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/mistral-7b-v0.3-bnb-4bit
|
| 3 |
+
library_name: peft
|
| 4 |
+
license: apache-2.0
|
| 5 |
+
tags:
|
| 6 |
+
- unsloth
|
| 7 |
+
- generated_from_trainer
|
| 8 |
+
model-index:
|
| 9 |
+
- name: Mistral-7B-v0.3_metamath_default
|
| 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 |
+
# Mistral-7B-v0.3_metamath_default
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [unsloth/mistral-7b-v0.3-bnb-4bit](https://huggingface.co/unsloth/mistral-7b-v0.3-bnb-4bit) on an unknown dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 4.0734
|
| 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 |
+
| 0.7559 | 0.0211 | 13 | 8.3985 |
|
| 55 |
+
| 9.4604 | 0.0421 | 26 | 6.8141 |
|
| 56 |
+
| 6.7353 | 0.0632 | 39 | 6.4223 |
|
| 57 |
+
| 6.4242 | 0.0842 | 52 | 6.2759 |
|
| 58 |
+
| 6.1115 | 0.1053 | 65 | 6.0333 |
|
| 59 |
+
| 5.9214 | 0.1264 | 78 | 5.8343 |
|
| 60 |
+
| 5.6735 | 0.1474 | 91 | 5.5846 |
|
| 61 |
+
| 5.557 | 0.1685 | 104 | 5.4916 |
|
| 62 |
+
| 5.3297 | 0.1896 | 117 | 5.2345 |
|
| 63 |
+
| 5.1963 | 0.2106 | 130 | 5.1310 |
|
| 64 |
+
| 5.1252 | 0.2317 | 143 | 5.0674 |
|
| 65 |
+
| 4.983 | 0.2527 | 156 | 4.9390 |
|
| 66 |
+
| 4.8933 | 0.2738 | 169 | 4.8252 |
|
| 67 |
+
| 4.7722 | 0.2949 | 182 | 4.7449 |
|
| 68 |
+
| 4.7722 | 0.3159 | 195 | 4.7386 |
|
| 69 |
+
| 4.6446 | 0.3370 | 208 | 4.6346 |
|
| 70 |
+
| 4.5823 | 0.3580 | 221 | 4.5544 |
|
| 71 |
+
| 4.576 | 0.3791 | 234 | 4.5238 |
|
| 72 |
+
| 4.5056 | 0.4002 | 247 | 4.6538 |
|
| 73 |
+
| 4.5501 | 0.4212 | 260 | 4.4766 |
|
| 74 |
+
| 4.5197 | 0.4423 | 273 | 4.4369 |
|
| 75 |
+
| 4.6259 | 0.4633 | 286 | 4.4561 |
|
| 76 |
+
| 4.546 | 0.4844 | 299 | 4.4278 |
|
| 77 |
+
| 4.3478 | 0.5055 | 312 | 4.3790 |
|
| 78 |
+
| 4.3754 | 0.5265 | 325 | 4.3635 |
|
| 79 |
+
| 4.2714 | 0.5476 | 338 | 4.3611 |
|
| 80 |
+
| 4.3724 | 0.5687 | 351 | 4.3629 |
|
| 81 |
+
| 4.2961 | 0.5897 | 364 | 4.2578 |
|
| 82 |
+
| 4.2806 | 0.6108 | 377 | 4.2863 |
|
| 83 |
+
| 4.3088 | 0.6318 | 390 | 4.2221 |
|
| 84 |
+
| 4.2165 | 0.6529 | 403 | 4.2158 |
|
| 85 |
+
| 4.1776 | 0.6740 | 416 | 4.1896 |
|
| 86 |
+
| 4.2615 | 0.6950 | 429 | 4.3146 |
|
| 87 |
+
| 4.2536 | 0.7161 | 442 | 4.2153 |
|
| 88 |
+
| 4.1308 | 0.7371 | 455 | 4.1701 |
|
| 89 |
+
| 4.1749 | 0.7582 | 468 | 4.1346 |
|
| 90 |
+
| 4.1219 | 0.7793 | 481 | 4.1276 |
|
| 91 |
+
| 4.136 | 0.8003 | 494 | 4.1162 |
|
| 92 |
+
| 4.1453 | 0.8214 | 507 | 4.1070 |
|
| 93 |
+
| 4.1025 | 0.8424 | 520 | 4.1167 |
|
| 94 |
+
| 4.1207 | 0.8635 | 533 | 4.0925 |
|
| 95 |
+
| 4.0847 | 0.8846 | 546 | 4.0926 |
|
| 96 |
+
| 4.1504 | 0.9056 | 559 | 4.0795 |
|
| 97 |
+
| 4.1211 | 0.9267 | 572 | 4.0711 |
|
| 98 |
+
| 4.038 | 0.9478 | 585 | 4.0763 |
|
| 99 |
+
| 4.0944 | 0.9688 | 598 | 4.0744 |
|
| 100 |
+
| 4.0771 | 0.9899 | 611 | 4.0734 |
|
| 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 83945296
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5c74f2dca02c48070781b4a3e11f48d2a0dfb3c9ee36ed9aaa9afbc40602b72d
|
| 3 |
size 83945296
|