oddadmix/masrawy-english-arabic-translator-opus-big-v2.8-only-claude-eval-as-test

README.md

@@ -0,0 +1,60 @@
+---
+license: cc-by-4.0
+base_model: Helsinki-NLP/opus-mt-tc-big-en-ar
+tags:
+- generated_from_trainer
+model-index:
+- name: masrawy-english-arabic-translator-opus-big-v2.8-only-claude-eval-as-test
+  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. -->
+
+# masrawy-english-arabic-translator-opus-big-v2.8-only-claude-eval-as-test
+
+This model is a fine-tuned version of [Helsinki-NLP/opus-mt-tc-big-en-ar](https://huggingface.co/Helsinki-NLP/opus-mt-tc-big-en-ar) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.3183
+
+## 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: 5e-05
+- train_batch_size: 64
+- eval_batch_size: 64
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 2
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 2.8734        | 0.42  | 1000 | 1.4521          |
+| 2.6556        | 0.83  | 2000 | 1.3604          |
+| 2.4215        | 1.25  | 3000 | 1.3340          |
+| 2.3495        | 1.66  | 4000 | 1.3183          |
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.1.1+cu121
+- Datasets 3.2.0
+- Tokenizers 0.15.1

config.json

@@ -0,0 +1,46 @@
+{
+  "_name_or_path": "Helsinki-NLP/opus-mt-tc-big-en-ar",
+  "activation_dropout": 0.0,
+  "activation_function": "relu",
+  "architectures": [
+    "MarianMTModel"
+  ],
+  "attention_dropout": 0.0,
+  "bad_words_ids": [
+    [
+      61246
+    ]
+  ],
+  "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": 61246,
+  "decoder_vocab_size": 61247,
+  "dropout": 0.1,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_token_id": 25897,
+  "forced_eos_token_id": 25897,
+  "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": 61246,
+  "scale_embedding": true,
+  "share_encoder_decoder_embeddings": true,
+  "static_position_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "use_cache": true,
+  "vocab_size": 61247
+}

generation_config.json

@@ -0,0 +1,16 @@
+{
+  "bad_words_ids": [
+    [
+      61246
+    ]
+  ],
+  "bos_token_id": 0,
+  "decoder_start_token_id": 61246,
+  "eos_token_id": 25897,
+  "forced_eos_token_id": 25897,
+  "max_length": 512,
+  "num_beams": 4,
+  "pad_token_id": 61246,
+  "renormalize_logits": true,
+  "transformers_version": "4.35.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2b2ae7b283204aa6888a9c756d2451e5b121e8885934301e634f95ada8e7aef
+size 956571820

runs/Jan02_19-59-30_ny55ag5bbw/events.out.tfevents.1735847970.ny55ag5bbw.81.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b35e5ea390e52fd9188eaad4e6ce94a13ec48970ad4d44b0c71448737f19a1b6
+size 88

runs/Jan02_20-00-05_ny55ag5bbw/events.out.tfevents.1735848005.ny55ag5bbw.81.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:741dbdc4797e3ec781cd659beb2d378724e87f558e23a91e836b2745317ed84c
+size 88

runs/Jan02_20-03-15_nkxgu8omhm/events.out.tfevents.1735848198.nkxgu8omhm.82.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23901bce7551e31d30ee5a96627b941355609caf4ffb2b09d65be5fbc56a5f98
+size 7885

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": {
+    "25897": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "30683": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "61246": {
+      "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>",
+  "separate_vocabs": false,
+  "source_lang": "en",
+  "sp_model_kwargs": {},
+  "target_lang": "ar",
+  "tokenizer_class": "MarianTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2933943d066ddc11fc93e0c6f3c08ae54d5ac1adadbd41de4be5e43e613a151a
+size 4856