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 +1,77 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: Helsinki-NLP/opus-mt-en-ru
+tags:
+- translation
+- generated_from_trainer
+metrics:
+- bleu
+model-index:
+- name: tatoeba-en-tok
+  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. -->
+
+# tatoeba-en-tok
+
+This model is a fine-tuned version of [Helsinki-NLP/opus-mt-en-ru](https://huggingface.co/Helsinki-NLP/opus-mt-en-ru) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3998
+- Bleu: 53.4755
+
+## 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 with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 15
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Bleu    |
+|:-------------:|:-----:|:-----:|:---------------:|:-------:|
+| 0.8007        | 1.0   | 1191  | 0.6103          | 42.1290 |
+| 0.601         | 2.0   | 2382  | 0.5092          | 46.7946 |
+| 0.5048        | 3.0   | 3573  | 0.4695          | 48.9150 |
+| 0.4607        | 4.0   | 4764  | 0.4463          | 50.2526 |
+| 0.4291        | 5.0   | 5955  | 0.4321          | 50.9477 |
+| 0.4013        | 6.0   | 7146  | 0.4202          | 51.7015 |
+| 0.3839        | 7.0   | 8337  | 0.4154          | 52.0396 |
+| 0.3674        | 8.0   | 9528  | 0.4090          | 52.7005 |
+| 0.3518        | 9.0   | 10719 | 0.4067          | 52.6233 |
+| 0.3423        | 10.0  | 11910 | 0.4053          | 52.7858 |
+| 0.3332        | 11.0  | 13101 | 0.4016          | 53.1131 |
+| 0.3251        | 12.0  | 14292 | 0.4008          | 53.2837 |
+| 0.3202        | 13.0  | 15483 | 0.3999          | 53.4268 |
+| 0.3131        | 14.0  | 16674 | 0.4001          | 53.4309 |
+| 0.3128        | 15.0  | 17865 | 0.3998          | 53.4755 |
+
+
+### Framework versions
+
+- Transformers 4.52.4
+- Pytorch 2.7.1+cu128
+- Datasets 3.6.0
+- Tokenizers 0.21.1

config.json

@@ -0,0 +1,55 @@
+{
+  "_num_labels": 3,
+  "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": 62517,
+  "decoder_vocab_size": 62518,
+  "dropout": 0.1,
+  "encoder_attention_heads": 8,
+  "encoder_ffn_dim": 2048,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_token_id": 0,
+  "forced_eos_token_id": 0,
+  "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": 62517,
+  "scale_embedding": true,
+  "share_encoder_decoder_embeddings": true,
+  "static_position_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.52.4",
+  "use_cache": true,
+  "vocab_size": 62518
+}

generation_config.json

@@ -0,0 +1,16 @@
+{
+  "bad_words_ids": [
+    [
+      62517
+    ]
+  ],
+  "bos_token_id": 0,
+  "decoder_start_token_id": 62517,
+  "eos_token_id": 0,
+  "forced_eos_token_id": 0,
+  "max_length": 512,
+  "num_beams": 4,
+  "pad_token_id": 62517,
+  "renormalize_logits": true,
+  "transformers_version": "4.52.4"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c8164f061532b7011f9bffacf25c89ac37c4eda127a95c929f46f17dbb4ce4d
+size 304869976

source.spm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16bebef1389a0b8ab452772c4e35b9e605e5713f8ac7baa71ca701394eaa086d
+size 802781

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

target.spm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:745998e51ba5b058e38b7ac7765c25c43ed5c1c39cc92b27163b9b2e323c9d7c
+size 1080169

tokenizer_config.json

@@ -0,0 +1,40 @@
+{
+  "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
+    },
+    "62517": {
+      "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>",
+  "return_tensors": "pt",
+  "separate_vocabs": false,
+  "source_lang": "en",
+  "sp_model_kwargs": {},
+  "target_lang": "ru",
+  "tokenizer_class": "MarianTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10d104cda681b54b11291b7a92a1e270d34be12da3522bd3cc321787c8a96cea
+size 5841