Training complete

README.md

@@ -0,0 +1,81 @@
+---
+base_model: google/pegasus-large
+tags:
+- summarization
+- generated_from_trainer
+datasets:
+- scientific_papers
+metrics:
+- rouge
+model-index:
+- name: pegasus-large-finetuned-scientific-articles
+  results:
+  - task:
+      name: Sequence-to-sequence Language Modeling
+      type: text2text-generation
+    dataset:
+      name: scientific_papers
+      type: scientific_papers
+      config: pubmed
+      split: train
+      args: pubmed
+    metrics:
+    - name: Rouge1
+      type: rouge
+      value: 32.8743
+---
+
+<!-- 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-large-finetuned-scientific-articles
+
+This model is a fine-tuned version of [google/pegasus-large](https://huggingface.co/google/pegasus-large) on the scientific_papers dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.4553
+- Rouge1: 32.8743
+- Rouge2: 10.8417
+- Rougel: 20.3101
+- Rougelsum: 28.3673
+
+## 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: 5.6e-05
+- 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: 500
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Rouge1  | Rouge2  | Rougel  | Rougelsum |
+|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|
+| 3.0377        | 1.0   | 252  | 2.5409          | 30.5637 | 9.5168  | 18.2596 | 26.2196   |
+| 2.6145        | 2.0   | 504  | 2.4722          | 31.5518 | 9.9698  | 19.9187 | 26.695    |
+| 2.4322        | 3.0   | 756  | 2.4553          | 32.8743 | 10.8417 | 20.3101 | 28.3673   |
+
+
+### Framework versions
+
+- Transformers 4.41.2
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.2
+- Tokenizers 0.19.1

generation_config.json

@@ -0,0 +1,11 @@
+{
+  "bos_token_id": 0,
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "forced_eos_token_id": 1,
+  "length_penalty": 0.8,
+  "max_length": 256,
+  "num_beams": 8,
+  "pad_token_id": 0,
+  "transformers_version": "4.41.2"
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be9bb56e58f4810915aabea8d3c6b32fa25e2f29f5d46564f0734b2ed0859e1f
+oid sha256:2f5f6882e9b19beea4679458d61eec1a2bd12e861a63efb994668f70ac7f4ecc
 size 2283652852

runs/Jun07_17-00-57_b2d283f455a0/events.out.tfevents.1717779663.b2d283f455a0.316.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:287c24808312b4ed4bbfce92e83bf7b035e5dc16bbcdb45c13d24a04b2aec507
-size 8385
+oid sha256:54ffaa21c44bff0a9f7ffd7006b61c4d1d60b3b4d4c6f867ebc398f35b03d46a
+size 9898

runs/Jun07_17-00-57_b2d283f455a0/events.out.tfevents.1717783363.b2d283f455a0.316.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f62c315146e4cc7e47c27f8396d5ef4b965bb58271ce8f78e3d352dca081bec
+size 562