| { | |
| "best_metric": 0.6904399394989014, | |
| "best_model_checkpoint": "nllb_200_distilled_600M_ENtoFO_bsz_64_epochs_10lr7e-05/checkpoint-16500", | |
| "epoch": 5.798947842417985, | |
| "eval_steps": 500, | |
| "global_step": 16500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 1.4e-05, | |
| "loss": 1.6553, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 2.8e-05, | |
| "loss": 1.3075, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 4.2e-05, | |
| "loss": 1.2606, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 5.6e-05, | |
| "loss": 1.2085, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 7e-05, | |
| "loss": 1.1956, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "eval_bleu": 36.3211, | |
| "eval_chrf++": 55.6095, | |
| "eval_gen_len": 17.5404, | |
| "eval_loss": 1.01542067527771, | |
| "eval_runtime": 1596.0286, | |
| "eval_samples_per_second": 4.587, | |
| "eval_steps_per_second": 2.294, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 6.974955277280858e-05, | |
| "loss": 1.1487, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 6.949910554561716e-05, | |
| "loss": 1.1406, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 6.924865831842576e-05, | |
| "loss": 1.1197, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 6.899821109123434e-05, | |
| "loss": 1.0739, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 6.874776386404293e-05, | |
| "loss": 1.0817, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "eval_bleu": 37.9118, | |
| "eval_chrf++": 57.1775, | |
| "eval_gen_len": 17.6499, | |
| "eval_loss": 0.9288437962532043, | |
| "eval_runtime": 1599.8831, | |
| "eval_samples_per_second": 4.576, | |
| "eval_steps_per_second": 2.288, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 6.849731663685151e-05, | |
| "loss": 1.0784, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 6.824686940966009e-05, | |
| "loss": 1.0538, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 6.799642218246869e-05, | |
| "loss": 1.0431, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 6.774597495527727e-05, | |
| "loss": 1.0347, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 6.749552772808586e-05, | |
| "loss": 1.0162, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "eval_bleu": 39.3818, | |
| "eval_chrf++": 58.3559, | |
| "eval_gen_len": 17.6375, | |
| "eval_loss": 0.8730005025863647, | |
| "eval_runtime": 1591.8771, | |
| "eval_samples_per_second": 4.599, | |
| "eval_steps_per_second": 2.3, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 6.724508050089444e-05, | |
| "loss": 0.9995, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 6.699463327370304e-05, | |
| "loss": 0.987, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 6.674418604651162e-05, | |
| "loss": 1.0009, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 6.64937388193202e-05, | |
| "loss": 0.9843, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 6.624329159212879e-05, | |
| "loss": 0.974, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "eval_bleu": 40.0752, | |
| "eval_chrf++": 58.9288, | |
| "eval_gen_len": 17.741, | |
| "eval_loss": 0.8381767272949219, | |
| "eval_runtime": 1584.9965, | |
| "eval_samples_per_second": 4.619, | |
| "eval_steps_per_second": 2.31, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 6.599284436493739e-05, | |
| "loss": 0.9649, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 6.574239713774597e-05, | |
| "loss": 0.9511, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 6.549194991055455e-05, | |
| "loss": 0.9689, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 6.524150268336314e-05, | |
| "loss": 0.9512, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 6.499105545617173e-05, | |
| "loss": 0.9513, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "eval_bleu": 40.6133, | |
| "eval_chrf++": 59.5241, | |
| "eval_gen_len": 17.7642, | |
| "eval_loss": 0.8131038546562195, | |
| "eval_runtime": 1608.2394, | |
| "eval_samples_per_second": 4.552, | |
| "eval_steps_per_second": 2.276, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 6.474060822898032e-05, | |
| "loss": 0.9476, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 6.44901610017889e-05, | |
| "loss": 0.9202, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 6.423971377459748e-05, | |
| "loss": 0.9423, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 6.398926654740608e-05, | |
| "loss": 0.8949, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 6.373881932021467e-05, | |
| "loss": 0.8405, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "eval_bleu": 40.8822, | |
| "eval_chrf++": 59.9339, | |
| "eval_gen_len": 17.7189, | |
| "eval_loss": 0.7998338937759399, | |
| "eval_runtime": 1592.0637, | |
| "eval_samples_per_second": 4.598, | |
| "eval_steps_per_second": 2.3, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 6.348837209302325e-05, | |
| "loss": 0.8431, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 6.323792486583183e-05, | |
| "loss": 0.8383, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 6.298747763864043e-05, | |
| "loss": 0.838, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 6.273703041144901e-05, | |
| "loss": 0.8527, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 6.24865831842576e-05, | |
| "loss": 0.8252, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "eval_bleu": 41.6082, | |
| "eval_chrf++": 60.3254, | |
| "eval_gen_len": 17.7662, | |
| "eval_loss": 0.7859154939651489, | |
| "eval_runtime": 1613.9109, | |
| "eval_samples_per_second": 4.536, | |
| "eval_steps_per_second": 2.268, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 6.22361359570662e-05, | |
| "loss": 0.836, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 6.198568872987478e-05, | |
| "loss": 0.8274, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 6.173524150268336e-05, | |
| "loss": 0.8257, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 6.148479427549194e-05, | |
| "loss": 0.8301, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 6.123434704830053e-05, | |
| "loss": 0.8235, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "eval_bleu": 41.9785, | |
| "eval_chrf++": 60.615, | |
| "eval_gen_len": 17.6996, | |
| "eval_loss": 0.7718562483787537, | |
| "eval_runtime": 1591.3834, | |
| "eval_samples_per_second": 4.6, | |
| "eval_steps_per_second": 2.301, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 6.098389982110912e-05, | |
| "loss": 0.8335, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 6.073345259391771e-05, | |
| "loss": 0.8184, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 6.048300536672629e-05, | |
| "loss": 0.8139, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 6.0232558139534877e-05, | |
| "loss": 0.8121, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 5.998211091234346e-05, | |
| "loss": 0.8174, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "eval_bleu": 41.9942, | |
| "eval_chrf++": 60.7015, | |
| "eval_gen_len": 17.7548, | |
| "eval_loss": 0.7601388692855835, | |
| "eval_runtime": 1610.8686, | |
| "eval_samples_per_second": 4.545, | |
| "eval_steps_per_second": 2.273, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 5.973166368515206e-05, | |
| "loss": 0.8232, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 5.948121645796064e-05, | |
| "loss": 0.8099, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 5.9230769230769225e-05, | |
| "loss": 0.8154, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 5.898032200357781e-05, | |
| "loss": 0.818, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 5.87298747763864e-05, | |
| "loss": 0.7992, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "eval_bleu": 42.3622, | |
| "eval_chrf++": 61.0481, | |
| "eval_gen_len": 17.8145, | |
| "eval_loss": 0.7486168146133423, | |
| "eval_runtime": 1597.5591, | |
| "eval_samples_per_second": 4.583, | |
| "eval_steps_per_second": 2.292, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 5.847942754919499e-05, | |
| "loss": 0.8087, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 5.822898032200357e-05, | |
| "loss": 0.7958, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 5.7978533094812156e-05, | |
| "loss": 0.8022, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 5.7728085867620747e-05, | |
| "loss": 0.7876, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 5.747763864042934e-05, | |
| "loss": 0.7915, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "eval_bleu": 42.4851, | |
| "eval_chrf++": 61.1145, | |
| "eval_gen_len": 17.7756, | |
| "eval_loss": 0.7351738810539246, | |
| "eval_runtime": 1598.7533, | |
| "eval_samples_per_second": 4.579, | |
| "eval_steps_per_second": 2.29, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 5.722719141323792e-05, | |
| "loss": 0.7795, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 5.6976744186046504e-05, | |
| "loss": 0.8015, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 5.6726296958855094e-05, | |
| "loss": 0.7219, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 5.647584973166368e-05, | |
| "loss": 0.7231, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 5.622540250447227e-05, | |
| "loss": 0.718, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "eval_bleu": 42.5957, | |
| "eval_chrf++": 61.1828, | |
| "eval_gen_len": 17.7144, | |
| "eval_loss": 0.7349444627761841, | |
| "eval_runtime": 1593.2386, | |
| "eval_samples_per_second": 4.595, | |
| "eval_steps_per_second": 2.298, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 5.597495527728085e-05, | |
| "loss": 0.7155, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 5.572450805008944e-05, | |
| "loss": 0.7222, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 5.5474060822898026e-05, | |
| "loss": 0.7113, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 5.522361359570661e-05, | |
| "loss": 0.7067, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 5.497316636851521e-05, | |
| "loss": 0.714, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "eval_bleu": 43.1947, | |
| "eval_chrf++": 61.6389, | |
| "eval_gen_len": 17.7485, | |
| "eval_loss": 0.7279652953147888, | |
| "eval_runtime": 1602.3425, | |
| "eval_samples_per_second": 4.569, | |
| "eval_steps_per_second": 2.285, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 5.472271914132379e-05, | |
| "loss": 0.7284, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 5.4472271914132374e-05, | |
| "loss": 0.7106, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 5.422182468694096e-05, | |
| "loss": 0.7226, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 5.3971377459749555e-05, | |
| "loss": 0.7151, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 5.372093023255814e-05, | |
| "loss": 0.7242, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "eval_bleu": 43.0217, | |
| "eval_chrf++": 61.4, | |
| "eval_gen_len": 17.7472, | |
| "eval_loss": 0.7255465984344482, | |
| "eval_runtime": 1596.9259, | |
| "eval_samples_per_second": 4.584, | |
| "eval_steps_per_second": 2.293, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 5.347048300536672e-05, | |
| "loss": 0.7115, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 5.3220035778175306e-05, | |
| "loss": 0.6996, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 5.296958855098389e-05, | |
| "loss": 0.7226, | |
| "step": 7300 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 5.2719141323792486e-05, | |
| "loss": 0.7023, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 5.246869409660107e-05, | |
| "loss": 0.7035, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "eval_bleu": 42.9886, | |
| "eval_chrf++": 61.5585, | |
| "eval_gen_len": 17.7513, | |
| "eval_loss": 0.7192216515541077, | |
| "eval_runtime": 1608.427, | |
| "eval_samples_per_second": 4.552, | |
| "eval_steps_per_second": 2.276, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 5.2218246869409654e-05, | |
| "loss": 0.7175, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 5.1967799642218244e-05, | |
| "loss": 0.7164, | |
| "step": 7700 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 5.171735241502683e-05, | |
| "loss": 0.703, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 5.146690518783542e-05, | |
| "loss": 0.7067, | |
| "step": 7900 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 5.1216457960644e-05, | |
| "loss": 0.7048, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "eval_bleu": 42.9399, | |
| "eval_chrf++": 61.4851, | |
| "eval_gen_len": 17.7067, | |
| "eval_loss": 0.7168448567390442, | |
| "eval_runtime": 1552.4929, | |
| "eval_samples_per_second": 4.716, | |
| "eval_steps_per_second": 2.358, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 5.096601073345259e-05, | |
| "loss": 0.7127, | |
| "step": 8100 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 5.0715563506261176e-05, | |
| "loss": 0.7091, | |
| "step": 8200 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 5.046511627906976e-05, | |
| "loss": 0.7122, | |
| "step": 8300 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 5.021466905187835e-05, | |
| "loss": 0.6949, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 4.996422182468694e-05, | |
| "loss": 0.685, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "eval_bleu": 43.114, | |
| "eval_chrf++": 61.6028, | |
| "eval_gen_len": 17.844, | |
| "eval_loss": 0.7094260454177856, | |
| "eval_runtime": 1415.2591, | |
| "eval_samples_per_second": 5.173, | |
| "eval_steps_per_second": 2.587, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 4.9713774597495524e-05, | |
| "loss": 0.6618, | |
| "step": 8600 | |
| }, | |
| { | |
| "epoch": 3.06, | |
| "learning_rate": 4.946332737030411e-05, | |
| "loss": 0.6417, | |
| "step": 8700 | |
| }, | |
| { | |
| "epoch": 3.09, | |
| "learning_rate": 4.92128801431127e-05, | |
| "loss": 0.65, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 3.13, | |
| "learning_rate": 4.896243291592129e-05, | |
| "loss": 0.6375, | |
| "step": 8900 | |
| }, | |
| { | |
| "epoch": 3.16, | |
| "learning_rate": 4.871198568872987e-05, | |
| "loss": 0.632, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 3.16, | |
| "eval_bleu": 43.3779, | |
| "eval_chrf++": 61.8915, | |
| "eval_gen_len": 17.7121, | |
| "eval_loss": 0.7186790108680725, | |
| "eval_runtime": 1408.2967, | |
| "eval_samples_per_second": 5.198, | |
| "eval_steps_per_second": 2.6, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "learning_rate": 4.8461538461538455e-05, | |
| "loss": 0.6434, | |
| "step": 9100 | |
| }, | |
| { | |
| "epoch": 3.23, | |
| "learning_rate": 4.821109123434704e-05, | |
| "loss": 0.6354, | |
| "step": 9200 | |
| }, | |
| { | |
| "epoch": 3.27, | |
| "learning_rate": 4.7960644007155636e-05, | |
| "loss": 0.6374, | |
| "step": 9300 | |
| }, | |
| { | |
| "epoch": 3.3, | |
| "learning_rate": 4.771019677996422e-05, | |
| "loss": 0.6478, | |
| "step": 9400 | |
| }, | |
| { | |
| "epoch": 3.34, | |
| "learning_rate": 4.74597495527728e-05, | |
| "loss": 0.6444, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 3.34, | |
| "eval_bleu": 43.0761, | |
| "eval_chrf++": 61.6092, | |
| "eval_gen_len": 17.7518, | |
| "eval_loss": 0.7161450982093811, | |
| "eval_runtime": 1412.5727, | |
| "eval_samples_per_second": 5.183, | |
| "eval_steps_per_second": 2.592, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 3.37, | |
| "learning_rate": 4.720930232558139e-05, | |
| "loss": 0.6358, | |
| "step": 9600 | |
| }, | |
| { | |
| "epoch": 3.41, | |
| "learning_rate": 4.695885509838998e-05, | |
| "loss": 0.6502, | |
| "step": 9700 | |
| }, | |
| { | |
| "epoch": 3.44, | |
| "learning_rate": 4.670840787119857e-05, | |
| "loss": 0.6376, | |
| "step": 9800 | |
| }, | |
| { | |
| "epoch": 3.48, | |
| "learning_rate": 4.645796064400715e-05, | |
| "loss": 0.638, | |
| "step": 9900 | |
| }, | |
| { | |
| "epoch": 3.51, | |
| "learning_rate": 4.6207513416815735e-05, | |
| "loss": 0.6302, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 3.51, | |
| "eval_bleu": 43.4763, | |
| "eval_chrf++": 61.8105, | |
| "eval_gen_len": 17.7754, | |
| "eval_loss": 0.7070448398590088, | |
| "eval_runtime": 1409.243, | |
| "eval_samples_per_second": 5.195, | |
| "eval_steps_per_second": 2.598, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 3.55, | |
| "learning_rate": 4.5957066189624325e-05, | |
| "loss": 0.632, | |
| "step": 10100 | |
| }, | |
| { | |
| "epoch": 3.58, | |
| "learning_rate": 4.570661896243291e-05, | |
| "loss": 0.6364, | |
| "step": 10200 | |
| }, | |
| { | |
| "epoch": 3.62, | |
| "learning_rate": 4.54561717352415e-05, | |
| "loss": 0.6466, | |
| "step": 10300 | |
| }, | |
| { | |
| "epoch": 3.66, | |
| "learning_rate": 4.520572450805009e-05, | |
| "loss": 0.6373, | |
| "step": 10400 | |
| }, | |
| { | |
| "epoch": 3.69, | |
| "learning_rate": 4.495527728085867e-05, | |
| "loss": 0.6478, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 3.69, | |
| "eval_bleu": 43.725, | |
| "eval_chrf++": 62.0616, | |
| "eval_gen_len": 17.788, | |
| "eval_loss": 0.705007016658783, | |
| "eval_runtime": 1414.2328, | |
| "eval_samples_per_second": 5.177, | |
| "eval_steps_per_second": 2.589, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 3.73, | |
| "learning_rate": 4.470483005366726e-05, | |
| "loss": 0.6516, | |
| "step": 10600 | |
| }, | |
| { | |
| "epoch": 3.76, | |
| "learning_rate": 4.445438282647585e-05, | |
| "loss": 0.6334, | |
| "step": 10700 | |
| }, | |
| { | |
| "epoch": 3.8, | |
| "learning_rate": 4.420393559928444e-05, | |
| "loss": 0.6542, | |
| "step": 10800 | |
| }, | |
| { | |
| "epoch": 3.83, | |
| "learning_rate": 4.395348837209302e-05, | |
| "loss": 0.646, | |
| "step": 10900 | |
| }, | |
| { | |
| "epoch": 3.87, | |
| "learning_rate": 4.3703041144901605e-05, | |
| "loss": 0.6374, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 3.87, | |
| "eval_bleu": 43.7206, | |
| "eval_chrf++": 62.1048, | |
| "eval_gen_len": 17.7229, | |
| "eval_loss": 0.6963800191879272, | |
| "eval_runtime": 1413.4358, | |
| "eval_samples_per_second": 5.18, | |
| "eval_steps_per_second": 2.59, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 3.9, | |
| "learning_rate": 4.345259391771019e-05, | |
| "loss": 0.6416, | |
| "step": 11100 | |
| }, | |
| { | |
| "epoch": 3.94, | |
| "learning_rate": 4.3202146690518786e-05, | |
| "loss": 0.6249, | |
| "step": 11200 | |
| }, | |
| { | |
| "epoch": 3.97, | |
| "learning_rate": 4.295169946332737e-05, | |
| "loss": 0.638, | |
| "step": 11300 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "learning_rate": 4.270125223613595e-05, | |
| "loss": 0.6352, | |
| "step": 11400 | |
| }, | |
| { | |
| "epoch": 4.04, | |
| "learning_rate": 4.2450805008944536e-05, | |
| "loss": 0.5804, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 4.04, | |
| "eval_bleu": 43.8669, | |
| "eval_chrf++": 62.1364, | |
| "eval_gen_len": 17.7865, | |
| "eval_loss": 0.7024260759353638, | |
| "eval_runtime": 1410.9857, | |
| "eval_samples_per_second": 5.189, | |
| "eval_steps_per_second": 2.595, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 4.08, | |
| "learning_rate": 4.220035778175313e-05, | |
| "loss": 0.5799, | |
| "step": 11600 | |
| }, | |
| { | |
| "epoch": 4.11, | |
| "learning_rate": 4.194991055456172e-05, | |
| "loss": 0.5852, | |
| "step": 11700 | |
| }, | |
| { | |
| "epoch": 4.15, | |
| "learning_rate": 4.16994633273703e-05, | |
| "loss": 0.5801, | |
| "step": 11800 | |
| }, | |
| { | |
| "epoch": 4.18, | |
| "learning_rate": 4.1449016100178884e-05, | |
| "loss": 0.5945, | |
| "step": 11900 | |
| }, | |
| { | |
| "epoch": 4.22, | |
| "learning_rate": 4.1198568872987475e-05, | |
| "loss": 0.5919, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 4.22, | |
| "eval_bleu": 43.6775, | |
| "eval_chrf++": 61.9586, | |
| "eval_gen_len": 17.8369, | |
| "eval_loss": 0.7032192945480347, | |
| "eval_runtime": 1420.6308, | |
| "eval_samples_per_second": 5.153, | |
| "eval_steps_per_second": 2.577, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 4.25, | |
| "learning_rate": 4.094812164579606e-05, | |
| "loss": 0.5928, | |
| "step": 12100 | |
| }, | |
| { | |
| "epoch": 4.29, | |
| "learning_rate": 4.069767441860465e-05, | |
| "loss": 0.5923, | |
| "step": 12200 | |
| }, | |
| { | |
| "epoch": 4.32, | |
| "learning_rate": 4.044722719141323e-05, | |
| "loss": 0.5943, | |
| "step": 12300 | |
| }, | |
| { | |
| "epoch": 4.36, | |
| "learning_rate": 4.019677996422182e-05, | |
| "loss": 0.5905, | |
| "step": 12400 | |
| }, | |
| { | |
| "epoch": 4.39, | |
| "learning_rate": 3.9946332737030406e-05, | |
| "loss": 0.5879, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 4.39, | |
| "eval_bleu": 43.9642, | |
| "eval_chrf++": 62.2021, | |
| "eval_gen_len": 17.7873, | |
| "eval_loss": 0.7024480104446411, | |
| "eval_runtime": 1420.746, | |
| "eval_samples_per_second": 5.153, | |
| "eval_steps_per_second": 2.577, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 4.43, | |
| "learning_rate": 3.9695885509839e-05, | |
| "loss": 0.5855, | |
| "step": 12600 | |
| }, | |
| { | |
| "epoch": 4.46, | |
| "learning_rate": 3.944543828264758e-05, | |
| "loss": 0.5855, | |
| "step": 12700 | |
| }, | |
| { | |
| "epoch": 4.5, | |
| "learning_rate": 3.919499105545617e-05, | |
| "loss": 0.5833, | |
| "step": 12800 | |
| }, | |
| { | |
| "epoch": 4.53, | |
| "learning_rate": 3.8944543828264754e-05, | |
| "loss": 0.5767, | |
| "step": 12900 | |
| }, | |
| { | |
| "epoch": 4.57, | |
| "learning_rate": 3.869409660107334e-05, | |
| "loss": 0.5858, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 4.57, | |
| "eval_bleu": 44.027, | |
| "eval_chrf++": 62.2226, | |
| "eval_gen_len": 17.7678, | |
| "eval_loss": 0.6992958784103394, | |
| "eval_runtime": 1410.8973, | |
| "eval_samples_per_second": 5.189, | |
| "eval_steps_per_second": 2.595, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 4.6, | |
| "learning_rate": 3.8443649373881935e-05, | |
| "loss": 0.5775, | |
| "step": 13100 | |
| }, | |
| { | |
| "epoch": 4.64, | |
| "learning_rate": 3.819320214669052e-05, | |
| "loss": 0.5825, | |
| "step": 13200 | |
| }, | |
| { | |
| "epoch": 4.67, | |
| "learning_rate": 3.79427549194991e-05, | |
| "loss": 0.5851, | |
| "step": 13300 | |
| }, | |
| { | |
| "epoch": 4.71, | |
| "learning_rate": 3.7692307692307686e-05, | |
| "loss": 0.5913, | |
| "step": 13400 | |
| }, | |
| { | |
| "epoch": 4.74, | |
| "learning_rate": 3.744186046511627e-05, | |
| "loss": 0.5877, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 4.74, | |
| "eval_bleu": 44.1426, | |
| "eval_chrf++": 62.3429, | |
| "eval_gen_len": 17.7805, | |
| "eval_loss": 0.6957116723060608, | |
| "eval_runtime": 1414.8882, | |
| "eval_samples_per_second": 5.174, | |
| "eval_steps_per_second": 2.587, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 4.78, | |
| "learning_rate": 3.719141323792487e-05, | |
| "loss": 0.5857, | |
| "step": 13600 | |
| }, | |
| { | |
| "epoch": 4.81, | |
| "learning_rate": 3.694096601073345e-05, | |
| "loss": 0.5776, | |
| "step": 13700 | |
| }, | |
| { | |
| "epoch": 4.85, | |
| "learning_rate": 3.6690518783542034e-05, | |
| "loss": 0.5985, | |
| "step": 13800 | |
| }, | |
| { | |
| "epoch": 4.89, | |
| "learning_rate": 3.644007155635062e-05, | |
| "loss": 0.5855, | |
| "step": 13900 | |
| }, | |
| { | |
| "epoch": 4.92, | |
| "learning_rate": 3.618962432915921e-05, | |
| "loss": 0.5895, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 4.92, | |
| "eval_bleu": 44.2097, | |
| "eval_chrf++": 62.4158, | |
| "eval_gen_len": 17.7713, | |
| "eval_loss": 0.6944009065628052, | |
| "eval_runtime": 1417.3776, | |
| "eval_samples_per_second": 5.165, | |
| "eval_steps_per_second": 2.583, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 4.96, | |
| "learning_rate": 3.59391771019678e-05, | |
| "loss": 0.581, | |
| "step": 14100 | |
| }, | |
| { | |
| "epoch": 4.99, | |
| "learning_rate": 3.568872987477638e-05, | |
| "loss": 0.5835, | |
| "step": 14200 | |
| }, | |
| { | |
| "epoch": 5.03, | |
| "learning_rate": 3.543828264758497e-05, | |
| "loss": 0.5512, | |
| "step": 14300 | |
| }, | |
| { | |
| "epoch": 5.06, | |
| "learning_rate": 3.5187835420393556e-05, | |
| "loss": 0.5324, | |
| "step": 14400 | |
| }, | |
| { | |
| "epoch": 5.1, | |
| "learning_rate": 3.4937388193202146e-05, | |
| "loss": 0.5381, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 5.1, | |
| "eval_bleu": 43.9778, | |
| "eval_chrf++": 62.2087, | |
| "eval_gen_len": 17.8153, | |
| "eval_loss": 0.7013605833053589, | |
| "eval_runtime": 1419.0259, | |
| "eval_samples_per_second": 5.159, | |
| "eval_steps_per_second": 2.58, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 5.13, | |
| "learning_rate": 3.468694096601073e-05, | |
| "loss": 0.5364, | |
| "step": 14600 | |
| }, | |
| { | |
| "epoch": 5.17, | |
| "learning_rate": 3.443649373881932e-05, | |
| "loss": 0.543, | |
| "step": 14700 | |
| }, | |
| { | |
| "epoch": 5.2, | |
| "learning_rate": 3.4186046511627904e-05, | |
| "loss": 0.5432, | |
| "step": 14800 | |
| }, | |
| { | |
| "epoch": 5.24, | |
| "learning_rate": 3.3935599284436494e-05, | |
| "loss": 0.542, | |
| "step": 14900 | |
| }, | |
| { | |
| "epoch": 5.27, | |
| "learning_rate": 3.368515205724508e-05, | |
| "loss": 0.5385, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 5.27, | |
| "eval_bleu": 44.1326, | |
| "eval_chrf++": 62.3372, | |
| "eval_gen_len": 17.8174, | |
| "eval_loss": 0.7036887407302856, | |
| "eval_runtime": 1418.4921, | |
| "eval_samples_per_second": 5.161, | |
| "eval_steps_per_second": 2.581, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 5.31, | |
| "learning_rate": 3.343470483005367e-05, | |
| "loss": 0.5467, | |
| "step": 15100 | |
| }, | |
| { | |
| "epoch": 5.34, | |
| "learning_rate": 3.318425760286225e-05, | |
| "loss": 0.5466, | |
| "step": 15200 | |
| }, | |
| { | |
| "epoch": 5.38, | |
| "learning_rate": 3.2933810375670835e-05, | |
| "loss": 0.5439, | |
| "step": 15300 | |
| }, | |
| { | |
| "epoch": 5.41, | |
| "learning_rate": 3.2683363148479426e-05, | |
| "loss": 0.5403, | |
| "step": 15400 | |
| }, | |
| { | |
| "epoch": 5.45, | |
| "learning_rate": 3.243291592128801e-05, | |
| "loss": 0.5481, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 5.45, | |
| "eval_bleu": 44.053, | |
| "eval_chrf++": 62.418, | |
| "eval_gen_len": 17.7614, | |
| "eval_loss": 0.6976599097251892, | |
| "eval_runtime": 1417.644, | |
| "eval_samples_per_second": 5.164, | |
| "eval_steps_per_second": 2.582, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 5.48, | |
| "learning_rate": 3.21824686940966e-05, | |
| "loss": 0.5445, | |
| "step": 15600 | |
| }, | |
| { | |
| "epoch": 5.52, | |
| "learning_rate": 3.1932021466905183e-05, | |
| "loss": 0.5518, | |
| "step": 15700 | |
| }, | |
| { | |
| "epoch": 5.55, | |
| "learning_rate": 3.1681574239713774e-05, | |
| "loss": 0.5451, | |
| "step": 15800 | |
| }, | |
| { | |
| "epoch": 5.59, | |
| "learning_rate": 3.143112701252236e-05, | |
| "loss": 0.5387, | |
| "step": 15900 | |
| }, | |
| { | |
| "epoch": 5.62, | |
| "learning_rate": 3.118067978533094e-05, | |
| "loss": 0.5473, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 5.62, | |
| "eval_bleu": 44.2406, | |
| "eval_chrf++": 62.4882, | |
| "eval_gen_len": 17.8263, | |
| "eval_loss": 0.6982511878013611, | |
| "eval_runtime": 1415.9788, | |
| "eval_samples_per_second": 5.17, | |
| "eval_steps_per_second": 2.585, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 5.66, | |
| "learning_rate": 3.093023255813953e-05, | |
| "loss": 0.5483, | |
| "step": 16100 | |
| }, | |
| { | |
| "epoch": 5.69, | |
| "learning_rate": 3.0679785330948115e-05, | |
| "loss": 0.537, | |
| "step": 16200 | |
| }, | |
| { | |
| "epoch": 5.73, | |
| "learning_rate": 3.0429338103756705e-05, | |
| "loss": 0.5479, | |
| "step": 16300 | |
| }, | |
| { | |
| "epoch": 5.76, | |
| "learning_rate": 3.0178890876565292e-05, | |
| "loss": 0.5445, | |
| "step": 16400 | |
| }, | |
| { | |
| "epoch": 5.8, | |
| "learning_rate": 2.992844364937388e-05, | |
| "loss": 0.5466, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 5.8, | |
| "eval_bleu": 44.2692, | |
| "eval_chrf++": 62.4172, | |
| "eval_gen_len": 17.7783, | |
| "eval_loss": 0.6904399394989014, | |
| "eval_runtime": 1415.8621, | |
| "eval_samples_per_second": 5.171, | |
| "eval_steps_per_second": 2.586, | |
| "step": 16500 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 28450, | |
| "num_train_epochs": 10, | |
| "save_steps": 1500, | |
| "total_flos": 2.2884516243072614e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |