End of training

README.md

@@ -1,5 +1,5 @@
 ---
-base_model: csebuetnlp/mT5_multilingual_XLSum
+base_model: malmarjeh/t5-arabic-text-summarization
 tags:
 - generated_from_trainer
 metrics:
@@ -14,14 +14,14 @@ should probably proofread and complete it, then remove this comment. -->
 
 # results_mt5_large
 
-This model is a fine-tuned version of [csebuetnlp/mT5_multilingual_XLSum](https://huggingface.co/csebuetnlp/mT5_multilingual_XLSum) on an unknown dataset.
+This model is a fine-tuned version of [malmarjeh/t5-arabic-text-summarization](https://huggingface.co/malmarjeh/t5-arabic-text-summarization) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: nan
-- Rouge1: 0.0
-- Rouge2: 0.0
-- Rougel: 0.0
-- Rougelsum: 0.0
-- Gen Len: 83.0
+- Loss: 0.0152
+- Rouge1: 0.1424
+- Rouge2: 0.0231
+- Rougel: 0.1425
+- Rougelsum: 0.1425
+- Gen Len: 18.7888
 
 ## Model description
 
@@ -54,15 +54,21 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Gen Len | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
 |:-------------:|:-----:|:----:|:-------:|:---------------:|:------:|:------:|:------:|:---------:|
-| 0.3998        | 0.11  | 500  | 81.3658 | 0.1042          | 0.161  | 0.0456 | 0.16   | 0.1601    |
-| 0.3176        | 0.22  | 1000 | 81.3658 | 0.1042          | 0.161  | 0.0456 | 0.16   | 0.1601    |
-| 0.3449        | 0.32  | 1500 | 81.3658 | 0.1042          | 0.161  | 0.0456 | 0.16   | 0.1601    |
-| 0.3739        | 0.43  | 2000 | nan     | 0.0             | 0.0    | 0.0    | 0.0    | 83.0      |
+| 2.5321        | 0.23  | 500  | 16.1877 | 0.1695          | 0.1549 | 0.0284 | 0.1546 | 0.1542    |
+| 2.6555        | 0.46  | 1000 | 13.5126 | 0.8393          | 0.1453 | 0.0271 | 0.1451 | 0.1453    |
+| 0.4292        | 0.7   | 1500 | 0.0667  | 0.1383          | 0.017  | 0.1389 | 0.1389 | 18.9296   |
+| 0.1733        | 0.93  | 2000 | 0.0385  | 0.1441          | 0.0216 | 0.1445 | 0.1447 | 19.0      |
+| 0.114         | 1.16  | 2500 | 0.0248  | 0.1414          | 0.0209 | 0.1415 | 0.142  | 19.0      |
+| 0.0858        | 1.39  | 3000 | 0.0248  | 0.1398          | 0.021  | 0.1401 | 0.1402 | 18.8375   |
+| 0.0667        | 1.62  | 3500 | 0.0205  | 0.1442          | 0.024  | 0.1445 | 0.1445 | 19.0      |
+| 0.053         | 1.86  | 4000 | 0.0164  | 0.1556          | 0.0352 | 0.1553 | 0.1562 | 18.843    |
+| 0.0426        | 2.09  | 4500 | 0.0140  | 0.1497          | 0.0287 | 0.1501 | 0.1504 | 18.9188   |
+| 0.0402        | 2.32  | 5000 | 0.0152  | 0.1424          | 0.0231 | 0.1425 | 0.1425 | 18.7888   |
 
 
 ### Framework versions
 
-- Transformers 4.39.0.dev0
+- Transformers 4.40.0.dev0
 - Pytorch 2.2.1+cu121
 - Datasets 2.18.0
 - Tokenizers 0.15.2

config.json

@@ -1,7 +1,7 @@
 {
-  "_name_or_path": "csebuetnlp/mT5_multilingual_XLSum",
+  "_name_or_path": "malmarjeh/t5-arabic-text-summarization",
   "architectures": [
-    "MT5ForConditionalGeneration"
+    "T5ForConditionalGeneration"
   ],
   "classifier_dropout": 0.0,
   "d_ff": 2048,
@@ -12,15 +12,12 @@
   "dropout_rate": 0.1,
   "eos_token_id": 1,
   "feed_forward_proj": "gated-gelu",
+  "gradient_checkpointing": false,
   "initializer_factor": 1.0,
   "is_encoder_decoder": true,
   "is_gated_act": true,
   "layer_norm_epsilon": 1e-06,
-  "length_penalty": 0.6,
-  "max_length": 84,
-  "model_type": "mt5",
-  "no_repeat_ngram_size": 2,
-  "num_beams": 4,
+  "model_type": "t5",
   "num_decoder_layers": 12,
   "num_heads": 12,
   "num_layers": 12,
@@ -28,10 +25,8 @@
   "pad_token_id": 0,
   "relative_attention_max_distance": 128,
   "relative_attention_num_buckets": 32,
-  "tie_word_embeddings": false,
-  "tokenizer_class": "T5Tokenizer",
   "torch_dtype": "float32",
-  "transformers_version": "4.39.0.dev0",
+  "transformers_version": "4.40.0.dev0",
   "use_cache": true,
-  "vocab_size": 250112
+  "vocab_size": 110080
 }

generation_config.json

@@ -1,10 +1,6 @@
 {
   "decoder_start_token_id": 0,
   "eos_token_id": 1,
-  "length_penalty": 0.6,
-  "max_length": 84,
-  "no_repeat_ngram_size": 2,
-  "num_beams": 4,
   "pad_token_id": 0,
-  "transformers_version": "4.39.0.dev0"
+  "transformers_version": "4.40.0.dev0"
 }

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b58bd8342c59711a1b0f1afc9a4698bd97dbaacb784d6599d1878cb914d338d
+size 1131180462

spiece.model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
-size 4309802
+oid sha256:5c7ae4407451bf02b459edec774d0539a06615005dd34d5c85c5c06765ff1606
+size 2435308

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5d0e18b86936c25d0717f6717f0c87a0576aaa261e4dc1818ac723ca2da021a
-size 16330827
+oid sha256:b53165a0d39eb514f956423ba2d16dd1aa1434c57627afa11d13d5a326769963
+size 7771660

tokenizer_config.json

@@ -31,6 +31,7 @@
   "eos_token": "</s>",
   "extra_ids": 0,
   "legacy": true,
+  "max_new_tokens": 512,
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<pad>",
   "sp_model_kwargs": {},

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:317f3a2eebc433b6461844a50f474425b45802e0e9ad887e5e4e39e58b974f85
-size 4984
+oid sha256:b2e8e680ee4a8101ba3668bf7e6f1ca9b607e50c549fc7f68357284e79600e1a
+size 5048