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_ortho_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_ortho_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: 9.3620
|
| 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 |
+
| 2.3352 | 0.0206 | 8 | 2.9038 |
|
| 55 |
+
| 11.3417 | 0.0412 | 16 | 11.9083 |
|
| 56 |
+
| 11.9918 | 0.0618 | 24 | 11.9774 |
|
| 57 |
+
| 11.9549 | 0.0824 | 32 | 11.9675 |
|
| 58 |
+
| 11.974 | 0.1030 | 40 | 11.9736 |
|
| 59 |
+
| 11.9403 | 0.1236 | 48 | 11.9468 |
|
| 60 |
+
| 11.9321 | 0.1442 | 56 | 11.8809 |
|
| 61 |
+
| 11.876 | 0.1648 | 64 | 11.8218 |
|
| 62 |
+
| 11.7886 | 0.1854 | 72 | 11.7345 |
|
| 63 |
+
| 11.6471 | 0.2060 | 80 | 11.6236 |
|
| 64 |
+
| 11.5982 | 0.2266 | 88 | 11.3718 |
|
| 65 |
+
| 11.7088 | 0.2472 | 96 | 11.6792 |
|
| 66 |
+
| 11.7296 | 0.2678 | 104 | 11.6883 |
|
| 67 |
+
| 11.6508 | 0.2885 | 112 | 11.4420 |
|
| 68 |
+
| 10.7655 | 0.3091 | 120 | 8.8174 |
|
| 69 |
+
| 8.5075 | 0.3297 | 128 | 9.0568 |
|
| 70 |
+
| 8.912 | 0.3503 | 136 | 9.4162 |
|
| 71 |
+
| 11.0052 | 0.3709 | 144 | 10.3473 |
|
| 72 |
+
| 9.103 | 0.3915 | 152 | 9.6451 |
|
| 73 |
+
| 8.9631 | 0.4121 | 160 | 8.6492 |
|
| 74 |
+
| 9.9634 | 0.4327 | 168 | 9.4401 |
|
| 75 |
+
| 9.814 | 0.4533 | 176 | 10.4748 |
|
| 76 |
+
| 10.507 | 0.4739 | 184 | 10.1910 |
|
| 77 |
+
| 9.6613 | 0.4945 | 192 | 9.2201 |
|
| 78 |
+
| 9.0448 | 0.5151 | 200 | 10.3913 |
|
| 79 |
+
| 9.4984 | 0.5357 | 208 | 8.5434 |
|
| 80 |
+
| 7.4393 | 0.5563 | 216 | 8.4350 |
|
| 81 |
+
| 10.0883 | 0.5769 | 224 | 10.2584 |
|
| 82 |
+
| 10.7162 | 0.5975 | 232 | 10.6899 |
|
| 83 |
+
| 10.4785 | 0.6181 | 240 | 10.4417 |
|
| 84 |
+
| 10.023 | 0.6387 | 248 | 9.6244 |
|
| 85 |
+
| 9.2272 | 0.6593 | 256 | 8.9308 |
|
| 86 |
+
| 9.1518 | 0.6799 | 264 | 9.2269 |
|
| 87 |
+
| 9.1733 | 0.7005 | 272 | 9.2434 |
|
| 88 |
+
| 9.3347 | 0.7211 | 280 | 9.2831 |
|
| 89 |
+
| 9.468 | 0.7417 | 288 | 9.1046 |
|
| 90 |
+
| 8.9402 | 0.7623 | 296 | 9.0102 |
|
| 91 |
+
| 9.1051 | 0.7829 | 304 | 9.2617 |
|
| 92 |
+
| 9.2223 | 0.8035 | 312 | 9.3921 |
|
| 93 |
+
| 9.3359 | 0.8241 | 320 | 9.3277 |
|
| 94 |
+
| 9.1508 | 0.8447 | 328 | 9.2755 |
|
| 95 |
+
| 9.5364 | 0.8654 | 336 | 9.3031 |
|
| 96 |
+
| 9.4429 | 0.8860 | 344 | 9.3229 |
|
| 97 |
+
| 9.3958 | 0.9066 | 352 | 9.3408 |
|
| 98 |
+
| 9.3778 | 0.9272 | 360 | 9.3577 |
|
| 99 |
+
| 9.1859 | 0.9478 | 368 | 9.3607 |
|
| 100 |
+
| 9.4256 | 0.9684 | 376 | 9.3622 |
|
| 101 |
+
| 9.3454 | 0.9890 | 384 | 9.3620 |
|
| 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 sha256:576080b8131adf7b0fb637902fccf7e9f6641dd2fecee714cb0705a88d4c0230
|
| 3 |
size 432223744
|