End of training

README.md

@@ -0,0 +1,94 @@
+---
+license: apache-2.0
+base_model: ahmeddbahaa/t5-arabic-base-finetuned-wikilingua-ar
+tags:
+- generated_from_trainer
+metrics:
+- rouge
+model-index:
+- name: results_t5_wiki
+  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_t5_wiki
+
+This model is a fine-tuned version of [ahmeddbahaa/t5-arabic-base-finetuned-wikilingua-ar](https://huggingface.co/ahmeddbahaa/t5-arabic-base-finetuned-wikilingua-ar) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0002
+- Rouge1: 0.1188
+- Rouge2: 0.0194
+- Rougel: 0.1188
+- Rougelsum: 0.1186
+- Gen Len: 19.0
+
+## 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
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 250
+- num_epochs: 10
+
+### Training results
+
+| Training Loss | Epoch  | Step  | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
+|:-------------:|:------:|:-----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
+| 0.8768        | 0.2143 | 500   | 0.0228          | 0.1148 | 0.0128 | 0.1148 | 0.1147    | 19.0    |
+| 0.0437        | 0.4286 | 1000  | 0.0111          | 0.1164 | 0.0154 | 0.1168 | 0.1165    | 19.0    |
+| 0.0436        | 0.6429 | 1500  | 0.0060          | 0.1168 | 0.0163 | 0.1171 | 0.1169    | 19.0    |
+| 0.0212        | 0.8573 | 2000  | 0.0052          | 0.117  | 0.0165 | 0.1173 | 0.117     | 19.0    |
+| 0.0161        | 1.0716 | 2500  | 0.0018          | 0.1188 | 0.0194 | 0.1188 | 0.1186    | 19.0    |
+| 0.011         | 1.2859 | 3000  | 0.0018          | 0.1188 | 0.0193 | 0.1188 | 0.1186    | 19.0    |
+| 0.0094        | 1.5002 | 3500  | 0.0014          | 0.1188 | 0.0194 | 0.1188 | 0.1186    | 19.0    |
+| 0.0107        | 1.7145 | 4000  | 0.0007          | 0.1188 | 0.0194 | 0.1188 | 0.1186    | 19.0    |
+| 0.0069        | 1.9288 | 4500  | 0.0006          | 0.1188 | 0.0194 | 0.1188 | 0.1186    | 19.0    |
+| 0.007         | 2.1432 | 5000  | 0.0006          | 0.1188 | 0.0194 | 0.1188 | 0.1186    | 19.0    |
+| 0.0064        | 2.3575 | 5500  | 0.0006          | 0.1188 | 0.0194 | 0.1188 | 0.1186    | 19.0    |
+| 0.0062        | 2.5718 | 6000  | 0.0015          | 0.1188 | 0.0194 | 0.1188 | 0.1186    | 19.0    |
+| 0.0042        | 2.7861 | 6500  | 0.0005          | 0.1188 | 0.0194 | 0.1188 | 0.1186    | 19.0    |
+| 0.0043        | 3.0004 | 7000  | 0.0004          | 0.1188 | 0.0194 | 0.1188 | 0.1186    | 19.0    |
+| 0.0042        | 3.2147 | 7500  | 0.0012          | 0.1188 | 0.0194 | 0.1188 | 0.1186    | 19.0    |
+| 0.0047        | 3.4291 | 8000  | 0.0010          | 0.1188 | 0.0194 | 0.1188 | 0.1186    | 19.0    |
+| 0.0043        | 3.6434 | 8500  | 0.0008          | 0.1188 | 0.0194 | 0.1188 | 0.1186    | 19.0    |
+| 0.0024        | 3.8577 | 9000  | 0.0003          | 0.1188 | 0.0194 | 0.1188 | 0.1186    | 19.0    |
+| 0.0026        | 4.0720 | 9500  | 0.0005          | 0.1188 | 0.0194 | 0.1188 | 0.1186    | 19.0    |
+| 0.0029        | 4.2863 | 10000 | 0.0003          | 0.1188 | 0.0194 | 0.1188 | 0.1186    | 19.0    |
+| 0.0045        | 4.5006 | 10500 | 0.0006          | 0.1188 | 0.0194 | 0.1188 | 0.1186    | 19.0    |
+| 0.0024        | 4.7150 | 11000 | 0.0001          | 0.1188 | 0.0194 | 0.1188 | 0.1186    | 19.0    |
+| 0.0018        | 4.9293 | 11500 | 0.0002          | 0.1188 | 0.0194 | 0.1188 | 0.1186    | 19.0    |
+| 0.002         | 5.1436 | 12000 | 0.0002          | 0.1188 | 0.0194 | 0.1188 | 0.1186    | 19.0    |
+| 0.0022        | 5.3579 | 12500 | 0.0001          | 0.1188 | 0.0194 | 0.1188 | 0.1186    | 19.0    |
+| 0.0017        | 5.5722 | 13000 | 0.0003          | 0.1188 | 0.0194 | 0.1188 | 0.1186    | 19.0    |
+| 0.0014        | 5.7865 | 13500 | 0.0005          | 0.1188 | 0.0194 | 0.1188 | 0.1186    | 19.0    |
+| 0.0055        | 6.0009 | 14000 | 0.0012          | 0.1188 | 0.0194 | 0.1188 | 0.1186    | 16.3147 |
+| 0.0127        | 6.2152 | 14500 | 0.0002          | 0.1188 | 0.0194 | 0.1188 | 0.1186    | 19.0    |
+| 0.0012        | 6.4295 | 15000 | 0.0002          | 0.1188 | 0.0194 | 0.1188 | 0.1186    | 19.0    |
+
+
+### Framework versions
+
+- Transformers 4.42.0.dev0
+- Pytorch 2.2.1+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "ahmeddbahaa/t5-arabic-base-finetuned-wikilingua-ar",
+  "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,
+  "tie_word_embeddings": false,
+  "tokenizer_class": "T5Tokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.0.dev0",
+  "use_cache": true,
+  "vocab_size": 35000
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.42.0.dev0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10f7ae9e085e0636002467dc95a0535c2e7847c162fa819f2e7ceb5932ec2f04
+size 1007990632

runs/May19_17-06-51_5d35f443cda0/events.out.tfevents.1716138524.5d35f443cda0.2219.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4456de3a71337cc0c6e1fed3cbc3e22bdbe58e722c755e93474d51713b75240a
+size 27656

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 sha256:0b1638b19c09773fb382835ebed2a612ba15aceff181dd79703365aad4ae6821
+size 847294

tokenizer_config.json

@@ -0,0 +1,42 @@
+{
+  "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,
+  "max_new_tokens": 512,
+  "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:ec9a4e465f8f33732cceee0c5420f1400f641050cec695f7ef68a6cf20c4c307
+size 5240