| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 50.0, | |
| "global_step": 49400, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 9.898785425101214e-06, | |
| "loss": 4.6519, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 2.3328564167022705, | |
| "eval_mae": 1.2115871906280518, | |
| "eval_mse": 2.3328561782836914, | |
| "eval_rmse": 1.5273690223693848, | |
| "eval_runtime": 2.139, | |
| "eval_samples_per_second": 460.504, | |
| "eval_steps_per_second": 57.972, | |
| "step": 988 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 9.79757085020243e-06, | |
| "loss": 1.9813, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 9.696356275303645e-06, | |
| "loss": 1.7364, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 2.25815749168396, | |
| "eval_mae": 1.1845210790634155, | |
| "eval_mse": 2.25815749168396, | |
| "eval_rmse": 1.5027166604995728, | |
| "eval_runtime": 2.2991, | |
| "eval_samples_per_second": 428.436, | |
| "eval_steps_per_second": 53.935, | |
| "step": 1976 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 9.595141700404859e-06, | |
| "loss": 1.6471, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 9.493927125506074e-06, | |
| "loss": 1.4318, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 2.2711498737335205, | |
| "eval_mae": 1.195154070854187, | |
| "eval_mse": 2.2711498737335205, | |
| "eval_rmse": 1.5070334672927856, | |
| "eval_runtime": 1.9177, | |
| "eval_samples_per_second": 513.633, | |
| "eval_steps_per_second": 64.66, | |
| "step": 2964 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "learning_rate": 9.392712550607288e-06, | |
| "loss": 1.3929, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 3.54, | |
| "learning_rate": 9.291497975708503e-06, | |
| "loss": 1.2099, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 2.5615780353546143, | |
| "eval_mae": 1.2618587017059326, | |
| "eval_mse": 2.5615780353546143, | |
| "eval_rmse": 1.60049307346344, | |
| "eval_runtime": 2.4694, | |
| "eval_samples_per_second": 398.879, | |
| "eval_steps_per_second": 50.214, | |
| "step": 3952 | |
| }, | |
| { | |
| "epoch": 4.05, | |
| "learning_rate": 9.190283400809717e-06, | |
| "loss": 1.1585, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 4.55, | |
| "learning_rate": 9.089068825910932e-06, | |
| "loss": 0.9984, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 2.386498212814331, | |
| "eval_mae": 1.2156014442443848, | |
| "eval_mse": 2.386498212814331, | |
| "eval_rmse": 1.5448294878005981, | |
| "eval_runtime": 2.1201, | |
| "eval_samples_per_second": 464.611, | |
| "eval_steps_per_second": 58.489, | |
| "step": 4940 | |
| }, | |
| { | |
| "epoch": 5.06, | |
| "learning_rate": 8.987854251012147e-06, | |
| "loss": 1.0114, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 5.57, | |
| "learning_rate": 8.886639676113361e-06, | |
| "loss": 0.897, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 2.3048605918884277, | |
| "eval_mae": 1.186144471168518, | |
| "eval_mse": 2.3048605918884277, | |
| "eval_rmse": 1.5181766748428345, | |
| "eval_runtime": 2.4807, | |
| "eval_samples_per_second": 397.063, | |
| "eval_steps_per_second": 49.986, | |
| "step": 5928 | |
| }, | |
| { | |
| "epoch": 6.07, | |
| "learning_rate": 8.785425101214575e-06, | |
| "loss": 0.912, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 6.58, | |
| "learning_rate": 8.68421052631579e-06, | |
| "loss": 0.7973, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 2.423027992248535, | |
| "eval_mae": 1.223141074180603, | |
| "eval_mse": 2.4230284690856934, | |
| "eval_rmse": 1.556607961654663, | |
| "eval_runtime": 2.3801, | |
| "eval_samples_per_second": 413.851, | |
| "eval_steps_per_second": 52.099, | |
| "step": 6916 | |
| }, | |
| { | |
| "epoch": 7.09, | |
| "learning_rate": 8.582995951417005e-06, | |
| "loss": 0.8141, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 7.59, | |
| "learning_rate": 8.481781376518219e-06, | |
| "loss": 0.7115, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 2.51936936378479, | |
| "eval_mae": 1.2446390390396118, | |
| "eval_mse": 2.51936936378479, | |
| "eval_rmse": 1.587252140045166, | |
| "eval_runtime": 2.2497, | |
| "eval_samples_per_second": 437.844, | |
| "eval_steps_per_second": 55.119, | |
| "step": 7904 | |
| }, | |
| { | |
| "epoch": 8.1, | |
| "learning_rate": 8.380566801619434e-06, | |
| "loss": 0.7455, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 8.6, | |
| "learning_rate": 8.279352226720648e-06, | |
| "loss": 0.6548, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 2.3894152641296387, | |
| "eval_mae": 1.20915687084198, | |
| "eval_mse": 2.3894152641296387, | |
| "eval_rmse": 1.5457733869552612, | |
| "eval_runtime": 2.012, | |
| "eval_samples_per_second": 489.572, | |
| "eval_steps_per_second": 61.631, | |
| "step": 8892 | |
| }, | |
| { | |
| "epoch": 9.11, | |
| "learning_rate": 8.178137651821862e-06, | |
| "loss": 0.6625, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 9.62, | |
| "learning_rate": 8.076923076923077e-06, | |
| "loss": 0.6466, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 2.3797826766967773, | |
| "eval_mae": 1.209175944328308, | |
| "eval_mse": 2.3797826766967773, | |
| "eval_rmse": 1.5426543951034546, | |
| "eval_runtime": 1.9282, | |
| "eval_samples_per_second": 510.852, | |
| "eval_steps_per_second": 64.31, | |
| "step": 9880 | |
| }, | |
| { | |
| "epoch": 10.12, | |
| "learning_rate": 7.975708502024292e-06, | |
| "loss": 0.6429, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 10.63, | |
| "learning_rate": 7.874493927125508e-06, | |
| "loss": 0.6218, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_loss": 2.325528383255005, | |
| "eval_mae": 1.197866678237915, | |
| "eval_mse": 2.325528383255005, | |
| "eval_rmse": 1.5249682664871216, | |
| "eval_runtime": 2.2819, | |
| "eval_samples_per_second": 431.658, | |
| "eval_steps_per_second": 54.341, | |
| "step": 10868 | |
| }, | |
| { | |
| "epoch": 11.13, | |
| "learning_rate": 7.773279352226721e-06, | |
| "loss": 0.596, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 11.64, | |
| "learning_rate": 7.672064777327935e-06, | |
| "loss": 0.5498, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_loss": 2.391416072845459, | |
| "eval_mae": 1.2055319547653198, | |
| "eval_mse": 2.391416072845459, | |
| "eval_rmse": 1.5464204549789429, | |
| "eval_runtime": 2.3484, | |
| "eval_samples_per_second": 419.443, | |
| "eval_steps_per_second": 52.803, | |
| "step": 11856 | |
| }, | |
| { | |
| "epoch": 12.15, | |
| "learning_rate": 7.570850202429151e-06, | |
| "loss": 0.5617, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 12.65, | |
| "learning_rate": 7.469635627530365e-06, | |
| "loss": 0.5403, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_loss": 2.4148483276367188, | |
| "eval_mae": 1.2168691158294678, | |
| "eval_mse": 2.4148483276367188, | |
| "eval_rmse": 1.5539782047271729, | |
| "eval_runtime": 2.3371, | |
| "eval_samples_per_second": 421.463, | |
| "eval_steps_per_second": 53.057, | |
| "step": 12844 | |
| }, | |
| { | |
| "epoch": 13.16, | |
| "learning_rate": 7.368421052631579e-06, | |
| "loss": 0.5424, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 13.66, | |
| "learning_rate": 7.267206477732795e-06, | |
| "loss": 0.5392, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_loss": 2.429582357406616, | |
| "eval_mae": 1.2232253551483154, | |
| "eval_mse": 2.429582357406616, | |
| "eval_rmse": 1.5587117671966553, | |
| "eval_runtime": 1.971, | |
| "eval_samples_per_second": 499.752, | |
| "eval_steps_per_second": 62.913, | |
| "step": 13832 | |
| }, | |
| { | |
| "epoch": 14.17, | |
| "learning_rate": 7.165991902834008e-06, | |
| "loss": 0.5105, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 14.68, | |
| "learning_rate": 7.064777327935223e-06, | |
| "loss": 0.5224, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_loss": 2.279872417449951, | |
| "eval_mae": 1.1799190044403076, | |
| "eval_mse": 2.279872417449951, | |
| "eval_rmse": 1.5099246501922607, | |
| "eval_runtime": 2.2712, | |
| "eval_samples_per_second": 433.694, | |
| "eval_steps_per_second": 54.597, | |
| "step": 14820 | |
| }, | |
| { | |
| "epoch": 15.18, | |
| "learning_rate": 6.963562753036438e-06, | |
| "loss": 0.5082, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 15.69, | |
| "learning_rate": 6.862348178137653e-06, | |
| "loss": 0.4868, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_loss": 2.309877634048462, | |
| "eval_mae": 1.1822220087051392, | |
| "eval_mse": 2.309877634048462, | |
| "eval_rmse": 1.519828200340271, | |
| "eval_runtime": 1.9368, | |
| "eval_samples_per_second": 508.564, | |
| "eval_steps_per_second": 64.022, | |
| "step": 15808 | |
| }, | |
| { | |
| "epoch": 16.19, | |
| "learning_rate": 6.761133603238867e-06, | |
| "loss": 0.5021, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 16.7, | |
| "learning_rate": 6.6599190283400816e-06, | |
| "loss": 0.4702, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_loss": 2.205157518386841, | |
| "eval_mae": 1.1669542789459229, | |
| "eval_mse": 2.205157518386841, | |
| "eval_rmse": 1.4849772453308105, | |
| "eval_runtime": 2.2927, | |
| "eval_samples_per_second": 429.627, | |
| "eval_steps_per_second": 54.085, | |
| "step": 16796 | |
| }, | |
| { | |
| "epoch": 17.21, | |
| "learning_rate": 6.558704453441296e-06, | |
| "loss": 0.4905, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 17.71, | |
| "learning_rate": 6.457489878542511e-06, | |
| "loss": 0.4665, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_loss": 2.323201894760132, | |
| "eval_mae": 1.1936134099960327, | |
| "eval_mse": 2.323201894760132, | |
| "eval_rmse": 1.5242053270339966, | |
| "eval_runtime": 2.1851, | |
| "eval_samples_per_second": 450.772, | |
| "eval_steps_per_second": 56.747, | |
| "step": 17784 | |
| }, | |
| { | |
| "epoch": 18.22, | |
| "learning_rate": 6.356275303643725e-06, | |
| "loss": 0.4431, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 18.72, | |
| "learning_rate": 6.2550607287449395e-06, | |
| "loss": 0.483, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_loss": 2.3569979667663574, | |
| "eval_mae": 1.2059428691864014, | |
| "eval_mse": 2.3569979667663574, | |
| "eval_rmse": 1.5352517366409302, | |
| "eval_runtime": 6.1451, | |
| "eval_samples_per_second": 160.29, | |
| "eval_steps_per_second": 20.179, | |
| "step": 18772 | |
| }, | |
| { | |
| "epoch": 19.23, | |
| "learning_rate": 6.153846153846155e-06, | |
| "loss": 0.4433, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 19.74, | |
| "learning_rate": 6.0526315789473685e-06, | |
| "loss": 0.4561, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_loss": 2.313786268234253, | |
| "eval_mae": 1.190987229347229, | |
| "eval_mse": 2.313786268234253, | |
| "eval_rmse": 1.5211135149002075, | |
| "eval_runtime": 6.1814, | |
| "eval_samples_per_second": 159.348, | |
| "eval_steps_per_second": 20.06, | |
| "step": 19760 | |
| }, | |
| { | |
| "epoch": 20.24, | |
| "learning_rate": 5.951417004048583e-06, | |
| "loss": 0.4688, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 20.75, | |
| "learning_rate": 5.850202429149798e-06, | |
| "loss": 0.4577, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_loss": 2.2783560752868652, | |
| "eval_mae": 1.1627191305160522, | |
| "eval_mse": 2.2783560752868652, | |
| "eval_rmse": 1.5094224214553833, | |
| "eval_runtime": 6.5272, | |
| "eval_samples_per_second": 150.907, | |
| "eval_steps_per_second": 18.997, | |
| "step": 20748 | |
| }, | |
| { | |
| "epoch": 21.26, | |
| "learning_rate": 5.748987854251013e-06, | |
| "loss": 0.4261, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 21.76, | |
| "learning_rate": 5.6477732793522265e-06, | |
| "loss": 0.4251, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_loss": 2.3060412406921387, | |
| "eval_mae": 1.176581621170044, | |
| "eval_mse": 2.3060412406921387, | |
| "eval_rmse": 1.5185655355453491, | |
| "eval_runtime": 6.411, | |
| "eval_samples_per_second": 153.641, | |
| "eval_steps_per_second": 19.342, | |
| "step": 21736 | |
| }, | |
| { | |
| "epoch": 22.27, | |
| "learning_rate": 5.546558704453442e-06, | |
| "loss": 0.4235, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 22.77, | |
| "learning_rate": 5.445344129554656e-06, | |
| "loss": 0.4477, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_loss": 2.3399007320404053, | |
| "eval_mae": 1.1934117078781128, | |
| "eval_mse": 2.339900493621826, | |
| "eval_rmse": 1.5296733379364014, | |
| "eval_runtime": 6.5358, | |
| "eval_samples_per_second": 150.708, | |
| "eval_steps_per_second": 18.972, | |
| "step": 22724 | |
| }, | |
| { | |
| "epoch": 23.28, | |
| "learning_rate": 5.344129554655872e-06, | |
| "loss": 0.3849, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 23.79, | |
| "learning_rate": 5.242914979757085e-06, | |
| "loss": 0.4274, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_loss": 2.2604634761810303, | |
| "eval_mae": 1.1710097789764404, | |
| "eval_mse": 2.2604634761810303, | |
| "eval_rmse": 1.503483772277832, | |
| "eval_runtime": 6.4581, | |
| "eval_samples_per_second": 152.522, | |
| "eval_steps_per_second": 19.201, | |
| "step": 23712 | |
| }, | |
| { | |
| "epoch": 24.29, | |
| "learning_rate": 5.1417004048583e-06, | |
| "loss": 0.402, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 24.8, | |
| "learning_rate": 5.040485829959515e-06, | |
| "loss": 0.4176, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_loss": 2.277299165725708, | |
| "eval_mae": 1.1737443208694458, | |
| "eval_mse": 2.277299404144287, | |
| "eval_rmse": 1.5090724229812622, | |
| "eval_runtime": 6.5489, | |
| "eval_samples_per_second": 150.407, | |
| "eval_steps_per_second": 18.935, | |
| "step": 24700 | |
| }, | |
| { | |
| "epoch": 25.3, | |
| "learning_rate": 4.939271255060729e-06, | |
| "loss": 0.4278, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 25.81, | |
| "learning_rate": 4.838056680161944e-06, | |
| "loss": 0.4105, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_loss": 2.3140110969543457, | |
| "eval_mae": 1.1842072010040283, | |
| "eval_mse": 2.3140110969543457, | |
| "eval_rmse": 1.521187424659729, | |
| "eval_runtime": 6.5703, | |
| "eval_samples_per_second": 149.918, | |
| "eval_steps_per_second": 18.873, | |
| "step": 25688 | |
| }, | |
| { | |
| "epoch": 26.32, | |
| "learning_rate": 4.736842105263158e-06, | |
| "loss": 0.404, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 26.82, | |
| "learning_rate": 4.635627530364373e-06, | |
| "loss": 0.3843, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_loss": 2.2196788787841797, | |
| "eval_mae": 1.1630769968032837, | |
| "eval_mse": 2.2196786403656006, | |
| "eval_rmse": 1.489858627319336, | |
| "eval_runtime": 4.2474, | |
| "eval_samples_per_second": 231.905, | |
| "eval_steps_per_second": 29.194, | |
| "step": 26676 | |
| }, | |
| { | |
| "epoch": 27.33, | |
| "learning_rate": 4.534412955465588e-06, | |
| "loss": 0.4395, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 27.83, | |
| "learning_rate": 4.433198380566802e-06, | |
| "loss": 0.3985, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_loss": 2.2451844215393066, | |
| "eval_mae": 1.1653474569320679, | |
| "eval_mse": 2.2451844215393066, | |
| "eval_rmse": 1.4983938932418823, | |
| "eval_runtime": 4.5968, | |
| "eval_samples_per_second": 214.279, | |
| "eval_steps_per_second": 26.975, | |
| "step": 27664 | |
| }, | |
| { | |
| "epoch": 28.34, | |
| "learning_rate": 4.3319838056680166e-06, | |
| "loss": 0.3633, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 28.85, | |
| "learning_rate": 4.230769230769231e-06, | |
| "loss": 0.4055, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_loss": 2.1678428649902344, | |
| "eval_mae": 1.1424471139907837, | |
| "eval_mse": 2.1678428649902344, | |
| "eval_rmse": 1.4723596572875977, | |
| "eval_runtime": 3.4579, | |
| "eval_samples_per_second": 284.854, | |
| "eval_steps_per_second": 35.86, | |
| "step": 28652 | |
| }, | |
| { | |
| "epoch": 29.35, | |
| "learning_rate": 4.1295546558704455e-06, | |
| "loss": 0.4101, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 29.86, | |
| "learning_rate": 4.028340080971661e-06, | |
| "loss": 0.3916, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_loss": 2.2453699111938477, | |
| "eval_mae": 1.166300654411316, | |
| "eval_mse": 2.2453699111938477, | |
| "eval_rmse": 1.4984558820724487, | |
| "eval_runtime": 2.9933, | |
| "eval_samples_per_second": 329.066, | |
| "eval_steps_per_second": 41.426, | |
| "step": 29640 | |
| }, | |
| { | |
| "epoch": 30.36, | |
| "learning_rate": 3.9271255060728745e-06, | |
| "loss": 0.3769, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 30.87, | |
| "learning_rate": 3.825910931174089e-06, | |
| "loss": 0.3905, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_loss": 2.278787136077881, | |
| "eval_mae": 1.170925259590149, | |
| "eval_mse": 2.278787136077881, | |
| "eval_rmse": 1.5095652341842651, | |
| "eval_runtime": 2.1743, | |
| "eval_samples_per_second": 453.018, | |
| "eval_steps_per_second": 57.03, | |
| "step": 30628 | |
| }, | |
| { | |
| "epoch": 31.38, | |
| "learning_rate": 3.724696356275304e-06, | |
| "loss": 0.3638, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 31.88, | |
| "learning_rate": 3.6234817813765184e-06, | |
| "loss": 0.4033, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_loss": 2.218869686126709, | |
| "eval_mae": 1.1555440425872803, | |
| "eval_mse": 2.218869686126709, | |
| "eval_rmse": 1.4895870685577393, | |
| "eval_runtime": 2.8668, | |
| "eval_samples_per_second": 343.59, | |
| "eval_steps_per_second": 43.254, | |
| "step": 31616 | |
| }, | |
| { | |
| "epoch": 32.39, | |
| "learning_rate": 3.522267206477733e-06, | |
| "loss": 0.3432, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 32.89, | |
| "learning_rate": 3.421052631578948e-06, | |
| "loss": 0.3603, | |
| "step": 32500 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_loss": 2.2483489513397217, | |
| "eval_mae": 1.1578136682510376, | |
| "eval_mse": 2.2483489513397217, | |
| "eval_rmse": 1.4994494915008545, | |
| "eval_runtime": 2.7175, | |
| "eval_samples_per_second": 362.47, | |
| "eval_steps_per_second": 45.631, | |
| "step": 32604 | |
| }, | |
| { | |
| "epoch": 33.4, | |
| "learning_rate": 3.3198380566801623e-06, | |
| "loss": 0.3832, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 33.91, | |
| "learning_rate": 3.218623481781377e-06, | |
| "loss": 0.3955, | |
| "step": 33500 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_loss": 2.2034738063812256, | |
| "eval_mae": 1.148417353630066, | |
| "eval_mse": 2.2034738063812256, | |
| "eval_rmse": 1.484410285949707, | |
| "eval_runtime": 2.6975, | |
| "eval_samples_per_second": 365.15, | |
| "eval_steps_per_second": 45.968, | |
| "step": 33592 | |
| }, | |
| { | |
| "epoch": 34.41, | |
| "learning_rate": 3.1174089068825913e-06, | |
| "loss": 0.3517, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 34.92, | |
| "learning_rate": 3.0161943319838062e-06, | |
| "loss": 0.3802, | |
| "step": 34500 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_loss": 2.2388076782226562, | |
| "eval_mae": 1.1580203771591187, | |
| "eval_mse": 2.238807201385498, | |
| "eval_rmse": 1.4962644577026367, | |
| "eval_runtime": 2.781, | |
| "eval_samples_per_second": 354.184, | |
| "eval_steps_per_second": 44.588, | |
| "step": 34580 | |
| }, | |
| { | |
| "epoch": 35.43, | |
| "learning_rate": 2.9149797570850203e-06, | |
| "loss": 0.3543, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 35.93, | |
| "learning_rate": 2.8137651821862348e-06, | |
| "loss": 0.3818, | |
| "step": 35500 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_loss": 2.3153350353240967, | |
| "eval_mae": 1.178168773651123, | |
| "eval_mse": 2.3153350353240967, | |
| "eval_rmse": 1.5216225385665894, | |
| "eval_runtime": 2.7673, | |
| "eval_samples_per_second": 355.946, | |
| "eval_steps_per_second": 44.81, | |
| "step": 35568 | |
| }, | |
| { | |
| "epoch": 36.44, | |
| "learning_rate": 2.7125506072874497e-06, | |
| "loss": 0.3451, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 36.94, | |
| "learning_rate": 2.6113360323886646e-06, | |
| "loss": 0.3837, | |
| "step": 36500 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_loss": 2.2114505767822266, | |
| "eval_mae": 1.1500502824783325, | |
| "eval_mse": 2.2114510536193848, | |
| "eval_rmse": 1.4870948791503906, | |
| "eval_runtime": 4.6473, | |
| "eval_samples_per_second": 211.95, | |
| "eval_steps_per_second": 26.682, | |
| "step": 36556 | |
| }, | |
| { | |
| "epoch": 37.45, | |
| "learning_rate": 2.5101214574898787e-06, | |
| "loss": 0.3335, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 37.96, | |
| "learning_rate": 2.408906882591093e-06, | |
| "loss": 0.3724, | |
| "step": 37500 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_loss": 2.190290927886963, | |
| "eval_mae": 1.1481947898864746, | |
| "eval_mse": 2.190290689468384, | |
| "eval_rmse": 1.4799630641937256, | |
| "eval_runtime": 4.4593, | |
| "eval_samples_per_second": 220.888, | |
| "eval_steps_per_second": 27.807, | |
| "step": 37544 | |
| }, | |
| { | |
| "epoch": 38.46, | |
| "learning_rate": 2.307692307692308e-06, | |
| "loss": 0.3631, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 38.97, | |
| "learning_rate": 2.2064777327935226e-06, | |
| "loss": 0.3525, | |
| "step": 38500 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "eval_loss": 2.208022117614746, | |
| "eval_mae": 1.1508959531784058, | |
| "eval_mse": 2.208022117614746, | |
| "eval_rmse": 1.4859415292739868, | |
| "eval_runtime": 4.5419, | |
| "eval_samples_per_second": 216.868, | |
| "eval_steps_per_second": 27.301, | |
| "step": 38532 | |
| }, | |
| { | |
| "epoch": 39.47, | |
| "learning_rate": 2.105263157894737e-06, | |
| "loss": 0.3589, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 39.98, | |
| "learning_rate": 2.0040485829959516e-06, | |
| "loss": 0.3477, | |
| "step": 39500 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_loss": 2.2591028213500977, | |
| "eval_mae": 1.1669268608093262, | |
| "eval_mse": 2.2591030597686768, | |
| "eval_rmse": 1.5030312538146973, | |
| "eval_runtime": 4.628, | |
| "eval_samples_per_second": 212.837, | |
| "eval_steps_per_second": 26.794, | |
| "step": 39520 | |
| }, | |
| { | |
| "epoch": 40.49, | |
| "learning_rate": 1.902834008097166e-06, | |
| "loss": 0.3239, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 40.99, | |
| "learning_rate": 1.8016194331983807e-06, | |
| "loss": 0.3891, | |
| "step": 40500 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "eval_loss": 2.2003180980682373, | |
| "eval_mae": 1.1513614654541016, | |
| "eval_mse": 2.2003180980682373, | |
| "eval_rmse": 1.483346939086914, | |
| "eval_runtime": 4.722, | |
| "eval_samples_per_second": 208.597, | |
| "eval_steps_per_second": 26.26, | |
| "step": 40508 | |
| }, | |
| { | |
| "epoch": 41.5, | |
| "learning_rate": 1.7004048582995952e-06, | |
| "loss": 0.3474, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_loss": 2.2396390438079834, | |
| "eval_mae": 1.1607612371444702, | |
| "eval_mse": 2.2396390438079834, | |
| "eval_rmse": 1.4965423345565796, | |
| "eval_runtime": 4.5927, | |
| "eval_samples_per_second": 214.471, | |
| "eval_steps_per_second": 26.999, | |
| "step": 41496 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "learning_rate": 1.59919028340081e-06, | |
| "loss": 0.347, | |
| "step": 41500 | |
| }, | |
| { | |
| "epoch": 42.51, | |
| "learning_rate": 1.4979757085020244e-06, | |
| "loss": 0.3173, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "eval_loss": 2.2095425128936768, | |
| "eval_mae": 1.151437520980835, | |
| "eval_mse": 2.2095425128936768, | |
| "eval_rmse": 1.4864530563354492, | |
| "eval_runtime": 4.6099, | |
| "eval_samples_per_second": 213.67, | |
| "eval_steps_per_second": 26.899, | |
| "step": 42484 | |
| }, | |
| { | |
| "epoch": 43.02, | |
| "learning_rate": 1.3967611336032391e-06, | |
| "loss": 0.3691, | |
| "step": 42500 | |
| }, | |
| { | |
| "epoch": 43.52, | |
| "learning_rate": 1.2955465587044536e-06, | |
| "loss": 0.335, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_loss": 2.1894824504852295, | |
| "eval_mae": 1.146257758140564, | |
| "eval_mse": 2.1894824504852295, | |
| "eval_rmse": 1.4796899557113647, | |
| "eval_runtime": 4.6282, | |
| "eval_samples_per_second": 212.828, | |
| "eval_steps_per_second": 26.793, | |
| "step": 43472 | |
| }, | |
| { | |
| "epoch": 44.03, | |
| "learning_rate": 1.1943319838056681e-06, | |
| "loss": 0.3441, | |
| "step": 43500 | |
| }, | |
| { | |
| "epoch": 44.53, | |
| "learning_rate": 1.0931174089068828e-06, | |
| "loss": 0.3443, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "eval_loss": 2.2246272563934326, | |
| "eval_mae": 1.1584477424621582, | |
| "eval_mse": 2.2246272563934326, | |
| "eval_rmse": 1.491518497467041, | |
| "eval_runtime": 4.7245, | |
| "eval_samples_per_second": 208.487, | |
| "eval_steps_per_second": 26.246, | |
| "step": 44460 | |
| }, | |
| { | |
| "epoch": 45.04, | |
| "learning_rate": 9.919028340080973e-07, | |
| "loss": 0.3242, | |
| "step": 44500 | |
| }, | |
| { | |
| "epoch": 45.55, | |
| "learning_rate": 8.906882591093118e-07, | |
| "loss": 0.3604, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_loss": 2.2161009311676025, | |
| "eval_mae": 1.1535395383834839, | |
| "eval_mse": 2.2161009311676025, | |
| "eval_rmse": 1.4886574745178223, | |
| "eval_runtime": 4.6251, | |
| "eval_samples_per_second": 212.97, | |
| "eval_steps_per_second": 26.81, | |
| "step": 45448 | |
| }, | |
| { | |
| "epoch": 46.05, | |
| "learning_rate": 7.894736842105263e-07, | |
| "loss": 0.3321, | |
| "step": 45500 | |
| }, | |
| { | |
| "epoch": 46.56, | |
| "learning_rate": 6.882591093117409e-07, | |
| "loss": 0.3422, | |
| "step": 46000 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "eval_loss": 2.2106308937072754, | |
| "eval_mae": 1.1536109447479248, | |
| "eval_mse": 2.2106311321258545, | |
| "eval_rmse": 1.4868191480636597, | |
| "eval_runtime": 4.7086, | |
| "eval_samples_per_second": 209.193, | |
| "eval_steps_per_second": 26.335, | |
| "step": 46436 | |
| }, | |
| { | |
| "epoch": 47.06, | |
| "learning_rate": 5.870445344129555e-07, | |
| "loss": 0.3223, | |
| "step": 46500 | |
| }, | |
| { | |
| "epoch": 47.57, | |
| "learning_rate": 4.858299595141701e-07, | |
| "loss": 0.3253, | |
| "step": 47000 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_loss": 2.2084391117095947, | |
| "eval_mae": 1.1512514352798462, | |
| "eval_mse": 2.2084388732910156, | |
| "eval_rmse": 1.4860817193984985, | |
| "eval_runtime": 4.6784, | |
| "eval_samples_per_second": 210.541, | |
| "eval_steps_per_second": 26.505, | |
| "step": 47424 | |
| }, | |
| { | |
| "epoch": 48.08, | |
| "learning_rate": 3.846153846153847e-07, | |
| "loss": 0.3418, | |
| "step": 47500 | |
| }, | |
| { | |
| "epoch": 48.58, | |
| "learning_rate": 2.834008097165992e-07, | |
| "loss": 0.3309, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "eval_loss": 2.2103824615478516, | |
| "eval_mae": 1.1521849632263184, | |
| "eval_mse": 2.2103824615478516, | |
| "eval_rmse": 1.486735463142395, | |
| "eval_runtime": 3.2286, | |
| "eval_samples_per_second": 305.083, | |
| "eval_steps_per_second": 38.406, | |
| "step": 48412 | |
| }, | |
| { | |
| "epoch": 49.09, | |
| "learning_rate": 1.8218623481781377e-07, | |
| "loss": 0.3491, | |
| "step": 48500 | |
| }, | |
| { | |
| "epoch": 49.6, | |
| "learning_rate": 8.097165991902835e-08, | |
| "loss": 0.3148, | |
| "step": 49000 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_loss": 2.2166781425476074, | |
| "eval_mae": 1.1540616750717163, | |
| "eval_mse": 2.2166783809661865, | |
| "eval_rmse": 1.4888513088226318, | |
| "eval_runtime": 4.5752, | |
| "eval_samples_per_second": 215.291, | |
| "eval_steps_per_second": 27.103, | |
| "step": 49400 | |
| } | |
| ], | |
| "max_steps": 49400, | |
| "num_train_epochs": 50, | |
| "total_flos": 2.61545223472896e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |