--- license: mit tags: - generated_from_trainer metrics: - f1 model-index: - name: Greg-Sentiment-classifier results: [] --- # Greg-Sentiment-classifier This model is a fine-tuned version of [microsoft/MiniLM-L12-H384-uncased](https://huggingface.co./microsoft/MiniLM-L12-H384-uncased) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.7903 - F1: 0.7123 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 16 - eval_batch_size: 16 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 2 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 | |:-------------:|:-----:|:----:|:---------------:|:------:| | 0.6542 | 0.03 | 16 | 0.8127 | 0.6943 | | 0.574 | 0.06 | 32 | 0.7935 | 0.6969 | | 0.7078 | 0.1 | 48 | 0.8009 | 0.6957 | | 0.5408 | 0.13 | 64 | 0.7863 | 0.7014 | | 0.5343 | 0.16 | 80 | 0.8077 | 0.6996 | | 0.5768 | 0.19 | 96 | 0.8239 | 0.6900 | | 0.6633 | 0.22 | 112 | 0.7942 | 0.7028 | | 0.5409 | 0.26 | 128 | 0.8025 | 0.6960 | | 0.7043 | 0.29 | 144 | 0.7954 | 0.6813 | | 0.5358 | 0.32 | 160 | 0.8058 | 0.6988 | | 0.5558 | 0.35 | 176 | 0.8476 | 0.6799 | | 0.5759 | 0.38 | 192 | 0.8232 | 0.7017 | | 0.596 | 0.42 | 208 | 0.8240 | 0.7072 | | 0.5977 | 0.45 | 224 | 0.8683 | 0.6947 | | 0.5655 | 0.48 | 240 | 0.8378 | 0.7053 | | 0.6274 | 0.51 | 256 | 0.8175 | 0.6980 | | 0.4952 | 0.55 | 272 | 0.8203 | 0.6957 | | 0.6501 | 0.58 | 288 | 0.8236 | 0.7014 | | 0.5365 | 0.61 | 304 | 0.8082 | 0.7059 | | 0.5598 | 0.64 | 320 | 0.8052 | 0.7121 | | 0.5692 | 0.67 | 336 | 0.7989 | 0.7075 | | 0.526 | 0.71 | 352 | 0.8030 | 0.6961 | | 0.5505 | 0.74 | 368 | 0.8157 | 0.7137 | | 0.4759 | 0.77 | 384 | 0.8466 | 0.6937 | | 0.6622 | 0.8 | 400 | 0.8518 | 0.6982 | | 0.6298 | 0.83 | 416 | 0.8272 | 0.6976 | | 0.6311 | 0.87 | 432 | 0.8445 | 0.6793 | | 0.5678 | 0.9 | 448 | 0.8096 | 0.6897 | | 0.6687 | 0.93 | 464 | 0.7948 | 0.6968 | | 0.6654 | 0.96 | 480 | 0.8047 | 0.7076 | | 0.6572 | 0.99 | 496 | 0.7944 | 0.7037 | | 0.5845 | 1.03 | 512 | 0.7772 | 0.7030 | | 0.6611 | 1.06 | 528 | 0.7829 | 0.7005 | | 0.4988 | 1.09 | 544 | 0.7953 | 0.7070 | | 0.6355 | 1.12 | 560 | 0.8252 | 0.6983 | | 0.5464 | 1.15 | 576 | 0.8293 | 0.7044 | | 0.6188 | 1.19 | 592 | 0.8077 | 0.7073 | | 0.5125 | 1.22 | 608 | 0.7975 | 0.7041 | | 0.6221 | 1.25 | 624 | 0.7947 | 0.7041 | | 0.5806 | 1.28 | 640 | 0.8027 | 0.6983 | | 0.6335 | 1.31 | 656 | 0.7992 | 0.7027 | | 0.6283 | 1.35 | 672 | 0.7836 | 0.7055 | | 0.6485 | 1.38 | 688 | 0.7891 | 0.7104 | | 0.5596 | 1.41 | 704 | 0.8146 | 0.7015 | | 0.4928 | 1.44 | 720 | 0.7998 | 0.7088 | | 0.5809 | 1.47 | 736 | 0.7850 | 0.7056 | | 0.5117 | 1.51 | 752 | 0.7994 | 0.7053 | | 0.6012 | 1.54 | 768 | 0.7960 | 0.7081 | | 0.5213 | 1.57 | 784 | 0.8109 | 0.7034 | | 0.6018 | 1.6 | 800 | 0.7927 | 0.7134 | | 0.5851 | 1.64 | 816 | 0.7978 | 0.7108 | | 0.6571 | 1.67 | 832 | 0.8131 | 0.7004 | | 0.5215 | 1.7 | 848 | 0.7942 | 0.7146 | | 0.5372 | 1.73 | 864 | 0.7957 | 0.7110 | | 0.5511 | 1.76 | 880 | 0.7915 | 0.7138 | | 0.5991 | 1.8 | 896 | 0.7899 | 0.7121 | | 0.6128 | 1.83 | 912 | 0.7879 | 0.7136 | | 0.5493 | 1.86 | 928 | 0.7960 | 0.7099 | | 0.6304 | 1.89 | 944 | 0.7924 | 0.7102 | | 0.4456 | 1.92 | 960 | 0.7904 | 0.7126 | | 0.5484 | 1.96 | 976 | 0.7906 | 0.7127 | | 0.515 | 1.99 | 992 | 0.7903 | 0.7123 | ### Framework versions - Transformers 4.30.2 - Pytorch 2.0.1+cu118 - Datasets 2.13.1 - Tokenizers 0.13.3