Unable to parse backend config error

[idmjky]

Hi, thank you for this great repo! I encountered an error during the trajectory generation stage. Do you have any idea how to solve this?
Starting trajectory: PDL1_l80_s175484
Stage 1: Test Logits
2024-12-15 22:49:06.705978: W external/xla/xla/service/gpu/ir_emitter_unnested.cc:1171] Unable to parse backend config for custom call: Could not convert JSON string to proto: Expected : between key:value pair.
= true, full_matrice
^
Fall back to parse the raw backend config str.
2024-12-15 22:52:07.183021: W external/xla/xla/service/gpu/ir_emitter_unnested.cc:1171] Unable to parse backend config for custom call: Could not convert JSON string to proto: Expected : between key:value pair.
= true, full_matrice
^
Fall back to parse the raw backend config str.
2024-12-15 22:53:44.051753: E external/xla/xla/service/slow_operation_alarm.cc:73]

---

[Compiling module jit__model] Very slow compile? If you want to file a bug, run with envvar XLA_FLAGS=--xla_dump_to=/tmp/foo and attach the results.

---

Killed

[martinpacesa]

What is your JAX version?

Also can you paste your target input json

[idmjky]

I figured out the problem. I think the JAX 0.4.37 is installed to accomodate CUDA12.4. The script is running properly even though everytime this error comes up. Do you know if this hurts the final designed binder results in anyway?

2024-12-15 23:24:12.929214: W external/xla/xla/service/gpu/ir_emitter_unnested.cc:1171] Unable to parse backend config for custom call: Could not convert JSON string to proto: Expected : between key:value pair.
= true, full_matrice
^
Fall back to parse the raw backend config str.
2024-12-15 23:26:24.944705: W external/xla/xla/service/gpu/ir_emitter_unnested.cc:1171] Unable to parse backend config for custom call: Could not convert JSON string to proto: Expected : between key:value pair.
= true, full_matrice
^
Fall back to parse the raw backend config str.
1 models [4] recycles 1 hard 0 soft 0.02 temp 1 loss 9.66 helix 1.41 pae 0.80 i_pae 0.77 con 4.76 i_con 4.08 plddt 0.29 ptm 0.53 i_ptm 0.10 rg 2.42
2 models [0] recycles 1 hard 0 soft 0.04 temp 1 loss 10.57 helix 1.29 pae 0.79 i_pae 0.80 con 4.55 i_con 3.99 plddt 0.33 ptm 0.53 i_ptm 0.11 rg 6.36
3 models [4] recycles 1 hard 0 soft 0.05 temp 1 loss 8.61 helix 1.18 pae 0.70 i_pae 0.65 con 4.26 i_con 3.59 plddt 0.35 ptm 0.55 i_ptm 0.17 rg 2.19
4 models [3] recycles 1 hard 0 soft 0.07 temp 1 loss 7.89 helix 0.73 pae 0.61 i_pae 0.64 con 3.73 i_con 3.94 plddt 0.45 ptm 0.55 i_ptm 0.16 rg 0.13
5 models [2] recycles 1 hard 0 soft 0.09 temp 1 loss 7.69 helix 0.74 pae 0.62 i_pae 0.61 con 3.75 i_con 3.78 plddt 0.45 ptm 0.55 i_ptm 0.17 rg -0.06
6 models [2] recycles 1 hard 0 soft 0.11 temp 1 loss 7.21 helix 0.72 pae 0.54 i_pae 0.54 con 3.58 i_con 3.44 plddt 0.51 ptm 0.58 i_ptm 0.25 rg 0.15
7 models [2] recycles 1 hard 0 soft 0.13 temp 1 loss 6.59 helix 0.75 pae 0.46 i_pae 0.46 con 3.26 i_con 3.18 plddt 0.58 ptm 0.61 i_ptm 0.33 rg 0.24
8 models [4] recycles 1 hard 0 soft 0.14 temp 1 loss 5.19 helix 0.94 pae 0.30 i_pae 0.24 con 2.76 i_con 2.28 plddt 0.72 ptm 0.76 i_ptm 0.66 rg 0.78
9 models [4] recycles 1 hard 0 soft 0.16 temp 1 loss 7.04 helix 0.65 pae 0.48 i_pae 0.43 con 3.47 i_con 2.64 plddt 0.59 ptm 0.65 i_ptm 0.51 rg 2.77