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: unsloth/Qwen2-7B
|
| 3 |
+
library_name: peft
|
| 4 |
+
license: apache-2.0
|
| 5 |
+
tags:
|
| 6 |
+
- unsloth
|
| 7 |
+
- generated_from_trainer
|
| 8 |
+
model-index:
|
| 9 |
+
- name: Qwen2-7B_pct_ortho_r16
|
| 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 |
+
# Qwen2-7B_pct_ortho_r16
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [unsloth/Qwen2-7B](https://huggingface.co/unsloth/Qwen2-7B) on an unknown dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 1.9385
|
| 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: 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 |
+
| 2.0486 | 0.0206 | 8 | 1.9976 |
|
| 55 |
+
| 1.9839 | 0.0412 | 16 | 1.9348 |
|
| 56 |
+
| 2.0083 | 0.0618 | 24 | 1.9231 |
|
| 57 |
+
| 1.923 | 0.0824 | 32 | 1.9185 |
|
| 58 |
+
| 1.9734 | 0.1031 | 40 | 1.9200 |
|
| 59 |
+
| 1.9761 | 0.1237 | 48 | 1.9230 |
|
| 60 |
+
| 1.9869 | 0.1443 | 56 | 1.9226 |
|
| 61 |
+
| 1.9196 | 0.1649 | 64 | 1.9238 |
|
| 62 |
+
| 1.9871 | 0.1855 | 72 | 1.9276 |
|
| 63 |
+
| 2.0064 | 0.2061 | 80 | 1.9251 |
|
| 64 |
+
| 1.9864 | 0.2267 | 88 | 1.9282 |
|
| 65 |
+
| 1.9204 | 0.2473 | 96 | 1.9319 |
|
| 66 |
+
| 2.0003 | 0.2680 | 104 | 1.9295 |
|
| 67 |
+
| 1.8821 | 0.2886 | 112 | 1.9357 |
|
| 68 |
+
| 1.9353 | 0.3092 | 120 | 1.9354 |
|
| 69 |
+
| 1.9737 | 0.3298 | 128 | 1.9392 |
|
| 70 |
+
| 1.9608 | 0.3504 | 136 | 1.9337 |
|
| 71 |
+
| 1.928 | 0.3710 | 144 | 1.9365 |
|
| 72 |
+
| 2.0019 | 0.3916 | 152 | 1.9326 |
|
| 73 |
+
| 2.0525 | 0.4122 | 160 | 1.9403 |
|
| 74 |
+
| 2.053 | 0.4329 | 168 | 1.9402 |
|
| 75 |
+
| 1.9342 | 0.4535 | 176 | 1.9374 |
|
| 76 |
+
| 1.9931 | 0.4741 | 184 | 1.9400 |
|
| 77 |
+
| 2.0008 | 0.4947 | 192 | 1.9413 |
|
| 78 |
+
| 1.9426 | 0.5153 | 200 | 1.9406 |
|
| 79 |
+
| 1.9732 | 0.5359 | 208 | 1.9409 |
|
| 80 |
+
| 2.0263 | 0.5565 | 216 | 1.9431 |
|
| 81 |
+
| 1.9589 | 0.5771 | 224 | 1.9444 |
|
| 82 |
+
| 1.9824 | 0.5977 | 232 | 1.9460 |
|
| 83 |
+
| 1.9252 | 0.6184 | 240 | 1.9399 |
|
| 84 |
+
| 1.9563 | 0.6390 | 248 | 1.9400 |
|
| 85 |
+
| 2.0096 | 0.6596 | 256 | 1.9414 |
|
| 86 |
+
| 1.9355 | 0.6802 | 264 | 1.9420 |
|
| 87 |
+
| 2.003 | 0.7008 | 272 | 1.9415 |
|
| 88 |
+
| 1.877 | 0.7214 | 280 | 1.9396 |
|
| 89 |
+
| 2.0395 | 0.7420 | 288 | 1.9378 |
|
| 90 |
+
| 1.9447 | 0.7626 | 296 | 1.9382 |
|
| 91 |
+
| 1.965 | 0.7833 | 304 | 1.9391 |
|
| 92 |
+
| 1.9656 | 0.8039 | 312 | 1.9353 |
|
| 93 |
+
| 1.9928 | 0.8245 | 320 | 1.9398 |
|
| 94 |
+
| 2.0004 | 0.8451 | 328 | 1.9392 |
|
| 95 |
+
| 1.9883 | 0.8657 | 336 | 1.9389 |
|
| 96 |
+
| 1.9764 | 0.8863 | 344 | 1.9395 |
|
| 97 |
+
| 1.9474 | 0.9069 | 352 | 1.9390 |
|
| 98 |
+
| 2.0375 | 0.9275 | 360 | 1.9382 |
|
| 99 |
+
| 1.9424 | 0.9481 | 368 | 1.9386 |
|
| 100 |
+
| 2.0088 | 0.9688 | 376 | 1.9385 |
|
| 101 |
+
| 1.9043 | 0.9894 | 384 | 1.9385 |
|
| 102 |
+
|
| 103 |
+
|
| 104 |
+
### Framework versions
|
| 105 |
+
|
| 106 |
+
- PEFT 0.12.0
|
| 107 |
+
- Transformers 4.44.0
|
| 108 |
+
- Pytorch 2.4.0+cu121
|
| 109 |
+
- Datasets 2.20.0
|
| 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 161533192
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d16e179e0ef8e75efa6993a39c0f6338a4a2d967534d9a5b9c45a34bd8f9bff6
|
| 3 |
size 161533192
|