{"model": "Qwen3.5-0.8B-Base", "total_params_B": 0.765, "lora_rank": 32, "targets": "attn_mlp", "adapted_modules": 96, "trainable_params_M": 12.78, "trainable_pct": 1.67, "batch": 1, "seq": 4096, "tokens_per_microbatch": 4096, "grad_checkpointing": true, "attn_impl": "sdpa", "dtype": "bfloat16", "device": "NVIDIA GB10", "torch": "2.14.0+cu130", "warmup": 3, "n": 10, "s_per_step_median": 7.5814, "s_per_step_min": 7.4864, "s_per_step_max": 7.6843, "s_per_step_spread_pct": 2.6, "tok_per_s_median": 540.3, "peak_mem_GiB": 15.1} {"model": "Qwen3.5-0.8B-Base", "total_params_B": 0.765, "lora_rank": 32, "targets": "attn_mlp", "adapted_modules": 96, "trainable_params_M": 12.78, "trainable_pct": 1.67, "batch": 1, "seq": 4096, "tokens_per_microbatch": 4096, "grad_checkpointing": false, "attn_impl": "sdpa", "dtype": "bfloat16", "device": "NVIDIA GB10", "torch": "2.14.0+cu130", "warmup": 3, "n": 10, "s_per_step_median": 6.3639, "s_per_step_min": 6.3549, "s_per_step_max": 6.4533, "s_per_step_spread_pct": 1.5, "tok_per_s_median": 643.6, "peak_mem_GiB": 38.91} {"model": "Qwen3-0.6B-Base", "total_params_B": 0.616, "lora_rank": 32, "targets": "attn_mlp", "adapted_modules": 196, "trainable_params_M": 20.19, "trainable_pct": 3.276, "batch": 1, "seq": 4096, "tokens_per_microbatch": 4096, "grad_checkpointing": true, "attn_impl": "sdpa", "dtype": "bfloat16", "device": "NVIDIA GB10", "torch": "2.14.0+cu130", "warmup": 3, "n": 10, "s_per_step_median": 1.7072, "s_per_step_min": 1.6993, "s_per_step_max": 1.7097, "s_per_step_spread_pct": 0.6, "tok_per_s_median": 2399.2, "peak_mem_GiB": 9.75} {"model": "Qwen3-1.7B-Base", "total_params_B": 1.755, "lora_rank": 32, "targets": "attn_mlp", "adapted_modules": 196, "trainable_params_M": 34.87, "trainable_pct": 1.986, "batch": 1, "seq": 4096, "tokens_per_microbatch": 4096, "grad_checkpointing": true, "attn_impl": "sdpa", "dtype": "bfloat16", "device": "NVIDIA GB10", "torch": "2.14.0+cu130", "warmup": 3, "n": 10, "s_per_step_median": 2.8946, "s_per_step_min": 2.8782, "s_per_step_max": 2.901, "s_per_step_spread_pct": 0.8, "tok_per_s_median": 1415.0, "peak_mem_GiB": 12.24} {"model": "Qwen3-1.7B-Base", "total_params_B": 1.755, "lora_rank": 32, "targets": "attn_mlp", "adapted_modules": 196, "trainable_params_M": 34.87, "trainable_pct": 1.986, "batch": 4, "seq": 4096, "tokens_per_microbatch": 16384, "grad_checkpointing": true, "attn_impl": "sdpa", "dtype": "bfloat16", "device": "NVIDIA GB10", "torch": "2.14.0+cu130", "warmup": 3, "n": 10, "s_per_step_median": 11.3872, "s_per_step_min": 11.3401, "s_per_step_max": 11.4128, "s_per_step_spread_pct": 0.6, "tok_per_s_median": 1438.8, "peak_mem_GiB": 37.99} {"model": "Qwen3.5-0.8B-Base", "total_params_B": 0.765, "lora_rank": 32, "targets": "attn_mlp", "adapted_modules": 96, "trainable_params_M": 12.78, "trainable_pct": 1.67, "batch": 4, "seq": 4096, "tokens_per_microbatch": 16384, "grad_checkpointing": true, "attn_impl": "sdpa", "dtype": "bfloat16", "device": "NVIDIA GB10", "torch": "2.14.0+cu130", "warmup": 3, "n": 10, "s_per_step_median": 30.0301, "s_per_step_min": 29.9379, "s_per_step_max": 30.1444, "s_per_step_spread_pct": 0.7, "tok_per_s_median": 545.6, "peak_mem_GiB": 55.49} {"model": "Qwen3-4B-Base", "total_params_B": 4.089, "lora_rank": 32, "targets": "attn_mlp", "adapted_modules": 252, "trainable_params_M": 66.06, "trainable_pct": 1.616, "batch": 1, "seq": 4096, "tokens_per_microbatch": 4096, "grad_checkpointing": true, "attn_impl": "sdpa", "dtype": "bfloat16", "device": "NVIDIA GB10", "torch": "2.14.0+cu130", "warmup": 3, "n": 10, "s_per_step_median": 5.7145, "s_per_step_min": 5.7085, "s_per_step_max": 5.727, "s_per_step_spread_pct": 0.3, "tok_per_s_median": 716.8, "peak_mem_GiB": 17.22}