Hugging Face's logo

zhuchi76
/
git-base-naruto

Text Generation
Transformers
TensorBoard
Safetensors
git
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
zhuchi76 commited on
Commit
7f9cfbd
•
1 Parent(s): 491128f

End of training

Browse files
Files changed (3) hide show
  1. README.md +10 -19
  2. model.safetensors +1 -1
  3. runs/May30_15-00-33_tzuchichen/events.out.tfevents.1717052478.tzuchichen.47.2 +2 -2
README.md CHANGED
@@ -15,8 +15,8 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  This model is a fine-tuned version of [microsoft/git-base](https://huggingface.co/microsoft/git-base) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 0.0629
19
- - Wer Score: 6.3548
20
 
21
  ## Model description
22
 
@@ -36,33 +36,24 @@ More information needed
36
 
37
  The following hyperparameters were used during training:
38
  - learning_rate: 5e-05
39
- - train_batch_size: 2
40
- - eval_batch_size: 2
41
  - seed: 42
42
  - gradient_accumulation_steps: 2
43
- - total_train_batch_size: 4
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
46
- - num_epochs: 50
47
  - mixed_precision_training: Native AMP
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Wer Score |
52
  |:-------------:|:-------:|:----:|:---------------:|:---------:|
53
- | 7.2993 | 3.7037 | 50 | 4.4559 | 11.1452 |
54
- | 2.2534 | 7.4074 | 100 | 0.4051 | 0.5 |
55
- | 0.1148 | 11.1111 | 150 | 0.0457 | 0.4032 |
56
- | 0.0153 | 14.8148 | 200 | 0.0451 | 0.4032 |
57
- | 0.0108 | 18.5185 | 250 | 0.0486 | 0.5161 |
58
- | 0.009 | 22.2222 | 300 | 0.0488 | 0.4516 |
59
- | 0.0066 | 25.9259 | 350 | 0.0522 | 0.7419 |
60
- | 0.0054 | 29.6296 | 400 | 0.0538 | 0.4032 |
61
- | 0.0033 | 33.3333 | 450 | 0.0575 | 5.8548 |
62
- | 0.0018 | 37.0370 | 500 | 0.0604 | 4.9839 |
63
- | 0.0009 | 40.7407 | 550 | 0.0625 | 6.2097 |
64
- | 0.0008 | 44.4444 | 600 | 0.0629 | 6.3226 |
65
- | 0.0007 | 48.1481 | 650 | 0.0629 | 6.3548 |
66
 
67
 
68
  ### Framework versions
 
15
 
16
  This model is a fine-tuned version of [microsoft/git-base](https://huggingface.co/microsoft/git-base) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 0.0481
19
+ - Wer Score: 3.1327
20
 
21
  ## Model description
22
 
 
36
 
37
  The following hyperparameters were used during training:
38
  - learning_rate: 5e-05
39
+ - train_batch_size: 8
40
+ - eval_batch_size: 8
41
  - seed: 42
42
  - gradient_accumulation_steps: 2
43
+ - total_train_batch_size: 16
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
46
+ - num_epochs: 15
47
  - mixed_precision_training: Native AMP
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Wer Score |
52
  |:-------------:|:-------:|:----:|:---------------:|:---------:|
53
+ | 0.0029 | 3.5714 | 50 | 0.0447 | 3.9381 |
54
+ | 0.0007 | 7.1429 | 100 | 0.0473 | 3.3097 |
55
+ | 0.0002 | 10.7143 | 150 | 0.0476 | 4.3274 |
56
+ | 0.0001 | 14.2857 | 200 | 0.0481 | 3.1327 |
 
 
 
 
 
 
 
 
 
57
 
58
 
59
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eef469242a42fe52a0e6c6965bcf6857503a4cf3838a429ec9514e738bbe39fd
3
  size 706516040
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbb81a8b8ea7afa83b07b15ab843e553d9dd2cf7a3058b51872981e71f884052
3
  size 706516040
runs/May30_15-00-33_tzuchichen/events.out.tfevents.1717052478.tzuchichen.47.2 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:365490875edf9e8be1fd3460186b356583dbd756eec033b24922707c1e33ab1b
3
- size 6473
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c521da382e296003f0ceca3e16f7993c6ed13e3b43211a226447749d2545f09
3
+ size 7362