DCAgent/e1_embedding_d1_original_sandboxes
DCAgent/e1_embedding_d1_original_sandboxes is an 8 billion parameter language model fine-tuned from Qwen/Qwen3-8B. This model was specifically trained on the /e/scratch/jureap59/raoof1/sft_data/hf_hub/datasets--DCAgent--e1_embedding_d1_original_sandboxes_glm_4.7_traces_jupiter/snapshots/8ff58cddcf0037fdb4a8582b9b828aec3265545a_thinking_preprocessed dataset. It is designed for tasks related to its specific fine-tuning data, offering specialized performance within that domain.
Loading preview...
Overview
DCAgent/e1_embedding_d1_original_sandboxes is an 8 billion parameter language model, derived from the Qwen3-8B architecture. It has undergone specific fine-tuning on a unique dataset, /e/scratch/jureap59/raoof1/sft_data/hf_hub/datasets--DCAgent--e1_embedding_d1_original_sandboxes_glm_4.7_traces_jupiter/snapshots/8ff58cddcf0037fdb4a8582b9b828aec3265545a_thinking_preprocessed, indicating a specialization for tasks related to the nature of this training data.
Training Details
The model was trained with a learning rate of 4e-05 over 7 epochs, utilizing a multi-GPU setup with 16 devices and a total batch size of 16. The optimizer used was ADAMW_TORCH_FUSED with specific beta and epsilon values, and a cosine learning rate scheduler with a 0.1 warmup ratio. This fine-tuning process aims to adapt the base Qwen3-8B model to perform optimally on the specific data it was trained on.
Intended Use
Given its fine-tuning on a specialized dataset, this model is best suited for applications that align with the characteristics and content of the /e/scratch/jureap59/raoof1/sft_data/hf_hub/datasets--DCAgent--e1_embedding_d1_original_sandboxes_glm_4.7_traces_jupiter/snapshots/8ff58cddcf0037fdb4a8582b9b828aec3265545a_thinking_preprocessed dataset. Developers should consider its specific training context when evaluating its suitability for their particular use cases.