|
{ |
|
"best_metric": 38.8455, |
|
"best_model_checkpoint": "./enko_mbartLarge_36p_tokenize_run1/checkpoint-50000", |
|
"epoch": 6.0392083991452195, |
|
"eval_steps": 5000, |
|
"global_step": 65000, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 5e-05, |
|
"loss": 1.9707, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 0.09, |
|
"learning_rate": 4.9766638663306266e-05, |
|
"loss": 1.5932, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 0.14, |
|
"learning_rate": 4.953327732661253e-05, |
|
"loss": 1.4429, |
|
"step": 1500 |
|
}, |
|
{ |
|
"epoch": 0.19, |
|
"learning_rate": 4.929991598991879e-05, |
|
"loss": 1.4161, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 0.23, |
|
"learning_rate": 4.9066554653225056e-05, |
|
"loss": 1.386, |
|
"step": 2500 |
|
}, |
|
{ |
|
"epoch": 0.28, |
|
"learning_rate": 4.883319331653132e-05, |
|
"loss": 1.3715, |
|
"step": 3000 |
|
}, |
|
{ |
|
"epoch": 0.33, |
|
"learning_rate": 4.859983197983758e-05, |
|
"loss": 1.3461, |
|
"step": 3500 |
|
}, |
|
{ |
|
"epoch": 0.37, |
|
"learning_rate": 4.8366470643143846e-05, |
|
"loss": 1.3319, |
|
"step": 4000 |
|
}, |
|
{ |
|
"epoch": 0.42, |
|
"learning_rate": 4.813310930645011e-05, |
|
"loss": 1.3196, |
|
"step": 4500 |
|
}, |
|
{ |
|
"epoch": 0.46, |
|
"learning_rate": 4.789974796975637e-05, |
|
"loss": 1.3157, |
|
"step": 5000 |
|
}, |
|
{ |
|
"epoch": 0.46, |
|
"eval_bleu": 34.4176, |
|
"eval_gen_len": 16.4931, |
|
"eval_loss": 1.2895288467407227, |
|
"eval_runtime": 1334.0511, |
|
"eval_samples_per_second": 16.195, |
|
"eval_steps_per_second": 1.013, |
|
"step": 5000 |
|
}, |
|
{ |
|
"epoch": 0.51, |
|
"learning_rate": 4.7666386633062636e-05, |
|
"loss": 1.2994, |
|
"step": 5500 |
|
}, |
|
{ |
|
"epoch": 0.56, |
|
"learning_rate": 4.74330252963689e-05, |
|
"loss": 1.2914, |
|
"step": 6000 |
|
}, |
|
{ |
|
"epoch": 0.6, |
|
"learning_rate": 4.719966395967516e-05, |
|
"loss": 1.2989, |
|
"step": 6500 |
|
}, |
|
{ |
|
"epoch": 0.65, |
|
"learning_rate": 4.6966302622981427e-05, |
|
"loss": 1.2784, |
|
"step": 7000 |
|
}, |
|
{ |
|
"epoch": 0.7, |
|
"learning_rate": 4.673294128628769e-05, |
|
"loss": 1.2662, |
|
"step": 7500 |
|
}, |
|
{ |
|
"epoch": 0.74, |
|
"learning_rate": 4.649957994959395e-05, |
|
"loss": 1.2529, |
|
"step": 8000 |
|
}, |
|
{ |
|
"epoch": 0.79, |
|
"learning_rate": 4.626621861290022e-05, |
|
"loss": 1.2614, |
|
"step": 8500 |
|
}, |
|
{ |
|
"epoch": 0.84, |
|
"learning_rate": 4.603285727620648e-05, |
|
"loss": 1.2564, |
|
"step": 9000 |
|
}, |
|
{ |
|
"epoch": 0.88, |
|
"learning_rate": 4.5799495939512744e-05, |
|
"loss": 1.2435, |
|
"step": 9500 |
|
}, |
|
{ |
|
"epoch": 0.93, |
|
"learning_rate": 4.556613460281901e-05, |
|
"loss": 1.2575, |
|
"step": 10000 |
|
}, |
|
{ |
|
"epoch": 0.93, |
|
"eval_bleu": 35.0029, |
|
"eval_gen_len": 16.8009, |
|
"eval_loss": 1.2279398441314697, |
|
"eval_runtime": 1342.4865, |
|
"eval_samples_per_second": 16.093, |
|
"eval_steps_per_second": 1.006, |
|
"step": 10000 |
|
}, |
|
{ |
|
"epoch": 0.98, |
|
"learning_rate": 4.533277326612527e-05, |
|
"loss": 1.2473, |
|
"step": 10500 |
|
}, |
|
{ |
|
"epoch": 1.02, |
|
"learning_rate": 4.5099411929431534e-05, |
|
"loss": 1.2544, |
|
"step": 11000 |
|
}, |
|
{ |
|
"epoch": 1.07, |
|
"learning_rate": 4.48660505927378e-05, |
|
"loss": 1.207, |
|
"step": 11500 |
|
}, |
|
{ |
|
"epoch": 1.11, |
|
"learning_rate": 4.463268925604406e-05, |
|
"loss": 1.1671, |
|
"step": 12000 |
|
}, |
|
{ |
|
"epoch": 1.16, |
|
"learning_rate": 4.4399327919350324e-05, |
|
"loss": 1.1709, |
|
"step": 12500 |
|
}, |
|
{ |
|
"epoch": 1.21, |
|
"learning_rate": 4.416596658265659e-05, |
|
"loss": 1.165, |
|
"step": 13000 |
|
}, |
|
{ |
|
"epoch": 1.25, |
|
"learning_rate": 4.393260524596285e-05, |
|
"loss": 1.1727, |
|
"step": 13500 |
|
}, |
|
{ |
|
"epoch": 1.3, |
|
"learning_rate": 4.3699243909269114e-05, |
|
"loss": 1.17, |
|
"step": 14000 |
|
}, |
|
{ |
|
"epoch": 1.35, |
|
"learning_rate": 4.346588257257538e-05, |
|
"loss": 1.1465, |
|
"step": 14500 |
|
}, |
|
{ |
|
"epoch": 1.39, |
|
"learning_rate": 4.323252123588164e-05, |
|
"loss": 1.1578, |
|
"step": 15000 |
|
}, |
|
{ |
|
"epoch": 1.39, |
|
"eval_bleu": 36.9282, |
|
"eval_gen_len": 16.5838, |
|
"eval_loss": 1.1733436584472656, |
|
"eval_runtime": 1318.0972, |
|
"eval_samples_per_second": 16.391, |
|
"eval_steps_per_second": 1.025, |
|
"step": 15000 |
|
}, |
|
{ |
|
"epoch": 1.44, |
|
"learning_rate": 4.2999159899187904e-05, |
|
"loss": 1.1582, |
|
"step": 15500 |
|
}, |
|
{ |
|
"epoch": 1.49, |
|
"learning_rate": 4.276579856249417e-05, |
|
"loss": 1.1495, |
|
"step": 16000 |
|
}, |
|
{ |
|
"epoch": 1.53, |
|
"learning_rate": 4.253243722580043e-05, |
|
"loss": 1.1349, |
|
"step": 16500 |
|
}, |
|
{ |
|
"epoch": 1.58, |
|
"learning_rate": 4.2299075889106695e-05, |
|
"loss": 1.1443, |
|
"step": 17000 |
|
}, |
|
{ |
|
"epoch": 1.63, |
|
"learning_rate": 4.206571455241296e-05, |
|
"loss": 1.1326, |
|
"step": 17500 |
|
}, |
|
{ |
|
"epoch": 1.67, |
|
"learning_rate": 4.183235321571922e-05, |
|
"loss": 1.1425, |
|
"step": 18000 |
|
}, |
|
{ |
|
"epoch": 1.72, |
|
"learning_rate": 4.1598991879025485e-05, |
|
"loss": 1.1196, |
|
"step": 18500 |
|
}, |
|
{ |
|
"epoch": 1.77, |
|
"learning_rate": 4.136563054233175e-05, |
|
"loss": 1.1272, |
|
"step": 19000 |
|
}, |
|
{ |
|
"epoch": 1.81, |
|
"learning_rate": 4.113226920563801e-05, |
|
"loss": 1.1186, |
|
"step": 19500 |
|
}, |
|
{ |
|
"epoch": 1.86, |
|
"learning_rate": 4.0898907868944275e-05, |
|
"loss": 1.0885, |
|
"step": 20000 |
|
}, |
|
{ |
|
"epoch": 1.86, |
|
"eval_bleu": 37.6913, |
|
"eval_gen_len": 16.6649, |
|
"eval_loss": 1.1464108228683472, |
|
"eval_runtime": 1319.4192, |
|
"eval_samples_per_second": 16.375, |
|
"eval_steps_per_second": 1.024, |
|
"step": 20000 |
|
}, |
|
{ |
|
"epoch": 1.9, |
|
"learning_rate": 4.066554653225054e-05, |
|
"loss": 1.0541, |
|
"step": 20500 |
|
}, |
|
{ |
|
"epoch": 1.95, |
|
"learning_rate": 4.04321851955568e-05, |
|
"loss": 1.0473, |
|
"step": 21000 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"learning_rate": 4.0198823858863065e-05, |
|
"loss": 1.0511, |
|
"step": 21500 |
|
}, |
|
{ |
|
"epoch": 2.04, |
|
"learning_rate": 3.996546252216933e-05, |
|
"loss": 1.0647, |
|
"step": 22000 |
|
}, |
|
{ |
|
"epoch": 2.09, |
|
"learning_rate": 3.973210118547559e-05, |
|
"loss": 1.0747, |
|
"step": 22500 |
|
}, |
|
{ |
|
"epoch": 2.14, |
|
"learning_rate": 3.9498739848781855e-05, |
|
"loss": 1.044, |
|
"step": 23000 |
|
}, |
|
{ |
|
"epoch": 2.18, |
|
"learning_rate": 3.926537851208812e-05, |
|
"loss": 1.052, |
|
"step": 23500 |
|
}, |
|
{ |
|
"epoch": 2.23, |
|
"learning_rate": 3.903201717539438e-05, |
|
"loss": 1.0624, |
|
"step": 24000 |
|
}, |
|
{ |
|
"epoch": 2.28, |
|
"learning_rate": 3.8798655838700645e-05, |
|
"loss": 1.0493, |
|
"step": 24500 |
|
}, |
|
{ |
|
"epoch": 2.32, |
|
"learning_rate": 3.856529450200691e-05, |
|
"loss": 1.0451, |
|
"step": 25000 |
|
}, |
|
{ |
|
"epoch": 2.32, |
|
"eval_bleu": 37.7875, |
|
"eval_gen_len": 16.5188, |
|
"eval_loss": 1.1437026262283325, |
|
"eval_runtime": 1315.5301, |
|
"eval_samples_per_second": 16.423, |
|
"eval_steps_per_second": 1.027, |
|
"step": 25000 |
|
}, |
|
{ |
|
"epoch": 2.37, |
|
"learning_rate": 3.833193316531317e-05, |
|
"loss": 1.054, |
|
"step": 25500 |
|
}, |
|
{ |
|
"epoch": 2.42, |
|
"learning_rate": 3.8098571828619436e-05, |
|
"loss": 1.0726, |
|
"step": 26000 |
|
}, |
|
{ |
|
"epoch": 2.46, |
|
"learning_rate": 3.78652104919257e-05, |
|
"loss": 1.032, |
|
"step": 26500 |
|
}, |
|
{ |
|
"epoch": 2.51, |
|
"learning_rate": 3.763184915523196e-05, |
|
"loss": 0.9733, |
|
"step": 27000 |
|
}, |
|
{ |
|
"epoch": 2.56, |
|
"learning_rate": 3.7398487818538226e-05, |
|
"loss": 0.9602, |
|
"step": 27500 |
|
}, |
|
{ |
|
"epoch": 2.6, |
|
"learning_rate": 3.716512648184449e-05, |
|
"loss": 0.9606, |
|
"step": 28000 |
|
}, |
|
{ |
|
"epoch": 2.65, |
|
"learning_rate": 3.693176514515075e-05, |
|
"loss": 0.9968, |
|
"step": 28500 |
|
}, |
|
{ |
|
"epoch": 2.69, |
|
"learning_rate": 3.6698403808457016e-05, |
|
"loss": 1.036, |
|
"step": 29000 |
|
}, |
|
{ |
|
"epoch": 2.74, |
|
"learning_rate": 3.646504247176328e-05, |
|
"loss": 1.0285, |
|
"step": 29500 |
|
}, |
|
{ |
|
"epoch": 2.79, |
|
"learning_rate": 3.623168113506954e-05, |
|
"loss": 1.0465, |
|
"step": 30000 |
|
}, |
|
{ |
|
"epoch": 2.79, |
|
"eval_bleu": 37.895, |
|
"eval_gen_len": 16.4987, |
|
"eval_loss": 1.1424869298934937, |
|
"eval_runtime": 1301.3337, |
|
"eval_samples_per_second": 16.602, |
|
"eval_steps_per_second": 1.038, |
|
"step": 30000 |
|
}, |
|
{ |
|
"epoch": 2.83, |
|
"learning_rate": 3.5998319798375806e-05, |
|
"loss": 1.0458, |
|
"step": 30500 |
|
}, |
|
{ |
|
"epoch": 2.88, |
|
"learning_rate": 3.576495846168207e-05, |
|
"loss": 0.9843, |
|
"step": 31000 |
|
}, |
|
{ |
|
"epoch": 2.93, |
|
"learning_rate": 3.553159712498833e-05, |
|
"loss": 0.9826, |
|
"step": 31500 |
|
}, |
|
{ |
|
"epoch": 2.97, |
|
"learning_rate": 3.5298235788294596e-05, |
|
"loss": 0.9817, |
|
"step": 32000 |
|
}, |
|
{ |
|
"epoch": 3.02, |
|
"learning_rate": 3.506487445160086e-05, |
|
"loss": 0.9911, |
|
"step": 32500 |
|
}, |
|
{ |
|
"epoch": 3.07, |
|
"learning_rate": 3.483151311490712e-05, |
|
"loss": 1.0227, |
|
"step": 33000 |
|
}, |
|
{ |
|
"epoch": 3.11, |
|
"learning_rate": 3.459815177821339e-05, |
|
"loss": 1.0126, |
|
"step": 33500 |
|
}, |
|
{ |
|
"epoch": 3.16, |
|
"learning_rate": 3.436479044151965e-05, |
|
"loss": 1.0125, |
|
"step": 34000 |
|
}, |
|
{ |
|
"epoch": 3.21, |
|
"learning_rate": 3.4131429104825913e-05, |
|
"loss": 1.0224, |
|
"step": 34500 |
|
}, |
|
{ |
|
"epoch": 3.25, |
|
"learning_rate": 3.389806776813218e-05, |
|
"loss": 1.0156, |
|
"step": 35000 |
|
}, |
|
{ |
|
"epoch": 3.25, |
|
"eval_bleu": 37.8434, |
|
"eval_gen_len": 16.5515, |
|
"eval_loss": 1.1464043855667114, |
|
"eval_runtime": 1324.0443, |
|
"eval_samples_per_second": 16.317, |
|
"eval_steps_per_second": 1.02, |
|
"step": 35000 |
|
}, |
|
{ |
|
"epoch": 3.3, |
|
"learning_rate": 3.366470643143844e-05, |
|
"loss": 1.009, |
|
"step": 35500 |
|
}, |
|
{ |
|
"epoch": 3.34, |
|
"learning_rate": 3.3431345094744704e-05, |
|
"loss": 0.964, |
|
"step": 36000 |
|
}, |
|
{ |
|
"epoch": 3.39, |
|
"learning_rate": 3.319798375805097e-05, |
|
"loss": 0.9596, |
|
"step": 36500 |
|
}, |
|
{ |
|
"epoch": 3.44, |
|
"learning_rate": 3.296462242135723e-05, |
|
"loss": 0.9587, |
|
"step": 37000 |
|
}, |
|
{ |
|
"epoch": 3.48, |
|
"learning_rate": 3.2731261084663494e-05, |
|
"loss": 0.9024, |
|
"step": 37500 |
|
}, |
|
{ |
|
"epoch": 3.53, |
|
"learning_rate": 3.249789974796976e-05, |
|
"loss": 0.9277, |
|
"step": 38000 |
|
}, |
|
{ |
|
"epoch": 3.58, |
|
"learning_rate": 3.226453841127603e-05, |
|
"loss": 0.9486, |
|
"step": 38500 |
|
}, |
|
{ |
|
"epoch": 3.62, |
|
"learning_rate": 3.2031177074582284e-05, |
|
"loss": 0.9543, |
|
"step": 39000 |
|
}, |
|
{ |
|
"epoch": 3.67, |
|
"learning_rate": 3.179781573788855e-05, |
|
"loss": 1.0035, |
|
"step": 39500 |
|
}, |
|
{ |
|
"epoch": 3.72, |
|
"learning_rate": 3.156445440119481e-05, |
|
"loss": 0.9893, |
|
"step": 40000 |
|
}, |
|
{ |
|
"epoch": 3.72, |
|
"eval_bleu": 37.358, |
|
"eval_gen_len": 16.6096, |
|
"eval_loss": 1.1543793678283691, |
|
"eval_runtime": 1317.3643, |
|
"eval_samples_per_second": 16.4, |
|
"eval_steps_per_second": 1.026, |
|
"step": 40000 |
|
}, |
|
{ |
|
"epoch": 3.76, |
|
"learning_rate": 3.1331093064501074e-05, |
|
"loss": 0.9877, |
|
"step": 40500 |
|
}, |
|
{ |
|
"epoch": 3.81, |
|
"learning_rate": 3.109773172780734e-05, |
|
"loss": 0.9901, |
|
"step": 41000 |
|
}, |
|
{ |
|
"epoch": 3.86, |
|
"learning_rate": 3.08643703911136e-05, |
|
"loss": 0.9699, |
|
"step": 41500 |
|
}, |
|
{ |
|
"epoch": 3.9, |
|
"learning_rate": 3.0631009054419864e-05, |
|
"loss": 0.9425, |
|
"step": 42000 |
|
}, |
|
{ |
|
"epoch": 3.95, |
|
"learning_rate": 3.039764771772613e-05, |
|
"loss": 0.9494, |
|
"step": 42500 |
|
}, |
|
{ |
|
"epoch": 4.0, |
|
"learning_rate": 3.016428638103239e-05, |
|
"loss": 0.9508, |
|
"step": 43000 |
|
}, |
|
{ |
|
"epoch": 4.04, |
|
"learning_rate": 2.9930925044338655e-05, |
|
"loss": 0.9409, |
|
"step": 43500 |
|
}, |
|
{ |
|
"epoch": 4.09, |
|
"learning_rate": 2.969756370764492e-05, |
|
"loss": 0.9012, |
|
"step": 44000 |
|
}, |
|
{ |
|
"epoch": 4.13, |
|
"learning_rate": 2.946420237095118e-05, |
|
"loss": 0.8723, |
|
"step": 44500 |
|
}, |
|
{ |
|
"epoch": 4.18, |
|
"learning_rate": 2.9230841034257445e-05, |
|
"loss": 0.8779, |
|
"step": 45000 |
|
}, |
|
{ |
|
"epoch": 4.18, |
|
"eval_bleu": 38.1772, |
|
"eval_gen_len": 16.457, |
|
"eval_loss": 1.1419273614883423, |
|
"eval_runtime": 1300.9539, |
|
"eval_samples_per_second": 16.607, |
|
"eval_steps_per_second": 1.038, |
|
"step": 45000 |
|
}, |
|
{ |
|
"epoch": 4.23, |
|
"learning_rate": 2.8997479697563705e-05, |
|
"loss": 0.8922, |
|
"step": 45500 |
|
}, |
|
{ |
|
"epoch": 4.27, |
|
"learning_rate": 2.8764118360869975e-05, |
|
"loss": 0.8749, |
|
"step": 46000 |
|
}, |
|
{ |
|
"epoch": 4.32, |
|
"learning_rate": 2.8530757024176235e-05, |
|
"loss": 0.8625, |
|
"step": 46500 |
|
}, |
|
{ |
|
"epoch": 4.37, |
|
"learning_rate": 2.82973956874825e-05, |
|
"loss": 0.8248, |
|
"step": 47000 |
|
}, |
|
{ |
|
"epoch": 4.41, |
|
"learning_rate": 2.8064034350788765e-05, |
|
"loss": 0.8554, |
|
"step": 47500 |
|
}, |
|
{ |
|
"epoch": 4.46, |
|
"learning_rate": 2.7830673014095025e-05, |
|
"loss": 0.8822, |
|
"step": 48000 |
|
}, |
|
{ |
|
"epoch": 4.51, |
|
"learning_rate": 2.759731167740129e-05, |
|
"loss": 0.7873, |
|
"step": 48500 |
|
}, |
|
{ |
|
"epoch": 4.55, |
|
"learning_rate": 2.7363950340707552e-05, |
|
"loss": 0.8181, |
|
"step": 49000 |
|
}, |
|
{ |
|
"epoch": 4.6, |
|
"learning_rate": 2.713058900401382e-05, |
|
"loss": 0.8259, |
|
"step": 49500 |
|
}, |
|
{ |
|
"epoch": 4.65, |
|
"learning_rate": 2.689722766732008e-05, |
|
"loss": 0.8565, |
|
"step": 50000 |
|
}, |
|
{ |
|
"epoch": 4.65, |
|
"eval_bleu": 38.8455, |
|
"eval_gen_len": 16.4749, |
|
"eval_loss": 1.1248719692230225, |
|
"eval_runtime": 1294.4037, |
|
"eval_samples_per_second": 16.691, |
|
"eval_steps_per_second": 1.044, |
|
"step": 50000 |
|
}, |
|
{ |
|
"epoch": 4.69, |
|
"learning_rate": 2.6663866330626342e-05, |
|
"loss": 0.9321, |
|
"step": 50500 |
|
}, |
|
{ |
|
"epoch": 4.74, |
|
"learning_rate": 2.643050499393261e-05, |
|
"loss": 0.8021, |
|
"step": 51000 |
|
}, |
|
{ |
|
"epoch": 4.78, |
|
"learning_rate": 2.6197143657238872e-05, |
|
"loss": 0.7701, |
|
"step": 51500 |
|
}, |
|
{ |
|
"epoch": 4.83, |
|
"learning_rate": 2.5963782320545132e-05, |
|
"loss": 0.7838, |
|
"step": 52000 |
|
}, |
|
{ |
|
"epoch": 4.88, |
|
"learning_rate": 2.5730420983851396e-05, |
|
"loss": 0.7467, |
|
"step": 52500 |
|
}, |
|
{ |
|
"epoch": 4.92, |
|
"learning_rate": 2.5497059647157663e-05, |
|
"loss": 0.7778, |
|
"step": 53000 |
|
}, |
|
{ |
|
"epoch": 4.97, |
|
"learning_rate": 2.5263698310463923e-05, |
|
"loss": 0.7451, |
|
"step": 53500 |
|
}, |
|
{ |
|
"epoch": 5.02, |
|
"learning_rate": 2.5030336973770186e-05, |
|
"loss": 0.7485, |
|
"step": 54000 |
|
}, |
|
{ |
|
"epoch": 5.06, |
|
"learning_rate": 2.479697563707645e-05, |
|
"loss": 0.7287, |
|
"step": 54500 |
|
}, |
|
{ |
|
"epoch": 5.11, |
|
"learning_rate": 2.4563614300382716e-05, |
|
"loss": 0.7293, |
|
"step": 55000 |
|
}, |
|
{ |
|
"epoch": 5.11, |
|
"eval_bleu": 38.4853, |
|
"eval_gen_len": 16.3462, |
|
"eval_loss": 1.1566184759140015, |
|
"eval_runtime": 1302.7449, |
|
"eval_samples_per_second": 16.584, |
|
"eval_steps_per_second": 1.037, |
|
"step": 55000 |
|
}, |
|
{ |
|
"epoch": 5.16, |
|
"learning_rate": 2.4330252963688976e-05, |
|
"loss": 0.7792, |
|
"step": 55500 |
|
}, |
|
{ |
|
"epoch": 5.2, |
|
"learning_rate": 2.409689162699524e-05, |
|
"loss": 0.7879, |
|
"step": 56000 |
|
}, |
|
{ |
|
"epoch": 5.25, |
|
"learning_rate": 2.3863530290301503e-05, |
|
"loss": 0.7784, |
|
"step": 56500 |
|
}, |
|
{ |
|
"epoch": 5.3, |
|
"learning_rate": 2.3630168953607766e-05, |
|
"loss": 0.7922, |
|
"step": 57000 |
|
}, |
|
{ |
|
"epoch": 5.34, |
|
"learning_rate": 2.3396807616914033e-05, |
|
"loss": 0.7878, |
|
"step": 57500 |
|
}, |
|
{ |
|
"epoch": 5.39, |
|
"learning_rate": 2.3163446280220293e-05, |
|
"loss": 0.7396, |
|
"step": 58000 |
|
}, |
|
{ |
|
"epoch": 5.44, |
|
"learning_rate": 2.293008494352656e-05, |
|
"loss": 0.7602, |
|
"step": 58500 |
|
}, |
|
{ |
|
"epoch": 5.48, |
|
"learning_rate": 2.269672360683282e-05, |
|
"loss": 0.7061, |
|
"step": 59000 |
|
}, |
|
{ |
|
"epoch": 5.53, |
|
"learning_rate": 2.2463362270139087e-05, |
|
"loss": 0.6956, |
|
"step": 59500 |
|
}, |
|
{ |
|
"epoch": 5.57, |
|
"learning_rate": 2.2230000933445347e-05, |
|
"loss": 0.7294, |
|
"step": 60000 |
|
}, |
|
{ |
|
"epoch": 5.57, |
|
"eval_bleu": 37.8822, |
|
"eval_gen_len": 16.3295, |
|
"eval_loss": 1.1824171543121338, |
|
"eval_runtime": 1289.8042, |
|
"eval_samples_per_second": 16.751, |
|
"eval_steps_per_second": 1.047, |
|
"step": 60000 |
|
}, |
|
{ |
|
"epoch": 5.62, |
|
"learning_rate": 2.199663959675161e-05, |
|
"loss": 0.7407, |
|
"step": 60500 |
|
}, |
|
{ |
|
"epoch": 5.67, |
|
"learning_rate": 2.1763278260057874e-05, |
|
"loss": 0.8116, |
|
"step": 61000 |
|
}, |
|
{ |
|
"epoch": 5.71, |
|
"learning_rate": 2.1529916923364137e-05, |
|
"loss": 0.8055, |
|
"step": 61500 |
|
}, |
|
{ |
|
"epoch": 5.76, |
|
"learning_rate": 2.1296555586670404e-05, |
|
"loss": 0.7065, |
|
"step": 62000 |
|
}, |
|
{ |
|
"epoch": 5.81, |
|
"learning_rate": 2.1063194249976664e-05, |
|
"loss": 0.688, |
|
"step": 62500 |
|
}, |
|
{ |
|
"epoch": 5.85, |
|
"learning_rate": 2.082983291328293e-05, |
|
"loss": 0.6955, |
|
"step": 63000 |
|
}, |
|
{ |
|
"epoch": 5.9, |
|
"learning_rate": 2.059647157658919e-05, |
|
"loss": 0.6782, |
|
"step": 63500 |
|
}, |
|
{ |
|
"epoch": 5.95, |
|
"learning_rate": 2.0363110239895454e-05, |
|
"loss": 0.7089, |
|
"step": 64000 |
|
}, |
|
{ |
|
"epoch": 5.99, |
|
"learning_rate": 2.0129748903201717e-05, |
|
"loss": 0.7563, |
|
"step": 64500 |
|
}, |
|
{ |
|
"epoch": 6.04, |
|
"learning_rate": 1.989638756650798e-05, |
|
"loss": 0.7254, |
|
"step": 65000 |
|
}, |
|
{ |
|
"epoch": 6.04, |
|
"eval_bleu": 37.3612, |
|
"eval_gen_len": 16.381, |
|
"eval_loss": 1.2153156995773315, |
|
"eval_runtime": 1293.9687, |
|
"eval_samples_per_second": 16.697, |
|
"eval_steps_per_second": 1.044, |
|
"step": 65000 |
|
} |
|
], |
|
"logging_steps": 500, |
|
"max_steps": 107630, |
|
"num_train_epochs": 10, |
|
"save_steps": 5000, |
|
"total_flos": 2.2540576769190134e+18, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|