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/llama-3-8b-bnb-4bit
|
| 3 |
+
library_name: peft
|
| 4 |
+
license: llama3
|
| 5 |
+
tags:
|
| 6 |
+
- unsloth
|
| 7 |
+
- generated_from_trainer
|
| 8 |
+
model-index:
|
| 9 |
+
- name: Meta-Llama-3-8B_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 |
+
# Meta-Llama-3-8B_metamath_default
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [unsloth/llama-3-8b-bnb-4bit](https://huggingface.co/unsloth/llama-3-8b-bnb-4bit) on an unknown dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 0.5076
|
| 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 |
+
| 1.1401 | 0.0211 | 13 | 0.7539 |
|
| 55 |
+
| 0.6625 | 0.0421 | 26 | 0.6617 |
|
| 56 |
+
| 0.6216 | 0.0632 | 39 | 0.6351 |
|
| 57 |
+
| 0.6049 | 0.0842 | 52 | 0.6233 |
|
| 58 |
+
| 0.5661 | 0.1053 | 65 | 0.6132 |
|
| 59 |
+
| 0.5763 | 0.1264 | 78 | 0.6084 |
|
| 60 |
+
| 0.5823 | 0.1474 | 91 | 0.6008 |
|
| 61 |
+
| 0.5671 | 0.1685 | 104 | 0.5951 |
|
| 62 |
+
| 0.5487 | 0.1896 | 117 | 0.5935 |
|
| 63 |
+
| 0.5486 | 0.2106 | 130 | 0.5895 |
|
| 64 |
+
| 0.5418 | 0.2317 | 143 | 0.5855 |
|
| 65 |
+
| 0.5522 | 0.2527 | 156 | 0.5829 |
|
| 66 |
+
| 0.547 | 0.2738 | 169 | 0.5749 |
|
| 67 |
+
| 0.5466 | 0.2949 | 182 | 0.5722 |
|
| 68 |
+
| 0.5369 | 0.3159 | 195 | 0.5694 |
|
| 69 |
+
| 0.5191 | 0.3370 | 208 | 0.5668 |
|
| 70 |
+
| 0.5274 | 0.3580 | 221 | 0.5617 |
|
| 71 |
+
| 0.5293 | 0.3791 | 234 | 0.5595 |
|
| 72 |
+
| 0.5384 | 0.4002 | 247 | 0.5551 |
|
| 73 |
+
| 0.5146 | 0.4212 | 260 | 0.5532 |
|
| 74 |
+
| 0.5283 | 0.4423 | 273 | 0.5499 |
|
| 75 |
+
| 0.5292 | 0.4633 | 286 | 0.5467 |
|
| 76 |
+
| 0.5305 | 0.4844 | 299 | 0.5441 |
|
| 77 |
+
| 0.5086 | 0.5055 | 312 | 0.5398 |
|
| 78 |
+
| 0.519 | 0.5265 | 325 | 0.5368 |
|
| 79 |
+
| 0.5084 | 0.5476 | 338 | 0.5355 |
|
| 80 |
+
| 0.5043 | 0.5687 | 351 | 0.5318 |
|
| 81 |
+
| 0.483 | 0.5897 | 364 | 0.5293 |
|
| 82 |
+
| 0.5066 | 0.6108 | 377 | 0.5257 |
|
| 83 |
+
| 0.5004 | 0.6318 | 390 | 0.5235 |
|
| 84 |
+
| 0.4927 | 0.6529 | 403 | 0.5226 |
|
| 85 |
+
| 0.498 | 0.6740 | 416 | 0.5199 |
|
| 86 |
+
| 0.4946 | 0.6950 | 429 | 0.5194 |
|
| 87 |
+
| 0.5002 | 0.7161 | 442 | 0.5174 |
|
| 88 |
+
| 0.49 | 0.7371 | 455 | 0.5149 |
|
| 89 |
+
| 0.477 | 0.7582 | 468 | 0.5142 |
|
| 90 |
+
| 0.4775 | 0.7793 | 481 | 0.5129 |
|
| 91 |
+
| 0.4745 | 0.8003 | 494 | 0.5119 |
|
| 92 |
+
| 0.506 | 0.8214 | 507 | 0.5105 |
|
| 93 |
+
| 0.4922 | 0.8424 | 520 | 0.5098 |
|
| 94 |
+
| 0.481 | 0.8635 | 533 | 0.5090 |
|
| 95 |
+
| 0.5014 | 0.8846 | 546 | 0.5085 |
|
| 96 |
+
| 0.4823 | 0.9056 | 559 | 0.5081 |
|
| 97 |
+
| 0.4781 | 0.9267 | 572 | 0.5078 |
|
| 98 |
+
| 0.4913 | 0.9478 | 585 | 0.5077 |
|
| 99 |
+
| 0.4975 | 0.9688 | 598 | 0.5075 |
|
| 100 |
+
| 0.4959 | 0.9899 | 611 | 0.5076 |
|
| 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:a0c3fb5866db88b61ef7fa15e23d69bc8bc262f2f1f60fbe5b07f6ce217adcdf
|
| 3 |
size 83945296
|