metadata
library_name: transformers
license: apache-2.0
base_model: alignment-handbook/zephyr-7b-sft-full
tags:
- trl
- dpo
- generated_from_trainer
model-index:
- name: zephyr-7b-align-scan-0.0-0.3-linear-3
results: []
zephyr-7b-align-scan-0.0-0.3-linear-3
This model is a fine-tuned version of alignment-handbook/zephyr-7b-sft-full on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.8316
- Rewards/chosen: -3.2765
- Rewards/rejected: -4.2890
- Rewards/accuracies: 0.3413
- Rewards/margins: 1.0125
- Logps/rejected: -94.3157
- Logps/chosen: -84.5654
- Logits/rejected: -2.4456
- Logits/chosen: -2.4656
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: 8.165546278140361e-07
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- total_eval_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3
Training results
Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
---|---|---|---|---|---|---|---|---|---|---|---|
0.5554 | 1.0417 | 100 | 0.7309 | 0.3343 | -0.2184 | 0.3393 | 0.5527 | -81.8000 | -73.4634 | -2.4356 | -2.4525 |
0.3557 | 2.0833 | 200 | 0.8316 | -3.2765 | -4.2890 | 0.3413 | 1.0125 | -94.3157 | -84.5654 | -2.4456 | -2.4656 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.0
- Datasets 2.21.0
- Tokenizers 0.19.1