Model save

.gitattributes

@@ -33,3 +33,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+onnx/source.spm filter=lfs diff=lfs merge=lfs -text
+onnx/target.spm filter=lfs diff=lfs merge=lfs -text
+source.spm filter=lfs diff=lfs merge=lfs -text
+target.spm filter=lfs diff=lfs merge=lfs -text

README.md

@@ -19,7 +19,7 @@ should probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [Helsinki-NLP/opus-mt-en-zh](https://huggingface.co/Helsinki-NLP/opus-mt-en-zh) on an unknown dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.0676
-- Bleu: 52.9985
+- Bleu: 59.6078
 
 ## Model description
 
@@ -52,31 +52,31 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Bleu    |
 |:-------------:|:-----:|:----:|:---------------:|:-------:|
-| 3.8048        | 1.0   | 63   | 0.1344          | 30.3088 |
-| 0.1753        | 2.0   | 126  | 0.0924          | 41.8687 |
-| 0.1159        | 3.0   | 189  | 0.0793          | 45.7034 |
-| 0.0683        | 4.0   | 252  | 0.0732          | 46.9496 |
-| 0.0518        | 5.0   | 315  | 0.0700          | 47.2102 |
-| 0.0436        | 6.0   | 378  | 0.0683          | 48.4953 |
-| 0.0377        | 7.0   | 441  | 0.0674          | 51.1274 |
-| 0.0273        | 8.0   | 504  | 0.0672          | 50.7599 |
-| 0.023         | 9.0   | 567  | 0.0670          | 51.9705 |
-| 0.0205        | 10.0  | 630  | 0.0671          | 52.3494 |
-| 0.0184        | 11.0  | 693  | 0.0668          | 52.7685 |
-| 0.0148        | 12.0  | 756  | 0.0669          | 53.2385 |
-| 0.0135        | 13.0  | 819  | 0.0673          | 52.1619 |
-| 0.0127        | 14.0  | 882  | 0.0673          | 52.4433 |
-| 0.0121        | 15.0  | 945  | 0.0671          | 52.4996 |
-| 0.0111        | 16.0  | 1008 | 0.0675          | 52.9848 |
-| 0.0104        | 17.0  | 1071 | 0.0675          | 52.6471 |
-| 0.0104        | 18.0  | 1134 | 0.0675          | 52.9092 |
-| 0.0104        | 19.0  | 1197 | 0.0676          | 53.0038 |
-| 0.0104        | 20.0  | 1260 | 0.0676          | 52.9985 |
+| 3.7911        | 1.0   | 63   | 0.1364          | 34.1462 |
+| 0.1769        | 2.0   | 126  | 0.0934          | 47.3847 |
+| 0.1169        | 3.0   | 189  | 0.0795          | 51.7291 |
+| 0.0696        | 4.0   | 252  | 0.0738          | 53.0698 |
+| 0.0528        | 5.0   | 315  | 0.0705          | 53.5829 |
+| 0.0445        | 6.0   | 378  | 0.0685          | 55.7554 |
+| 0.0382        | 7.0   | 441  | 0.0670          | 51.6892 |
+| 0.0275        | 8.0   | 504  | 0.0669          | 51.6109 |
+| 0.0235        | 9.0   | 567  | 0.0666          | 58.3831 |
+| 0.021         | 10.0  | 630  | 0.0667          | 57.9035 |
+| 0.0187        | 11.0  | 693  | 0.0666          | 59.5633 |
+| 0.0152        | 12.0  | 756  | 0.0668          | 59.4942 |
+| 0.0138        | 13.0  | 819  | 0.0670          | 59.9181 |
+| 0.0131        | 14.0  | 882  | 0.0674          | 59.6031 |
+| 0.0121        | 15.0  | 945  | 0.0671          | 60.1665 |
+| 0.0114        | 16.0  | 1008 | 0.0675          | 60.2263 |
+| 0.0106        | 17.0  | 1071 | 0.0675          | 59.9121 |
+| 0.0106        | 18.0  | 1134 | 0.0675          | 59.5278 |
+| 0.0105        | 19.0  | 1197 | 0.0676          | 59.5678 |
+| 0.0105        | 20.0  | 1260 | 0.0676          | 59.6078 |
 
 
 ### Framework versions
 
-- Transformers 4.46.3
-- Pytorch 2.5.1+cu121
+- Transformers 4.48.2
+- Pytorch 2.5.1+cu124
 - Datasets 3.2.0
-- Tokenizers 0.20.3
+- Tokenizers 0.21.0

config.json

@@ -53,7 +53,7 @@
   "share_encoder_decoder_embeddings": true,
   "static_position_embeddings": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.46.3",
+  "transformers_version": "4.48.2",
   "use_cache": true,
   "vocab_size": 65001
 }

generation_config.json

@@ -12,5 +12,5 @@
   "num_beams": 4,
   "pad_token_id": 65000,
   "renormalize_logits": true,
-  "transformers_version": "4.46.3"
+  "transformers_version": "4.48.2"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8e8dbca275191f067d2e528f79d277e7881c541035be84d84a353bf5cc8e115
+oid sha256:33d0424d199048d8f14ac0063408c6d645d603db95592d83da34443f1f86a2db
 size 309965092

onnx/decoder_model_merged.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25d617db878eb1faceed29c40c9668dfa0e3e9366e59ac890787158567dc5541
+oid sha256:679bc1fee8aec3e8340455727fdd71dab3b36d4b4e75b7a8781c85f93549d7e1
 size 235876901

onnx/decoder_model_merged_quantized.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db1f9f38fd402d9b5669cff76762a63a55a9cd86a6c7f7db73d269f49330387f
+oid sha256:ab014bee7f097174c9b9835c93ba2911e2866f4b853b6920f7158c94610713ac
 size 60180860

onnx/encoder_model.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4351ecc3769a683117ab95332f389002ecedc0ba0ecb95525a1a442aacd8811
+oid sha256:c0b866371fb45630d545fb9570bc8145e1f96c73d6b7f7098e57531dc98d5d1e
 size 209948474

onnx/encoder_model_quantized.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d308a8f1bb3010e951fe773fb884fa3a31fc2461e39413435a39942ff66c7bea
+oid sha256:1b617bbee0b77993aa49bfaac00f1b6c1b58428374f37eb20ac32db1a6d09177
 size 52802331

tokenizer_config.json

@@ -27,6 +27,7 @@
   },
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
+  "extra_special_tokens": {},
   "model_max_length": 512,
   "pad_token": "<pad>",
   "separate_vocabs": false,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28c715ccf566f1de094ea30d760a5ba49916fee950cccfd41056063c6f5b4f41
+oid sha256:8bc4a55f71ff4804e333a7576d29bac8d1c1f804070e8efddb7ae4a76e1c9088
 size 5496