add model

.gitignore

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

README.md

@@ -0,0 +1,68 @@
+---
+license: apache-2.0
+tags:
+- generated_from_trainer
+metrics:
+- bleu
+model_index:
+- name: opus-mt-ja-en-finetuned-ja-to-en_xml
+  results:
+  - task:
+      name: Sequence-to-sequence Language Modeling
+      type: text2text-generation
+    metric:
+      name: Bleu
+      type: bleu
+      value: 67.5347
+---
+
+<!-- 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-ja-en-finetuned-ja-to-en_xml
+
+This model is a fine-tuned version of [Helsinki-NLP/opus-mt-ja-en](https://huggingface.co/Helsinki-NLP/opus-mt-ja-en) on an unkown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5932
+- Bleu: 67.5347
+- Gen Len: 27.1941
+
+## 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: 0.0002
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 1
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Bleu    | Gen Len |
+|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|
+| 0.8055        | 1.0   | 748  | 0.5932          | 67.5347 | 27.1941 |
+
+
+### Framework versions
+
+- Transformers 4.9.1
+- Pytorch 1.10.0+cu111
+- Datasets 1.10.2
+- Tokenizers 0.10.3

config.json

@@ -0,0 +1,60 @@
+{
+  "_name_or_path": "Helsinki-NLP/opus-mt-ja-en",
+  "_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": [
+    [
+      60715
+    ]
+  ],
+  "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": 60715,
+  "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": 6,
+  "num_hidden_layers": 6,
+  "pad_token_id": 60715,
+  "scale_embedding": true,
+  "static_position_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.9.1",
+  "use_cache": true,
+  "vocab_size": 60716
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95e3b843511fc1107d81632eaa1382b8cacab3aef3f7290aa5de75ad73e6839e
+size 301227653

runs/Dec04_07-53-06_0555d0489403/1638604401.3774054/events.out.tfevents.1638604401.0555d0489403.73.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:498b4ccf837f887032150fd61af26f4f94a791cb424c55d378e1350f33487bb3
+size 4335

runs/Dec04_07-53-06_0555d0489403/events.out.tfevents.1638604401.0555d0489403.73.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c67d1a64ffe5233c2abd31c09464fe6c05d8945e21f48c2fb361a95ce84785a8
+size 4924

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1 @@
+{"source_lang": "ja", "target_lang": "en", "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-ja-en", "tokenizer_class": "MarianTokenizer"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a52b416afc9cd7616f5f8864baa9e5a2526a11a83c42c59470b24bdc8894e20
+size 2735