| { |
| "release": "hns-b300-training-seeds-20260913", |
| "repo_id": "tianzl66/Qwen3-8B-Magicoder-50K-LoRA-E1-Seed44", |
| "base": "Qwen3-8B", |
| "train_task": "magicoder", |
| "training_seed": 44, |
| "requested_run_args": { |
| "base_model": "<LOCAL_PATH>/Qwen3-8B", |
| "task": "magicoder", |
| "peft_method": "lora", |
| "output_dir": "<LOCAL_PATH>/magicoder", |
| "dataset_path": "<LOCAL_PATH>/magicoder-train.parquet", |
| "train_profile": "none", |
| "force_max_steps": false, |
| "max_steps": null, |
| "num_train_epochs": 1.0, |
| "stop_at_step": null, |
| "stop_at_epoch": null, |
| "resume_from_checkpoint": null, |
| "per_device_train_batch_size": 16, |
| "gradient_accumulation_steps": 2, |
| "global_train_batch_size": 32, |
| "lr": 2e-05, |
| "warmup_ratio": 0.05, |
| "weight_decay": 0.0, |
| "min_lr_ratio": null, |
| "lr_scheduler_type": "cosine", |
| "adam_beta1": 0.9, |
| "adam_beta2": 0.999, |
| "grad_clip": 1.0, |
| "max_seq_len": 4096, |
| "seed": 44, |
| "save_strategy": "epoch", |
| "save_steps": 500, |
| "save_total_limit": 1, |
| "logging_steps": 25, |
| "max_train_samples": 50000, |
| "dataset_seed": 42, |
| "bf16": true, |
| "fp16": false, |
| "gradient_checkpointing": true, |
| "group_by_length": false, |
| "pad_to_multiple_of": 8, |
| "dataloader_num_workers": 0, |
| "optim": null, |
| "use_qlora": false, |
| "sft_format": "chat", |
| "chat_template_mode": "non_thinking", |
| "target_modules": "all", |
| "r": 16, |
| "lora_alpha": 32, |
| "lora_dropout": 0.05, |
| "pissa_init_mode": "pissa", |
| "init_r": 32, |
| "target_r": 16, |
| "loraplus_lr_ratio": 20.0, |
| "loraplus_lr_embedding": null |
| }, |
| "effective_training_args": { |
| "output_dir": "<LOCAL_PATH>/magicoder", |
| "per_device_train_batch_size": 16, |
| "num_train_epochs": 1.0, |
| "max_steps": -1, |
| "learning_rate": 2e-05, |
| "lr_scheduler_type": "cosine", |
| "lr_scheduler_kwargs": null, |
| "warmup_steps": 0, |
| "optim": "adamw_torch_fused", |
| "optim_args": null, |
| "weight_decay": 0.0, |
| "adam_beta1": 0.9, |
| "adam_beta2": 0.999, |
| "adam_epsilon": 1e-08, |
| "optim_target_modules": null, |
| "gradient_accumulation_steps": 2, |
| "average_tokens_across_devices": true, |
| "max_grad_norm": 1.0, |
| "label_smoothing_factor": 0.0, |
| "bf16": true, |
| "fp16": false, |
| "bf16_full_eval": false, |
| "fp16_full_eval": false, |
| "tf32": null, |
| "gradient_checkpointing": true, |
| "gradient_checkpointing_kwargs": null, |
| "torch_compile": false, |
| "torch_compile_backend": null, |
| "torch_compile_mode": null, |
| "use_liger_kernel": false, |
| "liger_kernel_config": null, |
| "use_cache": false, |
| "neftune_noise_alpha": null, |
| "torch_empty_cache_steps": null, |
| "auto_find_batch_size": false, |
| "logging_strategy": "steps", |
| "logging_steps": 25, |
| "logging_first_step": false, |
| "log_on_each_node": true, |
| "logging_nan_inf_filter": true, |
| "include_num_input_tokens_seen": "no", |
| "log_level": "passive", |
| "log_level_replica": "warning", |
| "disable_tqdm": false, |
| "report_to": [], |
| "run_name": null, |
| "project": "huggingface", |
| "trackio_space_id": null, |
| "trackio_bucket_id": null, |
| "trackio_static_space_id": null, |
| "eval_strategy": "no", |
| "eval_steps": null, |
| "eval_delay": 0, |
| "per_device_eval_batch_size": 8, |
| "prediction_loss_only": false, |
| "eval_on_start": false, |
| "eval_do_concat_batches": true, |
| "eval_use_gather_object": false, |
| "eval_accumulation_steps": null, |
| "include_for_metrics": [], |
| "batch_eval_metrics": false, |
| "save_only_model": false, |
| "save_strategy": "epoch", |
| "save_steps": 500, |
| "save_on_each_node": false, |
| "save_total_limit": 1, |
| "enable_jit_checkpoint": false, |
| "push_to_hub": false, |
| "hub_token": "<REDACTED>", |
| "hub_private_repo": null, |
| "hub_model_id": null, |
| "hub_strategy": "every_save", |
| "hub_always_push": false, |
| "hub_revision": null, |
| "load_best_model_at_end": false, |
| "metric_for_best_model": null, |
| "greater_is_better": null, |
| "ignore_data_skip": false, |
| "restore_callback_states_from_checkpoint": false, |
| "full_determinism": false, |
| "seed": 44, |
| "data_seed": 44, |
| "use_cpu": false, |
| "accelerator_config": { |
| "split_batches": false, |
| "dispatch_batches": null, |
| "even_batches": true, |
| "use_seedable_sampler": true, |
| "non_blocking": false, |
| "gradient_accumulation_kwargs": null |
| }, |
| "parallelism_config": null, |
| "dataloader_drop_last": false, |
| "dataloader_num_workers": 0, |
| "dataloader_pin_memory": true, |
| "dataloader_persistent_workers": false, |
| "dataloader_prefetch_factor": null, |
| "dataloader_multiprocessing_context": null, |
| "dataloader_in_order": true, |
| "remove_unused_columns": false, |
| "label_names": null, |
| "train_sampling_strategy": "random", |
| "length_column_name": "length", |
| "ddp_find_unused_parameters": false, |
| "ddp_bucket_cap_mb": null, |
| "ddp_broadcast_buffers": null, |
| "ddp_static_graph": null, |
| "ddp_backend": null, |
| "ddp_timeout": 1800, |
| "fsdp": null, |
| "fsdp_config": null, |
| "deepspeed": null, |
| "debug": [], |
| "skip_memory_metrics": true, |
| "do_train": false, |
| "do_eval": false, |
| "do_predict": false, |
| "resume_from_checkpoint": null, |
| "local_rank": -1 |
| }, |
| "run_config": { |
| "base_model": "<LOCAL_PATH>/Qwen3-8B", |
| "task": "magicoder", |
| "peft_method": "lora", |
| "train_profile": "none", |
| "num_train_epochs": 1.0, |
| "max_steps": null, |
| "stop_at_step": null, |
| "stop_at_epoch": null, |
| "resume_from_checkpoint": null, |
| "training_budget": "epochs", |
| "per_device_train_batch_size": 16, |
| "gradient_accumulation_steps": 2, |
| "global_train_batch_size": 32, |
| "world_size": 1, |
| "effective_global_batch_size": 32, |
| "steps_per_epoch": 1563, |
| "total_steps": 1563, |
| "lr": 2e-05, |
| "warmup_ratio": 0.05, |
| "weight_decay": 0.0, |
| "lr_scheduler_type": "cosine", |
| "min_lr_ratio": null, |
| "max_seq_len": 4096, |
| "dataset_size": 50000, |
| "dataset_path": "<LOCAL_PATH>/magicoder-train.parquet", |
| "max_train_samples": 50000, |
| "dataset_seed": 42, |
| "sft_format": "chat", |
| "chat_template_mode": "non_thinking", |
| "save_strategy": "epoch", |
| "save_steps": 500, |
| "save_total_limit": 1, |
| "logging_steps": 25, |
| "adalora_schedule": null |
| }, |
| "actual_training_examples": 49936, |
| "trainer_state": { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 500, |
| "global_step": 1561, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.016020506247997435, |
| "grad_norm": 0.29081395268440247, |
| "learning_rate": 1.9988337222482776e-05, |
| "loss": 1.1990239715576172, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.03204101249599487, |
| "grad_norm": 0.11618245393037796, |
| "learning_rate": 1.9951414786166656e-05, |
| "loss": 0.9829273986816406, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.04806151874399231, |
| "grad_norm": 0.10595086961984634, |
| "learning_rate": 1.988930588781978e-05, |
| "loss": 0.92435546875, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.06408202499198974, |
| "grad_norm": 0.09951659291982651, |
| "learning_rate": 1.9802167721513908e-05, |
| "loss": 0.9162257385253906, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.08010253123998719, |
| "grad_norm": 0.08442762494087219, |
| "learning_rate": 1.9690220828967406e-05, |
| "loss": 0.8908739471435547, |
| "step": 125 |
| }, |
| { |
| "epoch": 0.09612303748798462, |
| "grad_norm": 0.10172899067401886, |
| "learning_rate": 1.9553748541366756e-05, |
| "loss": 0.9406523895263672, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.11214354373598205, |
| "grad_norm": 0.11054546386003494, |
| "learning_rate": 1.9393096262271533e-05, |
| "loss": 0.9146512603759765, |
| "step": 175 |
| }, |
| { |
| "epoch": 0.12816404998397948, |
| "grad_norm": 0.10347191989421844, |
| "learning_rate": 1.9208670593417723e-05, |
| "loss": 0.9219544219970703, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.14418455623197693, |
| "grad_norm": 0.10463545471429825, |
| "learning_rate": 1.9000938305631975e-05, |
| "loss": 0.9444712829589844, |
| "step": 225 |
| }, |
| { |
| "epoch": 0.16020506247997437, |
| "grad_norm": 0.10991481691598892, |
| "learning_rate": 1.877042515746132e-05, |
| "loss": 0.9139762115478516, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.1762255687279718, |
| "grad_norm": 0.12124437093734741, |
| "learning_rate": 1.8517714564508342e-05, |
| "loss": 0.9185218048095704, |
| "step": 275 |
| }, |
| { |
| "epoch": 0.19224607497596924, |
| "grad_norm": 0.10786885023117065, |
| "learning_rate": 1.824344612283962e-05, |
| "loss": 0.9175537872314453, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.20826658122396668, |
| "grad_norm": 0.11486810445785522, |
| "learning_rate": 1.7948313990204654e-05, |
| "loss": 0.8929530334472656, |
| "step": 325 |
| }, |
| { |
| "epoch": 0.2242870874719641, |
| "grad_norm": 0.11425229907035828, |
| "learning_rate": 1.7633065129162282e-05, |
| "loss": 0.8928473663330078, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.24030759371996155, |
| "grad_norm": 0.11112677305936813, |
| "learning_rate": 1.729849741656112e-05, |
| "loss": 0.9173651123046875, |
| "step": 375 |
| }, |
| { |
| "epoch": 0.25632809996795897, |
| "grad_norm": 0.1455482393503189, |
| "learning_rate": 1.694545762415887e-05, |
| "loss": 0.9193742370605469, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.2723486062159564, |
| "grad_norm": 0.14621497690677643, |
| "learning_rate": 1.657483927549141e-05, |
| "loss": 0.8958631134033204, |
| "step": 425 |
| }, |
| { |
| "epoch": 0.28836911246395386, |
| "grad_norm": 0.15076446533203125, |
| "learning_rate": 1.6187580384415785e-05, |
| "loss": 0.9202049255371094, |
| "step": 450 |
| }, |
| { |
| "epoch": 0.3043896187119513, |
| "grad_norm": 0.13701656460762024, |
| "learning_rate": 1.5784661081050744e-05, |
| "loss": 0.9259297943115234, |
| "step": 475 |
| }, |
| { |
| "epoch": 0.32041012495994875, |
| "grad_norm": 0.14176012575626373, |
| "learning_rate": 1.536710113112345e-05, |
| "loss": 0.9286505126953125, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.3364306312079462, |
| "grad_norm": 0.1571187525987625, |
| "learning_rate": 1.4935957355000695e-05, |
| "loss": 0.9105192565917969, |
| "step": 525 |
| }, |
| { |
| "epoch": 0.3524511374559436, |
| "grad_norm": 0.13166415691375732, |
| "learning_rate": 1.4492320952936956e-05, |
| "loss": 0.9180181121826172, |
| "step": 550 |
| }, |
| { |
| "epoch": 0.36847164370394103, |
| "grad_norm": 0.1260545551776886, |
| "learning_rate": 1.403731474330893e-05, |
| "loss": 0.8934297943115235, |
| "step": 575 |
| }, |
| { |
| "epoch": 0.3844921499519385, |
| "grad_norm": 0.15511398017406464, |
| "learning_rate": 1.3572090320826396e-05, |
| "loss": 0.9190473175048828, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.4005126561999359, |
| "grad_norm": 0.1460423320531845, |
| "learning_rate": 1.3097825141911824e-05, |
| "loss": 0.9066439056396485, |
| "step": 625 |
| }, |
| { |
| "epoch": 0.41653316244793337, |
| "grad_norm": 0.17855304479599, |
| "learning_rate": 1.261571954462547e-05, |
| "loss": 0.899425277709961, |
| "step": 650 |
| }, |
| { |
| "epoch": 0.4325536686959308, |
| "grad_norm": 0.16846759617328644, |
| "learning_rate": 1.2126993710678361e-05, |
| "loss": 0.9050975799560547, |
| "step": 675 |
| }, |
| { |
| "epoch": 0.4485741749439282, |
| "grad_norm": 0.16906635463237762, |
| "learning_rate": 1.1632884577222106e-05, |
| "loss": 0.9127249145507812, |
| "step": 700 |
| }, |
| { |
| "epoch": 0.46459468119192565, |
| "grad_norm": 0.15867382287979126, |
| "learning_rate": 1.1134642706231687e-05, |
| "loss": 0.9023185729980469, |
| "step": 725 |
| }, |
| { |
| "epoch": 0.4806151874399231, |
| "grad_norm": 0.16034585237503052, |
| "learning_rate": 1.0633529119404571e-05, |
| "loss": 0.9134428405761719, |
| "step": 750 |
| }, |
| { |
| "epoch": 0.49663569368792054, |
| "grad_norm": 0.16358235478401184, |
| "learning_rate": 1.013081210658687e-05, |
| "loss": 0.8995558166503906, |
| "step": 775 |
| }, |
| { |
| "epoch": 0.5126561999359179, |
| "grad_norm": 0.15758606791496277, |
| "learning_rate": 9.627764015804225e-06, |
| "loss": 0.8870352172851562, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.5286767061839154, |
| "grad_norm": 0.16830310225486755, |
| "learning_rate": 9.125658033021683e-06, |
| "loss": 0.8971255493164062, |
| "step": 825 |
| }, |
| { |
| "epoch": 0.5446972124319128, |
| "grad_norm": 0.16267818212509155, |
| "learning_rate": 8.6257649597828e-06, |
| "loss": 0.9000907135009766, |
| "step": 850 |
| }, |
| { |
| "epoch": 0.5607177186799103, |
| "grad_norm": 0.15891553461551666, |
| "learning_rate": 8.129349996883551e-06, |
| "loss": 0.899490966796875, |
| "step": 875 |
| }, |
| { |
| "epoch": 0.5767382249279077, |
| "grad_norm": 0.14320583641529083, |
| "learning_rate": 7.637669542221446e-06, |
| "loss": 0.8845912933349609, |
| "step": 900 |
| }, |
| { |
| "epoch": 0.5927587311759052, |
| "grad_norm": 0.16313546895980835, |
| "learning_rate": 7.1519680109242486e-06, |
| "loss": 0.9202222442626953, |
| "step": 925 |
| }, |
| { |
| "epoch": 0.6087792374239026, |
| "grad_norm": 0.17441782355308533, |
| "learning_rate": 6.673474685806436e-06, |
| "loss": 0.9076329803466797, |
| "step": 950 |
| }, |
| { |
| "epoch": 0.6247997436719, |
| "grad_norm": 0.14890457689762115, |
| "learning_rate": 6.2034006061246295e-06, |
| "loss": 0.9191471862792969, |
| "step": 975 |
| }, |
| { |
| "epoch": 0.6408202499198975, |
| "grad_norm": 0.17238198220729828, |
| "learning_rate": 5.742935502506485e-06, |
| "loss": 0.9056331634521484, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.656840756167895, |
| "grad_norm": 0.1785092055797577, |
| "learning_rate": 5.293244785810452e-06, |
| "loss": 0.9191907501220703, |
| "step": 1025 |
| }, |
| { |
| "epoch": 0.6728612624158924, |
| "grad_norm": 0.15417782962322235, |
| "learning_rate": 4.855466597537515e-06, |
| "loss": 0.9085941314697266, |
| "step": 1050 |
| }, |
| { |
| "epoch": 0.6888817686638897, |
| "grad_norm": 0.1511709988117218, |
| "learning_rate": 4.430708929260105e-06, |
| "loss": 0.9095938110351562, |
| "step": 1075 |
| }, |
| { |
| "epoch": 0.7049022749118872, |
| "grad_norm": 0.1562037169933319, |
| "learning_rate": 4.0200468183587556e-06, |
| "loss": 0.8718026733398437, |
| "step": 1100 |
| }, |
| { |
| "epoch": 0.7209227811598846, |
| "grad_norm": 0.16901475191116333, |
| "learning_rate": 3.624519627163946e-06, |
| "loss": 0.8942552947998047, |
| "step": 1125 |
| }, |
| { |
| "epoch": 0.7369432874078821, |
| "grad_norm": 0.15361268818378448, |
| "learning_rate": 3.24512841238944e-06, |
| "loss": 0.923448715209961, |
| "step": 1150 |
| }, |
| { |
| "epoch": 0.7529637936558795, |
| "grad_norm": 0.166425421833992, |
| "learning_rate": 2.8828333915149675e-06, |
| "loss": 0.9021080017089844, |
| "step": 1175 |
| }, |
| { |
| "epoch": 0.768984299903877, |
| "grad_norm": 0.17839516699314117, |
| "learning_rate": 2.5385515125306683e-06, |
| "loss": 0.9276787567138672, |
| "step": 1200 |
| }, |
| { |
| "epoch": 0.7850048061518744, |
| "grad_norm": 0.17206133902072906, |
| "learning_rate": 2.213154133194122e-06, |
| "loss": 0.9214431762695312, |
| "step": 1225 |
| }, |
| { |
| "epoch": 0.8010253123998718, |
| "grad_norm": 0.1896800845861435, |
| "learning_rate": 1.907464815673702e-06, |
| "loss": 0.9126302337646485, |
| "step": 1250 |
| }, |
| { |
| "epoch": 0.8170458186478693, |
| "grad_norm": 0.1757972687482834, |
| "learning_rate": 1.622257242159756e-06, |
| "loss": 0.9005342102050782, |
| "step": 1275 |
| }, |
| { |
| "epoch": 0.8330663248958667, |
| "grad_norm": 0.1621798872947693, |
| "learning_rate": 1.3582532567192509e-06, |
| "loss": 0.8823390960693359, |
| "step": 1300 |
| }, |
| { |
| "epoch": 0.8490868311438642, |
| "grad_norm": 0.15191422402858734, |
| "learning_rate": 1.1161210383496479e-06, |
| "loss": 0.9226659393310547, |
| "step": 1325 |
| }, |
| { |
| "epoch": 0.8651073373918616, |
| "grad_norm": 0.18351206183433533, |
| "learning_rate": 8.964734098561001e-07, |
| "loss": 0.9057015228271484, |
| "step": 1350 |
| }, |
| { |
| "epoch": 0.881127843639859, |
| "grad_norm": 0.16578508913516998, |
| "learning_rate": 6.998662868319139e-07, |
| "loss": 0.8983650970458984, |
| "step": 1375 |
| }, |
| { |
| "epoch": 0.8971483498878564, |
| "grad_norm": 0.17020930349826813, |
| "learning_rate": 5.267972706679991e-07, |
| "loss": 0.9050147247314453, |
| "step": 1400 |
| }, |
| { |
| "epoch": 0.9131688561358539, |
| "grad_norm": 0.17416594922542572, |
| "learning_rate": 3.777043891521559e-07, |
| "loss": 0.8866185760498047, |
| "step": 1425 |
| }, |
| { |
| "epoch": 0.9291893623838513, |
| "grad_norm": 0.16963180899620056, |
| "learning_rate": 2.529649878457985e-07, |
| "loss": 0.9323723602294922, |
| "step": 1450 |
| }, |
| { |
| "epoch": 0.9452098686318487, |
| "grad_norm": 0.18463164567947388, |
| "learning_rate": 1.528947750439036e-07, |
| "loss": 0.9038640594482422, |
| "step": 1475 |
| }, |
| { |
| "epoch": 0.9612303748798462, |
| "grad_norm": 0.1755848526954651, |
| "learning_rate": 7.774702273535938e-08, |
| "loss": 0.904787826538086, |
| "step": 1500 |
| }, |
| { |
| "epoch": 0.9772508811278436, |
| "grad_norm": 0.1582230031490326, |
| "learning_rate": 2.77119255860403e-08, |
| "loss": 0.8763291168212891, |
| "step": 1525 |
| }, |
| { |
| "epoch": 0.9932713873758411, |
| "grad_norm": 0.20413701236248016, |
| "learning_rate": 2.916119566973574e-09, |
| "loss": 0.920826416015625, |
| "step": 1550 |
| } |
| ], |
| "logging_steps": 25, |
| "max_steps": 1561, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 3.711778068942029e+18, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| }, |
| "adapter_config": { |
| "alora_invocation_tokens": null, |
| "alpha_pattern": {}, |
| "arrow_config": null, |
| "auto_mapping": null, |
| "base_model_name_or_path": "<LOCAL_PATH>/Qwen3-8B", |
| "bias": "none", |
| "corda_config": null, |
| "ensure_weight_tying": false, |
| "eva_config": null, |
| "exclude_modules": null, |
| "fan_in_fan_out": false, |
| "inference_mode": true, |
| "init_lora_weights": true, |
| "layer_replication": null, |
| "layers_pattern": null, |
| "layers_to_transform": null, |
| "loftq_config": {}, |
| "lora_alpha": 32, |
| "lora_bias": false, |
| "lora_dropout": 0.05, |
| "lora_ga_config": null, |
| "megatron_config": null, |
| "megatron_core": "megatron.core", |
| "modules_to_save": null, |
| "monteclora_config": null, |
| "peft_type": "LORA", |
| "peft_version": "0.20.0", |
| "qalora_group_size": 16, |
| "r": 16, |
| "rank_pattern": {}, |
| "revision": null, |
| "target_modules": [ |
| "up_proj", |
| "q_proj", |
| "k_proj", |
| "gate_proj", |
| "o_proj", |
| "v_proj", |
| "down_proj" |
| ], |
| "target_parameters": null, |
| "task_type": "CAUSAL_LM", |
| "trainable_token_indices": "<REDACTED>", |
| "use_bdlora": null, |
| "use_dora": false, |
| "use_qalora": false, |
| "use_rslora": false, |
| "velora_config": null |
| }, |
| "adapter_config_original_sha256": "09f5203f6929787edb04234aecdaa82044cf66c24cb5a39b7eed4598d87eebe5", |
| "adapter_weights_sha256": "eb3899888d043eb204ac10f9557344a1fabc0bb4d4e82965ae6a615047243932", |
| "base_provenance": { |
| "model_id": "Qwen/Qwen3-8B", |
| "download_metadata_revisions": { |
| "model-00001-of-00005.safetensors": "b968826d9c46dd6066d109eabc6255188de91218", |
| "generation_config.json": "b968826d9c46dd6066d109eabc6255188de91218", |
| ".gitattributes": "b968826d9c46dd6066d109eabc6255188de91218", |
| "model-00004-of-00005.safetensors": "b968826d9c46dd6066d109eabc6255188de91218", |
| "README.md": "b968826d9c46dd6066d109eabc6255188de91218", |
| "config.json": "b968826d9c46dd6066d109eabc6255188de91218", |
| "merges.txt": "b968826d9c46dd6066d109eabc6255188de91218", |
| "tokenizer_config.json": "b968826d9c46dd6066d109eabc6255188de91218", |
| "model-00002-of-00005.safetensors": "b968826d9c46dd6066d109eabc6255188de91218", |
| "model-00003-of-00005.safetensors": "b968826d9c46dd6066d109eabc6255188de91218", |
| "model.safetensors.index.json": "b968826d9c46dd6066d109eabc6255188de91218", |
| "tokenizer.json": "b968826d9c46dd6066d109eabc6255188de91218", |
| "LICENSE": "b968826d9c46dd6066d109eabc6255188de91218", |
| "vocab.json": "b968826d9c46dd6066d109eabc6255188de91218", |
| "model-00005-of-00005.safetensors": "b968826d9c46dd6066d109eabc6255188de91218" |
| }, |
| "revision": "b968826d9c46dd6066d109eabc6255188de91218", |
| "files_sha256": { |
| "model-00002-of-00005.safetensors": "5991236cea6fe21f3d43cab0f0e84448734fbbe0789816202989f2ddc9d18282", |
| "model-00005-of-00005.safetensors": "20c2d6366ab85c90786ccdd829cd2b9e7d30ef3b2ebbb998280e7e4014b542ff", |
| "tokenizer_config.json": "d5d09f07b48c3086c508b30d1c9114bd1189145b74e982a265350c923acd8101", |
| "model-00003-of-00005.safetensors": "c5185c4794be2d8a9784d5753c9922db38df478ce11f9ed0b415b7304d896836", |
| "model.safetensors.index.json": "f9fdbcb91c23971c13ec5d5f2573d2349e8f61f2f049371ec699281748fdb1bc", |
| "tokenizer.json": "aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4", |
| "config.json": "f7c4eadfbbf522470667b797a3c89be2524832d2d599797248dc304fff447c30", |
| "model-00004-of-00005.safetensors": "b5ee7de71fbf17db3d5704e0c8f2bc7d005ca9e1d7ca2aeb19827b0cfcaa917a", |
| "model-00001-of-00005.safetensors": "31d6a825ae35f11fb85b195b4c42c146c051e446433125a215336abdf95cbf5f" |
| }, |
| "revision_note": "Revision is taken from local download metadata, not current Hub main." |
| }, |
| "dataset": { |
| "dataset_id": "ise-uiuc/Magicoder-Evol-Instruct-110K", |
| "filename": "magicoder-train.parquet", |
| "file_sha256": "ff1dda789a725a9b8840f63aa9956bcff397b8dc4311cfc98aaa2c11ba0ed0ca", |
| "source_rows": 111183, |
| "upstream_revision": null, |
| "selected_index_semantics": "zero-based original parquet row index, before truncation filtering" |
| }, |
| "inference": { |
| "vllm_batch_invariant": "1", |
| "gpu_memory_utilization": 0.94, |
| "max_num_seqs": 1024, |
| "max_num_batched_tokens": 65536, |
| "adapter_block_size": 11, |
| "seed": 42 |
| }, |
| "evaluation_task": { |
| "benchmark": "HumanEval", |
| "dataset": "<LOCAL_PATH>/humaneval-test.parquet", |
| "samples": 164, |
| "primary_metric": "pass@1", |
| "max_new_tokens": 512 |
| }, |
| "historical_recipe_equivalence_verified": false, |
| "warmup_requested_but_effective_zero": true, |
| "training_python_version": "not separately recorded", |
| "publication_python_version": "3.12.3 (main, Nov 6 2024, 18:32:19) [GCC 13.2.0]", |
| "source_provenance": "publication-time snapshot; no clean training-time Git commit recorded", |
| "prepared_at_utc": "2026-09-13T08:13:00.991209+00:00", |
| "publication_eval_environment_observation": { |
| "vllm": "0.25.1+cu129", |
| "torch": "2.11.0+cu128", |
| "transformers": "5.16.1", |
| "peft": "0.20.0", |
| "datasets": "5.0.1", |
| "numpy": "2.3.5", |
| "human-eval": "1.0.3" |
| }, |
| "peer_source_adapters": [ |
| { |
| "repo_id": "tianzl66/Qwen3-8B-Magicoder-50K-LoRA-E1-Seed44", |
| "task": "magicoder", |
| "weights_sha256": "eb3899888d043eb204ac10f9557344a1fabc0bb4d4e82965ae6a615047243932" |
| }, |
| { |
| "repo_id": "tianzl66/Qwen3-8B-MetaMathQA-50K-LoRA-Seed44", |
| "task": "metamath", |
| "weights_sha256": "f6ac86577814d21d2245e9eb2e0c7b02e45194455ff8245726e1cc43789e29c2" |
| }, |
| { |
| "repo_id": "tianzl66/Qwen3-8B-InstructionFollowing-LoRA-Seed44", |
| "task": "tulu", |
| "weights_sha256": "8c26a920aada7d7a17dfc24e86f07350e3bb3d561f4eaf9c60292d55e127d99d" |
| } |
| ], |
| "compilation_cache_note": "Disabled, per-job cache root, short IPC temp path" |
| } |
|
|
