ds_chat_sppo_hard_new_iter0_2024-09-18-16.33
This model is a fine-tuned version of deepseek-ai/deepseek-llm-7b-chat on the self-generate/topp09_temp07_ds_chat_original_cn_mining_oj_iter0-binarized and the self-generate/topp09_temp07_ds_chat_original_cn_rl_oj_iter0-binarized datasets. It achieves the following results on the evaluation set:
- Loss: 0.4085
- Rewards/chosen: 0.0627
- Rewards/rejected: -0.1540
- Rewards/accuracies: 0.8269
- Rewards/margins: 0.2168
- Logps/rejected: -172.5034
- Logps/chosen: -143.7851
- Logits/rejected: 0.5654
- Logits/chosen: 0.5790
- Debug/policy Chosen Logits: 0.5790
- Debug/policy Rejected Logits: 0.5654
- Debug/policy Chosen Logps: -143.7851
- Debug/policy Rejected Logps: -172.5034
- Debug/reference Chosen Logps: -150.0583
- Debug/reference Rejected Logps: -157.1004
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: 8
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- 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: constant
- lr_scheduler_warmup_ratio: 0.1
- lr_scheduler_warmup_steps: 100
- num_epochs: 1.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen | Debug/policy Chosen Logits | Debug/policy Rejected Logits | Debug/policy Chosen Logps | Debug/policy Rejected Logps | Debug/reference Chosen Logps | Debug/reference Rejected Logps |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.4215 | 0.7042 | 100 | 0.4085 | 0.0627 | -0.1540 | 0.8269 | 0.2168 | -172.5034 | -143.7851 | 0.5654 | 0.5790 | 0.5790 | 0.5654 | -143.7851 | -172.5034 | -150.0583 | -157.1004 |
Framework versions
- Transformers 4.42.0
- Pytorch 2.3.0+cu121
- Datasets 2.14.6
- Tokenizers 0.19.1
- Downloads last month
- 49