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/qwen2-7b-bnb-4bit
|
| 3 |
+
library_name: peft
|
| 4 |
+
license: apache-2.0
|
| 5 |
+
tags:
|
| 6 |
+
- unsloth
|
| 7 |
+
- generated_from_trainer
|
| 8 |
+
model-index:
|
| 9 |
+
- name: Qwen2-7B_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 |
+
# Qwen2-7B_metamath_ortho
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [unsloth/qwen2-7b-bnb-4bit](https://huggingface.co/unsloth/qwen2-7b-bnb-4bit) on an unknown dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 0.2209
|
| 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: 8
|
| 41 |
+
- eval_batch_size: 8
|
| 42 |
+
- seed: 42
|
| 43 |
+
- gradient_accumulation_steps: 8
|
| 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 |
+
| 0.2058 | 0.0211 | 13 | 0.2001 |
|
| 55 |
+
| 0.2083 | 0.0421 | 26 | 0.2441 |
|
| 56 |
+
| 0.247 | 0.0632 | 39 | 0.2670 |
|
| 57 |
+
| 0.2629 | 0.0842 | 52 | 0.2797 |
|
| 58 |
+
| 0.2692 | 0.1053 | 65 | 0.2921 |
|
| 59 |
+
| 0.2867 | 0.1264 | 78 | 0.2992 |
|
| 60 |
+
| 0.2939 | 0.1474 | 91 | 0.3022 |
|
| 61 |
+
| 0.2839 | 0.1685 | 104 | 0.3037 |
|
| 62 |
+
| 0.2922 | 0.1896 | 117 | 0.3071 |
|
| 63 |
+
| 0.2937 | 0.2106 | 130 | 0.3114 |
|
| 64 |
+
| 0.3016 | 0.2317 | 143 | 0.3096 |
|
| 65 |
+
| 0.298 | 0.2527 | 156 | 0.3078 |
|
| 66 |
+
| 0.3059 | 0.2738 | 169 | 0.3083 |
|
| 67 |
+
| 0.2883 | 0.2949 | 182 | 0.3052 |
|
| 68 |
+
| 0.3013 | 0.3159 | 195 | 0.3010 |
|
| 69 |
+
| 0.2874 | 0.3370 | 208 | 0.2995 |
|
| 70 |
+
| 0.286 | 0.3580 | 221 | 0.2979 |
|
| 71 |
+
| 0.2877 | 0.3791 | 234 | 0.2981 |
|
| 72 |
+
| 0.2858 | 0.4002 | 247 | 0.2921 |
|
| 73 |
+
| 0.2853 | 0.4212 | 260 | 0.2906 |
|
| 74 |
+
| 0.2887 | 0.4423 | 273 | 0.2882 |
|
| 75 |
+
| 0.2772 | 0.4633 | 286 | 0.2837 |
|
| 76 |
+
| 0.2867 | 0.4844 | 299 | 0.2799 |
|
| 77 |
+
| 0.2659 | 0.5055 | 312 | 0.2776 |
|
| 78 |
+
| 0.2688 | 0.5265 | 325 | 0.2746 |
|
| 79 |
+
| 0.2564 | 0.5476 | 338 | 0.2690 |
|
| 80 |
+
| 0.2587 | 0.5687 | 351 | 0.2657 |
|
| 81 |
+
| 0.2615 | 0.5897 | 364 | 0.2619 |
|
| 82 |
+
| 0.2517 | 0.6108 | 377 | 0.2576 |
|
| 83 |
+
| 0.2453 | 0.6318 | 390 | 0.2516 |
|
| 84 |
+
| 0.2473 | 0.6529 | 403 | 0.2475 |
|
| 85 |
+
| 0.2494 | 0.6740 | 416 | 0.2444 |
|
| 86 |
+
| 0.2397 | 0.6950 | 429 | 0.2405 |
|
| 87 |
+
| 0.2438 | 0.7161 | 442 | 0.2369 |
|
| 88 |
+
| 0.2288 | 0.7371 | 455 | 0.2344 |
|
| 89 |
+
| 0.2293 | 0.7582 | 468 | 0.2319 |
|
| 90 |
+
| 0.2372 | 0.7793 | 481 | 0.2310 |
|
| 91 |
+
| 0.2296 | 0.8003 | 494 | 0.2284 |
|
| 92 |
+
| 0.2163 | 0.8214 | 507 | 0.2263 |
|
| 93 |
+
| 0.2249 | 0.8424 | 520 | 0.2241 |
|
| 94 |
+
| 0.219 | 0.8635 | 533 | 0.2234 |
|
| 95 |
+
| 0.2154 | 0.8846 | 546 | 0.2230 |
|
| 96 |
+
| 0.2107 | 0.9056 | 559 | 0.2221 |
|
| 97 |
+
| 0.2132 | 0.9267 | 572 | 0.2215 |
|
| 98 |
+
| 0.2202 | 0.9478 | 585 | 0.2212 |
|
| 99 |
+
| 0.2197 | 0.9688 | 598 | 0.2211 |
|
| 100 |
+
| 0.2168 | 0.9899 | 611 | 0.2209 |
|
| 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 80792096
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0bc87d419007c498b36c66497414e944e21e3eaf79295ed6065ae6cb0b70c0f3
|
| 3 |
size 80792096
|