End of training
Browse files- README.md +109 -0
- adapter_model.safetensors +1 -1
README.md
ADDED
|
@@ -0,0 +1,109 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: unsloth/gemma-2-9b
|
| 3 |
+
library_name: peft
|
| 4 |
+
license: gemma
|
| 5 |
+
tags:
|
| 6 |
+
- unsloth
|
| 7 |
+
- generated_from_trainer
|
| 8 |
+
model-index:
|
| 9 |
+
- name: gemma-2-9b_metamath_ortho
|
| 10 |
+
results: []
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 14 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
+
|
| 16 |
+
# gemma-2-9b_metamath_ortho
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [unsloth/gemma-2-9b](https://huggingface.co/unsloth/gemma-2-9b) on an unknown dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 8.8949
|
| 21 |
+
|
| 22 |
+
## Model description
|
| 23 |
+
|
| 24 |
+
More information needed
|
| 25 |
+
|
| 26 |
+
## Intended uses & limitations
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Training and evaluation data
|
| 31 |
+
|
| 32 |
+
More information needed
|
| 33 |
+
|
| 34 |
+
## Training procedure
|
| 35 |
+
|
| 36 |
+
### Training hyperparameters
|
| 37 |
+
|
| 38 |
+
The following hyperparameters were used during training:
|
| 39 |
+
- learning_rate: 0.0003
|
| 40 |
+
- train_batch_size: 2
|
| 41 |
+
- eval_batch_size: 2
|
| 42 |
+
- seed: 42
|
| 43 |
+
- gradient_accumulation_steps: 32
|
| 44 |
+
- total_train_batch_size: 64
|
| 45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 46 |
+
- lr_scheduler_type: cosine
|
| 47 |
+
- lr_scheduler_warmup_ratio: 0.02
|
| 48 |
+
- num_epochs: 1
|
| 49 |
+
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 53 |
+
|:-------------:|:------:|:----:|:---------------:|
|
| 54 |
+
| 0.7552 | 0.0211 | 13 | 11.3000 |
|
| 55 |
+
| 11.6101 | 0.0421 | 26 | 11.6207 |
|
| 56 |
+
| 11.2097 | 0.0632 | 39 | 11.2115 |
|
| 57 |
+
| 10.6416 | 0.0843 | 52 | 11.2629 |
|
| 58 |
+
| 11.087 | 0.1053 | 65 | 11.0208 |
|
| 59 |
+
| 10.911 | 0.1264 | 78 | 11.1743 |
|
| 60 |
+
| 10.3864 | 0.1474 | 91 | 9.9812 |
|
| 61 |
+
| 10.0221 | 0.1685 | 104 | 9.7955 |
|
| 62 |
+
| 10.1644 | 0.1896 | 117 | 10.3842 |
|
| 63 |
+
| 10.6605 | 0.2106 | 130 | 10.8225 |
|
| 64 |
+
| 10.6448 | 0.2317 | 143 | 10.6978 |
|
| 65 |
+
| 10.6678 | 0.2528 | 156 | 10.5545 |
|
| 66 |
+
| 10.3694 | 0.2738 | 169 | 9.2694 |
|
| 67 |
+
| 11.5024 | 0.2949 | 182 | 11.9171 |
|
| 68 |
+
| 11.731 | 0.3159 | 195 | 11.1801 |
|
| 69 |
+
| 11.5971 | 0.3370 | 208 | 10.8633 |
|
| 70 |
+
| 11.0785 | 0.3581 | 221 | 10.8301 |
|
| 71 |
+
| 10.5228 | 0.3791 | 234 | 10.5660 |
|
| 72 |
+
| 10.4021 | 0.4002 | 247 | 10.2953 |
|
| 73 |
+
| 10.2801 | 0.4213 | 260 | 10.1140 |
|
| 74 |
+
| 11.5045 | 0.4423 | 273 | 11.9247 |
|
| 75 |
+
| 11.7387 | 0.4634 | 286 | 11.5647 |
|
| 76 |
+
| 11.6365 | 0.4845 | 299 | 11.5171 |
|
| 77 |
+
| 10.8443 | 0.5055 | 312 | 9.7961 |
|
| 78 |
+
| 11.0662 | 0.5266 | 325 | 10.9008 |
|
| 79 |
+
| 10.9411 | 0.5476 | 338 | 11.0820 |
|
| 80 |
+
| 11.2701 | 0.5687 | 351 | 11.4640 |
|
| 81 |
+
| 10.8777 | 0.5898 | 364 | 9.6432 |
|
| 82 |
+
| 10.3239 | 0.6108 | 377 | 10.6138 |
|
| 83 |
+
| 10.8646 | 0.6319 | 390 | 10.7791 |
|
| 84 |
+
| 11.2221 | 0.6530 | 403 | 11.1868 |
|
| 85 |
+
| 11.0328 | 0.6740 | 416 | 10.8502 |
|
| 86 |
+
| 10.8706 | 0.6951 | 429 | 10.7639 |
|
| 87 |
+
| 10.9227 | 0.7162 | 442 | 10.7393 |
|
| 88 |
+
| 10.3582 | 0.7372 | 455 | 8.8997 |
|
| 89 |
+
| 9.4372 | 0.7583 | 468 | 9.9192 |
|
| 90 |
+
| 9.5329 | 0.7793 | 481 | 9.3924 |
|
| 91 |
+
| 9.6104 | 0.8004 | 494 | 9.3153 |
|
| 92 |
+
| 9.3477 | 0.8215 | 507 | 9.2830 |
|
| 93 |
+
| 9.7923 | 0.8425 | 520 | 8.8935 |
|
| 94 |
+
| 8.8863 | 0.8636 | 533 | 9.5862 |
|
| 95 |
+
| 8.9213 | 0.8847 | 546 | 8.4786 |
|
| 96 |
+
| 8.5736 | 0.9057 | 559 | 9.8808 |
|
| 97 |
+
| 9.5766 | 0.9268 | 572 | 8.6842 |
|
| 98 |
+
| 8.6045 | 0.9478 | 585 | 8.7064 |
|
| 99 |
+
| 8.6253 | 0.9689 | 598 | 8.8377 |
|
| 100 |
+
| 8.8052 | 0.9900 | 611 | 8.8949 |
|
| 101 |
+
|
| 102 |
+
|
| 103 |
+
### Framework versions
|
| 104 |
+
|
| 105 |
+
- PEFT 0.12.0
|
| 106 |
+
- Transformers 4.44.0
|
| 107 |
+
- Pytorch 2.4.0+cu121
|
| 108 |
+
- Datasets 2.20.0
|
| 109 |
+
- 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 108113968
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:88fb7596ea2460ddf2e5a52c7dfd4d5f28564321fbe17416f46e5584b79bccc9
|
| 3 |
size 108113968
|