| { |
| "train_loop_config": { |
| "_dataset": "xsum", |
| "_scenario": "clamp_sft_ref", |
| "a2g_norm": true, |
| "base_path": "/common/home/users/m/mq.nguyen.2023/testcode/SAC_LM/module9_clmv3", |
| "beta_coef": "0.1", |
| "block_size": 1024, |
| "buffer_max_size": 20000, |
| "causal_model": true, |
| "checkpoint_interval": "2_000", |
| "clamp_ref": true, |
| "clamp_update": false, |
| "config_name": null, |
| "constraint_type": "kl", |
| "cpu_per_worker": 6, |
| "dataset_config_name": null, |
| "dataset_name": "nbtpj/summ_ds_train", |
| "effective_batch_size": 16, |
| "ent_coef": 0.0001, |
| "epsilon": 0.2, |
| "eval_interval": "2_000", |
| "freeze_role2": true, |
| "gamma": 0.95, |
| "gpu_per_worker": 1, |
| "grad_norm": 0.5, |
| "gradient_accumulation_steps": 1, |
| "gradient_checkpoint": false, |
| "group_relative_norm": true, |
| "inference_config": { |
| "do_sample": true, |
| "max_new_tokens": 40, |
| "min_new_tokens": 15, |
| "temperature": 0.0 |
| }, |
| "keep_eval_size": false, |
| "label_col": "summary", |
| "learning_rate": 3e-07, |
| "lm_fraction": -1.0, |
| "lm_w": 0.0, |
| "log_interval": "5m", |
| "log_rollout_txt": true, |
| "lora": false, |
| "lr_scheduler_type": "constant", |
| "max_train_rollouts": 100000, |
| "max_train_steps": 100000, |
| "mini_epoch": 2, |
| "mixed_precision": "bf16", |
| "model_name_or_path": "gpt2", |
| "model_type": null, |
| "n_augment": 0, |
| "n_generate": 4, |
| "need_attn_mask": true, |
| "no_is_correction": false, |
| "num_warmup_steps": 200, |
| "only_train_role1": true, |
| "per_device_eval_batch_size": 16, |
| "per_device_query_rollout_batch_size": 32, |
| "per_device_train_batch_size": 16, |
| "pretrained_role2_name_or_path": "gpt2", |
| "prompt_0": "{text}", |
| "prompt_1": "{text}\nTL;DR: ", |
| "prompt_2": "Given the text: {role1_output}\nReconstruct the summarized text to the detailed:", |
| "prompt_eval": "{text}\nTL;DR:", |
| "push_to_hub": null, |
| "ref_role1_name_or_path": "nbtpj/summ_gpt2_tldr_xsum", |
| "ref_role2_name_or_path": "gpt2", |
| "rl_algo": "on_policy", |
| "rl_w": 1.0, |
| "rollout_config": { |
| "acc_scale": "log", |
| "accuracy_w": 1000.0, |
| "accuracy_w2": 0.01, |
| "len_pen": 1.0, |
| "len_pen2": 1.0, |
| "similarity_fn": "rouge", |
| "threshold": 0.002 |
| }, |
| "rollout_game": "baseline3v2", |
| "sample_config": { |
| "do_sample": true, |
| "min_new_tokens": 5, |
| "temperature": 1.0 |
| }, |
| "script": "/common/home/users/m/mq.nguyen.2023/testcode/SAC_LM/module9_clmv3/execute/role_ablation/role_ablation.py", |
| "seed": 0, |
| "test_clm": false, |
| "test_gen": true, |
| "test_glue": false, |
| "text_col": "text", |
| "text_template": "{text}\nTL;DR: {summary}", |
| "tokenizer_name": null, |
| "train_from_raw": true, |
| "train_split_name": "sim_with_one_golden__xsum_train", |
| "trunc_eval": 20000, |
| "trunc_evals": [ |
| "xsum___20000" |
| ], |
| "trust_remote_code": true, |
| "tune_metrics": [ |
| "xsum/rouge1___1.0", |
| "xsum/rouge2___2.0", |
| "xsum/bertscore_f1___0.25" |
| ], |
| "use_deepspeed": false, |
| "use_slow_tokenizer": false, |
| "vectorizer_path": "/common/home/users/m/mq.nguyen.2023/testcode/SAC_LM/module9_clmv3/vectorizer/wikitext103_tfidf_full.joblib", |
| "vllm_sleep": true, |
| "vllm_vram_ratio": 0.3, |
| "weight_decay": 1e-05, |
| "world_size": 1, |
| "zero_config": 2 |
| } |
| } |
