End of training
Browse files- README.md +50 -50
- adapter_model.safetensors +1 -1
README.md
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
---
|
| 2 |
-
base_model: unsloth/llama-3-8b
|
| 3 |
library_name: peft
|
| 4 |
license: llama3
|
| 5 |
tags:
|
|
@@ -15,9 +15,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# Meta-Llama-3-8B_metamath_ortho
|
| 17 |
|
| 18 |
-
This model is a fine-tuned version of [unsloth/llama-3-8b
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
-
- Loss: 0.
|
| 21 |
|
| 22 |
## Model description
|
| 23 |
|
|
@@ -51,53 +51,53 @@ The following hyperparameters were used during training:
|
|
| 51 |
|
| 52 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 53 |
|:-------------:|:------:|:----:|:---------------:|
|
| 54 |
-
| 0.
|
| 55 |
-
| 0.
|
| 56 |
-
| 0.
|
| 57 |
-
| 0.
|
| 58 |
-
| 0.
|
| 59 |
-
| 0.
|
| 60 |
-
| 0.
|
| 61 |
-
| 0.
|
| 62 |
-
| 0.
|
| 63 |
-
| 0.
|
| 64 |
-
| 0.
|
| 65 |
-
| 0.
|
| 66 |
-
| 0.
|
| 67 |
-
| 0.
|
| 68 |
-
| 0.
|
| 69 |
-
| 0.
|
| 70 |
-
| 0.
|
| 71 |
-
| 0.
|
| 72 |
-
| 0.
|
| 73 |
-
| 0.
|
| 74 |
-
| 0.
|
| 75 |
-
| 0.
|
| 76 |
-
| 0.5691 | 0.4844 | 299 | 0.
|
| 77 |
-
| 0.
|
| 78 |
-
| 0.
|
| 79 |
-
| 0.
|
| 80 |
-
| 0.
|
| 81 |
-
| 0.
|
| 82 |
-
| 0.
|
| 83 |
-
| 0.
|
| 84 |
-
| 0.
|
| 85 |
-
| 0.
|
| 86 |
-
| 0.
|
| 87 |
-
| 0.
|
| 88 |
-
| 0.
|
| 89 |
-
| 0.
|
| 90 |
-
| 0.
|
| 91 |
-
| 0.
|
| 92 |
-
| 0.
|
| 93 |
-
| 0.
|
| 94 |
-
| 0.
|
| 95 |
-
| 0.
|
| 96 |
-
| 0.
|
| 97 |
-
| 0.
|
| 98 |
-
| 0.
|
| 99 |
-
| 0.
|
| 100 |
-
| 0.
|
| 101 |
|
| 102 |
|
| 103 |
### Framework versions
|
|
|
|
| 1 |
---
|
| 2 |
+
base_model: unsloth/llama-3-8b
|
| 3 |
library_name: peft
|
| 4 |
license: llama3
|
| 5 |
tags:
|
|
|
|
| 15 |
|
| 16 |
# Meta-Llama-3-8B_metamath_ortho
|
| 17 |
|
| 18 |
+
This model is a fine-tuned version of [unsloth/llama-3-8b](https://huggingface.co/unsloth/llama-3-8b) on an unknown dataset.
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 0.4760
|
| 21 |
|
| 22 |
## Model description
|
| 23 |
|
|
|
|
| 51 |
|
| 52 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 53 |
|:-------------:|:------:|:----:|:---------------:|
|
| 54 |
+
| 0.9348 | 0.0211 | 13 | 0.7026 |
|
| 55 |
+
| 0.6609 | 0.0421 | 26 | 0.6960 |
|
| 56 |
+
| 0.6695 | 0.0632 | 39 | 0.6785 |
|
| 57 |
+
| 0.6578 | 0.0842 | 52 | 0.6770 |
|
| 58 |
+
| 0.6222 | 0.1053 | 65 | 0.6748 |
|
| 59 |
+
| 0.6331 | 0.1264 | 78 | 0.6662 |
|
| 60 |
+
| 0.6413 | 0.1474 | 91 | 0.6609 |
|
| 61 |
+
| 0.631 | 0.1685 | 104 | 0.6538 |
|
| 62 |
+
| 0.6115 | 0.1896 | 117 | 0.6490 |
|
| 63 |
+
| 0.6097 | 0.2106 | 130 | 0.6458 |
|
| 64 |
+
| 0.6052 | 0.2317 | 143 | 0.6533 |
|
| 65 |
+
| 0.6131 | 0.2527 | 156 | 0.6335 |
|
| 66 |
+
| 0.6012 | 0.2738 | 169 | 0.6165 |
|
| 67 |
+
| 0.6002 | 0.2949 | 182 | 0.6204 |
|
| 68 |
+
| 0.5849 | 0.3159 | 195 | 0.6220 |
|
| 69 |
+
| 0.5689 | 0.3370 | 208 | 0.6159 |
|
| 70 |
+
| 0.5781 | 0.3580 | 221 | 0.6110 |
|
| 71 |
+
| 0.5765 | 0.3791 | 234 | 0.6027 |
|
| 72 |
+
| 0.5899 | 0.4002 | 247 | 0.5983 |
|
| 73 |
+
| 0.5638 | 0.4212 | 260 | 0.5905 |
|
| 74 |
+
| 0.5716 | 0.4423 | 273 | 0.5874 |
|
| 75 |
+
| 0.5729 | 0.4633 | 286 | 0.5809 |
|
| 76 |
+
| 0.5691 | 0.4844 | 299 | 0.5729 |
|
| 77 |
+
| 0.5441 | 0.5055 | 312 | 0.5659 |
|
| 78 |
+
| 0.5468 | 0.5265 | 325 | 0.5584 |
|
| 79 |
+
| 0.536 | 0.5476 | 338 | 0.5544 |
|
| 80 |
+
| 0.5277 | 0.5687 | 351 | 0.5474 |
|
| 81 |
+
| 0.5052 | 0.5897 | 364 | 0.5397 |
|
| 82 |
+
| 0.5185 | 0.6108 | 377 | 0.5309 |
|
| 83 |
+
| 0.5161 | 0.6318 | 390 | 0.5262 |
|
| 84 |
+
| 0.5056 | 0.6529 | 403 | 0.5227 |
|
| 85 |
+
| 0.5091 | 0.6740 | 416 | 0.5164 |
|
| 86 |
+
| 0.492 | 0.6950 | 429 | 0.5115 |
|
| 87 |
+
| 0.4936 | 0.7161 | 442 | 0.5070 |
|
| 88 |
+
| 0.4818 | 0.7371 | 455 | 0.5005 |
|
| 89 |
+
| 0.4762 | 0.7582 | 468 | 0.4986 |
|
| 90 |
+
| 0.4685 | 0.7793 | 481 | 0.4938 |
|
| 91 |
+
| 0.4614 | 0.8003 | 494 | 0.4904 |
|
| 92 |
+
| 0.4942 | 0.8214 | 507 | 0.4870 |
|
| 93 |
+
| 0.4767 | 0.8424 | 520 | 0.4837 |
|
| 94 |
+
| 0.4589 | 0.8635 | 533 | 0.4819 |
|
| 95 |
+
| 0.4806 | 0.8846 | 546 | 0.4796 |
|
| 96 |
+
| 0.4647 | 0.9056 | 559 | 0.4782 |
|
| 97 |
+
| 0.461 | 0.9267 | 572 | 0.4773 |
|
| 98 |
+
| 0.4718 | 0.9478 | 585 | 0.4766 |
|
| 99 |
+
| 0.4684 | 0.9688 | 598 | 0.4761 |
|
| 100 |
+
| 0.4716 | 0.9899 | 611 | 0.4760 |
|
| 101 |
|
| 102 |
|
| 103 |
### Framework versions
|
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 sha256:2c71cdd27ba68ced2890f274b11a62ad179b0af38e86e45b029273ab84463dae
|
| 3 |
size 83945296
|