End of training

README.md

@@ -0,0 +1,66 @@
+---
+base_model: malmarjeh/t5-arabic-text-summarization
+tags:
+- generated_from_trainer
+model-index:
+- name: t5-arabic-text-summarization-finetuned-xsum
+  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. -->
+
+# t5-arabic-text-summarization-finetuned-xsum
+
+This model is a fine-tuned version of [malmarjeh/t5-arabic-text-summarization](https://huggingface.co/malmarjeh/t5-arabic-text-summarization) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.5723
+
+## 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: 2e-05
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 10
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 4.7847        | 1.0   | 840  | 3.4060          |
+| 3.9577        | 2.0   | 1680 | 3.1634          |
+| 3.6274        | 3.0   | 2520 | 2.9916          |
+| 3.5127        | 4.0   | 3360 | 2.8185          |
+| 3.324         | 5.0   | 4200 | 2.7196          |
+| 3.2254        | 6.0   | 5040 | 2.6812          |
+| 3.2065        | 7.0   | 5880 | 2.6396          |
+| 3.1036        | 8.0   | 6720 | 2.5930          |
+| 3.0984        | 9.0   | 7560 | 2.5850          |
+| 2.9747        | 10.0  | 8400 | 2.5723          |
+
+
+### Framework versions
+
+- Transformers 4.36.2
+- Pytorch 2.0.0+cu118
+- Datasets 2.16.1
+- Tokenizers 0.15.0

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "malmarjeh/t5-arabic-text-summarization",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "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",
+  "gradient_checkpointing": false,
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": true,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "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,
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.2",
+  "use_cache": true,
+  "vocab_size": 110080
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.36.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5929f0eb15a0485423ca9c8f40670dd2dd4e3b9f66546f0a6be812116ada519
+size 1131116304

runs/Jan05_16-24-09_jupyter-debi2023-2dgroup2/events.out.tfevents.1704471857.jupyter-debi2023-2dgroup2.1722.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd7f86a2905d56bcd5848b9b9b1ef1eb97e0abfb132819b18c8245864ad80d90
+size 10316

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 sha256:5c7ae4407451bf02b459edec774d0539a06615005dd34d5c85c5c06765ff1606
+size 2435308

tokenizer_config.json

@@ -0,0 +1,38 @@
+{
+  "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,
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c97e105f4d74e1d1f5c46f9b96e5259a963a590f1b57d2d5b27d9dedb0d2768
+size 4475