End of training

.gitattributes

@@ -33,3 +33,5 @@ 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
+source.spm filter=lfs diff=lfs merge=lfs -text
+target.spm filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,82 @@
+---
+library_name: transformers
+language:
+- nan
+license: apache-2.0
+base_model: Helsinki-NLP/opus-mt-en-ZH
+tags:
+- generated_from_trainer
+datasets:
+- mozilla-foundation/common_voice_12_0
+metrics:
+- bleu
+model-index:
+- name: helsinki_new_ver4
+  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. -->
+
+# helsinki_new_ver4
+
+This model is a fine-tuned version of [Helsinki-NLP/opus-mt-en-ZH](https://huggingface.co/Helsinki-NLP/opus-mt-en-ZH) on the mozilla-foundation/common_voice_12_0 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5400
+- Bleu: 2.4304
+
+## 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: 1e-06
+- train_batch_size: 8
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 1000
+- training_steps: 23000
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch   | Step  | Validation Loss | Bleu    |
+|:-------------:|:-------:|:-----:|:---------------:|:-------:|
+| 0.7027        | 0.6418  | 1000  | 0.6716          | 2.8141  |
+| 0.6767        | 1.2837  | 2000  | 0.6546          | 9.1063  |
+| 0.6526        | 1.9255  | 3000  | 0.6394          | 1.9859  |
+| 0.643         | 2.5674  | 4000  | 0.6252          | 12.4882 |
+| 0.6445        | 3.2092  | 5000  | 0.6118          | 8.8121  |
+| 0.6326        | 3.8511  | 6000  | 0.6010          | 12.7405 |
+| 0.604         | 4.4929  | 7000  | 0.5926          | 1.4845  |
+| 0.5877        | 5.1348  | 8000  | 0.5827          | 12.9972 |
+| 0.5721        | 5.7766  | 9000  | 0.5753          | 1.5982  |
+| 0.5826        | 6.4185  | 10000 | 0.5672          | 1.6842  |
+| 0.5622        | 7.0603  | 11000 | 0.5619          | 14.0609 |
+| 0.5486        | 7.7022  | 12000 | 0.5557          | 14.2992 |
+| 0.5451        | 8.3440  | 13000 | 0.5507          | 15.4044 |
+| 0.5571        | 8.9859  | 14000 | 0.5463          | 8.4964  |
+| 0.5448        | 9.6277  | 15000 | 0.5422          | 8.8203  |
+| 0.5306        | 10.2696 | 16000 | 0.5400          | 2.4304  |
+
+
+### Framework versions
+
+- Transformers 4.51.3
+- Pytorch 2.6.0+cu124
+- Datasets 3.5.1
+- Tokenizers 0.21.1

config.json

@@ -0,0 +1,58 @@
+{
+  "activation_dropout": 0.0,
+  "activation_function": "swish",
+  "add_bias_logits": false,
+  "add_final_layer_norm": false,
+  "architectures": [
+    "MarianMTModel"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "classif_dropout": 0.0,
+  "classifier_dropout": 0.0,
+  "d_model": 512,
+  "decoder_attention_heads": 8,
+  "decoder_ffn_dim": 2048,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "decoder_start_token_id": 65000,
+  "decoder_vocab_size": 65001,
+  "do_blenderbot_90_layernorm": false,
+  "dropout": 0.1,
+  "encoder_attention_heads": 8,
+  "encoder_ffn_dim": 2048,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_token_id": 0,
+  "extra_pos_embeddings": 0,
+  "force_bos_token_to_be_generated": false,
+  "forced_eos_token_id": 0,
+  "gradient_checkpointing": false,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "max_length": null,
+  "max_position_embeddings": 512,
+  "model_type": "marian",
+  "normalize_before": false,
+  "normalize_embedding": false,
+  "num_beams": null,
+  "num_hidden_layers": 6,
+  "pad_token_id": 65000,
+  "scale_embedding": true,
+  "share_encoder_decoder_embeddings": true,
+  "static_position_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "use_cache": true,
+  "vocab_size": 65001
+}

generation_config.json

@@ -0,0 +1,16 @@
+{
+  "bad_words_ids": [
+    [
+      65000
+    ]
+  ],
+  "bos_token_id": 0,
+  "decoder_start_token_id": 65000,
+  "eos_token_id": 0,
+  "forced_eos_token_id": 0,
+  "max_length": 512,
+  "num_beams": 4,
+  "pad_token_id": 65000,
+  "renormalize_logits": true,
+  "transformers_version": "4.51.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:637d59e07b49479505ad0d2a9e06cc11c5017fb883d6d08c13caec9a57f86619
+size 309965092

source.spm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5775ddc9e3ff2fae91554da56468ad35ff56edaba870fea74447bc7234bfdaa8
+size 806435

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

target.spm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81dc94efa84e4025ef38d25d5d07429fe41e3eb29d44003f1db6fe98487b0052
+size 804600

tokenizer_config.json

@@ -0,0 +1,39 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "65000": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "separate_vocabs": false,
+  "source_lang": "eng",
+  "sp_model_kwargs": {},
+  "target_lang": "zho",
+  "tokenizer_class": "MarianTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49026bd1c4726d8e98e25fd41476d5a6628447dcf16474f3753231c1244fe557
+size 5432