Model save

README.md

@@ -0,0 +1,80 @@
+---
+license: apache-2.0
+base_model: Helsinki-NLP/opus-mt-en-fr
+tags:
+- generated_from_trainer
+metrics:
+- bleu
+model-index:
+- name: opus-mt-en-fr-finetuned-en-to-fr
+  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. -->
+
+# opus-mt-en-fr-finetuned-en-to-fr
+
+This model is a fine-tuned version of [Helsinki-NLP/opus-mt-en-fr](https://huggingface.co/Helsinki-NLP/opus-mt-en-fr) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.4931
+- Bleu: 30.5787
+- Gen Len: 29.696
+
+## 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: 64
+- eval_batch_size: 64
+- seed: 42
+- 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    | Gen Len |
+|:-------------:|:-----:|:-----:|:---------------:|:-------:|:-------:|
+| 1.1697        | 1.0   | 1563  | 1.2757          | 33.5938 | 29.3857 |
+| 1.11          | 2.0   | 3126  | 1.2955          | 33.1752 | 29.5413 |
+| 1.0667        | 3.0   | 4689  | 1.3156          | 32.8594 | 29.6203 |
+| 1.0229        | 4.0   | 6252  | 1.3336          | 32.3786 | 29.5663 |
+| 0.9978        | 5.0   | 7815  | 1.3555          | 32.2937 | 29.5277 |
+| 0.9671        | 6.0   | 9378  | 1.3709          | 31.914  | 29.5797 |
+| 0.9434        | 7.0   | 10941 | 1.3889          | 31.7777 | 29.5977 |
+| 0.9238        | 8.0   | 12504 | 1.4028          | 31.6003 | 29.6357 |
+| 0.9005        | 9.0   | 14067 | 1.4189          | 31.3266 | 29.5643 |
+| 0.8862        | 10.0  | 15630 | 1.4310          | 31.0866 | 29.532  |
+| 0.864         | 11.0  | 17193 | 1.4410          | 30.9667 | 29.7047 |
+| 0.8564        | 12.0  | 18756 | 1.4514          | 30.7383 | 29.6737 |
+| 0.8389        | 13.0  | 20319 | 1.4622          | 30.7829 | 29.6223 |
+| 0.8311        | 14.0  | 21882 | 1.4674          | 30.6825 | 29.553  |
+| 0.8166        | 15.0  | 23445 | 1.4748          | 30.6912 | 29.6233 |
+| 0.8115        | 16.0  | 25008 | 1.4823          | 30.5806 | 29.7073 |
+| 0.8036        | 17.0  | 26571 | 1.4856          | 30.5507 | 29.7137 |
+| 0.8           | 18.0  | 28134 | 1.4888          | 30.5392 | 29.6727 |
+| 0.795         | 19.0  | 29697 | 1.4916          | 30.53   | 29.7203 |
+| 0.7907        | 20.0  | 31260 | 1.4931          | 30.5787 | 29.696  |
+
+
+### Framework versions
+
+- Transformers 4.32.1
+- Pytorch 1.12.1
+- Datasets 2.18.0
+- Tokenizers 0.13.2

generation_config.json

@@ -0,0 +1,16 @@
+{
+  "bad_words_ids": [
+    [
+      59513
+    ]
+  ],
+  "bos_token_id": 0,
+  "decoder_start_token_id": 59513,
+  "eos_token_id": 0,
+  "forced_eos_token_id": 0,
+  "max_length": 512,
+  "num_beams": 4,
+  "pad_token_id": 59513,
+  "renormalize_logits": true,
+  "transformers_version": "4.32.1"
+}

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fdcbb8e8fcb86a65374cb9e604658d171b5c843c340a5e22b5045caa22692d99
+oid sha256:2ade1162b2f0af5937a2fec21766cf51e2b4beef1c6b3e964708c4e1ffe6fc44
 size 298761157