opus-mt-ja-pl-pop-tests

README.md

@@ -0,0 +1,86 @@
+---
+license: apache-2.0
+base_model: Helsinki-NLP/opus-mt-ja-pl
+tags:
+- generated_from_trainer
+datasets:
+- tatoeba
+metrics:
+- bleu
+model-index:
+- name: opus_model
+  results:
+  - task:
+      name: Sequence-to-sequence Language Modeling
+      type: text2text-generation
+    dataset:
+      name: tatoeba
+      type: tatoeba
+      config: ja-pl
+      split: train
+      args: ja-pl
+    metrics:
+    - name: Bleu
+      type: bleu
+      value: 34.4952
+---
+
+<!-- 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_model
+
+This model is a fine-tuned version of [Helsinki-NLP/opus-mt-ja-pl](https://huggingface.co/Helsinki-NLP/opus-mt-ja-pl) on the tatoeba dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.1164
+- Bleu: 34.4952
+- Gen Len: 9.442
+- Meteor: 0.5692
+- Chrf: 53.728
+
+## 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: 3e-05
+- 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: 8
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step   | Validation Loss | Bleu    | Gen Len | Meteor | Chrf    |
+|:-------------:|:-----:|:------:|:---------------:|:-------:|:-------:|:------:|:-------:|
+| 2.5658        | 1.0   | 56681  | 1.6196          | 21.6767 | 9.2915  | 0.4586 | 43.4725 |
+| 2.3419        | 2.0   | 113362 | 1.4667          | 25.4469 | 9.3688  | 0.4916 | 46.3391 |
+| 2.23          | 3.0   | 170043 | 1.3715          | 27.166  | 9.4895  | 0.5089 | 48.2252 |
+| 2.1139        | 4.0   | 226724 | 1.2833          | 28.9288 | 9.4581  | 0.5244 | 49.4667 |
+| 1.9825        | 5.0   | 283405 | 1.2170          | 31.3751 | 9.3229  | 0.5358 | 51.0005 |
+| 1.8982        | 6.0   | 340086 | 1.1660          | 32.9805 | 9.4976  | 0.5563 | 52.5487 |
+| 1.8198        | 7.0   | 396767 | 1.1305          | 34.0223 | 9.4436  | 0.5665 | 53.2912 |
+| 1.7592        | 8.0   | 453448 | 1.1164          | 34.4952 | 9.442   | 0.5692 | 53.728  |
+
+
+### Framework versions
+
+- Transformers 4.42.3
+- Pytorch 2.1.2
+- Datasets 2.20.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,61 @@
+{
+  "_name_or_path": "Helsinki-NLP/opus-mt-ja-pl",
+  "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": [
+    [
+      65000
+    ]
+  ],
+  "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": 65000,
+  "decoder_vocab_size": 65001,
+  "dropout": 0.1,
+  "encoder_attention_heads": 8,
+  "encoder_ffn_dim": 2048,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_token_id": 0,
+  "extra_pos_embeddings": 65001,
+  "forced_eos_token_id": 0,
+  "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": 65000,
+  "scale_embedding": true,
+  "share_encoder_decoder_embeddings": true,
+  "static_position_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.3",
+  "use_cache": true,
+  "vocab_size": 65001
+}

generation_config.json

@@ -0,0 +1,16 @@
+{
+  "bad_words_ids": [
+    [
+      65000
+    ]
+  ],
+  "bos_token_id": 0,
+  "decoder_start_token_id": 65000,
+  "eos_token_id": 0,
+  "forced_eos_token_id": 0,
+  "max_length": 512,
+  "num_beams": 6,
+  "pad_token_id": 65000,
+  "renormalize_logits": true,
+  "transformers_version": "4.42.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:077a538f42756d5ae7d258b9e345ef3c58636253ae94b63ad48b0cbc1e221e0c
+size 309965092

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

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
+    },
+    "65000": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "separate_vocabs": false,
+  "source_lang": "jpn",
+  "sp_model_kwargs": {},
+  "target_lang": "pol",
+  "tokenizer_class": "MarianTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47757aa0d6131562a8af6a21ac198866eede03c18262efcef3ae24a3d6199f06
+size 5240