End of training

README.md

@@ -0,0 +1,82 @@
+---
+license: apache-2.0
+base_model: t5-small
+tags:
+- generated_from_trainer
+datasets:
+- xsum
+metrics:
+- rouge
+model-index:
+- name: t5-small-finetuned-xsum
+  results:
+  - task:
+      name: Sequence-to-sequence Language Modeling
+      type: text2text-generation
+    dataset:
+      name: xsum
+      type: xsum
+      config: default
+      split: validation
+      args: default
+    metrics:
+    - name: Rouge1
+      type: rouge
+      value: 28.451
+---
+
+<!-- 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-small-finetuned-xsum
+
+This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on the xsum dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.4684
+- Rouge1: 28.451
+- Rouge2: 7.8513
+- Rougel: 22.3844
+- Rougelsum: 22.3826
+- Gen Len: 18.8292
+
+## 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: 100
+- eval_batch_size: 100
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Rouge1  | Rouge2 | Rougel  | Rougelsum | Gen Len |
+|:-------------:|:-----:|:----:|:---------------:|:-------:|:------:|:-------:|:---------:|:-------:|
+| 2.7635        | 1.0   | 2041 | 2.5150          | 27.6651 | 7.3702 | 21.7165 | 21.7178   | 18.8121 |
+| 2.7114        | 2.0   | 4082 | 2.4780          | 28.3617 | 7.7832 | 22.3142 | 22.3121   | 18.8227 |
+| 2.695         | 3.0   | 6123 | 2.4684          | 28.451  | 7.8513 | 22.3844 | 22.3826   | 18.8292 |
+
+
+### Framework versions
+
+- Transformers 4.42.3
+- Pytorch 2.1.0+cu118
+- Datasets 2.20.0
+- Tokenizers 0.19.1

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.42.3"
+}