DCAgent/e1_gpt_long_sandboxes_2x_tacc-Qwen3-8B
DCAgent/e1_gpt_long_sandboxes_2x_tacc-Qwen3-8B is an 8 billion parameter language model, fine-tuned from Qwen/Qwen3-8B. This model is specifically trained on the DCAgent/e1_gpt_long_d1_original_sandboxes_8x_glm47_traces dataset, indicating an optimization for tasks related to agentic behavior within sandbox environments. It leverages a 32768 token context length, making it suitable for processing extensive conversational or operational traces.
Loading preview...
Overview
This model, e1_gpt_long_sandboxes_8x_tacc-Qwen3-8B, is an 8 billion parameter language model derived from the Qwen3-8B architecture. It has been fine-tuned on a specialized dataset, DCAgent/e1_gpt_long_d1_original_sandboxes_8x_glm47_traces, suggesting a focus on agent-based interactions and long-context sandbox environments. The training process utilized a learning rate of 4e-05, a cosine learning rate scheduler with a 0.1 warmup ratio, and ran for 7 epochs.
Key Training Details
- Base Model: Qwen/Qwen3-8B
- Dataset: DCAgent/e1_gpt_long_d1_original_sandboxes_8x_glm47_traces
- Learning Rate: 4e-05
- Optimizer: AdamW_Torch_Fused
- Epochs: 7.0
- Context Length: 32768 tokens
Intended Use
Given its fine-tuning on a dataset related to 'sandboxes' and 'traces', this model is likely optimized for tasks involving the analysis, generation, or simulation of agent interactions within constrained or simulated environments. Its substantial context length further supports handling complex, multi-turn dialogues or extensive operational logs.