End of training
Browse files- README.md +110 -0
- adapter_model.safetensors +1 -1
README.md
ADDED
|
@@ -0,0 +1,110 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: google/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_pct_default_r32
|
| 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_pct_default_r32
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [google/gemma-2-9b](https://huggingface.co/google/gemma-2-9b) on an unknown dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 9.9020
|
| 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: 0.0001
|
| 40 |
+
- train_batch_size: 1
|
| 41 |
+
- eval_batch_size: 1
|
| 42 |
+
- seed: 42
|
| 43 |
+
- gradient_accumulation_steps: 64
|
| 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 |
+
| 2.5978 | 0.0206 | 8 | 4.9799 |
|
| 55 |
+
| 11.0056 | 0.0412 | 16 | 11.4640 |
|
| 56 |
+
| 11.7215 | 0.0618 | 24 | 11.8765 |
|
| 57 |
+
| 11.8793 | 0.0824 | 32 | 11.9059 |
|
| 58 |
+
| 11.8739 | 0.1030 | 40 | 11.9781 |
|
| 59 |
+
| 11.8763 | 0.1236 | 48 | 11.9487 |
|
| 60 |
+
| 11.8231 | 0.1442 | 56 | 11.8282 |
|
| 61 |
+
| 11.7758 | 0.1648 | 64 | 11.7664 |
|
| 62 |
+
| 11.8011 | 0.1854 | 72 | 11.4372 |
|
| 63 |
+
| 11.6991 | 0.2060 | 80 | 11.7334 |
|
| 64 |
+
| 11.8108 | 0.2266 | 88 | 11.5005 |
|
| 65 |
+
| 11.6519 | 0.2472 | 96 | 11.5944 |
|
| 66 |
+
| 11.6905 | 0.2678 | 104 | 11.5944 |
|
| 67 |
+
| 11.6003 | 0.2885 | 112 | 11.5914 |
|
| 68 |
+
| 11.5813 | 0.3091 | 120 | 11.5684 |
|
| 69 |
+
| 11.5493 | 0.3297 | 128 | 11.7560 |
|
| 70 |
+
| 11.5458 | 0.3503 | 136 | 11.4566 |
|
| 71 |
+
| 11.5838 | 0.3709 | 144 | 11.4331 |
|
| 72 |
+
| 11.4815 | 0.3915 | 152 | 11.5174 |
|
| 73 |
+
| 11.5369 | 0.4121 | 160 | 11.5271 |
|
| 74 |
+
| 11.4617 | 0.4327 | 168 | 11.5392 |
|
| 75 |
+
| 11.4399 | 0.4533 | 176 | 11.3691 |
|
| 76 |
+
| 11.3199 | 0.4739 | 184 | 10.9823 |
|
| 77 |
+
| 10.6547 | 0.4945 | 192 | 10.0666 |
|
| 78 |
+
| 8.8163 | 0.5151 | 200 | 8.7638 |
|
| 79 |
+
| 9.5635 | 0.5357 | 208 | 8.5153 |
|
| 80 |
+
| 8.7862 | 0.5563 | 216 | 9.2186 |
|
| 81 |
+
| 10.2774 | 0.5769 | 224 | 10.3834 |
|
| 82 |
+
| 9.7932 | 0.5975 | 232 | 9.7972 |
|
| 83 |
+
| 9.5421 | 0.6181 | 240 | 9.6845 |
|
| 84 |
+
| 9.5401 | 0.6387 | 248 | 9.3438 |
|
| 85 |
+
| 10.9001 | 0.6593 | 256 | 10.6070 |
|
| 86 |
+
| 9.959 | 0.6799 | 264 | 9.6172 |
|
| 87 |
+
| 9.5409 | 0.7005 | 272 | 10.4762 |
|
| 88 |
+
| 10.8074 | 0.7211 | 280 | 10.4872 |
|
| 89 |
+
| 9.1645 | 0.7417 | 288 | 7.6567 |
|
| 90 |
+
| 8.1072 | 0.7623 | 296 | 8.7911 |
|
| 91 |
+
| 9.7069 | 0.7829 | 304 | 10.0043 |
|
| 92 |
+
| 10.0752 | 0.8035 | 312 | 10.1655 |
|
| 93 |
+
| 9.9734 | 0.8241 | 320 | 9.9644 |
|
| 94 |
+
| 9.6722 | 0.8447 | 328 | 9.7803 |
|
| 95 |
+
| 9.8279 | 0.8654 | 336 | 9.5826 |
|
| 96 |
+
| 9.6714 | 0.8860 | 344 | 9.5533 |
|
| 97 |
+
| 9.655 | 0.9066 | 352 | 9.6339 |
|
| 98 |
+
| 9.7184 | 0.9272 | 360 | 9.7651 |
|
| 99 |
+
| 9.6142 | 0.9478 | 368 | 9.8536 |
|
| 100 |
+
| 9.9249 | 0.9684 | 376 | 9.8906 |
|
| 101 |
+
| 9.8654 | 0.9890 | 384 | 9.9020 |
|
| 102 |
+
|
| 103 |
+
|
| 104 |
+
### Framework versions
|
| 105 |
+
|
| 106 |
+
- PEFT 0.12.0
|
| 107 |
+
- Transformers 4.44.2
|
| 108 |
+
- Pytorch 2.3.0+cu121
|
| 109 |
+
- Datasets 2.21.0
|
| 110 |
+
- 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 432223744
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4640e05299b3e974dd36f0c2df2315eb039a6e7f3723e5bf27ad96b1da3656fc
|
| 3 |
size 432223744
|