Training complete

README.md

@@ -0,0 +1,92 @@
+---
+license: apache-2.0
+base_model: google-t5/t5-small
+tags:
+- translation
+- generated_from_trainer
+metrics:
+- bleu
+model-index:
+- name: t5-small-finetuned-english-to-hausa
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# t5-small-finetuned-english-to-hausa
+
+This model is a fine-tuned version of [google-t5/t5-small](https://huggingface.co/google-t5/t5-small) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.9789
+- Bleu: 26.7998
+- Gen Len: 14.732
+
+## 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: 30
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Bleu    | Gen Len |
+|:-------------:|:-----:|:-----:|:---------------:|:-------:|:-------:|
+| 3.2669        | 1.0   | 1497  | 2.5511          | 0.5792  | 17.0373 |
+| 2.6176        | 2.0   | 2994  | 2.1280          | 2.8948  | 15.7297 |
+| 2.2969        | 3.0   | 4491  | 1.8747          | 5.9112  | 15.356  |
+| 2.0747        | 4.0   | 5988  | 1.6995          | 8.9433  | 15.1953 |
+| 1.9119        | 5.0   | 7485  | 1.5705          | 11.4531 | 15.1271 |
+| 1.7829        | 6.0   | 8982  | 1.4784          | 13.6106 | 14.8861 |
+| 1.6811        | 7.0   | 10479 | 1.3997          | 15.2789 | 14.9873 |
+| 1.6227        | 8.0   | 11976 | 1.3385          | 16.6919 | 14.9495 |
+| 1.5424        | 9.0   | 13473 | 1.2955          | 18.2538 | 14.786  |
+| 1.4964        | 10.0  | 14970 | 1.2492          | 19.328  | 14.9093 |
+| 1.441         | 11.0  | 16467 | 1.2104          | 20.1677 | 14.9034 |
+| 1.396         | 12.0  | 17964 | 1.1784          | 21.2916 | 15.0312 |
+| 1.3596        | 13.0  | 19461 | 1.1498          | 21.7787 | 14.84   |
+| 1.3364        | 14.0  | 20958 | 1.1255          | 22.5973 | 14.8233 |
+| 1.2971        | 15.0  | 22455 | 1.1044          | 23.0769 | 14.8186 |
+| 1.2657        | 16.0  | 23952 | 1.0858          | 23.6644 | 14.7918 |
+| 1.2573        | 17.0  | 25449 | 1.0718          | 24.3479 | 14.7274 |
+| 1.2421        | 18.0  | 26946 | 1.0536          | 24.8945 | 14.7964 |
+| 1.2192        | 19.0  | 28443 | 1.0415          | 25.0471 | 14.7531 |
+| 1.2196        | 20.0  | 29940 | 1.0278          | 25.4159 | 14.8381 |
+| 1.1853        | 21.0  | 31437 | 1.0194          | 25.5894 | 14.7703 |
+| 1.1863        | 22.0  | 32934 | 1.0119          | 25.9677 | 14.6953 |
+| 1.1765        | 23.0  | 34431 | 1.0007          | 26.1163 | 14.7952 |
+| 1.1631        | 24.0  | 35928 | 0.9963          | 26.223  | 14.7399 |
+| 1.1578        | 25.0  | 37425 | 0.9916          | 26.3776 | 14.6981 |
+| 1.1416        | 26.0  | 38922 | 0.9859          | 26.5215 | 14.7603 |
+| 1.1411        | 27.0  | 40419 | 0.9842          | 26.7362 | 14.7282 |
+| 1.1327        | 28.0  | 41916 | 0.9808          | 26.8666 | 14.7357 |
+| 1.1194        | 29.0  | 43413 | 0.9801          | 26.839  | 14.7264 |
+| 1.1229        | 30.0  | 44910 | 0.9789          | 26.7998 | 14.732  |
+
+
+### Framework versions
+
+- Transformers 4.44.0
+- Pytorch 2.3.1+cu121
+- Datasets 2.21.0
+- Tokenizers 0.19.1

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.44.0"
+}

runs/Aug16_06-47-17_c3a1acc19acb/events.out.tfevents.1723790839.c3a1acc19acb.177.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3926f19242a20bf839c4dbe05169007d0698bee3db04654c3e2746215169bf1b
-size 35824
+oid sha256:a832fc66731896ec35b2ff6d6950cfb194d9129a85f5a84332378ea00ed5a66d
+size 36561