Downloads · 30 days
9
24% of all-time downloads
UTI_M2_300steps_1e8rate_03beta_CSFTDPO
tsavage68/UTI_M2_300steps_1e8rate_03beta_CSFTDPO
UTI_M2_300steps_1e8rate_03beta_CSFTDPO 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
38
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
- Jun 4, 2024
- Updated
- Jun 4, 2024
- SHA
- c37cf579
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. -->
UTI_M2_300steps_1e8rate_03beta_CSFTDPO
This model is a fine-tuned version of tsavage68/UTI_M2_1000steps_1e5rate_SFT on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6896
- Rewards/chosen: 0.0028
- Rewards/rejected: -0.0045
- Rewards/accuracies: 0.6000
- Rewards/margins: 0.0073
- Logps/rejected: -44.1810
- Logps/chosen: -20.2852
- Logits/rejected: -3.8168
- Logits/chosen: -3.7448
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-08
- 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: 300
Training results
| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.6936 | 0.3333 | 25 | 0.6942 | 0.0013 | 0.0032 | 0.4000 | -0.0020 | -44.1553 | -20.2903 | -3.8168 | -3.7448 |
| 0.6921 | 0.6667 | 50 | 0.6936 | 0.0023 | 0.0030 | 0.5 | -0.0007 | -44.1562 | -20.2868 | -3.8168 | -3.7448 |
| 0.6943 | 1.0 | 75 | 0.6955 | 0.0005 | 0.0049 | 0.4200 | -0.0044 | -44.1498 | -20.2931 | -3.8169 | -3.7449 |
| 0.6933 | 1.3333 | 100 | 0.6933 | 0.0014 | 0.0014 | 0.4200 | -0.0001 | -44.1614 | -20.2900 | -3.8168 | -3.7448 |
| 0.6916 | 1.6667 | 125 | 0.6933 | 0.0008 | 0.0009 | 0.4300 | -0.0001 | -44.1631 | -20.2920 | -3.8169 | -3.7449 |
| 0.6888 | 2.0 | 150 | 0.6896 | 0.0020 | -0.0052 | 0.5500 | 0.0072 | -44.1835 | -20.2878 | -3.8168 | -3.7448 |
| 0.6905 | 2.3333 | 175 | 0.6868 | 0.0029 | -0.0101 | 0.6200 | 0.0130 | -44.1999 | -20.2849 | -3.8167 | -3.7447 |
| 0.6877 | 2.6667 | 200 | 0.6890 | 0.0023 | -0.0061 | 0.5600 | 0.0084 | -44.1865 | -20.2869 | -3.8168 | -3.7448 |
| 0.6881 | 3.0 | 225 | 0.6883 | 0.0034 | -0.0064 | 0.6000 | 0.0098 | -44.1874 | -20.2831 | -3.8169 | -3.7448 |
| 0.6886 | 3.3333 | 250 | 0.6899 | 0.0030 | -0.0037 | 0.5900 | 0.0067 | -44.1786 | -20.2846 | -3.8168 | -3.7448 |
| 0.6887 | 3.6667 | 275 | 0.6896 | 0.0028 | -0.0045 | 0.6000 | 0.0073 | -44.1810 | -20.2852 | -3.8168 | -3.7448 |
| 0.685 | 4.0 | 300 | 0.6896 | 0.0028 | -0.0045 | 0.6000 | 0.0073 | -44.1810 | -20.2852 | -3.8168 | -3.7448 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.0.0+cu117
- Datasets 2.19.2
- Tokenizers 0.19.1
- Task
- Text Generation
- Library
- transformers
- Type
- mistral
- License
- apache-2.0
- Created
- Jun 4, 2024
- Updated
- Jun 4, 2024