| { |
| "model_args": { |
| "model_name_or_path": "/sensei-fs-3/users/zichaol/models_shop/sft-Llama-3.2-1B-webshop-actonly/", |
| "instruct_tokenizer": null, |
| "trust_remote_code": false, |
| "padding_side": "right" |
| }, |
| "data_args": { |
| "data_path": "/home/colligo/agent/data/webshop_sft.json", |
| "eval_data_path": null, |
| "lazy_preprocess": false, |
| "n_data": null, |
| "action_only": true |
| }, |
| "training_args": { |
| "output_dir": "/sensei-fs-3/users/zichaol/models_shop/hsl-Llama-3.2-1B-webshop-hslw_0.5-full-brew-llamaRelabel-every4-h18-epc3-seed2026", |
| "overwrite_output_dir": false, |
| "do_train": false, |
| "do_eval": false, |
| "do_predict": false, |
| "eval_strategy": "no", |
| "prediction_loss_only": false, |
| "per_device_train_batch_size": 2, |
| "per_device_eval_batch_size": 4, |
| "per_gpu_train_batch_size": null, |
| "per_gpu_eval_batch_size": null, |
| "gradient_accumulation_steps": 2, |
| "eval_accumulation_steps": null, |
| "eval_delay": 0, |
| "torch_empty_cache_steps": null, |
| "learning_rate": 2e-05, |
| "weight_decay": 0.0, |
| "adam_beta1": 0.9, |
| "adam_beta2": 0.999, |
| "adam_epsilon": 1e-08, |
| "max_grad_norm": 1.0, |
| "num_train_epochs": 3.0, |
| "max_steps": -1, |
| "lr_scheduler_type": "cosine", |
| "lr_scheduler_kwargs": {}, |
| "warmup_ratio": 0.03, |
| "warmup_steps": 0, |
| "log_level": "passive", |
| "log_level_replica": "warning", |
| "log_on_each_node": true, |
| "logging_dir": "/sensei-fs-3/users/zichaol/models_shop/hsl-Llama-3.2-1B-webshop-hslw_0.5-full-brew-llamaRelabel-every4-h18-epc3-seed2026/runs/Nov18_21-12-40_pluto-prod-jkil-shop-2025-09-11-17-1-0", |
| "logging_strategy": "steps", |
| "logging_first_step": false, |
| "logging_steps": 5, |
| "logging_nan_inf_filter": true, |
| "save_strategy": "steps", |
| "save_steps": 8, |
| "save_total_limit": 2, |
| "save_safetensors": true, |
| "save_on_each_node": false, |
| "save_only_model": false, |
| "restore_callback_states_from_checkpoint": false, |
| "no_cuda": false, |
| "use_cpu": false, |
| "use_mps_device": false, |
| "seed": 2026, |
| "data_seed": null, |
| "jit_mode_eval": false, |
| "use_ipex": false, |
| "bf16": true, |
| "fp16": false, |
| "fp16_opt_level": "O1", |
| "half_precision_backend": "auto", |
| "bf16_full_eval": false, |
| "fp16_full_eval": false, |
| "tf32": true, |
| "local_rank": 1, |
| "ddp_backend": null, |
| "tpu_num_cores": null, |
| "tpu_metrics_debug": false, |
| "debug": [], |
| "dataloader_drop_last": false, |
| "eval_steps": null, |
| "dataloader_num_workers": 0, |
| "dataloader_prefetch_factor": null, |
| "past_index": -1, |
| "run_name": "/sensei-fs-3/users/zichaol/models_shop/hsl-Llama-3.2-1B-webshop-hslw_0.5-full-brew-llamaRelabel-every4-h18-epc3-seed2026", |
| "disable_tqdm": false, |
| "remove_unused_columns": true, |
| "label_names": null, |
| "load_best_model_at_end": false, |
| "metric_for_best_model": null, |
| "greater_is_better": null, |
| "ignore_data_skip": false, |
| "fsdp": [], |
| "fsdp_min_num_params": 0, |
| "fsdp_config": { |
| "min_num_params": 0, |
| "xla": false, |
| "xla_fsdp_v2": false, |
| "xla_fsdp_grad_ckpt": false |
| }, |
| "fsdp_transformer_layer_cls_to_wrap": null, |
| "accelerator_config": { |
| "split_batches": false, |
| "dispatch_batches": null, |
| "even_batches": true, |
| "use_seedable_sampler": true, |
| "non_blocking": false, |
| "gradient_accumulation_kwargs": null, |
| "use_configured_state": false |
| }, |
| "deepspeed": null, |
| "label_smoothing_factor": 0.0, |
| "optim": "adamw_torch", |
| "optim_args": null, |
| "adafactor": false, |
| "group_by_length": false, |
| "length_column_name": "length", |
| "report_to": [ |
| "wandb" |
| ], |
| "ddp_find_unused_parameters": null, |
| "ddp_bucket_cap_mb": null, |
| "ddp_broadcast_buffers": null, |
| "dataloader_pin_memory": true, |
| "dataloader_persistent_workers": false, |
| "skip_memory_metrics": true, |
| "use_legacy_prediction_loop": false, |
| "push_to_hub": false, |
| "resume_from_checkpoint": null, |
| "hub_model_id": null, |
| "hub_strategy": "every_save", |
| "hub_token": null, |
| "hub_private_repo": null, |
| "hub_always_push": false, |
| "hub_revision": null, |
| "gradient_checkpointing": true, |
| "gradient_checkpointing_kwargs": null, |
| "include_inputs_for_metrics": false, |
| "include_for_metrics": [], |
| "eval_do_concat_batches": true, |
| "fp16_backend": "auto", |
| "push_to_hub_model_id": null, |
| "push_to_hub_organization": null, |
| "push_to_hub_token": null, |
| "_n_gpu": 1, |
| "mp_parameters": "", |
| "auto_find_batch_size": false, |
| "full_determinism": false, |
| "torchdynamo": null, |
| "ray_scope": "last", |
| "ddp_timeout": 1800, |
| "torch_compile": false, |
| "torch_compile_backend": null, |
| "torch_compile_mode": null, |
| "include_tokens_per_second": false, |
| "include_num_input_tokens_seen": false, |
| "neftune_noise_alpha": null, |
| "optim_target_modules": null, |
| "batch_eval_metrics": false, |
| "eval_on_start": false, |
| "use_liger_kernel": false, |
| "liger_kernel_config": null, |
| "eval_use_gather_object": false, |
| "average_tokens_across_devices": false, |
| "cache_dir": null, |
| "model_max_length": 8096, |
| "use_replay": true, |
| "hsl_weight": 0.5, |
| "hsl_warmup_steps": 0, |
| "hsl_use_first": false, |
| "relabel_every": 4, |
| "hsl_sample_size": 18, |
| "hsl_collect_batch_size": 6, |
| "weight_replay_by_length": true, |
| "replay_temperature": 1.0, |
| "hsl_buffer_size": 100, |
| "relabel_class": "ShopBrew", |
| "relabel_api": "internal", |
| "task": "webshop", |
| "agent": null, |
| "env_config": "/home/colligo/agent/learn/eval_agent/configs/task/", |
| "reward_free": true |
| } |
| } |
