esol.out

Some weights of the model checkpoint at data/saved_models/our_90epochs_saved_model were not used when initializing RobertaForSelfiesClassification: ['lm_head.layer_norm.bias', 'lm_head.dense.bias', 'lm_head.layer_norm.weight', 'lm_head.bias', 'lm_head.dense.weight']
- This IS expected if you are initializing RobertaForSelfiesClassification from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).
- This IS NOT expected if you are initializing RobertaForSelfiesClassification from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).
Some weights of RobertaForSelfiesClassification were not initialized from the model checkpoint at data/saved_models/our_90epochs_saved_model and are newly initialized: ['classifier.dense.weight', 'classifier.out_proj.weight', 'classifier.out_proj.bias', 'classifier.dense.bias', 'roberta.pooler.dense.weight', 'roberta.pooler.dense.bias']
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
Not using a scaler.
***** Running training *****
  Num examples = 711
  Num Epochs = 50
  Instantaneous batch size per device = 8
  Total train batch size (w. parallel, distributed & accumulation) = 8
  Gradient Accumulation steps = 1
  Total optimization steps = 4450
***** Running Evaluation *****
  Num examples = 69
  Batch size = 8
{'eval_loss': 1.7501213550567627, 'eval_mse': 1.750120997428894, 'eval_rmse': 1.3229213953018188, 'eval_mae': 1.0687230825424194, 'eval_runtime': 0.213, 'eval_samples_per_second': 323.879, 'eval_steps_per_second': 42.245, 'epoch': 1.0}
Saving model checkpoint to our_esol_model/checkpoint-89
Configuration saved in our_esol_model/checkpoint-89/config.json
Model weights saved in our_esol_model/checkpoint-89/pytorch_model.bin
***** Running Evaluation *****
  Num examples = 69
  Batch size = 8
{'eval_loss': 0.9408809542655945, 'eval_mse': 0.9408809542655945, 'eval_rmse': 0.9699901938438416, 'eval_mae': 0.7522120475769043, 'eval_runtime': 0.4675, 'eval_samples_per_second': 147.6, 'eval_steps_per_second': 19.252, 'epoch': 2.0}
Saving model checkpoint to our_esol_model/checkpoint-178
Configuration saved in our_esol_model/checkpoint-178/config.json
Model weights saved in our_esol_model/checkpoint-178/pytorch_model.bin
Deleting older checkpoint [our_esol_model/checkpoint-89] due to args.save_total_limit
***** Running Evaluation *****
  Num examples = 69
  Batch size = 8
{'eval_loss': 0.7912163138389587, 'eval_mse': 0.7912163734436035, 'eval_rmse': 0.8895034193992615, 'eval_mae': 0.7013395428657532, 'eval_runtime': 0.4829, 'eval_samples_per_second': 142.893, 'eval_steps_per_second': 18.638, 'epoch': 3.0}
Saving model checkpoint to our_esol_model/checkpoint-267
Configuration saved in our_esol_model/checkpoint-267/config.json
Model weights saved in our_esol_model/checkpoint-267/pytorch_model.bin
Deleting older checkpoint [our_esol_model/checkpoint-178] due to args.save_total_limit
***** Running Evaluation *****
  Num examples = 69
  Batch size = 8
{'eval_loss': 0.7405096292495728, 'eval_mse': 0.7405097484588623, 'eval_rmse': 0.8605287671089172, 'eval_mae': 0.6587470769882202, 'eval_runtime': 0.4491, 'eval_samples_per_second': 153.654, 'eval_steps_per_second': 20.042, 'epoch': 4.0}
Saving model checkpoint to our_esol_model/checkpoint-356
Configuration saved in our_esol_model/checkpoint-356/config.json
Model weights saved in our_esol_model/checkpoint-356/pytorch_model.bin
Deleting older checkpoint [our_esol_model/checkpoint-267] due to args.save_total_limit
***** Running Evaluation *****
  Num examples = 69
  Batch size = 8
{'eval_loss': 0.6923832297325134, 'eval_mse': 0.6923832893371582, 'eval_rmse': 0.832095742225647, 'eval_mae': 0.6610296964645386, 'eval_runtime': 0.4191, 'eval_samples_per_second': 164.64, 'eval_steps_per_second': 21.475, 'epoch': 5.0}
Saving model checkpoint to our_esol_model/checkpoint-445
Configuration saved in our_esol_model/checkpoint-445/config.json
Model weights saved in our_esol_model/checkpoint-445/pytorch_model.bin
Deleting older checkpoint [our_esol_model/checkpoint-356] due to args.save_total_limit
{'loss': 0.9104, 'learning_rate': 8.876404494382023e-06, 'epoch': 5.62}
***** Running Evaluation *****
  Num examples = 69
  Batch size = 8
{'eval_loss': 0.6709772944450378, 'eval_mse': 0.6709771752357483, 'eval_rmse': 0.8191319704055786, 'eval_mae': 0.6442688703536987, 'eval_runtime': 0.4743, 'eval_samples_per_second': 145.467, 'eval_steps_per_second': 18.974, 'epoch': 6.0}
Saving model checkpoint to our_esol_model/checkpoint-534
Configuration saved in our_esol_model/checkpoint-534/config.json
Model weights saved in our_esol_model/checkpoint-534/pytorch_model.bin
Deleting older checkpoint [our_esol_model/checkpoint-445] due to args.save_total_limit
***** Running Evaluation *****
  Num examples = 69
  Batch size = 8
{'eval_loss': 0.5820761322975159, 'eval_mse': 0.5820761919021606, 'eval_rmse': 0.7629391551017761, 'eval_mae': 0.6152850389480591, 'eval_runtime': 0.364, 'eval_samples_per_second': 189.553, 'eval_steps_per_second': 24.724, 'epoch': 7.0}
Saving model checkpoint to our_esol_model/checkpoint-623
Configuration saved in our_esol_model/checkpoint-623/config.json
Model weights saved in our_esol_model/checkpoint-623/pytorch_model.bin
Deleting older checkpoint [our_esol_model/checkpoint-534] due to args.save_total_limit
***** Running Evaluation *****
  Num examples = 69
  Batch size = 8
{'eval_loss': 0.49572908878326416, 'eval_mse': 0.49572914838790894, 'eval_rmse': 0.70408034324646, 'eval_mae': 0.5509689450263977, 'eval_runtime': 0.4466, 'eval_samples_per_second': 154.492, 'eval_steps_per_second': 20.151, 'epoch': 8.0}
Saving model checkpoint to our_esol_model/checkpoint-712
Configuration saved in our_esol_model/checkpoint-712/config.json
Model weights saved in our_esol_model/checkpoint-712/pytorch_model.bin
Deleting older checkpoint [our_esol_model/checkpoint-623] due to args.save_total_limit
***** Running Evaluation *****
  Num examples = 69
  Batch size = 8
{'eval_loss': 0.5924321413040161, 'eval_mse': 0.5924323201179504, 'eval_rmse': 0.7696962356567383, 'eval_mae': 0.6066040396690369, 'eval_runtime': 0.4645, 'eval_samples_per_second': 148.549, 'eval_steps_per_second': 19.376, 'epoch': 9.0}
Saving model checkpoint to our_esol_model/checkpoint-801
Configuration saved in our_esol_model/checkpoint-801/config.json
Model weights saved in our_esol_model/checkpoint-801/pytorch_model.bin
Deleting older checkpoint [our_esol_model/checkpoint-712] due to args.save_total_limit
***** Running Evaluation *****
  Num examples = 69
  Batch size = 8
{'eval_loss': 0.4954969882965088, 'eval_mse': 0.4954971671104431, 'eval_rmse': 0.7039155960083008, 'eval_mae': 0.5473751425743103, 'eval_runtime': 0.3698, 'eval_samples_per_second': 186.61, 'eval_steps_per_second': 24.34, 'epoch': 10.0}
Saving model checkpoint to our_esol_model/checkpoint-890
Configuration saved in our_esol_model/checkpoint-890/config.json
Model weights saved in our_esol_model/checkpoint-890/pytorch_model.bin
Deleting older checkpoint [our_esol_model/checkpoint-801] due to args.save_total_limit
***** Running Evaluation *****
  Num examples = 69
  Batch size = 8
{'eval_loss': 0.5200049877166748, 'eval_mse': 0.52000492811203, 'eval_rmse': 0.7211136817932129, 'eval_mae': 0.5685440897941589, 'eval_runtime': 0.4266, 'eval_samples_per_second': 161.746, 'eval_steps_per_second': 21.097, 'epoch': 11.0}
Saving model checkpoint to our_esol_model/checkpoint-979
Configuration saved in our_esol_model/checkpoint-979/config.json
Model weights saved in our_esol_model/checkpoint-979/pytorch_model.bin
Deleting older checkpoint [our_esol_model/checkpoint-890] due to args.save_total_limit
{'loss': 0.128, 'learning_rate': 7.752808988764046e-06, 'epoch': 11.24}
***** Running Evaluation *****
  Num examples = 69
  Batch size = 8
{'eval_loss': 0.43686971068382263, 'eval_mse': 0.436869740486145, 'eval_rmse': 0.6609612107276917, 'eval_mae': 0.5061944723129272, 'eval_runtime': 0.4821, 'eval_samples_per_second': 143.124, 'eval_steps_per_second': 18.668, 'epoch': 12.0}
Saving model checkpoint to our_esol_model/checkpoint-1068
Configuration saved in our_esol_model/checkpoint-1068/config.json
Model weights saved in our_esol_model/checkpoint-1068/pytorch_model.bin
Deleting older checkpoint [our_esol_model/checkpoint-979] due to args.save_total_limit
***** Running Evaluation *****
  Num examples = 69
  Batch size = 8
{'eval_loss': 0.41416943073272705, 'eval_mse': 0.41416940093040466, 'eval_rmse': 0.6435599327087402, 'eval_mae': 0.46771711111068726, 'eval_runtime': 0.4624, 'eval_samples_per_second': 149.23, 'eval_steps_per_second': 19.465, 'epoch': 13.0}
Saving model checkpoint to our_esol_model/checkpoint-1157
Configuration saved in our_esol_model/checkpoint-1157/config.json
Model weights saved in our_esol_model/checkpoint-1157/pytorch_model.bin
Deleting older checkpoint [our_esol_model/checkpoint-1068] due to args.save_total_limit
***** Running Evaluation *****
  Num examples = 69
  Batch size = 8
{'eval_loss': 0.40698668360710144, 'eval_mse': 0.4069867730140686, 'eval_rmse': 0.6379551291465759, 'eval_mae': 0.45521026849746704, 'eval_runtime': 0.4757, 'eval_samples_per_second': 145.044, 'eval_steps_per_second': 18.919, 'epoch': 14.0}
Saving model checkpoint to our_esol_model/checkpoint-1246
Configuration saved in our_esol_model/checkpoint-1246/config.json
Model weights saved in our_esol_model/checkpoint-1246/pytorch_model.bin
Deleting older checkpoint [our_esol_model/checkpoint-1157] due to args.save_total_limit
***** Running Evaluation *****
  Num examples = 69
  Batch size = 8
{'eval_loss': 0.49930572509765625, 'eval_mse': 0.4993056654930115, 'eval_rmse': 0.7066156268119812, 'eval_mae': 0.5383840799331665, 'eval_runtime': 0.4656, 'eval_samples_per_second': 148.181, 'eval_steps_per_second': 19.328, 'epoch': 15.0}
Saving model checkpoint to our_esol_model/checkpoint-1335
Configuration saved in our_esol_model/checkpoint-1335/config.json
Model weights saved in our_esol_model/checkpoint-1335/pytorch_model.bin
Deleting older checkpoint [our_esol_model/checkpoint-1246] due to args.save_total_limit
***** Running Evaluation *****
  Num examples = 69
  Batch size = 8
{'eval_loss': 0.5578888654708862, 'eval_mse': 0.5578888058662415, 'eval_rmse': 0.746919572353363, 'eval_mae': 0.585189163684845, 'eval_runtime': 0.4755, 'eval_samples_per_second': 145.098, 'eval_steps_per_second': 18.926, 'epoch': 16.0}
Saving model checkpoint to our_esol_model/checkpoint-1424
Configuration saved in our_esol_model/checkpoint-1424/config.json
Model weights saved in our_esol_model/checkpoint-1424/pytorch_model.bin
Deleting older checkpoint [our_esol_model/checkpoint-1335] due to args.save_total_limit
{'loss': 0.0895, 'learning_rate': 6.629213483146067e-06, 'epoch': 16.85}
***** Running Evaluation *****
  Num examples = 69
  Batch size = 8
{'eval_loss': 0.5015009045600891, 'eval_mse': 0.5015009641647339, 'eval_rmse': 0.708167314529419, 'eval_mae': 0.561897337436676, 'eval_runtime': 0.3883, 'eval_samples_per_second': 177.714, 'eval_steps_per_second': 23.18, 'epoch': 17.0}
Saving model checkpoint to our_esol_model/checkpoint-1513
Configuration saved in our_esol_model/checkpoint-1513/config.json
Model weights saved in our_esol_model/checkpoint-1513/pytorch_model.bin
Deleting older checkpoint [our_esol_model/checkpoint-1424] due to args.save_total_limit
***** Running Evaluation *****
  Num examples = 69
  Batch size = 8
{'eval_loss': 0.4590393602848053, 'eval_mse': 0.45903947949409485, 'eval_rmse': 0.6775245070457458, 'eval_mae': 0.5263462066650391, 'eval_runtime': 0.4835, 'eval_samples_per_second': 142.705, 'eval_steps_per_second': 18.614, 'epoch': 18.0}
Saving model checkpoint to our_esol_model/checkpoint-1602
Configuration saved in our_esol_model/checkpoint-1602/config.json
Model weights saved in our_esol_model/checkpoint-1602/pytorch_model.bin
Deleting older checkpoint [our_esol_model/checkpoint-1513] due to args.save_total_limit
***** Running Evaluation *****
  Num examples = 69
  Batch size = 8
{'eval_loss': 0.4880666434764862, 'eval_mse': 0.4880666732788086, 'eval_rmse': 0.698617696762085, 'eval_mae': 0.5377508997917175, 'eval_runtime': 0.4715, 'eval_samples_per_second': 146.34, 'eval_steps_per_second': 19.088, 'epoch': 19.0}
Saving model checkpoint to our_esol_model/checkpoint-1691
Configuration saved in our_esol_model/checkpoint-1691/config.json
Model weights saved in our_esol_model/checkpoint-1691/pytorch_model.bin
Deleting older checkpoint [our_esol_model/checkpoint-1602] due to args.save_total_limit
***** Running Evaluation *****
  Num examples = 69
  Batch size = 8
{'eval_loss': 0.3925124704837799, 'eval_mse': 0.3925124406814575, 'eval_rmse': 0.6265081167221069, 'eval_mae': 0.46625784039497375, 'eval_runtime': 0.3158, 'eval_samples_per_second': 218.521, 'eval_steps_per_second': 28.503, 'epoch': 20.0}
Saving model checkpoint to our_esol_model/checkpoint-1780
Configuration saved in our_esol_model/checkpoint-1780/config.json
Model weights saved in our_esol_model/checkpoint-1780/pytorch_model.bin
Deleting older checkpoint [our_esol_model/checkpoint-1691] due to args.save_total_limit
***** Running Evaluation *****
  Num examples = 69
  Batch size = 8
{'eval_loss': 0.4392476975917816, 'eval_mse': 0.4392476975917816, 'eval_rmse': 0.6627576351165771, 'eval_mae': 0.5062677264213562, 'eval_runtime': 0.4321, 'eval_samples_per_second': 159.696, 'eval_steps_per_second': 20.83, 'epoch': 21.0}
Saving model checkpoint to our_esol_model/checkpoint-1869
Configuration saved in our_esol_model/checkpoint-1869/config.json
Model weights saved in our_esol_model/checkpoint-1869/pytorch_model.bin
Deleting older checkpoint [our_esol_model/checkpoint-1780] due to args.save_total_limit
***** Running Evaluation *****
  Num examples = 69
  Batch size = 8
{'eval_loss': 0.42705094814300537, 'eval_mse': 0.42705097794532776, 'eval_rmse': 0.6534913778305054, 'eval_mae': 0.48886218667030334, 'eval_runtime': 0.3907, 'eval_samples_per_second': 176.595, 'eval_steps_per_second': 23.034, 'epoch': 22.0}
Saving model checkpoint to our_esol_model/checkpoint-1958
Configuration saved in our_esol_model/checkpoint-1958/config.json
Model weights saved in our_esol_model/checkpoint-1958/pytorch_model.bin
Deleting older checkpoint [our_esol_model/checkpoint-1869] due to args.save_total_limit
{'loss': 0.0694, 'learning_rate': 5.50561797752809e-06, 'epoch': 22.47}
***** Running Evaluation *****
  Num examples = 69
  Batch size = 8
{'eval_loss': 0.40933796763420105, 'eval_mse': 0.4093380868434906, 'eval_rmse': 0.6397953629493713, 'eval_mae': 0.4783601760864258, 'eval_runtime': 0.3371, 'eval_samples_per_second': 204.706, 'eval_steps_per_second': 26.701, 'epoch': 23.0}
Saving model checkpoint to our_esol_model/checkpoint-2047
Configuration saved in our_esol_model/checkpoint-2047/config.json
Model weights saved in our_esol_model/checkpoint-2047/pytorch_model.bin
Deleting older checkpoint [our_esol_model/checkpoint-1958] due to args.save_total_limit
***** Running Evaluation *****
  Num examples = 69
  Batch size = 8
{'eval_loss': 0.42077454924583435, 'eval_mse': 0.42077454924583435, 'eval_rmse': 0.6486713886260986, 'eval_mae': 0.49500545859336853, 'eval_runtime': 0.4775, 'eval_samples_per_second': 144.493, 'eval_steps_per_second': 18.847, 'epoch': 24.0}
Saving model checkpoint to our_esol_model/checkpoint-2136
Configuration saved in our_esol_model/checkpoint-2136/config.json
Model weights saved in our_esol_model/checkpoint-2136/pytorch_model.bin
Deleting older checkpoint [our_esol_model/checkpoint-2047] due to args.save_total_limit
***** Running Evaluation *****
  Num examples = 69
  Batch size = 8
{'eval_loss': 0.40650996565818787, 'eval_mse': 0.4065099358558655, 'eval_rmse': 0.6375812888145447, 'eval_mae': 0.4869938790798187, 'eval_runtime': 0.4751, 'eval_samples_per_second': 145.227, 'eval_steps_per_second': 18.943, 'epoch': 25.0}
Saving model checkpoint to our_esol_model/checkpoint-2225
Configuration saved in our_esol_model/checkpoint-2225/config.json
Model weights saved in our_esol_model/checkpoint-2225/pytorch_model.bin
Deleting older checkpoint [our_esol_model/checkpoint-2136] due to args.save_total_limit
***** Running Evaluation *****
  Num examples = 69
  Batch size = 8
{'eval_loss': 0.4467940032482147, 'eval_mse': 0.44679397344589233, 'eval_rmse': 0.668426513671875, 'eval_mae': 0.5186977386474609, 'eval_runtime': 0.4523, 'eval_samples_per_second': 152.552, 'eval_steps_per_second': 19.898, 'epoch': 26.0}
Saving model checkpoint to our_esol_model/checkpoint-2314
Configuration saved in our_esol_model/checkpoint-2314/config.json
Model weights saved in our_esol_model/checkpoint-2314/pytorch_model.bin
Deleting older checkpoint [our_esol_model/checkpoint-2225] due to args.save_total_limit
***** Running Evaluation *****
  Num examples = 69
  Batch size = 8
{'eval_loss': 0.448551744222641, 'eval_mse': 0.4485517740249634, 'eval_rmse': 0.6697400808334351, 'eval_mae': 0.5286442041397095, 'eval_runtime': 0.3607, 'eval_samples_per_second': 191.288, 'eval_steps_per_second': 24.951, 'epoch': 27.0}
Saving model checkpoint to our_esol_model/checkpoint-2403
Configuration saved in our_esol_model/checkpoint-2403/config.json
Model weights saved in our_esol_model/checkpoint-2403/pytorch_model.bin
Deleting older checkpoint [our_esol_model/checkpoint-2314] due to args.save_total_limit
***** Running Evaluation *****
  Num examples = 69
  Batch size = 8
{'eval_loss': 0.4263148605823517, 'eval_mse': 0.4263148009777069, 'eval_rmse': 0.6529278755187988, 'eval_mae': 0.5110523700714111, 'eval_runtime': 0.4741, 'eval_samples_per_second': 145.544, 'eval_steps_per_second': 18.984, 'epoch': 28.0}
Saving model checkpoint to our_esol_model/checkpoint-2492
Configuration saved in our_esol_model/checkpoint-2492/config.json
Model weights saved in our_esol_model/checkpoint-2492/pytorch_model.bin
Deleting older checkpoint [our_esol_model/checkpoint-2403] due to args.save_total_limit
{'loss': 0.0575, 'learning_rate': 4.382022471910113e-06, 'epoch': 28.09}
***** Running Evaluation *****
  Num examples = 69
  Batch size = 8
{'eval_loss': 0.4624464213848114, 'eval_mse': 0.462446391582489, 'eval_rmse': 0.6800341010093689, 'eval_mae': 0.5141972303390503, 'eval_runtime': 0.4737, 'eval_samples_per_second': 145.658, 'eval_steps_per_second': 18.999, 'epoch': 29.0}
Saving model checkpoint to our_esol_model/checkpoint-2581
Configuration saved in our_esol_model/checkpoint-2581/config.json
Model weights saved in our_esol_model/checkpoint-2581/pytorch_model.bin
Deleting older checkpoint [our_esol_model/checkpoint-2492] due to args.save_total_limit
***** Running Evaluation *****
  Num examples = 69
  Batch size = 8
{'eval_loss': 0.4065593481063843, 'eval_mse': 0.40655940771102905, 'eval_rmse': 0.6376200914382935, 'eval_mae': 0.4846087396144867, 'eval_runtime': 0.3326, 'eval_samples_per_second': 207.482, 'eval_steps_per_second': 27.063, 'epoch': 30.0}
Saving model checkpoint to our_esol_model/checkpoint-2670
Configuration saved in our_esol_model/checkpoint-2670/config.json
Model weights saved in our_esol_model/checkpoint-2670/pytorch_model.bin
Deleting older checkpoint [our_esol_model/checkpoint-2581] due to args.save_total_limit
***** Running Evaluation *****
  Num examples = 69
  Batch size = 8
{'eval_loss': 0.4373004138469696, 'eval_mse': 0.437300443649292, 'eval_rmse': 0.6612869501113892, 'eval_mae': 0.5060880780220032, 'eval_runtime': 0.4249, 'eval_samples_per_second': 162.393, 'eval_steps_per_second': 21.182, 'epoch': 31.0}
Saving model checkpoint to our_esol_model/checkpoint-2759
Configuration saved in our_esol_model/checkpoint-2759/config.json
Model weights saved in our_esol_model/checkpoint-2759/pytorch_model.bin
Deleting older checkpoint [our_esol_model/checkpoint-2670] due to args.save_total_limit
***** Running Evaluation *****
  Num examples = 69
  Batch size = 8
{'eval_loss': 0.44729650020599365, 'eval_mse': 0.44729653000831604, 'eval_rmse': 0.6688023209571838, 'eval_mae': 0.5081753134727478, 'eval_runtime': 0.4601, 'eval_samples_per_second': 149.977, 'eval_steps_per_second': 19.562, 'epoch': 32.0}
Saving model checkpoint to our_esol_model/checkpoint-2848
Configuration saved in our_esol_model/checkpoint-2848/config.json
Model weights saved in our_esol_model/checkpoint-2848/pytorch_model.bin
Deleting older checkpoint [our_esol_model/checkpoint-2759] due to args.save_total_limit
***** Running Evaluation *****
  Num examples = 69
  Batch size = 8
{'eval_loss': 0.43939414620399475, 'eval_mse': 0.43939417600631714, 'eval_rmse': 0.6628681421279907, 'eval_mae': 0.5079318881034851, 'eval_runtime': 0.4736, 'eval_samples_per_second': 145.702, 'eval_steps_per_second': 19.005, 'epoch': 33.0}
Saving model checkpoint to our_esol_model/checkpoint-2937
Configuration saved in our_esol_model/checkpoint-2937/config.json
Model weights saved in our_esol_model/checkpoint-2937/pytorch_model.bin
Deleting older checkpoint [our_esol_model/checkpoint-2848] due to args.save_total_limit
{'loss': 0.0532, 'learning_rate': 3.258426966292135e-06, 'epoch': 33.71}
***** Running Evaluation *****
  Num examples = 69
  Batch size = 8
{'eval_loss': 0.4430878460407257, 'eval_mse': 0.44308778643608093, 'eval_rmse': 0.6656484007835388, 'eval_mae': 0.5065318942070007, 'eval_runtime': 0.4788, 'eval_samples_per_second': 144.103, 'eval_steps_per_second': 18.796, 'epoch': 34.0}
Saving model checkpoint to our_esol_model/checkpoint-3026
Configuration saved in our_esol_model/checkpoint-3026/config.json
Model weights saved in our_esol_model/checkpoint-3026/pytorch_model.bin
Deleting older checkpoint [our_esol_model/checkpoint-2937] due to args.save_total_limit
***** Running Evaluation *****
  Num examples = 69
  Batch size = 8
{'eval_loss': 0.4311515688896179, 'eval_mse': 0.4311515688896179, 'eval_rmse': 0.6566213369369507, 'eval_mae': 0.5022226572036743, 'eval_runtime': 0.47, 'eval_samples_per_second': 146.806, 'eval_steps_per_second': 19.149, 'epoch': 35.0}
Saving model checkpoint to our_esol_model/checkpoint-3115
Configuration saved in our_esol_model/checkpoint-3115/config.json
Model weights saved in our_esol_model/checkpoint-3115/pytorch_model.bin
Deleting older checkpoint [our_esol_model/checkpoint-3026] due to args.save_total_limit
***** Running Evaluation *****
  Num examples = 69
  Batch size = 8
{'eval_loss': 0.42474353313446045, 'eval_mse': 0.42474350333213806, 'eval_rmse': 0.6517235040664673, 'eval_mae': 0.49367982149124146, 'eval_runtime': 0.4548, 'eval_samples_per_second': 151.706, 'eval_steps_per_second': 19.788, 'epoch': 36.0}
Saving model checkpoint to our_esol_model/checkpoint-3204
Configuration saved in our_esol_model/checkpoint-3204/config.json
Model weights saved in our_esol_model/checkpoint-3204/pytorch_model.bin
Deleting older checkpoint [our_esol_model/checkpoint-3115] due to args.save_total_limit
***** Running Evaluation *****
  Num examples = 69
  Batch size = 8
{'eval_loss': 0.4552953541278839, 'eval_mse': 0.45529526472091675, 'eval_rmse': 0.6747556924819946, 'eval_mae': 0.5187087655067444, 'eval_runtime': 0.329, 'eval_samples_per_second': 209.749, 'eval_steps_per_second': 27.359, 'epoch': 37.0}
Saving model checkpoint to our_esol_model/checkpoint-3293
Configuration saved in our_esol_model/checkpoint-3293/config.json
Model weights saved in our_esol_model/checkpoint-3293/pytorch_model.bin
Deleting older checkpoint [our_esol_model/checkpoint-3204] due to args.save_total_limit
***** Running Evaluation *****
  Num examples = 69
  Batch size = 8
{'eval_loss': 0.42223644256591797, 'eval_mse': 0.4222363829612732, 'eval_rmse': 0.6497972011566162, 'eval_mae': 0.4933069348335266, 'eval_runtime': 0.3523, 'eval_samples_per_second': 195.847, 'eval_steps_per_second': 25.545, 'epoch': 38.0}
Saving model checkpoint to our_esol_model/checkpoint-3382
Configuration saved in our_esol_model/checkpoint-3382/config.json
Model weights saved in our_esol_model/checkpoint-3382/pytorch_model.bin
Deleting older checkpoint [our_esol_model/checkpoint-3293] due to args.save_total_limit
***** Running Evaluation *****
  Num examples = 69
  Batch size = 8
{'eval_loss': 0.4451429545879364, 'eval_mse': 0.4451429843902588, 'eval_rmse': 0.6671903729438782, 'eval_mae': 0.5115242004394531, 'eval_runtime': 0.1851, 'eval_samples_per_second': 372.87, 'eval_steps_per_second': 48.635, 'epoch': 39.0}
Saving model checkpoint to our_esol_model/checkpoint-3471
Configuration saved in our_esol_model/checkpoint-3471/config.json
Model weights saved in our_esol_model/checkpoint-3471/pytorch_model.bin
Deleting older checkpoint [our_esol_model/checkpoint-3382] due to args.save_total_limit
{'loss': 0.0421, 'learning_rate': 2.1348314606741574e-06, 'epoch': 39.33}
***** Running Evaluation *****
  Num examples = 69
  Batch size = 8
{'eval_loss': 0.42086702585220337, 'eval_mse': 0.4208669662475586, 'eval_rmse': 0.6487426161766052, 'eval_mae': 0.49490445852279663, 'eval_runtime': 0.3399, 'eval_samples_per_second': 203.01, 'eval_steps_per_second': 26.48, 'epoch': 40.0}
Saving model checkpoint to our_esol_model/checkpoint-3560
Configuration saved in our_esol_model/checkpoint-3560/config.json
Model weights saved in our_esol_model/checkpoint-3560/pytorch_model.bin
Deleting older checkpoint [our_esol_model/checkpoint-3471] due to args.save_total_limit
***** Running Evaluation *****
  Num examples = 69
  Batch size = 8
{'eval_loss': 0.44048014283180237, 'eval_mse': 0.4404800832271576, 'eval_rmse': 0.6636867523193359, 'eval_mae': 0.5092083215713501, 'eval_runtime': 0.3606, 'eval_samples_per_second': 191.355, 'eval_steps_per_second': 24.959, 'epoch': 41.0}
Saving model checkpoint to our_esol_model/checkpoint-3649
Configuration saved in our_esol_model/checkpoint-3649/config.json
Model weights saved in our_esol_model/checkpoint-3649/pytorch_model.bin
Deleting older checkpoint [our_esol_model/checkpoint-3560] due to args.save_total_limit
***** Running Evaluation *****
  Num examples = 69
  Batch size = 8
{'eval_loss': 0.41600948572158813, 'eval_mse': 0.4160095453262329, 'eval_rmse': 0.6449880003929138, 'eval_mae': 0.49518799781799316, 'eval_runtime': 0.3412, 'eval_samples_per_second': 202.233, 'eval_steps_per_second': 26.378, 'epoch': 42.0}
Saving model checkpoint to our_esol_model/checkpoint-3738
Configuration saved in our_esol_model/checkpoint-3738/config.json
Model weights saved in our_esol_model/checkpoint-3738/pytorch_model.bin
Deleting older checkpoint [our_esol_model/checkpoint-3649] due to args.save_total_limit
***** Running Evaluation *****
  Num examples = 69
  Batch size = 8
{'eval_loss': 0.42693421244621277, 'eval_mse': 0.42693421244621277, 'eval_rmse': 0.6534020304679871, 'eval_mae': 0.5002013444900513, 'eval_runtime': 0.2082, 'eval_samples_per_second': 331.427, 'eval_steps_per_second': 43.23, 'epoch': 43.0}
Saving model checkpoint to our_esol_model/checkpoint-3827
Configuration saved in our_esol_model/checkpoint-3827/config.json
Model weights saved in our_esol_model/checkpoint-3827/pytorch_model.bin
Deleting older checkpoint [our_esol_model/checkpoint-3738] due to args.save_total_limit
***** Running Evaluation *****
  Num examples = 69
  Batch size = 8
{'eval_loss': 0.4115591049194336, 'eval_mse': 0.4115590751171112, 'eval_rmse': 0.6415287256240845, 'eval_mae': 0.491961270570755, 'eval_runtime': 0.3428, 'eval_samples_per_second': 201.27, 'eval_steps_per_second': 26.253, 'epoch': 44.0}
Saving model checkpoint to our_esol_model/checkpoint-3916
Configuration saved in our_esol_model/checkpoint-3916/config.json
Model weights saved in our_esol_model/checkpoint-3916/pytorch_model.bin
Deleting older checkpoint [our_esol_model/checkpoint-3827] due to args.save_total_limit
{'loss': 0.0419, 'learning_rate': 1.01123595505618e-06, 'epoch': 44.94}
***** Running Evaluation *****
  Num examples = 69
  Batch size = 8
{'eval_loss': 0.41869696974754333, 'eval_mse': 0.41869693994522095, 'eval_rmse': 0.6470679640769958, 'eval_mae': 0.500180721282959, 'eval_runtime': 0.3406, 'eval_samples_per_second': 202.605, 'eval_steps_per_second': 26.427, 'epoch': 45.0}
Saving model checkpoint to our_esol_model/checkpoint-4005
Configuration saved in our_esol_model/checkpoint-4005/config.json
Model weights saved in our_esol_model/checkpoint-4005/pytorch_model.bin
Deleting older checkpoint [our_esol_model/checkpoint-3916] due to args.save_total_limit
***** Running Evaluation *****
  Num examples = 69
  Batch size = 8
{'eval_loss': 0.4199928641319275, 'eval_mse': 0.41999292373657227, 'eval_rmse': 0.6480686068534851, 'eval_mae': 0.504236102104187, 'eval_runtime': 0.3427, 'eval_samples_per_second': 201.361, 'eval_steps_per_second': 26.264, 'epoch': 46.0}
Saving model checkpoint to our_esol_model/checkpoint-4094
Configuration saved in our_esol_model/checkpoint-4094/config.json
Model weights saved in our_esol_model/checkpoint-4094/pytorch_model.bin
Deleting older checkpoint [our_esol_model/checkpoint-4005] due to args.save_total_limit
***** Running Evaluation *****
  Num examples = 69
  Batch size = 8
{'eval_loss': 0.4173473119735718, 'eval_mse': 0.41734734177589417, 'eval_rmse': 0.6460242867469788, 'eval_mae': 0.49992823600769043, 'eval_runtime': 0.3094, 'eval_samples_per_second': 222.982, 'eval_steps_per_second': 29.085, 'epoch': 47.0}
Saving model checkpoint to our_esol_model/checkpoint-4183
Configuration saved in our_esol_model/checkpoint-4183/config.json
Model weights saved in our_esol_model/checkpoint-4183/pytorch_model.bin
Deleting older checkpoint [our_esol_model/checkpoint-4094] due to args.save_total_limit
***** Running Evaluation *****
  Num examples = 69
  Batch size = 8
{'eval_loss': 0.41815370321273804, 'eval_mse': 0.4181537628173828, 'eval_rmse': 0.646648108959198, 'eval_mae': 0.4995117783546448, 'eval_runtime': 0.3301, 'eval_samples_per_second': 209.019, 'eval_steps_per_second': 27.263, 'epoch': 48.0}
Saving model checkpoint to our_esol_model/checkpoint-4272
Configuration saved in our_esol_model/checkpoint-4272/config.json
Model weights saved in our_esol_model/checkpoint-4272/pytorch_model.bin
Deleting older checkpoint [our_esol_model/checkpoint-4183] due to args.save_total_limit
***** Running Evaluation *****
  Num examples = 69
  Batch size = 8
{'eval_loss': 0.41537874937057495, 'eval_mse': 0.41537871956825256, 'eval_rmse': 0.6444988250732422, 'eval_mae': 0.49763771891593933, 'eval_runtime': 0.3396, 'eval_samples_per_second': 203.201, 'eval_steps_per_second': 26.504, 'epoch': 49.0}
Saving model checkpoint to our_esol_model/checkpoint-4361
Configuration saved in our_esol_model/checkpoint-4361/config.json
Model weights saved in our_esol_model/checkpoint-4361/pytorch_model.bin
Deleting older checkpoint [our_esol_model/checkpoint-4272] due to args.save_total_limit
***** Running Evaluation *****
  Num examples = 69
  Batch size = 8
{'eval_loss': 0.41592642664909363, 'eval_mse': 0.4159264862537384, 'eval_rmse': 0.6449236273765564, 'eval_mae': 0.4979737401008606, 'eval_runtime': 0.3167, 'eval_samples_per_second': 217.87, 'eval_steps_per_second': 28.418, 'epoch': 50.0}
Saving model checkpoint to our_esol_model/checkpoint-4450
Configuration saved in our_esol_model/checkpoint-4450/config.json
Model weights saved in our_esol_model/checkpoint-4450/pytorch_model.bin
Deleting older checkpoint [our_esol_model/checkpoint-4361] due to args.save_total_limit


Training completed. Do not forget to share your model on huggingface.co/models =)


{'train_runtime': 842.012, 'train_samples_per_second': 42.22, 'train_steps_per_second': 5.285, 'train_loss': 0.1603796991069665, 'epoch': 50.0}
Metrics
TrainOutput(global_step=4450, training_loss=0.1603796991069665, metrics={'train_runtime': 842.012, 'train_samples_per_second': 42.22, 'train_steps_per_second': 5.285, 'train_loss': 0.1603796991069665, 'epoch': 50.0})
Saving model checkpoint to our_esol_model
Configuration saved in our_esol_model/config.json
Model weights saved in our_esol_model/pytorch_model.bin
***** Running Prediction *****
  Num examples = 84
  Batch size = 8

Mean Squared Error (MSE): 0.4865848875608107
Root Mean Square Error (RMSE): 0.6975563687336033
Mean Absolute Error (MAE): 0.5087872081718275