, | |
| "loss": 1.098, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 1.9909077119106852e-05, | |
| "loss": 1.0314, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 1.9893908136642194e-05, | |
| "loss": 0.9714, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 1.987873915417754e-05, | |
| "loss": 0.9334, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 1.9863570171712883e-05, | |
| "loss": 0.8831, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 1.984840118924823e-05, | |
| "loss": 0.8505, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 1.983323220678357e-05, | |
| "loss": 0.8127, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 1.9818063224318917e-05, | |
| "loss": 0.786, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 1.980289424185426e-05, | |
| "loss": 0.7604, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 1.9787725259389602e-05, | |
| "loss": 0.7358, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 1.9772556276924944e-05, | |
| "loss": 0.7159, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 1.9757387294460287e-05, | |
| "loss": 0.6955, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 1.9742218311995633e-05, | |
| "loss": 0.6626, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 1.9727049329530975e-05, | |
| "loss": 0.6589, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 1.971188034706632e-05, | |
| "loss": 0.6474, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 1.9696711364601664e-05, | |
| "loss": 0.6252, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 1.9681572720101938e-05, | |
| "loss": 0.6126, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 1.966640373763728e-05, | |
| "loss": 0.6078, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 1.9651234755172626e-05, | |
| "loss": 0.5942, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 1.9636096110672897e-05, | |
| "loss": 0.5797, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 1.962092712820824e-05, | |
| "loss": 0.5718, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 1.9605758145743585e-05, | |
| "loss": 0.5652, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 1.9590589163278928e-05, | |
| "loss": 0.5503, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 1.9575450518779202e-05, | |
| "loss": 0.5468, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 1.9560311874279473e-05, | |
| "loss": 0.5312, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 1.954514289181482e-05, | |
| "loss": 0.5217, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 1.952997390935016e-05, | |
| "loss": 0.5175, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 1.9514804926885507e-05, | |
| "loss": 0.5108, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_bleu": 69.1957, | |
| "eval_gen_len": 13.9687, | |
| "eval_loss": 0.39875420928001404, | |
| "eval_runtime": 174.0832, | |
| "eval_samples_per_second": 92.622, | |
| "eval_steps_per_second": 2.895, | |
| "step": 16481 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 1.949963594442085e-05, | |
| "loss": 0.5057, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 1.9484466961956195e-05, | |
| "loss": 0.4922, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 1.9469297979491538e-05, | |
| "loss": 0.4873, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 1.945412899702688e-05, | |
| "loss": 0.485, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 1.9438960014562226e-05, | |
| "loss": 0.4729, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 1.942379103209757e-05, | |
| "loss": 0.4682, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 1.940862204963291e-05, | |
| "loss": 0.456, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 1.9393453067168254e-05, | |
| "loss": 0.4587, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 1.9378314422668528e-05, | |
| "loss": 0.4527, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 1.936314544020387e-05, | |
| "loss": 0.4474, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 1.9348006795704145e-05, | |
| "loss": 0.4398, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 1.933283781323949e-05, | |
| "loss": 0.4378, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 1.9317668830774833e-05, | |
| "loss": 0.4355, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 1.9302530186275107e-05, | |
| "loss": 0.4331, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 1.928736120381045e-05, | |
| "loss": 0.4294, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 1.9272192221345792e-05, | |
| "loss": 0.4286, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 1.9257023238881138e-05, | |
| "loss": 0.4174, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 1.924185425641648e-05, | |
| "loss": 0.4158, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 1.9226685273951823e-05, | |
| "loss": 0.4142, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 1.921151629148717e-05, | |
| "loss": 0.4067, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 1.919634730902251e-05, | |
| "loss": 0.4071, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 1.9181178326557857e-05, | |
| "loss": 0.4024, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 1.91660093440932e-05, | |
| "loss": 0.3952, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 1.9150840361628546e-05, | |
| "loss": 0.3987, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 1.9135671379163888e-05, | |
| "loss": 0.3952, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 1.912056307262909e-05, | |
| "loss": 0.3901, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 1.9105394090164433e-05, | |
| "loss": 0.3846, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 1.909022510769978e-05, | |
| "loss": 0.384, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 1.907505612523512e-05, | |
| "loss": 0.3851, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 1.9059887142770464e-05, | |
| "loss": 0.3849, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 1.904471816030581e-05, | |
| "loss": 0.3804, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 1.9029549177841152e-05, | |
| "loss": 0.3719, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 1.9014380195376495e-05, | |
| "loss": 0.3739, | |
| "step": 32500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_bleu": 74.3843, | |
| "eval_gen_len": 13.9751, | |
| "eval_loss": 0.3009156882762909, | |
| "eval_runtime": 172.1504, | |
| "eval_samples_per_second": 93.662, | |
| "eval_steps_per_second": 2.928, | |
| "step": 32962 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 1.8999211212911837e-05, | |
| "loss": 0.3771, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 1.8984042230447183e-05, | |
| "loss": 0.3596, | |
| "step": 33500 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 1.8968873247982526e-05, | |
| "loss": 0.3572, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 1.8953704265517872e-05, | |
| "loss": 0.357, | |
| "step": 34500 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 1.8938595958983074e-05, | |
| "loss": 0.3532, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 1.8923426976518417e-05, | |
| "loss": 0.3548, | |
| "step": 35500 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 1.890825799405376e-05, | |
| "loss": 0.3508, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 1.8893119349554033e-05, | |
| "loss": 0.3457, | |
| "step": 36500 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 1.8877950367089376e-05, | |
| "loss": 0.3467, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 1.886278138462472e-05, | |
| "loss": 0.3457, | |
| "step": 37500 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 1.8847612402160064e-05, | |
| "loss": 0.3488, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 1.8832443419695407e-05, | |
| "loss": 0.3419, | |
| "step": 38500 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 1.8817274437230753e-05, | |
| "loss": 0.344, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 1.8802135792731023e-05, | |
| "loss": 0.3382, | |
| "step": 39500 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 1.878696681026637e-05, | |
| "loss": 0.3381, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 1.8771797827801712e-05, | |
| "loss": 0.3378, | |
| "step": 40500 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 1.8756628845337058e-05, | |
| "loss": 0.337, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 1.8741520538802257e-05, | |
| "loss": 0.3354, | |
| "step": 41500 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 1.8726351556337603e-05, | |
| "loss": 0.3339, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 1.8711212911837874e-05, | |
| "loss": 0.3324, | |
| "step": 42500 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 1.869604392937322e-05, | |
| "loss": 0.3233, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 1.8680874946908562e-05, | |
| "loss": 0.3307, | |
| "step": 43500 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 1.8665736302408836e-05, | |
| "loss": 0.3245, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 1.865056731994418e-05, | |
| "loss": 0.3249, | |
| "step": 44500 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 1.8635398337479525e-05, | |
| "loss": 0.3181, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 1.8620229355014867e-05, | |
| "loss": 0.3238, | |
| "step": 45500 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 1.860506037255021e-05, | |
| "loss": 0.3256, | |
| "step": 46000 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "learning_rate": 1.8589891390085555e-05, | |
| "loss": 0.3203, | |
| "step": 46500 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 1.8574722407620898e-05, | |
| "loss": 0.3174, | |
| "step": 47000 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 1.8559553425156244e-05, | |
| "loss": 0.3185, | |
| "step": 47500 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 1.8544384442691586e-05, | |
| "loss": 0.3181, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 1.852921546022693e-05, | |
| "loss": 0.3172, | |
| "step": 48500 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 1.8514046477762275e-05, | |
| "loss": 0.3179, | |
| "step": 49000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_bleu": 76.4066, | |
| "eval_gen_len": 13.9632, | |
| "eval_loss": 0.26052698493003845, | |
| "eval_runtime": 171.9366, | |
| "eval_samples_per_second": 93.779, | |
| "eval_steps_per_second": 2.931, | |
| "step": 49443 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 1.8498877495297617e-05, | |
| "loss": 0.3118, | |
| "step": 49500 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "learning_rate": 1.848370851283296e-05, | |
| "loss": 0.2996, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 3.06, | |
| "learning_rate": 1.8468539530368302e-05, | |
| "loss": 0.3008, | |
| "step": 50500 | |
| }, | |
| { | |
| "epoch": 3.09, | |
| "learning_rate": 1.8453370547903648e-05, | |
| "loss": 0.3075, | |
| "step": 51000 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "learning_rate": 1.843820156543899e-05, | |
| "loss": 0.2995, | |
| "step": 51500 | |
| }, | |
| { | |
| "epoch": 3.16, | |
| "learning_rate": 1.8423032582974336e-05, | |
| "loss": 0.2985, | |
| "step": 52000 | |
| }, | |
| { | |
| "epoch": 3.19, | |
| "learning_rate": 1.840786360050968e-05, | |
| "loss": 0.2996, | |
| "step": 52500 | |
| }, | |
| { | |
| "epoch": 3.22, | |
| "learning_rate": 1.8392694618045025e-05, | |
| "loss": 0.2993, | |
| "step": 53000 | |
| }, | |
| { | |
| "epoch": 3.25, | |
| "learning_rate": 1.8377525635580367e-05, | |
| "loss": 0.3027, | |
| "step": 53500 | |
| }, | |
| { | |
| "epoch": 3.28, | |
| "learning_rate": 1.8362356653115713e-05, | |
| "loss": 0.2922, | |
| "step": 54000 | |
| }, | |
| { | |
| "epoch": 3.31, | |
| "learning_rate": 1.8347187670651056e-05, | |
| "loss": 0.2934, | |
| "step": 54500 | |
| }, | |
| { | |
| "epoch": 3.34, | |
| "learning_rate": 1.8332018688186398e-05, | |
| "loss": 0.297, | |
| "step": 55000 | |
| }, | |
| { | |
| "epoch": 3.37, | |
| "learning_rate": 1.8316880043686672e-05, | |
| "loss": 0.2923, | |
| "step": 55500 | |
| }, | |
| { | |
| "epoch": 3.4, | |
| "learning_rate": 1.8301741399186943e-05, | |
| "loss": 0.2942, | |
| "step": 56000 | |
| }, | |
| { | |
| "epoch": 3.43, | |
| "learning_rate": 1.828657241672229e-05, | |
| "loss": 0.2946, | |
| "step": 56500 | |
| }, | |
| { | |
| "epoch": 3.46, | |
| "learning_rate": 1.827140343425763e-05, | |
| "loss": 0.2859, | |
| "step": 57000 | |
| }, | |
| { | |
| "epoch": 3.49, | |
| "learning_rate": 1.8256234451792977e-05, | |
| "loss": 0.2873, | |
| "step": 57500 | |
| }, | |
| { | |
| "epoch": 3.52, | |
| "learning_rate": 1.824106546932832e-05, | |
| "loss": 0.2934, | |
| "step": 58000 | |
| }, | |
| { | |
| "epoch": 3.55, | |
| "learning_rate": 1.8225896486863662e-05, | |
| "loss": 0.2912, | |
| "step": 58500 | |
| }, | |
| { | |
| "epoch": 3.58, | |
| "learning_rate": 1.8210727504399005e-05, | |
| "loss": 0.2886, | |
| "step": 59000 | |
| }, | |
| { | |
| "epoch": 3.61, | |
| "learning_rate": 1.819555852193435e-05, | |
| "loss": 0.2859, | |
| "step": 59500 | |
| }, | |
| { | |
| "epoch": 3.64, | |
| "learning_rate": 1.8180389539469693e-05, | |
| "loss": 0.2891, | |
| "step": 60000 | |
| }, | |
| { | |
| "epoch": 3.67, | |
| "learning_rate": 1.8165220557005036e-05, | |
| "loss": 0.2834, | |
| "step": 60500 | |
| }, | |
| { | |
| "epoch": 3.7, | |
| "learning_rate": 1.815005157454038e-05, | |
| "loss": 0.2842, | |
| "step": 61000 | |
| }, | |
| { | |
| "epoch": 3.73, | |
| "learning_rate": 1.8134882592075724e-05, | |
| "loss": 0.2812, | |
| "step": 61500 | |
| }, | |
| { | |
| "epoch": 3.76, | |
| "learning_rate": 1.8119743947575998e-05, | |
| "loss": 0.2834, | |
| "step": 62000 | |
| }, | |
| { | |
| "epoch": 3.79, | |
| "learning_rate": 1.810457496511134e-05, | |
| "loss": 0.286, | |
| "step": 62500 | |
| }, | |
| { | |
| "epoch": 3.82, | |
| "learning_rate": 1.8089405982646687e-05, | |
| "loss": 0.2779, | |
| "step": 63000 | |
| }, | |
| { | |
| "epoch": 3.85, | |
| "learning_rate": 1.807423700018203e-05, | |
| "loss": 0.2847, | |
| "step": 63500 | |
| }, | |
| { | |
| "epoch": 3.88, | |
| "learning_rate": 1.8059068017717375e-05, | |
| "loss": 0.2834, | |
| "step": 64000 | |
| }, | |
| { | |
| "epoch": 3.91, | |
| "learning_rate": 1.8043929373217646e-05, | |
| "loss": 0.2792, | |
| "step": 64500 | |
| }, | |
| { | |
| "epoch": 3.94, | |
| "learning_rate": 1.802879072871792e-05, | |
| "loss": 0.2834, | |
| "step": 65000 | |
| }, | |
| { | |
| "epoch": 3.97, | |
| "learning_rate": 1.8013621746253263e-05, | |
| "loss": 0.2795, | |
| "step": 65500 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_bleu": 77.5034, | |
| "eval_gen_len": 14.0025, | |
| "eval_loss": 0.23620256781578064, | |
| "eval_runtime": 168.2, | |
| "eval_samples_per_second": 95.862, | |
| "eval_steps_per_second": 2.996, | |
| "step": 65924 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 1.799845276378861e-05, | |
| "loss": 0.2778, | |
| "step": 66000 | |
| }, | |
| { | |
| "epoch": 4.03, | |
| "learning_rate": 1.798328378132395e-05, | |
| "loss": 0.2714, | |
| "step": 66500 | |
| }, | |
| { | |
| "epoch": 4.07, | |
| "learning_rate": 1.7968145136824225e-05, | |
| "loss": 0.2727, | |
| "step": 67000 | |
| }, | |
| { | |
| "epoch": 4.1, | |
| "learning_rate": 1.7952976154359568e-05, | |
| "loss": 0.2677, | |
| "step": 67500 | |
| }, | |
| { | |
| "epoch": 4.13, | |
| "learning_rate": 1.793780717189491e-05, | |
| "loss": 0.2651, | |
| "step": 68000 | |
| }, | |
| { | |
| "epoch": 4.16, | |
| "learning_rate": 1.7922638189430256e-05, | |
| "loss": 0.2666, | |
| "step": 68500 | |
| }, | |
| { | |
| "epoch": 4.19, | |
| "learning_rate": 1.79074692069656e-05, | |
| "loss": 0.2655, | |
| "step": 69000 | |
| }, | |
| { | |
| "epoch": 4.22, | |
| "learning_rate": 1.789230022450094e-05, | |
| "loss": 0.2649, | |
| "step": 69500 | |
| }, | |
| { | |
| "epoch": 4.25, | |
| "learning_rate": 1.7877131242036287e-05, | |
| "loss": 0.2613, | |
| "step": 70000 | |
| }, | |
| { | |
| "epoch": 4.28, | |
| "learning_rate": 1.786196225957163e-05, | |
| "loss": 0.2708, | |
| "step": 70500 | |
| }, | |
| { | |
| "epoch": 4.31, | |
| "learning_rate": 1.7846823615071904e-05, | |
| "loss": 0.266, | |
| "step": 71000 | |
| }, | |
| { | |
| "epoch": 4.34, | |
| "learning_rate": 1.7831654632607246e-05, | |
| "loss": 0.2631, | |
| "step": 71500 | |
| }, | |
| { | |
| "epoch": 4.37, | |
| "learning_rate": 1.781648565014259e-05, | |
| "loss": 0.262, | |
| "step": 72000 | |
| }, | |
| { | |
| "epoch": 4.4, | |
| "learning_rate": 1.780131666767793e-05, | |
| "loss": 0.2614, | |
| "step": 72500 | |
| }, | |
| { | |
| "epoch": 4.43, | |
| "learning_rate": 1.7786147685213277e-05, | |
| "loss": 0.2607, | |
| "step": 73000 | |
| }, | |
| { | |
| "epoch": 4.46, | |
| "learning_rate": 1.7771009040713548e-05, | |
| "loss": 0.2646, | |
| "step": 73500 | |
| }, | |
| { | |
| "epoch": 4.49, | |
| "learning_rate": 1.7755840058248894e-05, | |
| "loss": 0.2619, | |
| "step": 74000 | |
| }, | |
| { | |
| "epoch": 4.52, | |
| "learning_rate": 1.7740731751714096e-05, | |
| "loss": 0.2572, | |
| "step": 74500 | |
| }, | |
| { | |
| "epoch": 4.55, | |
| "learning_rate": 1.772559310721437e-05, | |
| "loss": 0.2618, | |
| "step": 75000 | |
| }, | |
| { | |
| "epoch": 4.58, | |
| "learning_rate": 1.7710424124749713e-05, | |
| "loss": 0.2596, | |
| "step": 75500 | |
| }, | |
| { | |
| "epoch": 4.61, | |
| "learning_rate": 1.769525514228506e-05, | |
| "loss": 0.2612, | |
| "step": 76000 | |
| }, | |
| { | |
| "epoch": 4.64, | |
| "learning_rate": 1.76800861598204e-05, | |
| "loss": 0.2555, | |
| "step": 76500 | |
| }, | |
| { | |
| "epoch": 4.67, | |
| "learning_rate": 1.7664917177355744e-05, | |
| "loss": 0.2597, | |
| "step": 77000 | |
| }, | |
| { | |
| "epoch": 4.7, | |
| "learning_rate": 1.7649748194891086e-05, | |
| "loss": 0.2563, | |
| "step": 77500 | |
| }, | |
| { | |
| "epoch": 4.73, | |
| "learning_rate": 1.7634579212426432e-05, | |
| "loss": 0.2587, | |
| "step": 78000 | |
| }, | |
| { | |
| "epoch": 4.76, | |
| "learning_rate": 1.7619440567926703e-05, | |
| "loss": 0.2564, | |
| "step": 78500 | |
| }, | |
| { | |
| "epoch": 4.79, | |
| "learning_rate": 1.760427158546205e-05, | |
| "loss": 0.2589, | |
| "step": 79000 | |
| }, | |
| { | |
| "epoch": 4.82, | |
| "learning_rate": 1.758910260299739e-05, | |
| "loss": 0.2564, | |
| "step": 79500 | |
| }, | |
| { | |
| "epoch": 4.85, | |
| "learning_rate": 1.7573933620532737e-05, | |
| "loss": 0.2586, | |
| "step": 80000 | |
| }, | |
| { | |
| "epoch": 4.88, | |
| "learning_rate": 1.755876463806808e-05, | |
| "loss": 0.2519, | |
| "step": 80500 | |
| }, | |
| { | |
| "epoch": 4.91, | |
| "learning_rate": 1.7543595655603422e-05, | |
| "loss": 0.2539, | |
| "step": 81000 | |
| }, | |
| { | |
| "epoch": 4.95, | |
| "learning_rate": 1.7528426673138768e-05, | |
| "loss": 0.2547, | |
| "step": 81500 | |
| }, | |
| { | |
| "epoch": 4.98, | |
| "learning_rate": 1.751325769067411e-05, | |
| "loss": 0.2543, | |
| "step": 82000 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_bleu": 78.2577, | |
| "eval_gen_len": 14.0135, | |
| "eval_loss": 0.21999071538448334, | |
| "eval_runtime": 172.5496, | |
| "eval_samples_per_second": 93.446, | |
| "eval_steps_per_second": 2.921, | |
| "step": 82405 | |
| }, | |
| { | |
| "epoch": 5.01, | |
| "learning_rate": 1.7498088708209456e-05, | |
| "loss": 0.2506, | |
| "step": 82500 | |
| }, | |
| { | |
| "epoch": 5.04, | |
| "learning_rate": 1.74829197257448e-05, | |
| "loss": 0.2437, | |
| "step": 83000 | |
| }, | |
| { | |
| "epoch": 5.07, | |
| "learning_rate": 1.746775074328014e-05, | |
| "loss": 0.2438, | |
| "step": 83500 | |
| }, | |
| { | |
| "epoch": 5.1, | |
| "learning_rate": 1.7452581760815487e-05, | |
| "loss": 0.2487, | |
| "step": 84000 | |
| }, | |
| { | |
| "epoch": 5.13, | |
| "learning_rate": 1.743741277835083e-05, | |
| "loss": 0.2456, | |
| "step": 84500 | |
| }, | |
| { | |
| "epoch": 5.16, | |
| "learning_rate": 1.7422274133851104e-05, | |
| "loss": 0.2423, | |
| "step": 85000 | |
| }, | |
| { | |
| "epoch": 5.19, | |
| "learning_rate": 1.7407105151386446e-05, | |
| "loss": 0.2457, | |
| "step": 85500 | |
| }, | |
| { | |
| "epoch": 5.22, | |
| "learning_rate": 1.739193616892179e-05, | |
| "loss": 0.2449, | |
| "step": 86000 | |
| }, | |
| { | |
| "epoch": 5.25, | |
| "learning_rate": 1.737676718645713e-05, | |
| "loss": 0.2429, | |
| "step": 86500 | |
| }, | |
| { | |
| "epoch": 5.28, | |
| "learning_rate": 1.7361598203992477e-05, | |
| "loss": 0.2453, | |
| "step": 87000 | |
| }, | |
| { | |
| "epoch": 5.31, | |
| "learning_rate": 1.734642922152782e-05, | |
| "loss": 0.2453, | |
| "step": 87500 | |
| }, | |
| { | |
| "epoch": 5.34, | |
| "learning_rate": 1.7331290577028094e-05, | |
| "loss": 0.247, | |
| "step": 88000 | |
| }, | |
| { | |
| "epoch": 5.37, | |
| "learning_rate": 1.7316121594563436e-05, | |
| "loss": 0.2429, | |
| "step": 88500 | |
| }, | |
| { | |
| "epoch": 5.4, | |
| "learning_rate": 1.7300952612098782e-05, | |
| "loss": 0.2361, | |
| "step": 89000 | |
| }, | |
| { | |
| "epoch": 5.43, | |
| "learning_rate": 1.7285783629634125e-05, | |
| "loss": 0.2405, | |
| "step": 89500 | |
| }, | |
| { | |
| "epoch": 5.46, | |
| "learning_rate": 1.727061464716947e-05, | |
| "loss": 0.2454, | |
| "step": 90000 | |
| }, | |
| { | |
| "epoch": 5.49, | |
| "learning_rate": 1.7255445664704813e-05, | |
| "loss": 0.2409, | |
| "step": 90500 | |
| }, | |
| { | |
| "epoch": 5.52, | |
| "learning_rate": 1.7240276682240156e-05, | |
| "loss": 0.2417, | |
| "step": 91000 | |
| }, | |
| { | |
| "epoch": 5.55, | |
| "learning_rate": 1.72251076997755e-05, | |
| "loss": 0.24, | |
| "step": 91500 | |
| }, | |
| { | |
| "epoch": 5.58, | |
| "learning_rate": 1.7209969055275772e-05, | |
| "loss": 0.2356, | |
| "step": 92000 | |
| }, | |
| { | |
| "epoch": 5.61, | |
| "learning_rate": 1.7194800072811118e-05, | |
| "loss": 0.2387, | |
| "step": 92500 | |
| }, | |
| { | |
| "epoch": 5.64, | |
| "learning_rate": 1.717963109034646e-05, | |
| "loss": 0.2354, | |
| "step": 93000 | |
| }, | |
| { | |
| "epoch": 5.67, | |
| "learning_rate": 1.7164462107881807e-05, | |
| "loss": 0.2392, | |
| "step": 93500 | |
| }, | |
| { | |
| "epoch": 5.7, | |
| "learning_rate": 1.714929312541715e-05, | |
| "loss": 0.2404, | |
| "step": 94000 | |
| }, | |
| { | |
| "epoch": 5.73, | |
| "learning_rate": 1.7134154480917423e-05, | |
| "loss": 0.2354, | |
| "step": 94500 | |
| }, | |
| { | |
| "epoch": 5.76, | |
| "learning_rate": 1.7118985498452766e-05, | |
| "loss": 0.2372, | |
| "step": 95000 | |
| }, | |
| { | |
| "epoch": 5.79, | |
| "learning_rate": 1.710381651598811e-05, | |
| "loss": 0.2343, | |
| "step": 95500 | |
| }, | |
| { | |
| "epoch": 5.82, | |
| "learning_rate": 1.7088647533523454e-05, | |
| "loss": 0.2383, | |
| "step": 96000 | |
| }, | |
| { | |
| "epoch": 5.86, | |
| "learning_rate": 1.7073508889023725e-05, | |
| "loss": 0.2363, | |
| "step": 96500 | |
| }, | |
| { | |
| "epoch": 5.89, | |
| "learning_rate": 1.7058370244524e-05, | |
| "loss": 0.2352, | |
| "step": 97000 | |
| }, | |
| { | |
| "epoch": 5.92, | |
| "learning_rate": 1.7043201262059345e-05, | |
| "loss": 0.2367, | |
| "step": 97500 | |
| }, | |
| { | |
| "epoch": 5.95, | |
| "learning_rate": 1.7028032279594688e-05, | |
| "loss": 0.2327, | |
| "step": 98000 | |
| }, | |
| { | |
| "epoch": 5.98, | |
| "learning_rate": 1.7012893635094962e-05, | |
| "loss": 0.2341, | |
| "step": 98500 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_bleu": 78.7501, | |
| "eval_gen_len": 14.013, | |
| "eval_loss": 0.2089208960533142, | |
| "eval_runtime": 172.3801, | |
| "eval_samples_per_second": 93.537, | |
| "eval_steps_per_second": 2.924, | |
| "step": 98886 | |
| }, | |
| { | |
| "epoch": 6.01, | |
| "learning_rate": 1.6997724652630304e-05, | |
| "loss": 0.2272, | |
| "step": 99000 | |
| }, | |
| { | |
| "epoch": 6.04, | |
| "learning_rate": 1.6982555670165647e-05, | |
| "loss": 0.2315, | |
| "step": 99500 | |
| }, | |
| { | |
| "epoch": 6.07, | |
| "learning_rate": 1.696738668770099e-05, | |
| "loss": 0.2238, | |
| "step": 100000 | |
| }, | |
| { | |
| "epoch": 6.1, | |
| "learning_rate": 1.6952217705236335e-05, | |
| "loss": 0.2268, | |
| "step": 100500 | |
| }, | |
| { | |
| "epoch": 6.13, | |
| "learning_rate": 1.6937048722771678e-05, | |
| "loss": 0.2264, | |
| "step": 101000 | |
| }, | |
| { | |
| "epoch": 6.16, | |
| "learning_rate": 1.692187974030702e-05, | |
| "loss": 0.2255, | |
| "step": 101500 | |
| }, | |
| { | |
| "epoch": 6.19, | |
| "learning_rate": 1.6906710757842366e-05, | |
| "loss": 0.2262, | |
| "step": 102000 | |
| }, | |
| { | |
| "epoch": 6.22, | |
| "learning_rate": 1.689154177537771e-05, | |
| "loss": 0.2279, | |
| "step": 102500 | |
| }, | |
| { | |
| "epoch": 6.25, | |
| "learning_rate": 1.6876372792913054e-05, | |
| "loss": 0.2279, | |
| "step": 103000 | |
| }, | |
| { | |
| "epoch": 6.28, | |
| "learning_rate": 1.6861203810448397e-05, | |
| "loss": 0.2272, | |
| "step": 103500 | |
| }, | |
| { | |
| "epoch": 6.31, | |
| "learning_rate": 1.684603482798374e-05, | |
| "loss": 0.2235, | |
| "step": 104000 | |
| }, | |
| { | |
| "epoch": 6.34, | |
| "learning_rate": 1.6830896183484014e-05, | |
| "loss": 0.227, | |
| "step": 104500 | |
| }, | |
| { | |
| "epoch": 6.37, | |
| "learning_rate": 1.6815727201019356e-05, | |
| "loss": 0.2232, | |
| "step": 105000 | |
| }, | |
| { | |
| "epoch": 6.4, | |
| "learning_rate": 1.6800558218554702e-05, | |
| "loss": 0.2255, | |
| "step": 105500 | |
| }, | |
| { | |
| "epoch": 6.43, | |
| "learning_rate": 1.6785389236090044e-05, | |
| "loss": 0.2255, | |
| "step": 106000 | |
| }, | |
| { | |
| "epoch": 6.46, | |
| "learning_rate": 1.6770280929555247e-05, | |
| "loss": 0.2282, | |
| "step": 106500 | |
| }, | |
| { | |
| "epoch": 6.49, | |
| "learning_rate": 1.675511194709059e-05, | |
| "loss": 0.2219, | |
| "step": 107000 | |
| }, | |
| { | |
| "epoch": 6.52, | |
| "learning_rate": 1.6739942964625935e-05, | |
| "loss": 0.2246, | |
| "step": 107500 | |
| }, | |
| { | |
| "epoch": 6.55, | |
| "learning_rate": 1.6724773982161278e-05, | |
| "loss": 0.2238, | |
| "step": 108000 | |
| }, | |
| { | |
| "epoch": 6.58, | |
| "learning_rate": 1.6709604999696624e-05, | |
| "loss": 0.2246, | |
| "step": 108500 | |
| }, | |
| { | |
| "epoch": 6.61, | |
| "learning_rate": 1.6694466355196895e-05, | |
| "loss": 0.2237, | |
| "step": 109000 | |
| }, | |
| { | |
| "epoch": 6.64, | |
| "learning_rate": 1.667929737273224e-05, | |
| "loss": 0.2241, | |
| "step": 109500 | |
| }, | |
| { | |
| "epoch": 6.67, | |
| "learning_rate": 1.666415872823251e-05, | |
| "loss": 0.2259, | |
| "step": 110000 | |
| }, | |
| { | |
| "epoch": 6.7, | |
| "learning_rate": 1.6648989745767857e-05, | |
| "loss": 0.2225, | |
| "step": 110500 | |
| }, | |
| { | |
| "epoch": 6.74, | |
| "learning_rate": 1.66338207633032e-05, | |
| "loss": 0.2229, | |
| "step": 111000 | |
| }, | |
| { | |
| "epoch": 6.77, | |
| "learning_rate": 1.6618651780838542e-05, | |
| "loss": 0.2234, | |
| "step": 111500 | |
| }, | |
| { | |
| "epoch": 6.8, | |
| "learning_rate": 1.6603482798373888e-05, | |
| "loss": 0.2211, | |
| "step": 112000 | |
| }, | |
| { | |
| "epoch": 6.83, | |
| "learning_rate": 1.658831381590923e-05, | |
| "loss": 0.2203, | |
| "step": 112500 | |
| }, | |
| { | |
| "epoch": 6.86, | |
| "learning_rate": 1.6573144833444573e-05, | |
| "loss": 0.2195, | |
| "step": 113000 | |
| }, | |
| { | |
| "epoch": 6.89, | |
| "learning_rate": 1.6557975850979915e-05, | |
| "loss": 0.2219, | |
| "step": 113500 | |
| }, | |
| { | |
| "epoch": 6.92, | |
| "learning_rate": 1.654280686851526e-05, | |
| "loss": 0.22, | |
| "step": 114000 | |
| }, | |
| { | |
| "epoch": 6.95, | |
| "learning_rate": 1.6527668224015536e-05, | |
| "loss": 0.2217, | |
| "step": 114500 | |
| }, | |
| { | |
| "epoch": 6.98, | |
| "learning_rate": 1.6512499241550878e-05, | |
| "loss": 0.2182, | |
| "step": 115000 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_bleu": 79.0915, | |
| "eval_gen_len": 14.0505, | |
| "eval_loss": 0.1989297866821289, | |
| "eval_runtime": 170.8481, | |
| "eval_samples_per_second": 94.376, | |
| "eval_steps_per_second": 2.95, | |
| "step": 115367 | |
| }, | |
| { | |
| "epoch": 7.01, | |
| "learning_rate": 1.649733025908622e-05, | |
| "loss": 0.2219, | |
| "step": 115500 | |
| }, | |
| { | |
| "epoch": 7.04, | |
| "learning_rate": 1.6482161276621566e-05, | |
| "loss": 0.2165, | |
| "step": 116000 | |
| }, | |
| { | |
| "epoch": 7.07, | |
| "learning_rate": 1.6467022632121837e-05, | |
| "loss": 0.214, | |
| "step": 116500 | |
| }, | |
| { | |
| "epoch": 7.1, | |
| "learning_rate": 1.645185364965718e-05, | |
| "loss": 0.2143, | |
| "step": 117000 | |
| }, | |
| { | |
| "epoch": 7.13, | |
| "learning_rate": 1.6436684667192526e-05, | |
| "loss": 0.2193, | |
| "step": 117500 | |
| }, | |
| { | |
| "epoch": 7.16, | |
| "learning_rate": 1.6421515684727868e-05, | |
| "loss": 0.2139, | |
| "step": 118000 | |
| }, | |
| { | |
| "epoch": 7.19, | |
| "learning_rate": 1.6406346702263214e-05, | |
| "loss": 0.2176, | |
| "step": 118500 | |
| }, | |
| { | |
| "epoch": 7.22, | |
| "learning_rate": 1.6391177719798556e-05, | |
| "loss": 0.2162, | |
| "step": 119000 | |
| }, | |
| { | |
| "epoch": 7.25, | |
| "learning_rate": 1.6376008737333902e-05, | |
| "loss": 0.2114, | |
| "step": 119500 | |
| }, | |
| { | |
| "epoch": 7.28, | |
| "learning_rate": 1.6360839754869245e-05, | |
| "loss": 0.2172, | |
| "step": 120000 | |
| }, | |
| { | |
| "epoch": 7.31, | |
| "learning_rate": 1.634567077240459e-05, | |
| "loss": 0.2127, | |
| "step": 120500 | |
| }, | |
| { | |
| "epoch": 7.34, | |
| "learning_rate": 1.6330501789939933e-05, | |
| "loss": 0.2134, | |
| "step": 121000 | |
| }, | |
| { | |
| "epoch": 7.37, | |
| "learning_rate": 1.6315332807475276e-05, | |
| "loss": 0.2131, | |
| "step": 121500 | |
| }, | |
| { | |
| "epoch": 7.4, | |
| "learning_rate": 1.6300163825010618e-05, | |
| "loss": 0.2072, | |
| "step": 122000 | |
| }, | |
| { | |
| "epoch": 7.43, | |
| "learning_rate": 1.6284994842545964e-05, | |
| "loss": 0.2125, | |
| "step": 122500 | |
| }, | |
| { | |
| "epoch": 7.46, | |
| "learning_rate": 1.6269856198046238e-05, | |
| "loss": 0.2117, | |
| "step": 123000 | |
| }, | |
| { | |
| "epoch": 7.49, | |
| "learning_rate": 1.625468721558158e-05, | |
| "loss": 0.21, | |
| "step": 123500 | |
| }, | |
| { | |
| "epoch": 7.52, | |
| "learning_rate": 1.6239518233116923e-05, | |
| "loss": 0.2144, | |
| "step": 124000 | |
| }, | |
| { | |
| "epoch": 7.55, | |
| "learning_rate": 1.6224379588617197e-05, | |
| "loss": 0.2103, | |
| "step": 124500 | |
| }, | |
| { | |
| "epoch": 7.58, | |
| "learning_rate": 1.620921060615254e-05, | |
| "loss": 0.2081, | |
| "step": 125000 | |
| }, | |
| { | |
| "epoch": 7.61, | |
| "learning_rate": 1.6194071961652814e-05, | |
| "loss": 0.2102, | |
| "step": 125500 | |
| }, | |
| { | |
| "epoch": 7.65, | |
| "learning_rate": 1.6178902979188157e-05, | |
| "loss": 0.2059, | |
| "step": 126000 | |
| }, | |
| { | |
| "epoch": 7.68, | |
| "learning_rate": 1.616376433468843e-05, | |
| "loss": 0.2104, | |
| "step": 126500 | |
| }, | |
| { | |
| "epoch": 7.71, | |
| "learning_rate": 1.6148595352223773e-05, | |
| "loss": 0.2104, | |
| "step": 127000 | |
| }, | |
| { | |
| "epoch": 7.74, | |
| "learning_rate": 1.613342636975912e-05, | |
| "loss": 0.2068, | |
| "step": 127500 | |
| }, | |
| { | |
| "epoch": 7.77, | |
| "learning_rate": 1.6118257387294462e-05, | |
| "loss": 0.2107, | |
| "step": 128000 | |
| }, | |
| { | |
| "epoch": 7.8, | |
| "learning_rate": 1.6103088404829804e-05, | |
| "loss": 0.2086, | |
| "step": 128500 | |
| }, | |
| { | |
| "epoch": 7.83, | |
| "learning_rate": 1.6087919422365147e-05, | |
| "loss": 0.2097, | |
| "step": 129000 | |
| }, | |
| { | |
| "epoch": 7.86, | |
| "learning_rate": 1.6072811115830353e-05, | |
| "loss": 0.2097, | |
| "step": 129500 | |
| }, | |
| { | |
| "epoch": 7.89, | |
| "learning_rate": 1.6057642133365695e-05, | |
| "loss": 0.2083, | |
| "step": 130000 | |
| }, | |
| { | |
| "epoch": 7.92, | |
| "learning_rate": 1.6042473150901038e-05, | |
| "loss": 0.2117, | |
| "step": 130500 | |
| }, | |
| { | |
| "epoch": 7.95, | |
| "learning_rate": 1.602730416843638e-05, | |
| "loss": 0.2084, | |
| "step": 131000 | |
| }, | |
| { | |
| "epoch": 7.98, | |
| "learning_rate": 1.6012135185971726e-05, | |
| "loss": 0.2083, | |
| "step": 131500 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_bleu": 79.6569, | |
| "eval_gen_len": 14.0215, | |
| "eval_loss": 0.19143153727054596, | |
| "eval_runtime": 170.1846, | |
| "eval_samples_per_second": 94.744, | |
| "eval_steps_per_second": 2.961, | |
| "step": 131848 | |
| }, | |
| { | |
| "epoch": 8.01, | |
| "learning_rate": 1.599696620350707e-05, | |
| "loss": 0.2077, | |
| "step": 132000 | |
| }, | |
| { | |
| "epoch": 8.04, | |
| "learning_rate": 1.5981797221042414e-05, | |
| "loss": 0.2018, | |
| "step": 132500 | |
| }, | |
| { | |
| "epoch": 8.07, | |
| "learning_rate": 1.5966628238577757e-05, | |
| "loss": 0.204, | |
| "step": 133000 | |
| }, | |
| { | |
| "epoch": 8.1, | |
| "learning_rate": 1.5951459256113103e-05, | |
| "loss": 0.2021, | |
| "step": 133500 | |
| }, | |
| { | |
| "epoch": 8.13, | |
| "learning_rate": 1.5936290273648445e-05, | |
| "loss": 0.2026, | |
| "step": 134000 | |
| }, | |
| { | |
| "epoch": 8.16, | |
| "learning_rate": 1.592112129118379e-05, | |
| "loss": 0.2012, | |
| "step": 134500 | |
| }, | |
| { | |
| "epoch": 8.19, | |
| "learning_rate": 1.5905952308719134e-05, | |
| "loss": 0.2002, | |
| "step": 135000 | |
| }, | |
| { | |
| "epoch": 8.22, | |
| "learning_rate": 1.5890783326254476e-05, | |
| "loss": 0.1998, | |
| "step": 135500 | |
| }, | |
| { | |
| "epoch": 8.25, | |
| "learning_rate": 1.5875614343789822e-05, | |
| "loss": 0.2048, | |
| "step": 136000 | |
| }, | |
| { | |
| "epoch": 8.28, | |
| "learning_rate": 1.5860445361325164e-05, | |
| "loss": 0.2008, | |
| "step": 136500 | |
| }, | |
| { | |
| "epoch": 8.31, | |
| "learning_rate": 1.5845276378860507e-05, | |
| "loss": 0.2055, | |
| "step": 137000 | |
| }, | |
| { | |
| "epoch": 8.34, | |
| "learning_rate": 1.583010739639585e-05, | |
| "loss": 0.2053, | |
| "step": 137500 | |
| }, | |
| { | |
| "epoch": 8.37, | |
| "learning_rate": 1.5814938413931195e-05, | |
| "loss": 0.2024, | |
| "step": 138000 | |
| }, | |
| { | |
| "epoch": 8.4, | |
| "learning_rate": 1.5799769431466538e-05, | |
| "loss": 0.2022, | |
| "step": 138500 | |
| }, | |
| { | |
| "epoch": 8.43, | |
| "learning_rate": 1.578460044900188e-05, | |
| "loss": 0.2003, | |
| "step": 139000 | |
| }, | |
| { | |
| "epoch": 8.46, | |
| "learning_rate": 1.5769431466537226e-05, | |
| "loss": 0.2016, | |
| "step": 139500 | |
| }, | |
| { | |
| "epoch": 8.49, | |
| "learning_rate": 1.575426248407257e-05, | |
| "loss": 0.2011, | |
| "step": 140000 | |
| }, | |
| { | |
| "epoch": 8.52, | |
| "learning_rate": 1.5739123839572843e-05, | |
| "loss": 0.2025, | |
| "step": 140500 | |
| }, | |
| { | |
| "epoch": 8.56, | |
| "learning_rate": 1.5723954857108185e-05, | |
| "loss": 0.1995, | |
| "step": 141000 | |
| }, | |
| { | |
| "epoch": 8.59, | |
| "learning_rate": 1.570878587464353e-05, | |
| "loss": 0.2035, | |
| "step": 141500 | |
| }, | |
| { | |
| "epoch": 8.62, | |
| "learning_rate": 1.5693616892178874e-05, | |
| "loss": 0.2002, | |
| "step": 142000 | |
| }, | |
| { | |
| "epoch": 8.65, | |
| "learning_rate": 1.5678478247679148e-05, | |
| "loss": 0.2016, | |
| "step": 142500 | |
| }, | |
| { | |
| "epoch": 8.68, | |
| "learning_rate": 1.566330926521449e-05, | |
| "loss": 0.1985, | |
| "step": 143000 | |
| }, | |
| { | |
| "epoch": 8.71, | |
| "learning_rate": 1.5648170620714765e-05, | |
| "loss": 0.2004, | |
| "step": 143500 | |
| }, | |
| { | |
| "epoch": 8.74, | |
| "learning_rate": 1.5633001638250107e-05, | |
| "loss": 0.1992, | |
| "step": 144000 | |
| }, | |
| { | |
| "epoch": 8.77, | |
| "learning_rate": 1.561786299375038e-05, | |
| "loss": 0.2037, | |
| "step": 144500 | |
| }, | |
| { | |
| "epoch": 8.8, | |
| "learning_rate": 1.5602694011285724e-05, | |
| "loss": 0.203, | |
| "step": 145000 | |
| }, | |
| { | |
| "epoch": 8.83, | |
| "learning_rate": 1.558752502882107e-05, | |
| "loss": 0.202, | |
| "step": 145500 | |
| }, | |
| { | |
| "epoch": 8.86, | |
| "learning_rate": 1.5572356046356412e-05, | |
| "loss": 0.198, | |
| "step": 146000 | |
| }, | |
| { | |
| "epoch": 8.89, | |
| "learning_rate": 1.5557187063891755e-05, | |
| "loss": 0.1992, | |
| "step": 146500 | |
| }, | |
| { | |
| "epoch": 8.92, | |
| "learning_rate": 1.55420180814271e-05, | |
| "loss": 0.1988, | |
| "step": 147000 | |
| }, | |
| { | |
| "epoch": 8.95, | |
| "learning_rate": 1.5526849098962443e-05, | |
| "loss": 0.1992, | |
| "step": 147500 | |
| }, | |
| { | |
| "epoch": 8.98, | |
| "learning_rate": 1.5511680116497786e-05, | |
| "loss": 0.1986, | |
| "step": 148000 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_bleu": 79.9315, | |
| "eval_gen_len": 14.0219, | |
| "eval_loss": 0.18681135773658752, | |
| "eval_runtime": 171.5642, | |
| "eval_samples_per_second": 93.982, | |
| "eval_steps_per_second": 2.938, | |
| "step": 148329 | |
| }, | |
| { | |
| "epoch": 9.01, | |
| "learning_rate": 1.549651113403313e-05, | |
| "loss": 0.1942, | |
| "step": 148500 | |
| }, | |
| { | |
| "epoch": 9.04, | |
| "learning_rate": 1.5481342151568474e-05, | |
| "loss": 0.195, | |
| "step": 149000 | |
| }, | |
| { | |
| "epoch": 9.07, | |
| "learning_rate": 1.5466173169103816e-05, | |
| "loss": 0.1933, | |
| "step": 149500 | |
| }, | |
| { | |
| "epoch": 9.1, | |
| "learning_rate": 1.5451004186639162e-05, | |
| "loss": 0.1949, | |
| "step": 150000 | |
| }, | |
| { | |
| "epoch": 9.13, | |
| "learning_rate": 1.5435865542139433e-05, | |
| "loss": 0.1963, | |
| "step": 150500 | |
| }, | |
| { | |
| "epoch": 9.16, | |
| "learning_rate": 1.542069655967478e-05, | |
| "loss": 0.1926, | |
| "step": 151000 | |
| }, | |
| { | |
| "epoch": 9.19, | |
| "learning_rate": 1.540552757721012e-05, | |
| "loss": 0.1897, | |
| "step": 151500 | |
| }, | |
| { | |
| "epoch": 9.22, | |
| "learning_rate": 1.5390358594745464e-05, | |
| "loss": 0.1931, | |
| "step": 152000 | |
| }, | |
| { | |
| "epoch": 9.25, | |
| "learning_rate": 1.537518961228081e-05, | |
| "loss": 0.1907, | |
| "step": 152500 | |
| }, | |
| { | |
| "epoch": 9.28, | |
| "learning_rate": 1.5360020629816152e-05, | |
| "loss": 0.1919, | |
| "step": 153000 | |
| }, | |
| { | |
| "epoch": 9.31, | |
| "learning_rate": 1.5344851647351498e-05, | |
| "loss": 0.1925, | |
| "step": 153500 | |
| }, | |
| { | |
| "epoch": 9.34, | |
| "learning_rate": 1.532968266488684e-05, | |
| "loss": 0.1918, | |
| "step": 154000 | |
| }, | |
| { | |
| "epoch": 9.37, | |
| "learning_rate": 1.5314513682422187e-05, | |
| "loss": 0.1933, | |
| "step": 154500 | |
| }, | |
| { | |
| "epoch": 9.4, | |
| "learning_rate": 1.5299375037922457e-05, | |
| "loss": 0.1944, | |
| "step": 155000 | |
| }, | |
| { | |
| "epoch": 9.44, | |
| "learning_rate": 1.5284206055457803e-05, | |
| "loss": 0.1929, | |
| "step": 155500 | |
| }, | |
| { | |
| "epoch": 9.47, | |
| "learning_rate": 1.5269037072993146e-05, | |
| "loss": 0.1932, | |
| "step": 156000 | |
| }, | |
| { | |
| "epoch": 9.5, | |
| "learning_rate": 1.5253868090528488e-05, | |
| "loss": 0.1929, | |
| "step": 156500 | |
| }, | |
| { | |
| "epoch": 9.53, | |
| "learning_rate": 1.523872944602876e-05, | |
| "loss": 0.1916, | |
| "step": 157000 | |
| }, | |
| { | |
| "epoch": 9.56, | |
| "learning_rate": 1.5223560463564105e-05, | |
| "loss": 0.1938, | |
| "step": 157500 | |
| }, | |
| { | |
| "epoch": 9.59, | |
| "learning_rate": 1.5208391481099449e-05, | |
| "loss": 0.1891, | |
| "step": 158000 | |
| }, | |
| { | |
| "epoch": 9.62, | |
| "learning_rate": 1.5193222498634792e-05, | |
| "loss": 0.1875, | |
| "step": 158500 | |
| }, | |
| { | |
| "epoch": 9.65, | |
| "learning_rate": 1.5178083854135066e-05, | |
| "loss": 0.192, | |
| "step": 159000 | |
| }, | |
| { | |
| "epoch": 9.68, | |
| "learning_rate": 1.5162945209635338e-05, | |
| "loss": 0.1919, | |
| "step": 159500 | |
| }, | |
| { | |
| "epoch": 9.71, | |
| "learning_rate": 1.5147776227170683e-05, | |
| "loss": 0.1924, | |
| "step": 160000 | |
| }, | |
| { | |
| "epoch": 9.74, | |
| "learning_rate": 1.5132607244706025e-05, | |
| "loss": 0.1947, | |
| "step": 160500 | |
| }, | |
| { | |
| "epoch": 9.77, | |
| "learning_rate": 1.5117438262241371e-05, | |
| "loss": 0.1895, | |
| "step": 161000 | |
| }, | |
| { | |
| "epoch": 9.8, | |
| "learning_rate": 1.5102269279776713e-05, | |
| "loss": 0.1886, | |
| "step": 161500 | |
| }, | |
| { | |
| "epoch": 9.83, | |
| "learning_rate": 1.5087100297312058e-05, | |
| "loss": 0.1948, | |
| "step": 162000 | |
| }, | |
| { | |
| "epoch": 9.86, | |
| "learning_rate": 1.507196165281233e-05, | |
| "loss": 0.1947, | |
| "step": 162500 | |
| }, | |
| { | |
| "epoch": 9.89, | |
| "learning_rate": 1.5056792670347676e-05, | |
| "loss": 0.1904, | |
| "step": 163000 | |
| }, | |
| { | |
| "epoch": 9.92, | |
| "learning_rate": 1.5041623687883018e-05, | |
| "loss": 0.1895, | |
| "step": 163500 | |
| }, | |
| { | |
| "epoch": 9.95, | |
| "learning_rate": 1.5026454705418361e-05, | |
| "loss": 0.1907, | |
| "step": 164000 | |
| }, | |
| { | |
| "epoch": 9.98, | |
| "learning_rate": 1.5011285722953705e-05, | |
| "loss": 0.1956, | |
| "step": 164500 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_bleu": 80.0539, | |
| "eval_gen_len": 14.0305, | |
| "eval_loss": 0.18285295367240906, | |
| "eval_runtime": 168.5447, | |
| "eval_samples_per_second": 95.666, | |
| "eval_steps_per_second": 2.99, | |
| "step": 164810 | |
| }, | |
| { | |
| "epoch": 10.01, | |
| "learning_rate": 1.4996116740489048e-05, | |
| "loss": 0.1904, | |
| "step": 165000 | |
| }, | |
| { | |
| "epoch": 10.04, | |
| "learning_rate": 1.4980947758024394e-05, | |
| "loss": 0.185, | |
| "step": 165500 | |
| }, | |
| { | |
| "epoch": 10.07, | |
| "learning_rate": 1.4965778775559736e-05, | |
| "loss": 0.1841, | |
| "step": 166000 | |
| }, | |
| { | |
| "epoch": 10.1, | |
| "learning_rate": 1.4950609793095082e-05, | |
| "loss": 0.1853, | |
| "step": 166500 | |
| }, | |
| { | |
| "epoch": 10.13, | |
| "learning_rate": 1.4935440810630424e-05, | |
| "loss": 0.1851, | |
| "step": 167000 | |
| }, | |
| { | |
| "epoch": 10.16, | |
| "learning_rate": 1.4920302166130699e-05, | |
| "loss": 0.1842, | |
| "step": 167500 | |
| }, | |
| { | |
| "epoch": 10.19, | |
| "learning_rate": 1.4905133183666041e-05, | |
| "loss": 0.1846, | |
| "step": 168000 | |
| }, | |
| { | |
| "epoch": 10.22, | |
| "learning_rate": 1.4889964201201385e-05, | |
| "loss": 0.1852, | |
| "step": 168500 | |
| }, | |
| { | |
| "epoch": 10.25, | |
| "learning_rate": 1.4874795218736728e-05, | |
| "loss": 0.1871, | |
| "step": 169000 | |
| }, | |
| { | |
| "epoch": 10.28, | |
| "learning_rate": 1.4859656574237002e-05, | |
| "loss": 0.1875, | |
| "step": 169500 | |
| }, | |
| { | |
| "epoch": 10.31, | |
| "learning_rate": 1.4844487591772344e-05, | |
| "loss": 0.1857, | |
| "step": 170000 | |
| }, | |
| { | |
| "epoch": 10.35, | |
| "learning_rate": 1.4829318609307689e-05, | |
| "loss": 0.1856, | |
| "step": 170500 | |
| }, | |
| { | |
| "epoch": 10.38, | |
| "learning_rate": 1.4814149626843033e-05, | |
| "loss": 0.1867, | |
| "step": 171000 | |
| }, | |
| { | |
| "epoch": 10.41, | |
| "learning_rate": 1.4799010982343305e-05, | |
| "loss": 0.1858, | |
| "step": 171500 | |
| }, | |
| { | |
| "epoch": 10.44, | |
| "learning_rate": 1.478384199987865e-05, | |
| "loss": 0.1872, | |
| "step": 172000 | |
| }, | |
| { | |
| "epoch": 10.47, | |
| "learning_rate": 1.4768673017413992e-05, | |
| "loss": 0.1825, | |
| "step": 172500 | |
| }, | |
| { | |
| "epoch": 10.5, | |
| "learning_rate": 1.4753504034949338e-05, | |
| "loss": 0.1839, | |
| "step": 173000 | |
| }, | |
| { | |
| "epoch": 10.53, | |
| "learning_rate": 1.473833505248468e-05, | |
| "loss": 0.1862, | |
| "step": 173500 | |
| }, | |
| { | |
| "epoch": 10.56, | |
| "learning_rate": 1.4723166070020025e-05, | |
| "loss": 0.186, | |
| "step": 174000 | |
| }, | |
| { | |
| "epoch": 10.59, | |
| "learning_rate": 1.4707997087555369e-05, | |
| "loss": 0.1856, | |
| "step": 174500 | |
| }, | |
| { | |
| "epoch": 10.62, | |
| "learning_rate": 1.4692828105090711e-05, | |
| "loss": 0.1851, | |
| "step": 175000 | |
| }, | |
| { | |
| "epoch": 10.65, | |
| "learning_rate": 1.4677659122626055e-05, | |
| "loss": 0.1869, | |
| "step": 175500 | |
| }, | |
| { | |
| "epoch": 10.68, | |
| "learning_rate": 1.4662520478126328e-05, | |
| "loss": 0.1843, | |
| "step": 176000 | |
| }, | |
| { | |
| "epoch": 10.71, | |
| "learning_rate": 1.4647351495661672e-05, | |
| "loss": 0.1811, | |
| "step": 176500 | |
| }, | |
| { | |
| "epoch": 10.74, | |
| "learning_rate": 1.4632182513197015e-05, | |
| "loss": 0.1865, | |
| "step": 177000 | |
| }, | |
| { | |
| "epoch": 10.77, | |
| "learning_rate": 1.461701353073236e-05, | |
| "loss": 0.1843, | |
| "step": 177500 | |
| }, | |
| { | |
| "epoch": 10.8, | |
| "learning_rate": 1.4601844548267703e-05, | |
| "loss": 0.1836, | |
| "step": 178000 | |
| }, | |
| { | |
| "epoch": 10.83, | |
| "learning_rate": 1.4586736241732906e-05, | |
| "loss": 0.1832, | |
| "step": 178500 | |
| }, | |
| { | |
| "epoch": 10.86, | |
| "learning_rate": 1.457156725926825e-05, | |
| "loss": 0.182, | |
| "step": 179000 | |
| }, | |
| { | |
| "epoch": 10.89, | |
| "learning_rate": 1.4556398276803594e-05, | |
| "loss": 0.1841, | |
| "step": 179500 | |
| }, | |
| { | |
| "epoch": 10.92, | |
| "learning_rate": 1.4541229294338936e-05, | |
| "loss": 0.1866, | |
| "step": 180000 | |
| }, | |
| { | |
| "epoch": 10.95, | |
| "learning_rate": 1.4526060311874282e-05, | |
| "loss": 0.1851, | |
| "step": 180500 | |
| }, | |
| { | |
| "epoch": 10.98, | |
| "learning_rate": 1.4510891329409625e-05, | |
| "loss": 0.1826, | |
| "step": 181000 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_bleu": 80.3158, | |
| "eval_gen_len": 14.0452, | |
| "eval_loss": 0.17846250534057617, | |
| "eval_runtime": 168.9854, | |
| "eval_samples_per_second": 95.417, | |
| "eval_steps_per_second": 2.983, | |
| "step": 181291 | |
| }, | |
| { | |
| "epoch": 11.01, | |
| "learning_rate": 1.4495722346944967e-05, | |
| "loss": 0.1829, | |
| "step": 181500 | |
| }, | |
| { | |
| "epoch": 11.04, | |
| "learning_rate": 1.4480553364480311e-05, | |
| "loss": 0.1748, | |
| "step": 182000 | |
| }, | |
| { | |
| "epoch": 11.07, | |
| "learning_rate": 1.4465414719980584e-05, | |
| "loss": 0.1809, | |
| "step": 182500 | |
| }, | |
| { | |
| "epoch": 11.1, | |
| "learning_rate": 1.4450245737515928e-05, | |
| "loss": 0.1768, | |
| "step": 183000 | |
| }, | |
| { | |
| "epoch": 11.13, | |
| "learning_rate": 1.4435076755051272e-05, | |
| "loss": 0.1795, | |
| "step": 183500 | |
| }, | |
| { | |
| "epoch": 11.16, | |
| "learning_rate": 1.4419907772586617e-05, | |
| "loss": 0.1767, | |
| "step": 184000 | |
| }, | |
| { | |
| "epoch": 11.19, | |
| "learning_rate": 1.4404738790121959e-05, | |
| "loss": 0.1777, | |
| "step": 184500 | |
| }, | |
| { | |
| "epoch": 11.23, | |
| "learning_rate": 1.4389569807657305e-05, | |
| "loss": 0.1764, | |
| "step": 185000 | |
| }, | |
| { | |
| "epoch": 11.26, | |
| "learning_rate": 1.4374431163157576e-05, | |
| "loss": 0.1796, | |
| "step": 185500 | |
| }, | |
| { | |
| "epoch": 11.29, | |
| "learning_rate": 1.4359262180692922e-05, | |
| "loss": 0.1804, | |
| "step": 186000 | |
| }, | |
| { | |
| "epoch": 11.32, | |
| "learning_rate": 1.4344093198228264e-05, | |
| "loss": 0.1801, | |
| "step": 186500 | |
| }, | |
| { | |
| "epoch": 11.35, | |
| "learning_rate": 1.4328924215763608e-05, | |
| "loss": 0.1775, | |
| "step": 187000 | |
| }, | |
| { | |
| "epoch": 11.38, | |
| "learning_rate": 1.431375523329895e-05, | |
| "loss": 0.1775, | |
| "step": 187500 | |
| }, | |
| { | |
| "epoch": 11.41, | |
| "learning_rate": 1.4298616588799223e-05, | |
| "loss": 0.1789, | |
| "step": 188000 | |
| }, | |
| { | |
| "epoch": 11.44, | |
| "learning_rate": 1.4283447606334569e-05, | |
| "loss": 0.1802, | |
| "step": 188500 | |
| }, | |
| { | |
| "epoch": 11.47, | |
| "learning_rate": 1.4268278623869912e-05, | |
| "loss": 0.1791, | |
| "step": 189000 | |
| }, | |
| { | |
| "epoch": 11.5, | |
| "learning_rate": 1.4253109641405256e-05, | |
| "loss": 0.1786, | |
| "step": 189500 | |
| }, | |
| { | |
| "epoch": 11.53, | |
| "learning_rate": 1.4237970996905528e-05, | |
| "loss": 0.1833, | |
| "step": 190000 | |
| }, | |
| { | |
| "epoch": 11.56, | |
| "learning_rate": 1.4222832352405803e-05, | |
| "loss": 0.1777, | |
| "step": 190500 | |
| }, | |
| { | |
| "epoch": 11.59, | |
| "learning_rate": 1.4207693707906073e-05, | |
| "loss": 0.1786, | |
| "step": 191000 | |
| }, | |
| { | |
| "epoch": 11.62, | |
| "learning_rate": 1.419252472544142e-05, | |
| "loss": 0.1769, | |
| "step": 191500 | |
| }, | |
| { | |
| "epoch": 11.65, | |
| "learning_rate": 1.4177355742976762e-05, | |
| "loss": 0.1775, | |
| "step": 192000 | |
| }, | |
| { | |
| "epoch": 11.68, | |
| "learning_rate": 1.4162186760512106e-05, | |
| "loss": 0.1827, | |
| "step": 192500 | |
| }, | |
| { | |
| "epoch": 11.71, | |
| "learning_rate": 1.414701777804745e-05, | |
| "loss": 0.178, | |
| "step": 193000 | |
| }, | |
| { | |
| "epoch": 11.74, | |
| "learning_rate": 1.4131879133547724e-05, | |
| "loss": 0.1771, | |
| "step": 193500 | |
| }, | |
| { | |
| "epoch": 11.77, | |
| "learning_rate": 1.4116710151083067e-05, | |
| "loss": 0.1781, | |
| "step": 194000 | |
| }, | |
| { | |
| "epoch": 11.8, | |
| "learning_rate": 1.4101541168618411e-05, | |
| "loss": 0.1774, | |
| "step": 194500 | |
| }, | |
| { | |
| "epoch": 11.83, | |
| "learning_rate": 1.4086372186153753e-05, | |
| "loss": 0.1763, | |
| "step": 195000 | |
| }, | |
| { | |
| "epoch": 11.86, | |
| "learning_rate": 1.4071203203689096e-05, | |
| "loss": 0.1768, | |
| "step": 195500 | |
| }, | |
| { | |
| "epoch": 11.89, | |
| "learning_rate": 1.4056034221224442e-05, | |
| "loss": 0.1793, | |
| "step": 196000 | |
| }, | |
| { | |
| "epoch": 11.92, | |
| "learning_rate": 1.4040865238759784e-05, | |
| "loss": 0.1809, | |
| "step": 196500 | |
| }, | |
| { | |
| "epoch": 11.95, | |
| "learning_rate": 1.4025696256295129e-05, | |
| "loss": 0.1797, | |
| "step": 197000 | |
| }, | |
| { | |
| "epoch": 11.98, | |
| "learning_rate": 1.4010527273830473e-05, | |
| "loss": 0.1787, | |
| "step": 197500 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_bleu": 80.3265, | |
| "eval_gen_len": 14.0303, | |
| "eval_loss": 0.17605634033679962, | |
| "eval_runtime": 172.6821, | |
| "eval_samples_per_second": 93.374, | |
| "eval_steps_per_second": 2.919, | |
| "step": 197772 | |
| }, | |
| { | |
| "epoch": 12.01, | |
| "learning_rate": 1.3995358291365817e-05, | |
| "loss": 0.1764, | |
| "step": 198000 | |
| }, | |
| { | |
| "epoch": 12.04, | |
| "learning_rate": 1.398018930890116e-05, | |
| "loss": 0.1735, | |
| "step": 198500 | |
| }, | |
| { | |
| "epoch": 12.07, | |
| "learning_rate": 1.3965020326436505e-05, | |
| "loss": 0.1738, | |
| "step": 199000 | |
| }, | |
| { | |
| "epoch": 12.1, | |
| "learning_rate": 1.3949881681936776e-05, | |
| "loss": 0.1731, | |
| "step": 199500 | |
| }, | |
| { | |
| "epoch": 12.14, | |
| "learning_rate": 1.3934712699472122e-05, | |
| "loss": 0.1759, | |
| "step": 200000 | |
| }, | |
| { | |
| "epoch": 12.17, | |
| "learning_rate": 1.3919543717007464e-05, | |
| "loss": 0.1726, | |
| "step": 200500 | |
| }, | |
| { | |
| "epoch": 12.2, | |
| "learning_rate": 1.3904374734542807e-05, | |
| "loss": 0.1771, | |
| "step": 201000 | |
| }, | |
| { | |
| "epoch": 12.23, | |
| "learning_rate": 1.3889205752078153e-05, | |
| "loss": 0.1766, | |
| "step": 201500 | |
| }, | |
| { | |
| "epoch": 12.26, | |
| "learning_rate": 1.3874067107578424e-05, | |
| "loss": 0.1695, | |
| "step": 202000 | |
| }, | |
| { | |
| "epoch": 12.29, | |
| "learning_rate": 1.385889812511377e-05, | |
| "loss": 0.1714, | |
| "step": 202500 | |
| }, | |
| { | |
| "epoch": 12.32, | |
| "learning_rate": 1.384378981857897e-05, | |
| "loss": 0.1727, | |
| "step": 203000 | |
| }, | |
| { | |
| "epoch": 12.35, | |
| "learning_rate": 1.3828620836114315e-05, | |
| "loss": 0.1725, | |
| "step": 203500 | |
| }, | |
| { | |
| "epoch": 12.38, | |
| "learning_rate": 1.3813451853649657e-05, | |
| "loss": 0.1722, | |
| "step": 204000 | |
| }, | |
| { | |
| "epoch": 12.41, | |
| "learning_rate": 1.3798282871185003e-05, | |
| "loss": 0.179, | |
| "step": 204500 | |
| }, | |
| { | |
| "epoch": 12.44, | |
| "learning_rate": 1.3783113888720345e-05, | |
| "loss": 0.1732, | |
| "step": 205000 | |
| }, | |
| { | |
| "epoch": 12.47, | |
| "learning_rate": 1.376794490625569e-05, | |
| "loss": 0.1722, | |
| "step": 205500 | |
| }, | |
| { | |
| "epoch": 12.5, | |
| "learning_rate": 1.3752775923791034e-05, | |
| "loss": 0.1723, | |
| "step": 206000 | |
| }, | |
| { | |
| "epoch": 12.53, | |
| "learning_rate": 1.3737606941326378e-05, | |
| "loss": 0.1716, | |
| "step": 206500 | |
| }, | |
| { | |
| "epoch": 12.56, | |
| "learning_rate": 1.372243795886172e-05, | |
| "loss": 0.1738, | |
| "step": 207000 | |
| }, | |
| { | |
| "epoch": 12.59, | |
| "learning_rate": 1.3707299314361995e-05, | |
| "loss": 0.1732, | |
| "step": 207500 | |
| }, | |
| { | |
| "epoch": 12.62, | |
| "learning_rate": 1.3692130331897337e-05, | |
| "loss": 0.1736, | |
| "step": 208000 | |
| }, | |
| { | |
| "epoch": 12.65, | |
| "learning_rate": 1.367699168739761e-05, | |
| "loss": 0.1719, | |
| "step": 208500 | |
| }, | |
| { | |
| "epoch": 12.68, | |
| "learning_rate": 1.3661822704932954e-05, | |
| "loss": 0.1717, | |
| "step": 209000 | |
| }, | |
| { | |
| "epoch": 12.71, | |
| "learning_rate": 1.3646653722468296e-05, | |
| "loss": 0.1704, | |
| "step": 209500 | |
| }, | |
| { | |
| "epoch": 12.74, | |
| "learning_rate": 1.3631484740003642e-05, | |
| "loss": 0.174, | |
| "step": 210000 | |
| }, | |
| { | |
| "epoch": 12.77, | |
| "learning_rate": 1.3616315757538985e-05, | |
| "loss": 0.1718, | |
| "step": 210500 | |
| }, | |
| { | |
| "epoch": 12.8, | |
| "learning_rate": 1.360114677507433e-05, | |
| "loss": 0.1726, | |
| "step": 211000 | |
| }, | |
| { | |
| "epoch": 12.83, | |
| "learning_rate": 1.3585977792609673e-05, | |
| "loss": 0.1691, | |
| "step": 211500 | |
| }, | |
| { | |
| "epoch": 12.86, | |
| "learning_rate": 1.3570808810145017e-05, | |
| "loss": 0.1705, | |
| "step": 212000 | |
| }, | |
| { | |
| "epoch": 12.89, | |
| "learning_rate": 1.355563982768036e-05, | |
| "loss": 0.1715, | |
| "step": 212500 | |
| }, | |
| { | |
| "epoch": 12.92, | |
| "learning_rate": 1.3540470845215702e-05, | |
| "loss": 0.1712, | |
| "step": 213000 | |
| }, | |
| { | |
| "epoch": 12.95, | |
| "learning_rate": 1.3525301862751048e-05, | |
| "loss": 0.1731, | |
| "step": 213500 | |
| }, | |
| { | |
| "epoch": 12.98, | |
| "learning_rate": 1.351013288028639e-05, | |
| "loss": 0.1725, | |
| "step": 214000 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_bleu": 80.3976, | |
| "eval_gen_len": 14.0256, | |
| "eval_loss": 0.1731211394071579, | |
| "eval_runtime": 168.6298, | |
| "eval_samples_per_second": 95.618, | |
| "eval_steps_per_second": 2.989, | |
| "step": 214253 | |
| }, | |
| { | |
| "epoch": 13.01, | |
| "learning_rate": 1.3494994235786665e-05, | |
| "loss": 0.1726, | |
| "step": 214500 | |
| }, | |
| { | |
| "epoch": 13.05, | |
| "learning_rate": 1.3479855591286937e-05, | |
| "loss": 0.169, | |
| "step": 215000 | |
| }, | |
| { | |
| "epoch": 13.08, | |
| "learning_rate": 1.3464686608822282e-05, | |
| "loss": 0.1673, | |
| "step": 215500 | |
| }, | |
| { | |
| "epoch": 13.11, | |
| "learning_rate": 1.3449517626357624e-05, | |
| "loss": 0.1696, | |
| "step": 216000 | |
| }, | |
| { | |
| "epoch": 13.14, | |
| "learning_rate": 1.3434378981857898e-05, | |
| "loss": 0.1696, | |
| "step": 216500 | |
| }, | |
| { | |
| "epoch": 13.17, | |
| "learning_rate": 1.341920999939324e-05, | |
| "loss": 0.1679, | |
| "step": 217000 | |
| }, | |
| { | |
| "epoch": 13.2, | |
| "learning_rate": 1.3404041016928587e-05, | |
| "loss": 0.1695, | |
| "step": 217500 | |
| }, | |
| { | |
| "epoch": 13.23, | |
| "learning_rate": 1.3388872034463929e-05, | |
| "loss": 0.166, | |
| "step": 218000 | |
| }, | |
| { | |
| "epoch": 13.26, | |
| "learning_rate": 1.3373703051999273e-05, | |
| "loss": 0.1677, | |
| "step": 218500 | |
| }, | |
| { | |
| "epoch": 13.29, | |
| "learning_rate": 1.3358534069534617e-05, | |
| "loss": 0.1636, | |
| "step": 219000 | |
| }, | |
| { | |
| "epoch": 13.32, | |
| "learning_rate": 1.334336508706996e-05, | |
| "loss": 0.1637, | |
| "step": 219500 | |
| }, | |
| { | |
| "epoch": 13.35, | |
| "learning_rate": 1.3328196104605304e-05, | |
| "loss": 0.1665, | |
| "step": 220000 | |
| }, | |
| { | |
| "epoch": 13.38, | |
| "learning_rate": 1.3313027122140647e-05, | |
| "loss": 0.1657, | |
| "step": 220500 | |
| }, | |
| { | |
| "epoch": 13.41, | |
| "learning_rate": 1.3297858139675992e-05, | |
| "loss": 0.168, | |
| "step": 221000 | |
| }, | |
| { | |
| "epoch": 13.44, | |
| "learning_rate": 1.3282689157211335e-05, | |
| "loss": 0.1676, | |
| "step": 221500 | |
| }, | |
| { | |
| "epoch": 13.47, | |
| "learning_rate": 1.326752017474668e-05, | |
| "loss": 0.169, | |
| "step": 222000 | |
| }, | |
| { | |
| "epoch": 13.5, | |
| "learning_rate": 1.3252351192282022e-05, | |
| "loss": 0.1677, | |
| "step": 222500 | |
| }, | |
| { | |
| "epoch": 13.53, | |
| "learning_rate": 1.3237212547782296e-05, | |
| "loss": 0.1676, | |
| "step": 223000 | |
| }, | |
| { | |
| "epoch": 13.56, | |
| "learning_rate": 1.322204356531764e-05, | |
| "loss": 0.1667, | |
| "step": 223500 | |
| }, | |
| { | |
| "epoch": 13.59, | |
| "learning_rate": 1.3206874582852984e-05, | |
| "loss": 0.1663, | |
| "step": 224000 | |
| }, | |
| { | |
| "epoch": 13.62, | |
| "learning_rate": 1.3191705600388327e-05, | |
| "loss": 0.1659, | |
| "step": 224500 | |
| }, | |
| { | |
| "epoch": 13.65, | |
| "learning_rate": 1.3176566955888601e-05, | |
| "loss": 0.1672, | |
| "step": 225000 | |
| }, | |
| { | |
| "epoch": 13.68, | |
| "learning_rate": 1.3161397973423943e-05, | |
| "loss": 0.1683, | |
| "step": 225500 | |
| }, | |
| { | |
| "epoch": 13.71, | |
| "learning_rate": 1.3146228990959286e-05, | |
| "loss": 0.1681, | |
| "step": 226000 | |
| }, | |
| { | |
| "epoch": 13.74, | |
| "learning_rate": 1.3131060008494632e-05, | |
| "loss": 0.1659, | |
| "step": 226500 | |
| }, | |
| { | |
| "epoch": 13.77, | |
| "learning_rate": 1.3115921363994903e-05, | |
| "loss": 0.1681, | |
| "step": 227000 | |
| }, | |
| { | |
| "epoch": 13.8, | |
| "learning_rate": 1.3100752381530249e-05, | |
| "loss": 0.1703, | |
| "step": 227500 | |
| }, | |
| { | |
| "epoch": 13.83, | |
| "learning_rate": 1.3085583399065591e-05, | |
| "loss": 0.1679, | |
| "step": 228000 | |
| }, | |
| { | |
| "epoch": 13.86, | |
| "learning_rate": 1.3070414416600937e-05, | |
| "loss": 0.167, | |
| "step": 228500 | |
| }, | |
| { | |
| "epoch": 13.89, | |
| "learning_rate": 1.3055275772101208e-05, | |
| "loss": 0.1656, | |
| "step": 229000 | |
| }, | |
| { | |
| "epoch": 13.93, | |
| "learning_rate": 1.3040137127601482e-05, | |
| "loss": 0.172, | |
| "step": 229500 | |
| }, | |
| { | |
| "epoch": 13.96, | |
| "learning_rate": 1.3024968145136824e-05, | |
| "loss": 0.1678, | |
| "step": 230000 | |
| }, | |
| { | |
| "epoch": 13.99, | |
| "learning_rate": 1.300979916267217e-05, | |
| "loss": 0.1718, | |
| "step": 230500 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_bleu": 80.4785, | |
| "eval_gen_len": 14.0177, | |
| "eval_loss": 0.1709802895784378, | |
| "eval_runtime": 169.4766, | |
| "eval_samples_per_second": 95.14, | |
| "eval_steps_per_second": 2.974, | |
| "step": 230734 | |
| }, | |
| { | |
| "epoch": 14.02, | |
| "learning_rate": 1.2994630180207513e-05, | |
| "loss": 0.1667, | |
| "step": 231000 | |
| }, | |
| { | |
| "epoch": 14.05, | |
| "learning_rate": 1.2979461197742857e-05, | |
| "loss": 0.1626, | |
| "step": 231500 | |
| }, | |
| { | |
| "epoch": 14.08, | |
| "learning_rate": 1.29642922152782e-05, | |
| "loss": 0.1616, | |
| "step": 232000 | |
| }, | |
| { | |
| "epoch": 14.11, | |
| "learning_rate": 1.2949123232813544e-05, | |
| "loss": 0.163, | |
| "step": 232500 | |
| }, | |
| { | |
| "epoch": 14.14, | |
| "learning_rate": 1.2933954250348888e-05, | |
| "loss": 0.161, | |
| "step": 233000 | |
| }, | |
| { | |
| "epoch": 14.17, | |
| "learning_rate": 1.291881560584916e-05, | |
| "loss": 0.1664, | |
| "step": 233500 | |
| }, | |
| { | |
| "epoch": 14.2, | |
| "learning_rate": 1.2903646623384505e-05, | |
| "loss": 0.1609, | |
| "step": 234000 | |
| }, | |
| { | |
| "epoch": 14.23, | |
| "learning_rate": 1.2888477640919847e-05, | |
| "loss": 0.1619, | |
| "step": 234500 | |
| }, | |
| { | |
| "epoch": 14.26, | |
| "learning_rate": 1.2873308658455193e-05, | |
| "loss": 0.1632, | |
| "step": 235000 | |
| }, | |
| { | |
| "epoch": 14.29, | |
| "learning_rate": 1.2858139675990535e-05, | |
| "loss": 0.1654, | |
| "step": 235500 | |
| }, | |
| { | |
| "epoch": 14.32, | |
| "learning_rate": 1.284300103149081e-05, | |
| "loss": 0.1608, | |
| "step": 236000 | |
| }, | |
| { | |
| "epoch": 14.35, | |
| "learning_rate": 1.2827832049026152e-05, | |
| "loss": 0.1629, | |
| "step": 236500 | |
| }, | |
| { | |
| "epoch": 14.38, | |
| "learning_rate": 1.2812663066561496e-05, | |
| "loss": 0.1618, | |
| "step": 237000 | |
| }, | |
| { | |
| "epoch": 14.41, | |
| "learning_rate": 1.279749408409684e-05, | |
| "loss": 0.1618, | |
| "step": 237500 | |
| }, | |
| { | |
| "epoch": 14.44, | |
| "learning_rate": 1.2782355439597115e-05, | |
| "loss": 0.1651, | |
| "step": 238000 | |
| }, | |
| { | |
| "epoch": 14.47, | |
| "learning_rate": 1.2767186457132457e-05, | |
| "loss": 0.1639, | |
| "step": 238500 | |
| }, | |
| { | |
| "epoch": 14.5, | |
| "learning_rate": 1.27520174746678e-05, | |
| "loss": 0.1627, | |
| "step": 239000 | |
| }, | |
| { | |
| "epoch": 14.53, | |
| "learning_rate": 1.2736848492203144e-05, | |
| "loss": 0.161, | |
| "step": 239500 | |
| }, | |
| { | |
| "epoch": 14.56, | |
| "learning_rate": 1.2721709847703416e-05, | |
| "loss": 0.1646, | |
| "step": 240000 | |
| }, | |
| { | |
| "epoch": 14.59, | |
| "learning_rate": 1.270654086523876e-05, | |
| "loss": 0.1646, | |
| "step": 240500 | |
| }, | |
| { | |
| "epoch": 14.62, | |
| "learning_rate": 1.2691371882774105e-05, | |
| "loss": 0.1619, | |
| "step": 241000 | |
| }, | |
| { | |
| "epoch": 14.65, | |
| "learning_rate": 1.2676233238274377e-05, | |
| "loss": 0.1633, | |
| "step": 241500 | |
| }, | |
| { | |
| "epoch": 14.68, | |
| "learning_rate": 1.2661064255809721e-05, | |
| "loss": 0.1668, | |
| "step": 242000 | |
| }, | |
| { | |
| "epoch": 14.71, | |
| "learning_rate": 1.2645895273345066e-05, | |
| "loss": 0.1645, | |
| "step": 242500 | |
| }, | |
| { | |
| "epoch": 14.74, | |
| "learning_rate": 1.2630726290880408e-05, | |
| "loss": 0.1634, | |
| "step": 243000 | |
| }, | |
| { | |
| "epoch": 14.77, | |
| "learning_rate": 1.2615557308415754e-05, | |
| "loss": 0.1641, | |
| "step": 243500 | |
| }, | |
| { | |
| "epoch": 14.8, | |
| "learning_rate": 1.2600388325951096e-05, | |
| "loss": 0.1626, | |
| "step": 244000 | |
| }, | |
| { | |
| "epoch": 14.84, | |
| "learning_rate": 1.2585219343486439e-05, | |
| "loss": 0.1599, | |
| "step": 244500 | |
| }, | |
| { | |
| "epoch": 14.87, | |
| "learning_rate": 1.2570050361021783e-05, | |
| "loss": 0.162, | |
| "step": 245000 | |
| }, | |
| { | |
| "epoch": 14.9, | |
| "learning_rate": 1.2554881378557127e-05, | |
| "loss": 0.1651, | |
| "step": 245500 | |
| }, | |
| { | |
| "epoch": 14.93, | |
| "learning_rate": 1.2539712396092471e-05, | |
| "loss": 0.1628, | |
| "step": 246000 | |
| }, | |
| { | |
| "epoch": 14.96, | |
| "learning_rate": 1.2524543413627814e-05, | |
| "loss": 0.1633, | |
| "step": 246500 | |
| }, | |
| { | |
| "epoch": 14.99, | |
| "learning_rate": 1.2509404769128088e-05, | |
| "loss": 0.1635, | |
| "step": 247000 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_bleu": 80.6536, | |
| "eval_gen_len": 14.0499, | |
| "eval_loss": 0.16988149285316467, | |
| "eval_runtime": 171.1611, | |
| "eval_samples_per_second": 94.204, | |
| "eval_steps_per_second": 2.945, | |
| "step": 247215 | |
| }, | |
| { | |
| "epoch": 15.02, | |
| "learning_rate": 1.249423578666343e-05, | |
| "loss": 0.161, | |
| "step": 247500 | |
| }, | |
| { | |
| "epoch": 15.05, | |
| "learning_rate": 1.2479066804198777e-05, | |
| "loss": 0.158, | |
| "step": 248000 | |
| }, | |
| { | |
| "epoch": 15.08, | |
| "learning_rate": 1.2463897821734119e-05, | |
| "loss": 0.1592, | |
| "step": 248500 | |
| }, | |
| { | |
| "epoch": 15.11, | |
| "learning_rate": 1.2448728839269463e-05, | |
| "loss": 0.1589, | |
| "step": 249000 | |
| }, | |
| { | |
| "epoch": 15.14, | |
| "learning_rate": 1.2433590194769736e-05, | |
| "loss": 0.1584, | |
| "step": 249500 | |
| }, | |
| { | |
| "epoch": 15.17, | |
| "learning_rate": 1.241842121230508e-05, | |
| "loss": 0.1577, | |
| "step": 250000 | |
| }, | |
| { | |
| "epoch": 15.2, | |
| "learning_rate": 1.2403252229840424e-05, | |
| "loss": 0.1568, | |
| "step": 250500 | |
| }, | |
| { | |
| "epoch": 15.23, | |
| "learning_rate": 1.2388083247375767e-05, | |
| "loss": 0.1579, | |
| "step": 251000 | |
| }, | |
| { | |
| "epoch": 15.26, | |
| "learning_rate": 1.237291426491111e-05, | |
| "loss": 0.1568, | |
| "step": 251500 | |
| }, | |
| { | |
| "epoch": 15.29, | |
| "learning_rate": 1.2357775620411383e-05, | |
| "loss": 0.1591, | |
| "step": 252000 | |
| }, | |
| { | |
| "epoch": 15.32, | |
| "learning_rate": 1.2342636975911658e-05, | |
| "loss": 0.1615, | |
| "step": 252500 | |
| }, | |
| { | |
| "epoch": 15.35, | |
| "learning_rate": 1.2327467993447e-05, | |
| "loss": 0.1582, | |
| "step": 253000 | |
| }, | |
| { | |
| "epoch": 15.38, | |
| "learning_rate": 1.2312299010982344e-05, | |
| "loss": 0.1609, | |
| "step": 253500 | |
| }, | |
| { | |
| "epoch": 15.41, | |
| "learning_rate": 1.2297130028517688e-05, | |
| "loss": 0.1601, | |
| "step": 254000 | |
| }, | |
| { | |
| "epoch": 15.44, | |
| "learning_rate": 1.2281961046053033e-05, | |
| "loss": 0.1594, | |
| "step": 254500 | |
| }, | |
| { | |
| "epoch": 15.47, | |
| "learning_rate": 1.2266792063588375e-05, | |
| "loss": 0.1569, | |
| "step": 255000 | |
| }, | |
| { | |
| "epoch": 15.5, | |
| "learning_rate": 1.2251623081123721e-05, | |
| "loss": 0.1602, | |
| "step": 255500 | |
| }, | |
| { | |
| "epoch": 15.53, | |
| "learning_rate": 1.2236454098659063e-05, | |
| "loss": 0.1618, | |
| "step": 256000 | |
| }, | |
| { | |
| "epoch": 15.56, | |
| "learning_rate": 1.2221285116194406e-05, | |
| "loss": 0.1566, | |
| "step": 256500 | |
| }, | |
| { | |
| "epoch": 15.59, | |
| "learning_rate": 1.220614647169468e-05, | |
| "loss": 0.1584, | |
| "step": 257000 | |
| }, | |
| { | |
| "epoch": 15.62, | |
| "learning_rate": 1.2190977489230023e-05, | |
| "loss": 0.1573, | |
| "step": 257500 | |
| }, | |
| { | |
| "epoch": 15.65, | |
| "learning_rate": 1.2175808506765367e-05, | |
| "loss": 0.1591, | |
| "step": 258000 | |
| }, | |
| { | |
| "epoch": 15.68, | |
| "learning_rate": 1.2160639524300711e-05, | |
| "loss": 0.1569, | |
| "step": 258500 | |
| }, | |
| { | |
| "epoch": 15.72, | |
| "learning_rate": 1.2145470541836055e-05, | |
| "loss": 0.1584, | |
| "step": 259000 | |
| }, | |
| { | |
| "epoch": 15.75, | |
| "learning_rate": 1.2130331897336328e-05, | |
| "loss": 0.1621, | |
| "step": 259500 | |
| }, | |
| { | |
| "epoch": 15.78, | |
| "learning_rate": 1.2115162914871672e-05, | |
| "loss": 0.1607, | |
| "step": 260000 | |
| }, | |
| { | |
| "epoch": 15.81, | |
| "learning_rate": 1.2099993932407014e-05, | |
| "loss": 0.1606, | |
| "step": 260500 | |
| }, | |
| { | |
| "epoch": 15.84, | |
| "learning_rate": 1.208482494994236e-05, | |
| "loss": 0.1587, | |
| "step": 261000 | |
| }, | |
| { | |
| "epoch": 15.87, | |
| "learning_rate": 1.2069655967477703e-05, | |
| "loss": 0.1588, | |
| "step": 261500 | |
| }, | |
| { | |
| "epoch": 15.9, | |
| "learning_rate": 1.2054517322977977e-05, | |
| "loss": 0.1574, | |
| "step": 262000 | |
| }, | |
| { | |
| "epoch": 15.93, | |
| "learning_rate": 1.203934834051332e-05, | |
| "loss": 0.1639, | |
| "step": 262500 | |
| }, | |
| { | |
| "epoch": 15.96, | |
| "learning_rate": 1.2024209696013594e-05, | |
| "loss": 0.1579, | |
| "step": 263000 | |
| }, | |
| { | |
| "epoch": 15.99, | |
| "learning_rate": 1.2009040713548936e-05, | |
| "loss": 0.1593, | |
| "step": 263500 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_bleu": 80.6166, | |
| "eval_gen_len": 14.0258, | |
| "eval_loss": 0.16955877840518951, | |
| "eval_runtime": 170.3679, | |
| "eval_samples_per_second": 94.642, | |
| "eval_steps_per_second": 2.958, | |
| "step": 263696 | |
| }, | |
| { | |
| "epoch": 16.02, | |
| "learning_rate": 1.1993871731084279e-05, | |
| "loss": 0.1546, | |
| "step": 264000 | |
| }, | |
| { | |
| "epoch": 16.05, | |
| "learning_rate": 1.1978702748619624e-05, | |
| "loss": 0.1561, | |
| "step": 264500 | |
| }, | |
| { | |
| "epoch": 16.08, | |
| "learning_rate": 1.1963533766154967e-05, | |
| "loss": 0.1527, | |
| "step": 265000 | |
| }, | |
| { | |
| "epoch": 16.11, | |
| "learning_rate": 1.1948364783690311e-05, | |
| "loss": 0.1549, | |
| "step": 265500 | |
| }, | |
| { | |
| "epoch": 16.14, | |
| "learning_rate": 1.1933195801225654e-05, | |
| "loss": 0.1568, | |
| "step": 266000 | |
| }, | |
| { | |
| "epoch": 16.17, | |
| "learning_rate": 1.1918026818761e-05, | |
| "loss": 0.1508, | |
| "step": 266500 | |
| }, | |
| { | |
| "epoch": 16.2, | |
| "learning_rate": 1.190288817426127e-05, | |
| "loss": 0.1554, | |
| "step": 267000 | |
| }, | |
| { | |
| "epoch": 16.23, | |
| "learning_rate": 1.1887719191796616e-05, | |
| "loss": 0.1554, | |
| "step": 267500 | |
| }, | |
| { | |
| "epoch": 16.26, | |
| "learning_rate": 1.1872580547296889e-05, | |
| "loss": 0.1558, | |
| "step": 268000 | |
| }, | |
| { | |
| "epoch": 16.29, | |
| "learning_rate": 1.1857411564832233e-05, | |
| "loss": 0.1548, | |
| "step": 268500 | |
| }, | |
| { | |
| "epoch": 16.32, | |
| "learning_rate": 1.1842242582367575e-05, | |
| "loss": 0.1567, | |
| "step": 269000 | |
| }, | |
| { | |
| "epoch": 16.35, | |
| "learning_rate": 1.1827073599902918e-05, | |
| "loss": 0.1536, | |
| "step": 269500 | |
| }, | |
| { | |
| "epoch": 16.38, | |
| "learning_rate": 1.1811904617438264e-05, | |
| "loss": 0.1529, | |
| "step": 270000 | |
| }, | |
| { | |
| "epoch": 16.41, | |
| "learning_rate": 1.1796765972938535e-05, | |
| "loss": 0.1546, | |
| "step": 270500 | |
| }, | |
| { | |
| "epoch": 16.44, | |
| "learning_rate": 1.178159699047388e-05, | |
| "loss": 0.1538, | |
| "step": 271000 | |
| }, | |
| { | |
| "epoch": 16.47, | |
| "learning_rate": 1.1766428008009223e-05, | |
| "loss": 0.1579, | |
| "step": 271500 | |
| }, | |
| { | |
| "epoch": 16.5, | |
| "learning_rate": 1.1751259025544567e-05, | |
| "loss": 0.1526, | |
| "step": 272000 | |
| }, | |
| { | |
| "epoch": 16.53, | |
| "learning_rate": 1.1736090043079911e-05, | |
| "loss": 0.1516, | |
| "step": 272500 | |
| }, | |
| { | |
| "epoch": 16.56, | |
| "learning_rate": 1.1720921060615256e-05, | |
| "loss": 0.1541, | |
| "step": 273000 | |
| }, | |
| { | |
| "epoch": 16.59, | |
| "learning_rate": 1.1705752078150598e-05, | |
| "loss": 0.1539, | |
| "step": 273500 | |
| }, | |
| { | |
| "epoch": 16.63, | |
| "learning_rate": 1.1690583095685944e-05, | |
| "loss": 0.1567, | |
| "step": 274000 | |
| }, | |
| { | |
| "epoch": 16.66, | |
| "learning_rate": 1.1675444451186215e-05, | |
| "loss": 0.1529, | |
| "step": 274500 | |
| }, | |
| { | |
| "epoch": 16.69, | |
| "learning_rate": 1.1660275468721557e-05, | |
| "loss": 0.1569, | |
| "step": 275000 | |
| }, | |
| { | |
| "epoch": 16.72, | |
| "learning_rate": 1.1645106486256903e-05, | |
| "loss": 0.1554, | |
| "step": 275500 | |
| }, | |
| { | |
| "epoch": 16.75, | |
| "learning_rate": 1.1629937503792246e-05, | |
| "loss": 0.1555, | |
| "step": 276000 | |
| }, | |
| { | |
| "epoch": 16.78, | |
| "learning_rate": 1.1614768521327591e-05, | |
| "loss": 0.1583, | |
| "step": 276500 | |
| }, | |
| { | |
| "epoch": 16.81, | |
| "learning_rate": 1.1599599538862934e-05, | |
| "loss": 0.1585, | |
| "step": 277000 | |
| }, | |
| { | |
| "epoch": 16.84, | |
| "learning_rate": 1.1584430556398278e-05, | |
| "loss": 0.1558, | |
| "step": 277500 | |
| }, | |
| { | |
| "epoch": 16.87, | |
| "learning_rate": 1.156926157393362e-05, | |
| "loss": 0.1564, | |
| "step": 278000 | |
| }, | |
| { | |
| "epoch": 16.9, | |
| "learning_rate": 1.1554092591468967e-05, | |
| "loss": 0.156, | |
| "step": 278500 | |
| }, | |
| { | |
| "epoch": 16.93, | |
| "learning_rate": 1.1538953946969237e-05, | |
| "loss": 0.1573, | |
| "step": 279000 | |
| }, | |
| { | |
| "epoch": 16.96, | |
| "learning_rate": 1.1523784964504583e-05, | |
| "loss": 0.1524, | |
| "step": 279500 | |
| }, | |
| { | |
| "epoch": 16.99, | |
| "learning_rate": 1.1508615982039926e-05, | |
| "loss": 0.1561, | |
| "step": 280000 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_bleu": 80.7199, | |
| "eval_gen_len": 14.0692, | |
| "eval_loss": 0.16820241510868073, | |
| "eval_runtime": 169.5628, | |
| "eval_samples_per_second": 95.092, | |
| "eval_steps_per_second": 2.972, | |
| "step": 280177 | |
| }, | |
| { | |
| "epoch": 17.02, | |
| "learning_rate": 1.1493446999575268e-05, | |
| "loss": 0.1497, | |
| "step": 280500 | |
| }, | |
| { | |
| "epoch": 17.05, | |
| "learning_rate": 1.1478278017110614e-05, | |
| "loss": 0.15, | |
| "step": 281000 | |
| }, | |
| { | |
| "epoch": 17.08, | |
| "learning_rate": 1.1463139372610885e-05, | |
| "loss": 0.1535, | |
| "step": 281500 | |
| }, | |
| { | |
| "epoch": 17.11, | |
| "learning_rate": 1.1448000728111159e-05, | |
| "loss": 0.1501, | |
| "step": 282000 | |
| }, | |
| { | |
| "epoch": 17.14, | |
| "learning_rate": 1.1432831745646502e-05, | |
| "loss": 0.1513, | |
| "step": 282500 | |
| }, | |
| { | |
| "epoch": 17.17, | |
| "learning_rate": 1.1417662763181847e-05, | |
| "loss": 0.1535, | |
| "step": 283000 | |
| }, | |
| { | |
| "epoch": 17.2, | |
| "learning_rate": 1.140249378071719e-05, | |
| "loss": 0.1525, | |
| "step": 283500 | |
| }, | |
| { | |
| "epoch": 17.23, | |
| "learning_rate": 1.1387324798252534e-05, | |
| "loss": 0.151, | |
| "step": 284000 | |
| }, | |
| { | |
| "epoch": 17.26, | |
| "learning_rate": 1.1372155815787878e-05, | |
| "loss": 0.1497, | |
| "step": 284500 | |
| }, | |
| { | |
| "epoch": 17.29, | |
| "learning_rate": 1.1356986833323223e-05, | |
| "loss": 0.1517, | |
| "step": 285000 | |
| }, | |
| { | |
| "epoch": 17.32, | |
| "learning_rate": 1.1341817850858565e-05, | |
| "loss": 0.1525, | |
| "step": 285500 | |
| }, | |
| { | |
| "epoch": 17.35, | |
| "learning_rate": 1.1326648868393908e-05, | |
| "loss": 0.1548, | |
| "step": 286000 | |
| }, | |
| { | |
| "epoch": 17.38, | |
| "learning_rate": 1.1311479885929253e-05, | |
| "loss": 0.1516, | |
| "step": 286500 | |
| }, | |
| { | |
| "epoch": 17.41, | |
| "learning_rate": 1.1296310903464596e-05, | |
| "loss": 0.1546, | |
| "step": 287000 | |
| }, | |
| { | |
| "epoch": 17.44, | |
| "learning_rate": 1.128114192099994e-05, | |
| "loss": 0.1492, | |
| "step": 287500 | |
| }, | |
| { | |
| "epoch": 17.47, | |
| "learning_rate": 1.1266003276500213e-05, | |
| "loss": 0.1506, | |
| "step": 288000 | |
| }, | |
| { | |
| "epoch": 17.51, | |
| "learning_rate": 1.1250864632000487e-05, | |
| "loss": 0.1509, | |
| "step": 288500 | |
| }, | |
| { | |
| "epoch": 17.54, | |
| "learning_rate": 1.123569564953583e-05, | |
| "loss": 0.1521, | |
| "step": 289000 | |
| }, | |
| { | |
| "epoch": 17.57, | |
| "learning_rate": 1.1220526667071175e-05, | |
| "loss": 0.1528, | |
| "step": 289500 | |
| }, | |
| { | |
| "epoch": 17.6, | |
| "learning_rate": 1.1205357684606518e-05, | |
| "loss": 0.1543, | |
| "step": 290000 | |
| }, | |
| { | |
| "epoch": 17.63, | |
| "learning_rate": 1.1190188702141862e-05, | |
| "loss": 0.1492, | |
| "step": 290500 | |
| }, | |
| { | |
| "epoch": 17.66, | |
| "learning_rate": 1.1175050057642134e-05, | |
| "loss": 0.1526, | |
| "step": 291000 | |
| }, | |
| { | |
| "epoch": 17.69, | |
| "learning_rate": 1.1159881075177479e-05, | |
| "loss": 0.1516, | |
| "step": 291500 | |
| }, | |
| { | |
| "epoch": 17.72, | |
| "learning_rate": 1.1144712092712821e-05, | |
| "loss": 0.15, | |
| "step": 292000 | |
| }, | |
| { | |
| "epoch": 17.75, | |
| "learning_rate": 1.1129543110248164e-05, | |
| "loss": 0.151, | |
| "step": 292500 | |
| }, | |
| { | |
| "epoch": 17.78, | |
| "learning_rate": 1.1114404465748438e-05, | |
| "loss": 0.1508, | |
| "step": 293000 | |
| }, | |
| { | |
| "epoch": 17.81, | |
| "learning_rate": 1.1099235483283782e-05, | |
| "loss": 0.1501, | |
| "step": 293500 | |
| }, | |
| { | |
| "epoch": 17.84, | |
| "learning_rate": 1.1084066500819126e-05, | |
| "loss": 0.1517, | |
| "step": 294000 | |
| }, | |
| { | |
| "epoch": 17.87, | |
| "learning_rate": 1.1068897518354469e-05, | |
| "loss": 0.1499, | |
| "step": 294500 | |
| }, | |
| { | |
| "epoch": 17.9, | |
| "learning_rate": 1.1053728535889814e-05, | |
| "loss": 0.1504, | |
| "step": 295000 | |
| }, | |
| { | |
| "epoch": 17.93, | |
| "learning_rate": 1.1038589891390085e-05, | |
| "loss": 0.1514, | |
| "step": 295500 | |
| }, | |
| { | |
| "epoch": 17.96, | |
| "learning_rate": 1.1023420908925431e-05, | |
| "loss": 0.1493, | |
| "step": 296000 | |
| }, | |
| { | |
| "epoch": 17.99, | |
| "learning_rate": 1.1008251926460774e-05, | |
| "loss": 0.1532, | |
| "step": 296500 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_bleu": 80.7365, | |
| "eval_gen_len": 14.0628, | |
| "eval_loss": 0.16694927215576172, | |
| "eval_runtime": 170.5372, | |
| "eval_samples_per_second": 94.548, | |
| "eval_steps_per_second": 2.955, | |
| "step": 296658 | |
| }, | |
| { | |
| "epoch": 18.02, | |
| "learning_rate": 1.0993113281961048e-05, | |
| "loss": 0.1487, | |
| "step": 297000 | |
| }, | |
| { | |
| "epoch": 18.05, | |
| "learning_rate": 1.097794429949639e-05, | |
| "loss": 0.1455, | |
| "step": 297500 | |
| }, | |
| { | |
| "epoch": 18.08, | |
| "learning_rate": 1.0962775317031735e-05, | |
| "loss": 0.1449, | |
| "step": 298000 | |
| }, | |
| { | |
| "epoch": 18.11, | |
| "learning_rate": 1.0947636672532007e-05, | |
| "loss": 0.1498, | |
| "step": 298500 | |
| }, | |
| { | |
| "epoch": 18.14, | |
| "learning_rate": 1.0932467690067353e-05, | |
| "loss": 0.1475, | |
| "step": 299000 | |
| }, | |
| { | |
| "epoch": 18.17, | |
| "learning_rate": 1.0917298707602695e-05, | |
| "loss": 0.1477, | |
| "step": 299500 | |
| }, | |
| { | |
| "epoch": 18.2, | |
| "learning_rate": 1.0902129725138038e-05, | |
| "loss": 0.1488, | |
| "step": 300000 | |
| }, | |
| { | |
| "epoch": 18.23, | |
| "learning_rate": 1.0886960742673382e-05, | |
| "loss": 0.1471, | |
| "step": 300500 | |
| }, | |
| { | |
| "epoch": 18.26, | |
| "learning_rate": 1.0871822098173655e-05, | |
| "loss": 0.1503, | |
| "step": 301000 | |
| }, | |
| { | |
| "epoch": 18.29, | |
| "learning_rate": 1.0856653115708999e-05, | |
| "loss": 0.15, | |
| "step": 301500 | |
| }, | |
| { | |
| "epoch": 18.32, | |
| "learning_rate": 1.0841484133244341e-05, | |
| "loss": 0.1477, | |
| "step": 302000 | |
| }, | |
| { | |
| "epoch": 18.35, | |
| "learning_rate": 1.0826315150779687e-05, | |
| "loss": 0.1491, | |
| "step": 302500 | |
| }, | |
| { | |
| "epoch": 18.38, | |
| "learning_rate": 1.081114616831503e-05, | |
| "loss": 0.149, | |
| "step": 303000 | |
| }, | |
| { | |
| "epoch": 18.42, | |
| "learning_rate": 1.0795977185850376e-05, | |
| "loss": 0.1472, | |
| "step": 303500 | |
| }, | |
| { | |
| "epoch": 18.45, | |
| "learning_rate": 1.0780808203385718e-05, | |
| "loss": 0.1467, | |
| "step": 304000 | |
| }, | |
| { | |
| "epoch": 18.48, | |
| "learning_rate": 1.0765669558885992e-05, | |
| "loss": 0.1496, | |
| "step": 304500 | |
| }, | |
| { | |
| "epoch": 18.51, | |
| "learning_rate": 1.0750500576421335e-05, | |
| "loss": 0.148, | |
| "step": 305000 | |
| }, | |
| { | |
| "epoch": 18.54, | |
| "learning_rate": 1.0735331593956679e-05, | |
| "loss": 0.1456, | |
| "step": 305500 | |
| }, | |
| { | |
| "epoch": 18.57, | |
| "learning_rate": 1.0720192949456951e-05, | |
| "loss": 0.149, | |
| "step": 306000 | |
| }, | |
| { | |
| "epoch": 18.6, | |
| "learning_rate": 1.0705023966992294e-05, | |
| "loss": 0.1485, | |
| "step": 306500 | |
| }, | |
| { | |
| "epoch": 18.63, | |
| "learning_rate": 1.0689854984527638e-05, | |
| "loss": 0.1478, | |
| "step": 307000 | |
| }, | |
| { | |
| "epoch": 18.66, | |
| "learning_rate": 1.0674686002062982e-05, | |
| "loss": 0.1473, | |
| "step": 307500 | |
| }, | |
| { | |
| "epoch": 18.69, | |
| "learning_rate": 1.0659517019598326e-05, | |
| "loss": 0.1484, | |
| "step": 308000 | |
| }, | |
| { | |
| "epoch": 18.72, | |
| "learning_rate": 1.0644348037133669e-05, | |
| "loss": 0.149, | |
| "step": 308500 | |
| }, | |
| { | |
| "epoch": 18.75, | |
| "learning_rate": 1.0629179054669015e-05, | |
| "loss": 0.1484, | |
| "step": 309000 | |
| }, | |
| { | |
| "epoch": 18.78, | |
| "learning_rate": 1.0614010072204357e-05, | |
| "loss": 0.1463, | |
| "step": 309500 | |
| }, | |
| { | |
| "epoch": 18.81, | |
| "learning_rate": 1.0598841089739702e-05, | |
| "loss": 0.1482, | |
| "step": 310000 | |
| }, | |
| { | |
| "epoch": 18.84, | |
| "learning_rate": 1.0583672107275044e-05, | |
| "loss": 0.1466, | |
| "step": 310500 | |
| }, | |
| { | |
| "epoch": 18.87, | |
| "learning_rate": 1.0568503124810388e-05, | |
| "loss": 0.148, | |
| "step": 311000 | |
| }, | |
| { | |
| "epoch": 18.9, | |
| "learning_rate": 1.0553364480310662e-05, | |
| "loss": 0.1492, | |
| "step": 311500 | |
| }, | |
| { | |
| "epoch": 18.93, | |
| "learning_rate": 1.0538195497846005e-05, | |
| "loss": 0.1491, | |
| "step": 312000 | |
| }, | |
| { | |
| "epoch": 18.96, | |
| "learning_rate": 1.0523026515381349e-05, | |
| "loss": 0.1485, | |
| "step": 312500 | |
| }, | |
| { | |
| "epoch": 18.99, | |
| "learning_rate": 1.0507857532916692e-05, | |
| "loss": 0.15, | |
| "step": 313000 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_bleu": 80.8654, | |
| "eval_gen_len": 14.0824, | |
| "eval_loss": 0.16597765684127808, | |
| "eval_runtime": 172.4859, | |
| "eval_samples_per_second": 93.48, | |
| "eval_steps_per_second": 2.922, | |
| "step": 313139 | |
| }, | |
| { | |
| "epoch": 19.02, | |
| "learning_rate": 1.0492688550452037e-05, | |
| "loss": 0.1465, | |
| "step": 313500 | |
| }, | |
| { | |
| "epoch": 19.05, | |
| "learning_rate": 1.0477549905952308e-05, | |
| "loss": 0.1446, | |
| "step": 314000 | |
| }, | |
| { | |
| "epoch": 19.08, | |
| "learning_rate": 1.0462380923487654e-05, | |
| "loss": 0.1455, | |
| "step": 314500 | |
| }, | |
| { | |
| "epoch": 19.11, | |
| "learning_rate": 1.0447211941022997e-05, | |
| "loss": 0.1444, | |
| "step": 315000 | |
| }, | |
| { | |
| "epoch": 19.14, | |
| "learning_rate": 1.043204295855834e-05, | |
| "loss": 0.147, | |
| "step": 315500 | |
| }, | |
| { | |
| "epoch": 19.17, | |
| "learning_rate": 1.0416873976093685e-05, | |
| "loss": 0.1457, | |
| "step": 316000 | |
| }, | |
| { | |
| "epoch": 19.2, | |
| "learning_rate": 1.040170499362903e-05, | |
| "loss": 0.1434, | |
| "step": 316500 | |
| }, | |
| { | |
| "epoch": 19.23, | |
| "learning_rate": 1.0386536011164372e-05, | |
| "loss": 0.1455, | |
| "step": 317000 | |
| }, | |
| { | |
| "epoch": 19.26, | |
| "learning_rate": 1.0371367028699714e-05, | |
| "loss": 0.1456, | |
| "step": 317500 | |
| }, | |
| { | |
| "epoch": 19.29, | |
| "learning_rate": 1.035619804623506e-05, | |
| "loss": 0.1443, | |
| "step": 318000 | |
| }, | |
| { | |
| "epoch": 19.33, | |
| "learning_rate": 1.0341029063770403e-05, | |
| "loss": 0.1452, | |
| "step": 318500 | |
| }, | |
| { | |
| "epoch": 19.36, | |
| "learning_rate": 1.0325860081305747e-05, | |
| "loss": 0.1417, | |
| "step": 319000 | |
| }, | |
| { | |
| "epoch": 19.39, | |
| "learning_rate": 1.0310691098841091e-05, | |
| "loss": 0.1423, | |
| "step": 319500 | |
| }, | |
| { | |
| "epoch": 19.42, | |
| "learning_rate": 1.0295522116376435e-05, | |
| "loss": 0.1466, | |
| "step": 320000 | |
| }, | |
| { | |
| "epoch": 19.45, | |
| "learning_rate": 1.0280353133911778e-05, | |
| "loss": 0.149, | |
| "step": 320500 | |
| }, | |
| { | |
| "epoch": 19.48, | |
| "learning_rate": 1.026518415144712e-05, | |
| "loss": 0.1459, | |
| "step": 321000 | |
| }, | |
| { | |
| "epoch": 19.51, | |
| "learning_rate": 1.0250045506947394e-05, | |
| "loss": 0.1427, | |
| "step": 321500 | |
| }, | |
| { | |
| "epoch": 19.54, | |
| "learning_rate": 1.0234876524482737e-05, | |
| "loss": 0.1446, | |
| "step": 322000 | |
| }, | |
| { | |
| "epoch": 19.57, | |
| "learning_rate": 1.0219707542018083e-05, | |
| "loss": 0.1439, | |
| "step": 322500 | |
| }, | |
| { | |
| "epoch": 19.6, | |
| "learning_rate": 1.0204538559553425e-05, | |
| "loss": 0.1456, | |
| "step": 323000 | |
| }, | |
| { | |
| "epoch": 19.63, | |
| "learning_rate": 1.01893999150537e-05, | |
| "loss": 0.1463, | |
| "step": 323500 | |
| }, | |
| { | |
| "epoch": 19.66, | |
| "learning_rate": 1.0174230932589042e-05, | |
| "loss": 0.1454, | |
| "step": 324000 | |
| }, | |
| { | |
| "epoch": 19.69, | |
| "learning_rate": 1.0159061950124388e-05, | |
| "loss": 0.1439, | |
| "step": 324500 | |
| }, | |
| { | |
| "epoch": 19.72, | |
| "learning_rate": 1.014389296765973e-05, | |
| "loss": 0.1457, | |
| "step": 325000 | |
| }, | |
| { | |
| "epoch": 19.75, | |
| "learning_rate": 1.0128723985195074e-05, | |
| "loss": 0.1487, | |
| "step": 325500 | |
| }, | |
| { | |
| "epoch": 19.78, | |
| "learning_rate": 1.0113585340695347e-05, | |
| "loss": 0.1442, | |
| "step": 326000 | |
| }, | |
| { | |
| "epoch": 19.81, | |
| "learning_rate": 1.0098416358230691e-05, | |
| "loss": 0.1444, | |
| "step": 326500 | |
| }, | |
| { | |
| "epoch": 19.84, | |
| "learning_rate": 1.0083277713730964e-05, | |
| "loss": 0.1442, | |
| "step": 327000 | |
| }, | |
| { | |
| "epoch": 19.87, | |
| "learning_rate": 1.0068108731266308e-05, | |
| "loss": 0.1452, | |
| "step": 327500 | |
| }, | |
| { | |
| "epoch": 19.9, | |
| "learning_rate": 1.005293974880165e-05, | |
| "loss": 0.1451, | |
| "step": 328000 | |
| }, | |
| { | |
| "epoch": 19.93, | |
| "learning_rate": 1.0037770766336994e-05, | |
| "loss": 0.1439, | |
| "step": 328500 | |
| }, | |
| { | |
| "epoch": 19.96, | |
| "learning_rate": 1.0022601783872339e-05, | |
| "loss": 0.1444, | |
| "step": 329000 | |
| }, | |
| { | |
| "epoch": 19.99, | |
| "learning_rate": 1.0007432801407681e-05, | |
| "loss": 0.1479, | |
| "step": 329500 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_bleu": 80.8523, | |
| "eval_gen_len": 14.0607, | |
| "eval_loss": 0.16498535871505737, | |
| "eval_runtime": 169.9695, | |
| "eval_samples_per_second": 94.864, | |
| "eval_steps_per_second": 2.965, | |
| "step": 329620 | |
| }, | |
| { | |
| "epoch": 20.02, | |
| "learning_rate": 9.992263818943027e-06, | |
| "loss": 0.1415, | |
| "step": 330000 | |
| }, | |
| { | |
| "epoch": 20.05, | |
| "learning_rate": 9.97709483647837e-06, | |
| "loss": 0.1391, | |
| "step": 330500 | |
| }, | |
| { | |
| "epoch": 20.08, | |
| "learning_rate": 9.961925854013714e-06, | |
| "loss": 0.1411, | |
| "step": 331000 | |
| }, | |
| { | |
| "epoch": 20.11, | |
| "learning_rate": 9.946756871549056e-06, | |
| "loss": 0.1435, | |
| "step": 331500 | |
| }, | |
| { | |
| "epoch": 20.14, | |
| "learning_rate": 9.93161822704933e-06, | |
| "loss": 0.1422, | |
| "step": 332000 | |
| }, | |
| { | |
| "epoch": 20.17, | |
| "learning_rate": 9.916449244584675e-06, | |
| "loss": 0.1434, | |
| "step": 332500 | |
| }, | |
| { | |
| "epoch": 20.21, | |
| "learning_rate": 9.901280262120017e-06, | |
| "loss": 0.1407, | |
| "step": 333000 | |
| }, | |
| { | |
| "epoch": 20.24, | |
| "learning_rate": 9.886111279655361e-06, | |
| "loss": 0.1434, | |
| "step": 333500 | |
| }, | |
| { | |
| "epoch": 20.27, | |
| "learning_rate": 9.870942297190705e-06, | |
| "loss": 0.1433, | |
| "step": 334000 | |
| }, | |
| { | |
| "epoch": 20.3, | |
| "learning_rate": 9.855803652690978e-06, | |
| "loss": 0.1432, | |
| "step": 334500 | |
| }, | |
| { | |
| "epoch": 20.33, | |
| "learning_rate": 9.840634670226322e-06, | |
| "loss": 0.145, | |
| "step": 335000 | |
| }, | |
| { | |
| "epoch": 20.36, | |
| "learning_rate": 9.825465687761666e-06, | |
| "loss": 0.1427, | |
| "step": 335500 | |
| }, | |
| { | |
| "epoch": 20.39, | |
| "learning_rate": 9.81029670529701e-06, | |
| "loss": 0.1454, | |
| "step": 336000 | |
| }, | |
| { | |
| "epoch": 20.42, | |
| "learning_rate": 9.795158060797283e-06, | |
| "loss": 0.1467, | |
| "step": 336500 | |
| }, | |
| { | |
| "epoch": 20.45, | |
| "learning_rate": 9.780019416297556e-06, | |
| "loss": 0.1409, | |
| "step": 337000 | |
| }, | |
| { | |
| "epoch": 20.48, | |
| "learning_rate": 9.7648504338329e-06, | |
| "loss": 0.1432, | |
| "step": 337500 | |
| }, | |
| { | |
| "epoch": 20.51, | |
| "learning_rate": 9.749681451368242e-06, | |
| "loss": 0.1411, | |
| "step": 338000 | |
| }, | |
| { | |
| "epoch": 20.54, | |
| "learning_rate": 9.734512468903586e-06, | |
| "loss": 0.1394, | |
| "step": 338500 | |
| }, | |
| { | |
| "epoch": 20.57, | |
| "learning_rate": 9.71934348643893e-06, | |
| "loss": 0.1431, | |
| "step": 339000 | |
| }, | |
| { | |
| "epoch": 20.6, | |
| "learning_rate": 9.704174503974275e-06, | |
| "loss": 0.1451, | |
| "step": 339500 | |
| }, | |
| { | |
| "epoch": 20.63, | |
| "learning_rate": 9.689005521509617e-06, | |
| "loss": 0.1431, | |
| "step": 340000 | |
| }, | |
| { | |
| "epoch": 20.66, | |
| "learning_rate": 9.673836539044961e-06, | |
| "loss": 0.1452, | |
| "step": 340500 | |
| }, | |
| { | |
| "epoch": 20.69, | |
| "learning_rate": 9.658667556580306e-06, | |
| "loss": 0.1417, | |
| "step": 341000 | |
| }, | |
| { | |
| "epoch": 20.72, | |
| "learning_rate": 9.64349857411565e-06, | |
| "loss": 0.1422, | |
| "step": 341500 | |
| }, | |
| { | |
| "epoch": 20.75, | |
| "learning_rate": 9.628359929615922e-06, | |
| "loss": 0.1398, | |
| "step": 342000 | |
| }, | |
| { | |
| "epoch": 20.78, | |
| "learning_rate": 9.613190947151267e-06, | |
| "loss": 0.1409, | |
| "step": 342500 | |
| }, | |
| { | |
| "epoch": 20.81, | |
| "learning_rate": 9.598021964686609e-06, | |
| "loss": 0.1432, | |
| "step": 343000 | |
| }, | |
| { | |
| "epoch": 20.84, | |
| "learning_rate": 9.582852982221953e-06, | |
| "loss": 0.1418, | |
| "step": 343500 | |
| }, | |
| { | |
| "epoch": 20.87, | |
| "learning_rate": 9.567714337722226e-06, | |
| "loss": 0.1435, | |
| "step": 344000 | |
| }, | |
| { | |
| "epoch": 20.9, | |
| "learning_rate": 9.55254535525757e-06, | |
| "loss": 0.142, | |
| "step": 344500 | |
| }, | |
| { | |
| "epoch": 20.93, | |
| "learning_rate": 9.537376372792914e-06, | |
| "loss": 0.1402, | |
| "step": 345000 | |
| }, | |
| { | |
| "epoch": 20.96, | |
| "learning_rate": 9.522207390328258e-06, | |
| "loss": 0.1449, | |
| "step": 345500 | |
| }, | |
| { | |
| "epoch": 20.99, | |
| "learning_rate": 9.5070384078636e-06, | |
| "loss": 0.1404, | |
| "step": 346000 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_bleu": 80.9578, | |
| "eval_gen_len": 14.0655, | |
| "eval_loss": 0.164962500333786, | |
| "eval_runtime": 171.5734, | |
| "eval_samples_per_second": 93.977, | |
| "eval_steps_per_second": 2.938, | |
| "step": 346101 | |
| }, | |
| { | |
| "epoch": 21.02, | |
| "learning_rate": 9.491899763363875e-06, | |
| "loss": 0.1392, | |
| "step": 346500 | |
| }, | |
| { | |
| "epoch": 21.05, | |
| "learning_rate": 9.476730780899217e-06, | |
| "loss": 0.1375, | |
| "step": 347000 | |
| }, | |
| { | |
| "epoch": 21.08, | |
| "learning_rate": 9.461561798434562e-06, | |
| "loss": 0.142, | |
| "step": 347500 | |
| }, | |
| { | |
| "epoch": 21.12, | |
| "learning_rate": 9.446392815969906e-06, | |
| "loss": 0.139, | |
| "step": 348000 | |
| }, | |
| { | |
| "epoch": 21.15, | |
| "learning_rate": 9.43122383350525e-06, | |
| "loss": 0.1405, | |
| "step": 348500 | |
| }, | |
| { | |
| "epoch": 21.18, | |
| "learning_rate": 9.416054851040593e-06, | |
| "loss": 0.1399, | |
| "step": 349000 | |
| }, | |
| { | |
| "epoch": 21.21, | |
| "learning_rate": 9.400885868575937e-06, | |
| "loss": 0.1388, | |
| "step": 349500 | |
| }, | |
| { | |
| "epoch": 21.24, | |
| "learning_rate": 9.38574722407621e-06, | |
| "loss": 0.1403, | |
| "step": 350000 | |
| }, | |
| { | |
| "epoch": 21.27, | |
| "learning_rate": 9.370578241611553e-06, | |
| "loss": 0.1415, | |
| "step": 350500 | |
| }, | |
| { | |
| "epoch": 21.3, | |
| "learning_rate": 9.355409259146898e-06, | |
| "loss": 0.1387, | |
| "step": 351000 | |
| }, | |
| { | |
| "epoch": 21.33, | |
| "learning_rate": 9.34024027668224e-06, | |
| "loss": 0.1384, | |
| "step": 351500 | |
| }, | |
| { | |
| "epoch": 21.36, | |
| "learning_rate": 9.325101632182514e-06, | |
| "loss": 0.1396, | |
| "step": 352000 | |
| }, | |
| { | |
| "epoch": 21.39, | |
| "learning_rate": 9.309932649717858e-06, | |
| "loss": 0.1417, | |
| "step": 352500 | |
| }, | |
| { | |
| "epoch": 21.42, | |
| "learning_rate": 9.294763667253201e-06, | |
| "loss": 0.1388, | |
| "step": 353000 | |
| }, | |
| { | |
| "epoch": 21.45, | |
| "learning_rate": 9.279594684788545e-06, | |
| "loss": 0.139, | |
| "step": 353500 | |
| }, | |
| { | |
| "epoch": 21.48, | |
| "learning_rate": 9.26442570232389e-06, | |
| "loss": 0.1398, | |
| "step": 354000 | |
| }, | |
| { | |
| "epoch": 21.51, | |
| "learning_rate": 9.249256719859234e-06, | |
| "loss": 0.1402, | |
| "step": 354500 | |
| }, | |
| { | |
| "epoch": 21.54, | |
| "learning_rate": 9.234087737394576e-06, | |
| "loss": 0.1402, | |
| "step": 355000 | |
| }, | |
| { | |
| "epoch": 21.57, | |
| "learning_rate": 9.21891875492992e-06, | |
| "loss": 0.1401, | |
| "step": 355500 | |
| }, | |
| { | |
| "epoch": 21.6, | |
| "learning_rate": 9.203780110430193e-06, | |
| "loss": 0.1391, | |
| "step": 356000 | |
| }, | |
| { | |
| "epoch": 21.63, | |
| "learning_rate": 9.188641465930465e-06, | |
| "loss": 0.1394, | |
| "step": 356500 | |
| }, | |
| { | |
| "epoch": 21.66, | |
| "learning_rate": 9.17347248346581e-06, | |
| "loss": 0.1382, | |
| "step": 357000 | |
| }, | |
| { | |
| "epoch": 21.69, | |
| "learning_rate": 9.158303501001154e-06, | |
| "loss": 0.1388, | |
| "step": 357500 | |
| }, | |
| { | |
| "epoch": 21.72, | |
| "learning_rate": 9.143134518536498e-06, | |
| "loss": 0.1379, | |
| "step": 358000 | |
| }, | |
| { | |
| "epoch": 21.75, | |
| "learning_rate": 9.12799587403677e-06, | |
| "loss": 0.1417, | |
| "step": 358500 | |
| }, | |
| { | |
| "epoch": 21.78, | |
| "learning_rate": 9.112826891572114e-06, | |
| "loss": 0.1428, | |
| "step": 359000 | |
| }, | |
| { | |
| "epoch": 21.81, | |
| "learning_rate": 9.097657909107459e-06, | |
| "loss": 0.1406, | |
| "step": 359500 | |
| }, | |
| { | |
| "epoch": 21.84, | |
| "learning_rate": 9.082488926642801e-06, | |
| "loss": 0.1398, | |
| "step": 360000 | |
| }, | |
| { | |
| "epoch": 21.87, | |
| "learning_rate": 9.067319944178145e-06, | |
| "loss": 0.1396, | |
| "step": 360500 | |
| }, | |
| { | |
| "epoch": 21.9, | |
| "learning_rate": 9.052181299678418e-06, | |
| "loss": 0.1405, | |
| "step": 361000 | |
| }, | |
| { | |
| "epoch": 21.93, | |
| "learning_rate": 9.037012317213762e-06, | |
| "loss": 0.1384, | |
| "step": 361500 | |
| }, | |
| { | |
| "epoch": 21.96, | |
| "learning_rate": 9.021843334749105e-06, | |
| "loss": 0.1411, | |
| "step": 362000 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "learning_rate": 9.006674352284449e-06, | |
| "loss": 0.1428, | |
| "step": 362500 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_bleu": 80.9035, | |
| "eval_gen_len": 14.1041, | |
| "eval_loss": 0.16399070620536804, | |
| "eval_runtime": 169.4187, | |
| "eval_samples_per_second": 95.173, | |
| "eval_steps_per_second": 2.975, | |
| "step": 362582 | |
| }, | |
| { | |
| "epoch": 22.03, | |
| "learning_rate": 8.991505369819793e-06, | |
| "loss": 0.1366, | |
| "step": 363000 | |
| }, | |
| { | |
| "epoch": 22.06, | |
| "learning_rate": 8.976336387355137e-06, | |
| "loss": 0.138, | |
| "step": 363500 | |
| }, | |
| { | |
| "epoch": 22.09, | |
| "learning_rate": 8.96119774285541e-06, | |
| "loss": 0.1386, | |
| "step": 364000 | |
| }, | |
| { | |
| "epoch": 22.12, | |
| "learning_rate": 8.946028760390754e-06, | |
| "loss": 0.1391, | |
| "step": 364500 | |
| }, | |
| { | |
| "epoch": 22.15, | |
| "learning_rate": 8.930859777926098e-06, | |
| "loss": 0.1354, | |
| "step": 365000 | |
| }, | |
| { | |
| "epoch": 22.18, | |
| "learning_rate": 8.915690795461442e-06, | |
| "loss": 0.1372, | |
| "step": 365500 | |
| }, | |
| { | |
| "epoch": 22.21, | |
| "learning_rate": 8.900521812996785e-06, | |
| "loss": 0.1361, | |
| "step": 366000 | |
| }, | |
| { | |
| "epoch": 22.24, | |
| "learning_rate": 8.885352830532129e-06, | |
| "loss": 0.1341, | |
| "step": 366500 | |
| }, | |
| { | |
| "epoch": 22.27, | |
| "learning_rate": 8.870183848067473e-06, | |
| "loss": 0.1345, | |
| "step": 367000 | |
| }, | |
| { | |
| "epoch": 22.3, | |
| "learning_rate": 8.855014865602816e-06, | |
| "loss": 0.1382, | |
| "step": 367500 | |
| }, | |
| { | |
| "epoch": 22.33, | |
| "learning_rate": 8.839876221103088e-06, | |
| "loss": 0.1363, | |
| "step": 368000 | |
| }, | |
| { | |
| "epoch": 22.36, | |
| "learning_rate": 8.824707238638432e-06, | |
| "loss": 0.1369, | |
| "step": 368500 | |
| }, | |
| { | |
| "epoch": 22.39, | |
| "learning_rate": 8.809538256173776e-06, | |
| "loss": 0.1381, | |
| "step": 369000 | |
| }, | |
| { | |
| "epoch": 22.42, | |
| "learning_rate": 8.79436927370912e-06, | |
| "loss": 0.1346, | |
| "step": 369500 | |
| }, | |
| { | |
| "epoch": 22.45, | |
| "learning_rate": 8.779200291244465e-06, | |
| "loss": 0.1378, | |
| "step": 370000 | |
| }, | |
| { | |
| "epoch": 22.48, | |
| "learning_rate": 8.764031308779807e-06, | |
| "loss": 0.1393, | |
| "step": 370500 | |
| }, | |
| { | |
| "epoch": 22.51, | |
| "learning_rate": 8.748862326315151e-06, | |
| "loss": 0.1396, | |
| "step": 371000 | |
| }, | |
| { | |
| "epoch": 22.54, | |
| "learning_rate": 8.733693343850496e-06, | |
| "loss": 0.1395, | |
| "step": 371500 | |
| }, | |
| { | |
| "epoch": 22.57, | |
| "learning_rate": 8.718554699350768e-06, | |
| "loss": 0.1349, | |
| "step": 372000 | |
| }, | |
| { | |
| "epoch": 22.6, | |
| "learning_rate": 8.703385716886112e-06, | |
| "loss": 0.1376, | |
| "step": 372500 | |
| }, | |
| { | |
| "epoch": 22.63, | |
| "learning_rate": 8.688216734421455e-06, | |
| "loss": 0.1389, | |
| "step": 373000 | |
| }, | |
| { | |
| "epoch": 22.66, | |
| "learning_rate": 8.673078089921729e-06, | |
| "loss": 0.1368, | |
| "step": 373500 | |
| }, | |
| { | |
| "epoch": 22.69, | |
| "learning_rate": 8.657909107457072e-06, | |
| "loss": 0.1379, | |
| "step": 374000 | |
| }, | |
| { | |
| "epoch": 22.72, | |
| "learning_rate": 8.642740124992416e-06, | |
| "loss": 0.1348, | |
| "step": 374500 | |
| }, | |
| { | |
| "epoch": 22.75, | |
| "learning_rate": 8.62757114252776e-06, | |
| "loss": 0.136, | |
| "step": 375000 | |
| }, | |
| { | |
| "epoch": 22.78, | |
| "learning_rate": 8.612402160063104e-06, | |
| "loss": 0.1374, | |
| "step": 375500 | |
| }, | |
| { | |
| "epoch": 22.81, | |
| "learning_rate": 8.597233177598448e-06, | |
| "loss": 0.1396, | |
| "step": 376000 | |
| }, | |
| { | |
| "epoch": 22.84, | |
| "learning_rate": 8.58206419513379e-06, | |
| "loss": 0.1383, | |
| "step": 376500 | |
| }, | |
| { | |
| "epoch": 22.87, | |
| "learning_rate": 8.566925550634065e-06, | |
| "loss": 0.1387, | |
| "step": 377000 | |
| }, | |
| { | |
| "epoch": 22.91, | |
| "learning_rate": 8.551756568169407e-06, | |
| "loss": 0.1387, | |
| "step": 377500 | |
| }, | |
| { | |
| "epoch": 22.94, | |
| "learning_rate": 8.536587585704752e-06, | |
| "loss": 0.1391, | |
| "step": 378000 | |
| }, | |
| { | |
| "epoch": 22.97, | |
| "learning_rate": 8.521418603240096e-06, | |
| "loss": 0.1402, | |
| "step": 378500 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "learning_rate": 8.506249620775438e-06, | |
| "loss": 0.1378, | |
| "step": 379000 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_bleu": 80.9901, | |
| "eval_gen_len": 14.0593, | |
| "eval_loss": 0.16328243911266327, | |
| "eval_runtime": 168.8208, | |
| "eval_samples_per_second": 95.51, | |
| "eval_steps_per_second": 2.985, | |
| "step": 379063 | |
| }, | |
| { | |
| "epoch": 23.03, | |
| "learning_rate": 8.491080638310782e-06, | |
| "loss": 0.1356, | |
| "step": 379500 | |
| }, | |
| { | |
| "epoch": 23.06, | |
| "learning_rate": 8.475911655846127e-06, | |
| "loss": 0.1338, | |
| "step": 380000 | |
| }, | |
| { | |
| "epoch": 23.09, | |
| "learning_rate": 8.4607730113464e-06, | |
| "loss": 0.136, | |
| "step": 380500 | |
| }, | |
| { | |
| "epoch": 23.12, | |
| "learning_rate": 8.445634366846672e-06, | |
| "loss": 0.1362, | |
| "step": 381000 | |
| }, | |
| { | |
| "epoch": 23.15, | |
| "learning_rate": 8.430465384382016e-06, | |
| "loss": 0.1355, | |
| "step": 381500 | |
| }, | |
| { | |
| "epoch": 23.18, | |
| "learning_rate": 8.41529640191736e-06, | |
| "loss": 0.1359, | |
| "step": 382000 | |
| }, | |
| { | |
| "epoch": 23.21, | |
| "learning_rate": 8.400127419452704e-06, | |
| "loss": 0.1318, | |
| "step": 382500 | |
| }, | |
| { | |
| "epoch": 23.24, | |
| "learning_rate": 8.384958436988048e-06, | |
| "loss": 0.1335, | |
| "step": 383000 | |
| }, | |
| { | |
| "epoch": 23.27, | |
| "learning_rate": 8.369789454523391e-06, | |
| "loss": 0.1354, | |
| "step": 383500 | |
| }, | |
| { | |
| "epoch": 23.3, | |
| "learning_rate": 8.354620472058735e-06, | |
| "loss": 0.1351, | |
| "step": 384000 | |
| }, | |
| { | |
| "epoch": 23.33, | |
| "learning_rate": 8.33945148959408e-06, | |
| "loss": 0.1377, | |
| "step": 384500 | |
| }, | |
| { | |
| "epoch": 23.36, | |
| "learning_rate": 8.324312845094352e-06, | |
| "loss": 0.1367, | |
| "step": 385000 | |
| }, | |
| { | |
| "epoch": 23.39, | |
| "learning_rate": 8.309143862629694e-06, | |
| "loss": 0.1356, | |
| "step": 385500 | |
| }, | |
| { | |
| "epoch": 23.42, | |
| "learning_rate": 8.293974880165039e-06, | |
| "loss": 0.1352, | |
| "step": 386000 | |
| }, | |
| { | |
| "epoch": 23.45, | |
| "learning_rate": 8.278805897700383e-06, | |
| "loss": 0.1365, | |
| "step": 386500 | |
| }, | |
| { | |
| "epoch": 23.48, | |
| "learning_rate": 8.263636915235727e-06, | |
| "loss": 0.136, | |
| "step": 387000 | |
| }, | |
| { | |
| "epoch": 23.51, | |
| "learning_rate": 8.248467932771071e-06, | |
| "loss": 0.1374, | |
| "step": 387500 | |
| }, | |
| { | |
| "epoch": 23.54, | |
| "learning_rate": 8.233329288271344e-06, | |
| "loss": 0.1346, | |
| "step": 388000 | |
| }, | |
| { | |
| "epoch": 23.57, | |
| "learning_rate": 8.218160305806688e-06, | |
| "loss": 0.1364, | |
| "step": 388500 | |
| }, | |
| { | |
| "epoch": 23.6, | |
| "learning_rate": 8.20299132334203e-06, | |
| "loss": 0.1356, | |
| "step": 389000 | |
| }, | |
| { | |
| "epoch": 23.63, | |
| "learning_rate": 8.187822340877374e-06, | |
| "loss": 0.1349, | |
| "step": 389500 | |
| }, | |
| { | |
| "epoch": 23.66, | |
| "learning_rate": 8.172653358412719e-06, | |
| "loss": 0.1357, | |
| "step": 390000 | |
| }, | |
| { | |
| "epoch": 23.69, | |
| "learning_rate": 8.157514713912991e-06, | |
| "loss": 0.136, | |
| "step": 390500 | |
| }, | |
| { | |
| "epoch": 23.72, | |
| "learning_rate": 8.142345731448335e-06, | |
| "loss": 0.1334, | |
| "step": 391000 | |
| }, | |
| { | |
| "epoch": 23.75, | |
| "learning_rate": 8.127207086948608e-06, | |
| "loss": 0.1347, | |
| "step": 391500 | |
| }, | |
| { | |
| "epoch": 23.78, | |
| "learning_rate": 8.112038104483952e-06, | |
| "loss": 0.1359, | |
| "step": 392000 | |
| }, | |
| { | |
| "epoch": 23.82, | |
| "learning_rate": 8.096869122019295e-06, | |
| "loss": 0.1347, | |
| "step": 392500 | |
| }, | |
| { | |
| "epoch": 23.85, | |
| "learning_rate": 8.081700139554639e-06, | |
| "loss": 0.1378, | |
| "step": 393000 | |
| }, | |
| { | |
| "epoch": 23.88, | |
| "learning_rate": 8.066531157089983e-06, | |
| "loss": 0.1332, | |
| "step": 393500 | |
| }, | |
| { | |
| "epoch": 23.91, | |
| "learning_rate": 8.051362174625327e-06, | |
| "loss": 0.1352, | |
| "step": 394000 | |
| }, | |
| { | |
| "epoch": 23.94, | |
| "learning_rate": 8.036193192160671e-06, | |
| "loss": 0.1326, | |
| "step": 394500 | |
| }, | |
| { | |
| "epoch": 23.97, | |
| "learning_rate": 8.021024209696014e-06, | |
| "loss": 0.1347, | |
| "step": 395000 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "learning_rate": 8.005855227231358e-06, | |
| "loss": 0.1359, | |
| "step": 395500 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_bleu": 81.0343, | |
| "eval_gen_len": 14.0796, | |
| "eval_loss": 0.16283883154392242, | |
| "eval_runtime": 168.3093, | |
| "eval_samples_per_second": 95.8, | |
| "eval_steps_per_second": 2.994, | |
| "step": 395544 | |
| }, | |
| { | |
| "epoch": 24.03, | |
| "learning_rate": 7.990716582731632e-06, | |
| "loss": 0.1295, | |
| "step": 396000 | |
| }, | |
| { | |
| "epoch": 24.06, | |
| "learning_rate": 7.975547600266975e-06, | |
| "loss": 0.1321, | |
| "step": 396500 | |
| }, | |
| { | |
| "epoch": 24.09, | |
| "learning_rate": 7.960378617802319e-06, | |
| "loss": 0.1309, | |
| "step": 397000 | |
| }, | |
| { | |
| "epoch": 24.12, | |
| "learning_rate": 7.945209635337661e-06, | |
| "loss": 0.1327, | |
| "step": 397500 | |
| }, | |
| { | |
| "epoch": 24.15, | |
| "learning_rate": 7.930070990837936e-06, | |
| "loss": 0.1325, | |
| "step": 398000 | |
| }, | |
| { | |
| "epoch": 24.18, | |
| "learning_rate": 7.914902008373278e-06, | |
| "loss": 0.1309, | |
| "step": 398500 | |
| }, | |
| { | |
| "epoch": 24.21, | |
| "learning_rate": 7.899733025908622e-06, | |
| "loss": 0.1318, | |
| "step": 399000 | |
| }, | |
| { | |
| "epoch": 24.24, | |
| "learning_rate": 7.884564043443966e-06, | |
| "loss": 0.1297, | |
| "step": 399500 | |
| }, | |
| { | |
| "epoch": 24.27, | |
| "learning_rate": 7.86939506097931e-06, | |
| "loss": 0.1364, | |
| "step": 400000 | |
| }, | |
| { | |
| "epoch": 24.3, | |
| "learning_rate": 7.854226078514655e-06, | |
| "loss": 0.1321, | |
| "step": 400500 | |
| }, | |
| { | |
| "epoch": 24.33, | |
| "learning_rate": 7.839057096049997e-06, | |
| "loss": 0.136, | |
| "step": 401000 | |
| }, | |
| { | |
| "epoch": 24.36, | |
| "learning_rate": 7.823888113585341e-06, | |
| "loss": 0.1332, | |
| "step": 401500 | |
| }, | |
| { | |
| "epoch": 24.39, | |
| "learning_rate": 7.808719131120686e-06, | |
| "loss": 0.1324, | |
| "step": 402000 | |
| }, | |
| { | |
| "epoch": 24.42, | |
| "learning_rate": 7.793550148656028e-06, | |
| "loss": 0.1347, | |
| "step": 402500 | |
| }, | |
| { | |
| "epoch": 24.45, | |
| "learning_rate": 7.778381166191372e-06, | |
| "loss": 0.1343, | |
| "step": 403000 | |
| }, | |
| { | |
| "epoch": 24.48, | |
| "learning_rate": 7.763212183726716e-06, | |
| "loss": 0.1366, | |
| "step": 403500 | |
| }, | |
| { | |
| "epoch": 24.51, | |
| "learning_rate": 7.748073539226989e-06, | |
| "loss": 0.1346, | |
| "step": 404000 | |
| }, | |
| { | |
| "epoch": 24.54, | |
| "learning_rate": 7.732934894727261e-06, | |
| "loss": 0.1348, | |
| "step": 404500 | |
| }, | |
| { | |
| "epoch": 24.57, | |
| "learning_rate": 7.717765912262606e-06, | |
| "loss": 0.1361, | |
| "step": 405000 | |
| }, | |
| { | |
| "epoch": 24.6, | |
| "learning_rate": 7.70259692979795e-06, | |
| "loss": 0.1354, | |
| "step": 405500 | |
| }, | |
| { | |
| "epoch": 24.63, | |
| "learning_rate": 7.687427947333294e-06, | |
| "loss": 0.1327, | |
| "step": 406000 | |
| }, | |
| { | |
| "epoch": 24.66, | |
| "learning_rate": 7.672289302833567e-06, | |
| "loss": 0.1342, | |
| "step": 406500 | |
| }, | |
| { | |
| "epoch": 24.7, | |
| "learning_rate": 7.65712032036891e-06, | |
| "loss": 0.1314, | |
| "step": 407000 | |
| }, | |
| { | |
| "epoch": 24.73, | |
| "learning_rate": 7.641951337904255e-06, | |
| "loss": 0.1329, | |
| "step": 407500 | |
| }, | |
| { | |
| "epoch": 24.76, | |
| "learning_rate": 7.626782355439598e-06, | |
| "loss": 0.1357, | |
| "step": 408000 | |
| }, | |
| { | |
| "epoch": 24.79, | |
| "learning_rate": 7.611613372974942e-06, | |
| "loss": 0.1345, | |
| "step": 408500 | |
| }, | |
| { | |
| "epoch": 24.82, | |
| "learning_rate": 7.596444390510285e-06, | |
| "loss": 0.1316, | |
| "step": 409000 | |
| }, | |
| { | |
| "epoch": 24.85, | |
| "learning_rate": 7.581275408045628e-06, | |
| "loss": 0.1354, | |
| "step": 409500 | |
| }, | |
| { | |
| "epoch": 24.88, | |
| "learning_rate": 7.5661064255809725e-06, | |
| "loss": 0.1365, | |
| "step": 410000 | |
| }, | |
| { | |
| "epoch": 24.91, | |
| "learning_rate": 7.550937443116317e-06, | |
| "loss": 0.1334, | |
| "step": 410500 | |
| }, | |
| { | |
| "epoch": 24.94, | |
| "learning_rate": 7.53576846065166e-06, | |
| "loss": 0.134, | |
| "step": 411000 | |
| }, | |
| { | |
| "epoch": 24.97, | |
| "learning_rate": 7.520629816151933e-06, | |
| "loss": 0.1316, | |
| "step": 411500 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "learning_rate": 7.505460833687277e-06, | |
| "loss": 0.131, | |
| "step": 412000 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_bleu": 81.0024, | |
| "eval_gen_len": 14.078, | |
| "eval_loss": 0.16371172666549683, | |
| "eval_runtime": 168.3117, | |
| "eval_samples_per_second": 95.798, | |
| "eval_steps_per_second": 2.994, | |
| "step": 412025 | |
| }, | |
| { | |
| "epoch": 25.03, | |
| "learning_rate": 7.490291851222621e-06, | |
| "loss": 0.1291, | |
| "step": 412500 | |
| }, | |
| { | |
| "epoch": 25.06, | |
| "learning_rate": 7.475122868757965e-06, | |
| "loss": 0.1311, | |
| "step": 413000 | |
| }, | |
| { | |
| "epoch": 25.09, | |
| "learning_rate": 7.459953886293308e-06, | |
| "loss": 0.1326, | |
| "step": 413500 | |
| }, | |
| { | |
| "epoch": 25.12, | |
| "learning_rate": 7.444815241793582e-06, | |
| "loss": 0.1298, | |
| "step": 414000 | |
| }, | |
| { | |
| "epoch": 25.15, | |
| "learning_rate": 7.429646259328925e-06, | |
| "loss": 0.1309, | |
| "step": 414500 | |
| }, | |
| { | |
| "epoch": 25.18, | |
| "learning_rate": 7.4144772768642684e-06, | |
| "loss": 0.1319, | |
| "step": 415000 | |
| }, | |
| { | |
| "epoch": 25.21, | |
| "learning_rate": 7.399308294399612e-06, | |
| "loss": 0.1289, | |
| "step": 415500 | |
| }, | |
| { | |
| "epoch": 25.24, | |
| "learning_rate": 7.384139311934956e-06, | |
| "loss": 0.1313, | |
| "step": 416000 | |
| }, | |
| { | |
| "epoch": 25.27, | |
| "learning_rate": 7.3690006674352285e-06, | |
| "loss": 0.1304, | |
| "step": 416500 | |
| }, | |
| { | |
| "epoch": 25.3, | |
| "learning_rate": 7.353831684970573e-06, | |
| "loss": 0.1367, | |
| "step": 417000 | |
| }, | |
| { | |
| "epoch": 25.33, | |
| "learning_rate": 7.338662702505917e-06, | |
| "loss": 0.1327, | |
| "step": 417500 | |
| }, | |
| { | |
| "epoch": 25.36, | |
| "learning_rate": 7.32349372004126e-06, | |
| "loss": 0.1341, | |
| "step": 418000 | |
| }, | |
| { | |
| "epoch": 25.39, | |
| "learning_rate": 7.3083550755415335e-06, | |
| "loss": 0.1299, | |
| "step": 418500 | |
| }, | |
| { | |
| "epoch": 25.42, | |
| "learning_rate": 7.293186093076877e-06, | |
| "loss": 0.1322, | |
| "step": 419000 | |
| }, | |
| { | |
| "epoch": 25.45, | |
| "learning_rate": 7.278017110612221e-06, | |
| "loss": 0.1302, | |
| "step": 419500 | |
| }, | |
| { | |
| "epoch": 25.48, | |
| "learning_rate": 7.262848128147565e-06, | |
| "loss": 0.1285, | |
| "step": 420000 | |
| }, | |
| { | |
| "epoch": 25.51, | |
| "learning_rate": 7.247679145682908e-06, | |
| "loss": 0.1315, | |
| "step": 420500 | |
| }, | |
| { | |
| "epoch": 25.54, | |
| "learning_rate": 7.232510163218251e-06, | |
| "loss": 0.1329, | |
| "step": 421000 | |
| }, | |
| { | |
| "epoch": 25.57, | |
| "learning_rate": 7.217341180753595e-06, | |
| "loss": 0.1322, | |
| "step": 421500 | |
| }, | |
| { | |
| "epoch": 25.61, | |
| "learning_rate": 7.2021721982889395e-06, | |
| "loss": 0.1278, | |
| "step": 422000 | |
| }, | |
| { | |
| "epoch": 25.64, | |
| "learning_rate": 7.187033553789212e-06, | |
| "loss": 0.1288, | |
| "step": 422500 | |
| }, | |
| { | |
| "epoch": 25.67, | |
| "learning_rate": 7.171864571324556e-06, | |
| "loss": 0.1339, | |
| "step": 423000 | |
| }, | |
| { | |
| "epoch": 25.7, | |
| "learning_rate": 7.156725926824829e-06, | |
| "loss": 0.1319, | |
| "step": 423500 | |
| }, | |
| { | |
| "epoch": 25.73, | |
| "learning_rate": 7.141556944360173e-06, | |
| "loss": 0.1299, | |
| "step": 424000 | |
| }, | |
| { | |
| "epoch": 25.76, | |
| "learning_rate": 7.126387961895517e-06, | |
| "loss": 0.1321, | |
| "step": 424500 | |
| }, | |
| { | |
| "epoch": 25.79, | |
| "learning_rate": 7.11121897943086e-06, | |
| "loss": 0.131, | |
| "step": 425000 | |
| }, | |
| { | |
| "epoch": 25.82, | |
| "learning_rate": 7.096080334931134e-06, | |
| "loss": 0.1315, | |
| "step": 425500 | |
| }, | |
| { | |
| "epoch": 25.85, | |
| "learning_rate": 7.080911352466477e-06, | |
| "loss": 0.1305, | |
| "step": 426000 | |
| }, | |
| { | |
| "epoch": 25.88, | |
| "learning_rate": 7.065742370001821e-06, | |
| "loss": 0.1303, | |
| "step": 426500 | |
| }, | |
| { | |
| "epoch": 25.91, | |
| "learning_rate": 7.0505733875371654e-06, | |
| "loss": 0.1327, | |
| "step": 427000 | |
| }, | |
| { | |
| "epoch": 25.94, | |
| "learning_rate": 7.035404405072508e-06, | |
| "loss": 0.1303, | |
| "step": 427500 | |
| }, | |
| { | |
| "epoch": 25.97, | |
| "learning_rate": 7.0202657605727804e-06, | |
| "loss": 0.1306, | |
| "step": 428000 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "learning_rate": 7.005096778108125e-06, | |
| "loss": 0.1325, | |
| "step": 428500 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_bleu": 81.0978, | |
| "eval_gen_len": 14.0985, | |
| "eval_loss": 0.16260042786598206, | |
| "eval_runtime": 168.279, | |
| "eval_samples_per_second": 95.817, | |
| "eval_steps_per_second": 2.995, | |
| "step": 428506 | |
| }, | |
| { | |
| "epoch": 26.03, | |
| "learning_rate": 6.989927795643469e-06, | |
| "loss": 0.1257, | |
| "step": 429000 | |
| }, | |
| { | |
| "epoch": 26.06, | |
| "learning_rate": 6.974758813178812e-06, | |
| "loss": 0.1238, | |
| "step": 429500 | |
| }, | |
| { | |
| "epoch": 26.09, | |
| "learning_rate": 6.959589830714156e-06, | |
| "loss": 0.1316, | |
| "step": 430000 | |
| }, | |
| { | |
| "epoch": 26.12, | |
| "learning_rate": 6.944451186214429e-06, | |
| "loss": 0.1319, | |
| "step": 430500 | |
| }, | |
| { | |
| "epoch": 26.15, | |
| "learning_rate": 6.929282203749773e-06, | |
| "loss": 0.1305, | |
| "step": 431000 | |
| }, | |
| { | |
| "epoch": 26.18, | |
| "learning_rate": 6.914113221285117e-06, | |
| "loss": 0.1303, | |
| "step": 431500 | |
| }, | |
| { | |
| "epoch": 26.21, | |
| "learning_rate": 6.8989442388204606e-06, | |
| "loss": 0.1297, | |
| "step": 432000 | |
| }, | |
| { | |
| "epoch": 26.24, | |
| "learning_rate": 6.883835932285663e-06, | |
| "loss": 0.1284, | |
| "step": 432500 | |
| }, | |
| { | |
| "epoch": 26.27, | |
| "learning_rate": 6.8686669498210064e-06, | |
| "loss": 0.132, | |
| "step": 433000 | |
| }, | |
| { | |
| "epoch": 26.3, | |
| "learning_rate": 6.853497967356351e-06, | |
| "loss": 0.1277, | |
| "step": 433500 | |
| }, | |
| { | |
| "epoch": 26.33, | |
| "learning_rate": 6.838328984891695e-06, | |
| "loss": 0.1302, | |
| "step": 434000 | |
| }, | |
| { | |
| "epoch": 26.36, | |
| "learning_rate": 6.823160002427037e-06, | |
| "loss": 0.1287, | |
| "step": 434500 | |
| }, | |
| { | |
| "epoch": 26.39, | |
| "learning_rate": 6.8079910199623815e-06, | |
| "loss": 0.1277, | |
| "step": 435000 | |
| }, | |
| { | |
| "epoch": 26.42, | |
| "learning_rate": 6.792822037497725e-06, | |
| "loss": 0.128, | |
| "step": 435500 | |
| }, | |
| { | |
| "epoch": 26.45, | |
| "learning_rate": 6.777653055033069e-06, | |
| "loss": 0.1283, | |
| "step": 436000 | |
| }, | |
| { | |
| "epoch": 26.49, | |
| "learning_rate": 6.762484072568412e-06, | |
| "loss": 0.1314, | |
| "step": 436500 | |
| }, | |
| { | |
| "epoch": 26.52, | |
| "learning_rate": 6.7473150901037565e-06, | |
| "loss": 0.1307, | |
| "step": 437000 | |
| }, | |
| { | |
| "epoch": 26.55, | |
| "learning_rate": 6.73217644560403e-06, | |
| "loss": 0.1316, | |
| "step": 437500 | |
| }, | |
| { | |
| "epoch": 26.58, | |
| "learning_rate": 6.717007463139373e-06, | |
| "loss": 0.1291, | |
| "step": 438000 | |
| }, | |
| { | |
| "epoch": 26.61, | |
| "learning_rate": 6.701838480674717e-06, | |
| "loss": 0.1313, | |
| "step": 438500 | |
| }, | |
| { | |
| "epoch": 26.64, | |
| "learning_rate": 6.686669498210061e-06, | |
| "loss": 0.1282, | |
| "step": 439000 | |
| }, | |
| { | |
| "epoch": 26.67, | |
| "learning_rate": 6.671530853710334e-06, | |
| "loss": 0.1304, | |
| "step": 439500 | |
| }, | |
| { | |
| "epoch": 26.7, | |
| "learning_rate": 6.656361871245678e-06, | |
| "loss": 0.1272, | |
| "step": 440000 | |
| }, | |
| { | |
| "epoch": 26.73, | |
| "learning_rate": 6.641192888781021e-06, | |
| "loss": 0.1255, | |
| "step": 440500 | |
| }, | |
| { | |
| "epoch": 26.76, | |
| "learning_rate": 6.626023906316364e-06, | |
| "loss": 0.1308, | |
| "step": 441000 | |
| }, | |
| { | |
| "epoch": 26.79, | |
| "learning_rate": 6.610854923851708e-06, | |
| "loss": 0.1294, | |
| "step": 441500 | |
| }, | |
| { | |
| "epoch": 26.82, | |
| "learning_rate": 6.5956859413870525e-06, | |
| "loss": 0.1313, | |
| "step": 442000 | |
| }, | |
| { | |
| "epoch": 26.85, | |
| "learning_rate": 6.580516958922396e-06, | |
| "loss": 0.1313, | |
| "step": 442500 | |
| }, | |
| { | |
| "epoch": 26.88, | |
| "learning_rate": 6.56534797645774e-06, | |
| "loss": 0.1279, | |
| "step": 443000 | |
| }, | |
| { | |
| "epoch": 26.91, | |
| "learning_rate": 6.550178993993083e-06, | |
| "loss": 0.1289, | |
| "step": 443500 | |
| }, | |
| { | |
| "epoch": 26.94, | |
| "learning_rate": 6.535070687458286e-06, | |
| "loss": 0.1302, | |
| "step": 444000 | |
| }, | |
| { | |
| "epoch": 26.97, | |
| "learning_rate": 6.51990170499363e-06, | |
| "loss": 0.1308, | |
| "step": 444500 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_bleu": 81.1159, | |
| "eval_gen_len": 14.0921, | |
| "eval_loss": 0.16248230636119843, | |
| "eval_runtime": 170.0823, | |
| "eval_samples_per_second": 94.801, | |
| "eval_steps_per_second": 2.963, | |
| "step": 444987 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "learning_rate": 6.504732722528973e-06, | |
| "loss": 0.1315, | |
| "step": 445000 | |
| }, | |
| { | |
| "epoch": 27.03, | |
| "learning_rate": 1.3244781870032159e-05, | |
| "loss": 0.1289, | |
| "step": 445500 | |
| }, | |
| { | |
| "epoch": 27.06, | |
| "learning_rate": 1.3237197378799832e-05, | |
| "loss": 0.127, | |
| "step": 446000 | |
| }, | |
| { | |
| "epoch": 27.09, | |
| "learning_rate": 1.3229612887567503e-05, | |
| "loss": 0.1293, | |
| "step": 446500 | |
| }, | |
| { | |
| "epoch": 27.12, | |
| "learning_rate": 1.3222028396335176e-05, | |
| "loss": 0.13, | |
| "step": 447000 | |
| }, | |
| { | |
| "epoch": 27.15, | |
| "learning_rate": 1.3214443905102847e-05, | |
| "loss": 0.132, | |
| "step": 447500 | |
| }, | |
| { | |
| "epoch": 27.18, | |
| "learning_rate": 1.3206859413870518e-05, | |
| "loss": 0.1298, | |
| "step": 448000 | |
| }, | |
| { | |
| "epoch": 27.21, | |
| "learning_rate": 1.319930526060312e-05, | |
| "loss": 0.1287, | |
| "step": 448500 | |
| }, | |
| { | |
| "epoch": 27.24, | |
| "learning_rate": 1.3191720769370793e-05, | |
| "loss": 0.131, | |
| "step": 449000 | |
| }, | |
| { | |
| "epoch": 27.27, | |
| "learning_rate": 1.3184136278138464e-05, | |
| "loss": 0.1299, | |
| "step": 449500 | |
| }, | |
| { | |
| "epoch": 27.3, | |
| "learning_rate": 1.3176551786906135e-05, | |
| "loss": 0.1285, | |
| "step": 450000 | |
| }, | |
| { | |
| "epoch": 27.33, | |
| "learning_rate": 1.3168967295673806e-05, | |
| "loss": 0.1283, | |
| "step": 450500 | |
| }, | |
| { | |
| "epoch": 27.36, | |
| "learning_rate": 1.3161382804441478e-05, | |
| "loss": 0.1282, | |
| "step": 451000 | |
| }, | |
| { | |
| "epoch": 27.4, | |
| "learning_rate": 1.3153798313209152e-05, | |
| "loss": 0.1314, | |
| "step": 451500 | |
| }, | |
| { | |
| "epoch": 27.43, | |
| "learning_rate": 1.3146213821976823e-05, | |
| "loss": 0.1305, | |
| "step": 452000 | |
| }, | |
| { | |
| "epoch": 27.46, | |
| "learning_rate": 1.3138629330744495e-05, | |
| "loss": 0.1315, | |
| "step": 452500 | |
| }, | |
| { | |
| "epoch": 27.49, | |
| "learning_rate": 1.3131044839512166e-05, | |
| "loss": 0.1289, | |
| "step": 453000 | |
| }, | |
| { | |
| "epoch": 27.52, | |
| "learning_rate": 1.3123460348279839e-05, | |
| "loss": 0.1283, | |
| "step": 453500 | |
| }, | |
| { | |
| "epoch": 27.55, | |
| "learning_rate": 1.311587585704751e-05, | |
| "loss": 0.1302, | |
| "step": 454000 | |
| }, | |
| { | |
| "epoch": 27.58, | |
| "learning_rate": 1.3108306534797647e-05, | |
| "loss": 0.1299, | |
| "step": 454500 | |
| }, | |
| { | |
| "epoch": 27.61, | |
| "learning_rate": 1.3100722043565318e-05, | |
| "loss": 0.1259, | |
| "step": 455000 | |
| }, | |
| { | |
| "epoch": 27.64, | |
| "learning_rate": 1.3093152721315456e-05, | |
| "loss": 0.1309, | |
| "step": 455500 | |
| }, | |
| { | |
| "epoch": 27.67, | |
| "learning_rate": 1.3085568230083129e-05, | |
| "loss": 0.1307, | |
| "step": 456000 | |
| }, | |
| { | |
| "epoch": 27.7, | |
| "learning_rate": 1.30779837388508e-05, | |
| "loss": 0.1298, | |
| "step": 456500 | |
| }, | |
| { | |
| "epoch": 27.73, | |
| "learning_rate": 1.3070399247618471e-05, | |
| "loss": 0.1303, | |
| "step": 457000 | |
| }, | |
| { | |
| "epoch": 27.76, | |
| "learning_rate": 1.3062814756386142e-05, | |
| "loss": 0.1308, | |
| "step": 457500 | |
| }, | |
| { | |
| "epoch": 27.79, | |
| "learning_rate": 1.3055230265153815e-05, | |
| "loss": 0.1297, | |
| "step": 458000 | |
| }, | |
| { | |
| "epoch": 27.82, | |
| "learning_rate": 1.3047645773921486e-05, | |
| "loss": 0.1306, | |
| "step": 458500 | |
| }, | |
| { | |
| "epoch": 27.85, | |
| "learning_rate": 1.3040076451671624e-05, | |
| "loss": 0.1315, | |
| "step": 459000 | |
| }, | |
| { | |
| "epoch": 27.88, | |
| "learning_rate": 1.3032491960439295e-05, | |
| "loss": 0.1326, | |
| "step": 459500 | |
| }, | |
| { | |
| "epoch": 27.91, | |
| "learning_rate": 1.3024907469206966e-05, | |
| "loss": 0.1303, | |
| "step": 460000 | |
| }, | |
| { | |
| "epoch": 27.94, | |
| "learning_rate": 1.3017322977974637e-05, | |
| "loss": 0.1307, | |
| "step": 460500 | |
| }, | |
| { | |
| "epoch": 27.97, | |
| "learning_rate": 1.3009738486742309e-05, | |
| "loss": 0.1278, | |
| "step": 461000 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_bleu": 81.1163, | |
| "eval_gen_len": 14.0657, | |
| "eval_loss": 0.16175536811351776, | |
| "eval_runtime": 180.1879, | |
| "eval_samples_per_second": 89.484, | |
| "eval_steps_per_second": 2.797, | |
| "step": 461468 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "learning_rate": 1.3002153995509983e-05, | |
| "loss": 0.1301, | |
| "step": 461500 | |
| }, | |
| { | |
| "epoch": 28.03, | |
| "learning_rate": 1.2994569504277654e-05, | |
| "loss": 0.128, | |
| "step": 462000 | |
| }, | |
| { | |
| "epoch": 28.06, | |
| "learning_rate": 1.2986985013045326e-05, | |
| "loss": 0.1277, | |
| "step": 462500 | |
| }, | |
| { | |
| "epoch": 28.09, | |
| "learning_rate": 1.2979415690795463e-05, | |
| "loss": 0.1279, | |
| "step": 463000 | |
| }, | |
| { | |
| "epoch": 28.12, | |
| "learning_rate": 1.29718463685456e-05, | |
| "loss": 0.1274, | |
| "step": 463500 | |
| }, | |
| { | |
| "epoch": 28.15, | |
| "learning_rate": 1.2964261877313271e-05, | |
| "loss": 0.1287, | |
| "step": 464000 | |
| }, | |
| { | |
| "epoch": 28.18, | |
| "learning_rate": 1.2956677386080942e-05, | |
| "loss": 0.124, | |
| "step": 464500 | |
| }, | |
| { | |
| "epoch": 28.21, | |
| "learning_rate": 1.2949092894848614e-05, | |
| "loss": 0.1281, | |
| "step": 465000 | |
| }, | |
| { | |
| "epoch": 28.24, | |
| "learning_rate": 1.2941508403616288e-05, | |
| "loss": 0.1265, | |
| "step": 465500 | |
| }, | |
| { | |
| "epoch": 28.27, | |
| "learning_rate": 1.293392391238396e-05, | |
| "loss": 0.1277, | |
| "step": 466000 | |
| }, | |
| { | |
| "epoch": 28.31, | |
| "learning_rate": 1.292633942115163e-05, | |
| "loss": 0.1294, | |
| "step": 466500 | |
| }, | |
| { | |
| "epoch": 28.34, | |
| "learning_rate": 1.2918754929919302e-05, | |
| "loss": 0.1259, | |
| "step": 467000 | |
| }, | |
| { | |
| "epoch": 28.37, | |
| "learning_rate": 1.2911185607669439e-05, | |
| "loss": 0.1259, | |
| "step": 467500 | |
| }, | |
| { | |
| "epoch": 28.4, | |
| "learning_rate": 1.290360111643711e-05, | |
| "loss": 0.1273, | |
| "step": 468000 | |
| }, | |
| { | |
| "epoch": 28.43, | |
| "learning_rate": 1.2896016625204782e-05, | |
| "loss": 0.1297, | |
| "step": 468500 | |
| }, | |
| { | |
| "epoch": 28.46, | |
| "learning_rate": 1.2888432133972455e-05, | |
| "loss": 0.1271, | |
| "step": 469000 | |
| }, | |
| { | |
| "epoch": 28.49, | |
| "learning_rate": 1.2880847642740126e-05, | |
| "loss": 0.126, | |
| "step": 469500 | |
| }, | |
| { | |
| "epoch": 28.52, | |
| "learning_rate": 1.2873263151507797e-05, | |
| "loss": 0.1317, | |
| "step": 470000 | |
| }, | |
| { | |
| "epoch": 28.55, | |
| "learning_rate": 1.2865678660275468e-05, | |
| "loss": 0.1267, | |
| "step": 470500 | |
| }, | |
| { | |
| "epoch": 28.58, | |
| "learning_rate": 1.2858109338025605e-05, | |
| "loss": 0.1259, | |
| "step": 471000 | |
| }, | |
| { | |
| "epoch": 28.61, | |
| "learning_rate": 1.2850524846793278e-05, | |
| "loss": 0.1288, | |
| "step": 471500 | |
| }, | |
| { | |
| "epoch": 28.64, | |
| "learning_rate": 1.2842940355560951e-05, | |
| "loss": 0.1264, | |
| "step": 472000 | |
| }, | |
| { | |
| "epoch": 28.67, | |
| "learning_rate": 1.2835355864328622e-05, | |
| "loss": 0.1278, | |
| "step": 472500 | |
| }, | |
| { | |
| "epoch": 28.7, | |
| "learning_rate": 1.2827771373096294e-05, | |
| "loss": 0.1289, | |
| "step": 473000 | |
| }, | |
| { | |
| "epoch": 28.73, | |
| "learning_rate": 1.282020205084643e-05, | |
| "loss": 0.128, | |
| "step": 473500 | |
| }, | |
| { | |
| "epoch": 28.76, | |
| "learning_rate": 1.2812617559614102e-05, | |
| "loss": 0.1254, | |
| "step": 474000 | |
| }, | |
| { | |
| "epoch": 28.79, | |
| "learning_rate": 1.2805033068381773e-05, | |
| "loss": 0.1273, | |
| "step": 474500 | |
| }, | |
| { | |
| "epoch": 28.82, | |
| "learning_rate": 1.2797448577149445e-05, | |
| "loss": 0.1245, | |
| "step": 475000 | |
| }, | |
| { | |
| "epoch": 28.85, | |
| "learning_rate": 1.278986408591712e-05, | |
| "loss": 0.1278, | |
| "step": 475500 | |
| }, | |
| { | |
| "epoch": 28.88, | |
| "learning_rate": 1.278227959468479e-05, | |
| "loss": 0.1289, | |
| "step": 476000 | |
| }, | |
| { | |
| "epoch": 28.91, | |
| "learning_rate": 1.2774710272434928e-05, | |
| "loss": 0.1273, | |
| "step": 476500 | |
| }, | |
| { | |
| "epoch": 28.94, | |
| "learning_rate": 1.2767125781202599e-05, | |
| "loss": 0.1283, | |
| "step": 477000 | |
| }, | |
| { | |
| "epoch": 28.97, | |
| "learning_rate": 1.275954128997027e-05, | |
| "loss": 0.1317, | |
| "step": 477500 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_bleu": 81.0592, | |
| "eval_gen_len": 14.0958, | |
| "eval_loss": 0.163426473736763, | |
| "eval_runtime": 179.0747, | |
| "eval_samples_per_second": 90.041, | |
| "eval_steps_per_second": 2.814, | |
| "step": 477949 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "learning_rate": 1.2751956798737941e-05, | |
| "loss": 0.1268, | |
| "step": 478000 | |
| }, | |
| { | |
| "epoch": 29.03, | |
| "learning_rate": 1.2744372307505613e-05, | |
| "loss": 0.1252, | |
| "step": 478500 | |
| }, | |
| { | |
| "epoch": 29.06, | |
| "learning_rate": 1.2736787816273285e-05, | |
| "loss": 0.1219, | |
| "step": 479000 | |
| }, | |
| { | |
| "epoch": 29.09, | |
| "learning_rate": 1.2729203325040957e-05, | |
| "loss": 0.1253, | |
| "step": 479500 | |
| }, | |
| { | |
| "epoch": 29.12, | |
| "learning_rate": 1.2721634002791094e-05, | |
| "loss": 0.1198, | |
| "step": 480000 | |
| }, | |
| { | |
| "epoch": 29.15, | |
| "learning_rate": 1.2714049511558765e-05, | |
| "loss": 0.124, | |
| "step": 480500 | |
| }, | |
| { | |
| "epoch": 29.19, | |
| "learning_rate": 1.2706480189308902e-05, | |
| "loss": 0.1242, | |
| "step": 481000 | |
| }, | |
| { | |
| "epoch": 29.22, | |
| "learning_rate": 1.2698895698076575e-05, | |
| "loss": 0.1247, | |
| "step": 481500 | |
| }, | |
| { | |
| "epoch": 29.25, | |
| "learning_rate": 1.2691311206844246e-05, | |
| "loss": 0.1254, | |
| "step": 482000 | |
| }, | |
| { | |
| "epoch": 29.28, | |
| "learning_rate": 1.2683741884594383e-05, | |
| "loss": 0.1258, | |
| "step": 482500 | |
| }, | |
| { | |
| "epoch": 29.31, | |
| "learning_rate": 1.2676157393362055e-05, | |
| "loss": 0.1269, | |
| "step": 483000 | |
| }, | |
| { | |
| "epoch": 29.34, | |
| "learning_rate": 1.2668572902129726e-05, | |
| "loss": 0.1234, | |
| "step": 483500 | |
| }, | |
| { | |
| "epoch": 29.37, | |
| "learning_rate": 1.2660988410897399e-05, | |
| "loss": 0.1262, | |
| "step": 484000 | |
| }, | |
| { | |
| "epoch": 29.4, | |
| "learning_rate": 1.265340391966507e-05, | |
| "loss": 0.1248, | |
| "step": 484500 | |
| }, | |
| { | |
| "epoch": 29.43, | |
| "learning_rate": 1.2645819428432741e-05, | |
| "loss": 0.1247, | |
| "step": 485000 | |
| }, | |
| { | |
| "epoch": 29.46, | |
| "learning_rate": 1.2638234937200413e-05, | |
| "loss": 0.127, | |
| "step": 485500 | |
| }, | |
| { | |
| "epoch": 29.49, | |
| "learning_rate": 1.2630650445968084e-05, | |
| "loss": 0.1259, | |
| "step": 486000 | |
| }, | |
| { | |
| "epoch": 29.52, | |
| "learning_rate": 1.2623065954735759e-05, | |
| "loss": 0.1265, | |
| "step": 486500 | |
| }, | |
| { | |
| "epoch": 29.55, | |
| "learning_rate": 1.2615496632485892e-05, | |
| "loss": 0.1249, | |
| "step": 487000 | |
| }, | |
| { | |
| "epoch": 29.58, | |
| "learning_rate": 1.2607912141253567e-05, | |
| "loss": 0.1268, | |
| "step": 487500 | |
| }, | |
| { | |
| "epoch": 29.61, | |
| "learning_rate": 1.2600327650021238e-05, | |
| "loss": 0.1249, | |
| "step": 488000 | |
| }, | |
| { | |
| "epoch": 29.64, | |
| "learning_rate": 1.259274315878891e-05, | |
| "loss": 0.1256, | |
| "step": 488500 | |
| }, | |
| { | |
| "epoch": 29.67, | |
| "learning_rate": 1.258515866755658e-05, | |
| "loss": 0.1258, | |
| "step": 489000 | |
| }, | |
| { | |
| "epoch": 29.7, | |
| "learning_rate": 1.2577574176324254e-05, | |
| "loss": 0.1274, | |
| "step": 489500 | |
| }, | |
| { | |
| "epoch": 29.73, | |
| "learning_rate": 1.2569989685091926e-05, | |
| "loss": 0.1253, | |
| "step": 490000 | |
| }, | |
| { | |
| "epoch": 29.76, | |
| "learning_rate": 1.2562405193859598e-05, | |
| "loss": 0.1274, | |
| "step": 490500 | |
| }, | |
| { | |
| "epoch": 29.79, | |
| "learning_rate": 1.2554820702627269e-05, | |
| "loss": 0.1259, | |
| "step": 491000 | |
| }, | |
| { | |
| "epoch": 29.82, | |
| "learning_rate": 1.254723621139494e-05, | |
| "loss": 0.1251, | |
| "step": 491500 | |
| }, | |
| { | |
| "epoch": 29.85, | |
| "learning_rate": 1.2539666889145077e-05, | |
| "loss": 0.1261, | |
| "step": 492000 | |
| }, | |
| { | |
| "epoch": 29.88, | |
| "learning_rate": 1.2532082397912749e-05, | |
| "loss": 0.1282, | |
| "step": 492500 | |
| }, | |
| { | |
| "epoch": 29.91, | |
| "learning_rate": 1.2524497906680421e-05, | |
| "loss": 0.126, | |
| "step": 493000 | |
| }, | |
| { | |
| "epoch": 29.94, | |
| "learning_rate": 1.2516913415448093e-05, | |
| "loss": 0.1266, | |
| "step": 493500 | |
| }, | |
| { | |
| "epoch": 29.97, | |
| "learning_rate": 1.2509328924215764e-05, | |
| "loss": 0.1266, | |
| "step": 494000 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_bleu": 81.1592, | |
| "eval_gen_len": 14.0861, | |
| "eval_loss": 0.16239352524280548, | |
| "eval_runtime": 179.0019, | |
| "eval_samples_per_second": 90.077, | |
| "eval_steps_per_second": 2.816, | |
| "step": 494430 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "learning_rate": 1.2501759601965901e-05, | |
| "loss": 0.1257, | |
| "step": 494500 | |
| }, | |
| { | |
| "epoch": 30.03, | |
| "learning_rate": 1.2494175110733572e-05, | |
| "loss": 0.1209, | |
| "step": 495000 | |
| }, | |
| { | |
| "epoch": 30.06, | |
| "learning_rate": 1.2486590619501244e-05, | |
| "loss": 0.1227, | |
| "step": 495500 | |
| }, | |
| { | |
| "epoch": 30.1, | |
| "learning_rate": 1.2479006128268915e-05, | |
| "loss": 0.1234, | |
| "step": 496000 | |
| }, | |
| { | |
| "epoch": 30.13, | |
| "learning_rate": 1.247142163703659e-05, | |
| "loss": 0.1218, | |
| "step": 496500 | |
| }, | |
| { | |
| "epoch": 30.16, | |
| "learning_rate": 1.2463852314786725e-05, | |
| "loss": 0.1228, | |
| "step": 497000 | |
| }, | |
| { | |
| "epoch": 30.19, | |
| "learning_rate": 1.2456267823554398e-05, | |
| "loss": 0.1226, | |
| "step": 497500 | |
| }, | |
| { | |
| "epoch": 30.22, | |
| "learning_rate": 1.2448683332322069e-05, | |
| "loss": 0.122, | |
| "step": 498000 | |
| }, | |
| { | |
| "epoch": 30.25, | |
| "learning_rate": 1.244109884108974e-05, | |
| "loss": 0.1225, | |
| "step": 498500 | |
| }, | |
| { | |
| "epoch": 30.28, | |
| "learning_rate": 1.2433514349857412e-05, | |
| "loss": 0.1223, | |
| "step": 499000 | |
| }, | |
| { | |
| "epoch": 30.31, | |
| "learning_rate": 1.2425945027607549e-05, | |
| "loss": 0.1232, | |
| "step": 499500 | |
| }, | |
| { | |
| "epoch": 30.34, | |
| "learning_rate": 1.241836053637522e-05, | |
| "loss": 0.1228, | |
| "step": 500000 | |
| }, | |
| { | |
| "epoch": 30.37, | |
| "learning_rate": 1.2410776045142895e-05, | |
| "loss": 0.1199, | |
| "step": 500500 | |
| }, | |
| { | |
| "epoch": 30.4, | |
| "learning_rate": 1.2403191553910566e-05, | |
| "loss": 0.1235, | |
| "step": 501000 | |
| }, | |
| { | |
| "epoch": 30.43, | |
| "learning_rate": 1.2395607062678237e-05, | |
| "loss": 0.1229, | |
| "step": 501500 | |
| }, | |
| { | |
| "epoch": 30.46, | |
| "learning_rate": 1.2388037740428374e-05, | |
| "loss": 0.1222, | |
| "step": 502000 | |
| }, | |
| { | |
| "epoch": 30.49, | |
| "learning_rate": 1.2380453249196045e-05, | |
| "loss": 0.121, | |
| "step": 502500 | |
| }, | |
| { | |
| "epoch": 30.52, | |
| "learning_rate": 1.2372868757963717e-05, | |
| "loss": 0.1235, | |
| "step": 503000 | |
| }, | |
| { | |
| "epoch": 30.55, | |
| "learning_rate": 1.2365284266731388e-05, | |
| "loss": 0.1218, | |
| "step": 503500 | |
| }, | |
| { | |
| "epoch": 30.58, | |
| "learning_rate": 1.235769977549906e-05, | |
| "loss": 0.1248, | |
| "step": 504000 | |
| }, | |
| { | |
| "epoch": 30.61, | |
| "learning_rate": 1.2350115284266732e-05, | |
| "loss": 0.1224, | |
| "step": 504500 | |
| }, | |
| { | |
| "epoch": 30.64, | |
| "learning_rate": 1.2342530793034403e-05, | |
| "loss": 0.1252, | |
| "step": 505000 | |
| }, | |
| { | |
| "epoch": 30.67, | |
| "learning_rate": 1.233496147078454e-05, | |
| "loss": 0.122, | |
| "step": 505500 | |
| }, | |
| { | |
| "epoch": 30.7, | |
| "learning_rate": 1.2327376979552212e-05, | |
| "loss": 0.1234, | |
| "step": 506000 | |
| }, | |
| { | |
| "epoch": 30.73, | |
| "learning_rate": 1.2319792488319885e-05, | |
| "loss": 0.1215, | |
| "step": 506500 | |
| }, | |
| { | |
| "epoch": 30.76, | |
| "learning_rate": 1.2312207997087558e-05, | |
| "loss": 0.1224, | |
| "step": 507000 | |
| }, | |
| { | |
| "epoch": 30.79, | |
| "learning_rate": 1.2304623505855229e-05, | |
| "loss": 0.1232, | |
| "step": 507500 | |
| }, | |
| { | |
| "epoch": 30.82, | |
| "learning_rate": 1.22970390146229e-05, | |
| "loss": 0.1266, | |
| "step": 508000 | |
| }, | |
| { | |
| "epoch": 30.85, | |
| "learning_rate": 1.2289454523390571e-05, | |
| "loss": 0.1274, | |
| "step": 508500 | |
| }, | |
| { | |
| "epoch": 30.88, | |
| "learning_rate": 1.2281870032158243e-05, | |
| "loss": 0.1242, | |
| "step": 509000 | |
| }, | |
| { | |
| "epoch": 30.91, | |
| "learning_rate": 1.227430070990838e-05, | |
| "loss": 0.1242, | |
| "step": 509500 | |
| }, | |
| { | |
| "epoch": 30.94, | |
| "learning_rate": 1.2266716218676051e-05, | |
| "loss": 0.1241, | |
| "step": 510000 | |
| }, | |
| { | |
| "epoch": 30.98, | |
| "learning_rate": 1.2259131727443725e-05, | |
| "loss": 0.1241, | |
| "step": 510500 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_bleu": 81.1058, | |
| "eval_gen_len": 14.1131, | |
| "eval_loss": 0.16349713504314423, | |
| "eval_runtime": 179.2239, | |
| "eval_samples_per_second": 89.966, | |
| "eval_steps_per_second": 2.812, | |
| "step": 510911 | |
| }, | |
| { | |
| "epoch": 31.01, | |
| "learning_rate": 1.2251547236211397e-05, | |
| "loss": 0.1198, | |
| "step": 511000 | |
| }, | |
| { | |
| "epoch": 31.04, | |
| "learning_rate": 1.2243962744979068e-05, | |
| "loss": 0.1203, | |
| "step": 511500 | |
| }, | |
| { | |
| "epoch": 31.07, | |
| "learning_rate": 1.223637825374674e-05, | |
| "loss": 0.1183, | |
| "step": 512000 | |
| }, | |
| { | |
| "epoch": 31.1, | |
| "learning_rate": 1.2228808931496876e-05, | |
| "loss": 0.119, | |
| "step": 512500 | |
| }, | |
| { | |
| "epoch": 31.13, | |
| "learning_rate": 1.2221224440264548e-05, | |
| "loss": 0.1191, | |
| "step": 513000 | |
| }, | |
| { | |
| "epoch": 31.16, | |
| "learning_rate": 1.2213655118014685e-05, | |
| "loss": 0.12, | |
| "step": 513500 | |
| }, | |
| { | |
| "epoch": 31.19, | |
| "learning_rate": 1.2206070626782356e-05, | |
| "loss": 0.1192, | |
| "step": 514000 | |
| }, | |
| { | |
| "epoch": 31.22, | |
| "learning_rate": 1.2198486135550027e-05, | |
| "loss": 0.1182, | |
| "step": 514500 | |
| }, | |
| { | |
| "epoch": 31.25, | |
| "learning_rate": 1.21909016443177e-05, | |
| "loss": 0.1197, | |
| "step": 515000 | |
| }, | |
| { | |
| "epoch": 31.28, | |
| "learning_rate": 1.2183317153085373e-05, | |
| "loss": 0.1194, | |
| "step": 515500 | |
| }, | |
| { | |
| "epoch": 31.31, | |
| "learning_rate": 1.2175732661853044e-05, | |
| "loss": 0.1199, | |
| "step": 516000 | |
| }, | |
| { | |
| "epoch": 31.34, | |
| "learning_rate": 1.2168148170620716e-05, | |
| "loss": 0.1215, | |
| "step": 516500 | |
| }, | |
| { | |
| "epoch": 31.37, | |
| "learning_rate": 1.2160563679388388e-05, | |
| "loss": 0.1226, | |
| "step": 517000 | |
| }, | |
| { | |
| "epoch": 31.4, | |
| "learning_rate": 1.215297918815606e-05, | |
| "loss": 0.1214, | |
| "step": 517500 | |
| }, | |
| { | |
| "epoch": 31.43, | |
| "learning_rate": 1.2145409865906197e-05, | |
| "loss": 0.1203, | |
| "step": 518000 | |
| }, | |
| { | |
| "epoch": 31.46, | |
| "learning_rate": 1.2137825374673868e-05, | |
| "loss": 0.1202, | |
| "step": 518500 | |
| }, | |
| { | |
| "epoch": 31.49, | |
| "learning_rate": 1.213024088344154e-05, | |
| "loss": 0.1209, | |
| "step": 519000 | |
| }, | |
| { | |
| "epoch": 31.52, | |
| "learning_rate": 1.212265639220921e-05, | |
| "loss": 0.1223, | |
| "step": 519500 | |
| }, | |
| { | |
| "epoch": 31.55, | |
| "learning_rate": 1.2115071900976882e-05, | |
| "loss": 0.1221, | |
| "step": 520000 | |
| }, | |
| { | |
| "epoch": 31.58, | |
| "learning_rate": 1.2107487409744556e-05, | |
| "loss": 0.1204, | |
| "step": 520500 | |
| }, | |
| { | |
| "epoch": 31.61, | |
| "learning_rate": 1.2099902918512228e-05, | |
| "loss": 0.1206, | |
| "step": 521000 | |
| }, | |
| { | |
| "epoch": 31.64, | |
| "learning_rate": 1.2092318427279899e-05, | |
| "loss": 0.1194, | |
| "step": 521500 | |
| }, | |
| { | |
| "epoch": 31.67, | |
| "learning_rate": 1.2084749105030036e-05, | |
| "loss": 0.1212, | |
| "step": 522000 | |
| }, | |
| { | |
| "epoch": 31.7, | |
| "learning_rate": 1.2077164613797707e-05, | |
| "loss": 0.1207, | |
| "step": 522500 | |
| }, | |
| { | |
| "epoch": 31.73, | |
| "learning_rate": 1.2069580122565379e-05, | |
| "loss": 0.1173, | |
| "step": 523000 | |
| }, | |
| { | |
| "epoch": 31.76, | |
| "learning_rate": 1.2062010800315516e-05, | |
| "loss": 0.1198, | |
| "step": 523500 | |
| }, | |
| { | |
| "epoch": 31.79, | |
| "learning_rate": 1.2054426309083187e-05, | |
| "loss": 0.1219, | |
| "step": 524000 | |
| }, | |
| { | |
| "epoch": 31.82, | |
| "learning_rate": 1.204684181785086e-05, | |
| "loss": 0.122, | |
| "step": 524500 | |
| }, | |
| { | |
| "epoch": 31.85, | |
| "learning_rate": 1.2039257326618533e-05, | |
| "loss": 0.1208, | |
| "step": 525000 | |
| }, | |
| { | |
| "epoch": 31.89, | |
| "learning_rate": 1.2031672835386204e-05, | |
| "loss": 0.1227, | |
| "step": 525500 | |
| }, | |
| { | |
| "epoch": 31.92, | |
| "learning_rate": 1.2024088344153875e-05, | |
| "loss": 0.1218, | |
| "step": 526000 | |
| }, | |
| { | |
| "epoch": 31.95, | |
| "learning_rate": 1.2016503852921546e-05, | |
| "loss": 0.1238, | |
| "step": 526500 | |
| }, | |
| { | |
| "epoch": 31.98, | |
| "learning_rate": 1.2008934530671684e-05, | |
| "loss": 0.1233, | |
| "step": 527000 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_bleu": 81.231, | |
| "eval_gen_len": 14.1063, | |
| "eval_loss": 0.162692591547966, | |
| "eval_runtime": 178.4186, | |
| "eval_samples_per_second": 90.372, | |
| "eval_steps_per_second": 2.825, | |
| "step": 527392 | |
| }, | |
| { | |
| "epoch": 32.01, | |
| "learning_rate": 1.2001350039439355e-05, | |
| "loss": 0.1201, | |
| "step": 527500 | |
| }, | |
| { | |
| "epoch": 32.04, | |
| "learning_rate": 1.1993765548207028e-05, | |
| "loss": 0.1185, | |
| "step": 528000 | |
| }, | |
| { | |
| "epoch": 32.07, | |
| "learning_rate": 1.1986181056974699e-05, | |
| "loss": 0.1199, | |
| "step": 528500 | |
| }, | |
| { | |
| "epoch": 32.1, | |
| "learning_rate": 1.197859656574237e-05, | |
| "loss": 0.1172, | |
| "step": 529000 | |
| }, | |
| { | |
| "epoch": 32.13, | |
| "learning_rate": 1.1971012074510042e-05, | |
| "loss": 0.117, | |
| "step": 529500 | |
| }, | |
| { | |
| "epoch": 32.16, | |
| "learning_rate": 1.1963427583277716e-05, | |
| "loss": 0.121, | |
| "step": 530000 | |
| }, | |
| { | |
| "epoch": 32.19, | |
| "learning_rate": 1.1955843092045387e-05, | |
| "loss": 0.1139, | |
| "step": 530500 | |
| }, | |
| { | |
| "epoch": 32.22, | |
| "learning_rate": 1.1948273769795523e-05, | |
| "loss": 0.1178, | |
| "step": 531000 | |
| }, | |
| { | |
| "epoch": 32.25, | |
| "learning_rate": 1.1940689278563196e-05, | |
| "loss": 0.118, | |
| "step": 531500 | |
| }, | |
| { | |
| "epoch": 32.28, | |
| "learning_rate": 1.1933104787330867e-05, | |
| "loss": 0.1152, | |
| "step": 532000 | |
| }, | |
| { | |
| "epoch": 32.31, | |
| "learning_rate": 1.1925520296098538e-05, | |
| "loss": 0.1178, | |
| "step": 532500 | |
| }, | |
| { | |
| "epoch": 32.34, | |
| "learning_rate": 1.191793580486621e-05, | |
| "loss": 0.119, | |
| "step": 533000 | |
| }, | |
| { | |
| "epoch": 32.37, | |
| "learning_rate": 1.1910366482616347e-05, | |
| "loss": 0.1164, | |
| "step": 533500 | |
| }, | |
| { | |
| "epoch": 32.4, | |
| "learning_rate": 1.1902781991384018e-05, | |
| "loss": 0.1202, | |
| "step": 534000 | |
| }, | |
| { | |
| "epoch": 32.43, | |
| "learning_rate": 1.1895197500151692e-05, | |
| "loss": 0.1187, | |
| "step": 534500 | |
| }, | |
| { | |
| "epoch": 32.46, | |
| "learning_rate": 1.1887613008919364e-05, | |
| "loss": 0.1176, | |
| "step": 535000 | |
| }, | |
| { | |
| "epoch": 32.49, | |
| "learning_rate": 1.1880028517687035e-05, | |
| "loss": 0.1178, | |
| "step": 535500 | |
| }, | |
| { | |
| "epoch": 32.52, | |
| "learning_rate": 1.1872444026454706e-05, | |
| "loss": 0.1192, | |
| "step": 536000 | |
| }, | |
| { | |
| "epoch": 32.55, | |
| "learning_rate": 1.1864874704204843e-05, | |
| "loss": 0.1172, | |
| "step": 536500 | |
| }, | |
| { | |
| "epoch": 32.58, | |
| "learning_rate": 1.1857290212972515e-05, | |
| "loss": 0.1203, | |
| "step": 537000 | |
| }, | |
| { | |
| "epoch": 32.61, | |
| "learning_rate": 1.1849705721740186e-05, | |
| "loss": 0.1174, | |
| "step": 537500 | |
| }, | |
| { | |
| "epoch": 32.64, | |
| "learning_rate": 1.1842121230507859e-05, | |
| "loss": 0.1171, | |
| "step": 538000 | |
| }, | |
| { | |
| "epoch": 32.67, | |
| "learning_rate": 1.183453673927553e-05, | |
| "loss": 0.1174, | |
| "step": 538500 | |
| }, | |
| { | |
| "epoch": 32.7, | |
| "learning_rate": 1.1826967417025667e-05, | |
| "loss": 0.1196, | |
| "step": 539000 | |
| }, | |
| { | |
| "epoch": 32.73, | |
| "learning_rate": 1.1819382925793338e-05, | |
| "loss": 0.1188, | |
| "step": 539500 | |
| }, | |
| { | |
| "epoch": 32.77, | |
| "learning_rate": 1.181179843456101e-05, | |
| "loss": 0.1184, | |
| "step": 540000 | |
| }, | |
| { | |
| "epoch": 32.8, | |
| "learning_rate": 1.1804213943328683e-05, | |
| "loss": 0.1192, | |
| "step": 540500 | |
| }, | |
| { | |
| "epoch": 32.83, | |
| "learning_rate": 1.1796629452096355e-05, | |
| "loss": 0.118, | |
| "step": 541000 | |
| }, | |
| { | |
| "epoch": 32.86, | |
| "learning_rate": 1.1789044960864027e-05, | |
| "loss": 0.1175, | |
| "step": 541500 | |
| }, | |
| { | |
| "epoch": 32.89, | |
| "learning_rate": 1.1781475638614164e-05, | |
| "loss": 0.1195, | |
| "step": 542000 | |
| }, | |
| { | |
| "epoch": 32.92, | |
| "learning_rate": 1.1773891147381835e-05, | |
| "loss": 0.1181, | |
| "step": 542500 | |
| }, | |
| { | |
| "epoch": 32.95, | |
| "learning_rate": 1.1766306656149506e-05, | |
| "loss": 0.1188, | |
| "step": 543000 | |
| }, | |
| { | |
| "epoch": 32.98, | |
| "learning_rate": 1.1758737333899643e-05, | |
| "loss": 0.1206, | |
| "step": 543500 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_bleu": 81.2442, | |
| "eval_gen_len": 14.0953, | |
| "eval_loss": 0.16174831986427307, | |
| "eval_runtime": 179.0701, | |
| "eval_samples_per_second": 90.043, | |
| "eval_steps_per_second": 2.815, | |
| "step": 543873 | |
| }, | |
| { | |
| "epoch": 33.01, | |
| "learning_rate": 1.1751152842667315e-05, | |
| "loss": 0.119, | |
| "step": 544000 | |
| }, | |
| { | |
| "epoch": 33.04, | |
| "learning_rate": 1.1743568351434986e-05, | |
| "loss": 0.1132, | |
| "step": 544500 | |
| }, | |
| { | |
| "epoch": 33.07, | |
| "learning_rate": 1.1735983860202657e-05, | |
| "loss": 0.1148, | |
| "step": 545000 | |
| }, | |
| { | |
| "epoch": 33.1, | |
| "learning_rate": 1.1728399368970332e-05, | |
| "loss": 0.1156, | |
| "step": 545500 | |
| }, | |
| { | |
| "epoch": 33.13, | |
| "learning_rate": 1.1720814877738003e-05, | |
| "loss": 0.1142, | |
| "step": 546000 | |
| }, | |
| { | |
| "epoch": 33.16, | |
| "learning_rate": 1.171324555548814e-05, | |
| "loss": 0.1159, | |
| "step": 546500 | |
| }, | |
| { | |
| "epoch": 33.19, | |
| "learning_rate": 1.1705661064255811e-05, | |
| "loss": 0.1154, | |
| "step": 547000 | |
| }, | |
| { | |
| "epoch": 33.22, | |
| "learning_rate": 1.1698076573023483e-05, | |
| "loss": 0.1159, | |
| "step": 547500 | |
| }, | |
| { | |
| "epoch": 33.25, | |
| "learning_rate": 1.1690492081791154e-05, | |
| "loss": 0.1155, | |
| "step": 548000 | |
| }, | |
| { | |
| "epoch": 33.28, | |
| "learning_rate": 1.1682907590558825e-05, | |
| "loss": 0.115, | |
| "step": 548500 | |
| }, | |
| { | |
| "epoch": 33.31, | |
| "learning_rate": 1.1675338268308962e-05, | |
| "loss": 0.116, | |
| "step": 549000 | |
| }, | |
| { | |
| "epoch": 33.34, | |
| "learning_rate": 1.1667753777076633e-05, | |
| "loss": 0.117, | |
| "step": 549500 | |
| }, | |
| { | |
| "epoch": 33.37, | |
| "learning_rate": 1.166018445482677e-05, | |
| "loss": 0.1171, | |
| "step": 550000 | |
| }, | |
| { | |
| "epoch": 33.4, | |
| "learning_rate": 1.1652599963594442e-05, | |
| "loss": 0.1201, | |
| "step": 550500 | |
| }, | |
| { | |
| "epoch": 33.43, | |
| "learning_rate": 1.1645015472362116e-05, | |
| "loss": 0.1169, | |
| "step": 551000 | |
| }, | |
| { | |
| "epoch": 33.46, | |
| "learning_rate": 1.1637430981129788e-05, | |
| "loss": 0.1157, | |
| "step": 551500 | |
| }, | |
| { | |
| "epoch": 33.49, | |
| "learning_rate": 1.1629846489897459e-05, | |
| "loss": 0.1159, | |
| "step": 552000 | |
| }, | |
| { | |
| "epoch": 33.52, | |
| "learning_rate": 1.162226199866513e-05, | |
| "loss": 0.1144, | |
| "step": 552500 | |
| }, | |
| { | |
| "epoch": 33.55, | |
| "learning_rate": 1.1614677507432803e-05, | |
| "loss": 0.1186, | |
| "step": 553000 | |
| }, | |
| { | |
| "epoch": 33.58, | |
| "learning_rate": 1.1607093016200474e-05, | |
| "loss": 0.1142, | |
| "step": 553500 | |
| }, | |
| { | |
| "epoch": 33.61, | |
| "learning_rate": 1.1599508524968146e-05, | |
| "loss": 0.1179, | |
| "step": 554000 | |
| }, | |
| { | |
| "epoch": 33.64, | |
| "learning_rate": 1.1591924033735817e-05, | |
| "loss": 0.119, | |
| "step": 554500 | |
| }, | |
| { | |
| "epoch": 33.68, | |
| "learning_rate": 1.1584339542503488e-05, | |
| "loss": 0.1173, | |
| "step": 555000 | |
| }, | |
| { | |
| "epoch": 33.71, | |
| "learning_rate": 1.1576755051271163e-05, | |
| "loss": 0.1205, | |
| "step": 555500 | |
| }, | |
| { | |
| "epoch": 33.74, | |
| "learning_rate": 1.1569170560038834e-05, | |
| "loss": 0.1139, | |
| "step": 556000 | |
| }, | |
| { | |
| "epoch": 33.77, | |
| "learning_rate": 1.1561601237788971e-05, | |
| "loss": 0.119, | |
| "step": 556500 | |
| }, | |
| { | |
| "epoch": 33.8, | |
| "learning_rate": 1.1554016746556642e-05, | |
| "loss": 0.1156, | |
| "step": 557000 | |
| }, | |
| { | |
| "epoch": 33.83, | |
| "learning_rate": 1.1546432255324314e-05, | |
| "loss": 0.1152, | |
| "step": 557500 | |
| }, | |
| { | |
| "epoch": 33.86, | |
| "learning_rate": 1.1538847764091985e-05, | |
| "loss": 0.1155, | |
| "step": 558000 | |
| }, | |
| { | |
| "epoch": 33.89, | |
| "learning_rate": 1.1531263272859658e-05, | |
| "loss": 0.1154, | |
| "step": 558500 | |
| }, | |
| { | |
| "epoch": 33.92, | |
| "learning_rate": 1.152367878162733e-05, | |
| "loss": 0.1155, | |
| "step": 559000 | |
| }, | |
| { | |
| "epoch": 33.95, | |
| "learning_rate": 1.1516094290395002e-05, | |
| "loss": 0.117, | |
| "step": 559500 | |
| }, | |
| { | |
| "epoch": 33.98, | |
| "learning_rate": 1.1508509799162673e-05, | |
| "loss": 0.1184, | |
| "step": 560000 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_bleu": 81.2715, | |
| "eval_gen_len": 14.1176, | |
| "eval_loss": 0.16308197379112244, | |
| "eval_runtime": 178.7834, | |
| "eval_samples_per_second": 90.187, | |
| "eval_steps_per_second": 2.819, | |
| "step": 560354 | |
| }, | |
| { | |
| "epoch": 34.01, | |
| "learning_rate": 1.1500955645895276e-05, | |
| "loss": 0.1148, | |
| "step": 560500 | |
| }, | |
| { | |
| "epoch": 34.04, | |
| "learning_rate": 1.149338632364541e-05, | |
| "loss": 0.1118, | |
| "step": 561000 | |
| }, | |
| { | |
| "epoch": 34.07, | |
| "learning_rate": 1.1485801832413084e-05, | |
| "loss": 0.1116, | |
| "step": 561500 | |
| }, | |
| { | |
| "epoch": 34.1, | |
| "learning_rate": 1.1478217341180756e-05, | |
| "loss": 0.1146, | |
| "step": 562000 | |
| }, | |
| { | |
| "epoch": 34.13, | |
| "learning_rate": 1.1470632849948427e-05, | |
| "loss": 0.113, | |
| "step": 562500 | |
| }, | |
| { | |
| "epoch": 34.16, | |
| "learning_rate": 1.1463048358716098e-05, | |
| "loss": 0.1133, | |
| "step": 563000 | |
| }, | |
| { | |
| "epoch": 34.19, | |
| "learning_rate": 1.145546386748377e-05, | |
| "loss": 0.1118, | |
| "step": 563500 | |
| }, | |
| { | |
| "epoch": 34.22, | |
| "learning_rate": 1.1447879376251442e-05, | |
| "loss": 0.1151, | |
| "step": 564000 | |
| }, | |
| { | |
| "epoch": 34.25, | |
| "learning_rate": 1.1440294885019114e-05, | |
| "loss": 0.1117, | |
| "step": 564500 | |
| }, | |
| { | |
| "epoch": 34.28, | |
| "learning_rate": 1.1432710393786785e-05, | |
| "loss": 0.1139, | |
| "step": 565000 | |
| }, | |
| { | |
| "epoch": 34.31, | |
| "learning_rate": 1.1425141071536922e-05, | |
| "loss": 0.1156, | |
| "step": 565500 | |
| }, | |
| { | |
| "epoch": 34.34, | |
| "learning_rate": 1.1417556580304593e-05, | |
| "loss": 0.1155, | |
| "step": 566000 | |
| }, | |
| { | |
| "epoch": 34.37, | |
| "learning_rate": 1.1409972089072266e-05, | |
| "loss": 0.1167, | |
| "step": 566500 | |
| }, | |
| { | |
| "epoch": 34.4, | |
| "learning_rate": 1.1402402766822402e-05, | |
| "loss": 0.1116, | |
| "step": 567000 | |
| }, | |
| { | |
| "epoch": 34.43, | |
| "learning_rate": 1.1394818275590075e-05, | |
| "loss": 0.1132, | |
| "step": 567500 | |
| }, | |
| { | |
| "epoch": 34.46, | |
| "learning_rate": 1.1387233784357746e-05, | |
| "loss": 0.1146, | |
| "step": 568000 | |
| }, | |
| { | |
| "epoch": 34.49, | |
| "learning_rate": 1.1379649293125419e-05, | |
| "loss": 0.1144, | |
| "step": 568500 | |
| }, | |
| { | |
| "epoch": 34.52, | |
| "learning_rate": 1.137206480189309e-05, | |
| "loss": 0.1155, | |
| "step": 569000 | |
| }, | |
| { | |
| "epoch": 34.55, | |
| "learning_rate": 1.1364480310660761e-05, | |
| "loss": 0.1173, | |
| "step": 569500 | |
| }, | |
| { | |
| "epoch": 34.59, | |
| "learning_rate": 1.1356910988410898e-05, | |
| "loss": 0.112, | |
| "step": 570000 | |
| }, | |
| { | |
| "epoch": 34.62, | |
| "learning_rate": 1.134932649717857e-05, | |
| "loss": 0.114, | |
| "step": 570500 | |
| }, | |
| { | |
| "epoch": 34.65, | |
| "learning_rate": 1.134174200594624e-05, | |
| "loss": 0.1137, | |
| "step": 571000 | |
| }, | |
| { | |
| "epoch": 34.68, | |
| "learning_rate": 1.1334157514713915e-05, | |
| "loss": 0.1157, | |
| "step": 571500 | |
| }, | |
| { | |
| "epoch": 34.71, | |
| "learning_rate": 1.1326573023481587e-05, | |
| "loss": 0.1154, | |
| "step": 572000 | |
| }, | |
| { | |
| "epoch": 34.74, | |
| "learning_rate": 1.1318988532249258e-05, | |
| "loss": 0.1176, | |
| "step": 572500 | |
| }, | |
| { | |
| "epoch": 34.77, | |
| "learning_rate": 1.1311419209999395e-05, | |
| "loss": 0.1134, | |
| "step": 573000 | |
| }, | |
| { | |
| "epoch": 34.8, | |
| "learning_rate": 1.1303834718767066e-05, | |
| "loss": 0.1145, | |
| "step": 573500 | |
| }, | |
| { | |
| "epoch": 34.83, | |
| "learning_rate": 1.1296250227534738e-05, | |
| "loss": 0.1155, | |
| "step": 574000 | |
| }, | |
| { | |
| "epoch": 34.86, | |
| "learning_rate": 1.1288665736302409e-05, | |
| "loss": 0.1136, | |
| "step": 574500 | |
| }, | |
| { | |
| "epoch": 34.89, | |
| "learning_rate": 1.1281081245070082e-05, | |
| "loss": 0.1147, | |
| "step": 575000 | |
| }, | |
| { | |
| "epoch": 34.92, | |
| "learning_rate": 1.1273496753837753e-05, | |
| "loss": 0.1145, | |
| "step": 575500 | |
| }, | |
| { | |
| "epoch": 34.95, | |
| "learning_rate": 1.1265912262605426e-05, | |
| "loss": 0.1143, | |
| "step": 576000 | |
| }, | |
| { | |
| "epoch": 34.98, | |
| "learning_rate": 1.1258327771373097e-05, | |
| "loss": 0.1148, | |
| "step": 576500 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_bleu": 81.1501, | |
| "eval_gen_len": 14.0923, | |
| "eval_loss": 0.16266627609729767, | |
| "eval_runtime": 177.3751, | |
| "eval_samples_per_second": 90.903, | |
| "eval_steps_per_second": 2.841, | |
| "step": 576835 | |
| }, | |
| { | |
| "epoch": 35.01, | |
| "learning_rate": 1.125074328014077e-05, | |
| "loss": 0.1122, | |
| "step": 577000 | |
| }, | |
| { | |
| "epoch": 35.04, | |
| "learning_rate": 1.1243158788908441e-05, | |
| "loss": 0.1116, | |
| "step": 577500 | |
| }, | |
| { | |
| "epoch": 35.07, | |
| "learning_rate": 1.1235589466658578e-05, | |
| "loss": 0.1094, | |
| "step": 578000 | |
| }, | |
| { | |
| "epoch": 35.1, | |
| "learning_rate": 1.122800497542625e-05, | |
| "loss": 0.1106, | |
| "step": 578500 | |
| }, | |
| { | |
| "epoch": 35.13, | |
| "learning_rate": 1.1220435653176387e-05, | |
| "loss": 0.111, | |
| "step": 579000 | |
| }, | |
| { | |
| "epoch": 35.16, | |
| "learning_rate": 1.1212851161944058e-05, | |
| "loss": 0.1108, | |
| "step": 579500 | |
| }, | |
| { | |
| "epoch": 35.19, | |
| "learning_rate": 1.120526667071173e-05, | |
| "loss": 0.1088, | |
| "step": 580000 | |
| }, | |
| { | |
| "epoch": 35.22, | |
| "learning_rate": 1.11976821794794e-05, | |
| "loss": 0.1136, | |
| "step": 580500 | |
| }, | |
| { | |
| "epoch": 35.25, | |
| "learning_rate": 1.1190097688247072e-05, | |
| "loss": 0.1108, | |
| "step": 581000 | |
| }, | |
| { | |
| "epoch": 35.28, | |
| "learning_rate": 1.1182513197014746e-05, | |
| "loss": 0.1117, | |
| "step": 581500 | |
| }, | |
| { | |
| "epoch": 35.31, | |
| "learning_rate": 1.1174928705782418e-05, | |
| "loss": 0.1126, | |
| "step": 582000 | |
| }, | |
| { | |
| "epoch": 35.34, | |
| "learning_rate": 1.1167344214550089e-05, | |
| "loss": 0.1119, | |
| "step": 582500 | |
| }, | |
| { | |
| "epoch": 35.37, | |
| "learning_rate": 1.115975972331776e-05, | |
| "loss": 0.1165, | |
| "step": 583000 | |
| }, | |
| { | |
| "epoch": 35.4, | |
| "learning_rate": 1.1152205570050363e-05, | |
| "loss": 0.1123, | |
| "step": 583500 | |
| }, | |
| { | |
| "epoch": 35.43, | |
| "learning_rate": 1.1144621078818034e-05, | |
| "loss": 0.1094, | |
| "step": 584000 | |
| }, | |
| { | |
| "epoch": 35.47, | |
| "learning_rate": 1.1137036587585706e-05, | |
| "loss": 0.1129, | |
| "step": 584500 | |
| }, | |
| { | |
| "epoch": 35.5, | |
| "learning_rate": 1.1129452096353377e-05, | |
| "loss": 0.1117, | |
| "step": 585000 | |
| }, | |
| { | |
| "epoch": 35.53, | |
| "learning_rate": 1.1121867605121048e-05, | |
| "loss": 0.1128, | |
| "step": 585500 | |
| }, | |
| { | |
| "epoch": 35.56, | |
| "learning_rate": 1.1114283113888723e-05, | |
| "loss": 0.1143, | |
| "step": 586000 | |
| }, | |
| { | |
| "epoch": 35.59, | |
| "learning_rate": 1.1106698622656394e-05, | |
| "loss": 0.111, | |
| "step": 586500 | |
| }, | |
| { | |
| "epoch": 35.62, | |
| "learning_rate": 1.1099114131424065e-05, | |
| "loss": 0.1139, | |
| "step": 587000 | |
| }, | |
| { | |
| "epoch": 35.65, | |
| "learning_rate": 1.1091529640191736e-05, | |
| "loss": 0.1128, | |
| "step": 587500 | |
| }, | |
| { | |
| "epoch": 35.68, | |
| "learning_rate": 1.108394514895941e-05, | |
| "loss": 0.1109, | |
| "step": 588000 | |
| }, | |
| { | |
| "epoch": 35.71, | |
| "learning_rate": 1.107636065772708e-05, | |
| "loss": 0.1126, | |
| "step": 588500 | |
| }, | |
| { | |
| "epoch": 35.74, | |
| "learning_rate": 1.1068791335477218e-05, | |
| "loss": 0.1118, | |
| "step": 589000 | |
| }, | |
| { | |
| "epoch": 35.77, | |
| "learning_rate": 1.1061206844244889e-05, | |
| "loss": 0.1145, | |
| "step": 589500 | |
| }, | |
| { | |
| "epoch": 35.8, | |
| "learning_rate": 1.105362235301256e-05, | |
| "loss": 0.1114, | |
| "step": 590000 | |
| }, | |
| { | |
| "epoch": 35.83, | |
| "learning_rate": 1.1046037861780231e-05, | |
| "loss": 0.1086, | |
| "step": 590500 | |
| }, | |
| { | |
| "epoch": 35.86, | |
| "learning_rate": 1.1038453370547903e-05, | |
| "loss": 0.1159, | |
| "step": 591000 | |
| }, | |
| { | |
| "epoch": 35.89, | |
| "learning_rate": 1.1030868879315577e-05, | |
| "loss": 0.114, | |
| "step": 591500 | |
| }, | |
| { | |
| "epoch": 35.92, | |
| "learning_rate": 1.1023284388083249e-05, | |
| "loss": 0.1137, | |
| "step": 592000 | |
| }, | |
| { | |
| "epoch": 35.95, | |
| "learning_rate": 1.1015715065833386e-05, | |
| "loss": 0.11, | |
| "step": 592500 | |
| }, | |
| { | |
| "epoch": 35.98, | |
| "learning_rate": 1.1008130574601057e-05, | |
| "loss": 0.1132, | |
| "step": 593000 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_bleu": 81.3267, | |
| "eval_gen_len": 14.11, | |
| "eval_loss": 0.16219820082187653, | |
| "eval_runtime": 176.9165, | |
| "eval_samples_per_second": 91.139, | |
| "eval_steps_per_second": 2.849, | |
| "step": 593316 | |
| }, | |
| { | |
| "epoch": 36.01, | |
| "learning_rate": 1.1000546083368728e-05, | |
| "loss": 0.1134, | |
| "step": 593500 | |
| }, | |
| { | |
| "epoch": 36.04, | |
| "learning_rate": 1.09929615921364e-05, | |
| "loss": 0.1088, | |
| "step": 594000 | |
| }, | |
| { | |
| "epoch": 36.07, | |
| "learning_rate": 1.0985377100904074e-05, | |
| "loss": 0.1086, | |
| "step": 594500 | |
| }, | |
| { | |
| "epoch": 36.1, | |
| "learning_rate": 1.0977792609671745e-05, | |
| "loss": 0.1081, | |
| "step": 595000 | |
| }, | |
| { | |
| "epoch": 36.13, | |
| "learning_rate": 1.0970223287421882e-05, | |
| "loss": 0.11, | |
| "step": 595500 | |
| }, | |
| { | |
| "epoch": 36.16, | |
| "learning_rate": 1.0962638796189554e-05, | |
| "loss": 0.1076, | |
| "step": 596000 | |
| }, | |
| { | |
| "epoch": 36.19, | |
| "learning_rate": 1.0955054304957225e-05, | |
| "loss": 0.1124, | |
| "step": 596500 | |
| }, | |
| { | |
| "epoch": 36.22, | |
| "learning_rate": 1.0947469813724896e-05, | |
| "loss": 0.1113, | |
| "step": 597000 | |
| }, | |
| { | |
| "epoch": 36.25, | |
| "learning_rate": 1.0939885322492567e-05, | |
| "loss": 0.11, | |
| "step": 597500 | |
| }, | |
| { | |
| "epoch": 36.28, | |
| "learning_rate": 1.093230083126024e-05, | |
| "loss": 0.1116, | |
| "step": 598000 | |
| }, | |
| { | |
| "epoch": 36.31, | |
| "learning_rate": 1.0924716340027912e-05, | |
| "loss": 0.1089, | |
| "step": 598500 | |
| }, | |
| { | |
| "epoch": 36.34, | |
| "learning_rate": 1.0917147017778049e-05, | |
| "loss": 0.1083, | |
| "step": 599000 | |
| }, | |
| { | |
| "epoch": 36.38, | |
| "learning_rate": 1.090956252654572e-05, | |
| "loss": 0.1105, | |
| "step": 599500 | |
| }, | |
| { | |
| "epoch": 36.41, | |
| "learning_rate": 1.0901978035313391e-05, | |
| "loss": 0.1121, | |
| "step": 600000 | |
| }, | |
| { | |
| "epoch": 36.44, | |
| "learning_rate": 1.0894393544081064e-05, | |
| "loss": 0.1101, | |
| "step": 600500 | |
| }, | |
| { | |
| "epoch": 36.47, | |
| "learning_rate": 1.0886809052848737e-05, | |
| "loss": 0.1082, | |
| "step": 601000 | |
| }, | |
| { | |
| "epoch": 36.5, | |
| "learning_rate": 1.0879224561616408e-05, | |
| "loss": 0.1109, | |
| "step": 601500 | |
| }, | |
| { | |
| "epoch": 36.53, | |
| "learning_rate": 1.087164007038408e-05, | |
| "loss": 0.1074, | |
| "step": 602000 | |
| }, | |
| { | |
| "epoch": 36.56, | |
| "learning_rate": 1.086405557915175e-05, | |
| "loss": 0.1113, | |
| "step": 602500 | |
| }, | |
| { | |
| "epoch": 36.59, | |
| "learning_rate": 1.0856486256901888e-05, | |
| "loss": 0.1108, | |
| "step": 603000 | |
| }, | |
| { | |
| "epoch": 36.62, | |
| "learning_rate": 1.084890176566956e-05, | |
| "loss": 0.1108, | |
| "step": 603500 | |
| }, | |
| { | |
| "epoch": 36.65, | |
| "learning_rate": 1.084131727443723e-05, | |
| "loss": 0.1084, | |
| "step": 604000 | |
| }, | |
| { | |
| "epoch": 36.68, | |
| "learning_rate": 1.0833732783204905e-05, | |
| "loss": 0.1094, | |
| "step": 604500 | |
| }, | |
| { | |
| "epoch": 36.71, | |
| "learning_rate": 1.0826163460955039e-05, | |
| "loss": 0.1086, | |
| "step": 605000 | |
| }, | |
| { | |
| "epoch": 36.74, | |
| "learning_rate": 1.0818594138705176e-05, | |
| "loss": 0.1101, | |
| "step": 605500 | |
| }, | |
| { | |
| "epoch": 36.77, | |
| "learning_rate": 1.0811009647472847e-05, | |
| "loss": 0.1124, | |
| "step": 606000 | |
| }, | |
| { | |
| "epoch": 36.8, | |
| "learning_rate": 1.0803425156240522e-05, | |
| "loss": 0.1128, | |
| "step": 606500 | |
| }, | |
| { | |
| "epoch": 36.83, | |
| "learning_rate": 1.0795840665008193e-05, | |
| "loss": 0.1106, | |
| "step": 607000 | |
| }, | |
| { | |
| "epoch": 36.86, | |
| "learning_rate": 1.0788256173775864e-05, | |
| "loss": 0.1103, | |
| "step": 607500 | |
| }, | |
| { | |
| "epoch": 36.89, | |
| "learning_rate": 1.0780671682543535e-05, | |
| "loss": 0.1125, | |
| "step": 608000 | |
| }, | |
| { | |
| "epoch": 36.92, | |
| "learning_rate": 1.0773087191311207e-05, | |
| "loss": 0.1079, | |
| "step": 608500 | |
| }, | |
| { | |
| "epoch": 36.95, | |
| "learning_rate": 1.076550270007888e-05, | |
| "loss": 0.1143, | |
| "step": 609000 | |
| }, | |
| { | |
| "epoch": 36.98, | |
| "learning_rate": 1.0757948546811481e-05, | |
| "loss": 0.1133, | |
| "step": 609500 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_bleu": 81.3249, | |
| "eval_gen_len": 14.0937, | |
| "eval_loss": 0.16307313740253448, | |
| "eval_runtime": 177.1538, | |
| "eval_samples_per_second": 91.017, | |
| "eval_steps_per_second": 2.845, | |
| "step": 609797 | |
| }, | |
| { | |
| "epoch": 37.01, | |
| "learning_rate": 1.0750364055579152e-05, | |
| "loss": 0.1098, | |
| "step": 610000 | |
| }, | |
| { | |
| "epoch": 37.04, | |
| "learning_rate": 1.0742779564346823e-05, | |
| "loss": 0.1089, | |
| "step": 610500 | |
| }, | |
| { | |
| "epoch": 37.07, | |
| "learning_rate": 1.0735195073114496e-05, | |
| "loss": 0.1049, | |
| "step": 611000 | |
| }, | |
| { | |
| "epoch": 37.1, | |
| "learning_rate": 1.072761058188217e-05, | |
| "loss": 0.1083, | |
| "step": 611500 | |
| }, | |
| { | |
| "epoch": 37.13, | |
| "learning_rate": 1.072002609064984e-05, | |
| "loss": 0.108, | |
| "step": 612000 | |
| }, | |
| { | |
| "epoch": 37.16, | |
| "learning_rate": 1.0712441599417512e-05, | |
| "loss": 0.1036, | |
| "step": 612500 | |
| }, | |
| { | |
| "epoch": 37.19, | |
| "learning_rate": 1.0704857108185185e-05, | |
| "loss": 0.1112, | |
| "step": 613000 | |
| }, | |
| { | |
| "epoch": 37.22, | |
| "learning_rate": 1.069728778593532e-05, | |
| "loss": 0.107, | |
| "step": 613500 | |
| }, | |
| { | |
| "epoch": 37.26, | |
| "learning_rate": 1.0689703294702993e-05, | |
| "loss": 0.1078, | |
| "step": 614000 | |
| }, | |
| { | |
| "epoch": 37.29, | |
| "learning_rate": 1.0682149141435594e-05, | |
| "loss": 0.1092, | |
| "step": 614500 | |
| }, | |
| { | |
| "epoch": 37.32, | |
| "learning_rate": 1.0674564650203266e-05, | |
| "loss": 0.1054, | |
| "step": 615000 | |
| }, | |
| { | |
| "epoch": 37.35, | |
| "learning_rate": 1.0666980158970937e-05, | |
| "loss": 0.1072, | |
| "step": 615500 | |
| }, | |
| { | |
| "epoch": 37.38, | |
| "learning_rate": 1.0659395667738608e-05, | |
| "loss": 0.1114, | |
| "step": 616000 | |
| }, | |
| { | |
| "epoch": 37.41, | |
| "learning_rate": 1.0651811176506281e-05, | |
| "loss": 0.1099, | |
| "step": 616500 | |
| }, | |
| { | |
| "epoch": 37.44, | |
| "learning_rate": 1.0644226685273952e-05, | |
| "loss": 0.1072, | |
| "step": 617000 | |
| }, | |
| { | |
| "epoch": 37.47, | |
| "learning_rate": 1.0636642194041624e-05, | |
| "loss": 0.1109, | |
| "step": 617500 | |
| }, | |
| { | |
| "epoch": 37.5, | |
| "learning_rate": 1.0629057702809295e-05, | |
| "loss": 0.1071, | |
| "step": 618000 | |
| }, | |
| { | |
| "epoch": 37.53, | |
| "learning_rate": 1.062147321157697e-05, | |
| "loss": 0.111, | |
| "step": 618500 | |
| }, | |
| { | |
| "epoch": 37.56, | |
| "learning_rate": 1.061388872034464e-05, | |
| "loss": 0.1088, | |
| "step": 619000 | |
| }, | |
| { | |
| "epoch": 37.59, | |
| "learning_rate": 1.0606304229112312e-05, | |
| "loss": 0.1097, | |
| "step": 619500 | |
| }, | |
| { | |
| "epoch": 37.62, | |
| "learning_rate": 1.0598719737879983e-05, | |
| "loss": 0.1075, | |
| "step": 620000 | |
| }, | |
| { | |
| "epoch": 37.65, | |
| "learning_rate": 1.059115041563012e-05, | |
| "loss": 0.1083, | |
| "step": 620500 | |
| }, | |
| { | |
| "epoch": 37.68, | |
| "learning_rate": 1.0583565924397791e-05, | |
| "loss": 0.1095, | |
| "step": 621000 | |
| }, | |
| { | |
| "epoch": 37.71, | |
| "learning_rate": 1.0575996602147929e-05, | |
| "loss": 0.1106, | |
| "step": 621500 | |
| }, | |
| { | |
| "epoch": 37.74, | |
| "learning_rate": 1.05684121109156e-05, | |
| "loss": 0.1096, | |
| "step": 622000 | |
| }, | |
| { | |
| "epoch": 37.77, | |
| "learning_rate": 1.0560827619683271e-05, | |
| "loss": 0.1089, | |
| "step": 622500 | |
| }, | |
| { | |
| "epoch": 37.8, | |
| "learning_rate": 1.0553243128450946e-05, | |
| "loss": 0.1091, | |
| "step": 623000 | |
| }, | |
| { | |
| "epoch": 37.83, | |
| "learning_rate": 1.0545658637218617e-05, | |
| "loss": 0.1117, | |
| "step": 623500 | |
| }, | |
| { | |
| "epoch": 37.86, | |
| "learning_rate": 1.0538089314968754e-05, | |
| "loss": 0.1096, | |
| "step": 624000 | |
| }, | |
| { | |
| "epoch": 37.89, | |
| "learning_rate": 1.0530504823736425e-05, | |
| "loss": 0.108, | |
| "step": 624500 | |
| }, | |
| { | |
| "epoch": 37.92, | |
| "learning_rate": 1.0522920332504097e-05, | |
| "loss": 0.1094, | |
| "step": 625000 | |
| }, | |
| { | |
| "epoch": 37.95, | |
| "learning_rate": 1.0515335841271768e-05, | |
| "loss": 0.1094, | |
| "step": 625500 | |
| }, | |
| { | |
| "epoch": 37.98, | |
| "learning_rate": 1.050775135003944e-05, | |
| "loss": 0.1083, | |
| "step": 626000 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_bleu": 81.212, | |
| "eval_gen_len": 14.1108, | |
| "eval_loss": 0.16392718255519867, | |
| "eval_runtime": 179.1355, | |
| "eval_samples_per_second": 90.01, | |
| "eval_steps_per_second": 2.814, | |
| "step": 626278 | |
| }, | |
| { | |
| "epoch": 38.01, | |
| "learning_rate": 1.0500166858807112e-05, | |
| "loss": 0.1056, | |
| "step": 626500 | |
| }, | |
| { | |
| "epoch": 38.04, | |
| "learning_rate": 1.0492597536557249e-05, | |
| "loss": 0.1035, | |
| "step": 627000 | |
| }, | |
| { | |
| "epoch": 38.07, | |
| "learning_rate": 1.048501304532492e-05, | |
| "loss": 0.1055, | |
| "step": 627500 | |
| }, | |
| { | |
| "epoch": 38.1, | |
| "learning_rate": 1.0477428554092592e-05, | |
| "loss": 0.1067, | |
| "step": 628000 | |
| }, | |
| { | |
| "epoch": 38.13, | |
| "learning_rate": 1.0469844062860265e-05, | |
| "loss": 0.1059, | |
| "step": 628500 | |
| }, | |
| { | |
| "epoch": 38.17, | |
| "learning_rate": 1.0462259571627936e-05, | |
| "loss": 0.1047, | |
| "step": 629000 | |
| }, | |
| { | |
| "epoch": 38.2, | |
| "learning_rate": 1.0454690249378073e-05, | |
| "loss": 0.1067, | |
| "step": 629500 | |
| }, | |
| { | |
| "epoch": 38.23, | |
| "learning_rate": 1.0447105758145744e-05, | |
| "loss": 0.1056, | |
| "step": 630000 | |
| }, | |
| { | |
| "epoch": 38.26, | |
| "learning_rate": 1.0439521266913417e-05, | |
| "loss": 0.1079, | |
| "step": 630500 | |
| }, | |
| { | |
| "epoch": 38.29, | |
| "learning_rate": 1.0431936775681088e-05, | |
| "loss": 0.1036, | |
| "step": 631000 | |
| }, | |
| { | |
| "epoch": 38.32, | |
| "learning_rate": 1.0424367453431225e-05, | |
| "loss": 0.1068, | |
| "step": 631500 | |
| }, | |
| { | |
| "epoch": 38.35, | |
| "learning_rate": 1.0416782962198897e-05, | |
| "loss": 0.1068, | |
| "step": 632000 | |
| }, | |
| { | |
| "epoch": 38.38, | |
| "learning_rate": 1.0409198470966568e-05, | |
| "loss": 0.1078, | |
| "step": 632500 | |
| }, | |
| { | |
| "epoch": 38.41, | |
| "learning_rate": 1.0401613979734239e-05, | |
| "loss": 0.1053, | |
| "step": 633000 | |
| }, | |
| { | |
| "epoch": 38.44, | |
| "learning_rate": 1.039402948850191e-05, | |
| "loss": 0.1061, | |
| "step": 633500 | |
| }, | |
| { | |
| "epoch": 38.47, | |
| "learning_rate": 1.0386460166252047e-05, | |
| "loss": 0.1077, | |
| "step": 634000 | |
| }, | |
| { | |
| "epoch": 38.5, | |
| "learning_rate": 1.0378875675019719e-05, | |
| "loss": 0.1079, | |
| "step": 634500 | |
| }, | |
| { | |
| "epoch": 38.53, | |
| "learning_rate": 1.0371291183787393e-05, | |
| "loss": 0.1095, | |
| "step": 635000 | |
| }, | |
| { | |
| "epoch": 38.56, | |
| "learning_rate": 1.0363706692555065e-05, | |
| "loss": 0.1091, | |
| "step": 635500 | |
| }, | |
| { | |
| "epoch": 38.59, | |
| "learning_rate": 1.0356122201322736e-05, | |
| "loss": 0.1058, | |
| "step": 636000 | |
| }, | |
| { | |
| "epoch": 38.62, | |
| "learning_rate": 1.0348537710090407e-05, | |
| "loss": 0.109, | |
| "step": 636500 | |
| }, | |
| { | |
| "epoch": 38.65, | |
| "learning_rate": 1.0340968387840544e-05, | |
| "loss": 0.1074, | |
| "step": 637000 | |
| }, | |
| { | |
| "epoch": 38.68, | |
| "learning_rate": 1.0333383896608215e-05, | |
| "loss": 0.1058, | |
| "step": 637500 | |
| }, | |
| { | |
| "epoch": 38.71, | |
| "learning_rate": 1.0325799405375888e-05, | |
| "loss": 0.1058, | |
| "step": 638000 | |
| }, | |
| { | |
| "epoch": 38.74, | |
| "learning_rate": 1.0318214914143561e-05, | |
| "loss": 0.1089, | |
| "step": 638500 | |
| }, | |
| { | |
| "epoch": 38.77, | |
| "learning_rate": 1.0310645591893698e-05, | |
| "loss": 0.1079, | |
| "step": 639000 | |
| }, | |
| { | |
| "epoch": 38.8, | |
| "learning_rate": 1.030306110066137e-05, | |
| "loss": 0.1065, | |
| "step": 639500 | |
| }, | |
| { | |
| "epoch": 38.83, | |
| "learning_rate": 1.0295476609429041e-05, | |
| "loss": 0.1056, | |
| "step": 640000 | |
| }, | |
| { | |
| "epoch": 38.86, | |
| "learning_rate": 1.0287892118196712e-05, | |
| "loss": 0.1068, | |
| "step": 640500 | |
| }, | |
| { | |
| "epoch": 38.89, | |
| "learning_rate": 1.028032279594685e-05, | |
| "loss": 0.1071, | |
| "step": 641000 | |
| }, | |
| { | |
| "epoch": 38.92, | |
| "learning_rate": 1.027273830471452e-05, | |
| "loss": 0.1077, | |
| "step": 641500 | |
| }, | |
| { | |
| "epoch": 38.95, | |
| "learning_rate": 1.0265153813482192e-05, | |
| "loss": 0.1078, | |
| "step": 642000 | |
| }, | |
| { | |
| "epoch": 38.98, | |
| "learning_rate": 1.0257569322249865e-05, | |
| "loss": 0.1067, | |
| "step": 642500 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "eval_bleu": 81.2594, | |
| "eval_gen_len": 14.1177, | |
| "eval_loss": 0.16316094994544983, | |
| "eval_runtime": 176.9924, | |
| "eval_samples_per_second": 91.1, | |
| "eval_steps_per_second": 2.848, | |
| "step": 642759 | |
| }, | |
| { | |
| "epoch": 39.01, | |
| "learning_rate": 1.0249984831017536e-05, | |
| "loss": 0.1061, | |
| "step": 643000 | |
| }, | |
| { | |
| "epoch": 39.04, | |
| "learning_rate": 1.0242400339785207e-05, | |
| "loss": 0.1052, | |
| "step": 643500 | |
| }, | |
| { | |
| "epoch": 39.08, | |
| "learning_rate": 1.0234831017535344e-05, | |
| "loss": 0.1055, | |
| "step": 644000 | |
| }, | |
| { | |
| "epoch": 39.11, | |
| "learning_rate": 1.0227246526303016e-05, | |
| "loss": 0.1047, | |
| "step": 644500 | |
| }, | |
| { | |
| "epoch": 39.14, | |
| "learning_rate": 1.0219662035070688e-05, | |
| "loss": 0.1047, | |
| "step": 645000 | |
| }, | |
| { | |
| "epoch": 39.17, | |
| "learning_rate": 1.0212077543838361e-05, | |
| "loss": 0.1046, | |
| "step": 645500 | |
| }, | |
| { | |
| "epoch": 39.2, | |
| "learning_rate": 1.0204493052606033e-05, | |
| "loss": 0.1053, | |
| "step": 646000 | |
| }, | |
| { | |
| "epoch": 39.23, | |
| "learning_rate": 1.0196908561373704e-05, | |
| "loss": 0.1046, | |
| "step": 646500 | |
| }, | |
| { | |
| "epoch": 39.26, | |
| "learning_rate": 1.0189339239123841e-05, | |
| "loss": 0.1035, | |
| "step": 647000 | |
| }, | |
| { | |
| "epoch": 39.29, | |
| "learning_rate": 1.0181754747891512e-05, | |
| "loss": 0.1025, | |
| "step": 647500 | |
| }, | |
| { | |
| "epoch": 39.32, | |
| "learning_rate": 1.0174170256659184e-05, | |
| "loss": 0.1069, | |
| "step": 648000 | |
| }, | |
| { | |
| "epoch": 39.35, | |
| "learning_rate": 1.0166585765426855e-05, | |
| "loss": 0.1038, | |
| "step": 648500 | |
| }, | |
| { | |
| "epoch": 39.38, | |
| "learning_rate": 1.015900127419453e-05, | |
| "loss": 0.1044, | |
| "step": 649000 | |
| }, | |
| { | |
| "epoch": 39.41, | |
| "learning_rate": 1.01514167829622e-05, | |
| "loss": 0.1055, | |
| "step": 649500 | |
| }, | |
| { | |
| "epoch": 39.44, | |
| "learning_rate": 1.0143832291729872e-05, | |
| "loss": 0.1039, | |
| "step": 650000 | |
| }, | |
| { | |
| "epoch": 39.47, | |
| "learning_rate": 1.0136262969480009e-05, | |
| "loss": 0.1057, | |
| "step": 650500 | |
| }, | |
| { | |
| "epoch": 39.5, | |
| "learning_rate": 1.012867847824768e-05, | |
| "loss": 0.1059, | |
| "step": 651000 | |
| }, | |
| { | |
| "epoch": 39.53, | |
| "learning_rate": 1.0121093987015351e-05, | |
| "loss": 0.1053, | |
| "step": 651500 | |
| }, | |
| { | |
| "epoch": 39.56, | |
| "learning_rate": 1.0113509495783023e-05, | |
| "loss": 0.1038, | |
| "step": 652000 | |
| }, | |
| { | |
| "epoch": 39.59, | |
| "learning_rate": 1.010594017353316e-05, | |
| "loss": 0.1049, | |
| "step": 652500 | |
| }, | |
| { | |
| "epoch": 39.62, | |
| "learning_rate": 1.0098355682300831e-05, | |
| "loss": 0.1046, | |
| "step": 653000 | |
| }, | |
| { | |
| "epoch": 39.65, | |
| "learning_rate": 1.0090771191068504e-05, | |
| "loss": 0.1033, | |
| "step": 653500 | |
| }, | |
| { | |
| "epoch": 39.68, | |
| "learning_rate": 1.0083186699836175e-05, | |
| "loss": 0.1063, | |
| "step": 654000 | |
| }, | |
| { | |
| "epoch": 39.71, | |
| "learning_rate": 1.0075602208603848e-05, | |
| "loss": 0.1053, | |
| "step": 654500 | |
| }, | |
| { | |
| "epoch": 39.74, | |
| "learning_rate": 1.0068032886353985e-05, | |
| "loss": 0.1048, | |
| "step": 655000 | |
| }, | |
| { | |
| "epoch": 39.77, | |
| "learning_rate": 1.0060448395121657e-05, | |
| "loss": 0.1078, | |
| "step": 655500 | |
| }, | |
| { | |
| "epoch": 39.8, | |
| "learning_rate": 1.0052863903889328e-05, | |
| "loss": 0.1056, | |
| "step": 656000 | |
| }, | |
| { | |
| "epoch": 39.83, | |
| "learning_rate": 1.0045279412657e-05, | |
| "loss": 0.1046, | |
| "step": 656500 | |
| }, | |
| { | |
| "epoch": 39.86, | |
| "learning_rate": 1.0037694921424672e-05, | |
| "loss": 0.1048, | |
| "step": 657000 | |
| }, | |
| { | |
| "epoch": 39.89, | |
| "learning_rate": 1.0030110430192343e-05, | |
| "loss": 0.1053, | |
| "step": 657500 | |
| }, | |
| { | |
| "epoch": 39.92, | |
| "learning_rate": 1.002254110794248e-05, | |
| "loss": 0.105, | |
| "step": 658000 | |
| }, | |
| { | |
| "epoch": 39.96, | |
| "learning_rate": 1.0014956616710152e-05, | |
| "loss": 0.1042, | |
| "step": 658500 | |
| }, | |
| { | |
| "epoch": 39.99, | |
| "learning_rate": 1.0007372125477823e-05, | |
| "loss": 0.1033, | |
| "step": 659000 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_bleu": 81.214, | |
| "eval_gen_len": 14.1179, | |
| "eval_loss": 0.16460604965686798, | |
| "eval_runtime": 177.2705, | |
| "eval_samples_per_second": 90.957, | |
| "eval_steps_per_second": 2.843, | |
| "step": 659240 | |
| }, | |
| { | |
| "epoch": 40.02, | |
| "learning_rate": 9.999787634245496e-06, | |
| "loss": 0.1036, | |
| "step": 659500 | |
| }, | |
| { | |
| "epoch": 40.05, | |
| "learning_rate": 9.992218311995631e-06, | |
| "loss": 0.0997, | |
| "step": 660000 | |
| }, | |
| { | |
| "epoch": 40.08, | |
| "learning_rate": 9.984633820763304e-06, | |
| "loss": 0.1017, | |
| "step": 660500 | |
| }, | |
| { | |
| "epoch": 40.11, | |
| "learning_rate": 9.977049329530975e-06, | |
| "loss": 0.1038, | |
| "step": 661000 | |
| }, | |
| { | |
| "epoch": 40.14, | |
| "learning_rate": 9.969464838298648e-06, | |
| "loss": 0.1001, | |
| "step": 661500 | |
| }, | |
| { | |
| "epoch": 40.17, | |
| "learning_rate": 9.96188034706632e-06, | |
| "loss": 0.1035, | |
| "step": 662000 | |
| }, | |
| { | |
| "epoch": 40.2, | |
| "learning_rate": 9.954295855833992e-06, | |
| "loss": 0.1037, | |
| "step": 662500 | |
| }, | |
| { | |
| "epoch": 40.23, | |
| "learning_rate": 9.946711364601664e-06, | |
| "loss": 0.102, | |
| "step": 663000 | |
| }, | |
| { | |
| "epoch": 40.26, | |
| "learning_rate": 9.9391420423518e-06, | |
| "loss": 0.1026, | |
| "step": 663500 | |
| }, | |
| { | |
| "epoch": 40.29, | |
| "learning_rate": 9.931557551119472e-06, | |
| "loss": 0.1033, | |
| "step": 664000 | |
| }, | |
| { | |
| "epoch": 40.32, | |
| "learning_rate": 9.923973059887143e-06, | |
| "loss": 0.1034, | |
| "step": 664500 | |
| }, | |
| { | |
| "epoch": 40.35, | |
| "learning_rate": 9.916388568654816e-06, | |
| "loss": 0.1009, | |
| "step": 665000 | |
| }, | |
| { | |
| "epoch": 40.38, | |
| "learning_rate": 9.908804077422488e-06, | |
| "loss": 0.1039, | |
| "step": 665500 | |
| }, | |
| { | |
| "epoch": 40.41, | |
| "learning_rate": 9.901234755172625e-06, | |
| "loss": 0.1046, | |
| "step": 666000 | |
| }, | |
| { | |
| "epoch": 40.44, | |
| "learning_rate": 9.893650263940296e-06, | |
| "loss": 0.1043, | |
| "step": 666500 | |
| }, | |
| { | |
| "epoch": 40.47, | |
| "learning_rate": 9.886065772707967e-06, | |
| "loss": 0.1007, | |
| "step": 667000 | |
| }, | |
| { | |
| "epoch": 40.5, | |
| "learning_rate": 9.87848128147564e-06, | |
| "loss": 0.1035, | |
| "step": 667500 | |
| }, | |
| { | |
| "epoch": 40.53, | |
| "learning_rate": 9.870911959225775e-06, | |
| "loss": 0.104, | |
| "step": 668000 | |
| }, | |
| { | |
| "epoch": 40.56, | |
| "learning_rate": 9.863327467993448e-06, | |
| "loss": 0.104, | |
| "step": 668500 | |
| }, | |
| { | |
| "epoch": 40.59, | |
| "learning_rate": 9.85574297676112e-06, | |
| "loss": 0.1037, | |
| "step": 669000 | |
| }, | |
| { | |
| "epoch": 40.62, | |
| "learning_rate": 9.848158485528791e-06, | |
| "loss": 0.1018, | |
| "step": 669500 | |
| }, | |
| { | |
| "epoch": 40.65, | |
| "learning_rate": 9.840573994296462e-06, | |
| "loss": 0.1027, | |
| "step": 670000 | |
| }, | |
| { | |
| "epoch": 40.68, | |
| "learning_rate": 9.832989503064135e-06, | |
| "loss": 0.1008, | |
| "step": 670500 | |
| }, | |
| { | |
| "epoch": 40.71, | |
| "learning_rate": 9.825405011831806e-06, | |
| "loss": 0.1043, | |
| "step": 671000 | |
| }, | |
| { | |
| "epoch": 40.74, | |
| "learning_rate": 9.81782052059948e-06, | |
| "loss": 0.1028, | |
| "step": 671500 | |
| }, | |
| { | |
| "epoch": 40.77, | |
| "learning_rate": 9.810251198349615e-06, | |
| "loss": 0.1049, | |
| "step": 672000 | |
| }, | |
| { | |
| "epoch": 40.8, | |
| "learning_rate": 9.802681876099752e-06, | |
| "loss": 0.1061, | |
| "step": 672500 | |
| }, | |
| { | |
| "epoch": 40.83, | |
| "learning_rate": 9.795097384867423e-06, | |
| "loss": 0.1042, | |
| "step": 673000 | |
| }, | |
| { | |
| "epoch": 40.87, | |
| "learning_rate": 9.787512893635096e-06, | |
| "loss": 0.1055, | |
| "step": 673500 | |
| }, | |
| { | |
| "epoch": 40.9, | |
| "learning_rate": 9.779928402402767e-06, | |
| "loss": 0.1029, | |
| "step": 674000 | |
| }, | |
| { | |
| "epoch": 40.93, | |
| "learning_rate": 9.772359080152904e-06, | |
| "loss": 0.1039, | |
| "step": 674500 | |
| }, | |
| { | |
| "epoch": 40.96, | |
| "learning_rate": 9.764774588920576e-06, | |
| "loss": 0.1074, | |
| "step": 675000 | |
| }, | |
| { | |
| "epoch": 40.99, | |
| "learning_rate": 9.757190097688248e-06, | |
| "loss": 0.1039, | |
| "step": 675500 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "eval_bleu": 81.2844, | |
| "eval_gen_len": 14.0989, | |
| "eval_loss": 0.16462182998657227, | |
| "eval_runtime": 177.1935, | |
| "eval_samples_per_second": 90.997, | |
| "eval_steps_per_second": 2.844, | |
| "step": 675721 | |
| }, | |
| { | |
| "epoch": 41.02, | |
| "learning_rate": 9.74960560645592e-06, | |
| "loss": 0.1037, | |
| "step": 676000 | |
| }, | |
| { | |
| "epoch": 41.05, | |
| "learning_rate": 9.742021115223591e-06, | |
| "loss": 0.0975, | |
| "step": 676500 | |
| }, | |
| { | |
| "epoch": 41.08, | |
| "learning_rate": 9.734436623991264e-06, | |
| "loss": 0.0995, | |
| "step": 677000 | |
| }, | |
| { | |
| "epoch": 41.11, | |
| "learning_rate": 9.726852132758935e-06, | |
| "loss": 0.1018, | |
| "step": 677500 | |
| }, | |
| { | |
| "epoch": 41.14, | |
| "learning_rate": 9.719267641526608e-06, | |
| "loss": 0.1007, | |
| "step": 678000 | |
| }, | |
| { | |
| "epoch": 41.17, | |
| "learning_rate": 9.711698319276744e-06, | |
| "loss": 0.1005, | |
| "step": 678500 | |
| }, | |
| { | |
| "epoch": 41.2, | |
| "learning_rate": 9.70412899702688e-06, | |
| "loss": 0.1025, | |
| "step": 679000 | |
| }, | |
| { | |
| "epoch": 41.23, | |
| "learning_rate": 9.696544505794552e-06, | |
| "loss": 0.1027, | |
| "step": 679500 | |
| }, | |
| { | |
| "epoch": 41.26, | |
| "learning_rate": 9.688960014562225e-06, | |
| "loss": 0.1008, | |
| "step": 680000 | |
| }, | |
| { | |
| "epoch": 41.29, | |
| "learning_rate": 9.681375523329896e-06, | |
| "loss": 0.1006, | |
| "step": 680500 | |
| }, | |
| { | |
| "epoch": 41.32, | |
| "learning_rate": 9.673791032097567e-06, | |
| "loss": 0.1012, | |
| "step": 681000 | |
| }, | |
| { | |
| "epoch": 41.35, | |
| "learning_rate": 9.666221709847704e-06, | |
| "loss": 0.1013, | |
| "step": 681500 | |
| }, | |
| { | |
| "epoch": 41.38, | |
| "learning_rate": 9.658637218615377e-06, | |
| "loss": 0.1035, | |
| "step": 682000 | |
| }, | |
| { | |
| "epoch": 41.41, | |
| "learning_rate": 9.651052727383049e-06, | |
| "loss": 0.1018, | |
| "step": 682500 | |
| }, | |
| { | |
| "epoch": 41.44, | |
| "learning_rate": 9.64346823615072e-06, | |
| "loss": 0.1001, | |
| "step": 683000 | |
| }, | |
| { | |
| "epoch": 41.47, | |
| "learning_rate": 9.635898913900857e-06, | |
| "loss": 0.1018, | |
| "step": 683500 | |
| }, | |
| { | |
| "epoch": 41.5, | |
| "learning_rate": 9.628314422668528e-06, | |
| "loss": 0.1005, | |
| "step": 684000 | |
| }, | |
| { | |
| "epoch": 41.53, | |
| "learning_rate": 9.6207299314362e-06, | |
| "loss": 0.1013, | |
| "step": 684500 | |
| }, | |
| { | |
| "epoch": 41.56, | |
| "learning_rate": 9.613145440203872e-06, | |
| "loss": 0.1012, | |
| "step": 685000 | |
| }, | |
| { | |
| "epoch": 41.59, | |
| "learning_rate": 9.605560948971544e-06, | |
| "loss": 0.1009, | |
| "step": 685500 | |
| }, | |
| { | |
| "epoch": 41.62, | |
| "learning_rate": 9.59799162672168e-06, | |
| "loss": 0.104, | |
| "step": 686000 | |
| }, | |
| { | |
| "epoch": 41.65, | |
| "learning_rate": 9.590407135489352e-06, | |
| "loss": 0.1023, | |
| "step": 686500 | |
| }, | |
| { | |
| "epoch": 41.68, | |
| "learning_rate": 9.582822644257023e-06, | |
| "loss": 0.1012, | |
| "step": 687000 | |
| }, | |
| { | |
| "epoch": 41.71, | |
| "learning_rate": 9.575238153024696e-06, | |
| "loss": 0.1013, | |
| "step": 687500 | |
| }, | |
| { | |
| "epoch": 41.75, | |
| "learning_rate": 9.567653661792367e-06, | |
| "loss": 0.1018, | |
| "step": 688000 | |
| }, | |
| { | |
| "epoch": 41.78, | |
| "learning_rate": 9.56006917056004e-06, | |
| "loss": 0.1026, | |
| "step": 688500 | |
| }, | |
| { | |
| "epoch": 41.81, | |
| "learning_rate": 9.552484679327712e-06, | |
| "loss": 0.103, | |
| "step": 689000 | |
| }, | |
| { | |
| "epoch": 41.84, | |
| "learning_rate": 9.544900188095383e-06, | |
| "loss": 0.1029, | |
| "step": 689500 | |
| }, | |
| { | |
| "epoch": 41.87, | |
| "learning_rate": 9.53733086584552e-06, | |
| "loss": 0.103, | |
| "step": 690000 | |
| }, | |
| { | |
| "epoch": 41.9, | |
| "learning_rate": 9.529746374613191e-06, | |
| "loss": 0.1027, | |
| "step": 690500 | |
| }, | |
| { | |
| "epoch": 41.93, | |
| "learning_rate": 9.522161883380864e-06, | |
| "loss": 0.0986, | |
| "step": 691000 | |
| }, | |
| { | |
| "epoch": 41.96, | |
| "learning_rate": 9.514592561131e-06, | |
| "loss": 0.1012, | |
| "step": 691500 | |
| }, | |
| { | |
| "epoch": 41.99, | |
| "learning_rate": 9.507008069898672e-06, | |
| "loss": 0.106, | |
| "step": 692000 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_bleu": 81.2701, | |
| "eval_gen_len": 14.0995, | |
| "eval_loss": 0.16560077667236328, | |
| "eval_runtime": 176.936, | |
| "eval_samples_per_second": 91.129, | |
| "eval_steps_per_second": 2.848, | |
| "step": 692202 | |
| }, | |
| { | |
| "epoch": 42.02, | |
| "learning_rate": 9.499423578666344e-06, | |
| "loss": 0.1025, | |
| "step": 692500 | |
| }, | |
| { | |
| "epoch": 42.05, | |
| "learning_rate": 9.491839087434017e-06, | |
| "loss": 0.0978, | |
| "step": 693000 | |
| }, | |
| { | |
| "epoch": 42.08, | |
| "learning_rate": 9.484254596201688e-06, | |
| "loss": 0.0994, | |
| "step": 693500 | |
| }, | |
| { | |
| "epoch": 42.11, | |
| "learning_rate": 9.476685273951825e-06, | |
| "loss": 0.1013, | |
| "step": 694000 | |
| }, | |
| { | |
| "epoch": 42.14, | |
| "learning_rate": 9.469100782719496e-06, | |
| "loss": 0.1, | |
| "step": 694500 | |
| }, | |
| { | |
| "epoch": 42.17, | |
| "learning_rate": 9.461516291487167e-06, | |
| "loss": 0.0976, | |
| "step": 695000 | |
| }, | |
| { | |
| "epoch": 42.2, | |
| "learning_rate": 9.45393180025484e-06, | |
| "loss": 0.1008, | |
| "step": 695500 | |
| }, | |
| { | |
| "epoch": 42.23, | |
| "learning_rate": 9.446347309022512e-06, | |
| "loss": 0.0973, | |
| "step": 696000 | |
| }, | |
| { | |
| "epoch": 42.26, | |
| "learning_rate": 9.438762817790183e-06, | |
| "loss": 0.099, | |
| "step": 696500 | |
| }, | |
| { | |
| "epoch": 42.29, | |
| "learning_rate": 9.431178326557854e-06, | |
| "loss": 0.0995, | |
| "step": 697000 | |
| }, | |
| { | |
| "epoch": 42.32, | |
| "learning_rate": 9.423609004307991e-06, | |
| "loss": 0.1004, | |
| "step": 697500 | |
| }, | |
| { | |
| "epoch": 42.35, | |
| "learning_rate": 9.416024513075663e-06, | |
| "loss": 0.1004, | |
| "step": 698000 | |
| }, | |
| { | |
| "epoch": 42.38, | |
| "learning_rate": 9.408440021843335e-06, | |
| "loss": 0.1006, | |
| "step": 698500 | |
| }, | |
| { | |
| "epoch": 42.41, | |
| "learning_rate": 9.400855530611007e-06, | |
| "loss": 0.1003, | |
| "step": 699000 | |
| }, | |
| { | |
| "epoch": 42.44, | |
| "learning_rate": 9.39327103937868e-06, | |
| "loss": 0.1005, | |
| "step": 699500 | |
| }, | |
| { | |
| "epoch": 42.47, | |
| "learning_rate": 9.385686548146351e-06, | |
| "loss": 0.1009, | |
| "step": 700000 | |
| }, | |
| { | |
| "epoch": 42.5, | |
| "learning_rate": 9.378117225896488e-06, | |
| "loss": 0.1005, | |
| "step": 700500 | |
| }, | |
| { | |
| "epoch": 42.53, | |
| "learning_rate": 9.37053273466416e-06, | |
| "loss": 0.1015, | |
| "step": 701000 | |
| }, | |
| { | |
| "epoch": 42.56, | |
| "learning_rate": 9.36294824343183e-06, | |
| "loss": 0.1017, | |
| "step": 701500 | |
| }, | |
| { | |
| "epoch": 42.59, | |
| "learning_rate": 9.355363752199503e-06, | |
| "loss": 0.1009, | |
| "step": 702000 | |
| }, | |
| { | |
| "epoch": 42.62, | |
| "learning_rate": 9.347779260967175e-06, | |
| "loss": 0.0989, | |
| "step": 702500 | |
| }, | |
| { | |
| "epoch": 42.66, | |
| "learning_rate": 9.340194769734848e-06, | |
| "loss": 0.1006, | |
| "step": 703000 | |
| }, | |
| { | |
| "epoch": 42.69, | |
| "learning_rate": 9.332625447484983e-06, | |
| "loss": 0.1004, | |
| "step": 703500 | |
| }, | |
| { | |
| "epoch": 42.72, | |
| "learning_rate": 9.325040956252656e-06, | |
| "loss": 0.0999, | |
| "step": 704000 | |
| }, | |
| { | |
| "epoch": 42.75, | |
| "learning_rate": 9.317456465020327e-06, | |
| "loss": 0.1012, | |
| "step": 704500 | |
| }, | |
| { | |
| "epoch": 42.78, | |
| "learning_rate": 9.309887142770464e-06, | |
| "loss": 0.0996, | |
| "step": 705000 | |
| }, | |
| { | |
| "epoch": 42.81, | |
| "learning_rate": 9.302302651538136e-06, | |
| "loss": 0.0981, | |
| "step": 705500 | |
| }, | |
| { | |
| "epoch": 42.84, | |
| "learning_rate": 9.294718160305808e-06, | |
| "loss": 0.1001, | |
| "step": 706000 | |
| }, | |
| { | |
| "epoch": 42.87, | |
| "learning_rate": 9.28713366907348e-06, | |
| "loss": 0.0996, | |
| "step": 706500 | |
| }, | |
| { | |
| "epoch": 42.9, | |
| "learning_rate": 9.279549177841151e-06, | |
| "loss": 0.0994, | |
| "step": 707000 | |
| }, | |
| { | |
| "epoch": 42.93, | |
| "learning_rate": 9.271964686608824e-06, | |
| "loss": 0.0998, | |
| "step": 707500 | |
| }, | |
| { | |
| "epoch": 42.96, | |
| "learning_rate": 9.264380195376495e-06, | |
| "loss": 0.1009, | |
| "step": 708000 | |
| }, | |
| { | |
| "epoch": 42.99, | |
| "learning_rate": 9.256795704144166e-06, | |
| "loss": 0.1016, | |
| "step": 708500 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "eval_bleu": 81.3319, | |
| "eval_gen_len": 14.1486, | |
| "eval_loss": 0.16639186441898346, | |
| "eval_runtime": 176.8975, | |
| "eval_samples_per_second": 91.149, | |
| "eval_steps_per_second": 2.849, | |
| "step": 708683 | |
| }, | |
| { | |
| "epoch": 43.02, | |
| "learning_rate": 9.249211212911838e-06, | |
| "loss": 0.0985, | |
| "step": 709000 | |
| }, | |
| { | |
| "epoch": 43.05, | |
| "learning_rate": 9.24162672167951e-06, | |
| "loss": 0.097, | |
| "step": 709500 | |
| }, | |
| { | |
| "epoch": 43.08, | |
| "learning_rate": 9.234042230447182e-06, | |
| "loss": 0.0971, | |
| "step": 710000 | |
| }, | |
| { | |
| "epoch": 43.11, | |
| "learning_rate": 9.226457739214855e-06, | |
| "loss": 0.0939, | |
| "step": 710500 | |
| }, | |
| { | |
| "epoch": 43.14, | |
| "learning_rate": 9.21888841696499e-06, | |
| "loss": 0.0995, | |
| "step": 711000 | |
| }, | |
| { | |
| "epoch": 43.17, | |
| "learning_rate": 9.211303925732663e-06, | |
| "loss": 0.0955, | |
| "step": 711500 | |
| }, | |
| { | |
| "epoch": 43.2, | |
| "learning_rate": 9.203719434500334e-06, | |
| "loss": 0.0976, | |
| "step": 712000 | |
| }, | |
| { | |
| "epoch": 43.23, | |
| "learning_rate": 9.196134943268006e-06, | |
| "loss": 0.0969, | |
| "step": 712500 | |
| }, | |
| { | |
| "epoch": 43.26, | |
| "learning_rate": 9.188565621018143e-06, | |
| "loss": 0.098, | |
| "step": 713000 | |
| }, | |
| { | |
| "epoch": 43.29, | |
| "learning_rate": 9.180981129785814e-06, | |
| "loss": 0.0982, | |
| "step": 713500 | |
| }, | |
| { | |
| "epoch": 43.32, | |
| "learning_rate": 9.173396638553487e-06, | |
| "loss": 0.0977, | |
| "step": 714000 | |
| }, | |
| { | |
| "epoch": 43.35, | |
| "learning_rate": 9.165812147321158e-06, | |
| "loss": 0.098, | |
| "step": 714500 | |
| }, | |
| { | |
| "epoch": 43.38, | |
| "learning_rate": 9.158242825071295e-06, | |
| "loss": 0.0975, | |
| "step": 715000 | |
| }, | |
| { | |
| "epoch": 43.41, | |
| "learning_rate": 9.15067350282143e-06, | |
| "loss": 0.0994, | |
| "step": 715500 | |
| }, | |
| { | |
| "epoch": 43.44, | |
| "learning_rate": 9.143089011589104e-06, | |
| "loss": 0.0996, | |
| "step": 716000 | |
| }, | |
| { | |
| "epoch": 43.47, | |
| "learning_rate": 9.135504520356775e-06, | |
| "loss": 0.0983, | |
| "step": 716500 | |
| }, | |
| { | |
| "epoch": 43.5, | |
| "learning_rate": 9.127920029124448e-06, | |
| "loss": 0.0997, | |
| "step": 717000 | |
| }, | |
| { | |
| "epoch": 43.53, | |
| "learning_rate": 9.120335537892119e-06, | |
| "loss": 0.0983, | |
| "step": 717500 | |
| }, | |
| { | |
| "epoch": 43.57, | |
| "learning_rate": 9.112766215642256e-06, | |
| "loss": 0.099, | |
| "step": 718000 | |
| }, | |
| { | |
| "epoch": 43.6, | |
| "learning_rate": 9.105196893392392e-06, | |
| "loss": 0.0987, | |
| "step": 718500 | |
| }, | |
| { | |
| "epoch": 43.63, | |
| "learning_rate": 9.097612402160064e-06, | |
| "loss": 0.0992, | |
| "step": 719000 | |
| }, | |
| { | |
| "epoch": 43.66, | |
| "learning_rate": 9.090027910927736e-06, | |
| "loss": 0.0989, | |
| "step": 719500 | |
| }, | |
| { | |
| "epoch": 43.69, | |
| "learning_rate": 9.082443419695409e-06, | |
| "loss": 0.1004, | |
| "step": 720000 | |
| }, | |
| { | |
| "epoch": 43.72, | |
| "learning_rate": 9.07485892846308e-06, | |
| "loss": 0.0998, | |
| "step": 720500 | |
| }, | |
| { | |
| "epoch": 43.75, | |
| "learning_rate": 9.067274437230751e-06, | |
| "loss": 0.1005, | |
| "step": 721000 | |
| }, | |
| { | |
| "epoch": 43.78, | |
| "learning_rate": 9.059689945998424e-06, | |
| "loss": 0.0978, | |
| "step": 721500 | |
| }, | |
| { | |
| "epoch": 43.81, | |
| "learning_rate": 9.052105454766095e-06, | |
| "loss": 0.0998, | |
| "step": 722000 | |
| }, | |
| { | |
| "epoch": 43.84, | |
| "learning_rate": 9.044536132516232e-06, | |
| "loss": 0.0995, | |
| "step": 722500 | |
| }, | |
| { | |
| "epoch": 43.87, | |
| "learning_rate": 9.036951641283904e-06, | |
| "loss": 0.1005, | |
| "step": 723000 | |
| }, | |
| { | |
| "epoch": 43.9, | |
| "learning_rate": 9.029367150051575e-06, | |
| "loss": 0.1, | |
| "step": 723500 | |
| }, | |
| { | |
| "epoch": 43.93, | |
| "learning_rate": 9.021782658819246e-06, | |
| "loss": 0.0979, | |
| "step": 724000 | |
| }, | |
| { | |
| "epoch": 43.96, | |
| "learning_rate": 9.014198167586919e-06, | |
| "loss": 0.0997, | |
| "step": 724500 | |
| }, | |
| { | |
| "epoch": 43.99, | |
| "learning_rate": 9.00661367635459e-06, | |
| "loss": 0.0992, | |
| "step": 725000 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_bleu": 81.3473, | |
| "eval_gen_len": 14.1242, | |
| "eval_loss": 0.1655581146478653, | |
| "eval_runtime": 178.9799, | |
| "eval_samples_per_second": 90.088, | |
| "eval_steps_per_second": 2.816, | |
| "step": 725164 | |
| }, | |
| { | |
| "epoch": 44.02, | |
| "learning_rate": 8.999029185122262e-06, | |
| "loss": 0.0972, | |
| "step": 725500 | |
| }, | |
| { | |
| "epoch": 44.05, | |
| "learning_rate": 8.991444693889935e-06, | |
| "loss": 0.0954, | |
| "step": 726000 | |
| }, | |
| { | |
| "epoch": 44.08, | |
| "learning_rate": 8.98387537164007e-06, | |
| "loss": 0.0954, | |
| "step": 726500 | |
| }, | |
| { | |
| "epoch": 44.11, | |
| "learning_rate": 8.976290880407743e-06, | |
| "loss": 0.0961, | |
| "step": 727000 | |
| }, | |
| { | |
| "epoch": 44.14, | |
| "learning_rate": 8.968706389175414e-06, | |
| "loss": 0.0941, | |
| "step": 727500 | |
| }, | |
| { | |
| "epoch": 44.17, | |
| "learning_rate": 8.961121897943087e-06, | |
| "loss": 0.0952, | |
| "step": 728000 | |
| }, | |
| { | |
| "epoch": 44.2, | |
| "learning_rate": 8.953552575693223e-06, | |
| "loss": 0.0993, | |
| "step": 728500 | |
| }, | |
| { | |
| "epoch": 44.23, | |
| "learning_rate": 8.945968084460895e-06, | |
| "loss": 0.0966, | |
| "step": 729000 | |
| }, | |
| { | |
| "epoch": 44.26, | |
| "learning_rate": 8.938383593228567e-06, | |
| "loss": 0.0966, | |
| "step": 729500 | |
| }, | |
| { | |
| "epoch": 44.29, | |
| "learning_rate": 8.93079910199624e-06, | |
| "loss": 0.0968, | |
| "step": 730000 | |
| }, | |
| { | |
| "epoch": 44.32, | |
| "learning_rate": 8.923229779746375e-06, | |
| "loss": 0.0987, | |
| "step": 730500 | |
| }, | |
| { | |
| "epoch": 44.35, | |
| "learning_rate": 8.915660457496512e-06, | |
| "loss": 0.0982, | |
| "step": 731000 | |
| }, | |
| { | |
| "epoch": 44.38, | |
| "learning_rate": 8.908091135246648e-06, | |
| "loss": 0.0954, | |
| "step": 731500 | |
| }, | |
| { | |
| "epoch": 44.41, | |
| "learning_rate": 8.90050664401432e-06, | |
| "loss": 0.0973, | |
| "step": 732000 | |
| }, | |
| { | |
| "epoch": 44.45, | |
| "learning_rate": 8.892922152781992e-06, | |
| "loss": 0.0968, | |
| "step": 732500 | |
| }, | |
| { | |
| "epoch": 44.48, | |
| "learning_rate": 8.885337661549665e-06, | |
| "loss": 0.0966, | |
| "step": 733000 | |
| }, | |
| { | |
| "epoch": 44.51, | |
| "learning_rate": 8.877753170317336e-06, | |
| "loss": 0.0962, | |
| "step": 733500 | |
| }, | |
| { | |
| "epoch": 44.54, | |
| "learning_rate": 8.870168679085007e-06, | |
| "loss": 0.0946, | |
| "step": 734000 | |
| }, | |
| { | |
| "epoch": 44.57, | |
| "learning_rate": 8.86258418785268e-06, | |
| "loss": 0.1004, | |
| "step": 734500 | |
| }, | |
| { | |
| "epoch": 44.6, | |
| "learning_rate": 8.854999696620351e-06, | |
| "loss": 0.0983, | |
| "step": 735000 | |
| }, | |
| { | |
| "epoch": 44.63, | |
| "learning_rate": 8.847415205388024e-06, | |
| "loss": 0.0979, | |
| "step": 735500 | |
| }, | |
| { | |
| "epoch": 44.66, | |
| "learning_rate": 8.839830714155696e-06, | |
| "loss": 0.0976, | |
| "step": 736000 | |
| }, | |
| { | |
| "epoch": 44.69, | |
| "learning_rate": 8.832246222923367e-06, | |
| "loss": 0.0984, | |
| "step": 736500 | |
| }, | |
| { | |
| "epoch": 44.72, | |
| "learning_rate": 8.824661731691038e-06, | |
| "loss": 0.099, | |
| "step": 737000 | |
| }, | |
| { | |
| "epoch": 44.75, | |
| "learning_rate": 8.817092409441175e-06, | |
| "loss": 0.0983, | |
| "step": 737500 | |
| }, | |
| { | |
| "epoch": 44.78, | |
| "learning_rate": 8.809507918208846e-06, | |
| "loss": 0.0969, | |
| "step": 738000 | |
| }, | |
| { | |
| "epoch": 44.81, | |
| "learning_rate": 8.80192342697652e-06, | |
| "loss": 0.0979, | |
| "step": 738500 | |
| }, | |
| { | |
| "epoch": 44.84, | |
| "learning_rate": 8.794354104726656e-06, | |
| "loss": 0.0963, | |
| "step": 739000 | |
| }, | |
| { | |
| "epoch": 44.87, | |
| "learning_rate": 8.786769613494328e-06, | |
| "loss": 0.098, | |
| "step": 739500 | |
| }, | |
| { | |
| "epoch": 44.9, | |
| "learning_rate": 8.779185122261999e-06, | |
| "loss": 0.0979, | |
| "step": 740000 | |
| }, | |
| { | |
| "epoch": 44.93, | |
| "learning_rate": 8.77160063102967e-06, | |
| "loss": 0.0995, | |
| "step": 740500 | |
| }, | |
| { | |
| "epoch": 44.96, | |
| "learning_rate": 8.764016139797343e-06, | |
| "loss": 0.0956, | |
| "step": 741000 | |
| }, | |
| { | |
| "epoch": 44.99, | |
| "learning_rate": 8.756446817547479e-06, | |
| "loss": 0.1002, | |
| "step": 741500 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "eval_bleu": 81.3575, | |
| "eval_gen_len": 14.1571, | |
| "eval_loss": 0.16723676025867462, | |
| "eval_runtime": 178.3486, | |
| "eval_samples_per_second": 90.407, | |
| "eval_steps_per_second": 2.826, | |
| "step": 741645 | |
| }, | |
| { | |
| "epoch": 45.02, | |
| "learning_rate": 8.748862326315151e-06, | |
| "loss": 0.0968, | |
| "step": 742000 | |
| }, | |
| { | |
| "epoch": 45.05, | |
| "learning_rate": 8.741277835082823e-06, | |
| "loss": 0.0942, | |
| "step": 742500 | |
| }, | |
| { | |
| "epoch": 45.08, | |
| "learning_rate": 8.733693343850496e-06, | |
| "loss": 0.0955, | |
| "step": 743000 | |
| }, | |
| { | |
| "epoch": 45.11, | |
| "learning_rate": 8.726108852618167e-06, | |
| "loss": 0.0939, | |
| "step": 743500 | |
| }, | |
| { | |
| "epoch": 45.14, | |
| "learning_rate": 8.71852436138584e-06, | |
| "loss": 0.0937, | |
| "step": 744000 | |
| }, | |
| { | |
| "epoch": 45.17, | |
| "learning_rate": 8.710939870153511e-06, | |
| "loss": 0.0963, | |
| "step": 744500 | |
| }, | |
| { | |
| "epoch": 45.2, | |
| "learning_rate": 8.703355378921182e-06, | |
| "loss": 0.0956, | |
| "step": 745000 | |
| }, | |
| { | |
| "epoch": 45.23, | |
| "learning_rate": 8.69578605667132e-06, | |
| "loss": 0.097, | |
| "step": 745500 | |
| }, | |
| { | |
| "epoch": 45.26, | |
| "learning_rate": 8.688216734421455e-06, | |
| "loss": 0.0942, | |
| "step": 746000 | |
| }, | |
| { | |
| "epoch": 45.29, | |
| "learning_rate": 8.680632243189128e-06, | |
| "loss": 0.0945, | |
| "step": 746500 | |
| }, | |
| { | |
| "epoch": 45.32, | |
| "learning_rate": 8.673047751956799e-06, | |
| "loss": 0.0945, | |
| "step": 747000 | |
| }, | |
| { | |
| "epoch": 45.36, | |
| "learning_rate": 8.665463260724472e-06, | |
| "loss": 0.0956, | |
| "step": 747500 | |
| }, | |
| { | |
| "epoch": 45.39, | |
| "learning_rate": 8.657878769492143e-06, | |
| "loss": 0.0974, | |
| "step": 748000 | |
| }, | |
| { | |
| "epoch": 45.42, | |
| "learning_rate": 8.65030944724228e-06, | |
| "loss": 0.0963, | |
| "step": 748500 | |
| }, | |
| { | |
| "epoch": 45.45, | |
| "learning_rate": 8.642724956009952e-06, | |
| "loss": 0.0948, | |
| "step": 749000 | |
| }, | |
| { | |
| "epoch": 45.48, | |
| "learning_rate": 8.635140464777624e-06, | |
| "loss": 0.0976, | |
| "step": 749500 | |
| }, | |
| { | |
| "epoch": 45.51, | |
| "learning_rate": 8.627555973545296e-06, | |
| "loss": 0.0956, | |
| "step": 750000 | |
| }, | |
| { | |
| "epoch": 45.54, | |
| "learning_rate": 8.619971482312967e-06, | |
| "loss": 0.0947, | |
| "step": 750500 | |
| }, | |
| { | |
| "epoch": 45.57, | |
| "learning_rate": 8.612386991080638e-06, | |
| "loss": 0.097, | |
| "step": 751000 | |
| }, | |
| { | |
| "epoch": 45.6, | |
| "learning_rate": 8.604802499848311e-06, | |
| "loss": 0.0932, | |
| "step": 751500 | |
| }, | |
| { | |
| "epoch": 45.63, | |
| "learning_rate": 8.597218008615982e-06, | |
| "loss": 0.094, | |
| "step": 752000 | |
| }, | |
| { | |
| "epoch": 45.66, | |
| "learning_rate": 8.589663855348584e-06, | |
| "loss": 0.0953, | |
| "step": 752500 | |
| }, | |
| { | |
| "epoch": 45.69, | |
| "learning_rate": 8.582079364116257e-06, | |
| "loss": 0.0957, | |
| "step": 753000 | |
| }, | |
| { | |
| "epoch": 45.72, | |
| "learning_rate": 8.574510041866392e-06, | |
| "loss": 0.0981, | |
| "step": 753500 | |
| }, | |
| { | |
| "epoch": 45.75, | |
| "learning_rate": 8.566925550634065e-06, | |
| "loss": 0.0956, | |
| "step": 754000 | |
| }, | |
| { | |
| "epoch": 45.78, | |
| "learning_rate": 8.559341059401736e-06, | |
| "loss": 0.0955, | |
| "step": 754500 | |
| }, | |
| { | |
| "epoch": 45.81, | |
| "learning_rate": 8.551756568169407e-06, | |
| "loss": 0.1007, | |
| "step": 755000 | |
| }, | |
| { | |
| "epoch": 45.84, | |
| "learning_rate": 8.544172076937079e-06, | |
| "loss": 0.0996, | |
| "step": 755500 | |
| }, | |
| { | |
| "epoch": 45.87, | |
| "learning_rate": 8.536587585704752e-06, | |
| "loss": 0.0957, | |
| "step": 756000 | |
| }, | |
| { | |
| "epoch": 45.9, | |
| "learning_rate": 8.529003094472423e-06, | |
| "loss": 0.0977, | |
| "step": 756500 | |
| }, | |
| { | |
| "epoch": 45.93, | |
| "learning_rate": 8.521418603240096e-06, | |
| "loss": 0.0952, | |
| "step": 757000 | |
| }, | |
| { | |
| "epoch": 45.96, | |
| "learning_rate": 8.513834112007767e-06, | |
| "loss": 0.0966, | |
| "step": 757500 | |
| }, | |
| { | |
| "epoch": 45.99, | |
| "learning_rate": 8.506249620775438e-06, | |
| "loss": 0.0957, | |
| "step": 758000 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_bleu": 81.2624, | |
| "eval_gen_len": 14.1363, | |
| "eval_loss": 0.16791266202926636, | |
| "eval_runtime": 178.4651, | |
| "eval_samples_per_second": 90.348, | |
| "eval_steps_per_second": 2.824, | |
| "step": 758126 | |
| }, | |
| { | |
| "epoch": 46.02, | |
| "learning_rate": 8.498680298525575e-06, | |
| "loss": 0.0937, | |
| "step": 758500 | |
| }, | |
| { | |
| "epoch": 46.05, | |
| "learning_rate": 8.491095807293247e-06, | |
| "loss": 0.0933, | |
| "step": 759000 | |
| }, | |
| { | |
| "epoch": 46.08, | |
| "learning_rate": 8.48351131606092e-06, | |
| "loss": 0.0949, | |
| "step": 759500 | |
| }, | |
| { | |
| "epoch": 46.11, | |
| "learning_rate": 8.47592682482859e-06, | |
| "loss": 0.094, | |
| "step": 760000 | |
| }, | |
| { | |
| "epoch": 46.14, | |
| "learning_rate": 8.468357502578728e-06, | |
| "loss": 0.0919, | |
| "step": 760500 | |
| }, | |
| { | |
| "epoch": 46.17, | |
| "learning_rate": 8.4607730113464e-06, | |
| "loss": 0.0934, | |
| "step": 761000 | |
| }, | |
| { | |
| "epoch": 46.2, | |
| "learning_rate": 8.453188520114072e-06, | |
| "loss": 0.0947, | |
| "step": 761500 | |
| }, | |
| { | |
| "epoch": 46.24, | |
| "learning_rate": 8.445604028881743e-06, | |
| "loss": 0.0951, | |
| "step": 762000 | |
| }, | |
| { | |
| "epoch": 46.27, | |
| "learning_rate": 8.438019537649416e-06, | |
| "loss": 0.094, | |
| "step": 762500 | |
| }, | |
| { | |
| "epoch": 46.3, | |
| "learning_rate": 8.430450215399552e-06, | |
| "loss": 0.0931, | |
| "step": 763000 | |
| }, | |
| { | |
| "epoch": 46.33, | |
| "learning_rate": 8.422865724167225e-06, | |
| "loss": 0.0947, | |
| "step": 763500 | |
| }, | |
| { | |
| "epoch": 46.36, | |
| "learning_rate": 8.415281232934896e-06, | |
| "loss": 0.094, | |
| "step": 764000 | |
| }, | |
| { | |
| "epoch": 46.39, | |
| "learning_rate": 8.407696741702567e-06, | |
| "loss": 0.0927, | |
| "step": 764500 | |
| }, | |
| { | |
| "epoch": 46.42, | |
| "learning_rate": 8.40011225047024e-06, | |
| "loss": 0.0945, | |
| "step": 765000 | |
| }, | |
| { | |
| "epoch": 46.45, | |
| "learning_rate": 8.392527759237911e-06, | |
| "loss": 0.0951, | |
| "step": 765500 | |
| }, | |
| { | |
| "epoch": 46.48, | |
| "learning_rate": 8.384958436988048e-06, | |
| "loss": 0.0933, | |
| "step": 766000 | |
| }, | |
| { | |
| "epoch": 46.51, | |
| "learning_rate": 8.37737394575572e-06, | |
| "loss": 0.0941, | |
| "step": 766500 | |
| }, | |
| { | |
| "epoch": 46.54, | |
| "learning_rate": 8.369804623505857e-06, | |
| "loss": 0.0952, | |
| "step": 767000 | |
| }, | |
| { | |
| "epoch": 46.57, | |
| "learning_rate": 8.362220132273528e-06, | |
| "loss": 0.093, | |
| "step": 767500 | |
| }, | |
| { | |
| "epoch": 46.6, | |
| "learning_rate": 8.3546356410412e-06, | |
| "loss": 0.0954, | |
| "step": 768000 | |
| }, | |
| { | |
| "epoch": 46.63, | |
| "learning_rate": 8.34705114980887e-06, | |
| "loss": 0.0955, | |
| "step": 768500 | |
| }, | |
| { | |
| "epoch": 46.66, | |
| "learning_rate": 8.339466658576543e-06, | |
| "loss": 0.0932, | |
| "step": 769000 | |
| }, | |
| { | |
| "epoch": 46.69, | |
| "learning_rate": 8.331882167344215e-06, | |
| "loss": 0.0934, | |
| "step": 769500 | |
| }, | |
| { | |
| "epoch": 46.72, | |
| "learning_rate": 8.324297676111886e-06, | |
| "loss": 0.0939, | |
| "step": 770000 | |
| }, | |
| { | |
| "epoch": 46.75, | |
| "learning_rate": 8.316713184879559e-06, | |
| "loss": 0.0941, | |
| "step": 770500 | |
| }, | |
| { | |
| "epoch": 46.78, | |
| "learning_rate": 8.30912869364723e-06, | |
| "loss": 0.0966, | |
| "step": 771000 | |
| }, | |
| { | |
| "epoch": 46.81, | |
| "learning_rate": 8.301559371397367e-06, | |
| "loss": 0.0963, | |
| "step": 771500 | |
| }, | |
| { | |
| "epoch": 46.84, | |
| "learning_rate": 8.293974880165039e-06, | |
| "loss": 0.0924, | |
| "step": 772000 | |
| }, | |
| { | |
| "epoch": 46.87, | |
| "learning_rate": 8.286390388932711e-06, | |
| "loss": 0.0957, | |
| "step": 772500 | |
| }, | |
| { | |
| "epoch": 46.9, | |
| "learning_rate": 8.278805897700383e-06, | |
| "loss": 0.0963, | |
| "step": 773000 | |
| }, | |
| { | |
| "epoch": 46.93, | |
| "learning_rate": 8.271221406468056e-06, | |
| "loss": 0.0948, | |
| "step": 773500 | |
| }, | |
| { | |
| "epoch": 46.96, | |
| "learning_rate": 8.263636915235727e-06, | |
| "loss": 0.0978, | |
| "step": 774000 | |
| }, | |
| { | |
| "epoch": 46.99, | |
| "learning_rate": 8.256067592985864e-06, | |
| "loss": 0.0963, | |
| "step": 774500 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "eval_bleu": 81.339, | |
| "eval_gen_len": 14.1472, | |
| "eval_loss": 0.16813451051712036, | |
| "eval_runtime": 178.5484, | |
| "eval_samples_per_second": 90.306, | |
| "eval_steps_per_second": 2.823, | |
| "step": 774607 | |
| }, | |
| { | |
| "epoch": 47.02, | |
| "learning_rate": 8.248483101753535e-06, | |
| "loss": 0.0917, | |
| "step": 775000 | |
| }, | |
| { | |
| "epoch": 47.05, | |
| "learning_rate": 8.240898610521208e-06, | |
| "loss": 0.0903, | |
| "step": 775500 | |
| }, | |
| { | |
| "epoch": 47.08, | |
| "learning_rate": 8.23331411928888e-06, | |
| "loss": 0.094, | |
| "step": 776000 | |
| }, | |
| { | |
| "epoch": 47.11, | |
| "learning_rate": 8.225744797039017e-06, | |
| "loss": 0.0927, | |
| "step": 776500 | |
| }, | |
| { | |
| "epoch": 47.15, | |
| "learning_rate": 8.218160305806688e-06, | |
| "loss": 0.0906, | |
| "step": 777000 | |
| }, | |
| { | |
| "epoch": 47.18, | |
| "learning_rate": 8.210575814574359e-06, | |
| "loss": 0.0925, | |
| "step": 777500 | |
| }, | |
| { | |
| "epoch": 47.21, | |
| "learning_rate": 8.20299132334203e-06, | |
| "loss": 0.0925, | |
| "step": 778000 | |
| }, | |
| { | |
| "epoch": 47.24, | |
| "learning_rate": 8.195406832109703e-06, | |
| "loss": 0.0932, | |
| "step": 778500 | |
| }, | |
| { | |
| "epoch": 47.27, | |
| "learning_rate": 8.187822340877374e-06, | |
| "loss": 0.0928, | |
| "step": 779000 | |
| }, | |
| { | |
| "epoch": 47.3, | |
| "learning_rate": 8.180237849645046e-06, | |
| "loss": 0.0941, | |
| "step": 779500 | |
| }, | |
| { | |
| "epoch": 47.33, | |
| "learning_rate": 8.172668527395183e-06, | |
| "loss": 0.0902, | |
| "step": 780000 | |
| }, | |
| { | |
| "epoch": 47.36, | |
| "learning_rate": 8.165084036162854e-06, | |
| "loss": 0.0922, | |
| "step": 780500 | |
| }, | |
| { | |
| "epoch": 47.39, | |
| "learning_rate": 8.157514713912991e-06, | |
| "loss": 0.0929, | |
| "step": 781000 | |
| }, | |
| { | |
| "epoch": 47.42, | |
| "learning_rate": 8.149930222680662e-06, | |
| "loss": 0.0939, | |
| "step": 781500 | |
| }, | |
| { | |
| "epoch": 47.45, | |
| "learning_rate": 8.142345731448335e-06, | |
| "loss": 0.0942, | |
| "step": 782000 | |
| }, | |
| { | |
| "epoch": 47.48, | |
| "learning_rate": 8.134761240216007e-06, | |
| "loss": 0.093, | |
| "step": 782500 | |
| }, | |
| { | |
| "epoch": 47.51, | |
| "learning_rate": 8.127176748983678e-06, | |
| "loss": 0.0916, | |
| "step": 783000 | |
| }, | |
| { | |
| "epoch": 47.54, | |
| "learning_rate": 8.11959225775135e-06, | |
| "loss": 0.0931, | |
| "step": 783500 | |
| }, | |
| { | |
| "epoch": 47.57, | |
| "learning_rate": 8.112007766519022e-06, | |
| "loss": 0.0923, | |
| "step": 784000 | |
| }, | |
| { | |
| "epoch": 47.6, | |
| "learning_rate": 8.104423275286695e-06, | |
| "loss": 0.0928, | |
| "step": 784500 | |
| }, | |
| { | |
| "epoch": 47.63, | |
| "learning_rate": 8.096838784054366e-06, | |
| "loss": 0.0933, | |
| "step": 785000 | |
| }, | |
| { | |
| "epoch": 47.66, | |
| "learning_rate": 8.089254292822039e-06, | |
| "loss": 0.0935, | |
| "step": 785500 | |
| }, | |
| { | |
| "epoch": 47.69, | |
| "learning_rate": 8.08166980158971e-06, | |
| "loss": 0.0922, | |
| "step": 786000 | |
| }, | |
| { | |
| "epoch": 47.72, | |
| "learning_rate": 8.074085310357382e-06, | |
| "loss": 0.0941, | |
| "step": 786500 | |
| }, | |
| { | |
| "epoch": 47.75, | |
| "learning_rate": 8.066515988107519e-06, | |
| "loss": 0.0933, | |
| "step": 787000 | |
| }, | |
| { | |
| "epoch": 47.78, | |
| "learning_rate": 8.05893149687519e-06, | |
| "loss": 0.0939, | |
| "step": 787500 | |
| }, | |
| { | |
| "epoch": 47.81, | |
| "learning_rate": 8.051347005642863e-06, | |
| "loss": 0.093, | |
| "step": 788000 | |
| }, | |
| { | |
| "epoch": 47.84, | |
| "learning_rate": 8.043762514410534e-06, | |
| "loss": 0.095, | |
| "step": 788500 | |
| }, | |
| { | |
| "epoch": 47.87, | |
| "learning_rate": 8.036193192160671e-06, | |
| "loss": 0.0941, | |
| "step": 789000 | |
| }, | |
| { | |
| "epoch": 47.9, | |
| "learning_rate": 8.028608700928342e-06, | |
| "loss": 0.0957, | |
| "step": 789500 | |
| }, | |
| { | |
| "epoch": 47.93, | |
| "learning_rate": 8.02103937867848e-06, | |
| "loss": 0.0935, | |
| "step": 790000 | |
| }, | |
| { | |
| "epoch": 47.96, | |
| "learning_rate": 8.01345488744615e-06, | |
| "loss": 0.0941, | |
| "step": 790500 | |
| }, | |
| { | |
| "epoch": 47.99, | |
| "learning_rate": 8.005885565196288e-06, | |
| "loss": 0.0929, | |
| "step": 791000 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_bleu": 81.3094, | |
| "eval_gen_len": 14.1392, | |
| "eval_loss": 0.16808539628982544, | |
| "eval_runtime": 178.2856, | |
| "eval_samples_per_second": 90.439, | |
| "eval_steps_per_second": 2.827, | |
| "step": 791088 | |
| }, | |
| { | |
| "epoch": 48.02, | |
| "learning_rate": 7.99830107396396e-06, | |
| "loss": 0.0911, | |
| "step": 791500 | |
| }, | |
| { | |
| "epoch": 48.06, | |
| "learning_rate": 7.990716582731632e-06, | |
| "loss": 0.0914, | |
| "step": 792000 | |
| }, | |
| { | |
| "epoch": 48.09, | |
| "learning_rate": 7.983132091499303e-06, | |
| "loss": 0.0919, | |
| "step": 792500 | |
| }, | |
| { | |
| "epoch": 48.12, | |
| "learning_rate": 7.975547600266975e-06, | |
| "loss": 0.0893, | |
| "step": 793000 | |
| }, | |
| { | |
| "epoch": 48.15, | |
| "learning_rate": 7.967963109034646e-06, | |
| "loss": 0.089, | |
| "step": 793500 | |
| }, | |
| { | |
| "epoch": 48.18, | |
| "learning_rate": 7.960378617802319e-06, | |
| "loss": 0.0903, | |
| "step": 794000 | |
| }, | |
| { | |
| "epoch": 48.21, | |
| "learning_rate": 7.95279412656999e-06, | |
| "loss": 0.0927, | |
| "step": 794500 | |
| }, | |
| { | |
| "epoch": 48.24, | |
| "learning_rate": 7.945209635337661e-06, | |
| "loss": 0.0933, | |
| "step": 795000 | |
| }, | |
| { | |
| "epoch": 48.27, | |
| "learning_rate": 7.937640313087798e-06, | |
| "loss": 0.0919, | |
| "step": 795500 | |
| }, | |
| { | |
| "epoch": 48.3, | |
| "learning_rate": 7.93005582185547e-06, | |
| "loss": 0.0903, | |
| "step": 796000 | |
| }, | |
| { | |
| "epoch": 48.33, | |
| "learning_rate": 7.922471330623143e-06, | |
| "loss": 0.0928, | |
| "step": 796500 | |
| }, | |
| { | |
| "epoch": 48.36, | |
| "learning_rate": 7.914886839390814e-06, | |
| "loss": 0.0925, | |
| "step": 797000 | |
| }, | |
| { | |
| "epoch": 48.39, | |
| "learning_rate": 7.907302348158487e-06, | |
| "loss": 0.0916, | |
| "step": 797500 | |
| }, | |
| { | |
| "epoch": 48.42, | |
| "learning_rate": 7.899717856926158e-06, | |
| "loss": 0.0943, | |
| "step": 798000 | |
| }, | |
| { | |
| "epoch": 48.45, | |
| "learning_rate": 7.892148534676295e-06, | |
| "loss": 0.0897, | |
| "step": 798500 | |
| }, | |
| { | |
| "epoch": 48.48, | |
| "learning_rate": 7.884564043443966e-06, | |
| "loss": 0.0908, | |
| "step": 799000 | |
| }, | |
| { | |
| "epoch": 48.51, | |
| "learning_rate": 7.87697955221164e-06, | |
| "loss": 0.0933, | |
| "step": 799500 | |
| }, | |
| { | |
| "epoch": 48.54, | |
| "learning_rate": 7.86939506097931e-06, | |
| "loss": 0.0925, | |
| "step": 800000 | |
| }, | |
| { | |
| "epoch": 48.57, | |
| "learning_rate": 7.861810569746982e-06, | |
| "loss": 0.0923, | |
| "step": 800500 | |
| }, | |
| { | |
| "epoch": 48.6, | |
| "learning_rate": 7.854241247497119e-06, | |
| "loss": 0.0923, | |
| "step": 801000 | |
| }, | |
| { | |
| "epoch": 48.63, | |
| "learning_rate": 7.84665675626479e-06, | |
| "loss": 0.091, | |
| "step": 801500 | |
| }, | |
| { | |
| "epoch": 48.66, | |
| "learning_rate": 7.839072265032463e-06, | |
| "loss": 0.0929, | |
| "step": 802000 | |
| }, | |
| { | |
| "epoch": 48.69, | |
| "learning_rate": 7.831487773800134e-06, | |
| "loss": 0.0954, | |
| "step": 802500 | |
| }, | |
| { | |
| "epoch": 48.72, | |
| "learning_rate": 7.823918451550271e-06, | |
| "loss": 0.092, | |
| "step": 803000 | |
| }, | |
| { | |
| "epoch": 48.75, | |
| "learning_rate": 7.816333960317943e-06, | |
| "loss": 0.092, | |
| "step": 803500 | |
| }, | |
| { | |
| "epoch": 48.78, | |
| "learning_rate": 7.808749469085614e-06, | |
| "loss": 0.0893, | |
| "step": 804000 | |
| }, | |
| { | |
| "epoch": 48.81, | |
| "learning_rate": 7.801164977853287e-06, | |
| "loss": 0.0913, | |
| "step": 804500 | |
| }, | |
| { | |
| "epoch": 48.84, | |
| "learning_rate": 7.793580486620958e-06, | |
| "loss": 0.0918, | |
| "step": 805000 | |
| }, | |
| { | |
| "epoch": 48.87, | |
| "learning_rate": 7.786011164371095e-06, | |
| "loss": 0.093, | |
| "step": 805500 | |
| }, | |
| { | |
| "epoch": 48.9, | |
| "learning_rate": 7.778426673138766e-06, | |
| "loss": 0.0937, | |
| "step": 806000 | |
| }, | |
| { | |
| "epoch": 48.94, | |
| "learning_rate": 7.770842181906438e-06, | |
| "loss": 0.0904, | |
| "step": 806500 | |
| }, | |
| { | |
| "epoch": 48.97, | |
| "learning_rate": 7.763257690674109e-06, | |
| "loss": 0.0962, | |
| "step": 807000 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "learning_rate": 7.755673199441782e-06, | |
| "loss": 0.0916, | |
| "step": 807500 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "eval_bleu": 81.294, | |
| "eval_gen_len": 14.1299, | |
| "eval_loss": 0.16902963817119598, | |
| "eval_runtime": 178.1975, | |
| "eval_samples_per_second": 90.484, | |
| "eval_steps_per_second": 2.828, | |
| "step": 807569 | |
| }, | |
| { | |
| "epoch": 49.03, | |
| "learning_rate": 7.748103877191917e-06, | |
| "loss": 0.0899, | |
| "step": 808000 | |
| }, | |
| { | |
| "epoch": 49.06, | |
| "learning_rate": 7.74051938595959e-06, | |
| "loss": 0.0887, | |
| "step": 808500 | |
| }, | |
| { | |
| "epoch": 49.09, | |
| "learning_rate": 7.732934894727261e-06, | |
| "loss": 0.0899, | |
| "step": 809000 | |
| }, | |
| { | |
| "epoch": 49.12, | |
| "learning_rate": 7.725350403494934e-06, | |
| "loss": 0.0889, | |
| "step": 809500 | |
| }, | |
| { | |
| "epoch": 49.15, | |
| "learning_rate": 7.71778108124507e-06, | |
| "loss": 0.0909, | |
| "step": 810000 | |
| }, | |
| { | |
| "epoch": 49.18, | |
| "learning_rate": 7.710196590012743e-06, | |
| "loss": 0.0898, | |
| "step": 810500 | |
| }, | |
| { | |
| "epoch": 49.21, | |
| "learning_rate": 7.702612098780414e-06, | |
| "loss": 0.0903, | |
| "step": 811000 | |
| }, | |
| { | |
| "epoch": 49.24, | |
| "learning_rate": 7.695027607548087e-06, | |
| "loss": 0.0886, | |
| "step": 811500 | |
| }, | |
| { | |
| "epoch": 49.27, | |
| "learning_rate": 7.687443116315758e-06, | |
| "loss": 0.0909, | |
| "step": 812000 | |
| }, | |
| { | |
| "epoch": 49.3, | |
| "learning_rate": 7.67985862508343e-06, | |
| "loss": 0.0901, | |
| "step": 812500 | |
| }, | |
| { | |
| "epoch": 49.33, | |
| "learning_rate": 7.672289302833567e-06, | |
| "loss": 0.0901, | |
| "step": 813000 | |
| }, | |
| { | |
| "epoch": 49.36, | |
| "learning_rate": 7.664704811601238e-06, | |
| "loss": 0.0913, | |
| "step": 813500 | |
| }, | |
| { | |
| "epoch": 49.39, | |
| "learning_rate": 7.65712032036891e-06, | |
| "loss": 0.0912, | |
| "step": 814000 | |
| }, | |
| { | |
| "epoch": 49.42, | |
| "learning_rate": 7.649535829136582e-06, | |
| "loss": 0.0903, | |
| "step": 814500 | |
| }, | |
| { | |
| "epoch": 49.45, | |
| "learning_rate": 7.641951337904255e-06, | |
| "loss": 0.0917, | |
| "step": 815000 | |
| }, | |
| { | |
| "epoch": 49.48, | |
| "learning_rate": 7.634366846671926e-06, | |
| "loss": 0.0896, | |
| "step": 815500 | |
| }, | |
| { | |
| "epoch": 49.51, | |
| "learning_rate": 7.626782355439598e-06, | |
| "loss": 0.0912, | |
| "step": 816000 | |
| }, | |
| { | |
| "epoch": 49.54, | |
| "learning_rate": 7.6191978642072695e-06, | |
| "loss": 0.089, | |
| "step": 816500 | |
| }, | |
| { | |
| "epoch": 49.57, | |
| "learning_rate": 7.611628541957407e-06, | |
| "loss": 0.0919, | |
| "step": 817000 | |
| }, | |
| { | |
| "epoch": 49.6, | |
| "learning_rate": 7.604044050725078e-06, | |
| "loss": 0.092, | |
| "step": 817500 | |
| }, | |
| { | |
| "epoch": 49.63, | |
| "learning_rate": 7.596459559492751e-06, | |
| "loss": 0.0916, | |
| "step": 818000 | |
| }, | |
| { | |
| "epoch": 49.66, | |
| "learning_rate": 7.588875068260422e-06, | |
| "loss": 0.0882, | |
| "step": 818500 | |
| }, | |
| { | |
| "epoch": 49.69, | |
| "learning_rate": 7.5813057460105575e-06, | |
| "loss": 0.0918, | |
| "step": 819000 | |
| }, | |
| { | |
| "epoch": 49.72, | |
| "learning_rate": 7.57372125477823e-06, | |
| "loss": 0.0904, | |
| "step": 819500 | |
| }, | |
| { | |
| "epoch": 49.75, | |
| "learning_rate": 7.566136763545902e-06, | |
| "loss": 0.0916, | |
| "step": 820000 | |
| }, | |
| { | |
| "epoch": 49.78, | |
| "learning_rate": 7.558567441296039e-06, | |
| "loss": 0.0902, | |
| "step": 820500 | |
| }, | |
| { | |
| "epoch": 49.81, | |
| "learning_rate": 7.55098295006371e-06, | |
| "loss": 0.0918, | |
| "step": 821000 | |
| }, | |
| { | |
| "epoch": 49.85, | |
| "learning_rate": 7.543398458831382e-06, | |
| "loss": 0.0892, | |
| "step": 821500 | |
| }, | |
| { | |
| "epoch": 49.88, | |
| "learning_rate": 7.535813967599054e-06, | |
| "loss": 0.0914, | |
| "step": 822000 | |
| }, | |
| { | |
| "epoch": 49.91, | |
| "learning_rate": 7.528229476366726e-06, | |
| "loss": 0.0906, | |
| "step": 822500 | |
| }, | |
| { | |
| "epoch": 49.94, | |
| "learning_rate": 7.5206601541168625e-06, | |
| "loss": 0.0915, | |
| "step": 823000 | |
| }, | |
| { | |
| "epoch": 49.97, | |
| "learning_rate": 7.513075662884535e-06, | |
| "loss": 0.0919, | |
| "step": 823500 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "learning_rate": 7.505491171652206e-06, | |
| "loss": 0.0918, | |
| "step": 824000 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_bleu": 81.2345, | |
| "eval_gen_len": 14.1368, | |
| "eval_loss": 0.16936491429805756, | |
| "eval_runtime": 178.0893, | |
| "eval_samples_per_second": 90.539, | |
| "eval_steps_per_second": 2.83, | |
| "step": 824050 | |
| }, | |
| { | |
| "epoch": 50.03, | |
| "learning_rate": 7.497906680419879e-06, | |
| "loss": 0.0893, | |
| "step": 824500 | |
| }, | |
| { | |
| "epoch": 50.06, | |
| "learning_rate": 7.49032218918755e-06, | |
| "loss": 0.0881, | |
| "step": 825000 | |
| }, | |
| { | |
| "epoch": 50.09, | |
| "learning_rate": 7.482737697955221e-06, | |
| "loss": 0.0873, | |
| "step": 825500 | |
| }, | |
| { | |
| "epoch": 50.12, | |
| "learning_rate": 7.475168375705358e-06, | |
| "loss": 0.0892, | |
| "step": 826000 | |
| }, | |
| { | |
| "epoch": 50.15, | |
| "learning_rate": 7.46758388447303e-06, | |
| "loss": 0.0892, | |
| "step": 826500 | |
| }, | |
| { | |
| "epoch": 50.18, | |
| "learning_rate": 7.459999393240703e-06, | |
| "loss": 0.0907, | |
| "step": 827000 | |
| }, | |
| { | |
| "epoch": 50.21, | |
| "learning_rate": 7.452414902008374e-06, | |
| "loss": 0.0877, | |
| "step": 827500 | |
| }, | |
| { | |
| "epoch": 50.24, | |
| "learning_rate": 7.444830410776046e-06, | |
| "loss": 0.0893, | |
| "step": 828000 | |
| }, | |
| { | |
| "epoch": 50.27, | |
| "learning_rate": 7.437245919543717e-06, | |
| "loss": 0.0901, | |
| "step": 828500 | |
| }, | |
| { | |
| "epoch": 50.3, | |
| "learning_rate": 7.42966142831139e-06, | |
| "loss": 0.09, | |
| "step": 829000 | |
| }, | |
| { | |
| "epoch": 50.33, | |
| "learning_rate": 7.422076937079061e-06, | |
| "loss": 0.0872, | |
| "step": 829500 | |
| }, | |
| { | |
| "epoch": 50.36, | |
| "learning_rate": 7.414522783811663e-06, | |
| "loss": 0.0892, | |
| "step": 830000 | |
| }, | |
| { | |
| "epoch": 50.39, | |
| "learning_rate": 7.406938292579334e-06, | |
| "loss": 0.0883, | |
| "step": 830500 | |
| }, | |
| { | |
| "epoch": 50.42, | |
| "learning_rate": 7.399353801347007e-06, | |
| "loss": 0.0896, | |
| "step": 831000 | |
| }, | |
| { | |
| "epoch": 50.45, | |
| "learning_rate": 7.391769310114678e-06, | |
| "loss": 0.0871, | |
| "step": 831500 | |
| }, | |
| { | |
| "epoch": 50.48, | |
| "learning_rate": 7.384184818882349e-06, | |
| "loss": 0.0913, | |
| "step": 832000 | |
| }, | |
| { | |
| "epoch": 50.51, | |
| "learning_rate": 7.376600327650022e-06, | |
| "loss": 0.0898, | |
| "step": 832500 | |
| }, | |
| { | |
| "epoch": 50.54, | |
| "learning_rate": 7.3690158364176935e-06, | |
| "loss": 0.0899, | |
| "step": 833000 | |
| }, | |
| { | |
| "epoch": 50.57, | |
| "learning_rate": 7.3614313451853656e-06, | |
| "loss": 0.0902, | |
| "step": 833500 | |
| }, | |
| { | |
| "epoch": 50.6, | |
| "learning_rate": 7.353862022935502e-06, | |
| "loss": 0.0916, | |
| "step": 834000 | |
| }, | |
| { | |
| "epoch": 50.63, | |
| "learning_rate": 7.346277531703174e-06, | |
| "loss": 0.0918, | |
| "step": 834500 | |
| }, | |
| { | |
| "epoch": 50.66, | |
| "learning_rate": 7.338693040470846e-06, | |
| "loss": 0.0907, | |
| "step": 835000 | |
| }, | |
| { | |
| "epoch": 50.69, | |
| "learning_rate": 7.331108549238518e-06, | |
| "loss": 0.0891, | |
| "step": 835500 | |
| }, | |
| { | |
| "epoch": 50.73, | |
| "learning_rate": 7.323524058006189e-06, | |
| "loss": 0.0898, | |
| "step": 836000 | |
| }, | |
| { | |
| "epoch": 50.76, | |
| "learning_rate": 7.315939566773861e-06, | |
| "loss": 0.0908, | |
| "step": 836500 | |
| }, | |
| { | |
| "epoch": 50.79, | |
| "learning_rate": 7.3083550755415335e-06, | |
| "loss": 0.0904, | |
| "step": 837000 | |
| }, | |
| { | |
| "epoch": 50.82, | |
| "learning_rate": 7.300770584309205e-06, | |
| "loss": 0.0899, | |
| "step": 837500 | |
| }, | |
| { | |
| "epoch": 50.85, | |
| "learning_rate": 7.293186093076877e-06, | |
| "loss": 0.0902, | |
| "step": 838000 | |
| }, | |
| { | |
| "epoch": 50.88, | |
| "learning_rate": 7.285601601844549e-06, | |
| "loss": 0.0899, | |
| "step": 838500 | |
| }, | |
| { | |
| "epoch": 50.91, | |
| "learning_rate": 7.278032279594685e-06, | |
| "loss": 0.0891, | |
| "step": 839000 | |
| }, | |
| { | |
| "epoch": 50.94, | |
| "learning_rate": 7.270447788362357e-06, | |
| "loss": 0.0913, | |
| "step": 839500 | |
| }, | |
| { | |
| "epoch": 50.97, | |
| "learning_rate": 7.262863297130029e-06, | |
| "loss": 0.0903, | |
| "step": 840000 | |
| }, | |
| { | |
| "epoch": 51.0, | |
| "learning_rate": 7.255278805897701e-06, | |
| "loss": 0.0898, | |
| "step": 840500 | |
| }, | |
| { | |
| "epoch": 51.0, | |
| "eval_bleu": 81.3532, | |
| "eval_gen_len": 14.1407, | |
| "eval_loss": 0.1701522320508957, | |
| "eval_runtime": 178.4826, | |
| "eval_samples_per_second": 90.339, | |
| "eval_steps_per_second": 2.824, | |
| "step": 840531 | |
| }, | |
| { | |
| "epoch": 51.03, | |
| "learning_rate": 7.247694314665374e-06, | |
| "loss": 0.0886, | |
| "step": 841000 | |
| }, | |
| { | |
| "epoch": 51.06, | |
| "learning_rate": 7.240109823433045e-06, | |
| "loss": 0.088, | |
| "step": 841500 | |
| }, | |
| { | |
| "epoch": 51.09, | |
| "learning_rate": 7.232540501183182e-06, | |
| "loss": 0.089, | |
| "step": 842000 | |
| }, | |
| { | |
| "epoch": 51.12, | |
| "learning_rate": 7.224956009950853e-06, | |
| "loss": 0.0868, | |
| "step": 842500 | |
| }, | |
| { | |
| "epoch": 51.15, | |
| "learning_rate": 7.2173715187185244e-06, | |
| "loss": 0.0882, | |
| "step": 843000 | |
| }, | |
| { | |
| "epoch": 51.18, | |
| "learning_rate": 7.209787027486197e-06, | |
| "loss": 0.0886, | |
| "step": 843500 | |
| }, | |
| { | |
| "epoch": 51.21, | |
| "learning_rate": 7.202202536253869e-06, | |
| "loss": 0.0867, | |
| "step": 844000 | |
| }, | |
| { | |
| "epoch": 51.24, | |
| "learning_rate": 7.194618045021541e-06, | |
| "loss": 0.0873, | |
| "step": 844500 | |
| }, | |
| { | |
| "epoch": 51.27, | |
| "learning_rate": 7.187033553789212e-06, | |
| "loss": 0.0886, | |
| "step": 845000 | |
| }, | |
| { | |
| "epoch": 51.3, | |
| "learning_rate": 7.179449062556885e-06, | |
| "loss": 0.0872, | |
| "step": 845500 | |
| }, | |
| { | |
| "epoch": 51.33, | |
| "learning_rate": 7.17187974030702e-06, | |
| "loss": 0.0874, | |
| "step": 846000 | |
| }, | |
| { | |
| "epoch": 51.36, | |
| "learning_rate": 7.164295249074693e-06, | |
| "loss": 0.0881, | |
| "step": 846500 | |
| }, | |
| { | |
| "epoch": 51.39, | |
| "learning_rate": 7.1567107578423645e-06, | |
| "loss": 0.0867, | |
| "step": 847000 | |
| }, | |
| { | |
| "epoch": 51.42, | |
| "learning_rate": 7.149126266610036e-06, | |
| "loss": 0.0882, | |
| "step": 847500 | |
| }, | |
| { | |
| "epoch": 51.45, | |
| "learning_rate": 7.141572113342638e-06, | |
| "loss": 0.0897, | |
| "step": 848000 | |
| }, | |
| { | |
| "epoch": 51.48, | |
| "learning_rate": 7.13398762211031e-06, | |
| "loss": 0.0875, | |
| "step": 848500 | |
| }, | |
| { | |
| "epoch": 51.51, | |
| "learning_rate": 7.126403130877981e-06, | |
| "loss": 0.0874, | |
| "step": 849000 | |
| }, | |
| { | |
| "epoch": 51.54, | |
| "learning_rate": 7.1188186396456524e-06, | |
| "loss": 0.0894, | |
| "step": 849500 | |
| }, | |
| { | |
| "epoch": 51.57, | |
| "learning_rate": 7.111234148413325e-06, | |
| "loss": 0.0878, | |
| "step": 850000 | |
| }, | |
| { | |
| "epoch": 51.6, | |
| "learning_rate": 7.103649657180997e-06, | |
| "loss": 0.0886, | |
| "step": 850500 | |
| }, | |
| { | |
| "epoch": 51.64, | |
| "learning_rate": 7.096065165948669e-06, | |
| "loss": 0.09, | |
| "step": 851000 | |
| }, | |
| { | |
| "epoch": 51.67, | |
| "learning_rate": 7.08848067471634e-06, | |
| "loss": 0.0897, | |
| "step": 851500 | |
| }, | |
| { | |
| "epoch": 51.7, | |
| "learning_rate": 7.080926521448942e-06, | |
| "loss": 0.0896, | |
| "step": 852000 | |
| }, | |
| { | |
| "epoch": 51.73, | |
| "learning_rate": 7.073342030216613e-06, | |
| "loss": 0.0877, | |
| "step": 852500 | |
| }, | |
| { | |
| "epoch": 51.76, | |
| "learning_rate": 7.065757538984286e-06, | |
| "loss": 0.089, | |
| "step": 853000 | |
| }, | |
| { | |
| "epoch": 51.79, | |
| "learning_rate": 7.0581730477519575e-06, | |
| "loss": 0.0893, | |
| "step": 853500 | |
| }, | |
| { | |
| "epoch": 51.82, | |
| "learning_rate": 7.05058855651963e-06, | |
| "loss": 0.0897, | |
| "step": 854000 | |
| }, | |
| { | |
| "epoch": 51.85, | |
| "learning_rate": 7.043004065287301e-06, | |
| "loss": 0.0872, | |
| "step": 854500 | |
| }, | |
| { | |
| "epoch": 51.88, | |
| "learning_rate": 7.035419574054972e-06, | |
| "loss": 0.0877, | |
| "step": 855000 | |
| }, | |
| { | |
| "epoch": 51.91, | |
| "learning_rate": 7.027835082822645e-06, | |
| "loss": 0.0901, | |
| "step": 855500 | |
| }, | |
| { | |
| "epoch": 51.94, | |
| "learning_rate": 7.0202657605727804e-06, | |
| "loss": 0.0878, | |
| "step": 856000 | |
| }, | |
| { | |
| "epoch": 51.97, | |
| "learning_rate": 7.012681269340453e-06, | |
| "loss": 0.0901, | |
| "step": 856500 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "learning_rate": 7.005096778108125e-06, | |
| "loss": 0.0889, | |
| "step": 857000 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_bleu": 81.286, | |
| "eval_gen_len": 14.1467, | |
| "eval_loss": 0.17058435082435608, | |
| "eval_runtime": 178.2603, | |
| "eval_samples_per_second": 90.452, | |
| "eval_steps_per_second": 2.827, | |
| "step": 857012 | |
| }, | |
| { | |
| "epoch": 52.03, | |
| "learning_rate": 6.9975122868757976e-06, | |
| "loss": 0.0847, | |
| "step": 857500 | |
| }, | |
| { | |
| "epoch": 52.06, | |
| "learning_rate": 6.989942964625933e-06, | |
| "loss": 0.0872, | |
| "step": 858000 | |
| }, | |
| { | |
| "epoch": 52.09, | |
| "learning_rate": 6.982358473393606e-06, | |
| "loss": 0.0868, | |
| "step": 858500 | |
| }, | |
| { | |
| "epoch": 52.12, | |
| "learning_rate": 6.974773982161277e-06, | |
| "loss": 0.0842, | |
| "step": 859000 | |
| }, | |
| { | |
| "epoch": 52.15, | |
| "learning_rate": 6.967204659911414e-06, | |
| "loss": 0.0865, | |
| "step": 859500 | |
| }, | |
| { | |
| "epoch": 52.18, | |
| "learning_rate": 6.9596201686790855e-06, | |
| "loss": 0.0862, | |
| "step": 860000 | |
| }, | |
| { | |
| "epoch": 52.21, | |
| "learning_rate": 6.952035677446758e-06, | |
| "loss": 0.0874, | |
| "step": 860500 | |
| }, | |
| { | |
| "epoch": 52.24, | |
| "learning_rate": 6.944451186214429e-06, | |
| "loss": 0.0897, | |
| "step": 861000 | |
| }, | |
| { | |
| "epoch": 52.27, | |
| "learning_rate": 6.936866694982101e-06, | |
| "loss": 0.0854, | |
| "step": 861500 | |
| }, | |
| { | |
| "epoch": 52.3, | |
| "learning_rate": 6.929282203749773e-06, | |
| "loss": 0.0866, | |
| "step": 862000 | |
| }, | |
| { | |
| "epoch": 52.33, | |
| "learning_rate": 6.921697712517444e-06, | |
| "loss": 0.0878, | |
| "step": 862500 | |
| }, | |
| { | |
| "epoch": 52.36, | |
| "learning_rate": 6.914128390267581e-06, | |
| "loss": 0.0867, | |
| "step": 863000 | |
| }, | |
| { | |
| "epoch": 52.39, | |
| "learning_rate": 6.906543899035253e-06, | |
| "loss": 0.0877, | |
| "step": 863500 | |
| }, | |
| { | |
| "epoch": 52.42, | |
| "learning_rate": 6.8989594078029256e-06, | |
| "loss": 0.0879, | |
| "step": 864000 | |
| }, | |
| { | |
| "epoch": 52.45, | |
| "learning_rate": 6.891374916570597e-06, | |
| "loss": 0.0893, | |
| "step": 864500 | |
| }, | |
| { | |
| "epoch": 52.48, | |
| "learning_rate": 6.883790425338269e-06, | |
| "loss": 0.0879, | |
| "step": 865000 | |
| }, | |
| { | |
| "epoch": 52.52, | |
| "learning_rate": 6.876205934105941e-06, | |
| "loss": 0.0851, | |
| "step": 865500 | |
| }, | |
| { | |
| "epoch": 52.55, | |
| "learning_rate": 6.868636611856077e-06, | |
| "loss": 0.0883, | |
| "step": 866000 | |
| }, | |
| { | |
| "epoch": 52.58, | |
| "learning_rate": 6.861052120623749e-06, | |
| "loss": 0.089, | |
| "step": 866500 | |
| }, | |
| { | |
| "epoch": 52.61, | |
| "learning_rate": 6.8534676293914214e-06, | |
| "loss": 0.0892, | |
| "step": 867000 | |
| }, | |
| { | |
| "epoch": 52.64, | |
| "learning_rate": 6.845883138159093e-06, | |
| "loss": 0.0878, | |
| "step": 867500 | |
| }, | |
| { | |
| "epoch": 52.67, | |
| "learning_rate": 6.838298646926764e-06, | |
| "loss": 0.0846, | |
| "step": 868000 | |
| }, | |
| { | |
| "epoch": 52.7, | |
| "learning_rate": 6.830714155694437e-06, | |
| "loss": 0.0863, | |
| "step": 868500 | |
| }, | |
| { | |
| "epoch": 52.73, | |
| "learning_rate": 6.823129664462108e-06, | |
| "loss": 0.0883, | |
| "step": 869000 | |
| }, | |
| { | |
| "epoch": 52.76, | |
| "learning_rate": 6.81554517322978e-06, | |
| "loss": 0.0879, | |
| "step": 869500 | |
| }, | |
| { | |
| "epoch": 52.79, | |
| "learning_rate": 6.8079758509799165e-06, | |
| "loss": 0.0882, | |
| "step": 870000 | |
| }, | |
| { | |
| "epoch": 52.82, | |
| "learning_rate": 6.800391359747589e-06, | |
| "loss": 0.0866, | |
| "step": 870500 | |
| }, | |
| { | |
| "epoch": 52.85, | |
| "learning_rate": 6.792806868515261e-06, | |
| "loss": 0.0883, | |
| "step": 871000 | |
| }, | |
| { | |
| "epoch": 52.88, | |
| "learning_rate": 6.785222377282933e-06, | |
| "loss": 0.0874, | |
| "step": 871500 | |
| }, | |
| { | |
| "epoch": 52.91, | |
| "learning_rate": 6.777653055033069e-06, | |
| "loss": 0.0852, | |
| "step": 872000 | |
| }, | |
| { | |
| "epoch": 52.94, | |
| "learning_rate": 6.770068563800741e-06, | |
| "loss": 0.0867, | |
| "step": 872500 | |
| }, | |
| { | |
| "epoch": 52.97, | |
| "learning_rate": 6.762484072568412e-06, | |
| "loss": 0.0876, | |
| "step": 873000 | |
| }, | |
| { | |
| "epoch": 53.0, | |
| "eval_bleu": 81.2699, | |
| "eval_gen_len": 14.1363, | |
| "eval_loss": 0.1710740476846695, | |
| "eval_runtime": 178.2258, | |
| "eval_samples_per_second": 90.47, | |
| "eval_steps_per_second": 2.828, | |
| "step": 873493 | |
| }, | |
| { | |
| "epoch": 53.0, | |
| "learning_rate": 6.7548995813360844e-06, | |
| "loss": 0.0885, | |
| "step": 873500 | |
| }, | |
| { | |
| "epoch": 53.03, | |
| "learning_rate": 6.747330259086221e-06, | |
| "loss": 0.0851, | |
| "step": 874000 | |
| }, | |
| { | |
| "epoch": 53.06, | |
| "learning_rate": 6.739745767853893e-06, | |
| "loss": 0.0841, | |
| "step": 874500 | |
| }, | |
| { | |
| "epoch": 53.09, | |
| "learning_rate": 6.732161276621565e-06, | |
| "loss": 0.0838, | |
| "step": 875000 | |
| }, | |
| { | |
| "epoch": 53.12, | |
| "learning_rate": 6.724576785389236e-06, | |
| "loss": 0.0861, | |
| "step": 875500 | |
| }, | |
| { | |
| "epoch": 53.15, | |
| "learning_rate": 6.717007463139373e-06, | |
| "loss": 0.0841, | |
| "step": 876000 | |
| }, | |
| { | |
| "epoch": 53.18, | |
| "learning_rate": 6.7094229719070445e-06, | |
| "loss": 0.0842, | |
| "step": 876500 | |
| }, | |
| { | |
| "epoch": 53.21, | |
| "learning_rate": 6.701838480674717e-06, | |
| "loss": 0.0843, | |
| "step": 877000 | |
| }, | |
| { | |
| "epoch": 53.24, | |
| "learning_rate": 6.694253989442389e-06, | |
| "loss": 0.0868, | |
| "step": 877500 | |
| }, | |
| { | |
| "epoch": 53.27, | |
| "learning_rate": 6.686669498210061e-06, | |
| "loss": 0.0848, | |
| "step": 878000 | |
| }, | |
| { | |
| "epoch": 53.3, | |
| "learning_rate": 6.679085006977733e-06, | |
| "loss": 0.0865, | |
| "step": 878500 | |
| }, | |
| { | |
| "epoch": 53.33, | |
| "learning_rate": 6.671500515745404e-06, | |
| "loss": 0.0859, | |
| "step": 879000 | |
| }, | |
| { | |
| "epoch": 53.36, | |
| "learning_rate": 6.663916024513076e-06, | |
| "loss": 0.0873, | |
| "step": 879500 | |
| }, | |
| { | |
| "epoch": 53.39, | |
| "learning_rate": 6.656361871245678e-06, | |
| "loss": 0.087, | |
| "step": 880000 | |
| }, | |
| { | |
| "epoch": 53.43, | |
| "learning_rate": 6.6487773800133495e-06, | |
| "loss": 0.0869, | |
| "step": 880500 | |
| }, | |
| { | |
| "epoch": 53.46, | |
| "learning_rate": 6.641192888781021e-06, | |
| "loss": 0.0862, | |
| "step": 881000 | |
| }, | |
| { | |
| "epoch": 53.49, | |
| "learning_rate": 6.633608397548693e-06, | |
| "loss": 0.0869, | |
| "step": 881500 | |
| }, | |
| { | |
| "epoch": 53.52, | |
| "learning_rate": 6.626023906316364e-06, | |
| "loss": 0.0854, | |
| "step": 882000 | |
| }, | |
| { | |
| "epoch": 53.55, | |
| "learning_rate": 6.618439415084037e-06, | |
| "loss": 0.0861, | |
| "step": 882500 | |
| }, | |
| { | |
| "epoch": 53.58, | |
| "learning_rate": 6.610854923851708e-06, | |
| "loss": 0.0872, | |
| "step": 883000 | |
| }, | |
| { | |
| "epoch": 53.61, | |
| "learning_rate": 6.603270432619381e-06, | |
| "loss": 0.0857, | |
| "step": 883500 | |
| }, | |
| { | |
| "epoch": 53.64, | |
| "learning_rate": 6.595701110369517e-06, | |
| "loss": 0.0866, | |
| "step": 884000 | |
| }, | |
| { | |
| "epoch": 53.67, | |
| "learning_rate": 6.58811661913719e-06, | |
| "loss": 0.0871, | |
| "step": 884500 | |
| }, | |
| { | |
| "epoch": 53.7, | |
| "learning_rate": 6.580532127904861e-06, | |
| "loss": 0.0858, | |
| "step": 885000 | |
| }, | |
| { | |
| "epoch": 53.73, | |
| "learning_rate": 6.572947636672532e-06, | |
| "loss": 0.0857, | |
| "step": 885500 | |
| }, | |
| { | |
| "epoch": 53.76, | |
| "learning_rate": 6.565378314422669e-06, | |
| "loss": 0.0877, | |
| "step": 886000 | |
| }, | |
| { | |
| "epoch": 53.79, | |
| "learning_rate": 6.5577938231903404e-06, | |
| "loss": 0.0879, | |
| "step": 886500 | |
| }, | |
| { | |
| "epoch": 53.82, | |
| "learning_rate": 6.5502093319580125e-06, | |
| "loss": 0.0882, | |
| "step": 887000 | |
| }, | |
| { | |
| "epoch": 53.85, | |
| "learning_rate": 6.542640009708149e-06, | |
| "loss": 0.0853, | |
| "step": 887500 | |
| }, | |
| { | |
| "epoch": 53.88, | |
| "learning_rate": 6.535055518475822e-06, | |
| "loss": 0.0861, | |
| "step": 888000 | |
| }, | |
| { | |
| "epoch": 53.91, | |
| "learning_rate": 6.527471027243493e-06, | |
| "loss": 0.0875, | |
| "step": 888500 | |
| }, | |
| { | |
| "epoch": 53.94, | |
| "learning_rate": 6.519886536011165e-06, | |
| "loss": 0.0883, | |
| "step": 889000 | |
| }, | |
| { | |
| "epoch": 53.97, | |
| "learning_rate": 6.512302044778836e-06, | |
| "loss": 0.0864, | |
| "step": 889500 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "eval_bleu": 81.2685, | |
| "eval_gen_len": 14.1365, | |
| "eval_loss": 0.1724194884300232, | |
| "eval_runtime": 178.1859, | |
| "eval_samples_per_second": 90.49, | |
| "eval_steps_per_second": 2.829, | |
| "step": 889974 | |
| } | |
| ], | |
| "max_steps": 1318480, | |
| "num_train_epochs": 80, | |
| "total_flos": 1.2180001336815514e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |