predict2
This model is a fine-tuned version of internlm/internlm2_5-1_8b-chat on the openai dataset. It achieves the following results on the evaluation set:
- Loss: 0.2998
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: 4
- eval_batch_size: 2
- seed: 42
- distributed_type: multi-GPU
- gradient_accumulation_steps: 8
- total_train_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: 3.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.3022 | 0.6173 | 100 | 0.2812 |
| 0.2176 | 1.2346 | 200 | 0.2822 |
| 0.2157 | 1.8519 | 300 | 0.2725 |
| 0.126 | 2.4691 | 400 | 0.3032 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.0
- Datasets 2.21.0
- Tokenizers 0.19.1
- Downloads last month
- 4
Inference API (serverless) does not yet support model repos that contain custom code.
Model tree for anthonymeo/full-train-openai
Base model
internlm/internlm2_5-1_8b-chat