Delete logs/output_run_20260130_unhinge_northing.log

logs/output_run_20260130_unhinge_northing.log

@@ -1,34 +0,0 @@
-2026-01-30 17:59:37,859 - root - INFO - Run: run_20260130_unhinge_northing
-2026-01-30 17:59:37,859 - root - INFO - Log directory: /root/tiny_moe/training_runs/Tiny_MoE/logs
-2026-01-30 17:59:37,859 - root - INFO - Output dir: /root/tiny_moe/training_runs
-2026-01-30 17:59:37,890 - jax._src.xla_bridge - INFO - Unable to initialize backend 'tpu': INTERNAL: Failed to open libtpu.so: libtpu.so: cannot open shared object file: No such file or directory
-2026-01-30 17:59:37,890 - jax._src.xla_bridge - WARNING - An NVIDIA GPU may be present on this machine, but a CUDA-enabled jaxlib is not installed. Falling back to cpu.
-2026-01-30 17:59:40,951 - root - INFO - Flax version: 0.11.1
-2026-01-30 17:59:40,952 - root - INFO - Optax version: 0.2.6
-2026-01-30 17:59:40,952 - root - INFO - Platform: cpu
-2026-01-30 17:59:40,952 - root - INFO - Num Devices: 1
-2026-01-30 17:59:40,952 - root - INFO - Devices: [CpuDevice(id=0)]
-2026-01-30 17:59:41,022 - root - INFO - Model config:
-Config(name='Tiny_MoE',
-       dtype=<class 'jax.numpy.bfloat16'>,
-       vocab_size=50304,
-       block_size=2048,
-       n_layer=30,
-       n_embed=672,
-       n_glu_hidden=2048,
-       n_head=12,
-       n_kv_head=4,
-       n_experts=8,
-       init_stddev=0.02,
-       expert_load_factor=1.25,
-       aux_loss_coeff=0.01,
-       moe_bias=False,
-       mlp_bias=False,
-       attention_bias=False,
-       load_balance_loss_coeff=0.01,
-       z_loss_coeff=0.0005,
-       expert_top_k=2,
-       ln_epsilon=1e-05,
-       rope_theta=0.0001,
-       expert_partition_spec=PartitionSpec('devices',),
-       sdpa_implementation='xla')