--- license: apache-2.0 base_model: t5-small tags: - generated_from_keras_callback model-index: - name: pijarcandra22/t5Indo2Sunda results: [] --- # pijarcandra22/t5Indo2Sunda This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on an unknown dataset. It achieves the following results on the evaluation set: - Train Loss: 2.1941 - Validation Loss: 2.1230 - Epoch: 99 ## 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: - optimizer: {'name': 'AdamWeightDecay', 'learning_rate': 2e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01} - training_precision: float32 ### Training results | Train Loss | Validation Loss | Epoch | |:----------:|:---------------:|:-----:| | 4.3724 | 3.9124 | 0 | | 3.9887 | 3.6348 | 1 | | 3.7534 | 3.4215 | 2 | | 3.5819 | 3.2847 | 3 | | 3.4632 | 3.1902 | 4 | | 3.3751 | 3.1139 | 5 | | 3.3039 | 3.0493 | 6 | | 3.2447 | 2.9955 | 7 | | 3.1911 | 2.9481 | 8 | | 3.1455 | 2.9082 | 9 | | 3.1068 | 2.8718 | 10 | | 3.0697 | 2.8387 | 11 | | 3.0381 | 2.8105 | 12 | | 3.0050 | 2.7825 | 13 | | 2.9796 | 2.7568 | 14 | | 2.9510 | 2.7350 | 15 | | 2.9259 | 2.7096 | 16 | | 2.9053 | 2.6881 | 17 | | 2.8833 | 2.6696 | 18 | | 2.8599 | 2.6510 | 19 | | 2.8403 | 2.6328 | 20 | | 2.8207 | 2.6171 | 21 | | 2.8046 | 2.5999 | 22 | | 2.7861 | 2.5857 | 23 | | 2.7715 | 2.5699 | 24 | | 2.7557 | 2.5542 | 25 | | 2.7387 | 2.5420 | 26 | | 2.7225 | 2.5299 | 27 | | 2.7085 | 2.5182 | 28 | | 2.6950 | 2.5081 | 29 | | 2.6818 | 2.4951 | 30 | | 2.6687 | 2.4864 | 31 | | 2.6578 | 2.4760 | 32 | | 2.6461 | 2.4651 | 33 | | 2.6334 | 2.4559 | 34 | | 2.6213 | 2.4477 | 35 | | 2.6096 | 2.4373 | 36 | | 2.5993 | 2.4297 | 37 | | 2.5906 | 2.4208 | 38 | | 2.5778 | 2.4100 | 39 | | 2.5703 | 2.4025 | 40 | | 2.5594 | 2.3962 | 41 | | 2.5521 | 2.3901 | 42 | | 2.5414 | 2.3808 | 43 | | 2.5318 | 2.3726 | 44 | | 2.5235 | 2.3684 | 45 | | 2.5165 | 2.3592 | 46 | | 2.5060 | 2.3507 | 47 | | 2.4972 | 2.3466 | 48 | | 2.4892 | 2.3388 | 49 | | 2.4807 | 2.3325 | 50 | | 2.4732 | 2.3281 | 51 | | 2.4654 | 2.3210 | 52 | | 2.4592 | 2.3138 | 53 | | 2.4525 | 2.3100 | 54 | | 2.4439 | 2.3046 | 55 | | 2.4349 | 2.2980 | 56 | | 2.4283 | 2.2926 | 57 | | 2.4222 | 2.2884 | 58 | | 2.4139 | 2.2824 | 59 | | 2.4071 | 2.2759 | 60 | | 2.4008 | 2.2705 | 61 | | 2.3941 | 2.2664 | 62 | | 2.3882 | 2.2588 | 63 | | 2.3813 | 2.2566 | 64 | | 2.3759 | 2.2498 | 65 | | 2.3674 | 2.2461 | 66 | | 2.3618 | 2.2425 | 67 | | 2.3534 | 2.2377 | 68 | | 2.3522 | 2.2314 | 69 | | 2.3398 | 2.2269 | 70 | | 2.3391 | 2.2241 | 71 | | 2.3303 | 2.2184 | 72 | | 2.3275 | 2.2137 | 73 | | 2.3190 | 2.2100 | 74 | | 2.3159 | 2.2048 | 75 | | 2.3078 | 2.2011 | 76 | | 2.3048 | 2.1971 | 77 | | 2.3005 | 2.1936 | 78 | | 2.2938 | 2.1899 | 79 | | 2.2892 | 2.1859 | 80 | | 2.2824 | 2.1819 | 81 | | 2.2758 | 2.1787 | 82 | | 2.2739 | 2.1757 | 83 | | 2.2689 | 2.1716 | 84 | | 2.2623 | 2.1664 | 85 | | 2.2574 | 2.1657 | 86 | | 2.2537 | 2.1618 | 87 | | 2.2483 | 2.1563 | 88 | | 2.2407 | 2.1554 | 89 | | 2.2387 | 2.1510 | 90 | | 2.2351 | 2.1469 | 91 | | 2.2286 | 2.1436 | 92 | | 2.2226 | 2.1413 | 93 | | 2.2171 | 2.1395 | 94 | | 2.2159 | 2.1342 | 95 | | 2.2109 | 2.1314 | 96 | | 2.2041 | 2.1284 | 97 | | 2.1999 | 2.1260 | 98 | | 2.1941 | 2.1230 | 99 | ### Framework versions - Transformers 4.35.2 - TensorFlow 2.14.0 - Datasets 2.15.0 - Tokenizers 0.15.0