Downloads · 30 days
6
21% of all-time downloads
results_Phi3_medium_4k
kostasman1/results_Phi3_medium_4k
results_Phi3_medium_4k is a machine learning model from kostasman1. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft. The card lists the license as mit.
should probably proofread and complete it, then remove this comment. --
All-time downloads
29
Public
Repo size
85.7 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors85.2 MB · 97%
At a glance
- Library
- peft
- License
- mit
- Access
- Public
- Created
- Jun 14, 2024
- Updated
- Jun 14, 2024
- SHA
- 4a6b16e5
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. -->
results_Phi3_medium_4k
This model is a fine-tuned version of microsoft/Phi-3-medium-4k-instruct on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3210
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: 5e-05
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.1017 | 0.1065 | 100 | 2.1255 |
| 2.042 | 0.2130 | 200 | 2.0092 |
| 1.8529 | 0.3195 | 300 | 1.8467 |
| 1.7071 | 0.4260 | 400 | 1.6110 |
| 1.3058 | 0.5325 | 500 | 1.4370 |
| 1.0229 | 0.6390 | 600 | 1.1798 |
| 0.7982 | 0.7455 | 700 | 1.0212 |
| 0.9674 | 0.8520 | 800 | 0.8781 |
| 0.7444 | 0.9585 | 900 | 0.7509 |
| 0.6362 | 1.0650 | 1000 | 0.6309 |
| 0.4962 | 1.1715 | 1100 | 0.5848 |
| 0.3617 | 1.2780 | 1200 | 0.5107 |
| 0.3606 | 1.3845 | 1300 | 0.4532 |
| 0.4413 | 1.4909 | 1400 | 0.4173 |
| 0.4594 | 1.5974 | 1500 | 0.3998 |
| 0.3132 | 1.7039 | 1600 | 0.3795 |
| 0.313 | 1.8104 | 1700 | 0.3667 |
| 0.2656 | 1.9169 | 1800 | 0.3534 |
| 0.2892 | 2.0234 | 1900 | 0.3488 |
| 0.2654 | 2.1299 | 2000 | 0.3452 |
| 0.3642 | 2.2364 | 2100 | 0.3376 |
| 0.3124 | 2.3429 | 2200 | 0.3365 |
| 0.3334 | 2.4494 | 2300 | 0.3319 |
| 0.1839 | 2.5559 | 2400 | 0.3290 |
| 0.2809 | 2.6624 | 2500 | 0.3259 |
| 0.3199 | 2.7689 | 2600 | 0.3237 |
| 0.3017 | 2.8754 | 2700 | 0.3213 |
| 0.3106 | 2.9819 | 2800 | 0.3210 |
Framework versions
- PEFT 0.11.1
- Transformers 4.41.2
- Pytorch 2.1.2+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1
- Library
- peft
- License
- mit
- Created
- Jun 14, 2024
- Updated
- Jun 14, 2024