Training complete!
Browse files- README.md +75 -0
- pytorch_model.bin +1 -1
README.md
ADDED
|
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: mit
|
| 4 |
+
base_model: facebook/mbart-large-50
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
model-index:
|
| 8 |
+
- name: scenegraph_image_captioning
|
| 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 |
+
# scenegraph_image_captioning
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [facebook/mbart-large-50](https://huggingface.co/facebook/mbart-large-50) on an unknown dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 3.3994
|
| 20 |
+
- Bleu4: 10.148
|
| 21 |
+
|
| 22 |
+
## Model description
|
| 23 |
+
|
| 24 |
+
More information needed
|
| 25 |
+
|
| 26 |
+
## Intended uses & limitations
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Training and evaluation data
|
| 31 |
+
|
| 32 |
+
More information needed
|
| 33 |
+
|
| 34 |
+
## Training procedure
|
| 35 |
+
|
| 36 |
+
### Training hyperparameters
|
| 37 |
+
|
| 38 |
+
The following hyperparameters were used during training:
|
| 39 |
+
- learning_rate: 3e-05
|
| 40 |
+
- train_batch_size: 32
|
| 41 |
+
- eval_batch_size: 32
|
| 42 |
+
- seed: 42
|
| 43 |
+
- gradient_accumulation_steps: 2
|
| 44 |
+
- total_train_batch_size: 64
|
| 45 |
+
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 46 |
+
- lr_scheduler_type: linear
|
| 47 |
+
- lr_scheduler_warmup_steps: 350
|
| 48 |
+
- num_epochs: 30
|
| 49 |
+
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
| Training Loss | Epoch | Step | Validation Loss | Bleu4 |
|
| 53 |
+
|:-------------:|:-----:|:-----:|:---------------:|:-------:|
|
| 54 |
+
| 3.6494 | 1.0 | 4625 | 3.6095 | 8.3269 |
|
| 55 |
+
| 3.4809 | 2.0 | 9250 | 3.4953 | 9.0764 |
|
| 56 |
+
| 3.2703 | 3.0 | 13875 | 3.4439 | 9.185 |
|
| 57 |
+
| 3.3438 | 4.0 | 18500 | 3.4134 | 10.023 |
|
| 58 |
+
| 3.2965 | 5.0 | 23125 | 3.3911 | 10.0925 |
|
| 59 |
+
| 3.2711 | 6.0 | 27750 | 3.3830 | 10.4298 |
|
| 60 |
+
| 3.1469 | 7.0 | 32375 | 3.3745 | 10.5282 |
|
| 61 |
+
| 3.1113 | 8.0 | 37000 | 3.3760 | 10.292 |
|
| 62 |
+
| 3.0507 | 9.0 | 41625 | 3.3739 | 10.7014 |
|
| 63 |
+
| 3.0794 | 10.0 | 46250 | 3.3767 | 10.4073 |
|
| 64 |
+
| 3.0509 | 11.0 | 50875 | 3.3793 | 10.3126 |
|
| 65 |
+
| 3.0570 | 12.0 | 55500 | 3.3880 | 10.2934 |
|
| 66 |
+
| 2.9785 | 13.0 | 60125 | 3.3865 | 10.2243 |
|
| 67 |
+
| 2.9636 | 14.0 | 64750 | 3.3994 | 10.148 |
|
| 68 |
+
|
| 69 |
+
|
| 70 |
+
### Framework versions
|
| 71 |
+
|
| 72 |
+
- Transformers 5.10.2
|
| 73 |
+
- Pytorch 2.11.0+cu128
|
| 74 |
+
- Datasets 4.0.0
|
| 75 |
+
- Tokenizers 0.22.2
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 6140680585
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:38157b1b69207913d99a5ca67054dff3f029aebedd0befe37c8c298f35887eff
|
| 3 |
size 6140680585
|