d5bfea8476
Model: jackf857/llama-3-8b-base-new-dpo-harmless-s_star0.4-q_t0.4 Source: Original Platform
library_name, base_model, tags, datasets, model-index
| library_name | base_model | tags | datasets | model-index | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| transformers | W-61/llama-3-8b-base-sft-hh-harmless-4xh200 |
|
|
|
llama3-8b-base-new-method-s_star0.4
This model is a fine-tuned version of W-61/llama-3-8b-base-sft-hh-harmless-4xh200 on the Anthropic/hh-rlhf dataset. It achieves the following results on the evaluation set:
- Loss: 0.6075
- Fcm Dpo/beta: 0.0032
- Margin Dpo/margin Mean: 80.9270
- Margin Dpo/margin Std: 168.3527
- Logps/chosen: -278.6199
- Logps/rejected: -364.2365
- Logps/ref Chosen: -74.8595
- Logps/ref Rejected: -79.5490
- Logits/chosen: 0.8914
- Logits/rejected: 0.8742
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: 5e-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: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss | Fcm Dpo/beta | Margin Dpo/margin Mean | Margin Dpo/margin Std | Logps/chosen | Logps/rejected | Logps/ref Chosen | Logps/ref Rejected | Logits/chosen | Logits/rejected |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 1.0917 | 0.3023 | 200 | 0.5616 | 0.0221 | 20.9587 | 36.0271 | -112.0402 | -137.6885 | -74.8595 | -79.5490 | 0.5290 | 0.4788 |
| 1.134 | 0.6047 | 400 | 0.5988 | 0.0047 | 61.8184 | 122.3443 | -231.1051 | -297.6130 | -74.8595 | -79.5490 | 0.7731 | 0.7383 |
| 1.242 | 0.9070 | 600 | 0.6075 | 0.0032 | 80.9270 | 168.3527 | -278.6199 | -364.2365 | -74.8595 | -79.5490 | 0.8914 | 0.8742 |
Framework versions
- Transformers 4.51.0
- Pytorch 2.3.1+cu121
- Datasets 2.21.0
- Tokenizers 0.21.4