13 lines
235 B
Plaintext
13 lines
235 B
Plaintext
name: think_baseline
|
|
base_model: Qwen3-4B-Base
|
|
method: full SFT (ZeRO-3)
|
|
dataset: think_all
|
|
template: qwen3
|
|
epochs: 2
|
|
seed: 42
|
|
cutoff_len: 24576
|
|
learning_rate: 2e-5
|
|
train_loss: 0.6698
|
|
train_steps: 838
|
|
finished_at: 2026-06-08 00:22 CST
|