oddadmix/masrawy-english-arabic-translator-clauda-opus-v1

README.md

@@ -0,0 +1,71 @@
+---
+license: apache-2.0
+base_model: Helsinki-NLP/opus-mt-en-ar
+tags:
+- generated_from_trainer
+model-index:
+- name: masrawy-english-arabic-translator-clauda-opus-v1
+  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-clauda-opus-v1
+
+This model is a fine-tuned version of [Helsinki-NLP/opus-mt-en-ar](https://huggingface.co/Helsinki-NLP/opus-mt-en-ar) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.8534
+
+## 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: 32
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 15
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss |
+|:-------------:|:-----:|:-----:|:---------------:|
+| 2.8787        | 1.0   | 3529  | 2.7030          |
+| 2.6107        | 2.0   | 7058  | 2.5211          |
+| 2.4579        | 3.0   | 10587 | 2.4222          |
+| 2.3906        | 4.0   | 14116 | 2.3666          |
+| 2.2673        | 5.0   | 17645 | 2.3260          |
+| 2.2383        | 6.0   | 21174 | 2.2936          |
+| 2.1464        | 7.0   | 24703 | 2.2754          |
+| 2.1304        | 8.0   | 28232 | 2.2530          |
+| 2.0802        | 9.0   | 31761 | 2.2417          |
+| 2.048         | 10.0  | 35290 | 2.2341          |
+| 2.0323        | 11.0  | 38819 | 2.2255          |
+| 2.0012        | 12.0  | 42348 | 2.2233          |
+| 1.9905        | 13.0  | 45877 | 2.2193          |
+| 1.9648        | 14.0  | 49406 | 2.2162          |
+| 1.9716        | 15.0  | 52935 | 1.8534          |
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.1.1+cu121
+- Datasets 2.14.5
+- Tokenizers 0.15.1

config.json

@@ -0,0 +1,61 @@
+{
+  "_name_or_path": "Helsinki-NLP/opus-mt-en-ar",
+  "activation_dropout": 0.0,
+  "activation_function": "swish",
+  "add_bias_logits": false,
+  "add_final_layer_norm": false,
+  "architectures": [
+    "MarianMTModel"
+  ],
+  "attention_dropout": 0.0,
+  "bad_words_ids": [
+    [
+      62801
+    ]
+  ],
+  "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": 62801,
+  "decoder_vocab_size": 62802,
+  "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": 62802,
+  "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": 512,
+  "max_position_embeddings": 512,
+  "model_type": "marian",
+  "normalize_before": false,
+  "normalize_embedding": false,
+  "num_beams": 4,
+  "num_hidden_layers": 6,
+  "pad_token_id": 62801,
+  "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": 62802
+}

generation_config.json

@@ -0,0 +1,16 @@
+{
+  "bad_words_ids": [
+    [
+      62801
+    ]
+  ],
+  "bos_token_id": 0,
+  "decoder_start_token_id": 62801,
+  "eos_token_id": 0,
+  "forced_eos_token_id": 0,
+  "max_length": 512,
+  "num_beams": 4,
+  "pad_token_id": 62801,
+  "renormalize_logits": true,
+  "transformers_version": "4.35.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c06045c1aa28e023e9f07d69ceb22a44c1b1ea9ebbf1c1bf81ddb84fbf1fcda
+size 305452744

runs/Dec06_05-25-54_ngqm1asm95/events.out.tfevents.1733462755.ngqm1asm95.82.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:309dc6a5c60242083db0097a62839dcb02e607be07cac854b81d3fab281bc866
+size 25287

runs/Dec06_11-43-39_ny9ms9c3tk/events.out.tfevents.1733485423.ny9ms9c3tk.82.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78666e48e25702053f1c971906e1816050251428b679b8e89409c1d18d3273c9
+size 6335

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": {
+    "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
+    },
+    "62801": {
+      "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": "eng",
+  "sp_model_kwargs": {},
+  "target_lang": "ara",
+  "tokenizer_class": "MarianTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e43657cb6f7277d8f711eb2f810cbc3fdc53afe035e5f42cd4193197189777d8
+size 4792