oddadmix/English-To-EgyptianArabic-Translator

README.md

@@ -1,5 +1,4 @@
 ---
-library_name: transformers
 license: apache-2.0
 base_model: Helsinki-NLP/opus-mt-en-ar
 tags:
@@ -16,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 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: 1.8338
+- Loss: 2.3011
 
 ## Model description
 
@@ -39,7 +38,7 @@ The following hyperparameters were used during training:
 - train_batch_size: 16
 - eval_batch_size: 16
 - seed: 42
-- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - num_epochs: 20
 - mixed_precision_training: Native AMP
@@ -48,31 +47,31 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step  | Validation Loss |
 |:-------------:|:-----:|:-----:|:---------------:|
-| 2.1222        | 1.0   | 2019  | 1.9246          |
-| 1.9763        | 2.0   | 4038  | 1.8663          |
-| 1.8834        | 3.0   | 6057  | 1.8480          |
-| 1.8057        | 4.0   | 8076  | 1.8384          |
-| 1.7176        | 5.0   | 10095 | 1.8243          |
-| 1.6813        | 6.0   | 12114 | 1.8235          |
-| 1.5903        | 7.0   | 14133 | 1.8270          |
-| 1.5615        | 8.0   | 16152 | 1.8201          |
-| 1.4726        | 9.0   | 18171 | 1.8227          |
-| 1.4401        | 10.0  | 20190 | 1.8223          |
-| 1.4126        | 11.0  | 22209 | 1.8224          |
-| 1.4119        | 12.0  | 24228 | 1.8266          |
-| 1.3976        | 13.0  | 26247 | 1.8301          |
-| 1.3645        | 14.0  | 28266 | 1.8272          |
-| 1.3199        | 15.0  | 30285 | 1.8312          |
-| 1.3365        | 16.0  | 32304 | 1.8322          |
-| 1.2928        | 17.0  | 34323 | 1.8309          |
-| 1.2352        | 18.0  | 36342 | 1.8310          |
-| 1.2561        | 19.0  | 38361 | 1.8321          |
-| 1.2623        | 20.0  | 40380 | 1.8338          |
+| 2.9907        | 1.0   | 2396  | 2.7717          |
+| 2.6732        | 2.0   | 4792  | 2.5879          |
+| 2.4873        | 3.0   | 7188  | 2.5003          |
+| 2.2897        | 4.0   | 9584  | 2.4407          |
+| 2.2402        | 5.0   | 11980 | 2.4038          |
+| 2.1045        | 6.0   | 14376 | 2.3795          |
+| 2.032         | 7.0   | 16772 | 2.3621          |
+| 1.9792        | 8.0   | 19168 | 2.3410          |
+| 1.9129        | 9.0   | 21564 | 2.3319          |
+| 1.8975        | 10.0  | 23960 | 2.3192          |
+| 1.8107        | 11.0  | 26356 | 2.3170          |
+| 1.7901        | 12.0  | 28752 | 2.3128          |
+| 1.7654        | 13.0  | 31148 | 2.3061          |
+| 1.6899        | 14.0  | 33544 | 2.3042          |
+| 1.6535        | 15.0  | 35940 | 2.3061          |
+| 1.6733        | 16.0  | 38336 | 2.3027          |
+| 1.6643        | 17.0  | 40732 | 2.3029          |
+| 1.6471        | 18.0  | 43128 | 2.2996          |
+| 1.6138        | 19.0  | 45524 | 2.3013          |
+| 1.5878        | 20.0  | 47920 | 2.3011          |
 
 
 ### Framework versions
 
-- Transformers 4.46.3
+- Transformers 4.35.2
 - Pytorch 2.1.1+cu121
-- Datasets 3.1.0
-- Tokenizers 0.20.3
+- Datasets 2.14.5
+- Tokenizers 0.15.1

config.json

@@ -8,6 +8,11 @@
     "MarianMTModel"
   ],
   "attention_dropout": 0.0,
+  "bad_words_ids": [
+    [
+      62801
+    ]
+  ],
   "bos_token_id": 0,
   "classif_dropout": 0.0,
   "classifier_dropout": 0.0,
@@ -38,19 +43,19 @@
     "LABEL_1": 1,
     "LABEL_2": 2
   },
-  "max_length": null,
+  "max_length": 512,
   "max_position_embeddings": 512,
   "model_type": "marian",
   "normalize_before": false,
   "normalize_embedding": false,
-  "num_beams": null,
+  "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": "4.46.3",
+  "transformers_version": "4.35.2",
   "use_cache": true,
   "vocab_size": 62802
 }

generation_config.json

@@ -12,5 +12,5 @@
   "num_beams": 4,
   "pad_token_id": 62801,
   "renormalize_logits": true,
-  "transformers_version": "4.46.3"
+  "transformers_version": "4.35.2"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0710204ebe8eca4fd75b4a52492ecfdeda7663e44497a25e2650d9450ba367c6
+oid sha256:1223ea902922c7d3e3e45d91653ad8b5bc298a15a545af2ed1e94256d2a0fe29
 size 305452744

runs/Nov21_02-34-07_ncgki16hjz/events.out.tfevents.1732156449.ncgki16hjz.205.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4d3920a7f74979318891a16ee96ad593565120771308c559a874f477c6ec299
+size 5182

runs/Nov21_02-35-33_ncgki16hjz/events.out.tfevents.1732156534.ncgki16hjz.205.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:117a726ea6504ed4924f0a541d0986921f9d38c44eb30604f7d2f167c05bfeba
+size 26136

tokenizer_config.json

@@ -25,7 +25,7 @@
       "special": true
     }
   },
-  "clean_up_tokenization_spaces": false,
+  "clean_up_tokenization_spaces": true,
   "eos_token": "</s>",
   "model_max_length": 512,
   "pad_token": "<pad>",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65d24f948d8bd5c43d55238c89b87846c3bc45c8c9cb75d128d4dc98318f25d6
-size 5496
+oid sha256:b5311556afb3e79c7fd4cda661dce16faffba5d838a87824999817ae88082578
+size 4792