Training complete

README.md

@@ -0,0 +1,105 @@
+---
+license: apache-2.0
+base_model: Falconsai/text_summarization
+tags:
+- summarization
+- generated_from_trainer
+datasets:
+- cnn_dailymail
+metrics:
+- rouge
+model-index:
+- name: text_summarization-finetuned
+  results:
+  - task:
+      name: Sequence-to-sequence Language Modeling
+      type: text2text-generation
+    dataset:
+      name: cnn_dailymail
+      type: cnn_dailymail
+      config: 1.0.0
+      split: validation
+      args: 1.0.0
+    metrics:
+    - name: Rouge1
+      type: rouge
+      value: 0.2339
+---
+
+<!-- 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. -->
+
+# text_summarization-finetuned
+
+This model is a fine-tuned version of [Falconsai/text_summarization](https://huggingface.co/Falconsai/text_summarization) on the cnn_dailymail dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.5462
+- Rouge1: 0.2339
+- Rouge2: 0.1071
+- Rougel: 0.1909
+- Rougelsum: 0.2199
+
+## 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: 8
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 25
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
+|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|
+| 14.8371       | 0.99  | 31   | 10.4178         | 0.2031 | 0.0864 | 0.1631 | 0.1907    |
+| 11.0708       | 1.98  | 62   | 8.1794          | 0.2049 | 0.0873 | 0.1642 | 0.1909    |
+| 9.5037        | 2.98  | 93   | 5.3342          | 0.1989 | 0.0804 | 0.1559 | 0.1845    |
+| 6.2278        | 4.0   | 125  | 4.4009          | 0.201  | 0.0855 | 0.1571 | 0.1882    |
+| 5.152         | 4.99  | 156  | 3.4913          | 0.2094 | 0.0883 | 0.1668 | 0.1959    |
+| 3.9293        | 5.98  | 187  | 3.0893          | 0.2221 | 0.0957 | 0.1785 | 0.2083    |
+| 3.6608        | 6.98  | 218  | 2.9988          | 0.2174 | 0.0948 | 0.1775 | 0.2045    |
+| 3.3943        | 8.0   | 250  | 2.9427          | 0.2195 | 0.0959 | 0.179  | 0.2064    |
+| 3.2549        | 8.99  | 281  | 2.9013          | 0.2255 | 0.1002 | 0.1832 | 0.2124    |
+| 3.2028        | 9.98  | 312  | 2.8655          | 0.2298 | 0.1053 | 0.1865 | 0.2165    |
+| 3.1611        | 10.98 | 343  | 2.8306          | 0.2302 | 0.1069 | 0.1878 | 0.218     |
+| 3.1206        | 12.0  | 375  | 2.7931          | 0.2265 | 0.1044 | 0.1847 | 0.2142    |
+| 3.0716        | 12.99 | 406  | 2.7572          | 0.2301 | 0.1077 | 0.1883 | 0.2173    |
+| 3.0376        | 13.98 | 437  | 2.7239          | 0.231  | 0.1057 | 0.1883 | 0.2177    |
+| 3.0154        | 14.98 | 468  | 2.6894          | 0.2319 | 0.1062 | 0.1891 | 0.2177    |
+| 2.9518        | 16.0  | 500  | 2.6593          | 0.233  | 0.1071 | 0.1904 | 0.2192    |
+| 2.9359        | 16.99 | 531  | 2.6332          | 0.2338 | 0.108  | 0.1919 | 0.2208    |
+| 2.8874        | 17.98 | 562  | 2.6124          | 0.2322 | 0.1057 | 0.1896 | 0.2181    |
+| 2.8786        | 18.98 | 593  | 2.5941          | 0.2335 | 0.1066 | 0.1909 | 0.2196    |
+| 2.8584        | 20.0  | 625  | 2.5782          | 0.232  | 0.1056 | 0.1895 | 0.2178    |
+| 2.8517        | 20.99 | 656  | 2.5671          | 0.2327 | 0.1061 | 0.1901 | 0.2188    |
+| 2.8392        | 21.98 | 687  | 2.5562          | 0.2339 | 0.1067 | 0.1908 | 0.2198    |
+| 2.8478        | 22.98 | 718  | 2.5509          | 0.2339 | 0.1071 | 0.1909 | 0.2199    |
+| 2.8161        | 24.0  | 750  | 2.5469          | 0.2339 | 0.1071 | 0.1909 | 0.2199    |
+| 2.8385        | 24.8  | 775  | 2.5462          | 0.2339 | 0.1071 | 0.1909 | 0.2199    |
+
+
+### Framework versions
+
+- Transformers 4.38.0.dev0
+- Pytorch 2.2.0
+- Datasets 2.16.1
+- Tokenizers 0.15.1

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.38.0.dev0"
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d720e0618e7738df1f53c971844bf6c4be4ab01006bc067de8d3dd297a9132bd
+oid sha256:16c8d5884f26c88b62d267e1816de4c89bc02c674ac2ddd1b8838ddba37804b4
 size 242041896