UTI2_L3_175steps_1e7rate_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: 0.4424
- Rewards/chosen: 0.3849
- Rewards/rejected: -0.3042
- Rewards/accuracies: 0.6500
- Rewards/margins: 0.6891
- Logps/rejected: -29.4987
- Logps/chosen: -17.8203
- Logits/rejected: -1.1540
- Logits/chosen: -1.1495
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-07
- 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: 175
Training results
Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
---|---|---|---|---|---|---|---|---|---|---|---|
0.6944 | 0.3333 | 25 | 0.6884 | 0.0045 | -0.0054 | 0.3900 | 0.0099 | -28.5027 | -19.0882 | -1.1523 | -1.1488 |
0.6816 | 0.6667 | 50 | 0.6751 | 0.0295 | -0.0076 | 0.5600 | 0.0370 | -28.5099 | -19.0051 | -1.1524 | -1.1488 |
0.6338 | 1.0 | 75 | 0.6279 | 0.0961 | -0.0432 | 0.6300 | 0.1392 | -28.6285 | -18.7831 | -1.1525 | -1.1488 |
0.5045 | 1.3333 | 100 | 0.5423 | 0.2255 | -0.1296 | 0.6400 | 0.3551 | -28.9166 | -18.3516 | -1.1531 | -1.1490 |
0.4193 | 1.6667 | 125 | 0.4625 | 0.3477 | -0.2619 | 0.6500 | 0.6095 | -29.3576 | -17.9444 | -1.1536 | -1.1492 |
0.4777 | 2.0 | 150 | 0.4434 | 0.3849 | -0.3013 | 0.6500 | 0.6862 | -29.4891 | -17.8203 | -1.1539 | -1.1494 |
0.4132 | 2.3333 | 175 | 0.4424 | 0.3849 | -0.3042 | 0.6500 | 0.6891 | -29.4987 | -17.8203 | -1.1540 | -1.1495 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.0.0+cu117
- Datasets 2.19.2
- Tokenizers 0.19.1
- Downloads last month
- 3
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.