DCAgent/a1-curriculum_medium
DCAgent/a1-curriculum_medium is an 8 billion parameter language model fine-tuned from Qwen/Qwen3-8B. This model was trained on a specific dataset, /e/scratch/jureap59/raoof1/sft_data/hf_hub/datasets--DCAgent--exp_rpt_curriculum-medium_10k_glm_4.7_traces_jupiter/snapshots/fdf78173c8d3508962f19b140386e4f3836ffc5b_thinking_preprocessed, suggesting a specialization in areas related to its training data. With a 32768 token context length, it is suitable for tasks requiring extensive contextual understanding.
Loading preview...
Overview
DCAgent/a1-curriculum_medium is an 8 billion parameter language model, fine-tuned from the base Qwen/Qwen3-8B architecture. It was trained using a specific dataset, exp_rpt_curriculum-medium_10k_glm_4.7_traces_jupiter, indicating a potential specialization in areas covered by this data.
Key Training Details
The model underwent 7 epochs of training with a learning rate of 4e-05. It utilized a distributed training setup across 16 devices, with a total training batch size of 16. The optimizer used was ADAMW_TORCH_FUSED with specific beta and epsilon parameters, and a cosine learning rate scheduler with a 0.1 warmup ratio.
Intended Use & Limitations
As per the provided information, more details are needed regarding the model's specific intended uses and known limitations. Users should refer to future updates for comprehensive guidance on its optimal application and any constraints.
Framework Versions
Training was conducted using:
- Transformers 4.57.6
- Pytorch 2.9.1+cu130
- Datasets 4.7.0
- Tokenizers 0.22.2