Samuael/amBART_1000

README.md

@@ -1,4 +1,5 @@
 ---
+base_model: Samuael/amBART_1000
 tags:
 - generated_from_trainer
 model-index:
@@ -11,7 +12,17 @@ should probably proofread and complete it, then remove this comment. -->
 
 # amBART
 
-This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
+This model is a fine-tuned version of [Samuael/amBART_1000](https://huggingface.co/Samuael/amBART_1000) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- eval_loss: 2.9935
+- eval_wer: 0.9817
+- eval_cer: 0.7707
+- eval_bleu: 0.7418
+- eval_runtime: 9.129
+- eval_samples_per_second: 39.325
+- eval_steps_per_second: 0.329
+- epoch: 3.0
+- step: 2127
 
 ## Model description
 
@@ -30,17 +41,18 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.005
-- train_batch_size: 64
-- eval_batch_size: 64
+- learning_rate: 0.002
+- train_batch_size: 128
+- eval_batch_size: 128
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 30
+- num_epochs: 50
+- mixed_precision_training: Native AMP
 
 ### Framework versions
 
-- Transformers 4.38.1
+- Transformers 4.38.2
 - Pytorch 2.1.0+cu121
 - Datasets 2.18.0
 - Tokenizers 0.15.2

config.json

@@ -1,8 +1,9 @@
 {
+  "_name_or_path": "Samuael/amBART_1000",
   "activation_dropout": 0.0,
   "activation_function": "gelu",
   "architectures": [
-    "MBartModel"
+    "MBartForConditionalGeneration"
   ],
   "attention_dropout": 0.0,
   "bos_token_id": 0,
@@ -30,5 +31,5 @@
   "torch_dtype": "float32",
   "transformers_version": "4.38.2",
   "use_cache": true,
-  "vocab_size": 260
+  "vocab_size": 1027
 }

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "forced_eos_token_id": 2,
+  "max_length": 300,
+  "pad_token_id": 1,
+  "transformers_version": "4.38.2"
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57edf11149bec1eb85c6a8a425f6a023546e7838de010875b91419bea4fadbef
-size 179236624
+oid sha256:1504bcd0758ac82ab09f78650ebc0c7c431edde67e78c5fb92b4befcf30c490e
+size 180813204

sentencepiece.bpe.model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc579c42f174c74d5a56bc4a02e6eef7759711b9415d2fd1bf4810683bdb69c5
-size 240450
+oid sha256:8b2c9b3910462e773a7ace377cb26a40053dcfe4054d8eb8ecc5460495a93d9b
+size 253575

special_tokens_map.json

@@ -1,12 +1,73 @@
 {
   "additional_special_tokens": [
     "ar_AR",
-    "cs_CZ"
+    "cs_CZ",
+    "de_DE",
+    "en_XX",
+    "es_XX",
+    "et_EE",
+    "fi_FI",
+    "fr_XX",
+    "gu_IN",
+    "hi_IN",
+    "it_IT",
+    "ja_XX",
+    "kk_KZ",
+    "ko_KR",
+    "lt_LT",
+    "lv_LV",
+    "my_MM",
+    "ne_NP",
+    "nl_XX",
+    "ro_RO",
+    "ru_RU",
+    "si_LK",
+    "tr_TR",
+    "vi_VN",
+    "zh_CN",
+    "▁በኋላ",
+    "ብር"
   ],
-  "bos_token": "<s>",
-  "cls_token": "<s>",
-  "eos_token": "</s>",
-  "pad_token": "<pad>",
-  "sep_token": "</s>",
-  "unk_token": "<unk>"
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "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

@@ -33,7 +33,7 @@
       "special": true
     },
     "234": {
-      "content": "ar_AR",
+      "content": "▁በኋላ",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -41,6 +41,22 @@
       "special": true
     },
     "235": {
+      "content": "ብር",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1001": {
+      "content": "ar_AR",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1002": {
       "content": "cs_CZ",
       "lstrip": false,
       "normalized": false,
@@ -48,7 +64,7 @@
       "single_word": false,
       "special": true
     },
-    "236": {
+    "1003": {
       "content": "de_DE",
       "lstrip": false,
       "normalized": false,
@@ -56,7 +72,7 @@
       "single_word": false,
       "special": true
     },
-    "237": {
+    "1004": {
       "content": "en_XX",
       "lstrip": false,
       "normalized": false,
@@ -64,7 +80,7 @@
       "single_word": false,
       "special": true
     },
-    "238": {
+    "1005": {
       "content": "es_XX",
       "lstrip": false,
       "normalized": false,
@@ -72,7 +88,7 @@
       "single_word": false,
       "special": true
     },
-    "239": {
+    "1006": {
       "content": "et_EE",
       "lstrip": false,
       "normalized": false,
@@ -80,7 +96,7 @@
       "single_word": false,
       "special": true
     },
-    "240": {
+    "1007": {
       "content": "fi_FI",
       "lstrip": false,
       "normalized": false,
@@ -88,7 +104,7 @@
       "single_word": false,
       "special": true
     },
-    "241": {
+    "1008": {
       "content": "fr_XX",
       "lstrip": false,
       "normalized": false,
@@ -96,7 +112,7 @@
       "single_word": false,
       "special": true
     },
-    "242": {
+    "1009": {
       "content": "gu_IN",
       "lstrip": false,
       "normalized": false,
@@ -104,7 +120,7 @@
       "single_word": false,
       "special": true
     },
-    "243": {
+    "1010": {
       "content": "hi_IN",
       "lstrip": false,
       "normalized": false,
@@ -112,7 +128,7 @@
       "single_word": false,
       "special": true
     },
-    "244": {
+    "1011": {
       "content": "it_IT",
       "lstrip": false,
       "normalized": false,
@@ -120,7 +136,7 @@
       "single_word": false,
       "special": true
     },
-    "245": {
+    "1012": {
       "content": "ja_XX",
       "lstrip": false,
       "normalized": false,
@@ -128,7 +144,7 @@
       "single_word": false,
       "special": true
     },
-    "246": {
+    "1013": {
       "content": "kk_KZ",
       "lstrip": false,
       "normalized": false,
@@ -136,7 +152,7 @@
       "single_word": false,
       "special": true
     },
-    "247": {
+    "1014": {
       "content": "ko_KR",
       "lstrip": false,
       "normalized": false,
@@ -144,7 +160,7 @@
       "single_word": false,
       "special": true
     },
-    "248": {
+    "1015": {
       "content": "lt_LT",
       "lstrip": false,
       "normalized": false,
@@ -152,7 +168,7 @@
       "single_word": false,
       "special": true
     },
-    "249": {
+    "1016": {
       "content": "lv_LV",
       "lstrip": false,
       "normalized": false,
@@ -160,7 +176,7 @@
       "single_word": false,
       "special": true
     },
-    "250": {
+    "1017": {
       "content": "my_MM",
       "lstrip": false,
       "normalized": false,
@@ -168,7 +184,7 @@
       "single_word": false,
       "special": true
     },
-    "251": {
+    "1018": {
       "content": "ne_NP",
       "lstrip": false,
       "normalized": false,
@@ -176,7 +192,7 @@
       "single_word": false,
       "special": true
     },
-    "252": {
+    "1019": {
       "content": "nl_XX",
       "lstrip": false,
       "normalized": false,
@@ -184,7 +200,7 @@
       "single_word": false,
       "special": true
     },
-    "253": {
+    "1020": {
       "content": "ro_RO",
       "lstrip": false,
       "normalized": false,
@@ -192,7 +208,7 @@
       "single_word": false,
       "special": true
     },
-    "254": {
+    "1021": {
       "content": "ru_RU",
       "lstrip": false,
       "normalized": false,
@@ -200,7 +216,7 @@
       "single_word": false,
       "special": true
     },
-    "255": {
+    "1022": {
       "content": "si_LK",
       "lstrip": false,
       "normalized": false,
@@ -208,7 +224,7 @@
       "single_word": false,
       "special": true
     },
-    "256": {
+    "1023": {
       "content": "tr_TR",
       "lstrip": false,
       "normalized": false,
@@ -216,7 +232,7 @@
       "single_word": false,
       "special": true
     },
-    "257": {
+    "1024": {
       "content": "vi_VN",
       "lstrip": false,
       "normalized": false,
@@ -224,7 +240,7 @@
       "single_word": false,
       "special": true
     },
-    "258": {
+    "1025": {
       "content": "zh_CN",
       "lstrip": false,
       "normalized": false,
@@ -235,7 +251,32 @@
   },
   "additional_special_tokens": [
     "ar_AR",
-    "cs_CZ"
+    "cs_CZ",
+    "de_DE",
+    "en_XX",
+    "es_XX",
+    "et_EE",
+    "fi_FI",
+    "fr_XX",
+    "gu_IN",
+    "hi_IN",
+    "it_IT",
+    "ja_XX",
+    "kk_KZ",
+    "ko_KR",
+    "lt_LT",
+    "lv_LV",
+    "my_MM",
+    "ne_NP",
+    "nl_XX",
+    "ro_RO",
+    "ru_RU",
+    "si_LK",
+    "tr_TR",
+    "vi_VN",
+    "zh_CN",
+    "▁በኋላ",
+    "ብር"
   ],
   "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
@@ -249,6 +290,5 @@
   "src_lang": "ar_AR",
   "tgt_lang": "cs_CZ",
   "tokenizer_class": "MBartTokenizer",
-  "tokenizer_file": null,
   "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e53a7bf06d7267874d2691850983fbffe4f8767761a181083359c679d97356d0
-size 5048
+oid sha256:f19be77b3b5f0472323533764679e1f13184f30ee05c97f781d3b916fe948fbe
+size 4984