Interview_L3_1000rate_1e5_SFT_SFT
This model is a fine-tuned version of meta-llama/Meta-Llama-3-8B-Instruct on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0253
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: 1e-05
- train_batch_size: 2
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 100
- training_steps: 1000
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
1.3904 | 0.0376 | 50 | 1.2452 |
1.1582 | 0.0752 | 100 | 0.9397 |
0.9079 | 0.1129 | 150 | 0.6367 |
0.3786 | 0.1505 | 200 | 0.4351 |
0.258 | 0.1881 | 250 | 0.3067 |
0.2163 | 0.2257 | 300 | 0.2114 |
0.1031 | 0.2634 | 350 | 0.1570 |
0.0911 | 0.3010 | 400 | 0.1205 |
0.0739 | 0.3386 | 450 | 0.0901 |
0.0503 | 0.3762 | 500 | 0.0713 |
0.0713 | 0.4138 | 550 | 0.0598 |
0.066 | 0.4515 | 600 | 0.0457 |
0.0181 | 0.4891 | 650 | 0.0403 |
0.015 | 0.5267 | 700 | 0.0358 |
0.0172 | 0.5643 | 750 | 0.0301 |
0.0314 | 0.6020 | 800 | 0.0267 |
0.0279 | 0.6396 | 850 | 0.0259 |
0.0133 | 0.6772 | 900 | 0.0254 |
0.0122 | 0.7148 | 950 | 0.0253 |
0.0126 | 0.7524 | 1000 | 0.0253 |
Framework versions
- Transformers 4.40.2
- Pytorch 2.0.0+cu117
- Datasets 2.19.1
- Tokenizers 0.19.1
- Downloads last month
- 1
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.