fawern commited on
Commit
7847c79
1 Parent(s): 7f09b05

End of training

Browse files
README.md ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: nlpconnect/vit-gpt2-image-captioning
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: vit-gpt-person-image-captioning
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # vit-gpt-person-image-captioning
15
+
16
+ This model is a fine-tuned version of [nlpconnect/vit-gpt2-image-captioning](https://huggingface.co/nlpconnect/vit-gpt2-image-captioning) on an unknown dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 0.0173
19
+
20
+ ## Model description
21
+
22
+ More information needed
23
+
24
+ ## Intended uses & limitations
25
+
26
+ More information needed
27
+
28
+ ## Training and evaluation data
29
+
30
+ More information needed
31
+
32
+ ## Training procedure
33
+
34
+ ### Training hyperparameters
35
+
36
+ The following hyperparameters were used during training:
37
+ - learning_rate: 2e-05
38
+ - train_batch_size: 2
39
+ - eval_batch_size: 2
40
+ - seed: 42
41
+ - gradient_accumulation_steps: 16
42
+ - total_train_batch_size: 32
43
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
+ - lr_scheduler_type: linear
45
+ - num_epochs: 5
46
+ - mixed_precision_training: Native AMP
47
+
48
+ ### Training results
49
+
50
+ | Training Loss | Epoch | Step | Validation Loss |
51
+ |:-------------:|:------:|:----:|:---------------:|
52
+ | No log | 0.9984 | 312 | 0.0211 |
53
+ | 0.0609 | 2.0 | 625 | 0.0194 |
54
+ | 0.0609 | 2.9984 | 937 | 0.0183 |
55
+ | 0.021 | 4.0 | 1250 | 0.0176 |
56
+ | 0.0194 | 4.992 | 1560 | 0.0173 |
57
+
58
+
59
+ ### Framework versions
60
+
61
+ - Transformers 4.41.2
62
+ - Pytorch 2.1.2
63
+ - Datasets 2.19.2
64
+ - Tokenizers 0.19.1
generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "decoder_start_token_id": 50256,
5
+ "eos_token_id": 50256,
6
+ "pad_token_id": 50256,
7
+ "transformers_version": "4.41.2"
8
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8a9fa14505d1db8e8daca0ec358d1dec2b867e9fd01c383271e6d5aa7eb82634
3
  size 956835520
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e295c021c4c49bd55f35dc6710d129e51833fdf50da9976c65b50b892a4aeaf5
3
  size 956835520
runs/Jul06_13-48-28_dcf60f963850/events.out.tfevents.1720273712.dcf60f963850.34.1 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:67e46d720d97a4a0e847300e65c017ca36289b9aac1b2f36e55cb5caf54f1322
3
- size 10964
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5a2b04b32239165fabc473f4dd2832acdde73e2a785a76bb15f821f430913e3
3
+ size 11589