Training in progress, epoch 1

README.md

@@ -0,0 +1,73 @@
+---
+license: cc-by-4.0
+base_model: Helsinki-NLP/opus-mt-tc-big-en-tr
+tags:
+- translation
+- generated_from_trainer
+datasets:
+- tatoeba
+metrics:
+- bleu
+model-index:
+- name: opus-mt-tc-big-en-tr
+  results:
+  - task:
+      name: Sequence-to-sequence Language Modeling
+      type: text2text-generation
+    dataset:
+      name: tatoeba
+      type: tatoeba
+      config: en-tr
+      split: train
+      args: en-tr
+    metrics:
+    - name: Bleu
+      type: bleu
+      value: 54.405510741899164
+---
+
+<!-- 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. -->
+
+# opus-mt-tc-big-en-tr
+
+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 the tatoeba dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5573
+- Bleu: 54.4055
+
+## 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: 32
+- eval_batch_size: 64
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.38.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,46 @@
+{
+  "_name_or_path": "Helsinki-NLP/opus-mt-tc-big-en-tr",
+  "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": "4.38.2",
+  "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": "4.38.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15f12709fcd158c4a5d85b4afbccd861cf99db69082b04992e147ea0d1bdd4b6
+size 939405120

runs/Mar30_20-38-13_5cae252bde23/events.out.tfevents.1711831210.5cae252bde23.1389.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe88fcd974a9b7fa5436545a30709070b767995263d45d8eacf5c1d478213a97
+size 5810

runs/Mar30_20-38-13_5cae252bde23/events.out.tfevents.1711833332.5cae252bde23.1389.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77baf753e4955fcbbc88a09e41a23b6463ba707b08bb35958b9303339f4225e3
+size 401

runs/Mar30_21-16-42_5cae252bde23/events.out.tfevents.1711833603.5cae252bde23.1389.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d96acbc68572899e75585f8fc1e0d337eaec10b320c0020b4a9e5b7d3a16143
+size 5810

runs/Mar30_21-16-42_5cae252bde23/events.out.tfevents.1711837307.5cae252bde23.1389.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d68f6e4a02f29d6bd0c7eab039037be2a9dc8a9fe8709393d9196e17f62e38b
+size 401

runs/Mar30_22-26-03_5cae252bde23/events.out.tfevents.1711837656.5cae252bde23.1389.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db3844b6c83546a4d930e46d090498ea6c3e99e1336275502e4a7c248d2ed64c
+size 5810

runs/Mar30_22-26-03_5cae252bde23/events.out.tfevents.1711839515.5cae252bde23.1389.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:090f0a2f4a7a8fcbb8d922a1f4e9f72d3dfd1489776cdb17fe34ab9e2c208158
+size 401

runs/Mar30_23-19-56_5cae252bde23/events.out.tfevents.1711841011.5cae252bde23.1389.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed8eb6ed922ba0b60a247ff9359d5ac719b8ada7ae12606d99b7dd4acf181a63
+size 5462

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": "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 sha256:97859b17d5b9b2d376dd2aeefa2b0b350adc607c0dd2d80b98bd5ebd8515d954
+size 5048