|
|
2025-07-22 00:31:10,986 INFO MainThread:1729 [wandb_run.py:_config_callback():1358] config_cb None None {'thinker_config': {'audio_token_index': 151646, 'image_token_index': 151655, 'video_token_index': 151656, 'user_token_id': 872, 'position_id_per_seconds': 25, 'seconds_per_chunk': 2, 'audio_start_token_id': 151647, 'audio_end_token_id': 151648, 'initializer_range': 0.02, 'vision_config': {'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': None, 'use_bfloat16': False, 'tf_legacy_loss': False, 'pruned_heads': {}, 'tie_word_embeddings': True, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 20, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'num_beam_groups': 1, 'diversity_penalty': 0.0, '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': None, 'num_return_sequences': 1, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': None, 'architectures': None, 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': None, 'pad_token_id': None, 'eos_token_id': None, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_attn_implementation_autoset': False, 'embed_dim': 1280, 'in_chans': 3, 'init_std': 0.02, 'model_type': 'qwen2_5_omni_vision_encoder', 'spatial_patch_size': 14, 'tokens_per_second': 25, 'depth': 32, 'hidden_size': 1280, 'hidden_act': 'silu', 'intermediate_size': 3420, 'num_heads': 16, 'in_channels': 3, 'patch_size': 14, 'spatial_merge_size': 2, 'temporal_patch_size': 2, 'window_size': 112, 'fullatt_block_indexes': [7, 15, 23, 31], 'out_hidden_size': 3584, 'initializer_range': 0.02}, 'audio_config': {'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': None, 'use_bfloat16': False, 'tf_legacy_loss': False, 'pruned_heads': {}, 'tie_word_embeddings': True, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 20, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'num_beam_groups': 1, 'diversity_penalty': 0.0, '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': None, 'num_return_sequences': 1, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': None, 'architectures': None, 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': None, 'pad_token_id': None, 'eos_token_id': None, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_attn_implementation_autoset': False, 'encoder_layerdrop': 0.0, 'init_std': 0.02, 'model_type': 'qwen2_5_omni_audio_encoder', 'num_hidden_layers': 32, 'num_mel_bins': 128, 'd_model': 1280, 'encoder_layers': 32, 'encoder_attention_heads': 20, 'encoder_ffn_dim': 5120, 'dropout': 0.0, 'attention_dropout': 0.0, 'activation_function': 'gelu', 'activation_dropout': 0.0, 'initializer_range': 0.02, 'scale_embedding': False, 'max_source_positions': 1500, 'n_window': 100, 'output_dim': 3584}, 'text_config': {'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': None, 'use_bfloat16': False, 'tf_legacy_loss': False, 'pruned_heads': {}, 'tie_word_embeddings': False, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 20, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'num_beam_groups': 1, 'diversity_penalty': 0.0, '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': None, 'num_return_sequences': 1, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': None, 'architectures': None, 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': None, 'pad_token_id': None, 'eos_token_id': None, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_attn_implementation_autoset': False, 'init_std': 0.02, 'model_type': 'qwen2_5_omni_text', 'vocab_size': 152064, 'max_position_embeddings': 32768, 'hidden_size': 3584, 'intermediate_size': 18944, 'num_hidden_layers': 28, 'num_attention_heads': 28, 'use_sliding_window': False, 'sliding_window': 32768, 'max_window_layers': 28, 'num_key_value_heads': 4, 'hidden_act': 'silu', 'initializer_range': 0.02, 'rms_norm_eps': 1e-06, 'use_cache': True, 'rope_theta': 1000000.0, 'rope_scaling': {'mrope_section': [16, 24, 24], 'rope_type': 'default', 'type': 'default'}, 'attention_dropout': 0.0}, 'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': 'bfloat16', 'use_bfloat16': False, 'tf_legacy_loss': False, 'pruned_heads': {}, 'tie_word_embeddings': True, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 20, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'num_beam_groups': 1, 'diversity_penalty': 0.0, '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': None, 'num_return_sequences': 1, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': None, 'architectures': ['Qwen2OmniNaViTThinkerForConditionalGeneration'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': 151644, 'pad_token_id': 151643, 'eos_token_id': 151645, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_attn_implementation_autoset': True, 'ignore_index': -100, 'init_std': 0.02, 'model_type': 'qwen2_5_omni_thinker', 'vision_end_token_id': 151653, 'vision_start_token_id': 151652, 'vision_token_id': 151654}, 'talker_config': {'audio_token_index': 151646, 'image_token_index': 151655, 'video_token_index': 151656, 'tts_text_start_token_id': 151860, 'tts_text_end_token_id': 151861, 'tts_text_pad_token_id': 151859, 'tts_codec_start_token_id': 8293, 'tts_codec_end_token_id': 8294, 'tts_codec_pad_token_id': 8292, 'tts_codec_mask_token_id': 8296, 'vision_start_token_id': 151652, 'vision_end_token_id': 151653, 'vocab_size': 8448, 'head_dim': 128, 'embedding_size': 3584, 'max_position_embeddings': 32768, 'hidden_size': 896, 'intermediate_size': 18944, 'num_hidden_layers': 24, 'num_attention_heads': 12, 'use_sliding_window': False, 'sliding_window': 32768, 'max_window_layers': 28, 'num_key_value_heads': 4, 'hidden_act': 'silu', 'rms_norm_eps': 1e-06, 'use_cache': False, 'rope_theta': 1000000.0, 'attention_dropout': 0.0, 'rope_scaling': {'mrope_section': [16, 24, 24], 'rope_type': 'default', 'type': 'default'}, 'position_id_per_seconds': 25, 'seconds_per_chunk': 2, 'audio_start_token_id': 151647, 'audio_end_token_id': 151648, 'initializer_range': 0.02, 'spatial_merge_size': 2, 'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': 'bfloat16', 'use_bfloat16': False, 'tf_legacy_loss': False, 'pruned_heads': {}, 'tie_word_embeddings': False, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 20, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'num_beam_groups': 1, 'diversity_penalty': 0.0, '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': None, 'num_return_sequences': 1, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': None, 'architectures': ['Qwen2OmniTalkerForConditionalGeneration'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': None, 'pad_token_id': None, 'eos_token_id': None, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_attn_implementation_autoset': True, 'init_std': 0.02, 'model_type': 'qwen2_5_omni_talker'}, 'token2wav_config': {'dit_config': {'hidden_size': 1024, 'num_hidden_layers': 22, 'num_attention_heads': 16, 'ff_mult': 2, 'emb_dim': 512, 'head_dim': 64, 'rope_theta': 10000.0, 'max_position_embeddings': 32768, 'block_size': 24, 'look_ahead_layers': [10], 'look_backward_layers': [0, 20], 'repeats': 2, 'num_embeds': 8193, 'mel_dim': 80, 'dropout': 0.1, 'enc_emb_dim': 192, 'enc_dim': 128, 'enc_channels': [256, 256, 256, 256, 768], 'enc_kernel_sizes': [5, 3, 3, 3, 1], 'enc_dilations': [1, 2, 3, 4, 1], 'enc_attention_channels': 64, 'enc_res2net_scale': 2, 'enc_se_channels': 64, 'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': 'float32', 'use_bfloat16': False, 'tf_legacy_loss': False, 'pruned_heads': {}, 'tie_word_embeddings': True, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 20, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'num_beam_groups': 1, 'diversity_penalty': 0.0, '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': None, 'num_return_sequences': 1, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': None, 'architectures': None, 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': None, 'pad_token_id': None, 'eos_token_id': None, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_attn_implementation_autoset': False, 'depth': 22, 'dim': 1024, 'enc_global_context': True, 'enc_lin_neurons': 192, 'heads': 16, 'model_type': 'qwen2_5_omni_dit'}, 'bigvgan_config': {'mel_dim': 80, 'upsample_initial_channel': 1536, 'resblock_kernel_sizes': [3, 7, 11], 'resblock_dilation_sizes': [[1, 3, 5], [1, 3, 5], [1, 3, 5]], 'upsample_rates': [5, 3, 2, 2, 2, 2], 'upsample_kernel_sizes': [11, 7, 4, 4, 4, 4], 'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': None, 'use_bfloat16': False, 'tf_legacy_loss': False, 'pruned_heads': {}, 'tie_word_embeddings': True, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 20, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'num_beam_groups': 1, 'diversity_penalty': 0.0, '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': None, 'num_return_sequences': 1, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': None, 'architectures': None, 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': None, 'pad_token_id': None, 'eos_token_id': None, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_attn_implementation_autoset': False, 'model_type': 'qwen2_5_omni_bigvgan', 'use_bias_at_final': False}, 'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': 'bfloat16', 'use_bfloat16': False, 'tf_legacy_loss': False, 'pruned_heads': {}, 'tie_word_embeddings': True, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 20, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'num_beam_groups': 1, 'diversity_penalty': 0.0, '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': None, 'num_return_sequences': 1, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': None, 'architectures': None, 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': None, 'pad_token_id': 151643, 'eos_token_id': None, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_attn_implementation_autoset': True, 'model_type': 'qwen2_5_omni_token2wav'}, 'enable_audio_output': True, 'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': 'bfloat16', 'use_bfloat16': False, 'tf_legacy_loss': False, 'pruned_heads': {}, 'tie_word_embeddings': True, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 20, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'num_beam_groups': 1, 'diversity_penalty': 0.0, 'temperature': 1.0, 'top_k': 50, 'top_p': 0.9, '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': None, 'num_return_sequences': 1, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': None, 'architectures': ['Qwen2_5OmniForConditionalGeneration'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': None, 'pad_token_id': 151643, 'eos_token_id': None, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_attn_implementation_autoset': True, 'transformers_version': '4.52.0.dev0', 'enable_talker': True, 'hidden_size': 3584, 'keys_to_ignore_at_inference': ['past_key_values', 'hidden_states', 'attention_mask', 'hidden_states', 'attention_mask', 'hidden_states', 'attention_mask'], 'model_type': 'qwen2_5_omni', 'output_dir': '/root/autodl-tmp/output_7B_GRPO/v28-20250722-002940', 'overwrite_output_dir': False, 'do_train': False, 'do_eval': True, 'do_predict': False, 'eval_strategy': 'steps', 'prediction_loss_only': False, 'per_device_train_batch_size': 2, 'per_device_eval_batch_size': 2, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 2, 'eval_accumulation_steps': None, 'eval_delay': 0, 'torch_empty_cache_steps': None, 'learning_rate': 1e-06, 'weight_decay': 0.1, 'adam_beta1': 0.9, 'adam_beta2': 0.95, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 2.0, 'max_steps': -1, 'lr_scheduler_type': 'cosine', 'lr_scheduler_kwargs': None, 'warmup_ratio': 0.01, 'warmup_steps': 0, 'log_level': 'passive', 'log_level_replica': 'warning', 'log_on_each_node': True, 'logging_dir': '/root/autodl-tmp/output_7B_GRPO/v28-20250722-002940/runs', 'logging_strategy': 'steps', 'logging_first_step': True, 'logging_steps': 5, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 290, 'save_total_limit': 5, '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': 42, 'data_seed': 42, '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': None, 'local_rank': 0, 'ddp_backend': None, 'tpu_num_cores': None, 'tpu_metrics_debug': False, 'debug': [], 'dataloader_drop_last': True, 'eval_steps': 290, 'dataloader_num_workers': 1, 'dataloader_prefetch_factor': 10, 'past_index': -1, 'run_name': '/root/autodl-tmp/output_7B_GRPO/v28-20250722-002940', 'disable_tqdm': False, 'remove_unused_columns': False, 'label_names': None, 'load_best_model_at_end': False, 'metric_for_best_model': 'reward', 'greater_is_better': True, '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': None, 'accelerator_config': {'split_batches': False, 'dispatch_batches': False, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}, 'deepspeed': {'fp16': {'enabled': 'auto', 'loss_scale': 0, 'loss_scale_window': 1000, 'initial_scale_power': 16, 'hysteresis': 2, 'min_loss_scale': 1}, 'bf16': {'enabled': 'auto'}, 'zero_optimization': {'stage': 3, 'offload_optimizer': {'device': 'cpu', 'pin_memory': True}, 'offload_param': {'device': 'cpu', 'pin_memory': True}, 'overlap_comm': False, 'contiguous_gradients': True, 'sub_group_size': 1000000000.0, 'reduce_bucket_size': 'auto', 'stage3_prefetch_bucket_size': 0, 'stage3_param_persistence_threshold': 'auto', 'stage3_max_live_parameters': 1000000000.0, 'stage3_max_reuse_distance': 1000000000.0, 'stage3_gather_16bit_weights_on_model_save': True}, 'gradient_accumulation_steps': 'auto', 'gradient_clipping': 'auto', 'steps_per_print': 2000, 'train_batch_size': 'auto', 'train_micro_batch_size_per_gpu': 'auto', 'wall_clock_breakdown': False}, 'label_smoothing_factor': 0.0, 'optim': 'adamw_torch', 'optim_args': None, 'adafactor': False, 'group_by_length': False, 'length_column_name': 'length', 'report_to': ['wandb'], 'ddp_find_unused_parameters': None, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'skip_memory_metrics': True, 'use_legacy_prediction_loop': False, 'push_to_hub': False, 'resume_from_checkpoint': None, 'hub_model_id': None, 'hub_strategy': 'every_save', 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': None, 'hub_always_push': False, 'gradient_checkpointing': True, 'gradient_checkpointing_kwargs': None, 'include_inputs_for_metrics': False, 'include_for_metrics': [], 'eval_do_concat_batches': True, 'fp16_backend': 'auto', 'push_to_hub_model_id': None, 'push_to_hub_organization': None, 'push_to_hub_token': '<PUSH_TO_HUB_TOKEN>', 'mp_parameters': '', 'auto_find_batch_size': False, 'full_determinism': False, 'torchdynamo': None, 'ray_scope': 'last', 'ddp_timeout': 1800, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': False, 'neftune_noise_alpha': None, 'optim_target_modules': None, 'batch_eval_metrics': False, 'eval_on_start': False, 'use_liger_kernel': False, 'eval_use_gather_object': False, 'average_tokens_across_devices': False, 'model_init_kwargs': None, 'disable_dropout': False, 'max_prompt_length': 512, 'num_generations': 2, 'max_completion_length': 512, 'ds3_gather_for_generation': True, 'shuffle_dataset': True, 'min_p': None, 'cache_implementation': None, 'use_vllm': False, 'vllm_server_host': None, 'vllm_server_port': 8000, 'vllm_server_timeout': 240.0, 'vllm_guided_decoding_regex': None, 'beta': 0.01, 'num_iterations': 1, 'epsilon': 0.2, 'epsilon_high': None, 'reward_weights': None, 'scale_rewards': True, 'loss_type': 'grpo', 'mask_truncated_completions': False, 'sync_ref_model': False, 'ref_model_mixup_alpha': 0.6, 'ref_model_sync_steps': 512, 'use_liger_loss': False, 'log_completions': True, 'num_completions_to_print': None, 'wandb_log_unique_prompts': None, 'vllm_device': ['auto'], 'vllm_gpu_memory_utilization': 0.9, 'vllm_dtype': None, 'vllm_max_model_len': None, 'vllm_enable_prefix_caching': True, 'check_model': True, 'acc_strategy': 'token', 'train_dataloader_shuffle': True, 'max_epochs': None, 'metric_warmup_step': 0, 'fsdp_num': 1, 'acc_steps': 1, 'eval_use_evalscope': False, 'eval_datasets': [], 'eval_limit': None, 'eval_datasets_args': None, 'eval_generation_config': None, 'train_type': 'full', 'optimizer': None, 'local_repo_path': None, 'galore_config': None, 'num_infer_workers': 1, 'vllm_max_num_seqs': 256, 'vllm_enforce_eager': False, 'vllm_limit_mm_per_prompt': {}, 'cosine_min_len_value_wrong': -0.5, 'cosine_max_len_value_wrong': 0.0, 'cosine_min_len_value_correct': 1.0, 'cosine_max_len_value_correct': 0.5, 'cosine_max_len': 512, 'repetition_n_grams': 3, 'repetition_max_penalty': -1.0, 'reward_model': None, 'reward_model_plugin': None, 'use_lmdeploy': False, 'lmdeploy_device': 'auto', 'lmdeploy_session_len': None, 'lmdeploy_cache_max_entry_count': 0.8, 'async_generate': False, 'tensor_parallel_size': 1, 'sleep_level': 0, 'move_model_batches': None, 'offload_optimizer': False, 'offload_model': False, 'gc_collect_after_offload': False, 'multi_turn_func': None, 'dynamic_sample': False, 'max_resample_times': 3, 'overlong_filter': False, 'soft_max_length': None, 'soft_cache_length': None, 'dataset_shuffle': True, 'stop_words': []} |
