Some weights of the model checkpoint at data/saved_models/our_90epochs_saved_model were not used when initializing RobertaForSelfiesClassification: ['lm_head.bias', 'lm_head.dense.bias', 'lm_head.layer_norm.bias', 'lm_head.dense.weight', 'lm_head.layer_norm.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.out_proj.bias', 'roberta.pooler.dense.bias', 'classifier.dense.weight', 'classifier.out_proj.weight', 'roberta.pooler.dense.weight', 'classifier.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 = 3360
  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 = 21000
***** Running Evaluation *****
  Num examples = 420
  Batch size = 8
{'eval_loss': 0.7975520491600037, 'eval_mse': 0.7975521087646484, 'eval_rmse': 0.8930577039718628, 'eval_mae': 0.7266795039176941, 'eval_runtime': 2.2756, 'eval_samples_per_second': 184.568, 'eval_steps_per_second': 23.291, 'epoch': 1.0}
Saving model checkpoint to our_lipo_model/checkpoint-420
Configuration saved in our_lipo_model/checkpoint-420/config.json
Model weights saved in our_lipo_model/checkpoint-420/pytorch_model.bin
{'loss': 1.111, 'learning_rate': 9.761904761904762e-06, 'epoch': 1.19}
***** Running Evaluation *****
  Num examples = 420
  Batch size = 8
{'eval_loss': 0.609792947769165, 'eval_mse': 0.609792947769165, 'eval_rmse': 0.7808924317359924, 'eval_mae': 0.6158387660980225, 'eval_runtime': 1.9303, 'eval_samples_per_second': 217.582, 'eval_steps_per_second': 27.457, 'epoch': 2.0}
Saving model checkpoint to our_lipo_model/checkpoint-840
Configuration saved in our_lipo_model/checkpoint-840/config.json
Model weights saved in our_lipo_model/checkpoint-840/pytorch_model.bin
Deleting older checkpoint [our_lipo_model/checkpoint-420] due to args.save_total_limit
{'loss': 0.4808, 'learning_rate': 9.523809523809525e-06, 'epoch': 2.38}
***** Running Evaluation *****
  Num examples = 420
  Batch size = 8
{'eval_loss': 0.6106507182121277, 'eval_mse': 0.6106507778167725, 'eval_rmse': 0.7814414501190186, 'eval_mae': 0.5975062847137451, 'eval_runtime': 2.7602, 'eval_samples_per_second': 152.163, 'eval_steps_per_second': 19.202, 'epoch': 3.0}
Saving model checkpoint to our_lipo_model/checkpoint-1260
Configuration saved in our_lipo_model/checkpoint-1260/config.json
Model weights saved in our_lipo_model/checkpoint-1260/pytorch_model.bin
Deleting older checkpoint [our_lipo_model/checkpoint-840] due to args.save_total_limit
{'loss': 0.3196, 'learning_rate': 9.285714285714288e-06, 'epoch': 3.57}
***** Running Evaluation *****
  Num examples = 420
  Batch size = 8
{'eval_loss': 0.5748845338821411, 'eval_mse': 0.5748845934867859, 'eval_rmse': 0.7582114338874817, 'eval_mae': 0.584411084651947, 'eval_runtime': 1.9617, 'eval_samples_per_second': 214.099, 'eval_steps_per_second': 27.017, 'epoch': 4.0}
Saving model checkpoint to our_lipo_model/checkpoint-1680
Configuration saved in our_lipo_model/checkpoint-1680/config.json
Model weights saved in our_lipo_model/checkpoint-1680/pytorch_model.bin
Deleting older checkpoint [our_lipo_model/checkpoint-1260] due to args.save_total_limit
{'loss': 0.2357, 'learning_rate': 9.047619047619049e-06, 'epoch': 4.76}
***** Running Evaluation *****
  Num examples = 420
  Batch size = 8
{'eval_loss': 0.6165366172790527, 'eval_mse': 0.6165366172790527, 'eval_rmse': 0.785198450088501, 'eval_mae': 0.5906195640563965, 'eval_runtime': 2.7689, 'eval_samples_per_second': 151.687, 'eval_steps_per_second': 19.141, 'epoch': 5.0}
Saving model checkpoint to our_lipo_model/checkpoint-2100
Configuration saved in our_lipo_model/checkpoint-2100/config.json
Model weights saved in our_lipo_model/checkpoint-2100/pytorch_model.bin
Deleting older checkpoint [our_lipo_model/checkpoint-1680] due to args.save_total_limit
{'loss': 0.1909, 'learning_rate': 8.80952380952381e-06, 'epoch': 5.95}
***** Running Evaluation *****
  Num examples = 420
  Batch size = 8
{'eval_loss': 0.5579051375389099, 'eval_mse': 0.5579050779342651, 'eval_rmse': 0.7469304203987122, 'eval_mae': 0.5814845561981201, 'eval_runtime': 1.2975, 'eval_samples_per_second': 323.7, 'eval_steps_per_second': 40.848, 'epoch': 6.0}
Saving model checkpoint to our_lipo_model/checkpoint-2520
Configuration saved in our_lipo_model/checkpoint-2520/config.json
Model weights saved in our_lipo_model/checkpoint-2520/pytorch_model.bin
Deleting older checkpoint [our_lipo_model/checkpoint-2100] due to args.save_total_limit
***** Running Evaluation *****
  Num examples = 420
  Batch size = 8
{'eval_loss': 0.5374110341072083, 'eval_mse': 0.5374110341072083, 'eval_rmse': 0.7330832481384277, 'eval_mae': 0.5643972754478455, 'eval_runtime': 2.8385, 'eval_samples_per_second': 147.967, 'eval_steps_per_second': 18.672, 'epoch': 7.0}
Saving model checkpoint to our_lipo_model/checkpoint-2940
Configuration saved in our_lipo_model/checkpoint-2940/config.json
Model weights saved in our_lipo_model/checkpoint-2940/pytorch_model.bin
Deleting older checkpoint [our_lipo_model/checkpoint-2520] due to args.save_total_limit
{'loss': 0.157, 'learning_rate': 8.571428571428571e-06, 'epoch': 7.14}
***** Running Evaluation *****
  Num examples = 420
  Batch size = 8
{'eval_loss': 0.5414829850196838, 'eval_mse': 0.5414829254150391, 'eval_rmse': 0.735855221748352, 'eval_mae': 0.5653696060180664, 'eval_runtime': 2.0614, 'eval_samples_per_second': 203.747, 'eval_steps_per_second': 25.711, 'epoch': 8.0}
Saving model checkpoint to our_lipo_model/checkpoint-3360
Configuration saved in our_lipo_model/checkpoint-3360/config.json
Model weights saved in our_lipo_model/checkpoint-3360/pytorch_model.bin
Deleting older checkpoint [our_lipo_model/checkpoint-2940] due to args.save_total_limit
{'loss': 0.1334, 'learning_rate': 8.333333333333334e-06, 'epoch': 8.33}
***** Running Evaluation *****
  Num examples = 420
  Batch size = 8
{'eval_loss': 0.5609115958213806, 'eval_mse': 0.5609115362167358, 'eval_rmse': 0.7489402890205383, 'eval_mae': 0.5715270042419434, 'eval_runtime': 1.9712, 'eval_samples_per_second': 213.066, 'eval_steps_per_second': 26.887, 'epoch': 9.0}
Saving model checkpoint to our_lipo_model/checkpoint-3780
Configuration saved in our_lipo_model/checkpoint-3780/config.json
Model weights saved in our_lipo_model/checkpoint-3780/pytorch_model.bin
Deleting older checkpoint [our_lipo_model/checkpoint-3360] due to args.save_total_limit
{'loss': 0.1199, 'learning_rate': 8.095238095238097e-06, 'epoch': 9.52}
***** Running Evaluation *****
  Num examples = 420
  Batch size = 8
{'eval_loss': 0.5141286253929138, 'eval_mse': 0.5141286253929138, 'eval_rmse': 0.7170276045799255, 'eval_mae': 0.5450649261474609, 'eval_runtime': 1.9528, 'eval_samples_per_second': 215.081, 'eval_steps_per_second': 27.141, 'epoch': 10.0}
Saving model checkpoint to our_lipo_model/checkpoint-4200
Configuration saved in our_lipo_model/checkpoint-4200/config.json
Model weights saved in our_lipo_model/checkpoint-4200/pytorch_model.bin
Deleting older checkpoint [our_lipo_model/checkpoint-3780] due to args.save_total_limit
{'loss': 0.1112, 'learning_rate': 7.857142857142858e-06, 'epoch': 10.71}
***** Running Evaluation *****
  Num examples = 420
  Batch size = 8
{'eval_loss': 0.5070027112960815, 'eval_mse': 0.5070027112960815, 'eval_rmse': 0.7120411992073059, 'eval_mae': 0.5421043634414673, 'eval_runtime': 1.3515, 'eval_samples_per_second': 310.772, 'eval_steps_per_second': 39.216, 'epoch': 11.0}
Saving model checkpoint to our_lipo_model/checkpoint-4620
Configuration saved in our_lipo_model/checkpoint-4620/config.json
Model weights saved in our_lipo_model/checkpoint-4620/pytorch_model.bin
Deleting older checkpoint [our_lipo_model/checkpoint-4200] due to args.save_total_limit
{'loss': 0.0983, 'learning_rate': 7.61904761904762e-06, 'epoch': 11.9}
***** Running Evaluation *****
  Num examples = 420
  Batch size = 8
{'eval_loss': 0.5180405378341675, 'eval_mse': 0.5180405378341675, 'eval_rmse': 0.7197503447532654, 'eval_mae': 0.5500118732452393, 'eval_runtime': 1.2448, 'eval_samples_per_second': 337.399, 'eval_steps_per_second': 42.577, 'epoch': 12.0}
Saving model checkpoint to our_lipo_model/checkpoint-5040
Configuration saved in our_lipo_model/checkpoint-5040/config.json
Model weights saved in our_lipo_model/checkpoint-5040/pytorch_model.bin
Deleting older checkpoint [our_lipo_model/checkpoint-4620] due to args.save_total_limit
***** Running Evaluation *****
  Num examples = 420
  Batch size = 8
{'eval_loss': 0.5257736444473267, 'eval_mse': 0.5257736444473267, 'eval_rmse': 0.7251024842262268, 'eval_mae': 0.561431348323822, 'eval_runtime': 1.1775, 'eval_samples_per_second': 356.675, 'eval_steps_per_second': 45.009, 'epoch': 13.0}
Saving model checkpoint to our_lipo_model/checkpoint-5460
Configuration saved in our_lipo_model/checkpoint-5460/config.json
Model weights saved in our_lipo_model/checkpoint-5460/pytorch_model.bin
Deleting older checkpoint [our_lipo_model/checkpoint-5040] due to args.save_total_limit
{'loss': 0.0861, 'learning_rate': 7.380952380952382e-06, 'epoch': 13.1}
***** Running Evaluation *****
  Num examples = 420
  Batch size = 8
{'eval_loss': 0.5195261836051941, 'eval_mse': 0.5195261836051941, 'eval_rmse': 0.7207816243171692, 'eval_mae': 0.5508889555931091, 'eval_runtime': 1.2061, 'eval_samples_per_second': 348.216, 'eval_steps_per_second': 43.942, 'epoch': 14.0}
Saving model checkpoint to our_lipo_model/checkpoint-5880
Configuration saved in our_lipo_model/checkpoint-5880/config.json
Model weights saved in our_lipo_model/checkpoint-5880/pytorch_model.bin
Deleting older checkpoint [our_lipo_model/checkpoint-5460] due to args.save_total_limit
{'loss': 0.0833, 'learning_rate': 7.1428571428571436e-06, 'epoch': 14.29}
***** Running Evaluation *****
  Num examples = 420
  Batch size = 8
{'eval_loss': 0.5224341154098511, 'eval_mse': 0.5224341154098511, 'eval_rmse': 0.7227960228919983, 'eval_mae': 0.552178144454956, 'eval_runtime': 1.1671, 'eval_samples_per_second': 359.858, 'eval_steps_per_second': 45.411, 'epoch': 15.0}
Saving model checkpoint to our_lipo_model/checkpoint-6300
Configuration saved in our_lipo_model/checkpoint-6300/config.json
Model weights saved in our_lipo_model/checkpoint-6300/pytorch_model.bin
Deleting older checkpoint [our_lipo_model/checkpoint-5880] due to args.save_total_limit
{'loss': 0.0741, 'learning_rate': 6.9047619047619055e-06, 'epoch': 15.48}
***** Running Evaluation *****
  Num examples = 420
  Batch size = 8
{'eval_loss': 0.5121651291847229, 'eval_mse': 0.5121651291847229, 'eval_rmse': 0.715657114982605, 'eval_mae': 0.5470804572105408, 'eval_runtime': 1.1174, 'eval_samples_per_second': 375.865, 'eval_steps_per_second': 47.431, 'epoch': 16.0}
Saving model checkpoint to our_lipo_model/checkpoint-6720
Configuration saved in our_lipo_model/checkpoint-6720/config.json
Model weights saved in our_lipo_model/checkpoint-6720/pytorch_model.bin
Deleting older checkpoint [our_lipo_model/checkpoint-6300] due to args.save_total_limit
{'loss': 0.0744, 'learning_rate': 6.666666666666667e-06, 'epoch': 16.67}
***** Running Evaluation *****
  Num examples = 420
  Batch size = 8
{'eval_loss': 0.4920870065689087, 'eval_mse': 0.4920870065689087, 'eval_rmse': 0.7014891505241394, 'eval_mae': 0.5328148007392883, 'eval_runtime': 1.1494, 'eval_samples_per_second': 365.42, 'eval_steps_per_second': 46.112, 'epoch': 17.0}
Saving model checkpoint to our_lipo_model/checkpoint-7140
Configuration saved in our_lipo_model/checkpoint-7140/config.json
Model weights saved in our_lipo_model/checkpoint-7140/pytorch_model.bin
Deleting older checkpoint [our_lipo_model/checkpoint-6720] due to args.save_total_limit
{'loss': 0.0649, 'learning_rate': 6.4285714285714295e-06, 'epoch': 17.86}
***** Running Evaluation *****
  Num examples = 420
  Batch size = 8
{'eval_loss': 0.5028687119483948, 'eval_mse': 0.5028687119483948, 'eval_rmse': 0.7091323733329773, 'eval_mae': 0.5357252359390259, 'eval_runtime': 1.3327, 'eval_samples_per_second': 315.156, 'eval_steps_per_second': 39.77, 'epoch': 18.0}
Saving model checkpoint to our_lipo_model/checkpoint-7560
Configuration saved in our_lipo_model/checkpoint-7560/config.json
Model weights saved in our_lipo_model/checkpoint-7560/pytorch_model.bin
Deleting older checkpoint [our_lipo_model/checkpoint-7140] due to args.save_total_limit
***** Running Evaluation *****
  Num examples = 420
  Batch size = 8
{'eval_loss': 0.526236891746521, 'eval_mse': 0.526236891746521, 'eval_rmse': 0.7254218459129333, 'eval_mae': 0.5603699684143066, 'eval_runtime': 1.2696, 'eval_samples_per_second': 330.822, 'eval_steps_per_second': 41.747, 'epoch': 19.0}
Saving model checkpoint to our_lipo_model/checkpoint-7980
Configuration saved in our_lipo_model/checkpoint-7980/config.json
Model weights saved in our_lipo_model/checkpoint-7980/pytorch_model.bin
Deleting older checkpoint [our_lipo_model/checkpoint-7560] due to args.save_total_limit
{'loss': 0.0639, 'learning_rate': 6.1904761904761914e-06, 'epoch': 19.05}
***** Running Evaluation *****
  Num examples = 420
  Batch size = 8
{'eval_loss': 0.5124732851982117, 'eval_mse': 0.5124732851982117, 'eval_rmse': 0.7158724069595337, 'eval_mae': 0.5440532565116882, 'eval_runtime': 1.139, 'eval_samples_per_second': 368.742, 'eval_steps_per_second': 46.532, 'epoch': 20.0}
Saving model checkpoint to our_lipo_model/checkpoint-8400
Configuration saved in our_lipo_model/checkpoint-8400/config.json
Model weights saved in our_lipo_model/checkpoint-8400/pytorch_model.bin
Deleting older checkpoint [our_lipo_model/checkpoint-7980] due to args.save_total_limit
{'loss': 0.0609, 'learning_rate': 5.9523809523809525e-06, 'epoch': 20.24}
***** Running Evaluation *****
  Num examples = 420
  Batch size = 8
{'eval_loss': 0.4891616106033325, 'eval_mse': 0.48916158080101013, 'eval_rmse': 0.6994009017944336, 'eval_mae': 0.5339100956916809, 'eval_runtime': 1.0834, 'eval_samples_per_second': 387.673, 'eval_steps_per_second': 48.921, 'epoch': 21.0}
Saving model checkpoint to our_lipo_model/checkpoint-8820
Configuration saved in our_lipo_model/checkpoint-8820/config.json
Model weights saved in our_lipo_model/checkpoint-8820/pytorch_model.bin
Deleting older checkpoint [our_lipo_model/checkpoint-8400] due to args.save_total_limit
{'loss': 0.0547, 'learning_rate': 5.7142857142857145e-06, 'epoch': 21.43}
***** Running Evaluation *****
  Num examples = 420
  Batch size = 8
{'eval_loss': 0.4973764717578888, 'eval_mse': 0.4973764419555664, 'eval_rmse': 0.7052491903305054, 'eval_mae': 0.5337387919425964, 'eval_runtime': 1.1768, 'eval_samples_per_second': 356.886, 'eval_steps_per_second': 45.036, 'epoch': 22.0}
Saving model checkpoint to our_lipo_model/checkpoint-9240
Configuration saved in our_lipo_model/checkpoint-9240/config.json
Model weights saved in our_lipo_model/checkpoint-9240/pytorch_model.bin
Deleting older checkpoint [our_lipo_model/checkpoint-8820] due to args.save_total_limit
{'loss': 0.0528, 'learning_rate': 5.476190476190477e-06, 'epoch': 22.62}
***** Running Evaluation *****
  Num examples = 420
  Batch size = 8
{'eval_loss': 0.4779137670993805, 'eval_mse': 0.47791385650634766, 'eval_rmse': 0.6913131475448608, 'eval_mae': 0.5240978598594666, 'eval_runtime': 1.1884, 'eval_samples_per_second': 353.429, 'eval_steps_per_second': 44.599, 'epoch': 23.0}
Saving model checkpoint to our_lipo_model/checkpoint-9660
Configuration saved in our_lipo_model/checkpoint-9660/config.json
Model weights saved in our_lipo_model/checkpoint-9660/pytorch_model.bin
Deleting older checkpoint [our_lipo_model/checkpoint-9240] due to args.save_total_limit
{'loss': 0.0514, 'learning_rate': 5.2380952380952384e-06, 'epoch': 23.81}
***** Running Evaluation *****
  Num examples = 420
  Batch size = 8
{'eval_loss': 0.483572781085968, 'eval_mse': 0.48357275128364563, 'eval_rmse': 0.695393979549408, 'eval_mae': 0.5290801525115967, 'eval_runtime': 1.1926, 'eval_samples_per_second': 352.184, 'eval_steps_per_second': 44.442, 'epoch': 24.0}
Saving model checkpoint to our_lipo_model/checkpoint-10080
Configuration saved in our_lipo_model/checkpoint-10080/config.json
Model weights saved in our_lipo_model/checkpoint-10080/pytorch_model.bin
Deleting older checkpoint [our_lipo_model/checkpoint-9660] due to args.save_total_limit
{'loss': 0.0516, 'learning_rate': 5e-06, 'epoch': 25.0}
***** Running Evaluation *****
  Num examples = 420
  Batch size = 8
{'eval_loss': 0.4979321360588074, 'eval_mse': 0.49793222546577454, 'eval_rmse': 0.7056431174278259, 'eval_mae': 0.5313663482666016, 'eval_runtime': 1.1676, 'eval_samples_per_second': 359.71, 'eval_steps_per_second': 45.392, 'epoch': 25.0}
Saving model checkpoint to our_lipo_model/checkpoint-10500
Configuration saved in our_lipo_model/checkpoint-10500/config.json
Model weights saved in our_lipo_model/checkpoint-10500/pytorch_model.bin
Deleting older checkpoint [our_lipo_model/checkpoint-10080] due to args.save_total_limit
***** Running Evaluation *****
  Num examples = 420
  Batch size = 8
{'eval_loss': 0.48045653104782104, 'eval_mse': 0.48045653104782104, 'eval_rmse': 0.693149745464325, 'eval_mae': 0.530644416809082, 'eval_runtime': 1.1924, 'eval_samples_per_second': 352.222, 'eval_steps_per_second': 44.447, 'epoch': 26.0}
Saving model checkpoint to our_lipo_model/checkpoint-10920
Configuration saved in our_lipo_model/checkpoint-10920/config.json
Model weights saved in our_lipo_model/checkpoint-10920/pytorch_model.bin
Deleting older checkpoint [our_lipo_model/checkpoint-10500] due to args.save_total_limit
{'loss': 0.0463, 'learning_rate': 4.761904761904762e-06, 'epoch': 26.19}
***** Running Evaluation *****
  Num examples = 420
  Batch size = 8
{'eval_loss': 0.48534154891967773, 'eval_mse': 0.48534154891967773, 'eval_rmse': 0.696664571762085, 'eval_mae': 0.5263835191726685, 'eval_runtime': 1.1385, 'eval_samples_per_second': 368.9, 'eval_steps_per_second': 46.552, 'epoch': 27.0}
Saving model checkpoint to our_lipo_model/checkpoint-11340
Configuration saved in our_lipo_model/checkpoint-11340/config.json
Model weights saved in our_lipo_model/checkpoint-11340/pytorch_model.bin
Deleting older checkpoint [our_lipo_model/checkpoint-10920] due to args.save_total_limit
{'loss': 0.0451, 'learning_rate': 4.523809523809524e-06, 'epoch': 27.38}
***** Running Evaluation *****
  Num examples = 420
  Batch size = 8
{'eval_loss': 0.4952319264411926, 'eval_mse': 0.4952319264411926, 'eval_rmse': 0.7037271857261658, 'eval_mae': 0.5382465720176697, 'eval_runtime': 1.1142, 'eval_samples_per_second': 376.951, 'eval_steps_per_second': 47.568, 'epoch': 28.0}
Saving model checkpoint to our_lipo_model/checkpoint-11760
Configuration saved in our_lipo_model/checkpoint-11760/config.json
Model weights saved in our_lipo_model/checkpoint-11760/pytorch_model.bin
Deleting older checkpoint [our_lipo_model/checkpoint-11340] due to args.save_total_limit
{'loss': 0.0428, 'learning_rate': 4.2857142857142855e-06, 'epoch': 28.57}
***** Running Evaluation *****
  Num examples = 420
  Batch size = 8
{'eval_loss': 0.48455557227134705, 'eval_mse': 0.48455557227134705, 'eval_rmse': 0.6961002349853516, 'eval_mae': 0.529035210609436, 'eval_runtime': 1.1847, 'eval_samples_per_second': 354.512, 'eval_steps_per_second': 44.736, 'epoch': 29.0}
Saving model checkpoint to our_lipo_model/checkpoint-12180
Configuration saved in our_lipo_model/checkpoint-12180/config.json
Model weights saved in our_lipo_model/checkpoint-12180/pytorch_model.bin
Deleting older checkpoint [our_lipo_model/checkpoint-11760] due to args.save_total_limit
{'loss': 0.0417, 'learning_rate': 4.047619047619048e-06, 'epoch': 29.76}
***** Running Evaluation *****
  Num examples = 420
  Batch size = 8
{'eval_loss': 0.4880525767803192, 'eval_mse': 0.4880525767803192, 'eval_rmse': 0.6986076235771179, 'eval_mae': 0.5353544354438782, 'eval_runtime': 1.2654, 'eval_samples_per_second': 331.922, 'eval_steps_per_second': 41.885, 'epoch': 30.0}
Saving model checkpoint to our_lipo_model/checkpoint-12600
Configuration saved in our_lipo_model/checkpoint-12600/config.json
Model weights saved in our_lipo_model/checkpoint-12600/pytorch_model.bin
Deleting older checkpoint [our_lipo_model/checkpoint-12180] due to args.save_total_limit
{'loss': 0.0404, 'learning_rate': 3.80952380952381e-06, 'epoch': 30.95}
***** Running Evaluation *****
  Num examples = 420
  Batch size = 8
{'eval_loss': 0.48999953269958496, 'eval_mse': 0.4899995028972626, 'eval_rmse': 0.6999996304512024, 'eval_mae': 0.5326849222183228, 'eval_runtime': 1.2442, 'eval_samples_per_second': 337.554, 'eval_steps_per_second': 42.596, 'epoch': 31.0}
Saving model checkpoint to our_lipo_model/checkpoint-13020
Configuration saved in our_lipo_model/checkpoint-13020/config.json
Model weights saved in our_lipo_model/checkpoint-13020/pytorch_model.bin
Deleting older checkpoint [our_lipo_model/checkpoint-12600] due to args.save_total_limit
***** Running Evaluation *****
  Num examples = 420
  Batch size = 8
{'eval_loss': 0.5017576813697815, 'eval_mse': 0.5017576813697815, 'eval_rmse': 0.7083485722541809, 'eval_mae': 0.5423673987388611, 'eval_runtime': 1.1196, 'eval_samples_per_second': 375.135, 'eval_steps_per_second': 47.339, 'epoch': 32.0}
Saving model checkpoint to our_lipo_model/checkpoint-13440
Configuration saved in our_lipo_model/checkpoint-13440/config.json
Model weights saved in our_lipo_model/checkpoint-13440/pytorch_model.bin
Deleting older checkpoint [our_lipo_model/checkpoint-13020] due to args.save_total_limit
{'loss': 0.0391, 'learning_rate': 3.5714285714285718e-06, 'epoch': 32.14}
***** Running Evaluation *****
  Num examples = 420
  Batch size = 8
{'eval_loss': 0.48715752363204956, 'eval_mse': 0.48715752363204956, 'eval_rmse': 0.6979666948318481, 'eval_mae': 0.5341249108314514, 'eval_runtime': 1.1228, 'eval_samples_per_second': 374.062, 'eval_steps_per_second': 47.203, 'epoch': 33.0}
Saving model checkpoint to our_lipo_model/checkpoint-13860
Configuration saved in our_lipo_model/checkpoint-13860/config.json
Model weights saved in our_lipo_model/checkpoint-13860/pytorch_model.bin
Deleting older checkpoint [our_lipo_model/checkpoint-13440] due to args.save_total_limit
{'loss': 0.0373, 'learning_rate': 3.3333333333333333e-06, 'epoch': 33.33}
***** Running Evaluation *****
  Num examples = 420
  Batch size = 8
{'eval_loss': 0.479116827249527, 'eval_mse': 0.479116827249527, 'eval_rmse': 0.6921826601028442, 'eval_mae': 0.5321008563041687, 'eval_runtime': 1.206, 'eval_samples_per_second': 348.254, 'eval_steps_per_second': 43.946, 'epoch': 34.0}
Saving model checkpoint to our_lipo_model/checkpoint-14280
Configuration saved in our_lipo_model/checkpoint-14280/config.json
Model weights saved in our_lipo_model/checkpoint-14280/pytorch_model.bin
Deleting older checkpoint [our_lipo_model/checkpoint-13860] due to args.save_total_limit
{'loss': 0.0359, 'learning_rate': 3.0952380952380957e-06, 'epoch': 34.52}
***** Running Evaluation *****
  Num examples = 420
  Batch size = 8
{'eval_loss': 0.48590707778930664, 'eval_mse': 0.48590704798698425, 'eval_rmse': 0.6970703601837158, 'eval_mae': 0.5346122980117798, 'eval_runtime': 0.8892, 'eval_samples_per_second': 472.339, 'eval_steps_per_second': 59.605, 'epoch': 35.0}
Saving model checkpoint to our_lipo_model/checkpoint-14700
Configuration saved in our_lipo_model/checkpoint-14700/config.json
Model weights saved in our_lipo_model/checkpoint-14700/pytorch_model.bin
Deleting older checkpoint [our_lipo_model/checkpoint-14280] due to args.save_total_limit
{'loss': 0.0334, 'learning_rate': 2.8571428571428573e-06, 'epoch': 35.71}
***** Running Evaluation *****
  Num examples = 420
  Batch size = 8
{'eval_loss': 0.4766678810119629, 'eval_mse': 0.4766678810119629, 'eval_rmse': 0.690411388874054, 'eval_mae': 0.5263535380363464, 'eval_runtime': 1.286, 'eval_samples_per_second': 326.603, 'eval_steps_per_second': 41.214, 'epoch': 36.0}
Saving model checkpoint to our_lipo_model/checkpoint-15120
Configuration saved in our_lipo_model/checkpoint-15120/config.json
Model weights saved in our_lipo_model/checkpoint-15120/pytorch_model.bin
Deleting older checkpoint [our_lipo_model/checkpoint-14700] due to args.save_total_limit
{'loss': 0.0341, 'learning_rate': 2.6190476190476192e-06, 'epoch': 36.9}
***** Running Evaluation *****
  Num examples = 420
  Batch size = 8
{'eval_loss': 0.4740683436393738, 'eval_mse': 0.4740683138370514, 'eval_rmse': 0.6885262131690979, 'eval_mae': 0.5217899680137634, 'eval_runtime': 1.1893, 'eval_samples_per_second': 353.162, 'eval_steps_per_second': 44.566, 'epoch': 37.0}
Saving model checkpoint to our_lipo_model/checkpoint-15540
Configuration saved in our_lipo_model/checkpoint-15540/config.json
Model weights saved in our_lipo_model/checkpoint-15540/pytorch_model.bin
Deleting older checkpoint [our_lipo_model/checkpoint-15120] due to args.save_total_limit
***** Running Evaluation *****
  Num examples = 420
  Batch size = 8
{'eval_loss': 0.478584349155426, 'eval_mse': 0.478584349155426, 'eval_rmse': 0.6917979121208191, 'eval_mae': 0.527285635471344, 'eval_runtime': 1.1477, 'eval_samples_per_second': 365.939, 'eval_steps_per_second': 46.178, 'epoch': 38.0}
Saving model checkpoint to our_lipo_model/checkpoint-15960
Configuration saved in our_lipo_model/checkpoint-15960/config.json
Model weights saved in our_lipo_model/checkpoint-15960/pytorch_model.bin
Deleting older checkpoint [our_lipo_model/checkpoint-15540] due to args.save_total_limit
{'loss': 0.0325, 'learning_rate': 2.380952380952381e-06, 'epoch': 38.1}
***** Running Evaluation *****
  Num examples = 420
  Batch size = 8
{'eval_loss': 0.46834418177604675, 'eval_mse': 0.46834418177604675, 'eval_rmse': 0.6843567490577698, 'eval_mae': 0.5196450352668762, 'eval_runtime': 1.1282, 'eval_samples_per_second': 372.276, 'eval_steps_per_second': 46.978, 'epoch': 39.0}
Saving model checkpoint to our_lipo_model/checkpoint-16380
Configuration saved in our_lipo_model/checkpoint-16380/config.json
Model weights saved in our_lipo_model/checkpoint-16380/pytorch_model.bin
Deleting older checkpoint [our_lipo_model/checkpoint-15960] due to args.save_total_limit
{'loss': 0.0331, 'learning_rate': 2.1428571428571427e-06, 'epoch': 39.29}
***** Running Evaluation *****
  Num examples = 420
  Batch size = 8
{'eval_loss': 0.46904683113098145, 'eval_mse': 0.46904683113098145, 'eval_rmse': 0.6848699450492859, 'eval_mae': 0.522687554359436, 'eval_runtime': 1.1578, 'eval_samples_per_second': 362.764, 'eval_steps_per_second': 45.777, 'epoch': 40.0}
Saving model checkpoint to our_lipo_model/checkpoint-16800
Configuration saved in our_lipo_model/checkpoint-16800/config.json
Model weights saved in our_lipo_model/checkpoint-16800/pytorch_model.bin
Deleting older checkpoint [our_lipo_model/checkpoint-16380] due to args.save_total_limit
{'loss': 0.0315, 'learning_rate': 1.904761904761905e-06, 'epoch': 40.48}
***** Running Evaluation *****
  Num examples = 420
  Batch size = 8
{'eval_loss': 0.46947211027145386, 'eval_mse': 0.46947211027145386, 'eval_rmse': 0.6851803660392761, 'eval_mae': 0.5197708010673523, 'eval_runtime': 1.1711, 'eval_samples_per_second': 358.64, 'eval_steps_per_second': 45.257, 'epoch': 41.0}
Saving model checkpoint to our_lipo_model/checkpoint-17220
Configuration saved in our_lipo_model/checkpoint-17220/config.json
Model weights saved in our_lipo_model/checkpoint-17220/pytorch_model.bin
Deleting older checkpoint [our_lipo_model/checkpoint-16800] due to args.save_total_limit
{'loss': 0.0299, 'learning_rate': 1.6666666666666667e-06, 'epoch': 41.67}
***** Running Evaluation *****
  Num examples = 420
  Batch size = 8
{'eval_loss': 0.46514230966567993, 'eval_mse': 0.46514227986335754, 'eval_rmse': 0.6820133924484253, 'eval_mae': 0.518059253692627, 'eval_runtime': 1.1482, 'eval_samples_per_second': 365.797, 'eval_steps_per_second': 46.16, 'epoch': 42.0}
Saving model checkpoint to our_lipo_model/checkpoint-17640
Configuration saved in our_lipo_model/checkpoint-17640/config.json
Model weights saved in our_lipo_model/checkpoint-17640/pytorch_model.bin
Deleting older checkpoint [our_lipo_model/checkpoint-17220] due to args.save_total_limit
{'loss': 0.0314, 'learning_rate': 1.4285714285714286e-06, 'epoch': 42.86}
***** Running Evaluation *****
  Num examples = 420
  Batch size = 8
{'eval_loss': 0.4640100300312042, 'eval_mse': 0.46400997042655945, 'eval_rmse': 0.6811828017234802, 'eval_mae': 0.51801997423172, 'eval_runtime': 1.1908, 'eval_samples_per_second': 352.696, 'eval_steps_per_second': 44.507, 'epoch': 43.0}
Saving model checkpoint to our_lipo_model/checkpoint-18060
Configuration saved in our_lipo_model/checkpoint-18060/config.json
Model weights saved in our_lipo_model/checkpoint-18060/pytorch_model.bin
Deleting older checkpoint [our_lipo_model/checkpoint-17640] due to args.save_total_limit
***** Running Evaluation *****
  Num examples = 420
  Batch size = 8
{'eval_loss': 0.4704785943031311, 'eval_mse': 0.4704785943031311, 'eval_rmse': 0.6859143972396851, 'eval_mae': 0.5230998992919922, 'eval_runtime': 1.2463, 'eval_samples_per_second': 337.011, 'eval_steps_per_second': 42.528, 'epoch': 44.0}
Saving model checkpoint to our_lipo_model/checkpoint-18480
Configuration saved in our_lipo_model/checkpoint-18480/config.json
Model weights saved in our_lipo_model/checkpoint-18480/pytorch_model.bin
Deleting older checkpoint [our_lipo_model/checkpoint-18060] due to args.save_total_limit
{'loss': 0.0283, 'learning_rate': 1.1904761904761906e-06, 'epoch': 44.05}
***** Running Evaluation *****
  Num examples = 420
  Batch size = 8
{'eval_loss': 0.4678580164909363, 'eval_mse': 0.46785807609558105, 'eval_rmse': 0.6840015053749084, 'eval_mae': 0.521861732006073, 'eval_runtime': 1.2433, 'eval_samples_per_second': 337.812, 'eval_steps_per_second': 42.629, 'epoch': 45.0}
Saving model checkpoint to our_lipo_model/checkpoint-18900
Configuration saved in our_lipo_model/checkpoint-18900/config.json
Model weights saved in our_lipo_model/checkpoint-18900/pytorch_model.bin
Deleting older checkpoint [our_lipo_model/checkpoint-18480] due to args.save_total_limit
{'loss': 0.0284, 'learning_rate': 9.523809523809525e-07, 'epoch': 45.24}
***** Running Evaluation *****
  Num examples = 420
  Batch size = 8
{'eval_loss': 0.4686986207962036, 'eval_mse': 0.4686986207962036, 'eval_rmse': 0.6846156716346741, 'eval_mae': 0.5229542851448059, 'eval_runtime': 1.1892, 'eval_samples_per_second': 353.193, 'eval_steps_per_second': 44.57, 'epoch': 46.0}
Saving model checkpoint to our_lipo_model/checkpoint-19320
Configuration saved in our_lipo_model/checkpoint-19320/config.json
Model weights saved in our_lipo_model/checkpoint-19320/pytorch_model.bin
Deleting older checkpoint [our_lipo_model/checkpoint-18900] due to args.save_total_limit
{'loss': 0.0273, 'learning_rate': 7.142857142857143e-07, 'epoch': 46.43}
***** Running Evaluation *****
  Num examples = 420
  Batch size = 8
{'eval_loss': 0.46382173895835876, 'eval_mse': 0.4638217091560364, 'eval_rmse': 0.6810445785522461, 'eval_mae': 0.5197833776473999, 'eval_runtime': 1.2872, 'eval_samples_per_second': 326.279, 'eval_steps_per_second': 41.173, 'epoch': 47.0}
Saving model checkpoint to our_lipo_model/checkpoint-19740
Configuration saved in our_lipo_model/checkpoint-19740/config.json
Model weights saved in our_lipo_model/checkpoint-19740/pytorch_model.bin
Deleting older checkpoint [our_lipo_model/checkpoint-19320] due to args.save_total_limit
{'loss': 0.0283, 'learning_rate': 4.7619047619047623e-07, 'epoch': 47.62}
***** Running Evaluation *****
  Num examples = 420
  Batch size = 8
{'eval_loss': 0.4631454348564148, 'eval_mse': 0.4631454348564148, 'eval_rmse': 0.6805478930473328, 'eval_mae': 0.5184262990951538, 'eval_runtime': 1.1721, 'eval_samples_per_second': 358.345, 'eval_steps_per_second': 45.22, 'epoch': 48.0}
Saving model checkpoint to our_lipo_model/checkpoint-20160
Configuration saved in our_lipo_model/checkpoint-20160/config.json
Model weights saved in our_lipo_model/checkpoint-20160/pytorch_model.bin
Deleting older checkpoint [our_lipo_model/checkpoint-19740] due to args.save_total_limit
{'loss': 0.0268, 'learning_rate': 2.3809523809523811e-07, 'epoch': 48.81}
***** Running Evaluation *****
  Num examples = 420
  Batch size = 8
{'eval_loss': 0.4649342894554138, 'eval_mse': 0.4649342894554138, 'eval_rmse': 0.6818609237670898, 'eval_mae': 0.5196540355682373, 'eval_runtime': 1.1402, 'eval_samples_per_second': 368.356, 'eval_steps_per_second': 46.483, 'epoch': 49.0}
Saving model checkpoint to our_lipo_model/checkpoint-20580
Configuration saved in our_lipo_model/checkpoint-20580/config.json
Model weights saved in our_lipo_model/checkpoint-20580/pytorch_model.bin
Deleting older checkpoint [our_lipo_model/checkpoint-20160] due to args.save_total_limit
{'loss': 0.0269, 'learning_rate': 0.0, 'epoch': 50.0}
***** Running Evaluation *****
  Num examples = 420
  Batch size = 8
{'eval_loss': 0.46444272994995117, 'eval_mse': 0.46444275975227356, 'eval_rmse': 0.6815003752708435, 'eval_mae': 0.5188572406768799, 'eval_runtime': 1.0966, 'eval_samples_per_second': 382.987, 'eval_steps_per_second': 48.329, 'epoch': 50.0}
Saving model checkpoint to our_lipo_model/checkpoint-21000
Configuration saved in our_lipo_model/checkpoint-21000/config.json
Model weights saved in our_lipo_model/checkpoint-21000/pytorch_model.bin
Deleting older checkpoint [our_lipo_model/checkpoint-20580] due to args.save_total_limit


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


{'train_runtime': 2521.2916, 'train_samples_per_second': 66.633, 'train_steps_per_second': 8.329, 'train_loss': 0.10468049140203567, 'epoch': 50.0}
Metrics
TrainOutput(global_step=21000, training_loss=0.10468049140203567, metrics={'train_runtime': 2521.2916, 'train_samples_per_second': 66.633, 'train_steps_per_second': 8.329, 'train_loss': 0.10468049140203567, 'epoch': 50.0})
Saving model checkpoint to our_lipo_model
Configuration saved in our_lipo_model/config.json
Model weights saved in our_lipo_model/pytorch_model.bin
***** Running Prediction *****
  Num examples = 420
  Batch size = 8

Mean Squared Error (MSE): 0.5401966615179934
Root Mean Square Error (RMSE): 0.7349807218682632
Mean Absolute Error (MAE): 0.5634666012316232