End of training

README.md

@@ -0,0 +1,84 @@
+---
+base_model: google/pegasus-cnn_dailymail
+tags:
+- generated_from_trainer
+datasets:
+- samsum
+metrics:
+- rouge
+model-index:
+- name: pegasus-samsum
+  results:
+  - task:
+      name: Sequence-to-sequence Language Modeling
+      type: text2text-generation
+    dataset:
+      name: samsum
+      type: samsum
+      config: samsum
+      split: validation
+      args: samsum
+    metrics:
+    - name: Rouge1
+      type: rouge
+      value: 0.4616
+---
+
+<!-- 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. -->
+
+# pegasus-samsum
+
+This model is a fine-tuned version of [google/pegasus-cnn_dailymail](https://huggingface.co/google/pegasus-cnn_dailymail) on the samsum dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.3665
+- Rouge1: 0.4616
+- Rouge2: 0.2275
+- Rougel: 0.3725
+- Rougelsum: 0.3738
+- Gen Len: 35.6667
+
+## 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: 5.750420024069848e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 16
+- total_train_batch_size: 128
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 500
+- num_epochs: 4
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
+|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
+| 2.2186        | 0.87  | 100  | 1.7567          | 0.3571 | 0.1437 | 0.2779 | 0.2797    | 46.7733 |
+| 1.7368        | 1.74  | 200  | 1.4933          | 0.4347 | 0.2053 | 0.3459 | 0.3461    | 35.4533 |
+| 1.6744        | 2.61  | 300  | 1.4059          | 0.4547 | 0.2179 | 0.3629 | 0.3634    | 35.68   |
+| 1.5978        | 3.47  | 400  | 1.3665          | 0.4616 | 0.2275 | 0.3725 | 0.3738    | 35.6667 |
+
+
+### Framework versions
+
+- Transformers 4.33.1
+- Pytorch 2.0.1+cu118
+- Datasets 2.14.5
+- Tokenizers 0.13.3

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 0,
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "forced_eos_token_id": 1,
+  "length_penalty": 0.8,
+  "max_length": 128,
+  "min_length": 32,
+  "num_beams": 8,
+  "pad_token_id": 0,
+  "transformers_version": "4.33.1"
+}