End of training

README.md

@@ -1,5 +1,4 @@
 ---
-base_model: ahmeddbahaa/mT5_multilingual_XLSum-finetuned-ar
 tags:
 - generated_from_trainer
 model-index:
@@ -12,7 +11,14 @@ should probably proofread and complete it, then remove this comment. -->
 
 # results_mt5_xl-sum
 
-This model is a fine-tuned version of [ahmeddbahaa/mT5_multilingual_XLSum-finetuned-ar](https://huggingface.co/ahmeddbahaa/mT5_multilingual_XLSum-finetuned-ar) on an unknown dataset.
+This model was trained from scratch on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.8431
+- Rouge1 Fmeasure: 0.6139
+- Rouge2 Fmeasure: 0.1189
+- Rougel Fmeasure: 0.1997
+- Meteor: 0.3315
+- Bertscore F1: 0.8418
 
 ## Model description
 
@@ -32,16 +38,32 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0005
-- train_batch_size: 2
-- eval_batch_size: 2
+- train_batch_size: 4
+- eval_batch_size: 4
 - seed: 42
-- gradient_accumulation_steps: 8
-- total_train_batch_size: 16
+- gradient_accumulation_steps: 16
+- total_train_batch_size: 64
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 250
 - num_epochs: 10
-- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Rouge1 Fmeasure | Rouge2 Fmeasure | Rougel Fmeasure | Meteor | Bertscore F1 |
+|:-------------:|:------:|:----:|:---------------:|:---------------:|:---------------:|:---------------:|:------:|:------------:|
+| 2.6516        | 0.8529 | 500  | 0.9710          | 0.2668          | 0.0484          | 0.1537          | 0.2745 | 0.8284       |
+| 1.0475        | 1.7058 | 1000 | 0.8792          | 0.4289          | 0.0884          | 0.1737          | 0.2949 | 0.8278       |
+| 0.9413        | 2.5586 | 1500 | 0.8457          | 0.4960          | 0.0865          | 0.1898          | 0.3141 | 0.8339       |
+| 0.8711        | 3.4115 | 2000 | 0.8398          | 0.5400          | 0.1121          | 0.1941          | 0.3110 | 0.8397       |
+| 0.8235        | 4.2644 | 2500 | 0.8345          | 0.5587          | 0.1022          | 0.2041          | 0.3160 | 0.8388       |
+| 0.7797        | 5.1173 | 3000 | 0.8368          | 0.5735          | 0.1036          | 0.2044          | 0.3157 | 0.8344       |
+| 0.7401        | 5.9701 | 3500 | 0.8217          | 0.5507          | 0.1133          | 0.1936          | 0.3186 | 0.8366       |
+| 0.7022        | 6.8230 | 4000 | 0.8361          | 0.5808          | 0.1118          | 0.2008          | 0.3227 | 0.8406       |
+| 0.6796        | 7.6759 | 4500 | 0.8344          | 0.6173          | 0.1277          | 0.1986          | 0.3260 | 0.8407       |
+| 0.6523        | 8.5288 | 5000 | 0.8436          | 0.6232          | 0.1186          | 0.2024          | 0.3317 | 0.8398       |
+| 0.6385        | 9.3817 | 5500 | 0.8431          | 0.6139          | 0.1189          | 0.1997          | 0.3315 | 0.8418       |
+
 
 ### Framework versions
 

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "ahmeddbahaa/mT5_multilingual_XLSum-finetuned-ar",
+  "_name_or_path": "csebuetnlp/mT5_multilingual_XLSum",
   "architectures": [
     "MT5ForConditionalGeneration"
   ],

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f0df86a0b364ee3ebf8cc7ee044de831c60efb2b16c4adb3b6c63290f97727a
+oid sha256:8c8a8586fae75d1a71505ff6a91cdbfe2f3835003f1230e9f90998a83deac3d4
 size 2329601904

runs/Jul24_14-41-57_f531c75ea080/events.out.tfevents.1721832321.f531c75ea080.1181.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a700371ce49ecc5b891da5dff4ffd0d5eac40f720a91aa5e8981b5c2b50397ee
+size 15493

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59a46e92c70ae431bcb2de7cf875d9cf2a4eecd1a41c9ed516208800929118a1
-size 16315456
+oid sha256:c75db174930c130a1b55e88f4ee57d5f706099adf12eb9c22bc9ef7c599da913
+size 16330805

tokenizer_config.json

@@ -1,4 +1,5 @@
 {
+  "add_prefix_space": true,
   "added_tokens_decoder": {
     "0": {
       "content": "<pad>",
@@ -29,13 +30,10 @@
   "clean_up_tokenization_spaces": true,
   "eos_token": "</s>",
   "extra_ids": 0,
-  "max_length": 128,
+  "legacy": true,
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<pad>",
   "sp_model_kwargs": {},
-  "stride": 0,
   "tokenizer_class": "T5Tokenizer",
-  "truncation_side": "right",
-  "truncation_strategy": "longest_first",
   "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4fda699c241d0c8c9bd3a8265561b86c476853abb0ce15bb55d1b1b3eeccfb7b
+oid sha256:d415f66977db62e6e69262ed0fcbc54908e68fff0d6f1b3f0096c64c2ca3ef6d
 size 6712