Downloads · 30 days
10
22% of all-time downloads
Mistral2_400_STEPS_01beta_5e7rate_CDPOSFT
tsavage68/Mistral2_400_STEPS_01beta_5e7rate_CDPOSFT
Mistral2_400_STEPS_01beta_5e7rate_CDPOSFT is a text generation model from tsavage68. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
45
Public
Parameters
7.2B
14.5 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors29 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- apache-2.0
- Model type
- mistral
- Access
- Public
- Created
- May 6, 2024
- Updated
- May 6, 2024
- SHA
- c179b002
Try a prompt
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. -->
Mistral2_400_STEPS_01beta_5e7rate_CDPOSFT
This model is a fine-tuned version of tsavage68/mistralit2_1000_STEPS_5e7_SFT on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5596
- Rewards/chosen: -1.0432
- Rewards/rejected: -2.1060
- Rewards/accuracies: 0.6725
- Rewards/margins: 1.0628
- Logps/rejected: -47.6172
- Logps/chosen: -34.1036
- Logits/rejected: -1.9972
- Logits/chosen: -1.9972
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: 4
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 100
- training_steps: 400
Training results
| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.6269 | 0.0977 | 50 | 0.6140 | -0.3343 | -0.5430 | 0.6374 | 0.2087 | -31.9869 | -27.0148 | -2.2268 | -2.2264 |
| 0.5268 | 0.1953 | 100 | 0.5976 | -0.2761 | -1.1386 | 0.6286 | 0.8625 | -37.9425 | -26.4326 | -1.9212 | -1.9210 |
| 0.5374 | 0.2930 | 150 | 0.6040 | -1.7328 | -2.6503 | 0.6505 | 0.9176 | -53.0600 | -40.9992 | -1.9116 | -1.9117 |
| 0.4624 | 0.3906 | 200 | 0.5909 | -1.3926 | -2.2230 | 0.6527 | 0.8304 | -48.7870 | -37.5976 | -1.9300 | -1.9300 |
| 0.5512 | 0.4883 | 250 | 0.5701 | -0.8563 | -1.6501 | 0.6418 | 0.7938 | -43.0575 | -32.2344 | -2.0325 | -2.0325 |
| 0.4166 | 0.5859 | 300 | 0.5635 | -1.0951 | -2.1516 | 0.6813 | 1.0565 | -48.0729 | -34.6226 | -2.0058 | -2.0058 |
| 0.4196 | 0.6836 | 350 | 0.5588 | -1.0425 | -2.1063 | 0.6725 | 1.0638 | -47.6203 | -34.0969 | -1.9972 | -1.9972 |
| 0.4759 | 0.7812 | 400 | 0.5596 | -1.0432 | -2.1060 | 0.6725 | 1.0628 | -47.6172 | -34.1036 | -1.9972 | -1.9972 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.0.0+cu117
- Datasets 2.19.0
- Tokenizers 0.19.1
- Task
- Text Generation
- Library
- transformers
- Type
- mistral
- License
- apache-2.0
- Created
- May 6, 2024
- Updated
- May 6, 2024