|
--- |
|
base_model: meta-llama/Meta-Llama-3.1-8B-Instruct |
|
datasets: |
|
- barc0/induction_100k-gpt4-description-gpt4omini-code_generated_problems_messages_format_0.3 |
|
- barc0/induction_100k_gpt4o-mini_generated_problems_seed100.jsonl_messages_format_0.3 |
|
- barc0/induction_gpt-4_description_20000_with_llama_codegen_messages_format_0.3 |
|
- barc0/induction_gpt-4_description_20000_with_gpt-4o-mini_codegen_messages_format_0.3 |
|
library_name: peft |
|
license: llama3.1 |
|
tags: |
|
- alignment-handbook |
|
- trl |
|
- sft |
|
- generated_from_trainer |
|
model-index: |
|
- name: l3.1-8b-inst-lora64-induction-gpt4wmini100k-mini100k-gpt4wmini20k-gpt4wllama20k-lr2e-4-ep3 |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# l3.1-8b-inst-lora64-induction-gpt4wmini100k-mini100k-gpt4wmini20k-gpt4wllama20k-lr2e-4-ep3 |
|
|
|
This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct) on the barc0/induction_100k-gpt4-description-gpt4omini-code_generated_problems_messages_format_0.3, the barc0/induction_100k_gpt4o-mini_generated_problems_seed100.jsonl_messages_format_0.3, the barc0/induction_gpt-4_description_20000_with_llama_codegen_messages_format_0.3 and the barc0/induction_gpt-4_description_20000_with_gpt-4o-mini_codegen_messages_format_0.3 datasets. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.2684 |
|
|
|
## 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: 0.0002 |
|
- train_batch_size: 8 |
|
- eval_batch_size: 4 |
|
- seed: 42 |
|
- distributed_type: multi-GPU |
|
- num_devices: 8 |
|
- gradient_accumulation_steps: 2 |
|
- 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: 3 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 0.2882 | 1.0 | 1784 | 0.2852 | |
|
| 0.257 | 2.0 | 3568 | 0.2705 | |
|
| 0.2329 | 3.0 | 5352 | 0.2684 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.13.0 |
|
- Transformers 4.45.0.dev0 |
|
- Pytorch 2.4.1+cu121 |
|
- Datasets 3.0.0 |
|
- Tokenizers 0.19.1 |
