Downloads · 30 days
0
V0224O5
Litzy619/V0224O5
V0224O5 is a machine learning model from Litzy619. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as other.
should probably proofread and complete it, then remove this comment. --
Access
Public
Updated Feb 25, 2024
Parameters
6.9B
14.8 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors14 GB · 95%
Parameter types
How the weights are stored.
F166.7B · 98%
Base models
Model card
From the Hugging Face model README
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
V0224O5
This model is a fine-tuned version of yahma/llama-7b-hf on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.7713
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0003
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 32
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine_with_restarts
- lr_scheduler_warmup_steps: 20
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.8517 | 0.13 | 10 | 1.5009 |
| 1.1581 | 0.26 | 20 | 0.9980 |
| 0.9259 | 0.39 | 30 | 0.8965 |
| 0.8595 | 0.52 | 40 | 0.8535 |
| 0.8378 | 0.65 | 50 | 0.8322 |
| 0.8184 | 0.78 | 60 | 0.8194 |
| 0.7913 | 0.91 | 70 | 0.8080 |
| 0.7787 | 1.04 | 80 | 0.7965 |
| 0.7446 | 1.17 | 90 | 0.7864 |
| 0.83 | 1.3 | 100 | 0.8335 |
| 0.802 | 1.43 | 110 | 0.8142 |
| 0.7787 | 1.55 | 120 | 0.8029 |
| 0.762 | 1.68 | 130 | 0.7935 |
| 0.7683 | 1.81 | 140 | 0.7844 |
| 0.768 | 1.94 | 150 | 0.7758 |
| 0.739 | 2.07 | 160 | 0.7745 |
| 0.7162 | 2.2 | 170 | 0.7741 |
| 0.7284 | 2.33 | 180 | 0.7702 |
| 0.7196 | 2.46 | 190 | 0.7701 |
| 0.721 | 2.59 | 200 | 0.7708 |
| 0.7242 | 2.72 | 210 | 0.7702 |
| 0.7233 | 2.85 | 220 | 0.7713 |
| 0.7246 | 2.98 | 230 | 0.7713 |
Framework versions
- Transformers 4.36.0.dev0
- Pytorch 2.1.2+cu121
- Datasets 2.14.6
- Tokenizers 0.14.1
- License
- other
- Created
- Feb 25, 2024
- Updated
- Feb 25, 2024