| { |
| "stage": "train", |
| "timestamp": "2026-09-21T11:15:01+00:00", |
| "model_name": "LiquidAI/LFM2-700M", |
| "seed": 42, |
| "config": { |
| "paths": { |
| "data_dir": "data", |
| "raw_dir": "data/raw", |
| "processed_dir": "data/processed", |
| "train_dir": "data/train", |
| "validation_dir": "data/validation", |
| "test_dir": "data/test", |
| "reports_dir": "reports", |
| "outputs_dir": "outputs" |
| }, |
| "data": { |
| "nl2bash_repo": "jiacheng-ye/nl2bash", |
| "linux_commands_repo": "mecha-org/linux-command-dataset", |
| "nl2bash_archive_url": "https://www.dropbox.com/s/wy7uahzbir7lrq1/nl2bash.zip?dl=1", |
| "min_instruction_chars": 5, |
| "min_command_chars": 2, |
| "max_instruction_chars": 600, |
| "max_command_chars": 600, |
| "head_command_cap": 2500, |
| "exact_command_cap": 40, |
| "near_duplicate_threshold": 0.9, |
| "drop_near_duplicates": false, |
| "split_grouping": "template", |
| "train_ratio": 0.9, |
| "validation_ratio": 0.05, |
| "test_ratio": 0.05, |
| "seed": 42 |
| }, |
| "model": { |
| "model_name": "LiquidAI/LFM2-700M", |
| "dtype": "bfloat16", |
| "attn_implementation": "sdpa", |
| "system_prompt": null, |
| "max_length": 128, |
| "trust_remote_code": false |
| }, |
| "lora": { |
| "r": 32, |
| "alpha": 64, |
| "dropout": 0.05, |
| "target_modules": [ |
| "q_proj", |
| "k_proj", |
| "v_proj", |
| "out_proj", |
| "w1", |
| "w2", |
| "w3", |
| "in_proj" |
| ], |
| "exclude_modules": [ |
| "conv.conv" |
| ], |
| "modules_to_save": [] |
| }, |
| "training": { |
| "method": "full", |
| "output_dir": "outputs/lfm2-linux-command", |
| "run_name": "lfm2-700m-linux-command", |
| "num_train_epochs": 3, |
| "per_device_train_batch_size": 16, |
| "per_device_eval_batch_size": 32, |
| "gradient_accumulation_steps": 2, |
| "learning_rate": 3e-05, |
| "lr_scheduler_type": "cosine", |
| "warmup_ratio": 0.03, |
| "weight_decay": 0.01, |
| "max_grad_norm": 1.0, |
| "optim": "adamw_torch_fused", |
| "adam_beta1": 0.9, |
| "adam_beta2": 0.95, |
| "adam_epsilon": 1e-08, |
| "bf16": true, |
| "fp16": false, |
| "gradient_checkpointing": false, |
| "group_by_length": true, |
| "logging_steps": 20, |
| "eval_strategy": "epoch", |
| "save_strategy": "epoch", |
| "save_total_limit": 2, |
| "load_best_model_at_end": true, |
| "metric_for_best_model": "eval_loss", |
| "greater_is_better": false, |
| "early_stopping_patience": 2, |
| "dataloader_num_workers": 4, |
| "seed": 42, |
| "report_to": [] |
| }, |
| "generation": { |
| "max_new_tokens": 128, |
| "do_sample": false, |
| "temperature": 1.0, |
| "top_p": 1.0, |
| "num_beams": 1, |
| "repetition_penalty": 1.0, |
| "batch_size": 32 |
| }, |
| "evaluation": { |
| "limit": null, |
| "execute_in_sandbox": false, |
| "sandbox_image": "linux-cmd-sandbox:latest", |
| "sandbox_timeout_s": 10, |
| "sandbox_memory": "256m", |
| "sandbox_cpus": "1.0", |
| "sandbox_pids_limit": 128, |
| "sandbox_network": false, |
| "max_execution_examples": 200 |
| } |
| }, |
| "environment": { |
| "python": "3.12.3", |
| "platform": "Linux-6.18.33.2-microsoft-standard-WSL2-x86_64-with-glibc2.39", |
| "torch": "2.11.0+cu128", |
| "transformers": "5.17.0", |
| "git_revision": null, |
| "datasets": "4.3.0", |
| "peft": "0.18.1", |
| "accelerate": "1.12.0", |
| "trl": "0.24.0", |
| "gpu": "NVIDIA GeForce RTX 5060 Ti", |
| "gpu_memory_gb": 15.9, |
| "cuda": "12.8" |
| }, |
| "result": { |
| "method": "full", |
| "parameters": { |
| "total": 742489344, |
| "trainable": 742489344 |
| }, |
| "tokenization": { |
| "train": { |
| "encoded": 11756, |
| "skipped_too_long": 6, |
| "skipped_empty_target": 0 |
| }, |
| "validation": { |
| "encoded": 652, |
| "skipped_too_long": 2, |
| "skipped_empty_target": 0 |
| } |
| }, |
| "num_train_examples": 11756, |
| "num_validation_examples": 652, |
| "num_test_examples": 653, |
| "train_runtime_s": 425.0, |
| "train_metrics": { |
| "train_runtime": 416.811, |
| "train_samples_per_second": 84.614, |
| "train_steps_per_second": 2.649, |
| "total_flos": 5049728172804096.0, |
| "train_loss": 0.5160034051623897, |
| "epoch": 3.0 |
| }, |
| "eval_metrics": { |
| "eval_loss": 0.6445356011390686, |
| "eval_runtime": 2.2801, |
| "eval_samples_per_second": 285.956, |
| "eval_steps_per_second": 9.21, |
| "epoch": 3.0 |
| }, |
| "peak_vram_gb": 8.95, |
| "log_history": [ |
| { |
| "loss": 2.2648730278015137, |
| "grad_norm": 26.875, |
| "learning_rate": 0.0, |
| "epoch": 0.0027210884353741495, |
| "step": 1 |
| }, |
| { |
| "loss": 2.3296870181435034, |
| "grad_norm": 20.5, |
| "learning_rate": 1.6764705882352943e-05, |
| "epoch": 0.05442176870748299, |
| "step": 20 |
| }, |
| { |
| "loss": 1.2557416915893556, |
| "grad_norm": 15.5625, |
| "learning_rate": 2.999838368626891e-05, |
| "epoch": 0.10884353741496598, |
| "step": 40 |
| }, |
| { |
| "loss": 1.2152017593383788, |
| "grad_norm": 10.625, |
| "learning_rate": 2.995960957056267e-05, |
| "epoch": 0.16326530612244897, |
| "step": 60 |
| }, |
| { |
| "loss": 1.0797980308532715, |
| "grad_norm": 10.6875, |
| "learning_rate": 2.986926658161179e-05, |
| "epoch": 0.21768707482993196, |
| "step": 80 |
| }, |
| { |
| "loss": 0.7814510822296142, |
| "grad_norm": 22.875, |
| "learning_rate": 2.9727666150414773e-05, |
| "epoch": 0.272108843537415, |
| "step": 100 |
| }, |
| { |
| "loss": 1.1167201042175292, |
| "grad_norm": 7.40625, |
| "learning_rate": 2.953529640299211e-05, |
| "epoch": 0.32653061224489793, |
| "step": 120 |
| }, |
| { |
| "loss": 0.7122071743011474, |
| "grad_norm": 12.1875, |
| "learning_rate": 2.929282047771477e-05, |
| "epoch": 0.38095238095238093, |
| "step": 140 |
| }, |
| { |
| "loss": 0.8981359481811524, |
| "grad_norm": 7.78125, |
| "learning_rate": 2.9001074239328856e-05, |
| "epoch": 0.43537414965986393, |
| "step": 160 |
| }, |
| { |
| "loss": 0.8201946258544922, |
| "grad_norm": 8.25, |
| "learning_rate": 2.8661063397556667e-05, |
| "epoch": 0.4897959183673469, |
| "step": 180 |
| }, |
| { |
| "loss": 0.6475086212158203, |
| "grad_norm": 13.125, |
| "learning_rate": 2.8273960040206944e-05, |
| "epoch": 0.54421768707483, |
| "step": 200 |
| }, |
| { |
| "loss": 0.9737781524658203, |
| "grad_norm": 8.3125, |
| "learning_rate": 2.7841098592745374e-05, |
| "epoch": 0.5986394557823129, |
| "step": 220 |
| }, |
| { |
| "loss": 0.6579679012298584, |
| "grad_norm": 12.125, |
| "learning_rate": 2.7363971218253575e-05, |
| "epoch": 0.6530612244897959, |
| "step": 240 |
| }, |
| { |
| "loss": 0.803803539276123, |
| "grad_norm": 7.0625, |
| "learning_rate": 2.684422267363384e-05, |
| "epoch": 0.7074829931972789, |
| "step": 260 |
| }, |
| { |
| "loss": 0.742891788482666, |
| "grad_norm": 9.8125, |
| "learning_rate": 2.628364463979135e-05, |
| "epoch": 0.7619047619047619, |
| "step": 280 |
| }, |
| { |
| "loss": 0.5735934257507325, |
| "grad_norm": 8.8125, |
| "learning_rate": 2.568416954533894e-05, |
| "epoch": 0.8163265306122449, |
| "step": 300 |
| }, |
| { |
| "loss": 0.8808271408081054, |
| "grad_norm": 7.03125, |
| "learning_rate": 2.5047863905115338e-05, |
| "epoch": 0.8707482993197279, |
| "step": 320 |
| }, |
| { |
| "loss": 0.5917014122009278, |
| "grad_norm": 9.0625, |
| "learning_rate": 2.4376921196480406e-05, |
| "epoch": 0.9251700680272109, |
| "step": 340 |
| }, |
| { |
| "loss": 0.629461145401001, |
| "grad_norm": 9.375, |
| "learning_rate": 2.3673654297944308e-05, |
| "epoch": 0.9795918367346939, |
| "step": 360 |
| }, |
| { |
| "eval_loss": 0.7183327674865723, |
| "eval_runtime": 1.8387, |
| "eval_samples_per_second": 354.607, |
| "eval_steps_per_second": 11.421, |
| "epoch": 1.0, |
| "step": 368 |
| }, |
| { |
| "loss": 0.5892221450805664, |
| "grad_norm": 6.40625, |
| "learning_rate": 2.29404875161961e-05, |
| "epoch": 1.0326530612244897, |
| "step": 380 |
| }, |
| { |
| "loss": 0.4322396755218506, |
| "grad_norm": 7.875, |
| "learning_rate": 2.2179948229016393e-05, |
| "epoch": 1.0870748299319728, |
| "step": 400 |
| }, |
| { |
| "loss": 0.2959575176239014, |
| "grad_norm": 7.21875, |
| "learning_rate": 2.139465817288254e-05, |
| "epoch": 1.1414965986394559, |
| "step": 420 |
| }, |
| { |
| "loss": 0.5574175834655761, |
| "grad_norm": 9.5625, |
| "learning_rate": 2.0587324405299893e-05, |
| "epoch": 1.1959183673469387, |
| "step": 440 |
| }, |
| { |
| "loss": 0.3074038982391357, |
| "grad_norm": 6.9375, |
| "learning_rate": 1.9760729973013758e-05, |
| "epoch": 1.2503401360544217, |
| "step": 460 |
| }, |
| { |
| "loss": 0.4826845169067383, |
| "grad_norm": 7.40625, |
| "learning_rate": 1.8917724318270762e-05, |
| "epoch": 1.3047619047619048, |
| "step": 480 |
| }, |
| { |
| "loss": 0.37243363857269285, |
| "grad_norm": 8.0625, |
| "learning_rate": 1.806121345620111e-05, |
| "epoch": 1.3591836734693876, |
| "step": 500 |
| }, |
| { |
| "loss": 0.29408578872680663, |
| "grad_norm": 6.65625, |
| "learning_rate": 1.7194149957182412e-05, |
| "epoch": 1.4136054421768707, |
| "step": 520 |
| }, |
| { |
| "loss": 0.523699426651001, |
| "grad_norm": 8.0, |
| "learning_rate": 1.6319522768717947e-05, |
| "epoch": 1.4680272108843537, |
| "step": 540 |
| }, |
| { |
| "loss": 0.27834906578063967, |
| "grad_norm": 7.0625, |
| "learning_rate": 1.544034691191541e-05, |
| "epoch": 1.5224489795918368, |
| "step": 560 |
| }, |
| { |
| "loss": 0.45731005668640134, |
| "grad_norm": 7.34375, |
| "learning_rate": 1.455965308808459e-05, |
| "epoch": 1.5768707482993198, |
| "step": 580 |
| }, |
| { |
| "loss": 0.36221044063568114, |
| "grad_norm": 7.4375, |
| "learning_rate": 1.3680477231282058e-05, |
| "epoch": 1.6312925170068027, |
| "step": 600 |
| }, |
| { |
| "loss": 0.28891568183898925, |
| "grad_norm": 7.8125, |
| "learning_rate": 1.280585004281759e-05, |
| "epoch": 1.6857142857142857, |
| "step": 620 |
| }, |
| { |
| "loss": 0.5141252517700196, |
| "grad_norm": 7.1875, |
| "learning_rate": 1.1938786543798891e-05, |
| "epoch": 1.7401360544217686, |
| "step": 640 |
| }, |
| { |
| "loss": 0.29115273952484133, |
| "grad_norm": 5.3125, |
| "learning_rate": 1.1082275681729237e-05, |
| "epoch": 1.7945578231292516, |
| "step": 660 |
| }, |
| { |
| "loss": 0.41370329856872556, |
| "grad_norm": 5.90625, |
| "learning_rate": 1.0239270026986243e-05, |
| "epoch": 1.8489795918367347, |
| "step": 680 |
| }, |
| { |
| "loss": 0.3591457366943359, |
| "grad_norm": 7.90625, |
| "learning_rate": 9.412675594700113e-06, |
| "epoch": 1.9034013605442177, |
| "step": 700 |
| }, |
| { |
| "loss": 0.27732415199279786, |
| "grad_norm": 6.96875, |
| "learning_rate": 8.605341827117464e-06, |
| "epoch": 1.9578231292517008, |
| "step": 720 |
| }, |
| { |
| "eval_loss": 0.6445356011390686, |
| "eval_runtime": 1.8506, |
| "eval_samples_per_second": 352.315, |
| "eval_steps_per_second": 11.348, |
| "epoch": 2.0, |
| "step": 736 |
| }, |
| { |
| "loss": 0.3676326751708984, |
| "grad_norm": 5.59375, |
| "learning_rate": 7.820051770983611e-06, |
| "epoch": 2.0108843537414964, |
| "step": 740 |
| }, |
| { |
| "loss": 0.3336158752441406, |
| "grad_norm": 5.375, |
| "learning_rate": 7.059512483803904e-06, |
| "epoch": 2.0653061224489795, |
| "step": 760 |
| }, |
| { |
| "loss": 0.16438820362091064, |
| "grad_norm": 5.78125, |
| "learning_rate": 6.326345702055698e-06, |
| "epoch": 2.1197278911564625, |
| "step": 780 |
| }, |
| { |
| "loss": 0.3438990592956543, |
| "grad_norm": 5.6875, |
| "learning_rate": 5.623078803519595e-06, |
| "epoch": 2.1741496598639456, |
| "step": 800 |
| }, |
| { |
| "loss": 0.21838486194610596, |
| "grad_norm": 4.8125, |
| "learning_rate": 4.952136094884666e-06, |
| "epoch": 2.2285714285714286, |
| "step": 820 |
| }, |
| { |
| "loss": 0.2150651216506958, |
| "grad_norm": 6.75, |
| "learning_rate": 4.315830454661059e-06, |
| "epoch": 2.2829931972789117, |
| "step": 840 |
| }, |
| { |
| "loss": 0.34454209804534913, |
| "grad_norm": 6.125, |
| "learning_rate": 3.7163553602086496e-06, |
| "epoch": 2.3374149659863948, |
| "step": 860 |
| }, |
| { |
| "loss": 0.14302738904953002, |
| "grad_norm": 4.8125, |
| "learning_rate": 3.1557773263661605e-06, |
| "epoch": 2.3918367346938774, |
| "step": 880 |
| }, |
| { |
| "loss": 0.32184672355651855, |
| "grad_norm": 6.03125, |
| "learning_rate": 2.6360287817464257e-06, |
| "epoch": 2.4462585034013604, |
| "step": 900 |
| }, |
| { |
| "loss": 0.1849319100379944, |
| "grad_norm": 6.15625, |
| "learning_rate": 2.1589014072546294e-06, |
| "epoch": 2.5006802721088435, |
| "step": 920 |
| }, |
| { |
| "loss": 0.20881271362304688, |
| "grad_norm": 6.71875, |
| "learning_rate": 1.7260399597930592e-06, |
| "epoch": 2.5551020408163265, |
| "step": 940 |
| }, |
| { |
| "loss": 0.31119983196258544, |
| "grad_norm": 7.0625, |
| "learning_rate": 1.3389366024433347e-06, |
| "epoch": 2.6095238095238096, |
| "step": 960 |
| }, |
| { |
| "loss": 0.1483125329017639, |
| "grad_norm": 4.1875, |
| "learning_rate": 9.989257606711437e-07, |
| "epoch": 2.6639455782312926, |
| "step": 980 |
| }, |
| { |
| "loss": 0.3087357997894287, |
| "grad_norm": 7.09375, |
| "learning_rate": 7.071795222852296e-07, |
| "epoch": 2.7183673469387752, |
| "step": 1000 |
| }, |
| { |
| "loss": 0.19563177824020386, |
| "grad_norm": 4.96875, |
| "learning_rate": 4.6470359700789e-07, |
| "epoch": 2.7727891156462583, |
| "step": 1020 |
| }, |
| { |
| "loss": 0.1930193543434143, |
| "grad_norm": 6.15625, |
| "learning_rate": 2.7233384958522675e-07, |
| "epoch": 2.8272108843537413, |
| "step": 1040 |
| }, |
| { |
| "loss": 0.29953775405883787, |
| "grad_norm": 6.59375, |
| "learning_rate": 1.3073341838821028e-07, |
| "epoch": 2.8816326530612244, |
| "step": 1060 |
| }, |
| { |
| "loss": 0.15995726585388184, |
| "grad_norm": 5.40625, |
| "learning_rate": 4.039042943733251e-08, |
| "epoch": 2.9360544217687075, |
| "step": 1080 |
| }, |
| { |
| "loss": 0.20271103382110595, |
| "grad_norm": 5.5, |
| "learning_rate": 1.616313731091501e-09, |
| "epoch": 2.9904761904761905, |
| "step": 1100 |
| }, |
| { |
| "eval_loss": 0.6698360443115234, |
| "eval_runtime": 2.3865, |
| "eval_samples_per_second": 273.207, |
| "eval_steps_per_second": 8.8, |
| "epoch": 3.0, |
| "step": 1104 |
| }, |
| { |
| "train_runtime": 416.811, |
| "train_samples_per_second": 84.614, |
| "train_steps_per_second": 2.649, |
| "total_flos": 5049728172804096.0, |
| "train_loss": 0.5160034051623897, |
| "epoch": 3.0, |
| "step": 1104 |
| }, |
| { |
| "eval_loss": 0.6445356011390686, |
| "eval_runtime": 2.2801, |
| "eval_samples_per_second": 285.956, |
| "eval_steps_per_second": 9.21, |
| "epoch": 3.0, |
| "step": 1104 |
| } |
| ], |
| "runtime": { |
| "torch_version": "2.11.0+cu128", |
| "transformers_version": "5.17.0", |
| "cuda_available": true, |
| "dtype": "bfloat16", |
| "attn_implementation": "sdpa", |
| "gpu_name": "NVIDIA GeForce RTX 5060 Ti", |
| "gpu_total_memory_gb": 15.9, |
| "gpu_capability": "12.0" |
| } |
| } |
| } |
