Training complete!
Browse files- README.md +77 -0
- model.safetensors +1 -1
README.md
ADDED
|
@@ -0,0 +1,77 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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: image_captioning_model
|
| 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 |
+
# image_captioning_model
|
| 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: 3.9561
|
| 20 |
+
- Bleu4: 4.6602
|
| 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: 16
|
| 41 |
+
- eval_batch_size: 16
|
| 42 |
+
- seed: 42
|
| 43 |
+
- gradient_accumulation_steps: 4
|
| 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 |
+
| 12.4864 | 1.0 | 113 | 12.2093 | 0.9329 |
|
| 55 |
+
| 5.5024 | 2.0 | 226 | 5.1222 | 1.4283 |
|
| 56 |
+
| 4.8103 | 3.0 | 339 | 4.5379 | 2.3729 |
|
| 57 |
+
| 4.4941 | 4.0 | 452 | 4.2987 | 3.4861 |
|
| 58 |
+
| 4.2601 | 5.0 | 565 | 4.1685 | 4.2715 |
|
| 59 |
+
| 4.0996 | 6.0 | 678 | 4.1062 | 4.5653 |
|
| 60 |
+
| 4.0649 | 7.0 | 791 | 4.0509 | 4.4991 |
|
| 61 |
+
| 3.9869 | 8.0 | 904 | 4.0288 | 4.2192 |
|
| 62 |
+
| 3.8730 | 9.0 | 1017 | 3.9991 | 4.2306 |
|
| 63 |
+
| 3.7958 | 10.0 | 1130 | 3.9973 | 4.1558 |
|
| 64 |
+
| 3.7842 | 11.0 | 1243 | 3.9754 | 5.1463 |
|
| 65 |
+
| 3.7156 | 12.0 | 1356 | 3.9678 | 4.0594 |
|
| 66 |
+
| 3.6771 | 13.0 | 1469 | 3.9686 | 4.5274 |
|
| 67 |
+
| 3.6874 | 14.0 | 1582 | 3.9671 | 4.4852 |
|
| 68 |
+
| 3.6374 | 15.0 | 1695 | 3.9548 | 4.309 |
|
| 69 |
+
| 3.5811 | 16.0 | 1808 | 3.9561 | 4.6602 |
|
| 70 |
+
|
| 71 |
+
|
| 72 |
+
### Framework versions
|
| 73 |
+
|
| 74 |
+
- Transformers 5.0.0
|
| 75 |
+
- Pytorch 2.11.0+cu128
|
| 76 |
+
- Datasets 4.0.0
|
| 77 |
+
- Tokenizers 0.22.2
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 9212662176
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8d6d125a3bf7281a7f5eb56b7167ee78bfbd5508f69e1ac948da9c70f6774335
|
| 3 |
size 9212662176
|