| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 49.57446808510638, | |
| "eval_steps": 500, | |
| "global_step": 675, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.9999906714572185e-05, | |
| "loss": 2.0607, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 4.999766789911305e-05, | |
| "loss": 2.0068, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 4.999067203154777e-05, | |
| "loss": 1.8243, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "eval_loss": 1.6684231758117676, | |
| "eval_runtime": 4.0605, | |
| "eval_samples_per_second": 20.441, | |
| "eval_steps_per_second": 1.478, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 4.9979013702509664e-05, | |
| "loss": 1.7052, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 4.99626950870707e-05, | |
| "loss": 1.6022, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 4.994171922976348e-05, | |
| "loss": 1.5291, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "eval_loss": 1.400346040725708, | |
| "eval_runtime": 3.9709, | |
| "eval_samples_per_second": 20.902, | |
| "eval_steps_per_second": 1.511, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 4.991609004401324e-05, | |
| "loss": 1.4168, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 4.988581231140772e-05, | |
| "loss": 1.312, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 4.985089168080509e-05, | |
| "loss": 1.2355, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "eval_loss": 1.1807862520217896, | |
| "eval_runtime": 3.9823, | |
| "eval_samples_per_second": 20.842, | |
| "eval_steps_per_second": 1.507, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 3.19, | |
| "learning_rate": 4.981133466728004e-05, | |
| "loss": 1.1754, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 3.4, | |
| "learning_rate": 4.976714865090827e-05, | |
| "loss": 1.1393, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 3.57, | |
| "eval_loss": 1.0949289798736572, | |
| "eval_runtime": 3.9683, | |
| "eval_samples_per_second": 20.916, | |
| "eval_steps_per_second": 1.512, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 4.04, | |
| "learning_rate": 4.9718341875389625e-05, | |
| "loss": 1.123, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 4.26, | |
| "learning_rate": 4.966492344651005e-05, | |
| "loss": 1.0919, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 4.47, | |
| "learning_rate": 4.960690333044279e-05, | |
| "loss": 1.0659, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 4.55, | |
| "eval_loss": 1.045737624168396, | |
| "eval_runtime": 3.9807, | |
| "eval_samples_per_second": 20.85, | |
| "eval_steps_per_second": 1.507, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 5.11, | |
| "learning_rate": 4.9544292351888966e-05, | |
| "loss": 1.0601, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 5.32, | |
| "learning_rate": 4.947710219205808e-05, | |
| "loss": 1.0387, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 5.53, | |
| "learning_rate": 4.9405345386488614e-05, | |
| "loss": 1.0196, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 5.57, | |
| "eval_loss": 1.0065257549285889, | |
| "eval_runtime": 3.9679, | |
| "eval_samples_per_second": 20.918, | |
| "eval_steps_per_second": 1.512, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 6.17, | |
| "learning_rate": 4.9329035322709386e-05, | |
| "loss": 0.9975, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 6.38, | |
| "learning_rate": 4.924818623774178e-05, | |
| "loss": 0.9831, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 6.55, | |
| "eval_loss": 0.9685614109039307, | |
| "eval_runtime": 3.9721, | |
| "eval_samples_per_second": 20.896, | |
| "eval_steps_per_second": 1.511, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 7.02, | |
| "learning_rate": 4.916281321544362e-05, | |
| "loss": 0.9791, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 7.23, | |
| "learning_rate": 4.907293218369499e-05, | |
| "loss": 0.9494, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 7.45, | |
| "learning_rate": 4.897855991142658e-05, | |
| "loss": 0.9281, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 7.57, | |
| "eval_loss": 0.9254654049873352, | |
| "eval_runtime": 3.9691, | |
| "eval_samples_per_second": 20.911, | |
| "eval_steps_per_second": 1.512, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 8.09, | |
| "learning_rate": 4.88797140054912e-05, | |
| "loss": 0.9186, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 8.3, | |
| "learning_rate": 4.877641290737884e-05, | |
| "loss": 0.8878, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 8.51, | |
| "learning_rate": 4.8668675889776095e-05, | |
| "loss": 0.8678, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 8.55, | |
| "eval_loss": 0.8814197182655334, | |
| "eval_runtime": 3.978, | |
| "eval_samples_per_second": 20.865, | |
| "eval_steps_per_second": 1.508, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 9.15, | |
| "learning_rate": 4.855652305297052e-05, | |
| "loss": 0.8535, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 9.36, | |
| "learning_rate": 4.843997532110051e-05, | |
| "loss": 0.816, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 9.57, | |
| "learning_rate": 4.831905443825159e-05, | |
| "loss": 0.8054, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 9.57, | |
| "eval_loss": 0.8274821639060974, | |
| "eval_runtime": 3.9679, | |
| "eval_samples_per_second": 20.918, | |
| "eval_steps_per_second": 1.512, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 10.21, | |
| "learning_rate": 4.819378296439961e-05, | |
| "loss": 0.7717, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 10.43, | |
| "learning_rate": 4.806418427120179e-05, | |
| "loss": 0.7683, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 10.55, | |
| "eval_loss": 0.7860919237136841, | |
| "eval_runtime": 3.9806, | |
| "eval_samples_per_second": 20.851, | |
| "eval_steps_per_second": 1.507, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 11.06, | |
| "learning_rate": 4.793028253763633e-05, | |
| "loss": 0.741, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 11.28, | |
| "learning_rate": 4.779210274549134e-05, | |
| "loss": 0.7057, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 11.49, | |
| "learning_rate": 4.76496706747041e-05, | |
| "loss": 0.6906, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 11.57, | |
| "eval_loss": 0.7272327542304993, | |
| "eval_runtime": 3.9685, | |
| "eval_samples_per_second": 20.915, | |
| "eval_steps_per_second": 1.512, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 12.13, | |
| "learning_rate": 4.750301289855128e-05, | |
| "loss": 0.673, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 12.34, | |
| "learning_rate": 4.735215677869128e-05, | |
| "loss": 0.6411, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 12.55, | |
| "learning_rate": 4.719713046005938e-05, | |
| "loss": 0.6246, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 12.55, | |
| "eval_loss": 0.6794944405555725, | |
| "eval_runtime": 3.9823, | |
| "eval_samples_per_second": 20.842, | |
| "eval_steps_per_second": 1.507, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 13.19, | |
| "learning_rate": 4.703796286561679e-05, | |
| "loss": 0.6086, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 13.4, | |
| "learning_rate": 4.687468369095457e-05, | |
| "loss": 0.5813, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 13.57, | |
| "eval_loss": 0.6364239454269409, | |
| "eval_runtime": 3.9657, | |
| "eval_samples_per_second": 20.93, | |
| "eval_steps_per_second": 1.513, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 14.04, | |
| "learning_rate": 4.6707323398753346e-05, | |
| "loss": 0.5586, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 14.26, | |
| "learning_rate": 4.65359132131e-05, | |
| "loss": 0.5556, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 14.47, | |
| "learning_rate": 4.6360485113662216e-05, | |
| "loss": 0.5253, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 14.55, | |
| "eval_loss": 0.6078140139579773, | |
| "eval_runtime": 3.9649, | |
| "eval_samples_per_second": 20.934, | |
| "eval_steps_per_second": 1.513, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 15.11, | |
| "learning_rate": 4.618107182972209e-05, | |
| "loss": 0.5329, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 15.32, | |
| "learning_rate": 4.599770683406991e-05, | |
| "loss": 0.4948, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 15.53, | |
| "learning_rate": 4.581042433675921e-05, | |
| "loss": 0.5149, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 15.57, | |
| "eval_loss": 0.5811336636543274, | |
| "eval_runtime": 3.9681, | |
| "eval_samples_per_second": 20.917, | |
| "eval_steps_per_second": 1.512, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 16.17, | |
| "learning_rate": 4.5619259278724214e-05, | |
| "loss": 0.4857, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 16.38, | |
| "learning_rate": 4.542424732526105e-05, | |
| "loss": 0.4949, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 16.55, | |
| "eval_loss": 0.5605343580245972, | |
| "eval_runtime": 3.9813, | |
| "eval_samples_per_second": 20.847, | |
| "eval_steps_per_second": 1.507, | |
| "step": 229 | |
| }, | |
| { | |
| "epoch": 17.02, | |
| "learning_rate": 4.522542485937369e-05, | |
| "loss": 0.4737, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 17.23, | |
| "learning_rate": 4.5022828974986044e-05, | |
| "loss": 0.4675, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 17.45, | |
| "learning_rate": 4.4816497470021454e-05, | |
| "loss": 0.4644, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 17.57, | |
| "eval_loss": 0.5462371110916138, | |
| "eval_runtime": 3.9643, | |
| "eval_samples_per_second": 20.937, | |
| "eval_steps_per_second": 1.514, | |
| "step": 243 | |
| }, | |
| { | |
| "epoch": 18.09, | |
| "learning_rate": 4.4606468839350785e-05, | |
| "loss": 0.4565, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 18.3, | |
| "learning_rate": 4.43927822676105e-05, | |
| "loss": 0.4365, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 18.51, | |
| "learning_rate": 4.417547762189207e-05, | |
| "loss": 0.458, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 18.55, | |
| "eval_loss": 0.5346133708953857, | |
| "eval_runtime": 3.9682, | |
| "eval_samples_per_second": 20.916, | |
| "eval_steps_per_second": 1.512, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 19.15, | |
| "learning_rate": 4.395459544430407e-05, | |
| "loss": 0.449, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 19.36, | |
| "learning_rate": 4.373017694440827e-05, | |
| "loss": 0.4401, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 19.57, | |
| "learning_rate": 4.35022639915313e-05, | |
| "loss": 0.4294, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 19.57, | |
| "eval_loss": 0.5201942920684814, | |
| "eval_runtime": 3.9685, | |
| "eval_samples_per_second": 20.915, | |
| "eval_steps_per_second": 1.512, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 20.21, | |
| "learning_rate": 4.3270899106953105e-05, | |
| "loss": 0.4367, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 20.43, | |
| "learning_rate": 4.3036125455973896e-05, | |
| "loss": 0.4143, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 20.55, | |
| "eval_loss": 0.5177348852157593, | |
| "eval_runtime": 3.9827, | |
| "eval_samples_per_second": 20.84, | |
| "eval_steps_per_second": 1.507, | |
| "step": 283 | |
| }, | |
| { | |
| "epoch": 21.06, | |
| "learning_rate": 4.279798683986084e-05, | |
| "loss": 0.4244, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 21.28, | |
| "learning_rate": 4.2556527687676186e-05, | |
| "loss": 0.4096, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 21.49, | |
| "learning_rate": 4.231179304798815e-05, | |
| "loss": 0.4161, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 21.57, | |
| "eval_loss": 0.5107729434967041, | |
| "eval_runtime": 3.9674, | |
| "eval_samples_per_second": 20.92, | |
| "eval_steps_per_second": 1.512, | |
| "step": 297 | |
| }, | |
| { | |
| "epoch": 22.13, | |
| "learning_rate": 4.206382858046636e-05, | |
| "loss": 0.4075, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 22.34, | |
| "learning_rate": 4.181268054736318e-05, | |
| "loss": 0.4002, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 22.55, | |
| "learning_rate": 4.1558395804882695e-05, | |
| "loss": 0.4128, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 22.55, | |
| "eval_loss": 0.5056843757629395, | |
| "eval_runtime": 3.9783, | |
| "eval_samples_per_second": 20.863, | |
| "eval_steps_per_second": 1.508, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 23.19, | |
| "learning_rate": 4.130102179443877e-05, | |
| "loss": 0.3928, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 23.4, | |
| "learning_rate": 4.1040606533804024e-05, | |
| "loss": 0.4055, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 23.57, | |
| "eval_loss": 0.5070647597312927, | |
| "eval_runtime": 3.9713, | |
| "eval_samples_per_second": 20.9, | |
| "eval_steps_per_second": 1.511, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 24.04, | |
| "learning_rate": 4.077719860815132e-05, | |
| "loss": 0.4021, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 24.26, | |
| "learning_rate": 4.051084716098921e-05, | |
| "loss": 0.3999, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 24.47, | |
| "learning_rate": 4.0241601884993366e-05, | |
| "loss": 0.3937, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 24.55, | |
| "eval_loss": 0.505768895149231, | |
| "eval_runtime": 3.9783, | |
| "eval_samples_per_second": 20.863, | |
| "eval_steps_per_second": 1.508, | |
| "step": 337 | |
| }, | |
| { | |
| "epoch": 25.11, | |
| "learning_rate": 3.996951301273557e-05, | |
| "loss": 0.3927, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 25.32, | |
| "learning_rate": 3.969463130731183e-05, | |
| "loss": 0.377, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 25.53, | |
| "learning_rate": 3.941700805287168e-05, | |
| "loss": 0.3967, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 25.57, | |
| "eval_loss": 0.5016723871231079, | |
| "eval_runtime": 3.9654, | |
| "eval_samples_per_second": 20.931, | |
| "eval_steps_per_second": 1.513, | |
| "step": 351 | |
| }, | |
| { | |
| "epoch": 26.17, | |
| "learning_rate": 3.913669504505015e-05, | |
| "loss": 0.3859, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 26.38, | |
| "learning_rate": 3.885374458130438e-05, | |
| "loss": 0.3754, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 26.55, | |
| "eval_loss": 0.4997941851615906, | |
| "eval_runtime": 3.9766, | |
| "eval_samples_per_second": 20.872, | |
| "eval_steps_per_second": 1.509, | |
| "step": 364 | |
| }, | |
| { | |
| "epoch": 27.02, | |
| "learning_rate": 3.856820945115655e-05, | |
| "loss": 0.3853, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 27.23, | |
| "learning_rate": 3.828014292634509e-05, | |
| "loss": 0.3852, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 27.45, | |
| "learning_rate": 3.798959875088584e-05, | |
| "loss": 0.3742, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 27.57, | |
| "eval_loss": 0.5018514394760132, | |
| "eval_runtime": 3.9719, | |
| "eval_samples_per_second": 20.897, | |
| "eval_steps_per_second": 1.511, | |
| "step": 378 | |
| }, | |
| { | |
| "epoch": 28.09, | |
| "learning_rate": 3.769663113104516e-05, | |
| "loss": 0.3706, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 28.3, | |
| "learning_rate": 3.74012947252267e-05, | |
| "loss": 0.3759, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 28.51, | |
| "learning_rate": 3.7103644633774014e-05, | |
| "loss": 0.3756, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 28.55, | |
| "eval_loss": 0.5018544793128967, | |
| "eval_runtime": 3.9835, | |
| "eval_samples_per_second": 20.836, | |
| "eval_steps_per_second": 1.506, | |
| "step": 391 | |
| }, | |
| { | |
| "epoch": 29.15, | |
| "learning_rate": 3.680373638869047e-05, | |
| "loss": 0.3688, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 29.36, | |
| "learning_rate": 3.6501625943278805e-05, | |
| "loss": 0.3764, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 29.57, | |
| "learning_rate": 3.619736966170205e-05, | |
| "loss": 0.3652, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 29.57, | |
| "eval_loss": 0.5060749650001526, | |
| "eval_runtime": 3.9634, | |
| "eval_samples_per_second": 20.942, | |
| "eval_steps_per_second": 1.514, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 30.21, | |
| "learning_rate": 3.589102430846773e-05, | |
| "loss": 0.3688, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 30.43, | |
| "learning_rate": 3.5582647037837445e-05, | |
| "loss": 0.3597, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 30.55, | |
| "eval_loss": 0.5076042413711548, | |
| "eval_runtime": 3.9772, | |
| "eval_samples_per_second": 20.869, | |
| "eval_steps_per_second": 1.509, | |
| "step": 418 | |
| }, | |
| { | |
| "epoch": 31.06, | |
| "learning_rate": 3.527229538316371e-05, | |
| "loss": 0.3635, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 31.28, | |
| "learning_rate": 3.496002724615604e-05, | |
| "loss": 0.3564, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 31.49, | |
| "learning_rate": 3.464590088607839e-05, | |
| "loss": 0.3609, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 31.57, | |
| "eval_loss": 0.5078853964805603, | |
| "eval_runtime": 3.9577, | |
| "eval_samples_per_second": 20.972, | |
| "eval_steps_per_second": 1.516, | |
| "step": 432 | |
| }, | |
| { | |
| "epoch": 32.13, | |
| "learning_rate": 3.4329974908879783e-05, | |
| "loss": 0.3679, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 32.34, | |
| "learning_rate": 3.401230825626037e-05, | |
| "loss": 0.3498, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 32.55, | |
| "learning_rate": 3.369296019467473e-05, | |
| "loss": 0.3581, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 32.55, | |
| "eval_loss": 0.5108149647712708, | |
| "eval_runtime": 3.9725, | |
| "eval_samples_per_second": 20.894, | |
| "eval_steps_per_second": 1.51, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 33.19, | |
| "learning_rate": 3.3371990304274656e-05, | |
| "loss": 0.3623, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 33.4, | |
| "learning_rate": 3.304945846779346e-05, | |
| "loss": 0.3426, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 33.57, | |
| "eval_loss": 0.511660635471344, | |
| "eval_runtime": 3.9737, | |
| "eval_samples_per_second": 20.887, | |
| "eval_steps_per_second": 1.51, | |
| "step": 459 | |
| }, | |
| { | |
| "epoch": 34.04, | |
| "learning_rate": 3.272542485937369e-05, | |
| "loss": 0.3469, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 34.26, | |
| "learning_rate": 3.239994993334059e-05, | |
| "loss": 0.3513, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 34.47, | |
| "learning_rate": 3.207309441292325e-05, | |
| "loss": 0.3481, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 34.55, | |
| "eval_loss": 0.5140624046325684, | |
| "eval_runtime": 3.9754, | |
| "eval_samples_per_second": 20.878, | |
| "eval_steps_per_second": 1.509, | |
| "step": 472 | |
| }, | |
| { | |
| "epoch": 35.11, | |
| "learning_rate": 3.1744919278925605e-05, | |
| "loss": 0.3408, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 35.32, | |
| "learning_rate": 3.1415485758349346e-05, | |
| "loss": 0.3469, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 35.53, | |
| "learning_rate": 3.1084855312970896e-05, | |
| "loss": 0.3435, | |
| "step": 485 | |
| }, | |
| { | |
| "epoch": 35.57, | |
| "eval_loss": 0.5150405168533325, | |
| "eval_runtime": 3.9656, | |
| "eval_samples_per_second": 20.93, | |
| "eval_steps_per_second": 1.513, | |
| "step": 486 | |
| }, | |
| { | |
| "epoch": 36.17, | |
| "learning_rate": 3.075308962787466e-05, | |
| "loss": 0.3419, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 36.38, | |
| "learning_rate": 3.0420250599944523e-05, | |
| "loss": 0.3317, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 36.55, | |
| "eval_loss": 0.524531900882721, | |
| "eval_runtime": 3.975, | |
| "eval_samples_per_second": 20.881, | |
| "eval_steps_per_second": 1.509, | |
| "step": 499 | |
| }, | |
| { | |
| "epoch": 37.02, | |
| "learning_rate": 3.008640032631585e-05, | |
| "loss": 0.342, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 37.23, | |
| "learning_rate": 2.9751601092790184e-05, | |
| "loss": 0.3352, | |
| "step": 505 | |
| }, | |
| { | |
| "epoch": 37.45, | |
| "learning_rate": 2.9415915362214692e-05, | |
| "loss": 0.3387, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 37.57, | |
| "eval_loss": 0.5238548517227173, | |
| "eval_runtime": 3.9677, | |
| "eval_samples_per_second": 20.919, | |
| "eval_steps_per_second": 1.512, | |
| "step": 513 | |
| }, | |
| { | |
| "epoch": 38.09, | |
| "learning_rate": 2.907940576282856e-05, | |
| "loss": 0.3257, | |
| "step": 515 | |
| }, | |
| { | |
| "epoch": 38.3, | |
| "learning_rate": 2.874213507657861e-05, | |
| "loss": 0.3316, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 38.51, | |
| "learning_rate": 2.840416622740617e-05, | |
| "loss": 0.332, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 38.55, | |
| "eval_loss": 0.5318763852119446, | |
| "eval_runtime": 3.9794, | |
| "eval_samples_per_second": 20.858, | |
| "eval_steps_per_second": 1.508, | |
| "step": 526 | |
| }, | |
| { | |
| "epoch": 39.15, | |
| "learning_rate": 2.8065562269507463e-05, | |
| "loss": 0.3178, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 39.36, | |
| "learning_rate": 2.7726386375569748e-05, | |
| "loss": 0.3287, | |
| "step": 535 | |
| }, | |
| { | |
| "epoch": 39.57, | |
| "learning_rate": 2.7386701824985255e-05, | |
| "loss": 0.3334, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 39.57, | |
| "eval_loss": 0.5342416167259216, | |
| "eval_runtime": 3.9681, | |
| "eval_samples_per_second": 20.917, | |
| "eval_steps_per_second": 1.512, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 40.21, | |
| "learning_rate": 2.7046571992045334e-05, | |
| "loss": 0.3303, | |
| "step": 545 | |
| }, | |
| { | |
| "epoch": 40.43, | |
| "learning_rate": 2.6706060334116777e-05, | |
| "loss": 0.323, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 40.55, | |
| "eval_loss": 0.538831353187561, | |
| "eval_runtime": 3.9807, | |
| "eval_samples_per_second": 20.851, | |
| "eval_steps_per_second": 1.507, | |
| "step": 553 | |
| }, | |
| { | |
| "epoch": 41.06, | |
| "learning_rate": 2.636523037980275e-05, | |
| "loss": 0.3103, | |
| "step": 555 | |
| }, | |
| { | |
| "epoch": 41.28, | |
| "learning_rate": 2.6024145717090358e-05, | |
| "loss": 0.3232, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 41.49, | |
| "learning_rate": 2.5682869981487152e-05, | |
| "loss": 0.3144, | |
| "step": 565 | |
| }, | |
| { | |
| "epoch": 41.57, | |
| "eval_loss": 0.5423159599304199, | |
| "eval_runtime": 3.9774, | |
| "eval_samples_per_second": 20.868, | |
| "eval_steps_per_second": 1.509, | |
| "step": 567 | |
| }, | |
| { | |
| "epoch": 42.13, | |
| "learning_rate": 2.5341466844148775e-05, | |
| "loss": 0.3109, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 42.34, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.3162, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 42.55, | |
| "learning_rate": 2.4658533155851228e-05, | |
| "loss": 0.3092, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 42.55, | |
| "eval_loss": 0.54653400182724, | |
| "eval_runtime": 3.9802, | |
| "eval_samples_per_second": 20.853, | |
| "eval_steps_per_second": 1.507, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 43.19, | |
| "learning_rate": 2.431713001851286e-05, | |
| "loss": 0.3175, | |
| "step": 585 | |
| }, | |
| { | |
| "epoch": 43.4, | |
| "learning_rate": 2.3975854282909644e-05, | |
| "loss": 0.3084, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 43.57, | |
| "eval_loss": 0.5480648875236511, | |
| "eval_runtime": 3.9672, | |
| "eval_samples_per_second": 20.921, | |
| "eval_steps_per_second": 1.512, | |
| "step": 594 | |
| }, | |
| { | |
| "epoch": 44.04, | |
| "learning_rate": 2.3634769620197254e-05, | |
| "loss": 0.3039, | |
| "step": 595 | |
| }, | |
| { | |
| "epoch": 44.26, | |
| "learning_rate": 2.329393966588323e-05, | |
| "loss": 0.2977, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 44.47, | |
| "learning_rate": 2.295342800795468e-05, | |
| "loss": 0.3091, | |
| "step": 605 | |
| }, | |
| { | |
| "epoch": 44.55, | |
| "eval_loss": 0.5604838728904724, | |
| "eval_runtime": 3.9783, | |
| "eval_samples_per_second": 20.863, | |
| "eval_steps_per_second": 1.508, | |
| "step": 607 | |
| }, | |
| { | |
| "epoch": 45.11, | |
| "learning_rate": 2.261329817501475e-05, | |
| "loss": 0.3087, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 45.32, | |
| "learning_rate": 2.2273613624430255e-05, | |
| "loss": 0.2994, | |
| "step": 615 | |
| }, | |
| { | |
| "epoch": 45.53, | |
| "learning_rate": 2.1934437730492543e-05, | |
| "loss": 0.3044, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 45.57, | |
| "eval_loss": 0.560636579990387, | |
| "eval_runtime": 3.9626, | |
| "eval_samples_per_second": 20.946, | |
| "eval_steps_per_second": 1.514, | |
| "step": 621 | |
| }, | |
| { | |
| "epoch": 46.17, | |
| "learning_rate": 2.159583377259384e-05, | |
| "loss": 0.2867, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 46.38, | |
| "learning_rate": 2.1257864923421404e-05, | |
| "loss": 0.303, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 46.55, | |
| "eval_loss": 0.5683414340019226, | |
| "eval_runtime": 3.9884, | |
| "eval_samples_per_second": 20.81, | |
| "eval_steps_per_second": 1.504, | |
| "step": 634 | |
| }, | |
| { | |
| "epoch": 47.02, | |
| "learning_rate": 2.092059423717145e-05, | |
| "loss": 0.2971, | |
| "step": 635 | |
| }, | |
| { | |
| "epoch": 47.23, | |
| "learning_rate": 2.0584084637785317e-05, | |
| "loss": 0.2923, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 47.45, | |
| "learning_rate": 2.0248398907209826e-05, | |
| "loss": 0.2896, | |
| "step": 645 | |
| }, | |
| { | |
| "epoch": 47.57, | |
| "eval_loss": 0.572201669216156, | |
| "eval_runtime": 3.9766, | |
| "eval_samples_per_second": 20.872, | |
| "eval_steps_per_second": 1.509, | |
| "step": 648 | |
| }, | |
| { | |
| "epoch": 48.09, | |
| "learning_rate": 1.991359967368416e-05, | |
| "loss": 0.2963, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 48.3, | |
| "learning_rate": 1.957974940005548e-05, | |
| "loss": 0.2849, | |
| "step": 655 | |
| }, | |
| { | |
| "epoch": 48.51, | |
| "learning_rate": 1.9246910372125342e-05, | |
| "loss": 0.2854, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 48.55, | |
| "eval_loss": 0.5778339505195618, | |
| "eval_runtime": 3.9935, | |
| "eval_samples_per_second": 20.784, | |
| "eval_steps_per_second": 1.502, | |
| "step": 661 | |
| }, | |
| { | |
| "epoch": 49.15, | |
| "learning_rate": 1.8915144687029106e-05, | |
| "loss": 0.2884, | |
| "step": 665 | |
| }, | |
| { | |
| "epoch": 49.36, | |
| "learning_rate": 1.8584514241650666e-05, | |
| "loss": 0.2767, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 49.57, | |
| "learning_rate": 1.825508072107439e-05, | |
| "loss": 0.291, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 49.57, | |
| "eval_loss": 0.5825899839401245, | |
| "eval_runtime": 3.9815, | |
| "eval_samples_per_second": 20.846, | |
| "eval_steps_per_second": 1.507, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 49.57, | |
| "step": 675, | |
| "total_flos": 6306831714484224.0, | |
| "train_loss": 0.5519325028525458, | |
| "train_runtime": 6501.4714, | |
| "train_samples_per_second": 5.737, | |
| "train_steps_per_second": 0.177 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 1150, | |
| "num_train_epochs": 50, | |
| "save_steps": 500, | |
| "total_flos": 6306831714484224.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |