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-11826/source.spm filter=lfs diff=lfs merge=lfs -text
+checkpoint-11826/target.spm filter=lfs diff=lfs merge=lfs -text
+checkpoint-1971/source.spm filter=lfs diff=lfs merge=lfs -text
+checkpoint-1971/target.spm filter=lfs diff=lfs merge=lfs -text
+checkpoint-3942/source.spm filter=lfs diff=lfs merge=lfs -text
+checkpoint-3942/target.spm filter=lfs diff=lfs merge=lfs -text
+checkpoint-5913/source.spm filter=lfs diff=lfs merge=lfs -text
+checkpoint-5913/target.spm filter=lfs diff=lfs merge=lfs -text
+checkpoint-7884/source.spm filter=lfs diff=lfs merge=lfs -text
+checkpoint-7884/target.spm filter=lfs diff=lfs merge=lfs -text
+checkpoint-9855/source.spm filter=lfs diff=lfs merge=lfs -text
+checkpoint-9855/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-11826/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-11826/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-11826/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fff6e054402a7e94855cc3b3f2207329373797c55de20bfd0f9c15846558425
+size 309965092

checkpoint-11826/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08d7f5a25e2ec74b12d42479efd0ec1bef3abc7dcec7ec8120160239e75db4ac
+size 619563642

checkpoint-11826/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d34f69b47d6327fa2611573784d2b6e3b933e3338ecc5b3e464fb9350d817c6d
+size 14244

checkpoint-11826/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:600c499244df8db233478d843e4a62f93a9b482036853e3f85972f8d94e6c73d
+size 1064

checkpoint-11826/source.spm

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

checkpoint-11826/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-11826/target.spm

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

checkpoint-11826/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-11826/trainer_state.json

@@ -0,0 +1,284 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 6.0,
+  "eval_steps": 500,
+  "global_step": 11826,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.2536783358701167,
+      "grad_norm": 6.285004615783691,
+      "learning_rate": 1.9157787924911212e-05,
+      "loss": 1.589,
+      "step": 500
+    },
+    {
+      "epoch": 0.5073566717402334,
+      "grad_norm": 6.245589256286621,
+      "learning_rate": 1.8312193472010826e-05,
+      "loss": 0.8971,
+      "step": 1000
+    },
+    {
+      "epoch": 0.76103500761035,
+      "grad_norm": 7.839916706085205,
+      "learning_rate": 1.7466599019110436e-05,
+      "loss": 0.7412,
+      "step": 1500
+    },
+    {
+      "epoch": 1.0,
+      "eval_bleu": 77.9302498710783,
+      "eval_loss": 0.5189284682273865,
+      "eval_rouge": {
+        "rouge1": 0.8422585807632581,
+        "rouge2": 0.7462100224193878,
+        "rougeL": 0.8347423871515361,
+        "rougeLsum": 0.8348341110331449
+      },
+      "eval_runtime": 589.3644,
+      "eval_samples_per_second": 14.402,
+      "eval_steps_per_second": 0.901,
+      "step": 1971
+    },
+    {
+      "epoch": 1.0147133434804667,
+      "grad_norm": 4.194991111755371,
+      "learning_rate": 1.6621004566210046e-05,
+      "loss": 0.6173,
+      "step": 2000
+    },
+    {
+      "epoch": 1.2683916793505834,
+      "grad_norm": 4.830150127410889,
+      "learning_rate": 1.5775410113309656e-05,
+      "loss": 0.4964,
+      "step": 2500
+    },
+    {
+      "epoch": 1.5220700152207,
+      "grad_norm": 6.662743091583252,
+      "learning_rate": 1.4929815660409268e-05,
+      "loss": 0.4655,
+      "step": 3000
+    },
+    {
+      "epoch": 1.775748351090817,
+      "grad_norm": 5.814598560333252,
+      "learning_rate": 1.408422120750888e-05,
+      "loss": 0.4562,
+      "step": 3500
+    },
+    {
+      "epoch": 2.0,
+      "eval_bleu": 82.4671860062862,
+      "eval_loss": 0.4167616665363312,
+      "eval_rouge": {
+        "rouge1": 0.8726285922102037,
+        "rouge2": 0.7929049594785995,
+        "rougeL": 0.8662329420974849,
+        "rougeLsum": 0.8662523269791588
+      },
+      "eval_runtime": 558.5398,
+      "eval_samples_per_second": 15.197,
+      "eval_steps_per_second": 0.951,
+      "step": 3942
+    },
+    {
+      "epoch": 2.0294266869609334,
+      "grad_norm": 4.13426399230957,
+      "learning_rate": 1.323862675460849e-05,
+      "loss": 0.4122,
+      "step": 4000
+    },
+    {
+      "epoch": 2.2831050228310503,
+      "grad_norm": 4.324504375457764,
+      "learning_rate": 1.2393032301708102e-05,
+      "loss": 0.3451,
+      "step": 4500
+    },
+    {
+      "epoch": 2.536783358701167,
+      "grad_norm": 1.6161426305770874,
+      "learning_rate": 1.1549129037713514e-05,
+      "loss": 0.3359,
+      "step": 5000
+    },
+    {
+      "epoch": 2.7904616945712837,
+      "grad_norm": 3.2323482036590576,
+      "learning_rate": 1.0703534584813124e-05,
+      "loss": 0.3413,
+      "step": 5500
+    },
+    {
+      "epoch": 3.0,
+      "eval_bleu": 84.42968434246376,
+      "eval_loss": 0.3801760971546173,
+      "eval_rouge": {
+        "rouge1": 0.8853534128903551,
+        "rouge2": 0.8130151085172689,
+        "rougeL": 0.8794009703754694,
+        "rougeLsum": 0.8793662457667164
+      },
+      "eval_runtime": 553.0346,
+      "eval_samples_per_second": 15.348,
+      "eval_steps_per_second": 0.96,
+      "step": 5913
+    },
+    {
+      "epoch": 3.0441400304414,
+      "grad_norm": 3.7964985370635986,
+      "learning_rate": 9.857940131912736e-06,
+      "loss": 0.3074,
+      "step": 6000
+    },
+    {
+      "epoch": 3.297818366311517,
+      "grad_norm": 3.6037538051605225,
+      "learning_rate": 9.012345679012346e-06,
+      "loss": 0.269,
+      "step": 6500
+    },
+    {
+      "epoch": 3.551496702181634,
+      "grad_norm": 3.743192672729492,
+      "learning_rate": 8.166751226111958e-06,
+      "loss": 0.2655,
+      "step": 7000
+    },
+    {
+      "epoch": 3.8051750380517504,
+      "grad_norm": 1.6885374784469604,
+      "learning_rate": 7.321156773211569e-06,
+      "loss": 0.275,
+      "step": 7500
+    },
+    {
+      "epoch": 4.0,
+      "eval_bleu": 85.34047750600152,
+      "eval_loss": 0.3641541302204132,
+      "eval_rouge": {
+        "rouge1": 0.8913775651214185,
+        "rouge2": 0.8220615430193459,
+        "rougeL": 0.8858292704586206,
+        "rougeLsum": 0.8858430238896269
+      },
+      "eval_runtime": 560.5886,
+      "eval_samples_per_second": 15.141,
+      "eval_steps_per_second": 0.947,
+      "step": 7884
+    },
+    {
+      "epoch": 4.058853373921867,
+      "grad_norm": 2.691307783126831,
+      "learning_rate": 6.4755623203111796e-06,
+      "loss": 0.2498,
+      "step": 8000
+    },
+    {
+      "epoch": 4.312531709791983,
+      "grad_norm": 4.331101417541504,
+      "learning_rate": 5.6299678674107905e-06,
+      "loss": 0.2301,
+      "step": 8500
+    },
+    {
+      "epoch": 4.566210045662101,
+      "grad_norm": 3.2862532138824463,
+      "learning_rate": 4.786064603416202e-06,
+      "loss": 0.2386,
+      "step": 9000
+    },
+    {
+      "epoch": 4.819888381532217,
+      "grad_norm": 3.7428629398345947,
+      "learning_rate": 3.940470150515813e-06,
+      "loss": 0.2326,
+      "step": 9500
+    },
+    {
+      "epoch": 5.0,
+      "eval_bleu": 85.62474872165251,
+      "eval_loss": 0.35635867714881897,
+      "eval_rouge": {
+        "rouge1": 0.8957946109809499,
+        "rouge2": 0.8288231670050729,
+        "rougeL": 0.8903628109630211,
+        "rougeLsum": 0.8904334470778201
+      },
+      "eval_runtime": 554.4082,
+      "eval_samples_per_second": 15.31,
+      "eval_steps_per_second": 0.958,
+      "step": 9855
+    },
+    {
+      "epoch": 5.073566717402334,
+      "grad_norm": 2.8402657508850098,
+      "learning_rate": 3.0948756976154237e-06,
+      "loss": 0.22,
+      "step": 10000
+    },
+    {
+      "epoch": 5.327245053272451,
+      "grad_norm": 3.1032028198242188,
+      "learning_rate": 2.2492812447150347e-06,
+      "loss": 0.2083,
+      "step": 10500
+    },
+    {
+      "epoch": 5.580923389142567,
+      "grad_norm": 3.455146312713623,
+      "learning_rate": 1.4053779807204465e-06,
+      "loss": 0.2027,
+      "step": 11000
+    },
+    {
+      "epoch": 5.834601725012684,
+      "grad_norm": 2.128119468688965,
+      "learning_rate": 5.597835278200575e-07,
+      "loss": 0.2143,
+      "step": 11500
+    },
+    {
+      "epoch": 6.0,
+      "eval_bleu": 85.9174327850833,
+      "eval_loss": 0.3543717563152313,
+      "eval_rouge": {
+        "rouge1": 0.8969832695452472,
+        "rouge2": 0.8310275704571024,
+        "rougeL": 0.8913461546133479,
+        "rougeLsum": 0.8913688423165305
+      },
+      "eval_runtime": 553.9415,
+      "eval_samples_per_second": 15.323,
+      "eval_steps_per_second": 0.959,
+      "step": 11826
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 11826,
+  "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": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1596266324361216.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-11826/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d50538077dc9316af4f0e3a52d83f66a602e8f111533468407cd32fad55c01d
+size 5496

checkpoint-1971/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-1971/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-1971/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:457f802cad9b26588ccbb265d83407431be6d902f1e1991c4ab26391714c43fa
+size 309965092

checkpoint-1971/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b7286a84d2437f1e1c8b390ad47213ebec48ca128e00c611190138025dc744d
+size 619563642

checkpoint-1971/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9db98f0ce5cbfb036b11f8b357434db0be764cee68f5927c4b00e8f348b29786
+size 14244

checkpoint-1971/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be1e0f3c1bf5bfb20687bc226f7646f4a11677f08c1d29cf97f870f3f8ba0f29
+size 1064

checkpoint-1971/source.spm

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

checkpoint-1971/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-1971/target.spm

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

checkpoint-1971/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-1971/trainer_state.json

@@ -0,0 +1,69 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 1971,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.2536783358701167,
+      "grad_norm": 6.285004615783691,
+      "learning_rate": 1.9157787924911212e-05,
+      "loss": 1.589,
+      "step": 500
+    },
+    {
+      "epoch": 0.5073566717402334,
+      "grad_norm": 6.245589256286621,
+      "learning_rate": 1.8312193472010826e-05,
+      "loss": 0.8971,
+      "step": 1000
+    },
+    {
+      "epoch": 0.76103500761035,
+      "grad_norm": 7.839916706085205,
+      "learning_rate": 1.7466599019110436e-05,
+      "loss": 0.7412,
+      "step": 1500
+    },
+    {
+      "epoch": 1.0,
+      "eval_bleu": 77.9302498710783,
+      "eval_loss": 0.5189284682273865,
+      "eval_rouge": {
+        "rouge1": 0.8422585807632581,
+        "rouge2": 0.7462100224193878,
+        "rougeL": 0.8347423871515361,
+        "rougeLsum": 0.8348341110331449
+      },
+      "eval_runtime": 589.3644,
+      "eval_samples_per_second": 14.402,
+      "eval_steps_per_second": 0.901,
+      "step": 1971
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 11826,
+  "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": 266574887976960.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1971/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d50538077dc9316af4f0e3a52d83f66a602e8f111533468407cd32fad55c01d
+size 5496

checkpoint-3942/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-3942/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-3942/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:859e460154977ae936caadc7d20d31e8a8d895f4c30a384e5488a1a0ed451bba
+size 309965092

checkpoint-3942/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8537487bb1d383bdfa0e668b5dc53cb58ba6ac936c76d6c1409f1104dda4d501
+size 619563642

checkpoint-3942/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dca42cded49feccc60369b40fc5385380720f862f43024ffe0fd8fe3a7c92d4b
+size 14244

checkpoint-3942/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f0e64f689759835954ae6c93dc848789ea0a051a857e84fab50db368d9ad311
+size 1064

checkpoint-3942/source.spm

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

checkpoint-3942/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-3942/target.spm

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

checkpoint-3942/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-3942/trainer_state.json

@@ -0,0 +1,112 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 3942,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.2536783358701167,
+      "grad_norm": 6.285004615783691,
+      "learning_rate": 1.9157787924911212e-05,
+      "loss": 1.589,
+      "step": 500
+    },
+    {
+      "epoch": 0.5073566717402334,
+      "grad_norm": 6.245589256286621,
+      "learning_rate": 1.8312193472010826e-05,
+      "loss": 0.8971,
+      "step": 1000
+    },
+    {
+      "epoch": 0.76103500761035,
+      "grad_norm": 7.839916706085205,
+      "learning_rate": 1.7466599019110436e-05,
+      "loss": 0.7412,
+      "step": 1500
+    },
+    {
+      "epoch": 1.0,
+      "eval_bleu": 77.9302498710783,
+      "eval_loss": 0.5189284682273865,
+      "eval_rouge": {
+        "rouge1": 0.8422585807632581,
+        "rouge2": 0.7462100224193878,
+        "rougeL": 0.8347423871515361,
+        "rougeLsum": 0.8348341110331449
+      },
+      "eval_runtime": 589.3644,
+      "eval_samples_per_second": 14.402,
+      "eval_steps_per_second": 0.901,
+      "step": 1971
+    },
+    {
+      "epoch": 1.0147133434804667,
+      "grad_norm": 4.194991111755371,
+      "learning_rate": 1.6621004566210046e-05,
+      "loss": 0.6173,
+      "step": 2000
+    },
+    {
+      "epoch": 1.2683916793505834,
+      "grad_norm": 4.830150127410889,
+      "learning_rate": 1.5775410113309656e-05,
+      "loss": 0.4964,
+      "step": 2500
+    },
+    {
+      "epoch": 1.5220700152207,
+      "grad_norm": 6.662743091583252,
+      "learning_rate": 1.4929815660409268e-05,
+      "loss": 0.4655,
+      "step": 3000
+    },
+    {
+      "epoch": 1.775748351090817,
+      "grad_norm": 5.814598560333252,
+      "learning_rate": 1.408422120750888e-05,
+      "loss": 0.4562,
+      "step": 3500
+    },
+    {
+      "epoch": 2.0,
+      "eval_bleu": 82.4671860062862,
+      "eval_loss": 0.4167616665363312,
+      "eval_rouge": {
+        "rouge1": 0.8726285922102037,
+        "rouge2": 0.7929049594785995,
+        "rougeL": 0.8662329420974849,
+        "rougeLsum": 0.8662523269791588
+      },
+      "eval_runtime": 558.5398,
+      "eval_samples_per_second": 15.197,
+      "eval_steps_per_second": 0.951,
+      "step": 3942
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 11826,
+  "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": 531874085142528.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-3942/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d50538077dc9316af4f0e3a52d83f66a602e8f111533468407cd32fad55c01d
+size 5496

checkpoint-5913/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-5913/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-5913/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:838388e5434c711a6e41e7d25815812f9d4631f8c658a1eda64cd6f8045e2861
+size 309965092

checkpoint-5913/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd4dd35331b261c8401fcc244258cf208601e1239bb410f6881a92275402cd6b
+size 619563642

checkpoint-5913/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8041b037c9052a7992e9ff13a835adc04189793127123e37f382a3bbdac2c98f
+size 14244

checkpoint-5913/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a893a098cd7e476391b3409db82effe07a8fb4dcd8a40dacf66da774085b4f75
+size 1064

checkpoint-5913/source.spm

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

checkpoint-5913/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-5913/target.spm

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

checkpoint-5913/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>"
+}