Downloads · 30 days
0
V0305P4
Litzy619/V0305P4
V0305P4 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 Mar 6, 2024
Parameters
6.8B
14 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors13.8 GB · 98%
Parameter types
How the weights are stored.
F166.7B · 99%
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. -->
V0305P4
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: 0.0583
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 |
|---|---|---|---|
| 1.8125 | 0.09 | 10 | 0.6624 |
| 0.25 | 0.17 | 20 | 0.1568 |
| 0.1567 | 0.26 | 30 | 0.1543 |
| 0.1522 | 0.34 | 40 | 0.1471 |
| 0.1487 | 0.43 | 50 | 0.1446 |
| 0.1517 | 0.51 | 60 | 0.1370 |
| 0.1348 | 0.6 | 70 | 0.1154 |
| 0.1261 | 0.68 | 80 | 0.1077 |
| 0.1125 | 0.77 | 90 | 0.0915 |
| 0.1142 | 0.85 | 100 | 0.0879 |
| 0.1095 | 0.94 | 110 | 0.0932 |
| 0.1035 | 1.02 | 120 | 0.0936 |
| 0.094 | 1.11 | 130 | 0.0874 |
| 0.0899 | 1.19 | 140 | 0.0800 |
| 0.0875 | 1.28 | 150 | 0.0835 |
| 0.0887 | 1.37 | 160 | 0.0783 |
| 0.0884 | 1.45 | 170 | 0.0791 |
| 0.0819 | 1.54 | 180 | 0.0745 |
| 0.0831 | 1.62 | 190 | 0.0685 |
| 0.0878 | 1.71 | 200 | 0.0681 |
| 0.0847 | 1.79 | 210 | 0.0680 |
| 0.0798 | 1.88 | 220 | 0.0646 |
| 0.0757 | 1.96 | 230 | 0.0680 |
| 0.0653 | 2.05 | 240 | 0.0663 |
| 0.0557 | 2.13 | 250 | 0.0678 |
| 0.052 | 2.22 | 260 | 0.0634 |
| 0.0517 | 2.3 | 270 | 0.0654 |
| 0.0576 | 2.39 | 280 | 0.0593 |
| 0.0573 | 2.47 | 290 | 0.0584 |
| 0.056 | 2.56 | 300 | 0.0569 |
| 0.0597 | 2.65 | 310 | 0.0584 |
| 0.0514 | 2.73 | 320 | 0.0578 |
| 0.0533 | 2.82 | 330 | 0.0577 |
| 0.0538 | 2.9 | 340 | 0.0582 |
| 0.0507 | 2.99 | 350 | 0.0583 |
Framework versions
- Transformers 4.36.0.dev0
- Pytorch 2.1.2+cu121
- Datasets 2.14.6
- Tokenizers 0.14.1
- License
- other
- Created
- Mar 5, 2024
- Updated
- Mar 6, 2024