Instructions to use skumar1998/result with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use skumar1998/result with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("skumar1998/result", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Unsloth Desktop
Model save
Browse files
file.log
CHANGED
|
@@ -41,3 +41,4 @@ Dataset Split Statistics:
|
|
| 41 |
2026-07-28 10:30:19.706 | INFO | __main__:create_trainer:282 - Datasets: 4250 train, 563 eval samples
|
| 42 |
2026-07-28 10:30:20.492 | INFO | __main__:standard_training_loop:336 - Starting training
|
| 43 |
2026-07-28 10:30:20.677 | INFO | app.tasks.entity.vlm.model:train_model:600 - everything is set up, launching training
|
|
|
|
|
|
| 41 |
2026-07-28 10:30:19.706 | INFO | __main__:create_trainer:282 - Datasets: 4250 train, 563 eval samples
|
| 42 |
2026-07-28 10:30:20.492 | INFO | __main__:standard_training_loop:336 - Starting training
|
| 43 |
2026-07-28 10:30:20.677 | INFO | app.tasks.entity.vlm.model:train_model:600 - everything is set up, launching training
|
| 44 |
+
2026-07-28 18:27:27.595 | INFO | app.tasks.entity.vlm.model:train_model:606 - training complete: TrainOutput(global_step=264, training_loss=0.07196730663153258, metrics={'train_runtime': 28611.8808, 'train_samples_per_second': 0.295, 'train_steps_per_second': 0.009, 'total_flos': 2.938982658305549e+18, 'train_loss': 0.07196730663153258, 'epoch': 1.9849624060150375})
|
runs/Jul28_10-30-22_b6fbf603f302/events.out.tfevents.1785234622.b6fbf603f302.9985.0
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7c13b9234202043ea9b0b0840ad4f6d0af254b047dfc392cd8fda0b99c8cba50
|
| 3 |
+
size 21014
|