metadata
library_name: transformers
license: llama3.1
base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
tags:
- alignment-handbook
- trl
- sft
- generated_from_trainer
- trl
- sft
- generated_from_trainer
datasets:
- barc0/induction_heavy_100k_jsonl
- barc0/induction_heavy_suggestfunction_100k_jsonl
- >-
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
model-index:
- name: l3.1-8b-inst-fft-induction-barc-heavy-200k-old-200k-lr1e-5-ep3
results: []
l3.1-8b-inst-fft-induction-barc-heavy-200k-old-200k-lr1e-5-ep3
This model is a fine-tuned version of meta-llama/Meta-Llama-3.1-8B-Instruct on the barc0/induction_heavy_100k_jsonl, the barc0/induction_heavy_suggestfunction_100k_jsonl, the barc0/induction_100k-gpt4-description-gpt4omini-code_generated_problems_messages_format_0.3 and the barc0/induction_100k_gpt4o-mini_generated_problems_seed100.jsonl_messages_format_0.3 datasets. It achieves the following results on the evaluation set:
- Loss: 0.3711
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-05
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 2
- total_train_batch_size: 128
- total_eval_batch_size: 32
- optimizer: Use 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: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.4395 | 1.0 | 2995 | 0.4231 |
| 0.3529 | 2.0 | 5990 | 0.3733 |
| 0.2858 | 3.0 | 8985 | 0.3711 |
Framework versions
- Transformers 4.46.2
- Pytorch 2.4.0+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3