metadata
base_model: HuggingFaceH4/starcoder2-15b-ift
tags:
- alignment-handbook
- generated_from_trainer
datasets:
- HuggingFaceH4/ultrafeedback_binarized
- HuggingFaceH4/orca_dpo_pairs
model-index:
- name: starcoder2-15b-dpo-v4.0
results: []
starcoder2-15b-dpo-v4.0
This model is a fine-tuned version of HuggingFaceH4/starcoder2-15b-ift on the HuggingFaceH4/ultrafeedback_binarized and the HuggingFaceH4/orca_dpo_pairs datasets. It achieves the following results on the evaluation set:
- Loss: 0.4347
- Rewards/chosen: -0.9461
- Rewards/rejected: -2.7745
- Rewards/accuracies: 0.7658
- Rewards/margins: 1.8284
- Logps/rejected: -322.1934
- Logps/chosen: -316.1898
- Logits/rejected: -2.3817
- Logits/chosen: -2.3005
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: 2
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 8
- total_train_batch_size: 128
- total_eval_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 2
Training results
| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.717 | 0.17 | 100 | 0.6006 | -0.0924 | -0.2899 | 0.6329 | 0.1975 | -272.5022 | -299.1165 | -2.5313 | -2.4191 |
| 0.6273 | 0.35 | 200 | 0.5160 | -0.3994 | -0.9461 | 0.6930 | 0.5467 | -285.6261 | -305.2568 | -2.5281 | -2.4278 |
| 0.5538 | 0.52 | 300 | 0.4781 | -0.6589 | -1.5892 | 0.7247 | 0.9302 | -298.4870 | -310.4470 | -2.4996 | -2.4110 |
| 0.5056 | 0.7 | 400 | 0.4594 | -0.8283 | -2.1332 | 0.7437 | 1.3050 | -309.3687 | -313.8344 | -2.4472 | -2.3644 |
| 0.4983 | 0.87 | 500 | 0.4512 | -0.7758 | -2.2806 | 0.7468 | 1.5049 | -312.3167 | -312.7843 | -2.4223 | -2.3404 |
| 0.4662 | 1.04 | 600 | 0.4431 | -0.7839 | -2.4016 | 0.7658 | 1.6177 | -314.7355 | -312.9465 | -2.4049 | -2.3215 |
| 0.4411 | 1.22 | 700 | 0.4415 | -1.0090 | -2.7582 | 0.7690 | 1.7492 | -321.8679 | -317.4481 | -2.3840 | -2.3016 |
| 0.471 | 1.39 | 800 | 0.4368 | -0.9617 | -2.7445 | 0.7690 | 1.7828 | -321.5930 | -316.5019 | -2.3809 | -2.2991 |
| 0.4485 | 1.57 | 900 | 0.4351 | -0.9490 | -2.7594 | 0.7722 | 1.8103 | -321.8916 | -316.2497 | -2.3815 | -2.3004 |
| 0.4411 | 1.74 | 1000 | 0.4348 | -0.9293 | -2.7469 | 0.7658 | 1.8176 | -321.6409 | -315.8547 | -2.3823 | -2.3011 |
| 0.4499 | 1.92 | 1100 | 0.4348 | -0.9482 | -2.7767 | 0.7658 | 1.8285 | -322.2369 | -316.2320 | -2.3828 | -2.3012 |
Framework versions
- Transformers 4.39.0.dev0
- Pytorch 2.1.2+cu121
- Datasets 2.16.1
- Tokenizers 0.15.1