Model save

README.md

@@ -1,3 +1,82 @@
----
-license: mit
----
+---
+license: apache-2.0
+base_model: google/mt5-base
+tags:
+- generated_from_trainer
+metrics:
+- bleu
+model-index:
+- name: mt5-base-ainu
+  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. -->
+
+# mt5-base-ainu
+
+This model is a fine-tuned version of [google/mt5-base](https://huggingface.co/google/mt5-base) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.3022
+- Bleu: 35.9207
+- Chrf: 49.0639
+
+## 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: 0.0006
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 20
+
+### Training results
+
+| Training Loss | Epoch | Step   | Validation Loss | Bleu    | Chrf    |
+|:-------------:|:-----:|:------:|:---------------:|:-------:|:-------:|
+| 1.8747        | 1.0   | 9340   | 1.6606          | 23.2627 | 36.3985 |
+| 1.5561        | 2.0   | 18680  | 1.4484          | 27.8577 | 41.4160 |
+| 1.342         | 3.0   | 28020  | 1.3617          | 30.0171 | 43.7024 |
+| 1.189         | 4.0   | 37360  | 1.3196          | 31.6813 | 44.9223 |
+| 1.0639        | 5.0   | 46700  | 1.3125          | 32.2320 | 45.8694 |
+| 0.9555        | 6.0   | 56040  | 1.3191          | 32.9369 | 46.5324 |
+| 0.8687        | 7.0   | 65380  | 1.3418          | 33.8700 | 47.1238 |
+| 0.7725        | 8.0   | 74720  | 1.3792          | 34.0996 | 47.5675 |
+| 0.6913        | 9.0   | 84060  | 1.4118          | 34.0199 | 47.5628 |
+| 0.6156        | 10.0  | 93400  | 1.4761          | 34.5528 | 47.9750 |
+| 0.5368        | 11.0  | 102740 | 1.5256          | 34.8295 | 48.1106 |
+| 0.4769        | 12.0  | 112080 | 1.6086          | 35.1019 | 48.2665 |
+| 0.4132        | 13.0  | 121420 | 1.6682          | 35.1258 | 48.3908 |
+| 0.3653        | 14.0  | 130760 | 1.7393          | 35.1325 | 48.4715 |
+| 0.3196        | 15.0  | 140100 | 1.8277          | 35.2792 | 48.5062 |
+| 0.2698        | 16.0  | 149440 | 1.9076          | 35.3726 | 48.6938 |
+| 0.2335        | 17.0  | 158780 | 1.9845          | 35.5334 | 48.7919 |
+| 0.2025        | 18.0  | 168120 | 2.1150          | 35.6067 | 48.8451 |
+| 0.1709        | 19.0  | 177460 | 2.2327          | 35.7527 | 48.9483 |
+| 0.1497        | 20.0  | 186800 | 2.3022          | 35.9207 | 49.0639 |
+
+
+### Framework versions
+
+- Transformers 4.40.1
+- Pytorch 2.1.2
+- Datasets 2.19.0
+- 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": "4.40.1"
+}