Downloads · 30 days
0
llama-7b-absa-MT-restaurants
Shakhovak/llama-7b-absa-MT-restaurants
llama-7b-absa-MT-restaurants is a machine learning model from Shakhovak. 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 Apr 23, 2024
Repo size
1.9 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin269 MB · 99%
At a glance
- License
- other
- Access
- Public
- Created
- Apr 19, 2024
- Updated
- Apr 23, 2024
- SHA
- 24ff8616
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. -->
llama-7b-absa-MT-restaurants
This model is a fine-tuned version of baffo32/decapoda-research-llama-7B-hf on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0019
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 2
- training_steps: 1200
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.0917 | 0.13 | 40 | 0.0298 |
| 0.0249 | 0.25 | 80 | 0.0229 |
| 0.0216 | 0.38 | 120 | 0.0205 |
| 0.0215 | 0.51 | 160 | 0.0186 |
| 0.0181 | 0.63 | 200 | 0.0160 |
| 0.0148 | 0.76 | 240 | 0.0140 |
| 0.0141 | 0.89 | 280 | 0.0131 |
| 0.0121 | 1.01 | 320 | 0.0120 |
| 0.0077 | 1.14 | 360 | 0.0109 |
| 0.0074 | 1.27 | 400 | 0.0101 |
| 0.0062 | 1.39 | 440 | 0.0102 |
| 0.0076 | 1.52 | 480 | 0.0093 |
| 0.0072 | 1.65 | 520 | 0.0084 |
| 0.005 | 1.77 | 560 | 0.0066 |
| 0.0052 | 1.9 | 600 | 0.0054 |
| 0.0033 | 2.03 | 640 | 0.0053 |
| 0.0023 | 2.15 | 680 | 0.0056 |
| 0.002 | 2.28 | 720 | 0.0046 |
| 0.0021 | 2.41 | 760 | 0.0048 |
| 0.0019 | 2.53 | 800 | 0.0039 |
| 0.0014 | 2.66 | 840 | 0.0034 |
| 0.0013 | 2.78 | 880 | 0.0033 |
| 0.0012 | 2.91 | 920 | 0.0030 |
| 0.001 | 3.04 | 960 | 0.0026 |
| 0.0004 | 3.16 | 1000 | 0.0025 |
| 0.0004 | 3.29 | 1040 | 0.0022 |
| 0.0002 | 3.42 | 1080 | 0.0021 |
| 0.0003 | 3.54 | 1120 | 0.0021 |
| 0.0002 | 3.67 | 1160 | 0.0019 |
| 0.0003 | 3.8 | 1200 | 0.0019 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- License
- other
- Created
- Apr 19, 2024
- Updated
- Apr 23, 2024