Jérôme Bau
commited on
Commit
·
ebd5cf8
1
Parent(s):
79cde0c
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: google/flan-t5-large
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
metrics:
|
| 7 |
+
- rouge
|
| 8 |
+
model-index:
|
| 9 |
+
- name: flan-t5-large-finetuned-coding_instructions_2023_08_18__12_06
|
| 10 |
+
results: []
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 14 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
+
|
| 16 |
+
# flan-t5-large-finetuned-coding_instructions_2023_08_18__12_06
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [google/flan-t5-large](https://huggingface.co/google/flan-t5-large) on the None dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 0.6230
|
| 21 |
+
- Rouge1: 47.0864
|
| 22 |
+
- Rouge2: 31.2968
|
| 23 |
+
- Rougel: 45.9675
|
| 24 |
+
- Rougelsum: 46.0612
|
| 25 |
+
- Gen Len: 19.0
|
| 26 |
+
|
| 27 |
+
## Model description
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Intended uses & limitations
|
| 32 |
+
|
| 33 |
+
More information needed
|
| 34 |
+
|
| 35 |
+
## Training and evaluation data
|
| 36 |
+
|
| 37 |
+
More information needed
|
| 38 |
+
|
| 39 |
+
## Training procedure
|
| 40 |
+
|
| 41 |
+
### Training hyperparameters
|
| 42 |
+
|
| 43 |
+
The following hyperparameters were used during training:
|
| 44 |
+
- learning_rate: 2e-05
|
| 45 |
+
- train_batch_size: 8
|
| 46 |
+
- eval_batch_size: 8
|
| 47 |
+
- seed: 42
|
| 48 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 49 |
+
- lr_scheduler_type: linear
|
| 50 |
+
- num_epochs: 10
|
| 51 |
+
|
| 52 |
+
### Training results
|
| 53 |
+
|
| 54 |
+
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|
| 55 |
+
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
|
| 56 |
+
| No log | 1.0 | 10 | 0.9891 | 18.047 | 9.6197 | 18.1466 | 18.2622 | 16.9538 |
|
| 57 |
+
| No log | 2.0 | 20 | 0.7803 | 21.724 | 12.8839 | 21.4666 | 21.6773 | 17.7385 |
|
| 58 |
+
| No log | 3.0 | 30 | 0.6827 | 42.1883 | 27.0064 | 41.5285 | 41.6611 | 18.9077 |
|
| 59 |
+
| No log | 4.0 | 40 | 0.6526 | 44.8257 | 28.8931 | 43.8323 | 43.7858 | 18.9846 |
|
| 60 |
+
| No log | 5.0 | 50 | 0.6407 | 44.6781 | 29.5477 | 43.9053 | 43.8475 | 19.0 |
|
| 61 |
+
| No log | 6.0 | 60 | 0.6334 | 46.039 | 31.3315 | 45.3508 | 45.3701 | 19.0 |
|
| 62 |
+
| No log | 7.0 | 70 | 0.6281 | 46.8592 | 31.2186 | 46.1283 | 46.1169 | 19.0 |
|
| 63 |
+
| No log | 8.0 | 80 | 0.6250 | 46.5201 | 30.8844 | 45.5541 | 45.6876 | 19.0 |
|
| 64 |
+
| No log | 9.0 | 90 | 0.6236 | 47.074 | 31.2968 | 46.1336 | 46.258 | 19.0 |
|
| 65 |
+
| No log | 10.0 | 100 | 0.6230 | 47.0864 | 31.2968 | 45.9675 | 46.0612 | 19.0 |
|
| 66 |
+
|
| 67 |
+
|
| 68 |
+
### Framework versions
|
| 69 |
+
|
| 70 |
+
- Transformers 4.31.0
|
| 71 |
+
- Pytorch 2.0.1+cu118
|
| 72 |
+
- Datasets 2.14.4
|
| 73 |
+
- Tokenizers 0.13.3
|