End of training

README.md

@@ -0,0 +1,74 @@
+---
+license: apache-2.0
+base_model: moussaKam/AraBART
+tags:
+- generated_from_trainer
+metrics:
+- rouge
+model-index:
+- name: AraBART-finetuned-xlsum-ar
+  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. -->
+
+# AraBART-finetuned-xlsum-ar
+
+This model is a fine-tuned version of [moussaKam/AraBART](https://huggingface.co/moussaKam/AraBART) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.4655
+- Rouge1: 24.4029
+- Rouge2: 10.6961
+- Rougel: 21.8597
+- Rougelsum: 21.9193
+- Gen Len: 19.6173
+
+## 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: 16
+- eval_batch_size: 16
+- 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 | Rouge1  | Rouge2  | Rougel  | Rougelsum | Gen Len |
+|:-------------:|:-----:|:-----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
+| 2.8881        | 1.0   | 2111  | 2.5078          | 23.0537 | 9.805   | 20.6712 | 20.7358   | 19.4371 |
+| 2.7229        | 2.0   | 4222  | 2.4712          | 23.4792 | 10.0638 | 21.0179 | 21.0808   | 19.5933 |
+| 2.6235        | 3.0   | 6333  | 2.4606          | 23.793  | 10.2551 | 21.2806 | 21.3525   | 19.5784 |
+| 2.5475        | 4.0   | 8444  | 2.4557          | 23.8559 | 10.2547 | 21.3093 | 21.383    | 19.6013 |
+| 2.4579        | 5.0   | 10555 | 2.4567          | 24.3906 | 10.6549 | 21.8215 | 21.8672   | 19.6471 |
+| 2.4124        | 6.0   | 12666 | 2.4578          | 24.3648 | 10.6614 | 21.8584 | 21.9202   | 19.6018 |
+| 2.38          | 7.0   | 14777 | 2.4606          | 24.3488 | 10.722  | 21.8546 | 21.9218   | 19.5938 |
+| 2.3422        | 8.0   | 16888 | 2.4605          | 24.4836 | 10.7873 | 21.9424 | 21.9996   | 19.6215 |
+| 2.3185        | 9.0   | 18999 | 2.4630          | 24.2878 | 10.6124 | 21.8332 | 21.8687   | 19.5949 |
+| 2.2988        | 10.0  | 21110 | 2.4655          | 24.4029 | 10.6961 | 21.8597 | 21.9193   | 19.6173 |
+
+
+### Framework versions
+
+- Transformers 4.39.3
+- Pytorch 2.1.2
+- Datasets 2.18.0
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,59 @@
+{
+  "_name_or_path": "moussaKam/AraBART",
+  "activation_dropout": 0.1,
+  "activation_function": "gelu",
+  "add_bias_logits": false,
+  "add_final_layer_norm": true,
+  "architectures": [
+    "MBartForConditionalGeneration"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 0,
+  "classif_dropout": 0.1,
+  "classifier_dropout": 0.0,
+  "d_model": 768,
+  "decoder_attention_heads": 12,
+  "decoder_ffn_dim": 3072,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "decoder_start_token_id": 2,
+  "do_blenderbot_90_layernorm": false,
+  "dropout": 0.1,
+  "early_stopping": true,
+  "encoder_attention_heads": 12,
+  "encoder_ffn_dim": 3072,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_token_id": 2,
+  "extra_pos_embeddings": 2,
+  "force_bos_token_to_be_generated": false,
+  "forced_eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "max_position_embeddings": 1024,
+  "model_type": "mbart",
+  "no_repeat_ngram_size": 3,
+  "normalize_before": true,
+  "normalize_embedding": true,
+  "num_beams": 4,
+  "num_hidden_layers": 6,
+  "pad_token_id": 1,
+  "scale_embedding": false,
+  "static_position_embeddings": false,
+  "tokenizer_class": "BarthezTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.3",
+  "use_cache": true,
+  "vocab_size": 50002
+}

generation_config.json

@@ -0,0 +1,11 @@
+{
+  "bos_token_id": 0,
+  "decoder_start_token_id": 2,
+  "early_stopping": true,
+  "eos_token_id": 2,
+  "forced_eos_token_id": 2,
+  "no_repeat_ngram_size": 3,
+  "num_beams": 4,
+  "pad_token_id": 1,
+  "transformers_version": "4.39.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c60de8e7e9a63f7e9c099b82475ba805c8b9dfebbe53178fbe0c6420240c9649
+size 557116312

runs/May16_22-44-08_e0a9cab4452c/events.out.tfevents.1715899451.e0a9cab4452c.24.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f572e1c6f0ca4566929f08e350e55819b65b56eb16d177c5c4bd5a876b36edb
+size 20102

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbb59d772bc9bb2da5dc4a73a00c61c0912c6d2596aad970fa2cd3d69898b245
+size 1315170

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "BarthezTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ca35c718f4aa685d801637d6160427c2304e07a4c7b8bbde1a29e91631ba523
+size 5112