Downloads · 30 days
0
llama-7b-absa-MT-laptops
Shakhovak/llama-7b-absa-MT-laptops
llama-7b-absa-MT-laptops 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 22, 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 21, 2024
- Updated
- Apr 22, 2024
- SHA
- 263401dc
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-laptops
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: 0.0032
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 |
|---|---|---|---|
| 0.0853 | 0.13 | 40 | 0.0270 |
| 0.0209 | 0.25 | 80 | 0.0205 |
| 0.017 | 0.38 | 120 | 0.0178 |
| 0.016 | 0.51 | 160 | 0.0157 |
| 0.0129 | 0.63 | 200 | 0.0140 |
| 0.0129 | 0.76 | 240 | 0.0118 |
| 0.0108 | 0.89 | 280 | 0.0115 |
| 0.009 | 1.01 | 320 | 0.0107 |
| 0.0052 | 1.14 | 360 | 0.0087 |
| 0.0054 | 1.26 | 400 | 0.0074 |
| 0.0046 | 1.39 | 440 | 0.0087 |
| 0.005 | 1.52 | 480 | 0.0074 |
| 0.0043 | 1.64 | 520 | 0.0061 |
| 0.0035 | 1.77 | 560 | 0.0056 |
| 0.003 | 1.9 | 600 | 0.0053 |
| 0.0026 | 2.02 | 640 | 0.0049 |
| 0.0021 | 2.15 | 680 | 0.0052 |
| 0.0027 | 2.28 | 720 | 0.0047 |
| 0.0015 | 2.4 | 760 | 0.0044 |
| 0.0013 | 2.53 | 800 | 0.0043 |
| 0.0009 | 2.66 | 840 | 0.0042 |
| 0.001 | 2.78 | 880 | 0.0039 |
| 0.0008 | 2.91 | 920 | 0.0036 |
| 0.0005 | 3.04 | 960 | 0.0036 |
| 0.0006 | 3.16 | 1000 | 0.0039 |
| 0.0005 | 3.29 | 1040 | 0.0033 |
| 0.0002 | 3.42 | 1080 | 0.0032 |
| 0.0002 | 3.54 | 1120 | 0.0033 |
| 0.0002 | 3.67 | 1160 | 0.0031 |
| 0.0002 | 3.79 | 1200 | 0.0032 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- License
- other
- Created
- Apr 21, 2024
- Updated
- Apr 22, 2024