Hugging Face's logo

staghado
/
lightonocr-ft-iam-1ep

Text Generation
Transformers
Safetensors
lightonocr
Generated from Trainer
conversational
Model card Files
xet
Community
staghado commited on
Commit
3f89217
·
verified ·
1 Parent(s): 1089083

staghado/LightOnOCR-1B-1025-ft-iam

Browse files
Files changed (3) hide show
  1. README.md +8 -11
  2. model.safetensors +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [lightonai/LightOnOCR-1B-1025](https://huggingface.co/lightonai/LightOnOCR-1B-1025) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 0.1353
20
 
21
  ## Model description
22
 
@@ -44,21 +44,18 @@ The following hyperparameters were used during training:
44
  - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
45
  - lr_scheduler_type: cosine
46
  - lr_scheduler_warmup_steps: 10
47
- - num_epochs: 3
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss |
52
  |:-------------:|:------:|:----:|:---------------:|
53
- | 0.49 | 0.3322 | 100 | 0.2279 |
54
- | 0.3817 | 0.6645 | 200 | 0.1735 |
55
- | 0.3168 | 0.9967 | 300 | 0.1539 |
56
- | 0.1157 | 1.3289 | 400 | 0.1415 |
57
- | 0.1141 | 1.6611 | 500 | 0.1396 |
58
- | 0.1081 | 1.9934 | 600 | 0.1335 |
59
- | 0.0497 | 2.3256 | 700 | 0.1354 |
60
- | 0.0453 | 2.6578 | 800 | 0.1353 |
61
- | 0.054 | 2.9900 | 900 | 0.1353 |
62
 
63
 
64
  ### Framework versions
 
16
 
17
  This model is a fine-tuned version of [lightonai/LightOnOCR-1B-1025](https://huggingface.co/lightonai/LightOnOCR-1B-1025) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 0.1344
20
 
21
  ## Model description
22
 
 
44
  - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
45
  - lr_scheduler_type: cosine
46
  - lr_scheduler_warmup_steps: 10
47
+ - num_epochs: 2
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss |
52
  |:-------------:|:------:|:----:|:---------------:|
53
+ | 0.4848 | 0.3322 | 100 | 0.2298 |
54
+ | 0.3688 | 0.6645 | 200 | 0.1673 |
55
+ | 0.3001 | 0.9967 | 300 | 0.1429 |
56
+ | 0.1099 | 1.3289 | 400 | 0.1361 |
57
+ | 0.1136 | 1.6611 | 500 | 0.1348 |
58
+ | 0.1169 | 1.9934 | 600 | 0.1344 |
 
 
 
59
 
60
 
61
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1b8983937b762a245512761847b43938a8c3d45e3edadd2631558e8a92af7490
3
  size 2322532728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d545ea37cd66bfe1783907819fff5cab51148b3ab23cdf4039f72b063e9b0c2
3
  size 2322532728
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:782632d850fab541ddae65f81332af589fea2c59a37effc244c09a3167ffecbe
3
  size 5137
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a21b7846b2e1886921c793171e25a72106989084a1bfb04d0f6394992405b36
3
  size 5137