Some weights of the model checkpoint at data/saved_models/our_90epochs_saved_model were not used when initializing RobertaForSelfiesClassification: ['lm_head.dense.weight', 'lm_head.layer_norm.weight', 'lm_head.layer_norm.bias', 'lm_head.bias', 'lm_head.dense.bias'] - 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.dense.bias', 'classifier.out_proj.weight', 'classifier.out_proj.bias', 'roberta.pooler.dense.bias', 'roberta.pooler.dense.weight'] 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 = 511 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 = 3200 ***** Running Evaluation ***** Num examples = 64 Batch size = 8 {'eval_loss': 30.29538917541504, 'eval_mse': 30.29538917541504, 'eval_rmse': 5.504124641418457, 'eval_mae': 3.445791244506836, 'eval_runtime': 0.1613, 'eval_samples_per_second': 396.717, 'eval_steps_per_second': 49.59, 'epoch': 1.0} Saving model checkpoint to our_freesolv_model/checkpoint-64 Configuration saved in our_freesolv_model/checkpoint-64/config.json Model weights saved in our_freesolv_model/checkpoint-64/pytorch_model.bin ***** Running Evaluation ***** Num examples = 64 Batch size = 8 {'eval_loss': 22.2762508392334, 'eval_mse': 22.276248931884766, 'eval_rmse': 4.7197723388671875, 'eval_mae': 2.9041895866394043, 'eval_runtime': 0.1462, 'eval_samples_per_second': 437.674, 'eval_steps_per_second': 54.709, 'epoch': 2.0} Saving model checkpoint to our_freesolv_model/checkpoint-128 Configuration saved in our_freesolv_model/checkpoint-128/config.json Model weights saved in our_freesolv_model/checkpoint-128/pytorch_model.bin Deleting older checkpoint [our_freesolv_model/checkpoint-64] due to args.save_total_limit ***** Running Evaluation ***** Num examples = 64 Batch size = 8 {'eval_loss': 19.444108963012695, 'eval_mse': 19.444108963012695, 'eval_rmse': 4.409547328948975, 'eval_mae': 2.726284980773926, 'eval_runtime': 0.2087, 'eval_samples_per_second': 306.646, 'eval_steps_per_second': 38.331, 'epoch': 3.0} Saving model checkpoint to our_freesolv_model/checkpoint-192 Configuration saved in our_freesolv_model/checkpoint-192/config.json Model weights saved in our_freesolv_model/checkpoint-192/pytorch_model.bin Deleting older checkpoint [our_freesolv_model/checkpoint-128] due to args.save_total_limit ***** Running Evaluation ***** Num examples = 64 Batch size = 8 {'eval_loss': 17.12045669555664, 'eval_mse': 17.12045669555664, 'eval_rmse': 4.1376872062683105, 'eval_mae': 2.5535168647766113, 'eval_runtime': 0.3272, 'eval_samples_per_second': 195.59, 'eval_steps_per_second': 24.449, 'epoch': 4.0} Saving model checkpoint to our_freesolv_model/checkpoint-256 Configuration saved in our_freesolv_model/checkpoint-256/config.json Model weights saved in our_freesolv_model/checkpoint-256/pytorch_model.bin Deleting older checkpoint [our_freesolv_model/checkpoint-192] due to args.save_total_limit ***** Running Evaluation ***** Num examples = 64 Batch size = 8 {'eval_loss': 16.316720962524414, 'eval_mse': 16.316720962524414, 'eval_rmse': 4.039396286010742, 'eval_mae': 2.692227840423584, 'eval_runtime': 0.4287, 'eval_samples_per_second': 149.284, 'eval_steps_per_second': 18.661, 'epoch': 5.0} Saving model checkpoint to our_freesolv_model/checkpoint-320 Configuration saved in our_freesolv_model/checkpoint-320/config.json Model weights saved in our_freesolv_model/checkpoint-320/pytorch_model.bin Deleting older checkpoint [our_freesolv_model/checkpoint-256] due to args.save_total_limit ***** Running Evaluation ***** Num examples = 64 Batch size = 8 {'eval_loss': 15.293220520019531, 'eval_mse': 15.293218612670898, 'eval_rmse': 3.9106545448303223, 'eval_mae': 2.601778268814087, 'eval_runtime': 0.2956, 'eval_samples_per_second': 216.483, 'eval_steps_per_second': 27.06, 'epoch': 6.0} Saving model checkpoint to our_freesolv_model/checkpoint-384 Configuration saved in our_freesolv_model/checkpoint-384/config.json Model weights saved in our_freesolv_model/checkpoint-384/pytorch_model.bin Deleting older checkpoint [our_freesolv_model/checkpoint-320] due to args.save_total_limit ***** Running Evaluation ***** Num examples = 64 Batch size = 8 {'eval_loss': 14.56900691986084, 'eval_mse': 14.569008827209473, 'eval_rmse': 3.816937208175659, 'eval_mae': 2.5558180809020996, 'eval_runtime': 0.4164, 'eval_samples_per_second': 153.681, 'eval_steps_per_second': 19.21, 'epoch': 7.0} Saving model checkpoint to our_freesolv_model/checkpoint-448 Configuration saved in our_freesolv_model/checkpoint-448/config.json Model weights saved in our_freesolv_model/checkpoint-448/pytorch_model.bin Deleting older checkpoint [our_freesolv_model/checkpoint-384] due to args.save_total_limit {'loss': 3.9689, 'learning_rate': 8.4375e-06, 'epoch': 7.81} ***** Running Evaluation ***** Num examples = 64 Batch size = 8 {'eval_loss': 13.64460277557373, 'eval_mse': 13.64460277557373, 'eval_rmse': 3.6938600540161133, 'eval_mae': 2.39548397064209, 'eval_runtime': 0.4311, 'eval_samples_per_second': 148.456, 'eval_steps_per_second': 18.557, 'epoch': 8.0} Saving model checkpoint to our_freesolv_model/checkpoint-512 Configuration saved in our_freesolv_model/checkpoint-512/config.json Model weights saved in our_freesolv_model/checkpoint-512/pytorch_model.bin Deleting older checkpoint [our_freesolv_model/checkpoint-448] due to args.save_total_limit ***** Running Evaluation ***** Num examples = 64 Batch size = 8 {'eval_loss': 13.105853080749512, 'eval_mse': 13.105853080749512, 'eval_rmse': 3.6202006340026855, 'eval_mae': 2.4013423919677734, 'eval_runtime': 0.4297, 'eval_samples_per_second': 148.951, 'eval_steps_per_second': 18.619, 'epoch': 9.0} Saving model checkpoint to our_freesolv_model/checkpoint-576 Configuration saved in our_freesolv_model/checkpoint-576/config.json Model weights saved in our_freesolv_model/checkpoint-576/pytorch_model.bin Deleting older checkpoint [our_freesolv_model/checkpoint-512] due to args.save_total_limit ***** Running Evaluation ***** Num examples = 64 Batch size = 8 {'eval_loss': 13.048660278320312, 'eval_mse': 13.048660278320312, 'eval_rmse': 3.612293004989624, 'eval_mae': 2.3826305866241455, 'eval_runtime': 0.2978, 'eval_samples_per_second': 214.88, 'eval_steps_per_second': 26.86, 'epoch': 10.0} Saving model checkpoint to our_freesolv_model/checkpoint-640 Configuration saved in our_freesolv_model/checkpoint-640/config.json Model weights saved in our_freesolv_model/checkpoint-640/pytorch_model.bin Deleting older checkpoint [our_freesolv_model/checkpoint-576] due to args.save_total_limit ***** Running Evaluation ***** Num examples = 64 Batch size = 8 {'eval_loss': 12.558533668518066, 'eval_mse': 12.55853271484375, 'eval_rmse': 3.54380202293396, 'eval_mae': 2.3683643341064453, 'eval_runtime': 0.4369, 'eval_samples_per_second': 146.483, 'eval_steps_per_second': 18.31, 'epoch': 11.0} Saving model checkpoint to our_freesolv_model/checkpoint-704 Configuration saved in our_freesolv_model/checkpoint-704/config.json Model weights saved in our_freesolv_model/checkpoint-704/pytorch_model.bin Deleting older checkpoint [our_freesolv_model/checkpoint-640] due to args.save_total_limit ***** Running Evaluation ***** Num examples = 64 Batch size = 8 {'eval_loss': 12.03190803527832, 'eval_mse': 12.03190803527832, 'eval_rmse': 3.4687039852142334, 'eval_mae': 2.2633650302886963, 'eval_runtime': 0.4152, 'eval_samples_per_second': 154.131, 'eval_steps_per_second': 19.266, 'epoch': 12.0} Saving model checkpoint to our_freesolv_model/checkpoint-768 Configuration saved in our_freesolv_model/checkpoint-768/config.json Model weights saved in our_freesolv_model/checkpoint-768/pytorch_model.bin Deleting older checkpoint [our_freesolv_model/checkpoint-704] due to args.save_total_limit ***** Running Evaluation ***** Num examples = 64 Batch size = 8 {'eval_loss': 12.05549144744873, 'eval_mse': 12.05549144744873, 'eval_rmse': 3.472101926803589, 'eval_mae': 2.288928508758545, 'eval_runtime': 0.4311, 'eval_samples_per_second': 148.454, 'eval_steps_per_second': 18.557, 'epoch': 13.0} Saving model checkpoint to our_freesolv_model/checkpoint-832 Configuration saved in our_freesolv_model/checkpoint-832/config.json Model weights saved in our_freesolv_model/checkpoint-832/pytorch_model.bin Deleting older checkpoint [our_freesolv_model/checkpoint-768] due to args.save_total_limit ***** Running Evaluation ***** Num examples = 64 Batch size = 8 {'eval_loss': 11.724568367004395, 'eval_mse': 11.724568367004395, 'eval_rmse': 3.4241156578063965, 'eval_mae': 2.2129979133605957, 'eval_runtime': 0.4413, 'eval_samples_per_second': 145.038, 'eval_steps_per_second': 18.13, 'epoch': 14.0} Saving model checkpoint to our_freesolv_model/checkpoint-896 Configuration saved in our_freesolv_model/checkpoint-896/config.json Model weights saved in our_freesolv_model/checkpoint-896/pytorch_model.bin Deleting older checkpoint [our_freesolv_model/checkpoint-832] due to args.save_total_limit ***** Running Evaluation ***** Num examples = 64 Batch size = 8 {'eval_loss': 11.610068321228027, 'eval_mse': 11.610069274902344, 'eval_rmse': 3.4073550701141357, 'eval_mae': 2.238194227218628, 'eval_runtime': 0.41, 'eval_samples_per_second': 156.087, 'eval_steps_per_second': 19.511, 'epoch': 15.0} Saving model checkpoint to our_freesolv_model/checkpoint-960 Configuration saved in our_freesolv_model/checkpoint-960/config.json Model weights saved in our_freesolv_model/checkpoint-960/pytorch_model.bin Deleting older checkpoint [our_freesolv_model/checkpoint-896] due to args.save_total_limit {'loss': 0.8847, 'learning_rate': 6.875e-06, 'epoch': 15.62} ***** Running Evaluation ***** Num examples = 64 Batch size = 8 {'eval_loss': 11.409879684448242, 'eval_mse': 11.40987777709961, 'eval_rmse': 3.3778510093688965, 'eval_mae': 2.171018123626709, 'eval_runtime': 0.4279, 'eval_samples_per_second': 149.579, 'eval_steps_per_second': 18.697, 'epoch': 16.0} Saving model checkpoint to our_freesolv_model/checkpoint-1024 Configuration saved in our_freesolv_model/checkpoint-1024/config.json Model weights saved in our_freesolv_model/checkpoint-1024/pytorch_model.bin Deleting older checkpoint [our_freesolv_model/checkpoint-960] due to args.save_total_limit ***** Running Evaluation ***** Num examples = 64 Batch size = 8 {'eval_loss': 11.323513984680176, 'eval_mse': 11.323514938354492, 'eval_rmse': 3.3650431632995605, 'eval_mae': 2.1948208808898926, 'eval_runtime': 0.4359, 'eval_samples_per_second': 146.809, 'eval_steps_per_second': 18.351, 'epoch': 17.0} Saving model checkpoint to our_freesolv_model/checkpoint-1088 Configuration saved in our_freesolv_model/checkpoint-1088/config.json Model weights saved in our_freesolv_model/checkpoint-1088/pytorch_model.bin Deleting older checkpoint [our_freesolv_model/checkpoint-1024] due to args.save_total_limit ***** Running Evaluation ***** Num examples = 64 Batch size = 8 {'eval_loss': 10.922426223754883, 'eval_mse': 10.9224271774292, 'eval_rmse': 3.3049094676971436, 'eval_mae': 2.1065478324890137, 'eval_runtime': 0.4318, 'eval_samples_per_second': 148.218, 'eval_steps_per_second': 18.527, 'epoch': 18.0} Saving model checkpoint to our_freesolv_model/checkpoint-1152 Configuration saved in our_freesolv_model/checkpoint-1152/config.json Model weights saved in our_freesolv_model/checkpoint-1152/pytorch_model.bin Deleting older checkpoint [our_freesolv_model/checkpoint-1088] due to args.save_total_limit ***** Running Evaluation ***** Num examples = 64 Batch size = 8 {'eval_loss': 10.802040100097656, 'eval_mse': 10.80203914642334, 'eval_rmse': 3.2866456508636475, 'eval_mae': 2.1256909370422363, 'eval_runtime': 0.2822, 'eval_samples_per_second': 226.81, 'eval_steps_per_second': 28.351, 'epoch': 19.0} Saving model checkpoint to our_freesolv_model/checkpoint-1216 Configuration saved in our_freesolv_model/checkpoint-1216/config.json Model weights saved in our_freesolv_model/checkpoint-1216/pytorch_model.bin Deleting older checkpoint [our_freesolv_model/checkpoint-1152] due to args.save_total_limit ***** Running Evaluation ***** Num examples = 64 Batch size = 8 {'eval_loss': 10.668560981750488, 'eval_mse': 10.668560981750488, 'eval_rmse': 3.2662763595581055, 'eval_mae': 2.102822780609131, 'eval_runtime': 0.4297, 'eval_samples_per_second': 148.924, 'eval_steps_per_second': 18.616, 'epoch': 20.0} Saving model checkpoint to our_freesolv_model/checkpoint-1280 Configuration saved in our_freesolv_model/checkpoint-1280/config.json Model weights saved in our_freesolv_model/checkpoint-1280/pytorch_model.bin Deleting older checkpoint [our_freesolv_model/checkpoint-1216] due to args.save_total_limit ***** Running Evaluation ***** Num examples = 64 Batch size = 8 {'eval_loss': 10.928054809570312, 'eval_mse': 10.928054809570312, 'eval_rmse': 3.3057608604431152, 'eval_mae': 2.201329231262207, 'eval_runtime': 0.4133, 'eval_samples_per_second': 154.835, 'eval_steps_per_second': 19.354, 'epoch': 21.0} Saving model checkpoint to our_freesolv_model/checkpoint-1344 Configuration saved in our_freesolv_model/checkpoint-1344/config.json Model weights saved in our_freesolv_model/checkpoint-1344/pytorch_model.bin Deleting older checkpoint [our_freesolv_model/checkpoint-1280] due to args.save_total_limit ***** Running Evaluation ***** Num examples = 64 Batch size = 8 {'eval_loss': 10.920714378356934, 'eval_mse': 10.920713424682617, 'eval_rmse': 3.30465030670166, 'eval_mae': 2.1609740257263184, 'eval_runtime': 0.4362, 'eval_samples_per_second': 146.723, 'eval_steps_per_second': 18.34, 'epoch': 22.0} Saving model checkpoint to our_freesolv_model/checkpoint-1408 Configuration saved in our_freesolv_model/checkpoint-1408/config.json Model weights saved in our_freesolv_model/checkpoint-1408/pytorch_model.bin Deleting older checkpoint [our_freesolv_model/checkpoint-1344] due to args.save_total_limit ***** Running Evaluation ***** Num examples = 64 Batch size = 8 {'eval_loss': 10.914674758911133, 'eval_mse': 10.914674758911133, 'eval_rmse': 3.303736448287964, 'eval_mae': 2.1464970111846924, 'eval_runtime': 0.3154, 'eval_samples_per_second': 202.948, 'eval_steps_per_second': 25.369, 'epoch': 23.0} Saving model checkpoint to our_freesolv_model/checkpoint-1472 Configuration saved in our_freesolv_model/checkpoint-1472/config.json Model weights saved in our_freesolv_model/checkpoint-1472/pytorch_model.bin Deleting older checkpoint [our_freesolv_model/checkpoint-1408] due to args.save_total_limit {'loss': 0.6489, 'learning_rate': 5.3125e-06, 'epoch': 23.44} ***** Running Evaluation ***** Num examples = 64 Batch size = 8 {'eval_loss': 10.826024055480957, 'eval_mse': 10.826024055480957, 'eval_rmse': 3.290292501449585, 'eval_mae': 2.166719436645508, 'eval_runtime': 0.4282, 'eval_samples_per_second': 149.463, 'eval_steps_per_second': 18.683, 'epoch': 24.0} Saving model checkpoint to our_freesolv_model/checkpoint-1536 Configuration saved in our_freesolv_model/checkpoint-1536/config.json Model weights saved in our_freesolv_model/checkpoint-1536/pytorch_model.bin Deleting older checkpoint [our_freesolv_model/checkpoint-1472] due to args.save_total_limit ***** Running Evaluation ***** Num examples = 64 Batch size = 8 {'eval_loss': 10.914568901062012, 'eval_mse': 10.914569854736328, 'eval_rmse': 3.303720712661743, 'eval_mae': 2.1764001846313477, 'eval_runtime': 0.4401, 'eval_samples_per_second': 145.428, 'eval_steps_per_second': 18.178, 'epoch': 25.0} Saving model checkpoint to our_freesolv_model/checkpoint-1600 Configuration saved in our_freesolv_model/checkpoint-1600/config.json Model weights saved in our_freesolv_model/checkpoint-1600/pytorch_model.bin Deleting older checkpoint [our_freesolv_model/checkpoint-1536] due to args.save_total_limit ***** Running Evaluation ***** Num examples = 64 Batch size = 8 {'eval_loss': 11.035606384277344, 'eval_mse': 11.035605430603027, 'eval_rmse': 3.321988105773926, 'eval_mae': 2.2225704193115234, 'eval_runtime': 0.4326, 'eval_samples_per_second': 147.959, 'eval_steps_per_second': 18.495, 'epoch': 26.0} Saving model checkpoint to our_freesolv_model/checkpoint-1664 Configuration saved in our_freesolv_model/checkpoint-1664/config.json Model weights saved in our_freesolv_model/checkpoint-1664/pytorch_model.bin Deleting older checkpoint [our_freesolv_model/checkpoint-1600] due to args.save_total_limit ***** Running Evaluation ***** Num examples = 64 Batch size = 8 {'eval_loss': 11.038973808288574, 'eval_mse': 11.038971900939941, 'eval_rmse': 3.3224947452545166, 'eval_mae': 2.2142393589019775, 'eval_runtime': 0.435, 'eval_samples_per_second': 147.12, 'eval_steps_per_second': 18.39, 'epoch': 27.0} Saving model checkpoint to our_freesolv_model/checkpoint-1728 Configuration saved in our_freesolv_model/checkpoint-1728/config.json Model weights saved in our_freesolv_model/checkpoint-1728/pytorch_model.bin Deleting older checkpoint [our_freesolv_model/checkpoint-1664] due to args.save_total_limit ***** Running Evaluation ***** Num examples = 64 Batch size = 8 {'eval_loss': 11.178277015686035, 'eval_mse': 11.178277015686035, 'eval_rmse': 3.343393087387085, 'eval_mae': 2.2388522624969482, 'eval_runtime': 0.4403, 'eval_samples_per_second': 145.349, 'eval_steps_per_second': 18.169, 'epoch': 28.0} Saving model checkpoint to our_freesolv_model/checkpoint-1792 Configuration saved in our_freesolv_model/checkpoint-1792/config.json Model weights saved in our_freesolv_model/checkpoint-1792/pytorch_model.bin Deleting older checkpoint [our_freesolv_model/checkpoint-1728] due to args.save_total_limit ***** Running Evaluation ***** Num examples = 64 Batch size = 8 {'eval_loss': 10.676009178161621, 'eval_mse': 10.676008224487305, 'eval_rmse': 3.26741623878479, 'eval_mae': 2.163010358810425, 'eval_runtime': 0.4243, 'eval_samples_per_second': 150.831, 'eval_steps_per_second': 18.854, 'epoch': 29.0} Saving model checkpoint to our_freesolv_model/checkpoint-1856 Configuration saved in our_freesolv_model/checkpoint-1856/config.json Model weights saved in our_freesolv_model/checkpoint-1856/pytorch_model.bin Deleting older checkpoint [our_freesolv_model/checkpoint-1792] due to args.save_total_limit ***** Running Evaluation ***** Num examples = 64 Batch size = 8 {'eval_loss': 10.856060028076172, 'eval_mse': 10.856060981750488, 'eval_rmse': 3.294853687286377, 'eval_mae': 2.1758837699890137, 'eval_runtime': 0.4294, 'eval_samples_per_second': 149.044, 'eval_steps_per_second': 18.63, 'epoch': 30.0} Saving model checkpoint to our_freesolv_model/checkpoint-1920 Configuration saved in our_freesolv_model/checkpoint-1920/config.json Model weights saved in our_freesolv_model/checkpoint-1920/pytorch_model.bin Deleting older checkpoint [our_freesolv_model/checkpoint-1856] due to args.save_total_limit ***** Running Evaluation ***** Num examples = 64 Batch size = 8 {'eval_loss': 10.435661315917969, 'eval_mse': 10.435661315917969, 'eval_rmse': 3.2304275035858154, 'eval_mae': 2.1428065299987793, 'eval_runtime': 0.4438, 'eval_samples_per_second': 144.195, 'eval_steps_per_second': 18.024, 'epoch': 31.0} Saving model checkpoint to our_freesolv_model/checkpoint-1984 Configuration saved in our_freesolv_model/checkpoint-1984/config.json Model weights saved in our_freesolv_model/checkpoint-1984/pytorch_model.bin Deleting older checkpoint [our_freesolv_model/checkpoint-1920] due to args.save_total_limit {'loss': 0.5499, 'learning_rate': 3.7500000000000005e-06, 'epoch': 31.25} ***** Running Evaluation ***** Num examples = 64 Batch size = 8 {'eval_loss': 10.568000793457031, 'eval_mse': 10.568000793457031, 'eval_rmse': 3.2508461475372314, 'eval_mae': 2.1557540893554688, 'eval_runtime': 0.4281, 'eval_samples_per_second': 149.484, 'eval_steps_per_second': 18.686, 'epoch': 32.0} Saving model checkpoint to our_freesolv_model/checkpoint-2048 Configuration saved in our_freesolv_model/checkpoint-2048/config.json Model weights saved in our_freesolv_model/checkpoint-2048/pytorch_model.bin Deleting older checkpoint [our_freesolv_model/checkpoint-1984] due to args.save_total_limit ***** Running Evaluation ***** Num examples = 64 Batch size = 8 {'eval_loss': 10.61816120147705, 'eval_mse': 10.618160247802734, 'eval_rmse': 3.258551836013794, 'eval_mae': 2.1454195976257324, 'eval_runtime': 0.418, 'eval_samples_per_second': 153.1, 'eval_steps_per_second': 19.137, 'epoch': 33.0} Saving model checkpoint to our_freesolv_model/checkpoint-2112 Configuration saved in our_freesolv_model/checkpoint-2112/config.json Model weights saved in our_freesolv_model/checkpoint-2112/pytorch_model.bin Deleting older checkpoint [our_freesolv_model/checkpoint-2048] due to args.save_total_limit ***** Running Evaluation ***** Num examples = 64 Batch size = 8 {'eval_loss': 10.70760726928711, 'eval_mse': 10.707606315612793, 'eval_rmse': 3.272247791290283, 'eval_mae': 2.185828924179077, 'eval_runtime': 0.4346, 'eval_samples_per_second': 147.25, 'eval_steps_per_second': 18.406, 'epoch': 34.0} Saving model checkpoint to our_freesolv_model/checkpoint-2176 Configuration saved in our_freesolv_model/checkpoint-2176/config.json Model weights saved in our_freesolv_model/checkpoint-2176/pytorch_model.bin Deleting older checkpoint [our_freesolv_model/checkpoint-2112] due to args.save_total_limit ***** Running Evaluation ***** Num examples = 64 Batch size = 8 {'eval_loss': 10.65221118927002, 'eval_mse': 10.65221118927002, 'eval_rmse': 3.263772487640381, 'eval_mae': 2.1475348472595215, 'eval_runtime': 0.4365, 'eval_samples_per_second': 146.633, 'eval_steps_per_second': 18.329, 'epoch': 35.0} Saving model checkpoint to our_freesolv_model/checkpoint-2240 Configuration saved in our_freesolv_model/checkpoint-2240/config.json Model weights saved in our_freesolv_model/checkpoint-2240/pytorch_model.bin Deleting older checkpoint [our_freesolv_model/checkpoint-2176] due to args.save_total_limit ***** Running Evaluation ***** Num examples = 64 Batch size = 8 {'eval_loss': 10.60755443572998, 'eval_mse': 10.607553482055664, 'eval_rmse': 3.2569239139556885, 'eval_mae': 2.1597788333892822, 'eval_runtime': 0.3132, 'eval_samples_per_second': 204.312, 'eval_steps_per_second': 25.539, 'epoch': 36.0} Saving model checkpoint to our_freesolv_model/checkpoint-2304 Configuration saved in our_freesolv_model/checkpoint-2304/config.json Model weights saved in our_freesolv_model/checkpoint-2304/pytorch_model.bin Deleting older checkpoint [our_freesolv_model/checkpoint-2240] due to args.save_total_limit ***** Running Evaluation ***** Num examples = 64 Batch size = 8 {'eval_loss': 10.558968544006348, 'eval_mse': 10.558967590332031, 'eval_rmse': 3.2494564056396484, 'eval_mae': 2.1506295204162598, 'eval_runtime': 0.4253, 'eval_samples_per_second': 150.493, 'eval_steps_per_second': 18.812, 'epoch': 37.0} Saving model checkpoint to our_freesolv_model/checkpoint-2368 Configuration saved in our_freesolv_model/checkpoint-2368/config.json Model weights saved in our_freesolv_model/checkpoint-2368/pytorch_model.bin Deleting older checkpoint [our_freesolv_model/checkpoint-2304] due to args.save_total_limit ***** Running Evaluation ***** Num examples = 64 Batch size = 8 {'eval_loss': 10.674619674682617, 'eval_mse': 10.674619674682617, 'eval_rmse': 3.2672035694122314, 'eval_mae': 2.1740453243255615, 'eval_runtime': 0.4355, 'eval_samples_per_second': 146.966, 'eval_steps_per_second': 18.371, 'epoch': 38.0} Saving model checkpoint to our_freesolv_model/checkpoint-2432 Configuration saved in our_freesolv_model/checkpoint-2432/config.json Model weights saved in our_freesolv_model/checkpoint-2432/pytorch_model.bin Deleting older checkpoint [our_freesolv_model/checkpoint-2368] due to args.save_total_limit ***** Running Evaluation ***** Num examples = 64 Batch size = 8 {'eval_loss': 10.524478912353516, 'eval_mse': 10.5244779586792, 'eval_rmse': 3.244145154953003, 'eval_mae': 2.1458582878112793, 'eval_runtime': 0.4374, 'eval_samples_per_second': 146.309, 'eval_steps_per_second': 18.289, 'epoch': 39.0} Saving model checkpoint to our_freesolv_model/checkpoint-2496 Configuration saved in our_freesolv_model/checkpoint-2496/config.json Model weights saved in our_freesolv_model/checkpoint-2496/pytorch_model.bin Deleting older checkpoint [our_freesolv_model/checkpoint-2432] due to args.save_total_limit {'loss': 0.5012, 'learning_rate': 2.1875000000000002e-06, 'epoch': 39.06} ***** Running Evaluation ***** Num examples = 64 Batch size = 8 {'eval_loss': 10.667997360229492, 'eval_mse': 10.667997360229492, 'eval_rmse': 3.2661900520324707, 'eval_mae': 2.155714273452759, 'eval_runtime': 0.3418, 'eval_samples_per_second': 187.219, 'eval_steps_per_second': 23.402, 'epoch': 40.0} Saving model checkpoint to our_freesolv_model/checkpoint-2560 Configuration saved in our_freesolv_model/checkpoint-2560/config.json Model weights saved in our_freesolv_model/checkpoint-2560/pytorch_model.bin Deleting older checkpoint [our_freesolv_model/checkpoint-2496] due to args.save_total_limit ***** Running Evaluation ***** Num examples = 64 Batch size = 8 {'eval_loss': 10.641304016113281, 'eval_mse': 10.641304016113281, 'eval_rmse': 3.262101173400879, 'eval_mae': 2.174771547317505, 'eval_runtime': 0.4419, 'eval_samples_per_second': 144.834, 'eval_steps_per_second': 18.104, 'epoch': 41.0} Saving model checkpoint to our_freesolv_model/checkpoint-2624 Configuration saved in our_freesolv_model/checkpoint-2624/config.json Model weights saved in our_freesolv_model/checkpoint-2624/pytorch_model.bin Deleting older checkpoint [our_freesolv_model/checkpoint-2560] due to args.save_total_limit ***** Running Evaluation ***** Num examples = 64 Batch size = 8 {'eval_loss': 10.72380542755127, 'eval_mse': 10.723804473876953, 'eval_rmse': 3.274722099304199, 'eval_mae': 2.2047784328460693, 'eval_runtime': 0.4025, 'eval_samples_per_second': 158.999, 'eval_steps_per_second': 19.875, 'epoch': 42.0} Saving model checkpoint to our_freesolv_model/checkpoint-2688 Configuration saved in our_freesolv_model/checkpoint-2688/config.json Model weights saved in our_freesolv_model/checkpoint-2688/pytorch_model.bin Deleting older checkpoint [our_freesolv_model/checkpoint-2624] due to args.save_total_limit ***** Running Evaluation ***** Num examples = 64 Batch size = 8 {'eval_loss': 10.794100761413574, 'eval_mse': 10.79410171508789, 'eval_rmse': 3.285437822341919, 'eval_mae': 2.212890863418579, 'eval_runtime': 0.4371, 'eval_samples_per_second': 146.435, 'eval_steps_per_second': 18.304, 'epoch': 43.0} Saving model checkpoint to our_freesolv_model/checkpoint-2752 Configuration saved in our_freesolv_model/checkpoint-2752/config.json Model weights saved in our_freesolv_model/checkpoint-2752/pytorch_model.bin Deleting older checkpoint [our_freesolv_model/checkpoint-2688] due to args.save_total_limit ***** Running Evaluation ***** Num examples = 64 Batch size = 8 {'eval_loss': 10.679245948791504, 'eval_mse': 10.679245948791504, 'eval_rmse': 3.267911672592163, 'eval_mae': 2.199676513671875, 'eval_runtime': 0.4079, 'eval_samples_per_second': 156.894, 'eval_steps_per_second': 19.612, 'epoch': 44.0} Saving model checkpoint to our_freesolv_model/checkpoint-2816 Configuration saved in our_freesolv_model/checkpoint-2816/config.json Model weights saved in our_freesolv_model/checkpoint-2816/pytorch_model.bin Deleting older checkpoint [our_freesolv_model/checkpoint-2752] due to args.save_total_limit ***** Running Evaluation ***** Num examples = 64 Batch size = 8 {'eval_loss': 10.524163246154785, 'eval_mse': 10.524163246154785, 'eval_rmse': 3.2440967559814453, 'eval_mae': 2.1674587726593018, 'eval_runtime': 0.2984, 'eval_samples_per_second': 214.505, 'eval_steps_per_second': 26.813, 'epoch': 45.0} Saving model checkpoint to our_freesolv_model/checkpoint-2880 Configuration saved in our_freesolv_model/checkpoint-2880/config.json Model weights saved in our_freesolv_model/checkpoint-2880/pytorch_model.bin Deleting older checkpoint [our_freesolv_model/checkpoint-2816] due to args.save_total_limit ***** Running Evaluation ***** Num examples = 64 Batch size = 8 {'eval_loss': 10.532914161682129, 'eval_mse': 10.532913208007812, 'eval_rmse': 3.2454450130462646, 'eval_mae': 2.177356481552124, 'eval_runtime': 0.4463, 'eval_samples_per_second': 143.398, 'eval_steps_per_second': 17.925, 'epoch': 46.0} Saving model checkpoint to our_freesolv_model/checkpoint-2944 Configuration saved in our_freesolv_model/checkpoint-2944/config.json Model weights saved in our_freesolv_model/checkpoint-2944/pytorch_model.bin Deleting older checkpoint [our_freesolv_model/checkpoint-2880] due to args.save_total_limit {'loss': 0.471, 'learning_rate': 6.25e-07, 'epoch': 46.88} ***** Running Evaluation ***** Num examples = 64 Batch size = 8 {'eval_loss': 10.552495002746582, 'eval_mse': 10.552494049072266, 'eval_rmse': 3.248460292816162, 'eval_mae': 2.182786464691162, 'eval_runtime': 0.3828, 'eval_samples_per_second': 167.191, 'eval_steps_per_second': 20.899, 'epoch': 47.0} Saving model checkpoint to our_freesolv_model/checkpoint-3008 Configuration saved in our_freesolv_model/checkpoint-3008/config.json Model weights saved in our_freesolv_model/checkpoint-3008/pytorch_model.bin Deleting older checkpoint [our_freesolv_model/checkpoint-2944] due to args.save_total_limit ***** Running Evaluation ***** Num examples = 64 Batch size = 8 {'eval_loss': 10.577668190002441, 'eval_mse': 10.577667236328125, 'eval_rmse': 3.2523326873779297, 'eval_mae': 2.177499294281006, 'eval_runtime': 0.4436, 'eval_samples_per_second': 144.276, 'eval_steps_per_second': 18.035, 'epoch': 48.0} Saving model checkpoint to our_freesolv_model/checkpoint-3072 Configuration saved in our_freesolv_model/checkpoint-3072/config.json Model weights saved in our_freesolv_model/checkpoint-3072/pytorch_model.bin Deleting older checkpoint [our_freesolv_model/checkpoint-3008] due to args.save_total_limit ***** Running Evaluation ***** Num examples = 64 Batch size = 8 {'eval_loss': 10.599947929382324, 'eval_mse': 10.59994888305664, 'eval_rmse': 3.255756378173828, 'eval_mae': 2.184239625930786, 'eval_runtime': 0.2975, 'eval_samples_per_second': 215.1, 'eval_steps_per_second': 26.888, 'epoch': 49.0} Saving model checkpoint to our_freesolv_model/checkpoint-3136 Configuration saved in our_freesolv_model/checkpoint-3136/config.json Model weights saved in our_freesolv_model/checkpoint-3136/pytorch_model.bin Deleting older checkpoint [our_freesolv_model/checkpoint-3072] due to args.save_total_limit ***** Running Evaluation ***** Num examples = 64 Batch size = 8 {'eval_loss': 10.600202560424805, 'eval_mse': 10.600202560424805, 'eval_rmse': 3.2557952404022217, 'eval_mae': 2.1849870681762695, 'eval_runtime': 0.4398, 'eval_samples_per_second': 145.517, 'eval_steps_per_second': 18.19, 'epoch': 50.0} Saving model checkpoint to our_freesolv_model/checkpoint-3200 Configuration saved in our_freesolv_model/checkpoint-3200/config.json Model weights saved in our_freesolv_model/checkpoint-3200/pytorch_model.bin Deleting older checkpoint [our_freesolv_model/checkpoint-3136] due to args.save_total_limit Training completed. Do not forget to share your model on huggingface.co/models =) {'train_runtime': 665.9879, 'train_samples_per_second': 38.364, 'train_steps_per_second': 4.805, 'train_loss': 1.1251747608184814, 'epoch': 50.0} Metrics TrainOutput(global_step=3200, training_loss=1.1251747608184814, metrics={'train_runtime': 665.9879, 'train_samples_per_second': 38.364, 'train_steps_per_second': 4.805, 'train_loss': 1.1251747608184814, 'epoch': 50.0}) Saving model checkpoint to our_freesolv_model Configuration saved in our_freesolv_model/config.json Model weights saved in our_freesolv_model/pytorch_model.bin ***** Running Prediction ***** Num examples = 65 Batch size = 8 Mean Squared Error (MSE): 7.823581782801873 Root Mean Square Error (RMSE): 2.797066638963375 Mean Absolute Error (MAE): 1.7614372157431566