pepper/opus-mt-tc-big-en-ko-translation_en_to_ko-v1

.gitattributes

@@ -33,3 +33,5 @@ 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
+source.spm filter=lfs diff=lfs merge=lfs -text
+target.spm filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,64 @@
+---
+library_name: transformers
+license: cc-by-4.0
+base_model: Helsinki-NLP/opus-mt-tc-big-en-ko
+tags:
+- generated_from_trainer
+metrics:
+- bleu
+model-index:
+- name: my_awesome_opus_books_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. -->
+
+# my_awesome_opus_books_model
+
+This model is a fine-tuned version of [Helsinki-NLP/opus-mt-tc-big-en-ko](https://huggingface.co/Helsinki-NLP/opus-mt-tc-big-en-ko) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 4.5287
+- Bleu: 0.0
+- Gen Len: 9.335
+
+## 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: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 2
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
+|:-------------:|:-----:|:----:|:---------------:|:----:|:-------:|
+| 4.6139        | 1.0   | 50   | 4.5665          | 0.0  | 7.795   |
+| 4.4138        | 2.0   | 100  | 4.5287          | 0.0  | 9.335   |
+
+
+### Framework versions
+
+- Transformers 4.55.0
+- Pytorch 2.6.0+cu124
+- Datasets 4.0.0
+- Tokenizers 0.21.4

config.json

@@ -0,0 +1,40 @@
+{
+  "activation_dropout": 0.0,
+  "activation_function": "relu",
+  "architectures": [
+    "MarianMTModel"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "classifier_dropout": 0.0,
+  "d_model": 1024,
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 4096,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "decoder_start_token_id": 32000,
+  "decoder_vocab_size": 32001,
+  "dropout": 0.1,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_token_id": 2,
+  "forced_eos_token_id": null,
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "max_length": null,
+  "max_position_embeddings": 1024,
+  "model_type": "marian",
+  "normalize_embedding": false,
+  "num_beams": null,
+  "num_hidden_layers": 6,
+  "pad_token_id": 32000,
+  "scale_embedding": true,
+  "share_encoder_decoder_embeddings": true,
+  "static_position_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.55.0",
+  "use_cache": true,
+  "vocab_size": 32001
+}

generation_config.json

@@ -0,0 +1,16 @@
+{
+  "bad_words_ids": [
+    [
+      32000
+    ]
+  ],
+  "bos_token_id": 0,
+  "decoder_start_token_id": 32000,
+  "eos_token_id": 2,
+  "forced_eos_token_id": 2,
+  "max_length": 512,
+  "num_beams": 4,
+  "pad_token_id": 32000,
+  "renormalize_logits": true,
+  "transformers_version": "4.55.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dcfd5d69e0e88b076678fc80c664556a659af4487fab054c37be9bfada1e1670
+size 836663220

runs/Aug12_05-45-02_c7ecfccc36ad/events.out.tfevents.1754977895.c7ecfccc36ad.555.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cf370693a020c00a4ddc703fff1d08059e48f199a1e2da37ca73e4e981dcf71
+size 88

runs/Aug12_06-18-12_9521cc1a11c7/events.out.tfevents.1754979509.9521cc1a11c7.2533.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbde6548197e6ed92a5ac3efb2d7fa27c5f3f4094259331f700fa6bedd03af21
+size 10759

runs/Aug12_06-23-10_9521cc1a11c7/events.out.tfevents.1754979796.9521cc1a11c7.2533.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7ceb672b9fd76354f0dc0c44afd6331e4426411989b779ddf34364a76050f5e
+size 10759

runs/Aug12_06-28-29_9521cc1a11c7/events.out.tfevents.1754980110.9521cc1a11c7.2533.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c381644cc5b471a8a4058e1ed0e948c13a978748aad5cffa2604ef2245269ae7
+size 10759

runs/Aug12_06-29-44_9521cc1a11c7/events.out.tfevents.1754980185.9521cc1a11c7.2533.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91e7ea28417c8bad6850935d26010c94c31c92614d748c301b233e1ce67f596a
+size 17008

source.spm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d0591e65c49541d82f48df33d7b322c3d4ee7aa0ee8747f9a7f9355dbf22c95
+size 789870

special_tokens_map.json

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

target.spm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d2aa641a0890d8966ab8703b109895a4e522713ce99b4a0192bfacb495bc97c
+size 815483

tokenizer_config.json

@@ -0,0 +1,39 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "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
+    },
+    "32000": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "separate_vocabs": false,
+  "source_lang": "en",
+  "sp_model_kwargs": {},
+  "target_lang": "ko",
+  "tokenizer_class": "MarianTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad1d2162ca30cc0b5d5bfd6149742a6d7e9880c5989d9f4e8b464c6ea67d8d25
+size 5560