58f6ef2daa
Model: cjiao/OpenThoughts3-greedy-groups-top-openthinker3-1.5B-checkpoint-375-80 Source: Original Platform
library_name, base_model, tags, model-index
| library_name | base_model | tags | model-index | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| transformers | cjiao/OpenThinker3-1.5B-checkpoint-375 |
|
|
OpenThoughts3-greedy-groups-top-openthinker3-1.5B-checkpoint-375-80
This model is a fine-tuned version of cjiao/OpenThinker3-1.5B-checkpoint-375 on the cjiao/OpenThoughts3-greedy-groups-top-openthinker3-1.5B-checkpoint-375-80 dataset.
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: 0.00016
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 2
- gradient_accumulation_steps: 16
- total_train_batch_size: 256
- total_eval_batch_size: 16
- 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
- num_epochs: 2
Training results
Framework versions
- Transformers 4.46.1
- Pytorch 2.5.1+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3