Mellowpont/modelfornametranslate

.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

@@ -1,6 +1,6 @@
 ---
 license: apache-2.0
-base_model: facebook/wmt19-en-ru
+base_model: Helsinki-NLP/opus-mt-en-ru
 tags:
 - generated_from_trainer
 metrics:
@@ -15,11 +15,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 # finetuned-model
 
-This model is a fine-tuned version of [facebook/wmt19-en-ru](https://huggingface.co/facebook/wmt19-en-ru) on an unknown dataset.
+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: 4.2608
-- Bleu: 0.9992
-- Bert Score: 0.5747
+- Loss: 0.3868
+- Bleu: 0.0
+- Bert Score: 0.9776
 
 ## Model description
 

config.json

@@ -1,48 +1,61 @@
 {
-  "_name_or_path": "facebook/wmt19-en-ru",
+  "_name_or_path": "Helsinki-NLP/opus-mt-en-ru",
+  "_num_labels": 3,
   "activation_dropout": 0.0,
-  "activation_function": "relu",
+  "activation_function": "swish",
+  "add_bias_logits": false,
+  "add_final_layer_norm": false,
   "architectures": [
-    "FSMTForConditionalGeneration"
+    "MarianMTModel"
+  ],
+  "attention_dropout": 0.0,
+  "bad_words_ids": [
+    [
+      62517
+    ]
   ],
-  "attention_dropout": 0.1,
   "bos_token_id": 0,
-  "d_model": 1024,
-  "decoder": {
-    "bos_token_id": 2,
-    "model_type": "fsmt_decoder",
-    "vocab_size": 31232
-  },
-  "decoder_attention_heads": 16,
-  "decoder_ffn_dim": 4096,
-  "decoder_layerdrop": 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": 2,
-  "dropout": 0.2,
-  "encoder_attention_heads": 16,
-  "encoder_ffn_dim": 8192,
-  "encoder_layerdrop": 0,
+  "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": 2,
-  "forced_eos_token_id": 2,
+  "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,
-  "langs": [
-    "en",
-    "ru"
-  ],
-  "length_penalty": 1.15,
-  "max_length": 200,
-  "max_position_embeddings": 1024,
-  "model_type": "fsmt",
-  "num_beams": 5,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "max_length": 512,
+  "max_position_embeddings": 512,
+  "model_type": "marian",
+  "normalize_before": false,
+  "normalize_embedding": false,
+  "num_beams": 4,
   "num_hidden_layers": 6,
-  "pad_token_id": 1,
+  "pad_token_id": 62517,
   "scale_embedding": true,
-  "src_vocab_size": 31640,
-  "tgt_vocab_size": 31232,
-  "tie_word_embeddings": false,
+  "share_encoder_decoder_embeddings": true,
+  "static_position_embeddings": true,
   "torch_dtype": "float32",
   "transformers_version": "4.35.0",
-  "use_cache": true
+  "use_cache": true,
+  "vocab_size": 62518
 }

generation_config.json

@@ -1,11 +1,16 @@
 {
+  "bad_words_ids": [
+    [
+      62517
+    ]
+  ],
   "bos_token_id": 0,
-  "decoder_start_token_id": 2,
-  "eos_token_id": 2,
-  "forced_eos_token_id": 2,
-  "length_penalty": 1.15,
-  "max_length": 200,
-  "num_beams": 5,
-  "pad_token_id": 1,
+  "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": "4.35.0"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e62ab11859da4ef0c68732bb1c87d8613efc3043308eda8f072a674bb6223e7
-size 1172813064
+oid sha256:ca3f19df3b3fc66e0f3caba08339c64f11278efe7ccb8cdc43b4342ef0cb4272
+size 304869976

runs/Nov10_15-52-35_635c2182b73f/events.out.tfevents.1699631761.635c2182b73f.29220.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:729389adbf7e3b3752624ab18fbec7a30bebbeefc38bf212f13f99993f44f480
+size 5739

runs/Nov10_15-52-35_635c2182b73f/events.out.tfevents.1699632432.635c2182b73f.29220.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:516a6124801c15b3065ad539f8bb8edeb2a1edf05d62952581e8137d5d39afed
+size 454

special_tokens_map.json

@@ -1,6 +1,5 @@
 {
-  "bos_token": "<s>",
+  "eos_token": "</s>",
   "pad_token": "<pad>",
-  "sep_token": "</s>",
   "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

@@ -1,7 +1,7 @@
 {
   "added_tokens_decoder": {
     "0": {
-      "content": "<s>",
+      "content": "</s>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -9,23 +9,15 @@
       "special": true
     },
     "1": {
-      "content": "<pad>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "2": {
-      "content": "</s>",
+      "content": "<unk>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "3": {
-      "content": "<unk>",
+    "62517": {
+      "content": "<pad>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -33,16 +25,14 @@
       "special": true
     }
   },
-  "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
-  "do_lower_case": false,
-  "langs": [
-    "en",
-    "ru"
-  ],
-  "model_max_length": 1024,
+  "eos_token": "</s>",
+  "model_max_length": 512,
   "pad_token": "<pad>",
-  "sep_token": "</s>",
-  "tokenizer_class": "FSMTTokenizer",
+  "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:b04eb21bdd5579830bff016c53d18519903e1c7a797653d2838ee22dcd4e64d1
+oid sha256:3328d9d5315b3058b393854b48cc0e6b3f78f8f8866e4a3be1b757583e501f45
 size 4728