Training is complete
Browse files- README.md +69 -0
- generation_config.json +7 -0
README.md
ADDED
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: ucsahin/TraVisionLM-Object-Detection
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
model-index:
|
6 |
+
- name: TraVisionLM-Object-Detection-v2
|
7 |
+
results: []
|
8 |
+
---
|
9 |
+
|
10 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
11 |
+
should probably proofread and complete it, then remove this comment. -->
|
12 |
+
|
13 |
+
# TraVisionLM-Object-Detection-v2
|
14 |
+
|
15 |
+
This model is a fine-tuned version of [ucsahin/TraVisionLM-Object-Detection](https://huggingface.co/ucsahin/TraVisionLM-Object-Detection) on an unknown dataset.
|
16 |
+
It achieves the following results on the evaluation set:
|
17 |
+
- Loss: 2.2919
|
18 |
+
|
19 |
+
## Model description
|
20 |
+
|
21 |
+
More information needed
|
22 |
+
|
23 |
+
## Intended uses & limitations
|
24 |
+
|
25 |
+
More information needed
|
26 |
+
|
27 |
+
## Training and evaluation data
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Training procedure
|
32 |
+
|
33 |
+
### Training hyperparameters
|
34 |
+
|
35 |
+
The following hyperparameters were used during training:
|
36 |
+
- learning_rate: 1e-05
|
37 |
+
- train_batch_size: 4
|
38 |
+
- eval_batch_size: 4
|
39 |
+
- seed: 42
|
40 |
+
- gradient_accumulation_steps: 16
|
41 |
+
- total_train_batch_size: 64
|
42 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
43 |
+
- lr_scheduler_type: linear
|
44 |
+
- num_epochs: 3
|
45 |
+
|
46 |
+
### Training results
|
47 |
+
|
48 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
49 |
+
|:-------------:|:------:|:----:|:---------------:|
|
50 |
+
| 2.3213 | 0.2406 | 570 | 2.3409 |
|
51 |
+
| 2.3129 | 0.4813 | 1140 | 2.3436 |
|
52 |
+
| 2.3128 | 0.7219 | 1710 | 2.3322 |
|
53 |
+
| 2.3082 | 0.9626 | 2280 | 2.3239 |
|
54 |
+
| 2.2853 | 1.2032 | 2850 | 2.3228 |
|
55 |
+
| 2.2826 | 1.4438 | 3420 | 2.3098 |
|
56 |
+
| 2.2707 | 1.6845 | 3990 | 2.3067 |
|
57 |
+
| 2.2706 | 1.9251 | 4560 | 2.3042 |
|
58 |
+
| 2.2465 | 2.1658 | 5130 | 2.3014 |
|
59 |
+
| 2.2435 | 2.4064 | 5700 | 2.2978 |
|
60 |
+
| 2.2433 | 2.6470 | 6270 | 2.2953 |
|
61 |
+
| 2.2344 | 2.8877 | 6840 | 2.2919 |
|
62 |
+
|
63 |
+
|
64 |
+
### Framework versions
|
65 |
+
|
66 |
+
- Transformers 4.44.0.dev0
|
67 |
+
- Pytorch 2.3.1+cu121
|
68 |
+
- Datasets 2.20.0
|
69 |
+
- Tokenizers 0.19.1
|
generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 0,
|
4 |
+
"eos_token_id": 0,
|
5 |
+
"pad_token_id": 0,
|
6 |
+
"transformers_version": "4.44.0.dev0"
|
7 |
+
}
|