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 +1,64 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: Helsinki-NLP/opus-mt-tc-bible-big-mul-mul
+tags:
+- generated_from_trainer
+model-index:
+- name: opus-ph-ph
+  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-ph-ph
+
+This model is a fine-tuned version of [Helsinki-NLP/opus-mt-tc-bible-big-mul-mul](https://huggingface.co/Helsinki-NLP/opus-mt-tc-bible-big-mul-mul) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.6708
+- Bleu Global: 27.6541
+- Gen Len: 7.4658
+
+## 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: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 10
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Bleu Global | Gen Len |
+|:-------------:|:-----:|:----:|:---------------:|:-----------:|:-------:|
+| 0.1176        | 1.0   | 634  | 2.3737          | 27.2355     | 7.6117  |
+| 0.1024        | 2.0   | 1268 | 2.4315          | 28.4868     | 7.5173  |
+| 0.0788        | 3.0   | 1902 | 2.5622          | 28.2414     | 7.5385  |
+| 0.0438        | 4.0   | 2536 | 2.6708          | 27.6541     | 7.4658  |
+
+
+### Framework versions
+
+- Transformers 4.56.1
+- Pytorch 2.8.0+cu126
+- Datasets 4.0.0
+- Tokenizers 0.22.0

config.json

@@ -0,0 +1,39 @@
+{
+  "activation_dropout": 0.0,
+  "activation_function": "relu",
+  "architectures": [
+    "MarianMTModel"
+  ],
+  "attention_dropout": 0.0,
+  "classifier_dropout": 0.0,
+  "d_model": 1024,
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 4096,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "decoder_start_token_id": 69666,
+  "decoder_vocab_size": 69667,
+  "dropout": 0.1,
+  "dtype": "float32",
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_token_id": 524,
+  "forced_eos_token_id": null,
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "max_length": null,
+  "max_position_embeddings": 1024,
+  "model_type": "marian",
+  "normalize_embedding": false,
+  "num_beams": null,
+  "num_hidden_layers": 6,
+  "pad_token_id": 69666,
+  "scale_embedding": true,
+  "share_encoder_decoder_embeddings": true,
+  "static_position_embeddings": true,
+  "transformers_version": "4.56.1",
+  "use_cache": true,
+  "vocab_size": 69667
+}

generation_config.json

@@ -0,0 +1,16 @@
+{
+  "bad_words_ids": [
+    [
+      69666
+    ]
+  ],
+  "decoder_start_token_id": 69666,
+  "eos_token_id": [
+    524
+  ],
+  "forced_eos_token_id": 524,
+  "max_length": 512,
+  "num_beams": 4,
+  "pad_token_id": 69666,
+  "transformers_version": "4.56.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4587f881002bf9704af60bae1467de3100917b4f757abc524876af48b21b0ba3
+size 991093820

source.spm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fcc8ca830e320086a44a4e9a1e611e1de4ac6e229fdd8fde8aaf5651c6fbdec
+size 1315532

special_tokens_map.json

@@ -0,0 +1,14 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": ">>mdh<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

target.spm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fcc8ca830e320086a44a4e9a1e611e1de4ac6e229fdd8fde8aaf5651c6fbdec
+size 1315532

tokenizer_config.json

@@ -0,0 +1,50 @@
+{
+  "added_tokens_decoder": {
+    "524": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "783": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3677": {
+      "content": ">>mdh<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "69666": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    ">>mdh<<"
+  ],
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "separate_vocabs": false,
+  "source_lang": "mul",
+  "sp_model_kwargs": {},
+  "target_lang": "mul",
+  "tokenizer_class": "MarianTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71f24cbe3c62a056ecad4d78bd478274b807f5e6f66b6a39252acf304adf961a
+size 5905