Downloads · 30 days
10
6% of all-time downloads
UTI2_L3_50steps_1e6rate_03beta_CSFTDPO
tsavage68/UTI2_L3_50steps_1e6rate_03beta_CSFTDPO
UTI2_L3_50steps_1e6rate_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 llama3.
should probably proofread and complete it, then remove this comment. --
All-time downloads
171
Public
Parameters
8B
16.1 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors32.1 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- llama3
- Model type
- llama
- Access
- Public
- Created
- Jun 10, 2024
- Updated
- Jun 10, 2024
- SHA
- 4d12e2b6
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. -->
UTI2_M2_50steps_1e6rate_03beta_CSFTDPO
This model is a fine-tuned version of tsavage68/UTI_L3_1000steps_1e5rate_SFT on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0247
- Rewards/chosen: 1.6871
- Rewards/rejected: -4.8325
- Rewards/accuracies: 0.9900
- Rewards/margins: 6.5196
- Logps/rejected: -59.3778
- Logps/chosen: -23.6012
- Logits/rejected: -1.1583
- Logits/chosen: -1.1453
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-06
- 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: 50
Training results
| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.6012 | 0.3333 | 25 | 0.3684 | 0.4907 | -0.3471 | 0.9800 | 0.8378 | -44.4264 | -27.5892 | -1.1428 | -1.1369 |
| 0.0061 | 0.6667 | 50 | 0.0247 | 1.6871 | -4.8325 | 0.9900 | 6.5196 | -59.3778 | -23.6012 | -1.1583 | -1.1453 |
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
- llama
- License
- llama3
- Created
- Jun 10, 2024
- Updated
- Jun 10, 2024