End of training
Browse files- README.md +98 -0
- adapter_model.safetensors +1 -1
README.md
ADDED
|
@@ -0,0 +1,98 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
license: gemma
|
| 4 |
+
base_model: google/gemma-2-2b-it
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
model-index:
|
| 8 |
+
- name: gemma-2-2b-it-009
|
| 9 |
+
results: []
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
+
|
| 15 |
+
# gemma-2-2b-it-009
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [google/gemma-2-2b-it](https://huggingface.co/google/gemma-2-2b-it) on an unknown dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.5911
|
| 20 |
+
|
| 21 |
+
## Model description
|
| 22 |
+
|
| 23 |
+
More information needed
|
| 24 |
+
|
| 25 |
+
## Intended uses & limitations
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Training and evaluation data
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training procedure
|
| 34 |
+
|
| 35 |
+
### Training hyperparameters
|
| 36 |
+
|
| 37 |
+
The following hyperparameters were used during training:
|
| 38 |
+
- learning_rate: 2e-05
|
| 39 |
+
- train_batch_size: 1
|
| 40 |
+
- eval_batch_size: 8
|
| 41 |
+
- seed: 42
|
| 42 |
+
- gradient_accumulation_steps: 4
|
| 43 |
+
- total_train_batch_size: 4
|
| 44 |
+
- optimizer: Use paged_adamw_8bit with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 45 |
+
- lr_scheduler_type: linear
|
| 46 |
+
- num_epochs: 10
|
| 47 |
+
- mixed_precision_training: Native AMP
|
| 48 |
+
|
| 49 |
+
### Training results
|
| 50 |
+
|
| 51 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 52 |
+
|:-------------:|:------:|:----:|:---------------:|
|
| 53 |
+
| 1.9136 | 0.2694 | 100 | 1.8578 |
|
| 54 |
+
| 1.6469 | 0.5387 | 200 | 1.7018 |
|
| 55 |
+
| 1.5587 | 0.8081 | 300 | 1.5881 |
|
| 56 |
+
| 1.441 | 1.0754 | 400 | 1.4917 |
|
| 57 |
+
| 1.3434 | 1.3448 | 500 | 1.4168 |
|
| 58 |
+
| 1.3084 | 1.6141 | 600 | 1.3505 |
|
| 59 |
+
| 1.3159 | 1.8835 | 700 | 1.2916 |
|
| 60 |
+
| 1.2283 | 2.1508 | 800 | 1.2368 |
|
| 61 |
+
| 1.1159 | 2.4202 | 900 | 1.1855 |
|
| 62 |
+
| 1.0755 | 2.6896 | 1000 | 1.1303 |
|
| 63 |
+
| 1.0512 | 2.9589 | 1100 | 1.0780 |
|
| 64 |
+
| 1.04 | 3.2263 | 1200 | 1.0311 |
|
| 65 |
+
| 0.9028 | 3.4956 | 1300 | 0.9869 |
|
| 66 |
+
| 0.9561 | 3.7650 | 1400 | 0.9512 |
|
| 67 |
+
| 0.7814 | 4.0323 | 1500 | 0.9062 |
|
| 68 |
+
| 0.9104 | 4.3017 | 1600 | 0.8694 |
|
| 69 |
+
| 0.7495 | 4.5710 | 1700 | 0.8367 |
|
| 70 |
+
| 0.6661 | 4.8404 | 1800 | 0.8088 |
|
| 71 |
+
| 0.672 | 5.1077 | 1900 | 0.7803 |
|
| 72 |
+
| 0.6734 | 5.3771 | 2000 | 0.7566 |
|
| 73 |
+
| 0.6352 | 5.6465 | 2100 | 0.7309 |
|
| 74 |
+
| 0.6284 | 5.9158 | 2200 | 0.7213 |
|
| 75 |
+
| 0.5652 | 6.1832 | 2300 | 0.6951 |
|
| 76 |
+
| 0.5337 | 6.4525 | 2400 | 0.6878 |
|
| 77 |
+
| 0.6394 | 6.7219 | 2500 | 0.6675 |
|
| 78 |
+
| 0.5346 | 6.9912 | 2600 | 0.6543 |
|
| 79 |
+
| 0.4703 | 7.2586 | 2700 | 0.6480 |
|
| 80 |
+
| 0.6006 | 7.5279 | 2800 | 0.6389 |
|
| 81 |
+
| 0.5572 | 7.7973 | 2900 | 0.6265 |
|
| 82 |
+
| 0.5619 | 8.0646 | 3000 | 0.6163 |
|
| 83 |
+
| 0.4893 | 8.3340 | 3100 | 0.6114 |
|
| 84 |
+
| 0.4357 | 8.6034 | 3200 | 0.6060 |
|
| 85 |
+
| 0.4812 | 8.8727 | 3300 | 0.5998 |
|
| 86 |
+
| 0.4626 | 9.1401 | 3400 | 0.5989 |
|
| 87 |
+
| 0.4952 | 9.4094 | 3500 | 0.5938 |
|
| 88 |
+
| 0.3694 | 9.6788 | 3600 | 0.5918 |
|
| 89 |
+
| 0.4987 | 9.9481 | 3700 | 0.5911 |
|
| 90 |
+
|
| 91 |
+
|
| 92 |
+
### Framework versions
|
| 93 |
+
|
| 94 |
+
- PEFT 0.15.2
|
| 95 |
+
- Transformers 4.51.3
|
| 96 |
+
- Pytorch 2.6.0+cu126
|
| 97 |
+
- Datasets 3.5.0
|
| 98 |
+
- Tokenizers 0.21.1
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 12806992
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6d0b92d138c4e1ec7237c2a7c4a9631d12455f72303f6ea03bfcc0a8b489e2d2
|
| 3 |
size 12806992
|