Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,17 @@ 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
+checkpoint-1172/source.spm filter=lfs diff=lfs merge=lfs -text
+checkpoint-1172/target.spm filter=lfs diff=lfs merge=lfs -text
+checkpoint-1758/source.spm filter=lfs diff=lfs merge=lfs -text
+checkpoint-1758/target.spm filter=lfs diff=lfs merge=lfs -text
+checkpoint-2344/source.spm filter=lfs diff=lfs merge=lfs -text
+checkpoint-2344/target.spm filter=lfs diff=lfs merge=lfs -text
+checkpoint-2930/source.spm filter=lfs diff=lfs merge=lfs -text
+checkpoint-2930/target.spm filter=lfs diff=lfs merge=lfs -text
+checkpoint-3516/source.spm filter=lfs diff=lfs merge=lfs -text
+checkpoint-3516/target.spm filter=lfs diff=lfs merge=lfs -text
+checkpoint-586/source.spm filter=lfs diff=lfs merge=lfs -text
+checkpoint-586/target.spm 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

checkpoint-1172/config.json

@@ -0,0 +1,56 @@
+{
+  "_name_or_path": "Woondsc/opus-mt-ko-en-medterm",
+  "activation_dropout": 0.0,
+  "activation_function": "swish",
+  "add_bias_logits": false,
+  "add_final_layer_norm": false,
+  "architectures": [
+    "MarianMTModel"
+  ],
+  "attention_dropout": 0.0,
+  "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": null,
+  "max_position_embeddings": 512,
+  "model_type": "marian",
+  "normalize_before": false,
+  "normalize_embedding": false,
+  "num_beams": null,
+  "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": "4.48.3",
+  "use_cache": true,
+  "vocab_size": 65001
+}

checkpoint-1172/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": "4.48.3"
+}

checkpoint-1172/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62b01b7d210ad9320fe8c03d0660f74a52eb35b623d4eac80c65b8d951d61aad
+size 309965092

checkpoint-1172/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a29572d616980a68aae1f305f07112289b2f2c0ea4f9d9f57b191fb969000ae8
+size 619563642

checkpoint-1172/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5629f5bd384eb75bb6cb7e3bcb08a4dfec5da74d7f3b489cee0905e7cafd73e0
+size 14244

checkpoint-1172/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd443d2422bc9e6ddbaa16713140944279406fd161739a3d951292509af0de6f
+size 1064

checkpoint-1172/source.spm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9496f7c2be9aecb84c751ae9f35a875915dde8e3892f652a5c76811ab2a0f49
+size 841805

checkpoint-1172/special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-1172/target.spm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1531ac8576fe64267dfca0dc33950a6e9a2d3fd9e05346558ad7ea5ee0e65bf
+size 813126

checkpoint-1172/tokenizer_config.json

@@ -0,0 +1,39 @@
+{
+  "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": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "separate_vocabs": false,
+  "source_lang": "kor",
+  "sp_model_kwargs": {},
+  "target_lang": "eng",
+  "tokenizer_class": "MarianTokenizer",
+  "unk_token": "<unk>"
+}

checkpoint-1172/trainer_state.json

@@ -0,0 +1,77 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 1172,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.8532423208191127,
+      "grad_norm": 8.762770652770996,
+      "learning_rate": 1.7167235494880547e-05,
+      "loss": 1.4672,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_bleu": 71.17004731575985,
+      "eval_loss": 0.7510850429534912,
+      "eval_rouge": {
+        "rouge1": 0.7586685078425267,
+        "rouge2": 0.6115347357798906,
+        "rougeL": 0.7490533887167732,
+        "rougeLsum": 0.7484630926564035
+      },
+      "eval_runtime": 134.1556,
+      "eval_samples_per_second": 18.807,
+      "eval_steps_per_second": 1.178,
+      "step": 586
+    },
+    {
+      "epoch": 1.7064846416382253,
+      "grad_norm": 5.05549430847168,
+      "learning_rate": 1.4323094425483506e-05,
+      "loss": 0.7479,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_bleu": 77.98925833953002,
+      "eval_loss": 0.5916641354560852,
+      "eval_rouge": {
+        "rouge1": 0.7980118177508164,
+        "rouge2": 0.6728157741476863,
+        "rougeL": 0.7898294918297277,
+        "rougeLsum": 0.7889319703951503
+      },
+      "eval_runtime": 134.4934,
+      "eval_samples_per_second": 18.759,
+      "eval_steps_per_second": 1.175,
+      "step": 1172
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3516,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 118470548127744.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1172/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2d28648ba7f6f8e9e5d172a0e9e7e4d52e850fef13b0741a2fb166b63fba202
+size 5496

checkpoint-1758/config.json

@@ -0,0 +1,56 @@
+{
+  "_name_or_path": "Woondsc/opus-mt-ko-en-medterm",
+  "activation_dropout": 0.0,
+  "activation_function": "swish",
+  "add_bias_logits": false,
+  "add_final_layer_norm": false,
+  "architectures": [
+    "MarianMTModel"
+  ],
+  "attention_dropout": 0.0,
+  "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": null,
+  "max_position_embeddings": 512,
+  "model_type": "marian",
+  "normalize_before": false,
+  "normalize_embedding": false,
+  "num_beams": null,
+  "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": "4.48.3",
+  "use_cache": true,
+  "vocab_size": 65001
+}

checkpoint-1758/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": "4.48.3"
+}

checkpoint-1758/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae5dc2e61c1ba0c32fe7c467afa63d2842cb53e2723e12926d00d645e88b08c1
+size 309965092

checkpoint-1758/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f90d9112c78cc4f08915fdca6ec511e7c1417b98d010e6dd115c3f1038ca1ea8
+size 619563642

checkpoint-1758/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:039369bde3b349b36fed7be1fe52bee483eff4a13522093a7a14dced7f6975b6
+size 14244

checkpoint-1758/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c40abb44e078978f993b40cee2ee76bc70febdb041dfdebb588802807c323b5
+size 1064

checkpoint-1758/source.spm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9496f7c2be9aecb84c751ae9f35a875915dde8e3892f652a5c76811ab2a0f49
+size 841805

checkpoint-1758/special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-1758/target.spm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1531ac8576fe64267dfca0dc33950a6e9a2d3fd9e05346558ad7ea5ee0e65bf
+size 813126

checkpoint-1758/tokenizer_config.json

@@ -0,0 +1,39 @@
+{
+  "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": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "separate_vocabs": false,
+  "source_lang": "kor",
+  "sp_model_kwargs": {},
+  "target_lang": "eng",
+  "tokenizer_class": "MarianTokenizer",
+  "unk_token": "<unk>"
+}

checkpoint-1758/trainer_state.json

@@ -0,0 +1,99 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 1758,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.8532423208191127,
+      "grad_norm": 8.762770652770996,
+      "learning_rate": 1.7167235494880547e-05,
+      "loss": 1.4672,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_bleu": 71.17004731575985,
+      "eval_loss": 0.7510850429534912,
+      "eval_rouge": {
+        "rouge1": 0.7586685078425267,
+        "rouge2": 0.6115347357798906,
+        "rougeL": 0.7490533887167732,
+        "rougeLsum": 0.7484630926564035
+      },
+      "eval_runtime": 134.1556,
+      "eval_samples_per_second": 18.807,
+      "eval_steps_per_second": 1.178,
+      "step": 586
+    },
+    {
+      "epoch": 1.7064846416382253,
+      "grad_norm": 5.05549430847168,
+      "learning_rate": 1.4323094425483506e-05,
+      "loss": 0.7479,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_bleu": 77.98925833953002,
+      "eval_loss": 0.5916641354560852,
+      "eval_rouge": {
+        "rouge1": 0.7980118177508164,
+        "rouge2": 0.6728157741476863,
+        "rougeL": 0.7898294918297277,
+        "rougeLsum": 0.7889319703951503
+      },
+      "eval_runtime": 134.4934,
+      "eval_samples_per_second": 18.759,
+      "eval_steps_per_second": 1.175,
+      "step": 1172
+    },
+    {
+      "epoch": 2.5597269624573378,
+      "grad_norm": 3.831761360168457,
+      "learning_rate": 1.1478953356086462e-05,
+      "loss": 0.556,
+      "step": 1500
+    },
+    {
+      "epoch": 3.0,
+      "eval_bleu": 81.08165889470924,
+      "eval_loss": 0.5316380858421326,
+      "eval_rouge": {
+        "rouge1": 0.8151391371295702,
+        "rouge2": 0.6981852981887253,
+        "rougeL": 0.806655138353247,
+        "rougeLsum": 0.8059563640828541
+      },
+      "eval_runtime": 132.3183,
+      "eval_samples_per_second": 19.068,
+      "eval_steps_per_second": 1.194,
+      "step": 1758
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3516,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 178015144771584.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1758/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2d28648ba7f6f8e9e5d172a0e9e7e4d52e850fef13b0741a2fb166b63fba202
+size 5496

checkpoint-2344/config.json

@@ -0,0 +1,56 @@
+{
+  "_name_or_path": "Woondsc/opus-mt-ko-en-medterm",
+  "activation_dropout": 0.0,
+  "activation_function": "swish",
+  "add_bias_logits": false,
+  "add_final_layer_norm": false,
+  "architectures": [
+    "MarianMTModel"
+  ],
+  "attention_dropout": 0.0,
+  "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": null,
+  "max_position_embeddings": 512,
+  "model_type": "marian",
+  "normalize_before": false,
+  "normalize_embedding": false,
+  "num_beams": null,
+  "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": "4.48.3",
+  "use_cache": true,
+  "vocab_size": 65001
+}

checkpoint-2344/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": "4.48.3"
+}

checkpoint-2344/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bf05405650e7fbac4efa7f1bc9dfba93a8d6bb96de577a8cd16f9a6fd8ce347
+size 309965092

checkpoint-2344/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f763d2ee7c7861666001314852bb014ff5488dc3191b3f393ccd9c9123d4dbfd
+size 619563642

checkpoint-2344/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c83e56e2e5ee23f9fecf215ceded761be05ac394f33023930fd7e7d97910686
+size 14244

checkpoint-2344/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2639021da6e3d648d570927ed265d371063fd545e105458fc72dff7e0c0f84f
+size 1064

checkpoint-2344/source.spm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9496f7c2be9aecb84c751ae9f35a875915dde8e3892f652a5c76811ab2a0f49
+size 841805

checkpoint-2344/special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-2344/target.spm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1531ac8576fe64267dfca0dc33950a6e9a2d3fd9e05346558ad7ea5ee0e65bf
+size 813126

checkpoint-2344/tokenizer_config.json

@@ -0,0 +1,39 @@
+{
+  "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": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "separate_vocabs": false,
+  "source_lang": "kor",
+  "sp_model_kwargs": {},
+  "target_lang": "eng",
+  "tokenizer_class": "MarianTokenizer",
+  "unk_token": "<unk>"
+}

checkpoint-2344/trainer_state.json

@@ -0,0 +1,121 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 2344,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.8532423208191127,
+      "grad_norm": 8.762770652770996,
+      "learning_rate": 1.7167235494880547e-05,
+      "loss": 1.4672,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_bleu": 71.17004731575985,
+      "eval_loss": 0.7510850429534912,
+      "eval_rouge": {
+        "rouge1": 0.7586685078425267,
+        "rouge2": 0.6115347357798906,
+        "rougeL": 0.7490533887167732,
+        "rougeLsum": 0.7484630926564035
+      },
+      "eval_runtime": 134.1556,
+      "eval_samples_per_second": 18.807,
+      "eval_steps_per_second": 1.178,
+      "step": 586
+    },
+    {
+      "epoch": 1.7064846416382253,
+      "grad_norm": 5.05549430847168,
+      "learning_rate": 1.4323094425483506e-05,
+      "loss": 0.7479,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_bleu": 77.98925833953002,
+      "eval_loss": 0.5916641354560852,
+      "eval_rouge": {
+        "rouge1": 0.7980118177508164,
+        "rouge2": 0.6728157741476863,
+        "rougeL": 0.7898294918297277,
+        "rougeLsum": 0.7889319703951503
+      },
+      "eval_runtime": 134.4934,
+      "eval_samples_per_second": 18.759,
+      "eval_steps_per_second": 1.175,
+      "step": 1172
+    },
+    {
+      "epoch": 2.5597269624573378,
+      "grad_norm": 3.831761360168457,
+      "learning_rate": 1.1478953356086462e-05,
+      "loss": 0.556,
+      "step": 1500
+    },
+    {
+      "epoch": 3.0,
+      "eval_bleu": 81.08165889470924,
+      "eval_loss": 0.5316380858421326,
+      "eval_rouge": {
+        "rouge1": 0.8151391371295702,
+        "rouge2": 0.6981852981887253,
+        "rougeL": 0.806655138353247,
+        "rougeLsum": 0.8059563640828541
+      },
+      "eval_runtime": 132.3183,
+      "eval_samples_per_second": 19.068,
+      "eval_steps_per_second": 1.194,
+      "step": 1758
+    },
+    {
+      "epoch": 3.4129692832764507,
+      "grad_norm": 3.7003045082092285,
+      "learning_rate": 8.63481228668942e-06,
+      "loss": 0.4508,
+      "step": 2000
+    },
+    {
+      "epoch": 4.0,
+      "eval_bleu": 82.60133061747088,
+      "eval_loss": 0.4998228847980499,
+      "eval_rouge": {
+        "rouge1": 0.8238729032217965,
+        "rouge2": 0.7162403358709662,
+        "rougeL": 0.8167800536747541,
+        "rougeLsum": 0.8161987903541148
+      },
+      "eval_runtime": 132.5265,
+      "eval_samples_per_second": 19.038,
+      "eval_steps_per_second": 1.192,
+      "step": 2344
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3516,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 237695334875136.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2344/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2d28648ba7f6f8e9e5d172a0e9e7e4d52e850fef13b0741a2fb166b63fba202
+size 5496

checkpoint-2930/config.json

@@ -0,0 +1,56 @@
+{
+  "_name_or_path": "Woondsc/opus-mt-ko-en-medterm",
+  "activation_dropout": 0.0,
+  "activation_function": "swish",
+  "add_bias_logits": false,
+  "add_final_layer_norm": false,
+  "architectures": [
+    "MarianMTModel"
+  ],
+  "attention_dropout": 0.0,
+  "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": null,
+  "max_position_embeddings": 512,
+  "model_type": "marian",
+  "normalize_before": false,
+  "normalize_embedding": false,
+  "num_beams": null,
+  "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": "4.48.3",
+  "use_cache": true,
+  "vocab_size": 65001
+}

checkpoint-2930/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": "4.48.3"
+}

checkpoint-2930/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbb078397915a62890ca13d320685590c5734f3c6c33226b8e62a4cae7f2c822
+size 309965092

checkpoint-2930/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1626ad9a4cc60b8eaab30d92fc713533c0768561aab8255dc9ff75916c59e789
+size 619563642

checkpoint-2930/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dcdcb9f230c546ab808091009cf2f89a1cba7f2471e62b54888df416d85c1ec0
+size 14244

checkpoint-2930/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01fbea6b7c88ed9bb73296c972f4033dded5a90b4db9d824aa0d94455317f560
+size 1064

checkpoint-2930/source.spm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9496f7c2be9aecb84c751ae9f35a875915dde8e3892f652a5c76811ab2a0f49
+size 841805

checkpoint-2930/special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-2930/target.spm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1531ac8576fe64267dfca0dc33950a6e9a2d3fd9e05346558ad7ea5ee0e65bf
+size 813126

checkpoint-2930/tokenizer_config.json

@@ -0,0 +1,39 @@
+{
+  "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": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "separate_vocabs": false,
+  "source_lang": "kor",
+  "sp_model_kwargs": {},
+  "target_lang": "eng",
+  "tokenizer_class": "MarianTokenizer",
+  "unk_token": "<unk>"
+}