Training complete

README.md

@@ -0,0 +1,57 @@
+---
+license: cc-by-4.0
+base_model: Helsinki-NLP/opus-mt-tc-big-tr-en
+tags:
+- translation
+- generated_from_trainer
+model-index:
+- name: nmt_v0123_head10k
+  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. -->
+
+# nmt_v0123_head10k
+
+This model is a fine-tuned version of [Helsinki-NLP/opus-mt-tc-big-tr-en](https://huggingface.co/Helsinki-NLP/opus-mt-tc-big-tr-en) on the None dataset.
+It achieves the following results on the evaluation set:
+- eval_loss: 1.4075
+- eval_bleu: 29.7605
+- eval_runtime: 575.4386
+- eval_samples_per_second: 5.226
+- eval_steps_per_second: 2.614
+- step: 0
+
+## 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: 2
+- eval_batch_size: 2
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3
+- mixed_precision_training: Native AMP
+
+### Framework versions
+
+- Transformers 4.41.2
+- Pytorch 2.3.0+cu118
+- Datasets 2.4.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,46 @@
+{
+  "_name_or_path": "Helsinki-NLP/opus-mt-tc-big-tr-en",
+  "activation_dropout": 0.0,
+  "activation_function": "relu",
+  "architectures": [
+    "MarianMTModel"
+  ],
+  "attention_dropout": 0.0,
+  "bad_words_ids": [
+    [
+      57059
+    ]
+  ],
+  "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": 43741,
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "max_length": 512,
+  "max_position_embeddings": 1024,
+  "model_type": "marian",
+  "normalize_embedding": false,
+  "num_beams": 4,
+  "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": "4.41.2",
+  "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": "4.41.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:359068cb19e13ee0ceba05cea425467bc6fc86f394cae37ef631d3e137b48d3c
+size 939405120

runs/Jun02_22-22-03_tm211pc/events.out.tfevents.1717356745.tm211pc.708150.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f022aba3e8ab28c41a87082efaa60d64edecbaa5f5860b3a6ed184a89d2cc2d6
+size 596

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,39 @@
+{
+  "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": true,
+  "eos_token": "</s>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "return_tensors": "pt",
+  "separate_vocabs": false,
+  "source_lang": "tr",
+  "sp_model_kwargs": {},
+  "target_lang": "en",
+  "tokenizer_class": "MarianTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a19eb209ff92c69ae5d3f757bb426687df7e826732b27c732dc0831998c8752
+size 5304