{ "saved_args": { "context": 7, "n_hidden": 512, "c_context": 384, "depth": 8, "kernel": 3, "learn_win": true, "win_lr": 0.0003, "linout_kernel": 3, "tokenizer": "pythia31m", "ctx_ema": "512,64,16,4,1", "ctx_read_norm": 1.0, "dec_tree_kernels": "3,3,3", "dec_width": 256, "bn_frozen": false, "bn_momentum": 0.1, "init": "zero", "reset_scale": 0.0, "continuous": "", "image_encoder": "resnet50", "audio_encoder": "logmel", "fifo3": true, "streams": 3, "dataset": "smolfwedu", "mix": "fineweb:1", "full_crops": 0.5, "imagine": null, "imagine_window": 32, "imagine_min": 10, "imagine_size": 256, "imagine_batch": 16, "image": null, "shards": 14, "shard_offset": 1, "streaming": false, "shuffle": true, "workers": 12, "batch": 250, "lr_max": 0.04, "lr_min": 0.0004, "lr_period": 20000, "schedule": "coswarm", "lr_final": 0.001, "decay_steps": 200000, "decay_start": null, "eval_at_start": true, "profile": 0, "bptt": 16, "lr_restart": false, "momentum": 0.0, "weight_decay": 0.0, "run_steps": 3840000, "seed": 2958979956, "device": "cuda", "load": "checkpoint/v485_v484_learnwin512_fw_bptt16.pt", "save": "checkpoint/v485_v484_learnwin512_fw_bptt16.pt", "checkpoint": 20000, "log": "log/exp.v485_v484_learnwin512_fw_bptt16", "monitor": 100, "gen_interval": 2000, "gen_score": "EleutherAI/pythia-70m", "prompt": "", "temperature": 1.0, "gen_images": 8, "gen_vis": false, "sample_vis": false, "eval_interval": 20000, "eval_corpora": "fineweb,qaipt", "eval_docs": 100, "eval_bands": "1024,8192", "eval_info": 100, "eval_gen": 50, "eval_gen_judge": "Qwen/Qwen2.5-1.5B", "eval_gen_prompt": 128, "eval_gen_len": 128, "eval_cloze": 400, "eval_pairs": 1000, "eval_hold": 100, "doc_log": 100, "doc_log_len": 384, "doc_keep": 10, "doc_log_file": null, "eval_recent": 20, "weight_ema": "", "use_ema": 0, "doc_score": null, "state_pca": 0, "state_pca_stride": 16, "doc_ablate": "", "step_tokens": 0, "doc_tokens": false, "eval_wp": 0, "eval_wp_len": 256, "eval_qa": 100, "eval_rare": 10, "eval_reach": 100, "eval_reach_period": 256, "generate": false, "n": 200, "free_run": 0, "eval_free": 10000, "free_rows": 8, "free_window": 2000, "free_chunk": 128, "free_save": null, "prompt_tune": 0, "prompt_tune_lr": 0.01, "prompt_tune_cap": "1", "prompt_tune_batch": 10, "prompt_warm": 256, "prompt_tune_save": null, "clock_hz": 25.0, "ctx_tau": "20.48,2.56,0.64,0.16", "vision_hz": 2.0, "max_lag": 2.0, "nul_weight": 1.0, "clip": 0.0, "loss_norm": "words", "inner_voice": false, "min_p": 0.009220976663785505, "caption_feed": 0.0, "text_feed": 0.0, "top_k": 0, "audio_hz": 25.0, "speech_delay": 0.12, "speech_align": true, "align_min": 0.5, "write_surprise": null, "voice_drop": 0.0, "fluency_target": 100.0, "fluency_gain": 0.5, "video": null, "video_rate": 4.0, "video_sound": "mimi", "video_seconds": 0.0, "video_save": null, "teach": 0, "teach_ask": "data", "teach_teacher": "Qwen/Qwen2.5-1.5B-Instruct", "teach_lr": 0.001, "teach_steps": 1, "teach_control": 100, "teach_skip": 1000, "teach_para": true, "teach_json": null, "eval": false, "eval_json": null, "vis": false, "delay": 0.1, "cmap": "viridis", "push": false, "hub_repo": "siliconperception/vla", "private": false, "push_dir": null, "card": null, "hub_tag": null, "pretrained": null, "revision": null, "verbose": false }, "step": 10180000, "examples": 2441355, "examples_by": { "fineweb": 2298981 } }