first execution

.gitattributes

@@ -25,3 +25,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zstandard filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+*.spm filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,32 +1,62 @@
 ---
-tags:
-- translation
 license: apache-2.0
+tags:
+- generated_from_trainer
+metrics:
+- bleu
+model-index:
+- name: opus-mt-en-ru-finetuned
+  results: []
 ---
 
-### opus-mt-en-ru
+<!-- 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-mt-en-ru-finetuned
+
+This model is a fine-tuned version of [kazandaev/opus-mt-en-ru-finetuned](https://huggingface.co/kazandaev/opus-mt-en-ru-finetuned) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.0442
+- Bleu: 32.1889
+- Gen Len: 29.6331
+
+## 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: 0.0001
+- train_batch_size: 49
+- eval_batch_size: 24
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3
 
-* source languages: en
-* target languages: ru
-*  OPUS readme: [en-ru](https://github.com/Helsinki-NLP/OPUS-MT-train/blob/master/models/en-ru/README.md)
+### Training results
 
-*  dataset: opus
-* model: transformer-align
-* pre-processing: normalization + SentencePiece
-* download original weights: [opus-2020-02-11.zip](https://object.pouta.csc.fi/OPUS-MT-models/en-ru/opus-2020-02-11.zip)
-* test set translations: [opus-2020-02-11.test.txt](https://object.pouta.csc.fi/OPUS-MT-models/en-ru/opus-2020-02-11.test.txt)
-* test set scores: [opus-2020-02-11.eval.txt](https://object.pouta.csc.fi/OPUS-MT-models/en-ru/opus-2020-02-11.eval.txt)
+| Training Loss | Epoch | Step   | Validation Loss | Bleu    | Gen Len |
+|:-------------:|:-----:|:------:|:---------------:|:-------:|:-------:|
+| 1.346         | 1.0   | 35147  | 1.2394          | 28.3953 | 29.3971 |
+| 1.2061        | 2.0   | 70294  | 1.1150          | 30.8643 | 29.6302 |
+| 1.0891        | 3.0   | 105441 | 1.0442          | 32.1889 | 29.6331 |
 
-## Benchmarks
 
-| testset               | BLEU  | chr-F |
-|-----------------------|-------|-------|
-| newstest2012.en.ru 	| 31.1 	| 0.581 |
-| newstest2013.en.ru 	| 23.5 	| 0.513 |
-| newstest2015-enru.en.ru 	| 27.5 	| 0.564 |
-| newstest2016-enru.en.ru 	| 26.4 	| 0.548 |
-| newstest2017-enru.en.ru 	| 29.1 	| 0.572 |
-| newstest2018-enru.en.ru 	| 25.4 	| 0.554 |
-| newstest2019-enru.en.ru 	| 27.1 	| 0.533 |
-| Tatoeba.en.ru 	| 48.4 	| 0.669 |
+### Framework versions
 
+- Transformers 4.16.2
+- Pytorch 1.10.0+cu111
+- Datasets 1.18.3
+- Tokenizers 0.11.0

config.json

@@ -1,4 +1,5 @@
 {
+  "_name_or_path": "kazandaev/opus-mt-en-ru-finetuned",
   "_num_labels": 3,
   "activation_dropout": 0.0,
   "activation_function": "swish",
@@ -15,6 +16,7 @@
   ],
   "bos_token_id": 0,
   "classif_dropout": 0.0,
+  "classifier_dropout": 0.0,
   "d_model": 512,
   "decoder_attention_heads": 8,
   "decoder_ffn_dim": 2048,
@@ -27,6 +29,7 @@
   "encoder_layerdrop": 0.0,
   "encoder_layers": 6,
   "eos_token_id": 0,
+  "forced_eos_token_id": 0,
   "id2label": {
     "0": "LABEL_0",
     "1": "LABEL_1",
@@ -49,5 +52,8 @@
   "pad_token_id": 62517,
   "scale_embedding": true,
   "static_position_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.16.2",
+  "use_cache": true,
   "vocab_size": 62518
-}
+}

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d15fa58c6bc3efd3629c1b6b86d9aa6d15d2751a4620aa4cdd7eed7b5cbe583b
-size 306991893
+oid sha256:04a34a88460093340bc0fe832b0551b0a9076df5c71a5305486cfa629b07dc78
+size 304935301

runs/Feb22_18-58-37_22d008391efc/1645557026.79138/events.out.tfevents.1645557026.22d008391efc.125.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:224edd778c06ded1fea8a3fb5933a516a3ed7187173aa3eb7dfbc4fac3bb5966
+size 5040

runs/Feb22_18-58-37_22d008391efc/events.out.tfevents.1645556822.22d008391efc.125.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c06040d2aebac088f396ba016775c518d58e93d87609f2135fba7b2445bb52a9
+size 39427

special_tokens_map.json

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

tokenizer_config.json

@@ -1 +1 @@
-{"target_lang": "ru", "source_lang": "en"}
+{"source_lang": "en", "target_lang": "ru", "unk_token": "<unk>", "eos_token": "</s>", "pad_token": "<pad>", "model_max_length": 512, "sp_model_kwargs": {}, "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "kazandaev/opus-mt-en-ru-finetuned", "tokenizer_class": "MarianTokenizer"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a9ba672e106773190f00ca940461221e5097283d86cb81cb1da57b567e78b65
+size 3183