Commit ·
66a495d
1
Parent(s): b4f18eb
Model save
Browse files
README.md
ADDED
|
@@ -0,0 +1,71 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: ybelkada/flan-t5-xl-sharded-bf16
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
metrics:
|
| 6 |
+
- rouge
|
| 7 |
+
model-index:
|
| 8 |
+
- name: flan-xl-gen6
|
| 9 |
+
results: []
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
+
|
| 15 |
+
# flan-xl-gen6
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [ybelkada/flan-t5-xl-sharded-bf16](https://huggingface.co/ybelkada/flan-t5-xl-sharded-bf16) on the None dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.4978
|
| 20 |
+
- Rouge1: 29.5362
|
| 21 |
+
- Rouge2: 20.6621
|
| 22 |
+
- Rougel: 25.7689
|
| 23 |
+
- Rougelsum: 26.2351
|
| 24 |
+
- Gen Len: 12.7388
|
| 25 |
+
|
| 26 |
+
## Model description
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Intended uses & limitations
|
| 31 |
+
|
| 32 |
+
More information needed
|
| 33 |
+
|
| 34 |
+
## Training and evaluation data
|
| 35 |
+
|
| 36 |
+
More information needed
|
| 37 |
+
|
| 38 |
+
## Training procedure
|
| 39 |
+
|
| 40 |
+
### Training hyperparameters
|
| 41 |
+
|
| 42 |
+
The following hyperparameters were used during training:
|
| 43 |
+
- learning_rate: 0.0005
|
| 44 |
+
- train_batch_size: 8
|
| 45 |
+
- eval_batch_size: 8
|
| 46 |
+
- seed: 42
|
| 47 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 48 |
+
- lr_scheduler_type: cosine
|
| 49 |
+
- lr_scheduler_warmup_steps: 800
|
| 50 |
+
- num_epochs: 8
|
| 51 |
+
|
| 52 |
+
### Training results
|
| 53 |
+
|
| 54 |
+
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|
| 55 |
+
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
|
| 56 |
+
| No log | 1.0 | 328 | 0.6921 | 34.9112 | 26.7503 | 31.4124 | 31.7295 | 10.0172 |
|
| 57 |
+
| 6.8746 | 2.0 | 656 | 0.6025 | 33.9134 | 25.3236 | 30.1968 | 30.472 | 10.8454 |
|
| 58 |
+
| 6.8746 | 3.0 | 984 | 0.5687 | 31.6178 | 22.9463 | 27.8758 | 28.3572 | 11.8729 |
|
| 59 |
+
| 0.6462 | 4.0 | 1312 | 0.5355 | 30.8157 | 22.1783 | 27.1641 | 27.569 | 12.1306 |
|
| 60 |
+
| 0.5618 | 5.0 | 1640 | 0.5160 | 29.9183 | 21.0842 | 26.1671 | 26.5965 | 12.5017 |
|
| 61 |
+
| 0.5618 | 6.0 | 1968 | 0.5025 | 29.7823 | 21.1443 | 26.0286 | 26.5215 | 12.5086 |
|
| 62 |
+
| 0.498 | 7.0 | 2296 | 0.4978 | 29.1043 | 20.2391 | 25.3347 | 25.804 | 12.8969 |
|
| 63 |
+
| 0.4551 | 8.0 | 2624 | 0.4978 | 29.5362 | 20.6621 | 25.7689 | 26.2351 | 12.7388 |
|
| 64 |
+
|
| 65 |
+
|
| 66 |
+
### Framework versions
|
| 67 |
+
|
| 68 |
+
- Transformers 4.35.2
|
| 69 |
+
- Pytorch 2.1.0+cu118
|
| 70 |
+
- Datasets 2.15.0
|
| 71 |
+
- Tokenizers 0.15.0
|
logs/events.out.tfevents.1701213742.9d8b960cb172.268.4
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d444510f7fb020ebbc02fd275f4323c7dea0bed02502ad93f008a883c231dd24
|
| 3 |
+
size 613
|