add model

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

README.md

@@ -0,0 +1,72 @@
+---
+tags:
+- generated_from_trainer
+datasets:
+- wmt16
+metrics:
+- bleu
+model_index:
+- name: opus-mt-en-ro-finetuned-en-to-ro
+  results:
+  - task:
+      name: Sequence-to-sequence Language Modeling
+      type: text2text-generation
+    dataset:
+      name: wmt16
+      type: wmt16
+      args: ro-en
+    metric:
+      name: Bleu
+      type: bleu
+      value: 28.1641
+---
+
+<!-- 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-ro-finetuned-en-to-ro
+
+This model is a fine-tuned version of [Helsinki-NLP/opus-mt-en-ro](https://huggingface.co/Helsinki-NLP/opus-mt-en-ro) on the wmt16 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.2886
+- Bleu: 28.1641
+- Gen Len: 34.1071
+
+## 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: 16
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Bleu    | Gen Len |
+|:-------------:|:-----:|:-----:|:---------------:|:-------:|:-------:|
+| 0.7436        | 1.0   | 38145 | 1.2886          | 28.1641 | 34.1071 |
+
+
+### Framework versions
+
+- Transformers 4.9.1
+- Pytorch 1.9.0+cu102
+- Datasets 1.10.2
+- Tokenizers 0.10.3

config.json

@@ -0,0 +1,60 @@
+{
+  "_name_or_path": "Helsinki-NLP/opus-mt-en-ro",
+  "_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,
+  "bad_words_ids": [
+    [
+      59542
+    ]
+  ],
+  "bos_token_id": 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": 59542,
+  "dropout": 0.1,
+  "encoder_attention_heads": 8,
+  "encoder_ffn_dim": 2048,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_token_id": 0,
+  "forced_eos_token_id": 0,
+  "gradient_checkpointing": false,
+  "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": 512,
+  "max_position_embeddings": 512,
+  "model_type": "marian",
+  "normalize_before": false,
+  "normalize_embedding": false,
+  "num_beams": 4,
+  "num_hidden_layers": 6,
+  "pad_token_id": 59542,
+  "scale_embedding": true,
+  "static_position_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.9.1",
+  "use_cache": true,
+  "vocab_size": 59543
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1bee95f1226caf47e323fdf054cba4b6ab1d52a608ca510f09a06dfc95b3bde4
+size 298820677

runs/Jul27_03-16-02_baadd1eee5cb/1627355776.5392456/events.out.tfevents.1627355776.baadd1eee5cb.67.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc2b8b87082d6468010a120ec6383541a776637d75329788c40b3e99c373dfd8
+size 4337

runs/Jul27_03-16-02_baadd1eee5cb/events.out.tfevents.1627355776.baadd1eee5cb.67.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9da3fbc94682441def03397306aae574a5706a611b902fb34a934de3f0f2710e
+size 16534

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1 @@
+{"source_lang": "en", "target_lang": "ro", "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": "Helsinki-NLP/opus-mt-en-ro", "tokenizer_class": "MarianTokenizer"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8cbc967174535b894fca348a79e6d925f9e28b0140dc4e605ff24d178b338b9
+size 2735