Downloads · 30 days
15
31% of all-time downloads
mistral-7b-approx_ndcg
yangzhao02/mistral-7b-approx_ndcg
mistral-7b-approx_ndcg is a machine learning model from yangzhao02. 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 apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
49
Public
Parameters
7.2B
14.5 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors14.5 GB · 100%
At a glance
- License
- apache-2.0
- Model type
- mistral
- Access
- Public
- Created
- Aug 6, 2024
- Updated
- Aug 7, 2024
- SHA
- f5c789c4
Base models
Datasets
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. -->
mistral-7b-base-approx_ndcg_1-listsize_8-alpha_25.0-batchsize_128
This model is a fine-tuned version of alignment-handbook/zephyr-7b-sft-full on the yangzhao02/ListUltraFeedback dataset. It achieves the following results on the evaluation set:
- Loss: -0.9811
- Logps: -290.9563
- Logits: -2.9474
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-07
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- num_devices: 16
- gradient_accumulation_steps: 8
- total_train_batch_size: 128
- total_eval_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 1
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Logps | Logits |
|---|---|---|---|---|---|
| -0.9788 | 0.4275 | 200 | -0.9776 | -289.3082 | -3.0493 |
| -0.9812 | 0.8549 | 400 | -0.9810 | -291.1517 | -2.9495 |
Framework versions
- Transformers 4.42.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
- Type
- mistral
- License
- apache-2.0
- Created
- Aug 6, 2024
- Updated
- Aug 7, 2024