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 +1,91 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: Helsinki-NLP/opus-mt-en-ru
+tags:
+- generated_from_trainer
+metrics:
+- bleu
+model-index:
+- name: 68174dedb48e8aee3dbe7e2e374444f6
+  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. -->
+
+# 68174dedb48e8aee3dbe7e2e374444f6
+
+This model is a fine-tuned version of [Helsinki-NLP/opus-mt-en-ru](https://huggingface.co/Helsinki-NLP/opus-mt-en-ru) on the Helsinki-NLP/opus_books [fr-no] dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.7788
+- Data Size: 1.0
+- Epoch Runtime: 6.5770
+- Bleu: 1.8779
+
+## 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: 5e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- total_train_batch_size: 32
+- total_eval_batch_size: 32
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: constant
+- num_epochs: 50
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Data Size | Epoch Runtime | Bleu   |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:-------------:|:------:|
+| No log        | 0     | 0    | 8.1576          | 0         | 1.1298        | 0.0120 |
+| No log        | 1     | 86   | 7.2886          | 0.0078    | 1.6048        | 0.0364 |
+| No log        | 2     | 172  | 6.6430          | 0.0156    | 1.4120        | 0.0139 |
+| No log        | 3     | 258  | 6.1895          | 0.0312    | 1.6749        | 0.0290 |
+| No log        | 4     | 344  | 5.5434          | 0.0625    | 1.9136        | 0.0593 |
+| 0.3187        | 5     | 430  | 4.9139          | 0.125     | 2.3661        | 0.1100 |
+| 1.2067        | 6     | 516  | 4.2736          | 0.25      | 3.0119        | 0.1236 |
+| 1.5018        | 7     | 602  | 3.7627          | 0.5       | 3.9584        | 0.3964 |
+| 2.1437        | 8.0   | 688  | 3.3846          | 1.0       | 6.2046        | 0.7190 |
+| 3.339         | 9.0   | 774  | 3.1913          | 1.0       | 5.9831        | 0.8692 |
+| 3.1252        | 10.0  | 860  | 3.0527          | 1.0       | 6.0412        | 1.2043 |
+| 3.0013        | 11.0  | 946  | 2.9586          | 1.0       | 5.9485        | 1.1741 |
+| 2.798         | 12.0  | 1032 | 2.8913          | 1.0       | 6.2445        | 1.3138 |
+| 2.6842        | 13.0  | 1118 | 2.8311          | 1.0       | 6.0278        | 1.3558 |
+| 2.56          | 14.0  | 1204 | 2.7889          | 1.0       | 6.3031        | 1.5464 |
+| 2.4526        | 15.0  | 1290 | 2.7657          | 1.0       | 6.1649        | 1.5456 |
+| 2.3505        | 16.0  | 1376 | 2.7463          | 1.0       | 6.1921        | 1.3818 |
+| 2.2636        | 17.0  | 1462 | 2.7351          | 1.0       | 6.1744        | 1.5696 |
+| 2.1563        | 18.0  | 1548 | 2.7299          | 1.0       | 6.4085        | 1.7799 |
+| 2.0449        | 19.0  | 1634 | 2.7390          | 1.0       | 6.0078        | 1.7635 |
+| 1.9794        | 20.0  | 1720 | 2.7285          | 1.0       | 6.2261        | 1.7834 |
+| 1.9045        | 21.0  | 1806 | 2.7564          | 1.0       | 6.2097        | 1.6870 |
+| 1.8111        | 22.0  | 1892 | 2.7386          | 1.0       | 6.1472        | 1.8704 |
+| 1.7096        | 23.0  | 1978 | 2.7728          | 1.0       | 6.1480        | 1.8485 |
+| 1.6496        | 24.0  | 2064 | 2.7788          | 1.0       | 6.5770        | 1.8779 |
+
+
+### Framework versions
+
+- Transformers 4.57.0
+- Pytorch 2.8.0+cu128
+- Datasets 4.2.0
+- Tokenizers 0.22.1

config.json

@@ -0,0 +1,54 @@
+{
+  "_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,
+  "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,
+  "dtype": "float32",
+  "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,
+  "transformers_version": "4.57.0",
+  "use_cache": true,
+  "vocab_size": 62518
+}

generation_config.json

@@ -0,0 +1,17 @@
+{
+  "bad_words_ids": [
+    [
+      62517
+    ]
+  ],
+  "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": "4.57.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cddce658cb73e2ef87d0f74bbd2f931fa7ccd3aafed866f3c901a80b0887089a
+size 688981208

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 +1,39 @@
+{
+  "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
+    },
+    "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>",
+  "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 sha256:1708855b3cacc28d057f2eb26921357807cb17c5be5e74552a7229b3acbba265
+size 6097