kazparc_en_ru_marian_1

.gitattributes

@@ -33,3 +33,4 @@ 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
+target.spm filter=lfs diff=lfs merge=lfs -text

README.md

@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 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: 0.0291
+- Loss: 0.0186
 
 ## Model description
 
@@ -39,8 +39,6 @@ The following hyperparameters were used during training:
 - train_batch_size: 8
 - eval_batch_size: 16
 - seed: 42
-- gradient_accumulation_steps: 4
-- total_train_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: linear
 - num_epochs: 2
@@ -48,15 +46,15 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch  | Step | Validation Loss |
-|:-------------:|:------:|:----:|:---------------:|
-| 0.0337        | 0.9997 | 2825 | 0.0295          |
-| 0.0298        | 1.9995 | 5650 | 0.0291          |
+| Training Loss | Epoch | Step  | Validation Loss |
+|:-------------:|:-----:|:-----:|:---------------:|
+| 0.0225        | 1.0   | 9492  | 0.0195          |
+| 0.0168        | 2.0   | 18984 | 0.0186          |
 
 
 ### Framework versions
 
-- Transformers 4.46.2
+- Transformers 4.46.3
 - Pytorch 2.5.1+cu121
 - Datasets 3.1.0
 - Tokenizers 0.20.3

config.json

@@ -50,7 +50,7 @@
   "share_encoder_decoder_embeddings": true,
   "static_position_embeddings": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.46.2",
+  "transformers_version": "4.46.3",
   "use_cache": true,
   "vocab_size": 62518
 }

generation_config.json

@@ -12,5 +12,5 @@
   "num_beams": 4,
   "pad_token_id": 62517,
   "renormalize_logits": true,
-  "transformers_version": "4.46.2"
+  "transformers_version": "4.46.3"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2cfaba5e03c22043d16c99710ab693e7ae4ff4c4519214f3ad07c9aab08519b4
+oid sha256:9c926993dbf175ecbed64967eeb8ebdda0ab4b0b5a00f3517aa5162c5d732d74
 size 304869976

runs/Dec08_16-57-00_7a753c7f4b43/events.out.tfevents.1733677025.7a753c7f4b43.1232.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1cf8000441574f931f93149222f6be81e311c7c5aa17f606e96115168ed4ab86
+size 6642

runs/Dec08_17-53-57_7a753c7f4b43/events.out.tfevents.1733680438.7a753c7f4b43.15243.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:422568d38e251c6d6242850be1ee17726fe1d22a9b5593146aeb96790e61e18d
+size 6009

runs/Dec08_18-13-25_7a753c7f4b43/events.out.tfevents.1733681605.7a753c7f4b43.15243.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a3725736e3d409627591ede5eb772cece47324f80b04c0c529e62abc0bd3fe3
+size 14474

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 +1,38 @@
+{
+  "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>",
+  "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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:058e005e81412ac409705b6301157a8a782eca6ebb95da81764b6794e0d1e0e1
-size 5240
+oid sha256:9cd18280c85830717bb00f953cec4950d613df18648140b2943263fc287ff3b9
+size 5304