End of training
Browse files- README.md +73 -0
- adapter_model.safetensors +1 -1
README.md
ADDED
|
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: google/paligemma-3b-mix-448
|
| 3 |
+
datasets:
|
| 4 |
+
- khatt-paragraphs
|
| 5 |
+
library_name: peft
|
| 6 |
+
license: gemma
|
| 7 |
+
tags:
|
| 8 |
+
- generated_from_trainer
|
| 9 |
+
model-index:
|
| 10 |
+
- name: paligemma_khatt_paragraph_mix_448_ep1_r128
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/ahmed-heakl/huggingface/runs/x0hpb71u)
|
| 18 |
+
# paligemma_khatt_paragraph_mix_448_ep1_r128
|
| 19 |
+
|
| 20 |
+
This model is a fine-tuned version of [google/paligemma-3b-mix-448](https://huggingface.co/google/paligemma-3b-mix-448) on the khatt-paragraphs dataset.
|
| 21 |
+
It achieves the following results on the evaluation set:
|
| 22 |
+
- Loss: 1.6759
|
| 23 |
+
|
| 24 |
+
## Model description
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Intended uses & limitations
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training and evaluation data
|
| 33 |
+
|
| 34 |
+
More information needed
|
| 35 |
+
|
| 36 |
+
## Training procedure
|
| 37 |
+
|
| 38 |
+
### Training hyperparameters
|
| 39 |
+
|
| 40 |
+
The following hyperparameters were used during training:
|
| 41 |
+
- learning_rate: 1e-06
|
| 42 |
+
- train_batch_size: 1
|
| 43 |
+
- eval_batch_size: 1
|
| 44 |
+
- seed: 42
|
| 45 |
+
- gradient_accumulation_steps: 4
|
| 46 |
+
- total_train_batch_size: 4
|
| 47 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 48 |
+
- lr_scheduler_type: constant
|
| 49 |
+
- lr_scheduler_warmup_steps: 2
|
| 50 |
+
- num_epochs: 1
|
| 51 |
+
|
| 52 |
+
### Training results
|
| 53 |
+
|
| 54 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 55 |
+
|:-------------:|:------:|:----:|:---------------:|
|
| 56 |
+
| 2.5113 | 0.1014 | 100 | 2.4764 |
|
| 57 |
+
| 2.1232 | 0.2027 | 200 | 2.1948 |
|
| 58 |
+
| 1.8843 | 0.3041 | 300 | 2.0064 |
|
| 59 |
+
| 1.815 | 0.4055 | 400 | 1.8942 |
|
| 60 |
+
| 1.8574 | 0.5068 | 500 | 1.8223 |
|
| 61 |
+
| 1.6986 | 0.6082 | 600 | 1.7674 |
|
| 62 |
+
| 1.749 | 0.7096 | 700 | 1.7335 |
|
| 63 |
+
| 1.7122 | 0.8109 | 800 | 1.7025 |
|
| 64 |
+
| 1.61 | 0.9123 | 900 | 1.6759 |
|
| 65 |
+
|
| 66 |
+
|
| 67 |
+
### Framework versions
|
| 68 |
+
|
| 69 |
+
- PEFT 0.11.1
|
| 70 |
+
- Transformers 4.42.3
|
| 71 |
+
- Pytorch 2.1.2
|
| 72 |
+
- Datasets 2.20.0
|
| 73 |
+
- Tokenizers 0.19.1
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 361627272
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f38f3adbe1d5cfe558518d858e3d46e32ab70f051c3521f0e588407dfee39d34
|
| 3 |
size 361627272
|