End of training

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,51 @@
+---
+base_model: ahmeddbahaa/mT5_multilingual_XLSum-finetuned-ar
+tags:
+- generated_from_trainer
+model-index:
+- name: results_mt5_xl-sum
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+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.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0005
+- train_batch_size: 2
+- eval_batch_size: 2
+- seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 16
+- 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
+
+### Framework versions
+
+- Transformers 4.40.0
+- Pytorch 2.3.1+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "ahmeddbahaa/mT5_multilingual_XLSum-finetuned-ar",
+  "architectures": [
+    "MT5ForConditionalGeneration"
+  ],
+  "classifier_dropout": 0.0,
+  "d_ff": 2048,
+  "d_kv": 64,
+  "d_model": 768,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "gelu_new",
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "gated-gelu",
+  "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,
+  "num_decoder_layers": 12,
+  "num_heads": 12,
+  "num_layers": 12,
+  "output_past": true,
+  "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": "4.40.0",
+  "use_cache": true,
+  "vocab_size": 250112
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "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": "4.40.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f0df86a0b364ee3ebf8cc7ee044de831c60efb2b16c4adb3b6c63290f97727a
+size 2329601904

runs/Jul22_20-27-51_1acbbaf73417/events.out.tfevents.1721680167.1acbbaf73417.278.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8798012bc47e567c63a6114e1dfb05d489fca0ed32b0376fc40fcd5d7fa8d093
+size 14316

runs/Jul22_20-51-51_1acbbaf73417/events.out.tfevents.1721681688.1acbbaf73417.278.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f717fcb459bf58f978ab78d642d34f6578d7de59991fde6de2994b0b39b0ba9
+size 7202

runs/Jul22_20-51-51_1acbbaf73417/events.out.tfevents.1721683025.1acbbaf73417.278.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:189342f0db5539ac87eb6aeea0bcdcd50bd6158f996ad4d2682f5f66e9097fcd
+size 7205

runs/Jul22_20-51-51_1acbbaf73417/events.out.tfevents.1721683083.1acbbaf73417.278.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a3371aa3ff78d6a4ba30bb8efe098c1128b08b6d8b5a3d2ed73efd965b6234b
+size 7202

runs/Jul22_22-22-32_1acbbaf73417/events.out.tfevents.1721687106.1acbbaf73417.31526.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af381a48e0ca257ed4d1e75f81470971848c8d6e71f0eadf071fe0a5d4b7e059
+size 6764

runs/Jul22_22-22-32_1acbbaf73417/events.out.tfevents.1721695168.1acbbaf73417.31526.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fa2882c0147273f12f2d0799e9ad97536f866e4a4f3dc7f23826dec7bbe5393
+size 6764

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "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
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
+size 4309802

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59a46e92c70ae431bcb2de7cf875d9cf2a4eecd1a41c9ed516208800929118a1
+size 16315456

tokenizer_config.json

@@ -0,0 +1,41 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "extra_ids": 0,
+  "max_length": 128,
+  "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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fda699c241d0c8c9bd3a8265561b86c476853abb0ce15bb55d1b1b3eeccfb7b
+size 6712