gpt-neo-1.3B-emailgen
This model is a fine-tuned version of EleutherAI/gpt-neo-1.3B on the postbot/multi-emails-100k dataset. It achieves the following results on the evaluation set:
- Loss: 1.6930
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: 0.0001
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- gradient_accumulation_steps: 32
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.02
- num_epochs: 2
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
1.8669 | 1.0 | 789 | 1.7866 |
1.4049 | 2.0 | 1578 | 1.6930 |
Framework versions
- Transformers 4.22.2
- Pytorch 1.10.0+cu113
- Tokenizers 0.12.1
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
Metric | Value |
---|---|
Avg. | 33.47 |
AI2 Reasoning Challenge (25-Shot) | 29.95 |
HellaSwag (10-Shot) | 47.95 |
MMLU (5-Shot) | 24.11 |
TruthfulQA (0-shot) | 42.55 |
Winogrande (5-shot) | 56.27 |
GSM8k (5-shot) | 0.00 |
- Downloads last month
- 54
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
Model tree for postbot/gpt-neo-1.3B-emailgen
Base model
EleutherAI/gpt-neo-1.3BDataset used to train postbot/gpt-neo-1.3B-emailgen
Evaluation results
- normalized accuracy on AI2 Reasoning Challenge (25-Shot)test set Open LLM Leaderboard29.950
- normalized accuracy on HellaSwag (10-Shot)validation set Open LLM Leaderboard47.950
- accuracy on MMLU (5-Shot)test set Open LLM Leaderboard24.110
- mc2 on TruthfulQA (0-shot)validation set Open LLM Leaderboard42.550
- accuracy on Winogrande (5-shot)validation set Open LLM Leaderboard56.270
- accuracy on GSM8k (5-shot)test set Open LLM Leaderboard0.000