Model save
Browse files- README.md +81 -0
- adapter_model.safetensors +1 -1
README.md
ADDED
|
@@ -0,0 +1,81 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
license: llama3
|
| 4 |
+
base_model: meta-llama/Meta-Llama-3-8B-Instruct
|
| 5 |
+
tags:
|
| 6 |
+
- llama-factory
|
| 7 |
+
- generated_from_trainer
|
| 8 |
+
model-index:
|
| 9 |
+
- name: train_copa_1757340281
|
| 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 |
+
# train_copa_1757340281
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on an unknown dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 0.0330
|
| 21 |
+
- Num Input Tokens Seen: 281312
|
| 22 |
+
|
| 23 |
+
## Model description
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Intended uses & limitations
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training and evaluation data
|
| 32 |
+
|
| 33 |
+
More information needed
|
| 34 |
+
|
| 35 |
+
## Training procedure
|
| 36 |
+
|
| 37 |
+
### Training hyperparameters
|
| 38 |
+
|
| 39 |
+
The following hyperparameters were used during training:
|
| 40 |
+
- learning_rate: 5e-05
|
| 41 |
+
- train_batch_size: 4
|
| 42 |
+
- eval_batch_size: 4
|
| 43 |
+
- seed: 101112
|
| 44 |
+
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 45 |
+
- lr_scheduler_type: cosine
|
| 46 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 47 |
+
- num_epochs: 10.0
|
| 48 |
+
|
| 49 |
+
### Training results
|
| 50 |
+
|
| 51 |
+
| Training Loss | Epoch | Step | Validation Loss | Input Tokens Seen |
|
| 52 |
+
|:-------------:|:-----:|:----:|:---------------:|:-----------------:|
|
| 53 |
+
| 0.592 | 0.5 | 45 | 0.5497 | 14144 |
|
| 54 |
+
| 0.8778 | 1.0 | 90 | 0.3723 | 28192 |
|
| 55 |
+
| 0.0636 | 1.5 | 135 | 0.0465 | 42208 |
|
| 56 |
+
| 0.0595 | 2.0 | 180 | 0.0365 | 56256 |
|
| 57 |
+
| 0.242 | 2.5 | 225 | 0.0338 | 70368 |
|
| 58 |
+
| 0.014 | 3.0 | 270 | 0.0341 | 84320 |
|
| 59 |
+
| 0.1039 | 3.5 | 315 | 0.0326 | 98400 |
|
| 60 |
+
| 0.0307 | 4.0 | 360 | 0.0314 | 112416 |
|
| 61 |
+
| 0.3158 | 4.5 | 405 | 0.0345 | 126496 |
|
| 62 |
+
| 0.0098 | 5.0 | 450 | 0.0319 | 140544 |
|
| 63 |
+
| 0.0163 | 5.5 | 495 | 0.0342 | 154592 |
|
| 64 |
+
| 0.0024 | 6.0 | 540 | 0.0315 | 168768 |
|
| 65 |
+
| 0.0792 | 6.5 | 585 | 0.0330 | 182848 |
|
| 66 |
+
| 0.0327 | 7.0 | 630 | 0.0315 | 196896 |
|
| 67 |
+
| 0.1089 | 7.5 | 675 | 0.0345 | 210912 |
|
| 68 |
+
| 0.0141 | 8.0 | 720 | 0.0326 | 225024 |
|
| 69 |
+
| 0.0397 | 8.5 | 765 | 0.0324 | 239200 |
|
| 70 |
+
| 0.0891 | 9.0 | 810 | 0.0335 | 253152 |
|
| 71 |
+
| 0.0837 | 9.5 | 855 | 0.0317 | 267040 |
|
| 72 |
+
| 0.1442 | 10.0 | 900 | 0.0330 | 281312 |
|
| 73 |
+
|
| 74 |
+
|
| 75 |
+
### Framework versions
|
| 76 |
+
|
| 77 |
+
- PEFT 0.15.2
|
| 78 |
+
- Transformers 4.51.3
|
| 79 |
+
- Pytorch 2.8.0+cu128
|
| 80 |
+
- Datasets 3.6.0
|
| 81 |
+
- Tokenizers 0.21.1
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 798032
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f29a0d5237f3bf00417a9921c49900223a3442f12c6f32e9646e9519768a07d0
|
| 3 |
size 798032
|