| { | |
| "best_metric": 0.16182634234428406, | |
| "best_model_checkpoint": "checkpoints_orfeo/checkpoint-260316", | |
| "epoch": 40.0, | |
| "global_step": 289240, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 1.996570322223759e-05, | |
| "loss": 2.1923, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 1.9931129857557737e-05, | |
| "loss": 1.3226, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 1.989655649287789e-05, | |
| "loss": 1.1003, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 1.9861983128198038e-05, | |
| "loss": 0.9671, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 1.9827409763518186e-05, | |
| "loss": 0.8916, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 1.9792836398838338e-05, | |
| "loss": 0.8332, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 1.9758263034158486e-05, | |
| "loss": 0.7772, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 1.9723689669478635e-05, | |
| "loss": 0.734, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 1.9689116304798787e-05, | |
| "loss": 0.7019, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 1.9654542940118935e-05, | |
| "loss": 0.6743, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 1.9619969575439084e-05, | |
| "loss": 0.6475, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 1.9585396210759232e-05, | |
| "loss": 0.6189, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 1.9550822846079384e-05, | |
| "loss": 0.6036, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 1.9516249481399533e-05, | |
| "loss": 0.587, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_bleu": 60.5819, | |
| "eval_gen_len": 12.8913, | |
| "eval_loss": 0.4583694636821747, | |
| "eval_runtime": 327.4166, | |
| "eval_samples_per_second": 87.949, | |
| "eval_steps_per_second": 2.749, | |
| "step": 7231 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 1.948167611671968e-05, | |
| "loss": 0.5662, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 1.944710275203983e-05, | |
| "loss": 0.5361, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 1.9412529387359978e-05, | |
| "loss": 0.5269, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 1.937795602268013e-05, | |
| "loss": 0.5157, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 1.934338265800028e-05, | |
| "loss": 0.5041, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 1.9308809293320427e-05, | |
| "loss": 0.4851, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 1.9274305075369937e-05, | |
| "loss": 0.4798, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 1.9239731710690085e-05, | |
| "loss": 0.4697, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 1.9205158346010234e-05, | |
| "loss": 0.4657, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 1.9170584981330386e-05, | |
| "loss": 0.4555, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 1.9136011616650534e-05, | |
| "loss": 0.4485, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 1.9101507398700044e-05, | |
| "loss": 0.4446, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 1.9067003180749554e-05, | |
| "loss": 0.4311, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 1.9032429816069702e-05, | |
| "loss": 0.4213, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_bleu": 66.0413, | |
| "eval_gen_len": 12.9749, | |
| "eval_loss": 0.33632054924964905, | |
| "eval_runtime": 328.8185, | |
| "eval_samples_per_second": 87.574, | |
| "eval_steps_per_second": 2.737, | |
| "step": 14462 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 1.899785645138985e-05, | |
| "loss": 0.4164, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 1.896328308671e-05, | |
| "loss": 0.4019, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 1.892870972203015e-05, | |
| "loss": 0.3962, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 1.88941363573503e-05, | |
| "loss": 0.392, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 1.8859562992670448e-05, | |
| "loss": 0.3899, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 1.8824989627990596e-05, | |
| "loss": 0.3876, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 1.879041626331075e-05, | |
| "loss": 0.3774, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 1.8755842898630897e-05, | |
| "loss": 0.3744, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 1.8721269533951045e-05, | |
| "loss": 0.3724, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 1.8686696169271194e-05, | |
| "loss": 0.3614, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 1.8652191951320704e-05, | |
| "loss": 0.3665, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "learning_rate": 1.8617618586640852e-05, | |
| "loss": 0.3581, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 1.8583045221961004e-05, | |
| "loss": 0.3495, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 1.8548471857281153e-05, | |
| "loss": 0.3487, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 1.8513967639330662e-05, | |
| "loss": 0.354, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_bleu": 68.1423, | |
| "eval_gen_len": 12.9805, | |
| "eval_loss": 0.2864578068256378, | |
| "eval_runtime": 328.1672, | |
| "eval_samples_per_second": 87.748, | |
| "eval_steps_per_second": 2.743, | |
| "step": 21693 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "learning_rate": 1.847939427465081e-05, | |
| "loss": 0.3412, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 3.11, | |
| "learning_rate": 1.844482090997096e-05, | |
| "loss": 0.3407, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 3.18, | |
| "learning_rate": 1.8410247545291108e-05, | |
| "loss": 0.3336, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 3.25, | |
| "learning_rate": 1.8375743327340618e-05, | |
| "loss": 0.33, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 3.32, | |
| "learning_rate": 1.8341169962660766e-05, | |
| "loss": 0.3222, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 3.39, | |
| "learning_rate": 1.8306596597980918e-05, | |
| "loss": 0.3209, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 3.46, | |
| "learning_rate": 1.8272023233301066e-05, | |
| "loss": 0.3221, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 3.53, | |
| "learning_rate": 1.8237449868621215e-05, | |
| "loss": 0.3194, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 3.6, | |
| "learning_rate": 1.8202876503941363e-05, | |
| "loss": 0.309, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 3.66, | |
| "learning_rate": 1.8168303139261515e-05, | |
| "loss": 0.3149, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 3.73, | |
| "learning_rate": 1.8133729774581664e-05, | |
| "loss": 0.3069, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 3.8, | |
| "learning_rate": 1.8099225556631174e-05, | |
| "loss": 0.3158, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 3.87, | |
| "learning_rate": 1.8064652191951322e-05, | |
| "loss": 0.3039, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 3.94, | |
| "learning_rate": 1.803007882727147e-05, | |
| "loss": 0.3092, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_bleu": 69.4372, | |
| "eval_gen_len": 12.9939, | |
| "eval_loss": 0.2564955949783325, | |
| "eval_runtime": 327.0452, | |
| "eval_samples_per_second": 88.049, | |
| "eval_steps_per_second": 2.752, | |
| "step": 28924 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "learning_rate": 1.799550546259162e-05, | |
| "loss": 0.3004, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 4.08, | |
| "learning_rate": 1.796100124464113e-05, | |
| "loss": 0.2942, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 4.15, | |
| "learning_rate": 1.7926427879961277e-05, | |
| "loss": 0.2906, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 4.22, | |
| "learning_rate": 1.789185451528143e-05, | |
| "loss": 0.2907, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 4.29, | |
| "learning_rate": 1.7857281150601578e-05, | |
| "loss": 0.29, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 4.36, | |
| "learning_rate": 1.7822776932651088e-05, | |
| "loss": 0.2871, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 4.43, | |
| "learning_rate": 1.7788272714700597e-05, | |
| "loss": 0.2906, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 4.49, | |
| "learning_rate": 1.7753699350020746e-05, | |
| "loss": 0.287, | |
| "step": 32500 | |
| }, | |
| { | |
| "epoch": 4.56, | |
| "learning_rate": 1.7719125985340894e-05, | |
| "loss": 0.2797, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 4.63, | |
| "learning_rate": 1.7684552620661043e-05, | |
| "loss": 0.2864, | |
| "step": 33500 | |
| }, | |
| { | |
| "epoch": 4.7, | |
| "learning_rate": 1.7649979255981195e-05, | |
| "loss": 0.2841, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 4.77, | |
| "learning_rate": 1.7615405891301343e-05, | |
| "loss": 0.2781, | |
| "step": 34500 | |
| }, | |
| { | |
| "epoch": 4.84, | |
| "learning_rate": 1.7580901673350853e-05, | |
| "loss": 0.2803, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 4.91, | |
| "learning_rate": 1.7546328308671e-05, | |
| "loss": 0.2729, | |
| "step": 35500 | |
| }, | |
| { | |
| "epoch": 4.98, | |
| "learning_rate": 1.751175494399115e-05, | |
| "loss": 0.2717, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_bleu": 70.3702, | |
| "eval_gen_len": 12.957, | |
| "eval_loss": 0.23622238636016846, | |
| "eval_runtime": 329.1892, | |
| "eval_samples_per_second": 87.476, | |
| "eval_steps_per_second": 2.734, | |
| "step": 36155 | |
| }, | |
| { | |
| "epoch": 5.05, | |
| "learning_rate": 1.74771815793113e-05, | |
| "loss": 0.2668, | |
| "step": 36500 | |
| }, | |
| { | |
| "epoch": 5.12, | |
| "learning_rate": 1.744260821463145e-05, | |
| "loss": 0.2651, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 5.19, | |
| "learning_rate": 1.74080348499516e-05, | |
| "loss": 0.2647, | |
| "step": 37500 | |
| }, | |
| { | |
| "epoch": 5.26, | |
| "learning_rate": 1.7373461485271747e-05, | |
| "loss": 0.2618, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 5.32, | |
| "learning_rate": 1.7338888120591896e-05, | |
| "loss": 0.265, | |
| "step": 38500 | |
| }, | |
| { | |
| "epoch": 5.39, | |
| "learning_rate": 1.7304383902641406e-05, | |
| "loss": 0.2614, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 5.46, | |
| "learning_rate": 1.7269810537961554e-05, | |
| "loss": 0.2531, | |
| "step": 39500 | |
| }, | |
| { | |
| "epoch": 5.53, | |
| "learning_rate": 1.7235237173281706e-05, | |
| "loss": 0.2583, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 5.6, | |
| "learning_rate": 1.7200663808601855e-05, | |
| "loss": 0.2631, | |
| "step": 40500 | |
| }, | |
| { | |
| "epoch": 5.67, | |
| "learning_rate": 1.7166159590651364e-05, | |
| "loss": 0.2573, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 5.74, | |
| "learning_rate": 1.7131655372700874e-05, | |
| "loss": 0.2562, | |
| "step": 41500 | |
| }, | |
| { | |
| "epoch": 5.81, | |
| "learning_rate": 1.7097082008021023e-05, | |
| "loss": 0.2546, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 5.88, | |
| "learning_rate": 1.706250864334117e-05, | |
| "loss": 0.2527, | |
| "step": 42500 | |
| }, | |
| { | |
| "epoch": 5.95, | |
| "learning_rate": 1.702793527866132e-05, | |
| "loss": 0.2542, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_bleu": 70.9448, | |
| "eval_gen_len": 12.945, | |
| "eval_loss": 0.22083553671836853, | |
| "eval_runtime": 327.8279, | |
| "eval_samples_per_second": 87.839, | |
| "eval_steps_per_second": 2.745, | |
| "step": 43386 | |
| }, | |
| { | |
| "epoch": 6.02, | |
| "learning_rate": 1.699336191398147e-05, | |
| "loss": 0.2567, | |
| "step": 43500 | |
| }, | |
| { | |
| "epoch": 6.08, | |
| "learning_rate": 1.695878854930162e-05, | |
| "loss": 0.2443, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 6.15, | |
| "learning_rate": 1.692421518462177e-05, | |
| "loss": 0.2423, | |
| "step": 44500 | |
| }, | |
| { | |
| "epoch": 6.22, | |
| "learning_rate": 1.6889641819941917e-05, | |
| "loss": 0.2476, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 6.29, | |
| "learning_rate": 1.6855068455262065e-05, | |
| "loss": 0.2449, | |
| "step": 45500 | |
| }, | |
| { | |
| "epoch": 6.36, | |
| "learning_rate": 1.6820495090582217e-05, | |
| "loss": 0.2435, | |
| "step": 46000 | |
| }, | |
| { | |
| "epoch": 6.43, | |
| "learning_rate": 1.6785921725902366e-05, | |
| "loss": 0.2403, | |
| "step": 46500 | |
| }, | |
| { | |
| "epoch": 6.5, | |
| "learning_rate": 1.6751348361222514e-05, | |
| "loss": 0.2384, | |
| "step": 47000 | |
| }, | |
| { | |
| "epoch": 6.57, | |
| "learning_rate": 1.6716844143272024e-05, | |
| "loss": 0.2365, | |
| "step": 47500 | |
| }, | |
| { | |
| "epoch": 6.64, | |
| "learning_rate": 1.6682270778592173e-05, | |
| "loss": 0.2385, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 6.71, | |
| "learning_rate": 1.664769741391232e-05, | |
| "loss": 0.2373, | |
| "step": 48500 | |
| }, | |
| { | |
| "epoch": 6.78, | |
| "learning_rate": 1.6613124049232473e-05, | |
| "loss": 0.2432, | |
| "step": 49000 | |
| }, | |
| { | |
| "epoch": 6.85, | |
| "learning_rate": 1.6578619831281983e-05, | |
| "loss": 0.2375, | |
| "step": 49500 | |
| }, | |
| { | |
| "epoch": 6.91, | |
| "learning_rate": 1.654404646660213e-05, | |
| "loss": 0.234, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 6.98, | |
| "learning_rate": 1.650947310192228e-05, | |
| "loss": 0.2344, | |
| "step": 50500 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_bleu": 71.317, | |
| "eval_gen_len": 12.9746, | |
| "eval_loss": 0.21209098398685455, | |
| "eval_runtime": 332.4569, | |
| "eval_samples_per_second": 86.616, | |
| "eval_steps_per_second": 2.707, | |
| "step": 50617 | |
| }, | |
| { | |
| "epoch": 7.05, | |
| "learning_rate": 1.6474899737242428e-05, | |
| "loss": 0.2278, | |
| "step": 51000 | |
| }, | |
| { | |
| "epoch": 7.12, | |
| "learning_rate": 1.6440395519291938e-05, | |
| "loss": 0.2249, | |
| "step": 51500 | |
| }, | |
| { | |
| "epoch": 7.19, | |
| "learning_rate": 1.6405891301341448e-05, | |
| "loss": 0.2326, | |
| "step": 52000 | |
| }, | |
| { | |
| "epoch": 7.26, | |
| "learning_rate": 1.6371317936661596e-05, | |
| "loss": 0.2287, | |
| "step": 52500 | |
| }, | |
| { | |
| "epoch": 7.33, | |
| "learning_rate": 1.6336744571981745e-05, | |
| "loss": 0.2276, | |
| "step": 53000 | |
| }, | |
| { | |
| "epoch": 7.4, | |
| "learning_rate": 1.6302171207301897e-05, | |
| "loss": 0.2279, | |
| "step": 53500 | |
| }, | |
| { | |
| "epoch": 7.47, | |
| "learning_rate": 1.6267597842622045e-05, | |
| "loss": 0.2242, | |
| "step": 54000 | |
| }, | |
| { | |
| "epoch": 7.54, | |
| "learning_rate": 1.6233024477942194e-05, | |
| "loss": 0.2269, | |
| "step": 54500 | |
| }, | |
| { | |
| "epoch": 7.61, | |
| "learning_rate": 1.6198451113262342e-05, | |
| "loss": 0.2243, | |
| "step": 55000 | |
| }, | |
| { | |
| "epoch": 7.68, | |
| "learning_rate": 1.6163946895311852e-05, | |
| "loss": 0.2221, | |
| "step": 55500 | |
| }, | |
| { | |
| "epoch": 7.74, | |
| "learning_rate": 1.6129373530632e-05, | |
| "loss": 0.2268, | |
| "step": 56000 | |
| }, | |
| { | |
| "epoch": 7.81, | |
| "learning_rate": 1.609486931268151e-05, | |
| "loss": 0.2189, | |
| "step": 56500 | |
| }, | |
| { | |
| "epoch": 7.88, | |
| "learning_rate": 1.6060295948001662e-05, | |
| "loss": 0.2221, | |
| "step": 57000 | |
| }, | |
| { | |
| "epoch": 7.95, | |
| "learning_rate": 1.602579173005117e-05, | |
| "loss": 0.2206, | |
| "step": 57500 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_bleu": 71.7397, | |
| "eval_gen_len": 12.9546, | |
| "eval_loss": 0.2024153172969818, | |
| "eval_runtime": 331.9482, | |
| "eval_samples_per_second": 86.748, | |
| "eval_steps_per_second": 2.711, | |
| "step": 57848 | |
| }, | |
| { | |
| "epoch": 8.02, | |
| "learning_rate": 1.599121836537132e-05, | |
| "loss": 0.2218, | |
| "step": 58000 | |
| }, | |
| { | |
| "epoch": 8.09, | |
| "learning_rate": 1.595664500069147e-05, | |
| "loss": 0.2122, | |
| "step": 58500 | |
| }, | |
| { | |
| "epoch": 8.16, | |
| "learning_rate": 1.5922071636011617e-05, | |
| "loss": 0.214, | |
| "step": 59000 | |
| }, | |
| { | |
| "epoch": 8.23, | |
| "learning_rate": 1.5887498271331766e-05, | |
| "loss": 0.2145, | |
| "step": 59500 | |
| }, | |
| { | |
| "epoch": 8.3, | |
| "learning_rate": 1.5852924906651918e-05, | |
| "loss": 0.2138, | |
| "step": 60000 | |
| }, | |
| { | |
| "epoch": 8.37, | |
| "learning_rate": 1.5818351541972066e-05, | |
| "loss": 0.2157, | |
| "step": 60500 | |
| }, | |
| { | |
| "epoch": 8.44, | |
| "learning_rate": 1.5783778177292215e-05, | |
| "loss": 0.211, | |
| "step": 61000 | |
| }, | |
| { | |
| "epoch": 8.51, | |
| "learning_rate": 1.5749204812612363e-05, | |
| "loss": 0.2078, | |
| "step": 61500 | |
| }, | |
| { | |
| "epoch": 8.57, | |
| "learning_rate": 1.5714631447932512e-05, | |
| "loss": 0.2137, | |
| "step": 62000 | |
| }, | |
| { | |
| "epoch": 8.64, | |
| "learning_rate": 1.5680058083252664e-05, | |
| "loss": 0.2164, | |
| "step": 62500 | |
| }, | |
| { | |
| "epoch": 8.71, | |
| "learning_rate": 1.5645484718572812e-05, | |
| "loss": 0.2141, | |
| "step": 63000 | |
| }, | |
| { | |
| "epoch": 8.78, | |
| "learning_rate": 1.5610980500622322e-05, | |
| "loss": 0.2139, | |
| "step": 63500 | |
| }, | |
| { | |
| "epoch": 8.85, | |
| "learning_rate": 1.557640713594247e-05, | |
| "loss": 0.2121, | |
| "step": 64000 | |
| }, | |
| { | |
| "epoch": 8.92, | |
| "learning_rate": 1.554183377126262e-05, | |
| "loss": 0.2151, | |
| "step": 64500 | |
| }, | |
| { | |
| "epoch": 8.99, | |
| "learning_rate": 1.550726040658277e-05, | |
| "loss": 0.2117, | |
| "step": 65000 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_bleu": 72.143, | |
| "eval_gen_len": 12.9467, | |
| "eval_loss": 0.19509540498256683, | |
| "eval_runtime": 327.4667, | |
| "eval_samples_per_second": 87.936, | |
| "eval_steps_per_second": 2.748, | |
| "step": 65079 | |
| }, | |
| { | |
| "epoch": 9.06, | |
| "learning_rate": 1.547268704190292e-05, | |
| "loss": 0.2024, | |
| "step": 65500 | |
| }, | |
| { | |
| "epoch": 9.13, | |
| "learning_rate": 1.5438113677223068e-05, | |
| "loss": 0.2026, | |
| "step": 66000 | |
| }, | |
| { | |
| "epoch": 9.2, | |
| "learning_rate": 1.5403540312543216e-05, | |
| "loss": 0.2066, | |
| "step": 66500 | |
| }, | |
| { | |
| "epoch": 9.27, | |
| "learning_rate": 1.5368966947863365e-05, | |
| "loss": 0.1989, | |
| "step": 67000 | |
| }, | |
| { | |
| "epoch": 9.33, | |
| "learning_rate": 1.5334462729912875e-05, | |
| "loss": 0.2057, | |
| "step": 67500 | |
| }, | |
| { | |
| "epoch": 9.4, | |
| "learning_rate": 1.5299889365233026e-05, | |
| "loss": 0.2047, | |
| "step": 68000 | |
| }, | |
| { | |
| "epoch": 9.47, | |
| "learning_rate": 1.5265316000553175e-05, | |
| "loss": 0.2022, | |
| "step": 68500 | |
| }, | |
| { | |
| "epoch": 9.54, | |
| "learning_rate": 1.5230811782602683e-05, | |
| "loss": 0.2055, | |
| "step": 69000 | |
| }, | |
| { | |
| "epoch": 9.61, | |
| "learning_rate": 1.5196238417922833e-05, | |
| "loss": 0.2064, | |
| "step": 69500 | |
| }, | |
| { | |
| "epoch": 9.68, | |
| "learning_rate": 1.5161665053242982e-05, | |
| "loss": 0.2041, | |
| "step": 70000 | |
| }, | |
| { | |
| "epoch": 9.75, | |
| "learning_rate": 1.5127091688563132e-05, | |
| "loss": 0.2, | |
| "step": 70500 | |
| }, | |
| { | |
| "epoch": 9.82, | |
| "learning_rate": 1.509251832388328e-05, | |
| "loss": 0.1993, | |
| "step": 71000 | |
| }, | |
| { | |
| "epoch": 9.89, | |
| "learning_rate": 1.505794495920343e-05, | |
| "loss": 0.2008, | |
| "step": 71500 | |
| }, | |
| { | |
| "epoch": 9.96, | |
| "learning_rate": 1.5023371594523579e-05, | |
| "loss": 0.2018, | |
| "step": 72000 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_bleu": 72.2777, | |
| "eval_gen_len": 12.9741, | |
| "eval_loss": 0.19072672724723816, | |
| "eval_runtime": 327.3978, | |
| "eval_samples_per_second": 87.954, | |
| "eval_steps_per_second": 2.749, | |
| "step": 72310 | |
| }, | |
| { | |
| "epoch": 10.03, | |
| "learning_rate": 1.4988798229843731e-05, | |
| "loss": 0.1979, | |
| "step": 72500 | |
| }, | |
| { | |
| "epoch": 10.1, | |
| "learning_rate": 1.4954294011893237e-05, | |
| "loss": 0.1957, | |
| "step": 73000 | |
| }, | |
| { | |
| "epoch": 10.16, | |
| "learning_rate": 1.4919720647213388e-05, | |
| "loss": 0.1945, | |
| "step": 73500 | |
| }, | |
| { | |
| "epoch": 10.23, | |
| "learning_rate": 1.4885147282533536e-05, | |
| "loss": 0.1945, | |
| "step": 74000 | |
| }, | |
| { | |
| "epoch": 10.3, | |
| "learning_rate": 1.4850573917853686e-05, | |
| "loss": 0.1933, | |
| "step": 74500 | |
| }, | |
| { | |
| "epoch": 10.37, | |
| "learning_rate": 1.4816069699903194e-05, | |
| "loss": 0.19, | |
| "step": 75000 | |
| }, | |
| { | |
| "epoch": 10.44, | |
| "learning_rate": 1.4781496335223345e-05, | |
| "loss": 0.1929, | |
| "step": 75500 | |
| }, | |
| { | |
| "epoch": 10.51, | |
| "learning_rate": 1.4746922970543493e-05, | |
| "loss": 0.1957, | |
| "step": 76000 | |
| }, | |
| { | |
| "epoch": 10.58, | |
| "learning_rate": 1.4712349605863643e-05, | |
| "loss": 0.1944, | |
| "step": 76500 | |
| }, | |
| { | |
| "epoch": 10.65, | |
| "learning_rate": 1.4677776241183795e-05, | |
| "loss": 0.1984, | |
| "step": 77000 | |
| }, | |
| { | |
| "epoch": 10.72, | |
| "learning_rate": 1.4643202876503944e-05, | |
| "loss": 0.1901, | |
| "step": 77500 | |
| }, | |
| { | |
| "epoch": 10.79, | |
| "learning_rate": 1.4608629511824092e-05, | |
| "loss": 0.1935, | |
| "step": 78000 | |
| }, | |
| { | |
| "epoch": 10.86, | |
| "learning_rate": 1.4574056147144242e-05, | |
| "loss": 0.1921, | |
| "step": 78500 | |
| }, | |
| { | |
| "epoch": 10.93, | |
| "learning_rate": 1.4539551929193749e-05, | |
| "loss": 0.1909, | |
| "step": 79000 | |
| }, | |
| { | |
| "epoch": 10.99, | |
| "learning_rate": 1.45049785645139e-05, | |
| "loss": 0.1944, | |
| "step": 79500 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_bleu": 72.448, | |
| "eval_gen_len": 12.9678, | |
| "eval_loss": 0.18560351431369781, | |
| "eval_runtime": 331.6458, | |
| "eval_samples_per_second": 86.828, | |
| "eval_steps_per_second": 2.714, | |
| "step": 79541 | |
| }, | |
| { | |
| "epoch": 11.06, | |
| "learning_rate": 1.447040519983405e-05, | |
| "loss": 0.1887, | |
| "step": 80000 | |
| }, | |
| { | |
| "epoch": 11.13, | |
| "learning_rate": 1.44358318351542e-05, | |
| "loss": 0.1842, | |
| "step": 80500 | |
| }, | |
| { | |
| "epoch": 11.2, | |
| "learning_rate": 1.4401327617203706e-05, | |
| "loss": 0.1891, | |
| "step": 81000 | |
| }, | |
| { | |
| "epoch": 11.27, | |
| "learning_rate": 1.4366754252523856e-05, | |
| "loss": 0.1866, | |
| "step": 81500 | |
| }, | |
| { | |
| "epoch": 11.34, | |
| "learning_rate": 1.4332180887844008e-05, | |
| "loss": 0.1851, | |
| "step": 82000 | |
| }, | |
| { | |
| "epoch": 11.41, | |
| "learning_rate": 1.4297607523164156e-05, | |
| "loss": 0.185, | |
| "step": 82500 | |
| }, | |
| { | |
| "epoch": 11.48, | |
| "learning_rate": 1.4263172451943024e-05, | |
| "loss": 0.1872, | |
| "step": 83000 | |
| }, | |
| { | |
| "epoch": 11.55, | |
| "learning_rate": 1.4228599087263172e-05, | |
| "loss": 0.1847, | |
| "step": 83500 | |
| }, | |
| { | |
| "epoch": 11.62, | |
| "learning_rate": 1.4194025722583323e-05, | |
| "loss": 0.1838, | |
| "step": 84000 | |
| }, | |
| { | |
| "epoch": 11.69, | |
| "learning_rate": 1.4159452357903471e-05, | |
| "loss": 0.1883, | |
| "step": 84500 | |
| }, | |
| { | |
| "epoch": 11.75, | |
| "learning_rate": 1.4124948139952981e-05, | |
| "loss": 0.1832, | |
| "step": 85000 | |
| }, | |
| { | |
| "epoch": 11.82, | |
| "learning_rate": 1.409037477527313e-05, | |
| "loss": 0.1876, | |
| "step": 85500 | |
| }, | |
| { | |
| "epoch": 11.89, | |
| "learning_rate": 1.405580141059328e-05, | |
| "loss": 0.1861, | |
| "step": 86000 | |
| }, | |
| { | |
| "epoch": 11.96, | |
| "learning_rate": 1.4021228045913428e-05, | |
| "loss": 0.1856, | |
| "step": 86500 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_bleu": 72.6473, | |
| "eval_gen_len": 12.9764, | |
| "eval_loss": 0.18210774660110474, | |
| "eval_runtime": 326.793, | |
| "eval_samples_per_second": 88.117, | |
| "eval_steps_per_second": 2.754, | |
| "step": 86772 | |
| }, | |
| { | |
| "epoch": 12.03, | |
| "learning_rate": 1.3986654681233578e-05, | |
| "loss": 0.1826, | |
| "step": 87000 | |
| }, | |
| { | |
| "epoch": 12.1, | |
| "learning_rate": 1.3952081316553727e-05, | |
| "loss": 0.1785, | |
| "step": 87500 | |
| }, | |
| { | |
| "epoch": 12.17, | |
| "learning_rate": 1.3917507951873877e-05, | |
| "loss": 0.1791, | |
| "step": 88000 | |
| }, | |
| { | |
| "epoch": 12.24, | |
| "learning_rate": 1.3882934587194025e-05, | |
| "loss": 0.1777, | |
| "step": 88500 | |
| }, | |
| { | |
| "epoch": 12.31, | |
| "learning_rate": 1.3848361222514177e-05, | |
| "loss": 0.1786, | |
| "step": 89000 | |
| }, | |
| { | |
| "epoch": 12.38, | |
| "learning_rate": 1.3813857004563684e-05, | |
| "loss": 0.1792, | |
| "step": 89500 | |
| }, | |
| { | |
| "epoch": 12.45, | |
| "learning_rate": 1.3779283639883834e-05, | |
| "loss": 0.179, | |
| "step": 90000 | |
| }, | |
| { | |
| "epoch": 12.52, | |
| "learning_rate": 1.3744779421933344e-05, | |
| "loss": 0.1777, | |
| "step": 90500 | |
| }, | |
| { | |
| "epoch": 12.58, | |
| "learning_rate": 1.3710206057253492e-05, | |
| "loss": 0.1816, | |
| "step": 91000 | |
| }, | |
| { | |
| "epoch": 12.65, | |
| "learning_rate": 1.367563269257364e-05, | |
| "loss": 0.1772, | |
| "step": 91500 | |
| }, | |
| { | |
| "epoch": 12.72, | |
| "learning_rate": 1.3641059327893791e-05, | |
| "loss": 0.1778, | |
| "step": 92000 | |
| }, | |
| { | |
| "epoch": 12.79, | |
| "learning_rate": 1.360648596321394e-05, | |
| "loss": 0.182, | |
| "step": 92500 | |
| }, | |
| { | |
| "epoch": 12.86, | |
| "learning_rate": 1.357198174526345e-05, | |
| "loss": 0.1805, | |
| "step": 93000 | |
| }, | |
| { | |
| "epoch": 12.93, | |
| "learning_rate": 1.35374083805836e-05, | |
| "loss": 0.1781, | |
| "step": 93500 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "learning_rate": 1.3502835015903748e-05, | |
| "loss": 0.1816, | |
| "step": 94000 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_bleu": 72.7148, | |
| "eval_gen_len": 12.9977, | |
| "eval_loss": 0.17964386940002441, | |
| "eval_runtime": 331.7781, | |
| "eval_samples_per_second": 86.793, | |
| "eval_steps_per_second": 2.713, | |
| "step": 94003 | |
| }, | |
| { | |
| "epoch": 13.07, | |
| "learning_rate": 1.3468261651223898e-05, | |
| "loss": 0.1737, | |
| "step": 94500 | |
| }, | |
| { | |
| "epoch": 13.14, | |
| "learning_rate": 1.3433757433273406e-05, | |
| "loss": 0.1732, | |
| "step": 95000 | |
| }, | |
| { | |
| "epoch": 13.21, | |
| "learning_rate": 1.3399184068593556e-05, | |
| "loss": 0.1714, | |
| "step": 95500 | |
| }, | |
| { | |
| "epoch": 13.28, | |
| "learning_rate": 1.3364610703913705e-05, | |
| "loss": 0.1744, | |
| "step": 96000 | |
| }, | |
| { | |
| "epoch": 13.35, | |
| "learning_rate": 1.3330037339233855e-05, | |
| "loss": 0.1734, | |
| "step": 96500 | |
| }, | |
| { | |
| "epoch": 13.41, | |
| "learning_rate": 1.3295463974554004e-05, | |
| "loss": 0.1759, | |
| "step": 97000 | |
| }, | |
| { | |
| "epoch": 13.48, | |
| "learning_rate": 1.3260890609874154e-05, | |
| "loss": 0.177, | |
| "step": 97500 | |
| }, | |
| { | |
| "epoch": 13.55, | |
| "learning_rate": 1.3226317245194304e-05, | |
| "loss": 0.175, | |
| "step": 98000 | |
| }, | |
| { | |
| "epoch": 13.62, | |
| "learning_rate": 1.3191743880514454e-05, | |
| "loss": 0.1714, | |
| "step": 98500 | |
| }, | |
| { | |
| "epoch": 13.69, | |
| "learning_rate": 1.315723966256396e-05, | |
| "loss": 0.1735, | |
| "step": 99000 | |
| }, | |
| { | |
| "epoch": 13.76, | |
| "learning_rate": 1.312266629788411e-05, | |
| "loss": 0.1706, | |
| "step": 99500 | |
| }, | |
| { | |
| "epoch": 13.83, | |
| "learning_rate": 1.308809293320426e-05, | |
| "loss": 0.1725, | |
| "step": 100000 | |
| }, | |
| { | |
| "epoch": 13.9, | |
| "learning_rate": 1.3053519568524411e-05, | |
| "loss": 0.1697, | |
| "step": 100500 | |
| }, | |
| { | |
| "epoch": 13.97, | |
| "learning_rate": 1.301894620384456e-05, | |
| "loss": 0.1735, | |
| "step": 101000 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_bleu": 72.9217, | |
| "eval_gen_len": 12.9687, | |
| "eval_loss": 0.17671316862106323, | |
| "eval_runtime": 331.3829, | |
| "eval_samples_per_second": 86.896, | |
| "eval_steps_per_second": 2.716, | |
| "step": 101234 | |
| }, | |
| { | |
| "epoch": 14.04, | |
| "learning_rate": 1.2984441985894068e-05, | |
| "loss": 0.1672, | |
| "step": 101500 | |
| }, | |
| { | |
| "epoch": 14.11, | |
| "learning_rate": 1.2949868621214216e-05, | |
| "loss": 0.1681, | |
| "step": 102000 | |
| }, | |
| { | |
| "epoch": 14.18, | |
| "learning_rate": 1.2915295256534366e-05, | |
| "loss": 0.1679, | |
| "step": 102500 | |
| }, | |
| { | |
| "epoch": 14.24, | |
| "learning_rate": 1.2880721891854517e-05, | |
| "loss": 0.1656, | |
| "step": 103000 | |
| }, | |
| { | |
| "epoch": 14.31, | |
| "learning_rate": 1.2846217673904025e-05, | |
| "loss": 0.1677, | |
| "step": 103500 | |
| }, | |
| { | |
| "epoch": 14.38, | |
| "learning_rate": 1.2811644309224173e-05, | |
| "loss": 0.1675, | |
| "step": 104000 | |
| }, | |
| { | |
| "epoch": 14.45, | |
| "learning_rate": 1.2777070944544323e-05, | |
| "loss": 0.1693, | |
| "step": 104500 | |
| }, | |
| { | |
| "epoch": 14.52, | |
| "learning_rate": 1.2742497579864475e-05, | |
| "loss": 0.1662, | |
| "step": 105000 | |
| }, | |
| { | |
| "epoch": 14.59, | |
| "learning_rate": 1.2708062508643341e-05, | |
| "loss": 0.1666, | |
| "step": 105500 | |
| }, | |
| { | |
| "epoch": 14.66, | |
| "learning_rate": 1.2673489143963491e-05, | |
| "loss": 0.1711, | |
| "step": 106000 | |
| }, | |
| { | |
| "epoch": 14.73, | |
| "learning_rate": 1.263891577928364e-05, | |
| "loss": 0.1676, | |
| "step": 106500 | |
| }, | |
| { | |
| "epoch": 14.8, | |
| "learning_rate": 1.260434241460379e-05, | |
| "loss": 0.1665, | |
| "step": 107000 | |
| }, | |
| { | |
| "epoch": 14.87, | |
| "learning_rate": 1.2569769049923939e-05, | |
| "loss": 0.1715, | |
| "step": 107500 | |
| }, | |
| { | |
| "epoch": 14.94, | |
| "learning_rate": 1.2535195685244089e-05, | |
| "loss": 0.1673, | |
| "step": 108000 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_bleu": 73.0674, | |
| "eval_gen_len": 12.9771, | |
| "eval_loss": 0.17453685402870178, | |
| "eval_runtime": 331.4528, | |
| "eval_samples_per_second": 86.878, | |
| "eval_steps_per_second": 2.715, | |
| "step": 108465 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "learning_rate": 1.2500622320564237e-05, | |
| "loss": 0.1662, | |
| "step": 108500 | |
| }, | |
| { | |
| "epoch": 15.07, | |
| "learning_rate": 1.2466048955884387e-05, | |
| "loss": 0.1629, | |
| "step": 109000 | |
| }, | |
| { | |
| "epoch": 15.14, | |
| "learning_rate": 1.2431475591204536e-05, | |
| "loss": 0.1616, | |
| "step": 109500 | |
| }, | |
| { | |
| "epoch": 15.21, | |
| "learning_rate": 1.2396971373254046e-05, | |
| "loss": 0.1626, | |
| "step": 110000 | |
| }, | |
| { | |
| "epoch": 15.28, | |
| "learning_rate": 1.2362398008574194e-05, | |
| "loss": 0.16, | |
| "step": 110500 | |
| }, | |
| { | |
| "epoch": 15.35, | |
| "learning_rate": 1.2327824643894344e-05, | |
| "loss": 0.1635, | |
| "step": 111000 | |
| }, | |
| { | |
| "epoch": 15.42, | |
| "learning_rate": 1.2293251279214493e-05, | |
| "loss": 0.161, | |
| "step": 111500 | |
| }, | |
| { | |
| "epoch": 15.49, | |
| "learning_rate": 1.2258747061264003e-05, | |
| "loss": 0.1618, | |
| "step": 112000 | |
| }, | |
| { | |
| "epoch": 15.56, | |
| "learning_rate": 1.2224173696584151e-05, | |
| "loss": 0.1667, | |
| "step": 112500 | |
| }, | |
| { | |
| "epoch": 15.63, | |
| "learning_rate": 1.2189600331904301e-05, | |
| "loss": 0.1609, | |
| "step": 113000 | |
| }, | |
| { | |
| "epoch": 15.7, | |
| "learning_rate": 1.215502696722445e-05, | |
| "loss": 0.1653, | |
| "step": 113500 | |
| }, | |
| { | |
| "epoch": 15.77, | |
| "learning_rate": 1.212052274927396e-05, | |
| "loss": 0.1619, | |
| "step": 114000 | |
| }, | |
| { | |
| "epoch": 15.83, | |
| "learning_rate": 1.2085949384594108e-05, | |
| "loss": 0.1632, | |
| "step": 114500 | |
| }, | |
| { | |
| "epoch": 15.9, | |
| "learning_rate": 1.2051376019914258e-05, | |
| "loss": 0.1682, | |
| "step": 115000 | |
| }, | |
| { | |
| "epoch": 15.97, | |
| "learning_rate": 1.2016802655234407e-05, | |
| "loss": 0.1603, | |
| "step": 115500 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_bleu": 73.0685, | |
| "eval_gen_len": 13.0001, | |
| "eval_loss": 0.1714019477367401, | |
| "eval_runtime": 331.5243, | |
| "eval_samples_per_second": 86.859, | |
| "eval_steps_per_second": 2.715, | |
| "step": 115696 | |
| }, | |
| { | |
| "epoch": 16.04, | |
| "learning_rate": 1.1982298437283917e-05, | |
| "loss": 0.158, | |
| "step": 116000 | |
| }, | |
| { | |
| "epoch": 16.11, | |
| "learning_rate": 1.1947725072604067e-05, | |
| "loss": 0.1612, | |
| "step": 116500 | |
| }, | |
| { | |
| "epoch": 16.18, | |
| "learning_rate": 1.1913151707924215e-05, | |
| "loss": 0.1541, | |
| "step": 117000 | |
| }, | |
| { | |
| "epoch": 16.25, | |
| "learning_rate": 1.1878578343244364e-05, | |
| "loss": 0.1585, | |
| "step": 117500 | |
| }, | |
| { | |
| "epoch": 16.32, | |
| "learning_rate": 1.1844074125293874e-05, | |
| "loss": 0.1608, | |
| "step": 118000 | |
| }, | |
| { | |
| "epoch": 16.39, | |
| "learning_rate": 1.1809500760614024e-05, | |
| "loss": 0.1593, | |
| "step": 118500 | |
| }, | |
| { | |
| "epoch": 16.46, | |
| "learning_rate": 1.1774927395934172e-05, | |
| "loss": 0.156, | |
| "step": 119000 | |
| }, | |
| { | |
| "epoch": 16.53, | |
| "learning_rate": 1.1740354031254323e-05, | |
| "loss": 0.1573, | |
| "step": 119500 | |
| }, | |
| { | |
| "epoch": 16.6, | |
| "learning_rate": 1.1705780666574471e-05, | |
| "loss": 0.1584, | |
| "step": 120000 | |
| }, | |
| { | |
| "epoch": 16.66, | |
| "learning_rate": 1.1671276448623981e-05, | |
| "loss": 0.1595, | |
| "step": 120500 | |
| }, | |
| { | |
| "epoch": 16.73, | |
| "learning_rate": 1.1636772230673489e-05, | |
| "loss": 0.1604, | |
| "step": 121000 | |
| }, | |
| { | |
| "epoch": 16.8, | |
| "learning_rate": 1.160219886599364e-05, | |
| "loss": 0.1608, | |
| "step": 121500 | |
| }, | |
| { | |
| "epoch": 16.87, | |
| "learning_rate": 1.1567625501313788e-05, | |
| "loss": 0.1545, | |
| "step": 122000 | |
| }, | |
| { | |
| "epoch": 16.94, | |
| "learning_rate": 1.1533052136633938e-05, | |
| "loss": 0.1599, | |
| "step": 122500 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_bleu": 73.1736, | |
| "eval_gen_len": 13.0044, | |
| "eval_loss": 0.17083990573883057, | |
| "eval_runtime": 331.5218, | |
| "eval_samples_per_second": 86.86, | |
| "eval_steps_per_second": 2.715, | |
| "step": 122927 | |
| }, | |
| { | |
| "epoch": 17.01, | |
| "learning_rate": 1.1498478771954086e-05, | |
| "loss": 0.1588, | |
| "step": 123000 | |
| }, | |
| { | |
| "epoch": 17.08, | |
| "learning_rate": 1.1463905407274237e-05, | |
| "loss": 0.1534, | |
| "step": 123500 | |
| }, | |
| { | |
| "epoch": 17.15, | |
| "learning_rate": 1.1429332042594385e-05, | |
| "loss": 0.1555, | |
| "step": 124000 | |
| }, | |
| { | |
| "epoch": 17.22, | |
| "learning_rate": 1.1394758677914535e-05, | |
| "loss": 0.1545, | |
| "step": 124500 | |
| }, | |
| { | |
| "epoch": 17.29, | |
| "learning_rate": 1.1360185313234684e-05, | |
| "loss": 0.1522, | |
| "step": 125000 | |
| }, | |
| { | |
| "epoch": 17.36, | |
| "learning_rate": 1.1325750242013553e-05, | |
| "loss": 0.1581, | |
| "step": 125500 | |
| }, | |
| { | |
| "epoch": 17.42, | |
| "learning_rate": 1.1291176877333703e-05, | |
| "loss": 0.1571, | |
| "step": 126000 | |
| }, | |
| { | |
| "epoch": 17.49, | |
| "learning_rate": 1.1256603512653852e-05, | |
| "loss": 0.1521, | |
| "step": 126500 | |
| }, | |
| { | |
| "epoch": 17.56, | |
| "learning_rate": 1.1222030147974002e-05, | |
| "loss": 0.1536, | |
| "step": 127000 | |
| }, | |
| { | |
| "epoch": 17.63, | |
| "learning_rate": 1.118745678329415e-05, | |
| "loss": 0.1565, | |
| "step": 127500 | |
| }, | |
| { | |
| "epoch": 17.7, | |
| "learning_rate": 1.1152883418614299e-05, | |
| "loss": 0.1516, | |
| "step": 128000 | |
| }, | |
| { | |
| "epoch": 17.77, | |
| "learning_rate": 1.1118310053934449e-05, | |
| "loss": 0.1525, | |
| "step": 128500 | |
| }, | |
| { | |
| "epoch": 17.84, | |
| "learning_rate": 1.1083736689254598e-05, | |
| "loss": 0.1543, | |
| "step": 129000 | |
| }, | |
| { | |
| "epoch": 17.91, | |
| "learning_rate": 1.1049232471304107e-05, | |
| "loss": 0.1526, | |
| "step": 129500 | |
| }, | |
| { | |
| "epoch": 17.98, | |
| "learning_rate": 1.1014659106624258e-05, | |
| "loss": 0.1547, | |
| "step": 130000 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_bleu": 73.1982, | |
| "eval_gen_len": 12.9891, | |
| "eval_loss": 0.16940416395664215, | |
| "eval_runtime": 331.787, | |
| "eval_samples_per_second": 86.791, | |
| "eval_steps_per_second": 2.713, | |
| "step": 130158 | |
| }, | |
| { | |
| "epoch": 18.05, | |
| "learning_rate": 1.0980085741944406e-05, | |
| "loss": 0.1542, | |
| "step": 130500 | |
| }, | |
| { | |
| "epoch": 18.12, | |
| "learning_rate": 1.0945512377264556e-05, | |
| "loss": 0.1527, | |
| "step": 131000 | |
| }, | |
| { | |
| "epoch": 18.19, | |
| "learning_rate": 1.0911008159314064e-05, | |
| "loss": 0.148, | |
| "step": 131500 | |
| }, | |
| { | |
| "epoch": 18.25, | |
| "learning_rate": 1.0876503941363574e-05, | |
| "loss": 0.148, | |
| "step": 132000 | |
| }, | |
| { | |
| "epoch": 18.32, | |
| "learning_rate": 1.0841930576683723e-05, | |
| "loss": 0.1474, | |
| "step": 132500 | |
| }, | |
| { | |
| "epoch": 18.39, | |
| "learning_rate": 1.0807357212003873e-05, | |
| "loss": 0.1525, | |
| "step": 133000 | |
| }, | |
| { | |
| "epoch": 18.46, | |
| "learning_rate": 1.0772783847324021e-05, | |
| "loss": 0.1502, | |
| "step": 133500 | |
| }, | |
| { | |
| "epoch": 18.53, | |
| "learning_rate": 1.0738210482644172e-05, | |
| "loss": 0.1532, | |
| "step": 134000 | |
| }, | |
| { | |
| "epoch": 18.6, | |
| "learning_rate": 1.070363711796432e-05, | |
| "loss": 0.1517, | |
| "step": 134500 | |
| }, | |
| { | |
| "epoch": 18.67, | |
| "learning_rate": 1.066906375328447e-05, | |
| "loss": 0.1456, | |
| "step": 135000 | |
| }, | |
| { | |
| "epoch": 18.74, | |
| "learning_rate": 1.0634490388604619e-05, | |
| "loss": 0.154, | |
| "step": 135500 | |
| }, | |
| { | |
| "epoch": 18.81, | |
| "learning_rate": 1.0599986170654129e-05, | |
| "loss": 0.151, | |
| "step": 136000 | |
| }, | |
| { | |
| "epoch": 18.88, | |
| "learning_rate": 1.0565481952703638e-05, | |
| "loss": 0.152, | |
| "step": 136500 | |
| }, | |
| { | |
| "epoch": 18.95, | |
| "learning_rate": 1.0530977734753147e-05, | |
| "loss": 0.1505, | |
| "step": 137000 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_bleu": 73.2671, | |
| "eval_gen_len": 12.9711, | |
| "eval_loss": 0.16765068471431732, | |
| "eval_runtime": 325.5863, | |
| "eval_samples_per_second": 88.444, | |
| "eval_steps_per_second": 2.764, | |
| "step": 137389 | |
| }, | |
| { | |
| "epoch": 19.02, | |
| "learning_rate": 1.0496404370073297e-05, | |
| "loss": 0.1522, | |
| "step": 137500 | |
| }, | |
| { | |
| "epoch": 19.08, | |
| "learning_rate": 1.0461969298852166e-05, | |
| "loss": 0.1462, | |
| "step": 138000 | |
| }, | |
| { | |
| "epoch": 19.15, | |
| "learning_rate": 1.0427395934172315e-05, | |
| "loss": 0.145, | |
| "step": 138500 | |
| }, | |
| { | |
| "epoch": 19.22, | |
| "learning_rate": 1.0392822569492465e-05, | |
| "loss": 0.1479, | |
| "step": 139000 | |
| }, | |
| { | |
| "epoch": 19.29, | |
| "learning_rate": 1.0358318351541975e-05, | |
| "loss": 0.1457, | |
| "step": 139500 | |
| }, | |
| { | |
| "epoch": 19.36, | |
| "learning_rate": 1.0323744986862123e-05, | |
| "loss": 0.1502, | |
| "step": 140000 | |
| }, | |
| { | |
| "epoch": 19.43, | |
| "learning_rate": 1.0289171622182272e-05, | |
| "loss": 0.1474, | |
| "step": 140500 | |
| }, | |
| { | |
| "epoch": 19.5, | |
| "learning_rate": 1.0254598257502422e-05, | |
| "loss": 0.1467, | |
| "step": 141000 | |
| }, | |
| { | |
| "epoch": 19.57, | |
| "learning_rate": 1.022002489282257e-05, | |
| "loss": 0.1514, | |
| "step": 141500 | |
| }, | |
| { | |
| "epoch": 19.64, | |
| "learning_rate": 1.018545152814272e-05, | |
| "loss": 0.1507, | |
| "step": 142000 | |
| }, | |
| { | |
| "epoch": 19.71, | |
| "learning_rate": 1.0150878163462869e-05, | |
| "loss": 0.1489, | |
| "step": 142500 | |
| }, | |
| { | |
| "epoch": 19.78, | |
| "learning_rate": 1.0116373945512379e-05, | |
| "loss": 0.1471, | |
| "step": 143000 | |
| }, | |
| { | |
| "epoch": 19.85, | |
| "learning_rate": 1.0081800580832529e-05, | |
| "loss": 0.1455, | |
| "step": 143500 | |
| }, | |
| { | |
| "epoch": 19.91, | |
| "learning_rate": 1.0047227216152677e-05, | |
| "loss": 0.1459, | |
| "step": 144000 | |
| }, | |
| { | |
| "epoch": 19.98, | |
| "learning_rate": 1.0012653851472826e-05, | |
| "loss": 0.1464, | |
| "step": 144500 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_bleu": 73.3543, | |
| "eval_gen_len": 12.9918, | |
| "eval_loss": 0.16689570248126984, | |
| "eval_runtime": 325.9649, | |
| "eval_samples_per_second": 88.341, | |
| "eval_steps_per_second": 2.761, | |
| "step": 144620 | |
| }, | |
| { | |
| "epoch": 20.05, | |
| "learning_rate": 9.978080486792976e-06, | |
| "loss": 0.1458, | |
| "step": 145000 | |
| }, | |
| { | |
| "epoch": 20.12, | |
| "learning_rate": 9.943507122113125e-06, | |
| "loss": 0.1418, | |
| "step": 145500 | |
| }, | |
| { | |
| "epoch": 20.19, | |
| "learning_rate": 9.908933757433275e-06, | |
| "loss": 0.1446, | |
| "step": 146000 | |
| }, | |
| { | |
| "epoch": 20.26, | |
| "learning_rate": 9.874360392753423e-06, | |
| "loss": 0.1473, | |
| "step": 146500 | |
| }, | |
| { | |
| "epoch": 20.33, | |
| "learning_rate": 9.839787028073573e-06, | |
| "loss": 0.1471, | |
| "step": 147000 | |
| }, | |
| { | |
| "epoch": 20.4, | |
| "learning_rate": 9.805213663393722e-06, | |
| "loss": 0.1411, | |
| "step": 147500 | |
| }, | |
| { | |
| "epoch": 20.47, | |
| "learning_rate": 9.770640298713872e-06, | |
| "loss": 0.1439, | |
| "step": 148000 | |
| }, | |
| { | |
| "epoch": 20.54, | |
| "learning_rate": 9.73606693403402e-06, | |
| "loss": 0.1452, | |
| "step": 148500 | |
| }, | |
| { | |
| "epoch": 20.61, | |
| "learning_rate": 9.70149356935417e-06, | |
| "loss": 0.1422, | |
| "step": 149000 | |
| }, | |
| { | |
| "epoch": 20.67, | |
| "learning_rate": 9.66692020467432e-06, | |
| "loss": 0.1427, | |
| "step": 149500 | |
| }, | |
| { | |
| "epoch": 20.74, | |
| "learning_rate": 9.63234683999447e-06, | |
| "loss": 0.1423, | |
| "step": 150000 | |
| }, | |
| { | |
| "epoch": 20.81, | |
| "learning_rate": 9.597773475314618e-06, | |
| "loss": 0.1445, | |
| "step": 150500 | |
| }, | |
| { | |
| "epoch": 20.88, | |
| "learning_rate": 9.563269257364128e-06, | |
| "loss": 0.1465, | |
| "step": 151000 | |
| }, | |
| { | |
| "epoch": 20.95, | |
| "learning_rate": 9.528695892684276e-06, | |
| "loss": 0.1449, | |
| "step": 151500 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_bleu": 73.3506, | |
| "eval_gen_len": 12.9916, | |
| "eval_loss": 0.16551125049591064, | |
| "eval_runtime": 331.0362, | |
| "eval_samples_per_second": 86.987, | |
| "eval_steps_per_second": 2.719, | |
| "step": 151851 | |
| }, | |
| { | |
| "epoch": 21.02, | |
| "learning_rate": 9.494122528004426e-06, | |
| "loss": 0.1462, | |
| "step": 152000 | |
| }, | |
| { | |
| "epoch": 21.09, | |
| "learning_rate": 9.459549163324575e-06, | |
| "loss": 0.1398, | |
| "step": 152500 | |
| }, | |
| { | |
| "epoch": 21.16, | |
| "learning_rate": 9.424975798644725e-06, | |
| "loss": 0.1408, | |
| "step": 153000 | |
| }, | |
| { | |
| "epoch": 21.23, | |
| "learning_rate": 9.390402433964875e-06, | |
| "loss": 0.1415, | |
| "step": 153500 | |
| }, | |
| { | |
| "epoch": 21.3, | |
| "learning_rate": 9.355829069285024e-06, | |
| "loss": 0.1426, | |
| "step": 154000 | |
| }, | |
| { | |
| "epoch": 21.37, | |
| "learning_rate": 9.321255704605174e-06, | |
| "loss": 0.1402, | |
| "step": 154500 | |
| }, | |
| { | |
| "epoch": 21.44, | |
| "learning_rate": 9.286682339925322e-06, | |
| "loss": 0.1406, | |
| "step": 155000 | |
| }, | |
| { | |
| "epoch": 21.5, | |
| "learning_rate": 9.252108975245473e-06, | |
| "loss": 0.1375, | |
| "step": 155500 | |
| }, | |
| { | |
| "epoch": 21.57, | |
| "learning_rate": 9.217535610565621e-06, | |
| "loss": 0.1429, | |
| "step": 156000 | |
| }, | |
| { | |
| "epoch": 21.64, | |
| "learning_rate": 9.18296224588577e-06, | |
| "loss": 0.1426, | |
| "step": 156500 | |
| }, | |
| { | |
| "epoch": 21.71, | |
| "learning_rate": 9.14838888120592e-06, | |
| "loss": 0.1433, | |
| "step": 157000 | |
| }, | |
| { | |
| "epoch": 21.78, | |
| "learning_rate": 9.113815516526068e-06, | |
| "loss": 0.1414, | |
| "step": 157500 | |
| }, | |
| { | |
| "epoch": 21.85, | |
| "learning_rate": 9.079242151846218e-06, | |
| "loss": 0.1469, | |
| "step": 158000 | |
| }, | |
| { | |
| "epoch": 21.92, | |
| "learning_rate": 9.044668787166367e-06, | |
| "loss": 0.1397, | |
| "step": 158500 | |
| }, | |
| { | |
| "epoch": 21.99, | |
| "learning_rate": 9.010164569215877e-06, | |
| "loss": 0.1389, | |
| "step": 159000 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_bleu": 73.4685, | |
| "eval_gen_len": 13.01, | |
| "eval_loss": 0.16494113206863403, | |
| "eval_runtime": 326.5923, | |
| "eval_samples_per_second": 88.171, | |
| "eval_steps_per_second": 2.756, | |
| "step": 159082 | |
| }, | |
| { | |
| "epoch": 22.06, | |
| "learning_rate": 8.975591204536025e-06, | |
| "loss": 0.1405, | |
| "step": 159500 | |
| }, | |
| { | |
| "epoch": 22.13, | |
| "learning_rate": 8.941017839856175e-06, | |
| "loss": 0.1378, | |
| "step": 160000 | |
| }, | |
| { | |
| "epoch": 22.2, | |
| "learning_rate": 8.906444475176324e-06, | |
| "loss": 0.137, | |
| "step": 160500 | |
| }, | |
| { | |
| "epoch": 22.27, | |
| "learning_rate": 8.871940257225834e-06, | |
| "loss": 0.1416, | |
| "step": 161000 | |
| }, | |
| { | |
| "epoch": 22.33, | |
| "learning_rate": 8.837366892545984e-06, | |
| "loss": 0.138, | |
| "step": 161500 | |
| }, | |
| { | |
| "epoch": 22.4, | |
| "learning_rate": 8.802793527866132e-06, | |
| "loss": 0.1389, | |
| "step": 162000 | |
| }, | |
| { | |
| "epoch": 22.47, | |
| "learning_rate": 8.768220163186283e-06, | |
| "loss": 0.1422, | |
| "step": 162500 | |
| }, | |
| { | |
| "epoch": 22.54, | |
| "learning_rate": 8.73371594523579e-06, | |
| "loss": 0.1354, | |
| "step": 163000 | |
| }, | |
| { | |
| "epoch": 22.61, | |
| "learning_rate": 8.699142580555941e-06, | |
| "loss": 0.1404, | |
| "step": 163500 | |
| }, | |
| { | |
| "epoch": 22.68, | |
| "learning_rate": 8.66456921587609e-06, | |
| "loss": 0.1416, | |
| "step": 164000 | |
| }, | |
| { | |
| "epoch": 22.75, | |
| "learning_rate": 8.6300649979256e-06, | |
| "loss": 0.1395, | |
| "step": 164500 | |
| }, | |
| { | |
| "epoch": 22.82, | |
| "learning_rate": 8.595491633245748e-06, | |
| "loss": 0.1405, | |
| "step": 165000 | |
| }, | |
| { | |
| "epoch": 22.89, | |
| "learning_rate": 8.560918268565898e-06, | |
| "loss": 0.1377, | |
| "step": 165500 | |
| }, | |
| { | |
| "epoch": 22.96, | |
| "learning_rate": 8.526344903886046e-06, | |
| "loss": 0.1362, | |
| "step": 166000 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_bleu": 73.4517, | |
| "eval_gen_len": 13.0042, | |
| "eval_loss": 0.16470502316951752, | |
| "eval_runtime": 326.27, | |
| "eval_samples_per_second": 88.258, | |
| "eval_steps_per_second": 2.758, | |
| "step": 166313 | |
| }, | |
| { | |
| "epoch": 23.03, | |
| "learning_rate": 8.491771539206197e-06, | |
| "loss": 0.1374, | |
| "step": 166500 | |
| }, | |
| { | |
| "epoch": 23.1, | |
| "learning_rate": 8.457198174526345e-06, | |
| "loss": 0.1373, | |
| "step": 167000 | |
| }, | |
| { | |
| "epoch": 23.16, | |
| "learning_rate": 8.422624809846495e-06, | |
| "loss": 0.1361, | |
| "step": 167500 | |
| }, | |
| { | |
| "epoch": 23.23, | |
| "learning_rate": 8.388051445166644e-06, | |
| "loss": 0.1333, | |
| "step": 168000 | |
| }, | |
| { | |
| "epoch": 23.3, | |
| "learning_rate": 8.353547227216154e-06, | |
| "loss": 0.1369, | |
| "step": 168500 | |
| }, | |
| { | |
| "epoch": 23.37, | |
| "learning_rate": 8.318973862536302e-06, | |
| "loss": 0.1369, | |
| "step": 169000 | |
| }, | |
| { | |
| "epoch": 23.44, | |
| "learning_rate": 8.284400497856452e-06, | |
| "loss": 0.1364, | |
| "step": 169500 | |
| }, | |
| { | |
| "epoch": 23.51, | |
| "learning_rate": 8.2498271331766e-06, | |
| "loss": 0.1369, | |
| "step": 170000 | |
| }, | |
| { | |
| "epoch": 23.58, | |
| "learning_rate": 8.215253768496751e-06, | |
| "loss": 0.1362, | |
| "step": 170500 | |
| }, | |
| { | |
| "epoch": 23.65, | |
| "learning_rate": 8.180749550546259e-06, | |
| "loss": 0.1386, | |
| "step": 171000 | |
| }, | |
| { | |
| "epoch": 23.72, | |
| "learning_rate": 8.14617618586641e-06, | |
| "loss": 0.1386, | |
| "step": 171500 | |
| }, | |
| { | |
| "epoch": 23.79, | |
| "learning_rate": 8.111602821186558e-06, | |
| "loss": 0.1352, | |
| "step": 172000 | |
| }, | |
| { | |
| "epoch": 23.86, | |
| "learning_rate": 8.077029456506708e-06, | |
| "loss": 0.1367, | |
| "step": 172500 | |
| }, | |
| { | |
| "epoch": 23.92, | |
| "learning_rate": 8.042525238556218e-06, | |
| "loss": 0.1355, | |
| "step": 173000 | |
| }, | |
| { | |
| "epoch": 23.99, | |
| "learning_rate": 8.008021020605726e-06, | |
| "loss": 0.1322, | |
| "step": 173500 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_bleu": 73.5427, | |
| "eval_gen_len": 13.025, | |
| "eval_loss": 0.16514846682548523, | |
| "eval_runtime": 326.8973, | |
| "eval_samples_per_second": 88.089, | |
| "eval_steps_per_second": 2.753, | |
| "step": 173544 | |
| }, | |
| { | |
| "epoch": 24.06, | |
| "learning_rate": 7.973447655925876e-06, | |
| "loss": 0.132, | |
| "step": 174000 | |
| }, | |
| { | |
| "epoch": 24.13, | |
| "learning_rate": 7.938874291246024e-06, | |
| "loss": 0.1332, | |
| "step": 174500 | |
| }, | |
| { | |
| "epoch": 24.2, | |
| "learning_rate": 7.904300926566175e-06, | |
| "loss": 0.1351, | |
| "step": 175000 | |
| }, | |
| { | |
| "epoch": 24.27, | |
| "learning_rate": 7.869727561886323e-06, | |
| "loss": 0.135, | |
| "step": 175500 | |
| }, | |
| { | |
| "epoch": 24.34, | |
| "learning_rate": 7.835154197206473e-06, | |
| "loss": 0.1354, | |
| "step": 176000 | |
| }, | |
| { | |
| "epoch": 24.41, | |
| "learning_rate": 7.800580832526622e-06, | |
| "loss": 0.1351, | |
| "step": 176500 | |
| }, | |
| { | |
| "epoch": 24.48, | |
| "learning_rate": 7.766007467846772e-06, | |
| "loss": 0.132, | |
| "step": 177000 | |
| }, | |
| { | |
| "epoch": 24.55, | |
| "learning_rate": 7.73150324989628e-06, | |
| "loss": 0.1317, | |
| "step": 177500 | |
| }, | |
| { | |
| "epoch": 24.62, | |
| "learning_rate": 7.69692988521643e-06, | |
| "loss": 0.1366, | |
| "step": 178000 | |
| }, | |
| { | |
| "epoch": 24.69, | |
| "learning_rate": 7.662356520536579e-06, | |
| "loss": 0.1328, | |
| "step": 178500 | |
| }, | |
| { | |
| "epoch": 24.75, | |
| "learning_rate": 7.627783155856728e-06, | |
| "loss": 0.1348, | |
| "step": 179000 | |
| }, | |
| { | |
| "epoch": 24.82, | |
| "learning_rate": 7.5932097911768775e-06, | |
| "loss": 0.1345, | |
| "step": 179500 | |
| }, | |
| { | |
| "epoch": 24.89, | |
| "learning_rate": 7.558705573226387e-06, | |
| "loss": 0.1331, | |
| "step": 180000 | |
| }, | |
| { | |
| "epoch": 24.96, | |
| "learning_rate": 7.524132208546537e-06, | |
| "loss": 0.1337, | |
| "step": 180500 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_bleu": 73.5595, | |
| "eval_gen_len": 13.0306, | |
| "eval_loss": 0.16346952319145203, | |
| "eval_runtime": 325.4712, | |
| "eval_samples_per_second": 88.475, | |
| "eval_steps_per_second": 2.765, | |
| "step": 180775 | |
| }, | |
| { | |
| "epoch": 25.03, | |
| "learning_rate": 7.489558843866685e-06, | |
| "loss": 0.1342, | |
| "step": 181000 | |
| }, | |
| { | |
| "epoch": 25.1, | |
| "learning_rate": 7.4549854791868344e-06, | |
| "loss": 0.1325, | |
| "step": 181500 | |
| }, | |
| { | |
| "epoch": 25.17, | |
| "learning_rate": 7.420481261236344e-06, | |
| "loss": 0.1297, | |
| "step": 182000 | |
| }, | |
| { | |
| "epoch": 25.24, | |
| "learning_rate": 7.385907896556494e-06, | |
| "loss": 0.1344, | |
| "step": 182500 | |
| }, | |
| { | |
| "epoch": 25.31, | |
| "learning_rate": 7.351334531876643e-06, | |
| "loss": 0.133, | |
| "step": 183000 | |
| }, | |
| { | |
| "epoch": 25.38, | |
| "learning_rate": 7.316761167196792e-06, | |
| "loss": 0.1311, | |
| "step": 183500 | |
| }, | |
| { | |
| "epoch": 25.45, | |
| "learning_rate": 7.282256949246301e-06, | |
| "loss": 0.1341, | |
| "step": 184000 | |
| }, | |
| { | |
| "epoch": 25.52, | |
| "learning_rate": 7.2476835845664506e-06, | |
| "loss": 0.1312, | |
| "step": 184500 | |
| }, | |
| { | |
| "epoch": 25.58, | |
| "learning_rate": 7.21317936661596e-06, | |
| "loss": 0.132, | |
| "step": 185000 | |
| }, | |
| { | |
| "epoch": 25.65, | |
| "learning_rate": 7.178606001936109e-06, | |
| "loss": 0.13, | |
| "step": 185500 | |
| }, | |
| { | |
| "epoch": 25.72, | |
| "learning_rate": 7.144032637256258e-06, | |
| "loss": 0.134, | |
| "step": 186000 | |
| }, | |
| { | |
| "epoch": 25.79, | |
| "learning_rate": 7.1094592725764075e-06, | |
| "loss": 0.1295, | |
| "step": 186500 | |
| }, | |
| { | |
| "epoch": 25.86, | |
| "learning_rate": 7.074885907896557e-06, | |
| "loss": 0.1332, | |
| "step": 187000 | |
| }, | |
| { | |
| "epoch": 25.93, | |
| "learning_rate": 7.040312543216706e-06, | |
| "loss": 0.133, | |
| "step": 187500 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "learning_rate": 7.0057391785368556e-06, | |
| "loss": 0.1308, | |
| "step": 188000 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_bleu": 73.5529, | |
| "eval_gen_len": 13.0183, | |
| "eval_loss": 0.16344179213047028, | |
| "eval_runtime": 323.8431, | |
| "eval_samples_per_second": 88.92, | |
| "eval_steps_per_second": 2.779, | |
| "step": 188006 | |
| }, | |
| { | |
| "epoch": 26.07, | |
| "learning_rate": 6.971165813857005e-06, | |
| "loss": 0.1298, | |
| "step": 188500 | |
| }, | |
| { | |
| "epoch": 26.14, | |
| "learning_rate": 6.936661595906514e-06, | |
| "loss": 0.1277, | |
| "step": 189000 | |
| }, | |
| { | |
| "epoch": 26.21, | |
| "learning_rate": 6.902157377956024e-06, | |
| "loss": 0.1334, | |
| "step": 189500 | |
| }, | |
| { | |
| "epoch": 26.28, | |
| "learning_rate": 6.867584013276173e-06, | |
| "loss": 0.1289, | |
| "step": 190000 | |
| }, | |
| { | |
| "epoch": 26.34, | |
| "learning_rate": 6.833010648596322e-06, | |
| "loss": 0.1301, | |
| "step": 190500 | |
| }, | |
| { | |
| "epoch": 26.41, | |
| "learning_rate": 6.798437283916472e-06, | |
| "loss": 0.1318, | |
| "step": 191000 | |
| }, | |
| { | |
| "epoch": 26.48, | |
| "learning_rate": 6.763863919236621e-06, | |
| "loss": 0.1311, | |
| "step": 191500 | |
| }, | |
| { | |
| "epoch": 26.55, | |
| "learning_rate": 6.72929055455677e-06, | |
| "loss": 0.1314, | |
| "step": 192000 | |
| }, | |
| { | |
| "epoch": 26.62, | |
| "learning_rate": 6.694717189876919e-06, | |
| "loss": 0.131, | |
| "step": 192500 | |
| }, | |
| { | |
| "epoch": 26.69, | |
| "learning_rate": 6.660143825197068e-06, | |
| "loss": 0.1297, | |
| "step": 193000 | |
| }, | |
| { | |
| "epoch": 26.76, | |
| "learning_rate": 6.625639607246578e-06, | |
| "loss": 0.1284, | |
| "step": 193500 | |
| }, | |
| { | |
| "epoch": 26.83, | |
| "learning_rate": 6.591066242566727e-06, | |
| "loss": 0.1309, | |
| "step": 194000 | |
| }, | |
| { | |
| "epoch": 26.9, | |
| "learning_rate": 6.556562024616236e-06, | |
| "loss": 0.1281, | |
| "step": 194500 | |
| }, | |
| { | |
| "epoch": 26.97, | |
| "learning_rate": 6.521988659936386e-06, | |
| "loss": 0.1309, | |
| "step": 195000 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_bleu": 73.6151, | |
| "eval_gen_len": 13.0011, | |
| "eval_loss": 0.16237156093120575, | |
| "eval_runtime": 322.9735, | |
| "eval_samples_per_second": 89.159, | |
| "eval_steps_per_second": 2.787, | |
| "step": 195237 | |
| }, | |
| { | |
| "epoch": 27.04, | |
| "learning_rate": 6.487415295256535e-06, | |
| "loss": 0.1252, | |
| "step": 195500 | |
| }, | |
| { | |
| "epoch": 27.11, | |
| "learning_rate": 6.452841930576684e-06, | |
| "loss": 0.1296, | |
| "step": 196000 | |
| }, | |
| { | |
| "epoch": 27.17, | |
| "learning_rate": 6.418268565896834e-06, | |
| "loss": 0.129, | |
| "step": 196500 | |
| }, | |
| { | |
| "epoch": 27.24, | |
| "learning_rate": 6.383695201216983e-06, | |
| "loss": 0.1249, | |
| "step": 197000 | |
| }, | |
| { | |
| "epoch": 27.31, | |
| "learning_rate": 6.349121836537132e-06, | |
| "loss": 0.1292, | |
| "step": 197500 | |
| }, | |
| { | |
| "epoch": 27.38, | |
| "learning_rate": 6.314548471857282e-06, | |
| "loss": 0.1278, | |
| "step": 198000 | |
| }, | |
| { | |
| "epoch": 27.45, | |
| "learning_rate": 6.279975107177431e-06, | |
| "loss": 0.1271, | |
| "step": 198500 | |
| }, | |
| { | |
| "epoch": 27.52, | |
| "learning_rate": 6.24547088922694e-06, | |
| "loss": 0.1298, | |
| "step": 199000 | |
| }, | |
| { | |
| "epoch": 27.59, | |
| "learning_rate": 6.210897524547089e-06, | |
| "loss": 0.1299, | |
| "step": 199500 | |
| }, | |
| { | |
| "epoch": 27.66, | |
| "learning_rate": 6.176324159867239e-06, | |
| "loss": 0.1283, | |
| "step": 200000 | |
| }, | |
| { | |
| "epoch": 27.73, | |
| "learning_rate": 6.141750795187388e-06, | |
| "loss": 0.1283, | |
| "step": 200500 | |
| }, | |
| { | |
| "epoch": 27.8, | |
| "learning_rate": 6.107246577236897e-06, | |
| "loss": 0.1307, | |
| "step": 201000 | |
| }, | |
| { | |
| "epoch": 27.87, | |
| "learning_rate": 6.072673212557046e-06, | |
| "loss": 0.1317, | |
| "step": 201500 | |
| }, | |
| { | |
| "epoch": 27.94, | |
| "learning_rate": 6.038099847877196e-06, | |
| "loss": 0.1269, | |
| "step": 202000 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_bleu": 73.6409, | |
| "eval_gen_len": 13.0209, | |
| "eval_loss": 0.1626293659210205, | |
| "eval_runtime": 324.7844, | |
| "eval_samples_per_second": 88.662, | |
| "eval_steps_per_second": 2.771, | |
| "step": 202468 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "learning_rate": 6.003595629926705e-06, | |
| "loss": 0.1262, | |
| "step": 202500 | |
| }, | |
| { | |
| "epoch": 28.07, | |
| "learning_rate": 5.969091411976214e-06, | |
| "loss": 0.1246, | |
| "step": 203000 | |
| }, | |
| { | |
| "epoch": 28.14, | |
| "learning_rate": 5.934518047296364e-06, | |
| "loss": 0.1253, | |
| "step": 203500 | |
| }, | |
| { | |
| "epoch": 28.21, | |
| "learning_rate": 5.899944682616513e-06, | |
| "loss": 0.1229, | |
| "step": 204000 | |
| }, | |
| { | |
| "epoch": 28.28, | |
| "learning_rate": 5.865371317936662e-06, | |
| "loss": 0.1286, | |
| "step": 204500 | |
| }, | |
| { | |
| "epoch": 28.35, | |
| "learning_rate": 5.830797953256812e-06, | |
| "loss": 0.123, | |
| "step": 205000 | |
| }, | |
| { | |
| "epoch": 28.42, | |
| "learning_rate": 5.796224588576961e-06, | |
| "loss": 0.1266, | |
| "step": 205500 | |
| }, | |
| { | |
| "epoch": 28.49, | |
| "learning_rate": 5.76165122389711e-06, | |
| "loss": 0.1268, | |
| "step": 206000 | |
| }, | |
| { | |
| "epoch": 28.56, | |
| "learning_rate": 5.72707785921726e-06, | |
| "loss": 0.1268, | |
| "step": 206500 | |
| }, | |
| { | |
| "epoch": 28.63, | |
| "learning_rate": 5.692504494537408e-06, | |
| "loss": 0.1273, | |
| "step": 207000 | |
| }, | |
| { | |
| "epoch": 28.7, | |
| "learning_rate": 5.6579311298575576e-06, | |
| "loss": 0.1286, | |
| "step": 207500 | |
| }, | |
| { | |
| "epoch": 28.77, | |
| "learning_rate": 5.623496058636427e-06, | |
| "loss": 0.1281, | |
| "step": 208000 | |
| }, | |
| { | |
| "epoch": 28.83, | |
| "learning_rate": 5.588922693956576e-06, | |
| "loss": 0.1289, | |
| "step": 208500 | |
| }, | |
| { | |
| "epoch": 28.9, | |
| "learning_rate": 5.554349329276726e-06, | |
| "loss": 0.1285, | |
| "step": 209000 | |
| }, | |
| { | |
| "epoch": 28.97, | |
| "learning_rate": 5.5198451113262355e-06, | |
| "loss": 0.1239, | |
| "step": 209500 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_bleu": 73.6486, | |
| "eval_gen_len": 13.023, | |
| "eval_loss": 0.1618330031633377, | |
| "eval_runtime": 321.6597, | |
| "eval_samples_per_second": 89.523, | |
| "eval_steps_per_second": 2.798, | |
| "step": 209699 | |
| }, | |
| { | |
| "epoch": 29.04, | |
| "learning_rate": 5.485271746646385e-06, | |
| "loss": 0.1327, | |
| "step": 210000 | |
| }, | |
| { | |
| "epoch": 29.11, | |
| "learning_rate": 5.450698381966534e-06, | |
| "loss": 0.126, | |
| "step": 210500 | |
| }, | |
| { | |
| "epoch": 29.18, | |
| "learning_rate": 5.416125017286683e-06, | |
| "loss": 0.1253, | |
| "step": 211000 | |
| }, | |
| { | |
| "epoch": 29.25, | |
| "learning_rate": 5.381551652606832e-06, | |
| "loss": 0.1265, | |
| "step": 211500 | |
| }, | |
| { | |
| "epoch": 29.32, | |
| "learning_rate": 5.346978287926981e-06, | |
| "loss": 0.1222, | |
| "step": 212000 | |
| }, | |
| { | |
| "epoch": 29.39, | |
| "learning_rate": 5.312404923247131e-06, | |
| "loss": 0.1258, | |
| "step": 212500 | |
| }, | |
| { | |
| "epoch": 29.46, | |
| "learning_rate": 5.27783155856728e-06, | |
| "loss": 0.1254, | |
| "step": 213000 | |
| }, | |
| { | |
| "epoch": 29.53, | |
| "learning_rate": 5.243258193887429e-06, | |
| "loss": 0.1257, | |
| "step": 213500 | |
| }, | |
| { | |
| "epoch": 29.59, | |
| "learning_rate": 5.208684829207579e-06, | |
| "loss": 0.1256, | |
| "step": 214000 | |
| }, | |
| { | |
| "epoch": 29.66, | |
| "learning_rate": 5.174111464527728e-06, | |
| "loss": 0.1245, | |
| "step": 214500 | |
| }, | |
| { | |
| "epoch": 29.73, | |
| "learning_rate": 5.139538099847877e-06, | |
| "loss": 0.1237, | |
| "step": 215000 | |
| }, | |
| { | |
| "epoch": 29.8, | |
| "learning_rate": 5.104964735168027e-06, | |
| "loss": 0.1243, | |
| "step": 215500 | |
| }, | |
| { | |
| "epoch": 29.87, | |
| "learning_rate": 5.070391370488177e-06, | |
| "loss": 0.1262, | |
| "step": 216000 | |
| }, | |
| { | |
| "epoch": 29.94, | |
| "learning_rate": 5.035818005808326e-06, | |
| "loss": 0.1216, | |
| "step": 216500 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_bleu": 73.7267, | |
| "eval_gen_len": 13.0134, | |
| "eval_loss": 0.16207487881183624, | |
| "eval_runtime": 321.9244, | |
| "eval_samples_per_second": 89.45, | |
| "eval_steps_per_second": 2.796, | |
| "step": 216930 | |
| }, | |
| { | |
| "epoch": 30.01, | |
| "learning_rate": 5.001313787857834e-06, | |
| "loss": 0.1246, | |
| "step": 217000 | |
| }, | |
| { | |
| "epoch": 30.08, | |
| "learning_rate": 4.9667404231779845e-06, | |
| "loss": 0.1237, | |
| "step": 217500 | |
| }, | |
| { | |
| "epoch": 30.15, | |
| "learning_rate": 4.932167058498134e-06, | |
| "loss": 0.1242, | |
| "step": 218000 | |
| }, | |
| { | |
| "epoch": 30.22, | |
| "learning_rate": 4.897593693818283e-06, | |
| "loss": 0.1228, | |
| "step": 218500 | |
| }, | |
| { | |
| "epoch": 30.29, | |
| "learning_rate": 4.863020329138432e-06, | |
| "loss": 0.1239, | |
| "step": 219000 | |
| }, | |
| { | |
| "epoch": 30.36, | |
| "learning_rate": 4.828446964458581e-06, | |
| "loss": 0.1227, | |
| "step": 219500 | |
| }, | |
| { | |
| "epoch": 30.42, | |
| "learning_rate": 4.793873599778731e-06, | |
| "loss": 0.1218, | |
| "step": 220000 | |
| }, | |
| { | |
| "epoch": 30.49, | |
| "learning_rate": 4.7593002350988805e-06, | |
| "loss": 0.123, | |
| "step": 220500 | |
| }, | |
| { | |
| "epoch": 30.56, | |
| "learning_rate": 4.72472687041903e-06, | |
| "loss": 0.1272, | |
| "step": 221000 | |
| }, | |
| { | |
| "epoch": 30.63, | |
| "learning_rate": 4.690222652468539e-06, | |
| "loss": 0.1236, | |
| "step": 221500 | |
| }, | |
| { | |
| "epoch": 30.7, | |
| "learning_rate": 4.655649287788688e-06, | |
| "loss": 0.1246, | |
| "step": 222000 | |
| }, | |
| { | |
| "epoch": 30.77, | |
| "learning_rate": 4.6210759231088375e-06, | |
| "loss": 0.1239, | |
| "step": 222500 | |
| }, | |
| { | |
| "epoch": 30.84, | |
| "learning_rate": 4.586502558428987e-06, | |
| "loss": 0.1227, | |
| "step": 223000 | |
| }, | |
| { | |
| "epoch": 30.91, | |
| "learning_rate": 4.551998340478496e-06, | |
| "loss": 0.1228, | |
| "step": 223500 | |
| }, | |
| { | |
| "epoch": 30.98, | |
| "learning_rate": 4.517494122528005e-06, | |
| "loss": 0.1276, | |
| "step": 224000 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_bleu": 73.7362, | |
| "eval_gen_len": 13.0236, | |
| "eval_loss": 0.16207154095172882, | |
| "eval_runtime": 322.2078, | |
| "eval_samples_per_second": 89.371, | |
| "eval_steps_per_second": 2.793, | |
| "step": 224161 | |
| }, | |
| { | |
| "epoch": 31.05, | |
| "learning_rate": 4.482920757848154e-06, | |
| "loss": 0.1211, | |
| "step": 224500 | |
| }, | |
| { | |
| "epoch": 31.12, | |
| "learning_rate": 4.4483473931683034e-06, | |
| "loss": 0.1211, | |
| "step": 225000 | |
| }, | |
| { | |
| "epoch": 31.19, | |
| "learning_rate": 4.413774028488453e-06, | |
| "loss": 0.1214, | |
| "step": 225500 | |
| }, | |
| { | |
| "epoch": 31.25, | |
| "learning_rate": 4.379200663808602e-06, | |
| "loss": 0.1215, | |
| "step": 226000 | |
| }, | |
| { | |
| "epoch": 31.32, | |
| "learning_rate": 4.3446272991287515e-06, | |
| "loss": 0.1232, | |
| "step": 226500 | |
| }, | |
| { | |
| "epoch": 31.39, | |
| "learning_rate": 4.310053934448901e-06, | |
| "loss": 0.1258, | |
| "step": 227000 | |
| }, | |
| { | |
| "epoch": 31.46, | |
| "learning_rate": 4.27548056976905e-06, | |
| "loss": 0.1229, | |
| "step": 227500 | |
| }, | |
| { | |
| "epoch": 31.53, | |
| "learning_rate": 4.240976351818559e-06, | |
| "loss": 0.1222, | |
| "step": 228000 | |
| }, | |
| { | |
| "epoch": 31.6, | |
| "learning_rate": 4.2064029871387084e-06, | |
| "loss": 0.1267, | |
| "step": 228500 | |
| }, | |
| { | |
| "epoch": 31.67, | |
| "learning_rate": 4.171829622458858e-06, | |
| "loss": 0.1212, | |
| "step": 229000 | |
| }, | |
| { | |
| "epoch": 31.74, | |
| "learning_rate": 4.137256257779008e-06, | |
| "loss": 0.124, | |
| "step": 229500 | |
| }, | |
| { | |
| "epoch": 31.81, | |
| "learning_rate": 4.102752039828516e-06, | |
| "loss": 0.1232, | |
| "step": 230000 | |
| }, | |
| { | |
| "epoch": 31.88, | |
| "learning_rate": 4.068178675148665e-06, | |
| "loss": 0.1228, | |
| "step": 230500 | |
| }, | |
| { | |
| "epoch": 31.95, | |
| "learning_rate": 4.033674457198175e-06, | |
| "loss": 0.1207, | |
| "step": 231000 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_bleu": 73.7607, | |
| "eval_gen_len": 13.0179, | |
| "eval_loss": 0.162560373544693, | |
| "eval_runtime": 322.4139, | |
| "eval_samples_per_second": 89.314, | |
| "eval_steps_per_second": 2.791, | |
| "step": 231392 | |
| }, | |
| { | |
| "epoch": 32.01, | |
| "learning_rate": 3.9991010925183246e-06, | |
| "loss": 0.1249, | |
| "step": 231500 | |
| }, | |
| { | |
| "epoch": 32.08, | |
| "learning_rate": 3.9645968745678335e-06, | |
| "loss": 0.1206, | |
| "step": 232000 | |
| }, | |
| { | |
| "epoch": 32.15, | |
| "learning_rate": 3.930023509887982e-06, | |
| "loss": 0.12, | |
| "step": 232500 | |
| }, | |
| { | |
| "epoch": 32.22, | |
| "learning_rate": 3.895450145208132e-06, | |
| "loss": 0.1209, | |
| "step": 233000 | |
| }, | |
| { | |
| "epoch": 32.29, | |
| "learning_rate": 3.8608767805282815e-06, | |
| "loss": 0.1229, | |
| "step": 233500 | |
| }, | |
| { | |
| "epoch": 32.36, | |
| "learning_rate": 3.826303415848431e-06, | |
| "loss": 0.12, | |
| "step": 234000 | |
| }, | |
| { | |
| "epoch": 32.43, | |
| "learning_rate": 3.79173005116858e-06, | |
| "loss": 0.1222, | |
| "step": 234500 | |
| }, | |
| { | |
| "epoch": 32.5, | |
| "learning_rate": 3.757156686488729e-06, | |
| "loss": 0.1248, | |
| "step": 235000 | |
| }, | |
| { | |
| "epoch": 32.57, | |
| "learning_rate": 3.7225833218088785e-06, | |
| "loss": 0.1222, | |
| "step": 235500 | |
| }, | |
| { | |
| "epoch": 32.64, | |
| "learning_rate": 3.688009957129028e-06, | |
| "loss": 0.1216, | |
| "step": 236000 | |
| }, | |
| { | |
| "epoch": 32.71, | |
| "learning_rate": 3.6534365924491776e-06, | |
| "loss": 0.1235, | |
| "step": 236500 | |
| }, | |
| { | |
| "epoch": 32.78, | |
| "learning_rate": 3.618863227769327e-06, | |
| "loss": 0.1203, | |
| "step": 237000 | |
| }, | |
| { | |
| "epoch": 32.84, | |
| "learning_rate": 3.5842898630894762e-06, | |
| "loss": 0.1212, | |
| "step": 237500 | |
| }, | |
| { | |
| "epoch": 32.91, | |
| "learning_rate": 3.549785645138985e-06, | |
| "loss": 0.1208, | |
| "step": 238000 | |
| }, | |
| { | |
| "epoch": 32.98, | |
| "learning_rate": 3.5152122804591345e-06, | |
| "loss": 0.1217, | |
| "step": 238500 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_bleu": 73.75, | |
| "eval_gen_len": 13.0163, | |
| "eval_loss": 0.1623145490884781, | |
| "eval_runtime": 322.1607, | |
| "eval_samples_per_second": 89.384, | |
| "eval_steps_per_second": 2.794, | |
| "step": 238623 | |
| }, | |
| { | |
| "epoch": 33.05, | |
| "learning_rate": 3.4806389157792843e-06, | |
| "loss": 0.1208, | |
| "step": 239000 | |
| }, | |
| { | |
| "epoch": 33.12, | |
| "learning_rate": 3.4460655510994336e-06, | |
| "loss": 0.1198, | |
| "step": 239500 | |
| }, | |
| { | |
| "epoch": 33.19, | |
| "learning_rate": 3.4114921864195825e-06, | |
| "loss": 0.1207, | |
| "step": 240000 | |
| }, | |
| { | |
| "epoch": 33.26, | |
| "learning_rate": 3.3769879684690915e-06, | |
| "loss": 0.1217, | |
| "step": 240500 | |
| }, | |
| { | |
| "epoch": 33.33, | |
| "learning_rate": 3.3424146037892413e-06, | |
| "loss": 0.1196, | |
| "step": 241000 | |
| }, | |
| { | |
| "epoch": 33.4, | |
| "learning_rate": 3.3078412391093906e-06, | |
| "loss": 0.12, | |
| "step": 241500 | |
| }, | |
| { | |
| "epoch": 33.47, | |
| "learning_rate": 3.27326787442954e-06, | |
| "loss": 0.1219, | |
| "step": 242000 | |
| }, | |
| { | |
| "epoch": 33.54, | |
| "learning_rate": 3.2387636564790485e-06, | |
| "loss": 0.1213, | |
| "step": 242500 | |
| }, | |
| { | |
| "epoch": 33.61, | |
| "learning_rate": 3.204190291799198e-06, | |
| "loss": 0.1208, | |
| "step": 243000 | |
| }, | |
| { | |
| "epoch": 33.67, | |
| "learning_rate": 3.1696169271193476e-06, | |
| "loss": 0.1206, | |
| "step": 243500 | |
| }, | |
| { | |
| "epoch": 33.74, | |
| "learning_rate": 3.135043562439497e-06, | |
| "loss": 0.1209, | |
| "step": 244000 | |
| }, | |
| { | |
| "epoch": 33.81, | |
| "learning_rate": 3.100539344489006e-06, | |
| "loss": 0.1187, | |
| "step": 244500 | |
| }, | |
| { | |
| "epoch": 33.88, | |
| "learning_rate": 3.0660351265385153e-06, | |
| "loss": 0.1184, | |
| "step": 245000 | |
| }, | |
| { | |
| "epoch": 33.95, | |
| "learning_rate": 3.0314617618586646e-06, | |
| "loss": 0.1194, | |
| "step": 245500 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_bleu": 73.7724, | |
| "eval_gen_len": 13.0249, | |
| "eval_loss": 0.16194060444831848, | |
| "eval_runtime": 321.7496, | |
| "eval_samples_per_second": 89.498, | |
| "eval_steps_per_second": 2.797, | |
| "step": 245854 | |
| }, | |
| { | |
| "epoch": 34.02, | |
| "learning_rate": 2.996888397178814e-06, | |
| "loss": 0.1224, | |
| "step": 246000 | |
| }, | |
| { | |
| "epoch": 34.09, | |
| "learning_rate": 2.962315032498963e-06, | |
| "loss": 0.1187, | |
| "step": 246500 | |
| }, | |
| { | |
| "epoch": 34.16, | |
| "learning_rate": 2.927741667819112e-06, | |
| "loss": 0.12, | |
| "step": 247000 | |
| }, | |
| { | |
| "epoch": 34.23, | |
| "learning_rate": 2.8931683031392615e-06, | |
| "loss": 0.1197, | |
| "step": 247500 | |
| }, | |
| { | |
| "epoch": 34.3, | |
| "learning_rate": 2.858664085188771e-06, | |
| "loss": 0.1199, | |
| "step": 248000 | |
| }, | |
| { | |
| "epoch": 34.37, | |
| "learning_rate": 2.8240907205089203e-06, | |
| "loss": 0.1198, | |
| "step": 248500 | |
| }, | |
| { | |
| "epoch": 34.44, | |
| "learning_rate": 2.7895173558290696e-06, | |
| "loss": 0.1193, | |
| "step": 249000 | |
| }, | |
| { | |
| "epoch": 34.5, | |
| "learning_rate": 2.754943991149219e-06, | |
| "loss": 0.117, | |
| "step": 249500 | |
| }, | |
| { | |
| "epoch": 34.57, | |
| "learning_rate": 2.720370626469368e-06, | |
| "loss": 0.1213, | |
| "step": 250000 | |
| }, | |
| { | |
| "epoch": 34.64, | |
| "learning_rate": 2.685797261789518e-06, | |
| "loss": 0.1165, | |
| "step": 250500 | |
| }, | |
| { | |
| "epoch": 34.71, | |
| "learning_rate": 2.651223897109667e-06, | |
| "loss": 0.12, | |
| "step": 251000 | |
| }, | |
| { | |
| "epoch": 34.78, | |
| "learning_rate": 2.6166505324298163e-06, | |
| "loss": 0.1215, | |
| "step": 251500 | |
| }, | |
| { | |
| "epoch": 34.85, | |
| "learning_rate": 2.5820771677499656e-06, | |
| "loss": 0.1183, | |
| "step": 252000 | |
| }, | |
| { | |
| "epoch": 34.92, | |
| "learning_rate": 2.5475729497994746e-06, | |
| "loss": 0.1175, | |
| "step": 252500 | |
| }, | |
| { | |
| "epoch": 34.99, | |
| "learning_rate": 2.5129995851196243e-06, | |
| "loss": 0.1229, | |
| "step": 253000 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_bleu": 73.7548, | |
| "eval_gen_len": 13.0268, | |
| "eval_loss": 0.16187956929206848, | |
| "eval_runtime": 322.0456, | |
| "eval_samples_per_second": 89.416, | |
| "eval_steps_per_second": 2.795, | |
| "step": 253085 | |
| }, | |
| { | |
| "epoch": 35.06, | |
| "learning_rate": 2.4784262204397733e-06, | |
| "loss": 0.117, | |
| "step": 253500 | |
| }, | |
| { | |
| "epoch": 35.13, | |
| "learning_rate": 2.443852855759923e-06, | |
| "loss": 0.1198, | |
| "step": 254000 | |
| }, | |
| { | |
| "epoch": 35.2, | |
| "learning_rate": 2.409348637809432e-06, | |
| "loss": 0.1191, | |
| "step": 254500 | |
| }, | |
| { | |
| "epoch": 35.26, | |
| "learning_rate": 2.3747752731295813e-06, | |
| "loss": 0.1171, | |
| "step": 255000 | |
| }, | |
| { | |
| "epoch": 35.33, | |
| "learning_rate": 2.3402710551790903e-06, | |
| "loss": 0.1169, | |
| "step": 255500 | |
| }, | |
| { | |
| "epoch": 35.4, | |
| "learning_rate": 2.3056976904992396e-06, | |
| "loss": 0.1202, | |
| "step": 256000 | |
| }, | |
| { | |
| "epoch": 35.47, | |
| "learning_rate": 2.271124325819389e-06, | |
| "loss": 0.1196, | |
| "step": 256500 | |
| }, | |
| { | |
| "epoch": 35.54, | |
| "learning_rate": 2.2365509611395383e-06, | |
| "loss": 0.1194, | |
| "step": 257000 | |
| }, | |
| { | |
| "epoch": 35.61, | |
| "learning_rate": 2.2019775964596876e-06, | |
| "loss": 0.1221, | |
| "step": 257500 | |
| }, | |
| { | |
| "epoch": 35.68, | |
| "learning_rate": 2.1674733785091966e-06, | |
| "loss": 0.1198, | |
| "step": 258000 | |
| }, | |
| { | |
| "epoch": 35.75, | |
| "learning_rate": 2.132900013829346e-06, | |
| "loss": 0.1185, | |
| "step": 258500 | |
| }, | |
| { | |
| "epoch": 35.82, | |
| "learning_rate": 2.0983266491494957e-06, | |
| "loss": 0.1188, | |
| "step": 259000 | |
| }, | |
| { | |
| "epoch": 35.89, | |
| "learning_rate": 2.0637532844696446e-06, | |
| "loss": 0.1199, | |
| "step": 259500 | |
| }, | |
| { | |
| "epoch": 35.96, | |
| "learning_rate": 2.029179919789794e-06, | |
| "loss": 0.1158, | |
| "step": 260000 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_bleu": 73.7699, | |
| "eval_gen_len": 13.0219, | |
| "eval_loss": 0.16182634234428406, | |
| "eval_runtime": 322.0872, | |
| "eval_samples_per_second": 89.404, | |
| "eval_steps_per_second": 2.794, | |
| "step": 260316 | |
| }, | |
| { | |
| "epoch": 36.03, | |
| "learning_rate": 1.9946065551099433e-06, | |
| "loss": 0.121, | |
| "step": 260500 | |
| }, | |
| { | |
| "epoch": 36.09, | |
| "learning_rate": 1.9601023371594522e-06, | |
| "loss": 0.119, | |
| "step": 261000 | |
| }, | |
| { | |
| "epoch": 36.16, | |
| "learning_rate": 1.925528972479602e-06, | |
| "loss": 0.1198, | |
| "step": 261500 | |
| }, | |
| { | |
| "epoch": 36.23, | |
| "learning_rate": 1.8909556077997511e-06, | |
| "loss": 0.1204, | |
| "step": 262000 | |
| }, | |
| { | |
| "epoch": 36.3, | |
| "learning_rate": 1.8563822431199005e-06, | |
| "loss": 0.1191, | |
| "step": 262500 | |
| }, | |
| { | |
| "epoch": 36.37, | |
| "learning_rate": 1.82180887844005e-06, | |
| "loss": 0.1149, | |
| "step": 263000 | |
| }, | |
| { | |
| "epoch": 36.44, | |
| "learning_rate": 1.7872355137601993e-06, | |
| "loss": 0.1165, | |
| "step": 263500 | |
| }, | |
| { | |
| "epoch": 36.51, | |
| "learning_rate": 1.7526621490803487e-06, | |
| "loss": 0.1192, | |
| "step": 264000 | |
| }, | |
| { | |
| "epoch": 36.58, | |
| "learning_rate": 1.7180887844004978e-06, | |
| "loss": 0.1206, | |
| "step": 264500 | |
| }, | |
| { | |
| "epoch": 36.65, | |
| "learning_rate": 1.6835154197206474e-06, | |
| "loss": 0.12, | |
| "step": 265000 | |
| }, | |
| { | |
| "epoch": 36.72, | |
| "learning_rate": 1.6490112017701565e-06, | |
| "loss": 0.1159, | |
| "step": 265500 | |
| }, | |
| { | |
| "epoch": 36.79, | |
| "learning_rate": 1.6144378370903059e-06, | |
| "loss": 0.1205, | |
| "step": 266000 | |
| }, | |
| { | |
| "epoch": 36.86, | |
| "learning_rate": 1.579864472410455e-06, | |
| "loss": 0.1174, | |
| "step": 266500 | |
| }, | |
| { | |
| "epoch": 36.92, | |
| "learning_rate": 1.5452911077306045e-06, | |
| "loss": 0.1177, | |
| "step": 267000 | |
| }, | |
| { | |
| "epoch": 36.99, | |
| "learning_rate": 1.5107868897801133e-06, | |
| "loss": 0.117, | |
| "step": 267500 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_bleu": 73.7699, | |
| "eval_gen_len": 13.0218, | |
| "eval_loss": 0.16194874048233032, | |
| "eval_runtime": 324.2894, | |
| "eval_samples_per_second": 88.797, | |
| "eval_steps_per_second": 2.775, | |
| "step": 267547 | |
| }, | |
| { | |
| "epoch": 37.06, | |
| "learning_rate": 1.4762135251002629e-06, | |
| "loss": 0.1176, | |
| "step": 268000 | |
| }, | |
| { | |
| "epoch": 37.13, | |
| "learning_rate": 1.4416401604204122e-06, | |
| "loss": 0.1191, | |
| "step": 268500 | |
| }, | |
| { | |
| "epoch": 37.2, | |
| "learning_rate": 1.4070667957405615e-06, | |
| "loss": 0.1161, | |
| "step": 269000 | |
| }, | |
| { | |
| "epoch": 37.27, | |
| "learning_rate": 1.3725625777900705e-06, | |
| "loss": 0.1156, | |
| "step": 269500 | |
| }, | |
| { | |
| "epoch": 37.34, | |
| "learning_rate": 1.33798921311022e-06, | |
| "loss": 0.116, | |
| "step": 270000 | |
| }, | |
| { | |
| "epoch": 37.41, | |
| "learning_rate": 1.3034158484303694e-06, | |
| "loss": 0.1189, | |
| "step": 270500 | |
| }, | |
| { | |
| "epoch": 37.48, | |
| "learning_rate": 1.2688424837505187e-06, | |
| "loss": 0.1176, | |
| "step": 271000 | |
| }, | |
| { | |
| "epoch": 37.55, | |
| "learning_rate": 1.2343382658000277e-06, | |
| "loss": 0.1162, | |
| "step": 271500 | |
| }, | |
| { | |
| "epoch": 37.62, | |
| "learning_rate": 1.1997649011201772e-06, | |
| "loss": 0.1211, | |
| "step": 272000 | |
| }, | |
| { | |
| "epoch": 37.68, | |
| "learning_rate": 1.1651915364403264e-06, | |
| "loss": 0.1158, | |
| "step": 272500 | |
| }, | |
| { | |
| "epoch": 37.75, | |
| "learning_rate": 1.130618171760476e-06, | |
| "loss": 0.12, | |
| "step": 273000 | |
| }, | |
| { | |
| "epoch": 37.82, | |
| "learning_rate": 1.0960448070806252e-06, | |
| "loss": 0.1176, | |
| "step": 273500 | |
| }, | |
| { | |
| "epoch": 37.89, | |
| "learning_rate": 1.0615405891301342e-06, | |
| "loss": 0.1195, | |
| "step": 274000 | |
| }, | |
| { | |
| "epoch": 37.96, | |
| "learning_rate": 1.0269672244502835e-06, | |
| "loss": 0.1181, | |
| "step": 274500 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_bleu": 73.7582, | |
| "eval_gen_len": 13.0304, | |
| "eval_loss": 0.16226525604724884, | |
| "eval_runtime": 323.3851, | |
| "eval_samples_per_second": 89.046, | |
| "eval_steps_per_second": 2.783, | |
| "step": 274778 | |
| }, | |
| { | |
| "epoch": 38.03, | |
| "learning_rate": 9.923938597704329e-07, | |
| "loss": 0.1179, | |
| "step": 275000 | |
| }, | |
| { | |
| "epoch": 38.1, | |
| "learning_rate": 9.578204950905822e-07, | |
| "loss": 0.1173, | |
| "step": 275500 | |
| }, | |
| { | |
| "epoch": 38.17, | |
| "learning_rate": 9.233162771400914e-07, | |
| "loss": 0.1181, | |
| "step": 276000 | |
| }, | |
| { | |
| "epoch": 38.24, | |
| "learning_rate": 8.887429124602406e-07, | |
| "loss": 0.118, | |
| "step": 276500 | |
| }, | |
| { | |
| "epoch": 38.31, | |
| "learning_rate": 8.541695477803901e-07, | |
| "loss": 0.1171, | |
| "step": 277000 | |
| }, | |
| { | |
| "epoch": 38.38, | |
| "learning_rate": 8.195961831005395e-07, | |
| "loss": 0.1189, | |
| "step": 277500 | |
| }, | |
| { | |
| "epoch": 38.45, | |
| "learning_rate": 7.850919651500484e-07, | |
| "loss": 0.1182, | |
| "step": 278000 | |
| }, | |
| { | |
| "epoch": 38.51, | |
| "learning_rate": 7.505186004701978e-07, | |
| "loss": 0.1168, | |
| "step": 278500 | |
| }, | |
| { | |
| "epoch": 38.58, | |
| "learning_rate": 7.159452357903473e-07, | |
| "loss": 0.1165, | |
| "step": 279000 | |
| }, | |
| { | |
| "epoch": 38.65, | |
| "learning_rate": 6.813718711104965e-07, | |
| "loss": 0.1151, | |
| "step": 279500 | |
| }, | |
| { | |
| "epoch": 38.72, | |
| "learning_rate": 6.468676531600056e-07, | |
| "loss": 0.1172, | |
| "step": 280000 | |
| }, | |
| { | |
| "epoch": 38.79, | |
| "learning_rate": 6.122942884801549e-07, | |
| "loss": 0.1174, | |
| "step": 280500 | |
| }, | |
| { | |
| "epoch": 38.86, | |
| "learning_rate": 5.777209238003043e-07, | |
| "loss": 0.1209, | |
| "step": 281000 | |
| }, | |
| { | |
| "epoch": 38.93, | |
| "learning_rate": 5.431475591204537e-07, | |
| "loss": 0.1193, | |
| "step": 281500 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "learning_rate": 5.08574194440603e-07, | |
| "loss": 0.1132, | |
| "step": 282000 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "eval_bleu": 73.7861, | |
| "eval_gen_len": 13.0281, | |
| "eval_loss": 0.16211672127246857, | |
| "eval_runtime": 325.6515, | |
| "eval_samples_per_second": 88.426, | |
| "eval_steps_per_second": 2.764, | |
| "step": 282009 | |
| }, | |
| { | |
| "epoch": 39.07, | |
| "learning_rate": 4.740699764901121e-07, | |
| "loss": 0.1193, | |
| "step": 282500 | |
| }, | |
| { | |
| "epoch": 39.14, | |
| "learning_rate": 4.395657585396211e-07, | |
| "loss": 0.1177, | |
| "step": 283000 | |
| }, | |
| { | |
| "epoch": 39.21, | |
| "learning_rate": 4.0499239385977044e-07, | |
| "loss": 0.1142, | |
| "step": 283500 | |
| }, | |
| { | |
| "epoch": 39.28, | |
| "learning_rate": 3.704190291799198e-07, | |
| "loss": 0.1159, | |
| "step": 284000 | |
| }, | |
| { | |
| "epoch": 39.34, | |
| "learning_rate": 3.358456645000692e-07, | |
| "loss": 0.1151, | |
| "step": 284500 | |
| }, | |
| { | |
| "epoch": 39.41, | |
| "learning_rate": 3.0127229982021856e-07, | |
| "loss": 0.1155, | |
| "step": 285000 | |
| }, | |
| { | |
| "epoch": 39.48, | |
| "learning_rate": 2.666989351403679e-07, | |
| "loss": 0.1189, | |
| "step": 285500 | |
| }, | |
| { | |
| "epoch": 39.55, | |
| "learning_rate": 2.3212557046051725e-07, | |
| "loss": 0.1179, | |
| "step": 286000 | |
| }, | |
| { | |
| "epoch": 39.62, | |
| "learning_rate": 1.975522057806666e-07, | |
| "loss": 0.1169, | |
| "step": 286500 | |
| }, | |
| { | |
| "epoch": 39.69, | |
| "learning_rate": 1.6297884110081592e-07, | |
| "loss": 0.1164, | |
| "step": 287000 | |
| }, | |
| { | |
| "epoch": 39.76, | |
| "learning_rate": 1.284054764209653e-07, | |
| "loss": 0.1182, | |
| "step": 287500 | |
| }, | |
| { | |
| "epoch": 39.83, | |
| "learning_rate": 9.383211174111465e-08, | |
| "loss": 0.1179, | |
| "step": 288000 | |
| }, | |
| { | |
| "epoch": 39.9, | |
| "learning_rate": 5.925874706126401e-08, | |
| "loss": 0.1164, | |
| "step": 288500 | |
| }, | |
| { | |
| "epoch": 39.97, | |
| "learning_rate": 2.475452911077306e-08, | |
| "loss": 0.1199, | |
| "step": 289000 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_bleu": 73.7743, | |
| "eval_gen_len": 13.0286, | |
| "eval_loss": 0.16223154962062836, | |
| "eval_runtime": 325.8877, | |
| "eval_samples_per_second": 88.362, | |
| "eval_steps_per_second": 2.762, | |
| "step": 289240 | |
| } | |
| ], | |
| "max_steps": 289240, | |
| "num_train_epochs": 40, | |
| "total_flos": 6.189779025355162e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |