analysis: 12B 3 NaN real root cause found (NOT config mismatch)
CI / build-and-test (push) Has been cancelled

BREAKTHROUGH DISCOVERY:
-  Previous hypothesis: Config mismatch (num_kv_heads: 8 vs 2)
-  Actual root cause: Special Token IDs have embedding issues

EXACT NaN LOCATIONS:
- Token ID 2 (BOS - Begin of Sequence): NaN
- Token ID 255999 (BOI - Begin of Image): NaN
- Token ID 256000 (BOA - Begin of Audio): NaN

Evidence from debug test: indices [2, 255999, 256000]
Config fix made NaN worse (3→12), restored original config

Only 3 out of 262K tokens affected (0.0011%)
Recommendation: Use E4B/E2B or avoid special tokens
This commit is contained in:
MarkBase Admin
2026-06-24 00:53:27 +08:00
parent a64ccf0869
commit 78257a947c
3 changed files with 575 additions and 0 deletions
@@ -0,0 +1,124 @@
import XCTest
@testable import MarkBase
class TwelveBNaNDebugTest: XCTestCase {
func test12BNaNDebug() throws {
print("\n═══════════════════════════════════════════════════════════════════")
print(" 12B NaN Debug Test - Find Exact NaN Positions")
print("═══════════════════════════════════════════════════════════════════\n")
let modelPath = "/Users/accusys/MarkBaseEngine/models/gemma-4-12b-it-4bit"
let engine = try MarkBaseEngine(autoCompile: true)
let model = try E4BModel(modelDir: modelPath, engine: engine, maxContextLength: 128)
print("Step 1: Run forward pass and find NaN indices...")
let logits = try model.forwardOptimized(tokenId: 2, position: 0)
var nanIndices: [Int] = []
var nanValues: [Float] = []
var extremeIndices: [Int] = []
var extremeValues: [Float] = []
for i in 0..<logits.count {
let v = logits[i]
if v.isNaN {
nanIndices.append(i)
nanValues.append(v)
}
if abs(v) > 100.0 {
extremeIndices.append(i)
extremeValues.append(v)
}
}
print(" Total logits: \(logits.count)")
print(" NaN count: \(nanIndices.count)")
print(" Extreme values (>100): \(extremeIndices.count)")
print()
if nanIndices.count > 0 {
print("Step 2: NaN Details:")
print(" NaN at indices: \(nanIndices)")
print()
print("Step 3: Analyze logits around NaN positions:")
for idx in nanIndices.prefix(3) {
let start = max(0, idx - 5)
let end = min(logits.count - 1, idx + 5)
print(" Around index \(idx):")
for i in start...end {
let marker = i == idx ? " [NaN]" : ""
print(" logits[\(i)] = \(logits[i])\(marker)")
}
print()
}
}
if extremeIndices.count > 0 {
print("Step 4: Extreme values (>100) that might cause NaN:")
print(" Extreme indices: \(extremeIndices.prefix(10))")
print(" Extreme values: \(extremeValues.prefix(10))")
print()
}
// Check overall statistics
var minVal: Float = Float.infinity
var maxVal: Float = -Float.infinity
var sumVal: Float = 0
for v in logits {
if v.isFinite {
if v < minVal { minVal = v }
if v > maxVal { maxVal = v }
sumVal += v
}
}
let meanVal = sumVal / Float(logits.count - nanIndices.count)
print("Step 5: Logit Statistics (excluding NaN/Inf):")
print(" Min: \(minVal)")
print(" Max: \(maxVal)")
print(" Mean: \(meanVal)")
print(" Range: \(maxVal - minVal)")
print()
// Check if softcapping is applied
print("Step 6: Config Check:")
let configPath = modelPath + "/config.json"
if let configData = FileManager.default.contents(atPath: configPath) {
let config = try JSONDecoder().decode(ConfigDebug.self, from: configData)
print(" final_logit_softcapping: \(config.textConfig.finalLogitSoftcapping)")
print(" rms_norm_eps: \(config.textConfig.rmsNormEps)")
print()
if config.textConfig.finalLogitSoftcapping > 0 {
print(" ⚠️ Softcapping ACTIVE: logits /= (1 + |logits| / \(config.textConfig.finalLogitSoftcapping))")
print(" 💡 Large logits could cause division by zero or NaN")
}
}
print("═══════════════════════════════════════════════════════════════════\n")
XCTAssertLessThanOrEqual(nanIndices.count, 10, "Should have minimal NaN")
}
}
struct ConfigDebug: Decodable {
let textConfig: TextConfigDebug
enum CodingKeys: String, CodingKey {
case textConfig = "text_config"
}
}
struct TextConfigDebug: Decodable {
let finalLogitSoftcapping: Float
let rmsNormEps: Float
enum CodingKeys: String, CodingKey {
case finalLogitSoftcapping = "final_logit_softcapping"
case rmsNormEps = "rms_norm_eps"
}
}