kazparc_en_tr_marian_1

README.md

@@ -0,0 +1,61 @@
+---
+library_name: transformers
+license: cc-by-4.0
+base_model: Helsinki-NLP/opus-mt-tc-big-en-tr
+tags:
+- generated_from_trainer
+model-index:
+- name: kazparc_en_tr_marian_1
+  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. -->
+
+# kazparc_en_tr_marian_1
+
+This model is a fine-tuned version of [Helsinki-NLP/opus-mt-tc-big-en-tr](https://huggingface.co/Helsinki-NLP/opus-mt-tc-big-en-tr) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0132
+
+## 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: 8
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Use 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: 3
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss |
+|:-------------:|:-----:|:-----:|:---------------:|
+| 0.0151        | 1.0   | 9491  | 0.0138          |
+| 0.0104        | 2.0   | 18982 | 0.0132          |
+| 0.0075        | 3.0   | 28473 | 0.0132          |
+
+
+### Framework versions
+
+- Transformers 4.46.3
+- Pytorch 2.5.1+cu121
+- Datasets 3.2.0
+- Tokenizers 0.20.3

config.json

@@ -0,0 +1,41 @@
+{
+  "_name_or_path": "Helsinki-NLP/opus-mt-tc-big-en-tr",
+  "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": 57059,
+  "decoder_vocab_size": 57060,
+  "dropout": 0.1,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_token_id": 43741,
+  "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": 57059,
+  "scale_embedding": true,
+  "share_encoder_decoder_embeddings": true,
+  "static_position_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.3",
+  "use_cache": true,
+  "vocab_size": 57060
+}

generation_config.json

@@ -0,0 +1,16 @@
+{
+  "bad_words_ids": [
+    [
+      57059
+    ]
+  ],
+  "bos_token_id": 0,
+  "decoder_start_token_id": 57059,
+  "eos_token_id": 43741,
+  "forced_eos_token_id": 43741,
+  "max_length": 512,
+  "num_beams": 4,
+  "pad_token_id": 57059,
+  "renormalize_logits": true,
+  "transformers_version": "4.46.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d17b2abf0a51c339bee1ac84d4ec6e2db2c3a655bbb92f77fa30b0e95112f06
+size 939405120

runs/Dec14_22-09-23_1232351a06b1/events.out.tfevents.1734214165.1232351a06b1.6936.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49c8f2aba4baf03e3b81a79f6d8fd7e8341520000c60c7c81a87939be91dde0a
+size 18649

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": {
+    "43741": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "52508": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "57059": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "separate_vocabs": false,
+  "source_lang": "en",
+  "sp_model_kwargs": {},
+  "target_lang": "tr",
+  "tokenizer_class": "MarianTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1594961d6246594888b5284519c6b3f5e6cc79e7172bfdaadd18c9e9b0a95fa8
+size 5304