Mellowpont/modelfornametranslate

README.md

@@ -0,0 +1,58 @@
+---
+license: apache-2.0
+base_model: facebook/wmt19-en-ru
+tags:
+- generated_from_trainer
+metrics:
+- bleu
+model-index:
+- name: finetuned-model
+  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. -->
+
+# 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.
+It achieves the following results on the evaluation set:
+- Loss: 4.2608
+- Bleu: 0.9992
+- Bert Score: 0.5747
+
+## 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: 32
+- eval_batch_size: 64
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.35.0
+- Pytorch 2.1.0+cu118
+- Datasets 2.14.6
+- Tokenizers 0.14.1

config.json

@@ -0,0 +1,48 @@
+{
+  "_name_or_path": "facebook/wmt19-en-ru",
+  "activation_dropout": 0.0,
+  "activation_function": "relu",
+  "architectures": [
+    "FSMTForConditionalGeneration"
+  ],
+  "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,
+  "decoder_layers": 6,
+  "decoder_start_token_id": 2,
+  "dropout": 0.2,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 8192,
+  "encoder_layerdrop": 0,
+  "encoder_layers": 6,
+  "eos_token_id": 2,
+  "forced_eos_token_id": 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,
+  "num_hidden_layers": 6,
+  "pad_token_id": 1,
+  "scale_embedding": true,
+  "src_vocab_size": 31640,
+  "tgt_vocab_size": 31232,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.0",
+  "use_cache": true
+}

generation_config.json

@@ -0,0 +1,11 @@
+{
+  "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,
+  "transformers_version": "4.35.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e62ab11859da4ef0c68732bb1c87d8613efc3043308eda8f072a674bb6223e7
+size 1172813064

runs/Nov10_14-05-50_635c2182b73f/events.out.tfevents.1699625500.635c2182b73f.3300.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48a72a5285358dfc21daafd01b0af1020d12b1d5185525b98148552166ffb488
+size 5450

runs/Nov10_14-05-50_635c2182b73f/events.out.tfevents.1699628252.635c2182b73f.3300.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ea33eaa75b4ec42c825e28ca1b085d99248aa00ef9757510fcc0634a4ed3ba6
+size 454

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,48 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": false,
+  "langs": [
+    "en",
+    "ru"
+  ],
+  "model_max_length": 1024,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "FSMTTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b04eb21bdd5579830bff016c53d18519903e1c7a797653d2838ee22dcd4e64d1
+size 4728