jmz2023/t5_eli5_v1

README.md

@@ -0,0 +1,83 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: google/flan-t5-base
+tags:
+- generated_from_trainer
+datasets:
+- eli5_category
+metrics:
+- rouge
+model-index:
+- name: flan-t5-base-finetuned-t5
+  results:
+  - task:
+      name: Sequence-to-sequence Language Modeling
+      type: text2text-generation
+    dataset:
+      name: eli5_category
+      type: eli5_category
+      config: default
+      split: validation1
+      args: default
+    metrics:
+    - name: Rouge1
+      type: rouge
+      value: 10.1877
+---
+
+<!-- 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. -->
+
+# flan-t5-base-finetuned-t5
+
+This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on the eli5_category dataset.
+It achieves the following results on the evaluation set:
+- Loss: nan
+- Rouge1: 10.1877
+- Rouge2: 0.0
+- Rougel: 10.1808
+- Rougelsum: 10.1824
+- Gen Len: 9.366
+
+## 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: 3
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Rouge1  | Rouge2 | Rougel  | Rougelsum | Gen Len |
+|:-------------:|:-----:|:-----:|:---------------:|:-------:|:------:|:-------:|:---------:|:-------:|
+| 0.0           | 1.0   | 5736  | nan             | 10.1877 | 0.0    | 10.1808 | 10.1824   | 9.366   |
+| 0.0           | 2.0   | 11472 | nan             | 10.1877 | 0.0    | 10.1808 | 10.1824   | 9.366   |
+| 0.0           | 3.0   | 17208 | nan             | 10.1877 | 0.0    | 10.1808 | 10.1824   | 9.366   |
+
+
+### Framework versions
+
+- Transformers 4.44.2
+- Pytorch 2.4.1+cu121
+- Datasets 3.0.1
+- 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": "4.44.2"
+}

runs/Sep27_18-29-43_bf8f55ccff97/events.out.tfevents.1727462534.bf8f55ccff97.560.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1025872b763001b58029a9b40534da11c0747272c284c71660f9fdf7a139c7a7
-size 14197
+oid sha256:4b05d05b1d48077fc03064d6a70f9083957225cee3fa4e78951b0b655f691741
+size 15092