{
  "utc_started": "2026-09-13T04:59:28.807707+00:00",
  "model": "HuggingFaceTB/SmolLM2-135M",
  "model_lock": {
    "model": "HuggingFaceTB/SmolLM2-135M",
    "revision": "93efa2f097d58c2a74874c7e644dbc9b0cee75a2",
    "path": "/root/inference-engineering/lessons/01-baseline/.cache/huggingface/hub/models--HuggingFaceTB--SmolLM2-135M/snapshots/93efa2f097d58c2a74874c7e644dbc9b0cee75a2"
  },
  "platform": "Linux-6.8.0-110-generic-x86_64-with-glibc2.39",
  "python": "3.12.3",
  "torch": "2.6.0+cpu",
  "transformers": "4.48.3",
  "device": "cpu",
  "cuda_available": false,
  "cpu_count": 2,
  "cpu_description": "Architecture:                            x86_64\nCPU op-mode(s):                          32-bit, 64-bit\nAddress sizes:                           40 bits physical, 48 bits virtual\nByte Order:                              Little Endian\nCPU(s):                                  2\nOn-line CPU(s) list:                     0,1\nVendor ID:                               GenuineIntel\nBIOS Vendor ID:                          QEMU\nModel name:                              DO-Regular\nBIOS Model name:                         pc-i440fx-6.1  CPU @ 2.0GHz\nBIOS CPU family:                         1\nCPU family:                              6\nModel:                                   79\nThread(s) per core:                      1\nCore(s) per socket:                      2\nSocket(s):                               1\nStepping:                                1\nBogoMIPS:                                4589.22\nFlags:                                   fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ss ht syscall nx rdtscp lm constant_tsc rep_good nopl xtopology cpuid tsc_known_freq pni pclmulqdq vmx ssse3 fma cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand hypervisor lahf_lm abm 3dnowprefetch cpuid_fault pti ssbd ibrs ibpb tpr_shadow flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid rdseed adx smap xsaveopt arat vnmi md_clear\nVirtualization:                          VT-x\nHypervisor vendor:                       KVM\nVirtualization type:                     full\nL1d cache:                               64 KiB (2 instances)\nL1i cache:                               64 KiB (2 instances)\nL2 cache:                                8 MiB (2 instances)\nNUMA node(s):                            1\nNUMA node0 CPU(s):                       0,1\nVulnerability Gather data sampling:      Not affected\nVulnerability Indirect target selection: Mitigation; Aligned branch/return thunks\nVulnerability Itlb multihit:             KVM: Mitigation: VMX disabled\nVulnerability L1tf:                      Mitigation; PTE Inversion; VMX conditional cache flushes, SMT disabled\nVulnerability Mds:                       Mitigation; Clear CPU buffers; SMT Host state unknown\nVulnerability Meltdown:                  Mitigation; PTI\nVulnerability Mmio stale data:           Vulnerable: Clear CPU buffers attempted, no microcode; SMT Host state unknown\nVulnerability Reg file data sampling:    Not affected\nVulnerability Retbleed:                  Not affected\nVulnerability Spec rstack overflow:      Not affected\nVulnerability Spec store bypass:         Mitigation; Speculative Store Bypass disabled via prctl\nVulnerability Spectre v1:                Mitigation; usercopy/swapgs barriers and __user pointer sanitization\nVulnerability Spectre v2:                Mitigation; Retpolines; IBPB conditional; IBRS_FW; STIBP disabled; RSB filling; PBRSB-eIBRS Not affected; BHI Retpoline\nVulnerability Srbds:                     Not affected\nVulnerability Tsa:                       Not affected\nVulnerability Tsx async abort:           Not affected\nVulnerability Vmscape:                   Not affected\n",
  "system_ram_gib": 3.824108123779297,
  "torch_threads": 2,
  "dtype": "float32",
  "attention_backend": "eager",
  "batch_size": 1,
  "use_cache": true,
  "timing_scope": "model.generate wall time; excludes loading, tokenization and detokenization; includes generation orchestration",
  "fixed_output_length": true,
  "warmups_per_shape": 2,
  "measured_repeats_per_shape": 5,
  "order_seed": 42,
  "model_tokenizer_load_s": 1.2872828543186188,
  "download_excluded": true,
  "process_peak_rss_mib": 1087.47265625,
  "process_swap_mib": 0.0,
  "system_swap_counter_delta": {
    "pswpin": 0,
    "pswpout": 0
  },
  "parameters_unique": 134515008,
  "parameter_bytes": 538060032,
  "layers": 30,
  "kv_heads": 3,
  "head_dim": 64,
  "kv_bytes_per_cached_token_batch1": 46080,
  "actual_kv_bytes_64_tokens": 2949120,
  "source_sha256": "dc10b6500f64e2a05e50d64a4fadcd73409ffd4539c9b1f6752dcb5240c5c8d2"
}