{ "norm_stats": { "libero_aggregated": { "action": { "q01": [ -0.7071428298950195, -0.8008928298950195, -0.9375, -0.11464285850524902, -0.16285714507102966, -0.22285714745521545, -1.0 ], "q99": [ 0.9375, 0.8732143044471741, 0.9375, 0.13178572058677673, 0.1907142847776413, 0.33964285254478455, 1.0 ], "mean": [ 0.06188340485095978, 0.087010458111763, -0.09098797291517258, 0.0005711889243684709, 0.005523346830159426, -0.0050172158516943455, -0.05251104384660721 ], "std": [ 0.3350602984428406, 0.3785671591758728, 0.4437214732170105, 0.03920658305287361, 0.06300227344036102, 0.07836004346609116, 0.9982072114944458 ], "min": [ -0.9375, -0.9375, -0.9375, -0.24214285612106323, -0.375, -0.3642857074737549, -1.0 ], "max": [ 0.9375, 0.9375, 0.9375, 0.3557142913341522, 0.375, 0.375, 1.0 ], "mask": [ true, true, true, true, true, true, false ] } } }, "n_action_bins": 256, "vision_backbone_id": "dinosiglip-vit-so-224px", "llm_backbone_id": "llama2-7b-pure", "arch_specifier": "no-align+fused-gelu-mlp", "output_projector_states": false, "use_fused_vision_backbone": true, "timm_model_ids": [ "vit_large_patch14_reg4_dinov2.lvd142m", "vit_so400m_patch14_siglip_224" ], "timm_override_act_layers": [ null, null ], "image_sizes": [ 224, 224 ], "image_resize_strategy": "resize-naive", "hf_llm_id": "meta-llama/Llama-2-7b-hf", "llm_max_length": 2048, "pad_token_id": 32000, "pad_to_multiple_of": 64, "text_config": { "vocab_size": 32064, "max_position_embeddings": 2048, "hidden_size": 4096, "intermediate_size": 11008, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 32, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-06, "pretraining_tp": 1, "use_cache": true, "rope_theta": 10000.0, "rope_scaling": null, "attention_bias": false, "attention_dropout": 0.0, "mlp_bias": false, "head_dim": 128, "return_dict": true, "output_hidden_states": false, "torchscript": false, "dtype": "bfloat16", "pruned_heads": {}, "tie_word_embeddings": false, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "architectures": null, "finetuning_task": null, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "task_specific_params": null, "problem_type": null, "tokenizer_class": null, "prefix": null, "bos_token_id": 1, "pad_token_id": 32000, "eos_token_id": 2, "sep_token_id": null, "decoder_start_token_id": null, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": null, "num_beam_groups": 1, "diversity_penalty": 0.0, "_name_or_path": "", "model_type": "llama", "tf_legacy_loss": false, "use_bfloat16": false, "output_attentions": false }, "return_dict": true, "output_hidden_states": false, "torchscript": false, "dtype": "bfloat16", "pruned_heads": {}, "tie_word_embeddings": true, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "architectures": [ "OpenVLAForActionPrediction" ], "finetuning_task": null, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "task_specific_params": null, "problem_type": null, "tokenizer_class": null, "prefix": null, "bos_token_id": null, "eos_token_id": null, "sep_token_id": null, "decoder_start_token_id": null, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": null, "num_beam_groups": 1, "diversity_penalty": 0.0, "_name_or_path": "checkpoints/libero_sft_eval/step_1000/pretrained_model", "transformers_version": "4.57.6", "auto_map": { "AutoConfig": "configuration_prismatic.OpenVLAConfig", "AutoModelForVision2Seq": "modeling_prismatic.OpenVLAForActionPrediction" }, "model_type": "openvla_oft", "action_dim": 7, "num_actions_chunk": 10, "num_images_in_input": 2, "invert_gripper": true, "is_causal": false, "vocab_size": 32000, "unnorm_key": "libero_aggregated", "num_action_chunks": 10, "tf_legacy_loss": false, "use_bfloat16": false, "output_attentions": false }