--- license: apache-2.0 base_model: google/flan-t5-base tags: - generated_from_trainer metrics: - bleu model-index: - name: Nahuatl_Espanol_v1 results: [] --- # Nahuatl_Espanol_v1 This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 2.3093 - Bleu: 0.928 - Gen Len: 17.3008 ## 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: 5 ### Training results | Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len | |:-------------:|:-----:|:----:|:---------------:|:------:|:-------:| | No log | 0.1 | 100 | 3.4034 | 0.3143 | 17.3089 | | No log | 0.2 | 200 | 3.1638 | 0.3187 | 17.4173 | | No log | 0.3 | 300 | 3.0323 | 0.3292 | 17.2922 | | No log | 0.4 | 400 | 2.9391 | 0.3713 | 17.1362 | | 3.4051 | 0.5 | 500 | 2.8715 | 0.4182 | 17.2461 | | 3.4051 | 0.6 | 600 | 2.8084 | 0.4782 | 17.2052 | | 3.4051 | 0.71 | 700 | 2.7614 | 0.4541 | 17.1109 | | 3.4051 | 0.81 | 800 | 2.7171 | 0.6082 | 17.2327 | | 3.4051 | 0.91 | 900 | 2.6860 | 0.7904 | 17.2443 | | 2.961 | 1.01 | 1000 | 2.6516 | 0.8488 | 17.3227 | | 2.961 | 1.11 | 1100 | 2.6256 | 0.8094 | 17.3409 | | 2.961 | 1.21 | 1200 | 2.5967 | 0.7545 | 17.3147 | | 2.961 | 1.31 | 1300 | 2.5753 | 0.7891 | 17.2418 | | 2.961 | 1.41 | 1400 | 2.5545 | 0.7925 | 17.2849 | | 2.7764 | 1.51 | 1500 | 2.5335 | 0.7728 | 17.3243 | | 2.7764 | 1.61 | 1600 | 2.5163 | 0.8055 | 17.4302 | | 2.7764 | 1.71 | 1700 | 2.4993 | 0.843 | 17.2501 | | 2.7764 | 1.81 | 1800 | 2.4840 | 0.8297 | 17.2136 | | 2.7764 | 1.92 | 1900 | 2.4719 | 0.8457 | 17.3364 | | 2.6783 | 2.02 | 2000 | 2.4598 | 0.9152 | 17.2453 | | 2.6783 | 2.12 | 2100 | 2.4458 | 0.8597 | 17.2405 | | 2.6783 | 2.22 | 2200 | 2.4345 | 0.8741 | 17.2436 | | 2.6783 | 2.32 | 2300 | 2.4245 | 0.8681 | 17.3492 | | 2.6783 | 2.42 | 2400 | 2.4166 | 0.8936 | 17.2708 | | 2.6228 | 2.52 | 2500 | 2.4055 | 0.9256 | 17.3568 | | 2.6228 | 2.62 | 2600 | 2.3960 | 0.9354 | 17.3248 | | 2.6228 | 2.72 | 2700 | 2.3873 | 0.9543 | 17.3961 | | 2.6228 | 2.82 | 2800 | 2.3823 | 0.93 | 17.2564 | | 2.6228 | 2.92 | 2900 | 2.3740 | 0.9701 | 17.2161 | | 2.5527 | 3.02 | 3000 | 2.3671 | 0.9669 | 17.26 | | 2.5527 | 3.12 | 3100 | 2.3583 | 0.8909 | 17.4082 | | 2.5527 | 3.23 | 3200 | 2.3555 | 0.9186 | 17.3296 | | 2.5527 | 3.33 | 3300 | 2.3508 | 0.9321 | 17.3119 | | 2.5527 | 3.43 | 3400 | 2.3459 | 0.9821 | 17.2859 | | 2.5106 | 3.53 | 3500 | 2.3410 | 0.9371 | 17.292 | | 2.5106 | 3.63 | 3600 | 2.3373 | 0.9368 | 17.2756 | | 2.5106 | 3.73 | 3700 | 2.3330 | 0.9312 | 17.295 | | 2.5106 | 3.83 | 3800 | 2.3304 | 0.9827 | 17.2847 | | 2.5106 | 3.93 | 3900 | 2.3263 | 0.9637 | 17.2867 | | 2.5138 | 4.03 | 4000 | 2.3216 | 0.9209 | 17.3356 | | 2.5138 | 4.13 | 4100 | 2.3198 | 0.9088 | 17.3548 | | 2.5138 | 4.23 | 4200 | 2.3177 | 0.9193 | 17.3401 | | 2.5138 | 4.33 | 4300 | 2.3151 | 0.937 | 17.3346 | | 2.5138 | 4.44 | 4400 | 2.3142 | 0.9396 | 17.2953 | | 2.4804 | 4.54 | 4500 | 2.3130 | 0.9446 | 17.3099 | | 2.4804 | 4.64 | 4600 | 2.3109 | 0.9449 | 17.3018 | | 2.4804 | 4.74 | 4700 | 2.3102 | 0.9363 | 17.3106 | | 2.4804 | 4.84 | 4800 | 2.3095 | 0.9306 | 17.3033 | | 2.4804 | 4.94 | 4900 | 2.3093 | 0.928 | 17.3008 | ### Framework versions - Transformers 4.38.2 - Pytorch 2.2.1+cu121 - Datasets 2.18.0 - Tokenizers 0.15.2