[
 {
  "benchmark": "indicmmlu_pro_ta",
  "split": "test",
  "n": 12032,
  "metric": "acc",
  "score": 0.1167,
  "script": "eval/suite.py",
  "commit": "d6a1c36",
  "timestamp": "2026-08-25T20:05:28",
  "stage": "base",
  "model": "Qwen/Qwen3.5-2B-Base",
  "adapter": null
 },
 {
  "benchmark": "belebele_ta",
  "split": "test",
  "n": 720,
  "metric": "acc",
  "score": 0.2181,
  "script": "eval/suite.py",
  "commit": "d6a1c36",
  "timestamp": "2026-08-25T20:06:37",
  "stage": "base",
  "model": "Qwen/Qwen3.5-2B-Base",
  "adapter": null
 },
 {
  "benchmark": "include_ta",
  "split": "test",
  "n": 448,
  "metric": "acc",
  "score": 0.2344,
  "script": "eval/suite.py",
  "commit": "d6a1c36",
  "timestamp": "2026-08-25T20:07:20",
  "stage": "base",
  "model": "Qwen/Qwen3.5-2B-Base",
  "adapter": null
 },
 {
  "benchmark": "mmlu_en",
  "split": "test",
  "n": 400,
  "metric": "acc",
  "score": 0.5525,
  "script": "eval/suite.py",
  "commit": "d6a1c36",
  "timestamp": "2026-08-25T20:08:00",
  "stage": "base",
  "model": "Qwen/Qwen3.5-2B-Base",
  "adapter": null
 },
 {
  "benchmark": "gsm8k_en",
  "split": "test",
  "n": 160,
  "metric": "acc",
  "score": 0.6375,
  "script": "eval/suite.py",
  "commit": "d6a1c36",
  "timestamp": "2026-08-25T20:19:33",
  "stage": "base",
  "model": "Qwen/Qwen3.5-2B-Base",
  "adapter": null
 },
 {
  "benchmark": "indicxnli_ta",
  "split": "test",
  "n": 5010,
  "metric": "acc",
  "score": 0.3333,
  "script": "eval/suite.py",
  "commit": "d6a1c36",
  "timestamp": "2026-08-25T20:26:19",
  "stage": "base",
  "model": "Qwen/Qwen3.5-2B-Base",
  "adapter": null
 },
 {
  "benchmark": "indiccopa_ta",
  "split": "test",
  "n": 400,
  "metric": "acc",
  "score": 0.4775,
  "script": "eval/suite.py",
  "commit": "d6a1c36",
  "timestamp": "2026-08-25T20:26:40",
  "stage": "base",
  "model": "Qwen/Qwen3.5-2B-Base",
  "adapter": null
 },
 {
  "benchmark": "indicsentiment_ta",
  "split": "test",
  "n": 998,
  "metric": "acc",
  "score": 0.481,
  "script": "eval/suite.py",
  "commit": "d6a1c36",
  "timestamp": "2026-08-25T20:27:33",
  "stage": "base",
  "model": "Qwen/Qwen3.5-2B-Base",
  "adapter": null
 },
 {
  "benchmark": "indicqa_ta",
  "split": "test",
  "n": 1022,
  "metric": "f1",
  "score": 0.0422,
  "script": "eval/suite.py",
  "commit": "d6a1c36",
  "timestamp": "2026-08-25T20:47:43",
  "stage": "base",
  "model": "Qwen/Qwen3.5-2B-Base",
  "adapter": null
 },
 {
  "benchmark": "flores_en_ta",
  "split": "test",
  "n": 1012,
  "metric": "chrf++",
  "score": 3.2674,
  "script": "eval/suite.py",
  "commit": "d6a1c36",
  "timestamp": "2026-08-25T21:40:06",
  "stage": "base",
  "model": "Qwen/Qwen3.5-2B-Base",
  "adapter": null
 },
 {
  "benchmark": "flores_en_ta",
  "split": "test",
  "n": 1012,
  "metric": "bleu",
  "score": 0.0786,
  "script": "eval/suite.py",
  "commit": "d6a1c36",
  "timestamp": "2026-08-25T21:40:06",
  "stage": "base",
  "model": "Qwen/Qwen3.5-2B-Base",
  "adapter": null
 },
 {
  "benchmark": "flores_ta_en",
  "split": "test",
  "n": 1012,
  "metric": "chrf++",
  "score": 11.8811,
  "script": "eval/suite.py",
  "commit": "d6a1c36",
  "timestamp": "2026-08-25T22:28:27",
  "stage": "base",
  "model": "Qwen/Qwen3.5-2B-Base",
  "adapter": null
 },
 {
  "benchmark": "flores_ta_en",
  "split": "test",
  "n": 1012,
  "metric": "bleu",
  "score": 1.491,
  "script": "eval/suite.py",
  "commit": "d6a1c36",
  "timestamp": "2026-08-25T22:28:27",
  "stage": "base",
  "model": "Qwen/Qwen3.5-2B-Base",
  "adapter": null
 },
 {
  "benchmark": "xlsum_ta",
  "split": "test",
  "n": 2027,
  "metric": "rougeL",
  "score": 0.3586,
  "script": "eval/suite.py",
  "commit": "d6a1c36",
  "timestamp": "2026-08-25T23:43:31",
  "stage": "base",
  "model": "Qwen/Qwen3.5-2B-Base",
  "adapter": null
 },
 {
  "benchmark": "tanglish_heldout",
  "split": "test",
  "n": 2740,
  "metric": "bpc",
  "score": 3.2534,
  "script": "eval/suite.py",
  "commit": "d6a1c36",
  "timestamp": "2026-08-25T23:44:34",
  "stage": "base",
  "model": "Qwen/Qwen3.5-2B-Base",
  "adapter": null
 },
 {
  "benchmark": "milu_ta",
  "split": "test",
  "n": 6372,
  "metric": "acc",
  "score": 0.2666,
  "script": "eval/suite.py",
  "commit": "b160a84",
  "timestamp": "2026-08-26T11:55:13",
  "stage": "base",
  "model": "Qwen/Qwen3.5-2B-Base",
  "adapter": null
 },
 {
  "benchmark": "in22gen_en_ta",
  "split": "test",
  "n": 820,
  "metric": "chrf++",
  "score": 3.9127,
  "script": "eval/suite.py",
  "commit": "b160a84",
  "timestamp": "2026-08-26T12:47:23",
  "stage": "base",
  "model": "Qwen/Qwen3.5-2B-Base",
  "adapter": null
 },
 {
  "benchmark": "in22gen_en_ta",
  "split": "test",
  "n": 820,
  "metric": "bleu",
  "score": 0.0671,
  "script": "eval/suite.py",
  "commit": "b160a84",
  "timestamp": "2026-08-26T12:47:23",
  "stage": "base",
  "model": "Qwen/Qwen3.5-2B-Base",
  "adapter": null
 },
 {
  "benchmark": "in22gen_ta_en",
  "split": "test",
  "n": 820,
  "metric": "chrf++",
  "score": 11.6249,
  "script": "eval/suite.py",
  "commit": "b160a84",
  "timestamp": "2026-08-26T13:32:55",
  "stage": "base",
  "model": "Qwen/Qwen3.5-2B-Base",
  "adapter": null
 },
 {
  "benchmark": "in22gen_ta_en",
  "split": "test",
  "n": 820,
  "metric": "bleu",
  "score": 2.0367,
  "script": "eval/suite.py",
  "commit": "b160a84",
  "timestamp": "2026-08-26T13:32:55",
  "stage": "base",
  "model": "Qwen/Qwen3.5-2B-Base",
  "adapter": null
 }
]