Model save
Browse files- README.md +88 -0
- adapter_model.safetensors +1 -1
README.md
ADDED
|
@@ -0,0 +1,88 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: llama3
|
| 3 |
+
library_name: peft
|
| 4 |
+
tags:
|
| 5 |
+
- trl
|
| 6 |
+
- sft
|
| 7 |
+
- generated_from_trainer
|
| 8 |
+
base_model: meta-llama/Meta-Llama-3-8B-Instruct
|
| 9 |
+
datasets:
|
| 10 |
+
- generator
|
| 11 |
+
model-index:
|
| 12 |
+
- name: Llama3-20240602
|
| 13 |
+
results: []
|
| 14 |
+
---
|
| 15 |
+
|
| 16 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 17 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 18 |
+
|
| 19 |
+
# Llama3-20240602
|
| 20 |
+
|
| 21 |
+
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 the generator dataset.
|
| 22 |
+
It achieves the following results on the evaluation set:
|
| 23 |
+
- Loss: 1.4100
|
| 24 |
+
|
| 25 |
+
## Model description
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Intended uses & limitations
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training and evaluation data
|
| 34 |
+
|
| 35 |
+
More information needed
|
| 36 |
+
|
| 37 |
+
## Training procedure
|
| 38 |
+
|
| 39 |
+
### Training hyperparameters
|
| 40 |
+
|
| 41 |
+
The following hyperparameters were used during training:
|
| 42 |
+
- learning_rate: 0.0002
|
| 43 |
+
- train_batch_size: 4
|
| 44 |
+
- eval_batch_size: 4
|
| 45 |
+
- seed: 42
|
| 46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 47 |
+
- lr_scheduler_type: constant
|
| 48 |
+
- lr_scheduler_warmup_steps: 0.03
|
| 49 |
+
- training_steps: 960
|
| 50 |
+
- mixed_precision_training: Native AMP
|
| 51 |
+
|
| 52 |
+
### Training results
|
| 53 |
+
|
| 54 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 55 |
+
|:-------------:|:------:|:----:|:---------------:|
|
| 56 |
+
| No log | 0.1356 | 40 | 1.3411 |
|
| 57 |
+
| No log | 0.2712 | 80 | 1.3121 |
|
| 58 |
+
| 1.335 | 0.4068 | 120 | 1.2957 |
|
| 59 |
+
| 1.335 | 0.5424 | 160 | 1.2854 |
|
| 60 |
+
| 1.258 | 0.6780 | 200 | 1.2772 |
|
| 61 |
+
| 1.258 | 0.8136 | 240 | 1.2706 |
|
| 62 |
+
| 1.258 | 0.9492 | 280 | 1.2642 |
|
| 63 |
+
| 1.2379 | 1.0847 | 320 | 1.2746 |
|
| 64 |
+
| 1.2379 | 1.2203 | 360 | 1.2682 |
|
| 65 |
+
| 1.1301 | 1.3559 | 400 | 1.2697 |
|
| 66 |
+
| 1.1301 | 1.4915 | 440 | 1.2713 |
|
| 67 |
+
| 1.1301 | 1.6271 | 480 | 1.2671 |
|
| 68 |
+
| 1.1256 | 1.7627 | 520 | 1.2633 |
|
| 69 |
+
| 1.1256 | 1.8983 | 560 | 1.2620 |
|
| 70 |
+
| 1.0987 | 2.0339 | 600 | 1.2888 |
|
| 71 |
+
| 1.0987 | 2.1695 | 640 | 1.3127 |
|
| 72 |
+
| 1.0987 | 2.3051 | 680 | 1.3148 |
|
| 73 |
+
| 0.9445 | 2.4407 | 720 | 1.3093 |
|
| 74 |
+
| 0.9445 | 2.5763 | 760 | 1.3086 |
|
| 75 |
+
| 0.9553 | 2.7119 | 800 | 1.3095 |
|
| 76 |
+
| 0.9553 | 2.8475 | 840 | 1.3029 |
|
| 77 |
+
| 0.9553 | 2.9831 | 880 | 1.3066 |
|
| 78 |
+
| 0.9298 | 3.1186 | 920 | 1.4147 |
|
| 79 |
+
| 0.9298 | 3.2542 | 960 | 1.4100 |
|
| 80 |
+
|
| 81 |
+
|
| 82 |
+
### Framework versions
|
| 83 |
+
|
| 84 |
+
- PEFT 0.11.1
|
| 85 |
+
- Transformers 4.41.2
|
| 86 |
+
- Pytorch 2.3.0+cu121
|
| 87 |
+
- Datasets 2.19.1
|
| 88 |
+
- 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 2806378968
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:010b822cff637325f3a78c3c5b8a09c0602ed06b9890101b864fb9b3c56fa154
|
| 3 |
size 2806378968
|