{"model": "models/gemma-4-E4B-it-text", "commit": "ee0ef6023621cff504d758262d4e04895a5af4a2+text-only", "mode": "lora", "seq_len": 2048, "micro_batch": 8, "total_params": 7501892608, "trainable_params": 38879232, "tokens_per_s": 500.3, "step_seconds": 32.75, "peak_mem_gb": 81.3, "extra_gb_for_fp32_adam": 0.1, "days_per_1B_tokens": 23.14, "env": {"python": "3.12.3", "machine": "aarch64", "torch": "2.14.1+cu130", "transformers": "5.19.0", "datasets": "5.1.0", "peft": "0.21.2", "accelerate": "1.15.0", "huggingface_hub": "2.2.0", "gpu": "NVIDIA GB10", "cuda": "13.0", "git_commit": "HEAD", "git_dirty": true}} {"model": "models/gemma-4-E4B-it-text", "commit": "ee0ef6023621cff504d758262d4e04895a5af4a2+text-only", "mode": "freeze-embed", "seq_len": 2048, "micro_batch": 8, "total_params": 7463013376, "trainable_params": 3973352448, "tokens_per_s": 704.9, "step_seconds": 23.24, "peak_mem_gb": 97.4, "extra_gb_for_fp32_adam": 14.8, "days_per_1B_tokens": 16.42, "env": {"python": "3.12.3", "machine": "aarch64", "torch": "2.14.1+cu130", "transformers": "5.19.0", "datasets": "5.1.0", "peft": "0.21.2", "accelerate": "1.15.0", "huggingface_hub": "2.2.0", "gpu": "NVIDIA GB10", "cuda": "13.0", "git_commit": "HEAD", "git_dirty": true}} {"model": "models/gemma-4-E4B-it-text", "commit": "ee0ef6023621cff504d758262d4e04895a5af4a2+text-only", "mode": "freeze-embed", "loss": "chunked", "ckpt_every": 1, "compile": false, "tag": "speedups", "seq_len": 2048, "micro_batch": 32, "total_params": 7463013376, "trainable_params": 3973352448, "tokens_per_s": 628.9, "step_seconds": 104.21, "peak_mem_gb": 71.0, "extra_gb_for_fp32_adam": 14.8, "days_per_1B_tokens": 18.4, "env": {"python": "3.12.3", "machine": "aarch64", "torch": "2.14.1+cu130", "transformers": "5.19.0", "datasets": "5.1.0", "peft": "0.21.2", "accelerate": "1.15.0", "huggingface_hub": "2.2.0", "gpu": "NVIDIA GB10", "cuda": "13.0", "git_commit": "HEAD", "git_dirty": true}} {"model": "models/gemma-4-E4B-it-text", "commit": "ee0ef6023621cff504d758262d4e04895a5af4a2+text-only", "mode": "freeze-embed", "loss": "liger", "ckpt_every": 1, "compile": false, "tag": "speedups", "seq_len": 2048, "micro_batch": 32, "total_params": 7463013376, "trainable_params": 3973352448, "tokens_per_s": 714.1, "step_seconds": 91.77, "peak_mem_gb": 71.0, "extra_gb_for_fp32_adam": 14.8, "days_per_1B_tokens": 16.21, "env": {"python": "3.12.3", "machine": "aarch64", "torch": "2.14.1+cu130", "transformers": "5.19.0", "datasets": "5.1.0", "peft": "0.21.2", "accelerate": "1.15.0", "huggingface_hub": "2.2.0", "gpu": "NVIDIA GB10", "cuda": "13.0", "git_commit": "HEAD", "git_dirty": true}} {"model": "models/gemma-4-E4B-it-text", "commit": "ee0ef6023621cff504d758262d4e04895a5af4a2+text-only", "mode": "freeze-embed", "loss": "liger", "ckpt_every": 0, "compile": false, "tag": "speedups", "seq_len": 2048, "micro_batch": 2, "total_params": 7463013376, "trainable_params": 3973352448, "tokens_per_s": 763.1, "step_seconds": 5.37, "peak_mem_gb": 69.1, "extra_gb_for_fp32_adam": 14.8, "days_per_1B_tokens": 15.17, "env": {"python": "3.12.3", "machine": "aarch64", "torch": "2.14.1+cu130", "transformers": "5.19.0", "datasets": "5.1.0", "peft": "0.21.2", "accelerate": "1.15.0", "huggingface_hub": "2.2.0", "gpu": "NVIDIA GB10", "cuda": "13.0", "git_commit": "HEAD", "git_dirty": true}} {"model": "models/gemma-4-E4B-it-text", "commit": "ee0ef6023621cff504d758262d4e04895a5af4a2+text-only", "mode": "freeze-embed", "loss": "liger", "ckpt_every": 1, "compile": true, "tag": "speedups", "seq_len": 2048, "micro_batch": 32, "total_params": 7463013376, "trainable_params": 3973352448, "tokens_per_s": 712.2, "step_seconds": 92.02, "peak_mem_gb": 71.0, "extra_gb_for_fp32_adam": 14.8, "days_per_1B_tokens": 16.25, "env": {"python": "3.12.3", "machine": "aarch64", "torch": "2.14.1+cu130", "transformers": "5.19.0", "datasets": "5.1.0", "peft": "0.21.2", "accelerate": "1.15.0", "huggingface_hub": "2.2.0", "gpu": "NVIDIA GB10", "cuda": "13.0", "git_commit": "HEAD", "git_dirty": true}} {"model": "models/gemma-4-E4B-it-text", "commit": "ee0ef6023621cff504d758262d4e04895a5af4a2+text-only", "mode": "lora", "loss": "liger", "ckpt_every": 1, "compile": true, "tag": "speedups", "seq_len": 2048, "micro_batch": 32, "total_params": 7501892608, "trainable_params": 38879232, "tokens_per_s": 505.2, "step_seconds": 129.71, "peak_mem_gb": 52.1, "extra_gb_for_fp32_adam": 0.1, "days_per_1B_tokens": 22.91, "env": {"python": "3.12.3", "machine": "aarch64", "torch": "2.14.1+cu130", "transformers": "5.19.0", "datasets": "5.1.0", "peft": "0.21.2", "accelerate": "1.15.0", "huggingface_hub": "2.2.0", "gpu": "NVIDIA GB10", "cuda": "13.0", "git_commit": "HEAD", "git_dirty": true}} {"model": "Qwen/Qwen3.5-4B", "commit": "851bf6e806efd8d0a36b00ddf55e13ccb7b8cd0a", "mode": "full", "loss": "hf", "ckpt_every": 1, "compile": false, "tag": "speedups", "seq_len": 2048, "micro_batch": 8, "total_params": 4205751296, "trainable_params": 4205751296, "tokens_per_s": 1016.3, "step_seconds": 16.12, "peak_mem_gb": 72.1, "extra_gb_for_fp32_adam": 15.7, "days_per_1B_tokens": 11.39, "env": {"python": "3.12.3", "machine": "aarch64", "torch": "2.14.1+cu130", "transformers": "5.19.0", "datasets": "5.1.0", "peft": "0.21.2", "accelerate": "1.15.0", "huggingface_hub": "2.2.0", "gpu": "NVIDIA GB10", "cuda": "13.0", "git_commit": "HEAD", "git_dirty": true}} {"model": "Qwen/Qwen3.5-4B", "commit": "851bf6e806efd8d0a36b00ddf55e13ccb7b8cd0a", "mode": "full", "loss": "liger", "ckpt_every": 1, "compile": false, "tag": "speedups", "seq_len": 2048, "micro_batch": 32, "total_params": 4205751296, "trainable_params": 4205751296, "tokens_per_s": 1084.7, "step_seconds": 60.42, "peak_mem_gb": 53.4, "extra_gb_for_fp32_adam": 15.7, "days_per_1B_tokens": 10.67, "env": {"python": "3.12.3", "machine": "aarch64", "torch": "2.14.1+cu130", "transformers": "5.19.0", "datasets": "5.1.0", "peft": "0.21.2", "accelerate": "1.15.0", "huggingface_hub": "2.2.0", "gpu": "NVIDIA GB10", "cuda": "13.0", "git_commit": "HEAD", "git_dirty": true}} {"model": "Qwen/Qwen3.5-4B", "commit": "851bf6e806efd8d0a36b00ddf55e13ccb7b8cd0a", "mode": "full", "loss": "liger", "ckpt_every": 1, "compile": true, "tag": "speedups", "seq_len": 2048, "micro_batch": 32, "total_params": 4205751296, "trainable_params": 4205751296, "tokens_per_s": 1583.8, "step_seconds": 41.38, "peak_mem_gb": 46.9, "extra_gb_for_fp32_adam": 15.7, "days_per_1B_tokens": 7.31, "env": {"python": "3.12.3", "machine": "aarch64", "torch": "2.14.1+cu130", "transformers": "5.19.0", "datasets": "5.1.0", "peft": "0.21.2", "accelerate": "1.15.0", "huggingface_hub": "2.2.0", "gpu": "NVIDIA GB10", "cuda": "13.0", "git_commit": "HEAD", "git_dirty": true}} {"model": "Qwen/Qwen3.5-4B", "commit": "851bf6e806efd8d0a36b00ddf55e13ccb7b8cd0a", "mode": "lora", "loss": "liger", "ckpt_every": 1, "compile": true, "tag": "speedups", "seq_len": 2048, "micro_batch": 32, "total_params": 4238216192, "trainable_params": 32464896, "tokens_per_s": 1179.6, "step_seconds": 55.56, "peak_mem_gb": 38.0, "extra_gb_for_fp32_adam": 0.1, "days_per_1B_tokens": 9.81, "env": {"python": "3.12.3", "machine": "aarch64", "torch": "2.14.1+cu130", "transformers": "5.19.0", "datasets": "5.1.0", "peft": "0.21.2", "accelerate": "1.15.0", "huggingface_hub": "2.2.0", "gpu": "NVIDIA GB10", "cuda": "13.0", "git_commit": "HEAD", "git_dirty": true}} {"model": "models/gemma-4-E4B-it-text", "commit": "ee0ef6023621cff504d758262d4e04895a5af4a2+text-only", "mode": "freeze-embed", "loss": "liger", "ckpt_every": 0, "compile": true, "tag": "compile_fixed", "seq_len": 2048, "micro_batch": 2, "total_params": 7463013376, "trainable_params": 3973352448, "tokens_per_s": 1150.4, "step_seconds": 3.56, "peak_mem_gb": 98.5, "extra_gb_for_fp32_adam": 14.8, "days_per_1B_tokens": 10.06, "env": {"python": "3.12.3", "machine": "aarch64", "torch": "2.14.1+cu130", "transformers": "5.19.0", "datasets": "5.1.0", "peft": "0.21.2", "accelerate": "1.15.0", "huggingface_hub": "2.2.0", "gpu": "NVIDIA GB10", "cuda": "13.0", "git_commit": "HEAD", "git_dirty": true}} {"model": "models/gemma-4-E4B-it-text", "commit": "ee0ef6023621cff504d758262d4e04895a5af4a2+text-only", "mode": "freeze-embed", "loss": "liger", "ckpt_every": 0, "compile": true, "optim": "adamw8bit", "tag": "memory", "seq_len": 2048, "micro_batch": 2, "total_params": 7463013376, "trainable_params": 3973352448, "tokens_per_s": 1148.9, "step_seconds": 3.57, "peak_mem_gb": 91.3, "extra_gb_for_fp32_adam": 14.8, "days_per_1B_tokens": 10.07, "env": {"python": "3.12.3", "machine": "aarch64", "torch": "2.14.1+cu130", "transformers": "5.19.0", "datasets": "5.1.0", "peft": "0.21.2", "accelerate": "1.15.0", "huggingface_hub": "2.2.0", "gpu": "NVIDIA GB10", "cuda": "13.0", "git_commit": "HEAD", "git_dirty": true}} {"model": "models/gemma-4-E4B-it-text", "commit": "ee0ef6023621cff504d758262d4e04895a5af4a2+text-only", "mode": "freeze-embed", "loss": "liger", "ckpt_every": 2, "compile": true, "optim": "adamw8bit", "tag": "memory", "seq_len": 2048, "micro_batch": 4, "total_params": 7463013376, "trainable_params": 3973352448, "tokens_per_s": 1262.6, "step_seconds": 6.49, "peak_mem_gb": 98.1, "extra_gb_for_fp32_adam": 14.8, "days_per_1B_tokens": 9.17, "env": {"python": "3.12.3", "machine": "aarch64", "torch": "2.14.1+cu130", "transformers": "5.19.0", "datasets": "5.1.0", "peft": "0.21.2", "accelerate": "1.15.0", "huggingface_hub": "2.2.0", "gpu": "NVIDIA GB10", "cuda": "13.0", "git_commit": "HEAD", "git_dirty": true}}