BounharAbdelaziz/Transliteration-Moroccan-Darija

README.md

@@ -30,9 +30,9 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0005
-- train_batch_size: 384
-- eval_batch_size: 384
+- learning_rate: 0.05
+- train_batch_size: 512
+- eval_batch_size: 512
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "./BounharAbdelaziz/Transliteration-Moroccan-Darija/checkpoint-5000/",
+  "_name_or_path": "./checkpoint-1500/",
   "architectures": [
     "EncoderDecoderModel"
   ],
@@ -26,7 +26,7 @@
     "forced_eos_token_id": null,
     "hidden_act": "gelu",
     "hidden_dropout_prob": 0.1,
-    "hidden_size": 512,
+    "hidden_size": 64,
     "id2label": {
       "0": "LABEL_0",
       "1": "LABEL_1"
@@ -46,10 +46,10 @@
     "min_length": 0,
     "model_type": "bert",
     "no_repeat_ngram_size": 0,
-    "num_attention_heads": 8,
+    "num_attention_heads": 2,
     "num_beam_groups": 1,
     "num_beams": 1,
-    "num_hidden_layers": 4,
+    "num_hidden_layers": 2,
     "num_return_sequences": 1,
     "output_attentions": false,
     "output_hidden_states": false,
@@ -81,7 +81,7 @@
     "use_cache": true,
     "vocab_size": 30522
   },
-  "decoder_start_token_id": 15,
+  "decoder_start_token_id": 1,
   "encoder": {
     "_name_or_path": "",
     "add_cross_attention": false,
@@ -105,7 +105,7 @@
     "forced_eos_token_id": null,
     "hidden_act": "gelu",
     "hidden_dropout_prob": 0.1,
-    "hidden_size": 512,
+    "hidden_size": 64,
     "id2label": {
       "0": "LABEL_0",
       "1": "LABEL_1"
@@ -125,10 +125,10 @@
     "min_length": 0,
     "model_type": "bert",
     "no_repeat_ngram_size": 0,
-    "num_attention_heads": 8,
+    "num_attention_heads": 2,
     "num_beam_groups": 1,
     "num_beams": 1,
-    "num_hidden_layers": 4,
+    "num_hidden_layers": 2,
     "num_return_sequences": 1,
     "output_attentions": false,
     "output_hidden_states": false,
@@ -162,7 +162,7 @@
   },
   "is_encoder_decoder": true,
   "model_type": "encoder-decoder",
-  "pad_token_id": 14,
+  "pad_token_id": 0,
   "torch_dtype": "float32",
   "transformers_version": "4.39.2"
 }

generation_config.json

@@ -1,6 +1,6 @@
 {
   "_from_model_config": true,
-  "decoder_start_token_id": 15,
-  "pad_token_id": 14,
+  "decoder_start_token_id": 1,
+  "pad_token_id": 0,
   "transformers_version": "4.39.2"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ececda637307182678f8138549fe6e6a9a1bc86299ef7c211595b3807811187
-size 280671840
+oid sha256:816a30480e3c6c9dbbbb8beda170def7573bba47ecbd7ea18790f9829eadfcae
+size 22805496

special_tokens_map.json

@@ -1,9 +1,30 @@
 {
-  "bos_token": "<sos>",
-  "cls_token": "[CLS]",
-  "eos_token": "<eos>",
-  "mask_token": "[MASK]",
-  "pad_token": "<pad>",
-  "sep_token": "[SEP]",
-  "unk_token": "<unk>"
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer_config.json

@@ -1,14 +1,6 @@
 {
   "added_tokens_decoder": {
-    "13": {
-      "content": "<eos>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "14": {
+    "0": {
       "content": "<pad>",
       "lstrip": false,
       "normalized": false,
@@ -16,40 +8,24 @@
       "single_word": false,
       "special": true
     },
-    "15": {
-      "content": "<sos>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "16": {
-      "content": "<unk>",
+    "1": {
+      "content": "<bos>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "85": {
-      "content": "[SEP]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "86": {
-      "content": "[CLS]",
+    "2": {
+      "content": "<eos>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "87": {
-      "content": "[MASK]",
+    "3": {
+      "content": "<unk>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -57,27 +33,11 @@
       "special": true
     }
   },
-  "bos_token": "<sos>",
+  "bos_token": "<bos>",
   "clean_up_tokenization_spaces": true,
-  "cls_token": "[CLS]",
-  "do_basic_tokenize": true,
-  "do_lower_case": true,
   "eos_token": "<eos>",
-  "mask_token": "[MASK]",
-  "max_length": 128,
   "model_max_length": 1000000000000000019884624838656,
-  "never_split": null,
-  "pad_to_multiple_of": null,
   "pad_token": "<pad>",
-  "pad_token_type_id": 0,
-  "padding_side": "right",
-  "sep_token": "[SEP]",
-  "stride": 0,
-  "strip_accents": null,
-  "tokenize_chinese_chars": true,
-  "tokenizer_class": "BertTokenizer",
-  "trainable": true,
-  "truncation_side": "right",
-  "truncation_strategy": "longest_first",
+  "tokenizer_class": "PreTrainedTokenizerFast",
   "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:451ec24aae7e96054ac1348fb7c1ce2acc36f6242c9a05fe6fb4a94c07f2d26f
+oid sha256:000459e2b1cc8e87d2d315734c195c15b6a59ac770c9921ddf85433e87be1519
 size 5048