Add files using upload-large-folder tool

LlamaFactory/wandb/run-20260209_081117-18fi1m6s/files/config.yaml

@@ -0,0 +1,723 @@
+_name_or_path:
+    value: /workspace/Qwen/Qwen3-8B-Base
+_wandb:
+    value:
+        cli_version: 0.24.2
+        e:
+            cpeblcn9qsylpv3vdjtepn4bz3uf73py:
+                args:
+                    - /workspace/v127rc_exp2/B_dup.yaml
+                cpu_count: 16
+                cpu_count_logical: 32
+                cudaVersion: "12.9"
+                disk:
+                    /:
+                        total: "21474836480"
+                        used: "2060402688"
+                email: markmochi200@gmail.com
+                executable: /usr/bin/python
+                git:
+                    commit: 1a02717fa84c270d1c156c4c4a391c2f95525a63
+                    remote: https://github.com/hiyouga/LlamaFactory.git
+                gpu: NVIDIA GeForce RTX 4090
+                gpu_count: 1
+                gpu_nvidia:
+                    - architecture: Ada
+                      cudaCores: 16384
+                      memoryTotal: "25757220864"
+                      name: NVIDIA GeForce RTX 4090
+                      uuid: GPU-6c1e98c2-1b34-cfd8-5de5-319e272f1d1e
+                host: 3bebe963f251
+                memory:
+                    total: "134156767232"
+                os: Linux-6.8.0-60-generic-x86_64-with-glibc2.35
+                program: /usr/local/bin/llamafactory-cli
+                python: CPython 3.11.10
+                root: /workspace/LlamaFactory
+                startedAt: "2026-02-09T08:11:17.633214Z"
+                writerId: cpeblcn9qsylpv3vdjtepn4bz3uf73py
+        m:
+            - "1": train/global_step
+              "6":
+                - 3
+              "7": []
+            - "2": '*'
+              "5": 1
+              "6":
+                - 1
+              "7": []
+        python_version: 3.11.10
+        t:
+            "1":
+                - 1
+                - 11
+                - 41
+                - 49
+                - 51
+                - 71
+                - 84
+                - 98
+                - 105
+            "2":
+                - 1
+                - 11
+                - 41
+                - 49
+                - 51
+                - 71
+                - 84
+                - 98
+                - 105
+            "3":
+                - 7
+                - 19
+                - 62
+                - 66
+            "4": 3.11.10
+            "5": 0.24.2
+            "6": 5.0.0
+            "9":
+                "1": transformers_trainer
+            "12": 0.24.2
+            "13": linux-x86_64
+accelerator_config:
+    value:
+        dispatch_batches: null
+        even_batches: true
+        gradient_accumulation_kwargs: null
+        non_blocking: false
+        split_batches: false
+        use_seedable_sampler: true
+adam_beta1:
+    value: 0.9
+adam_beta2:
+    value: 0.95
+adam_epsilon:
+    value: 1e-08
+architectures:
+    value:
+        - Qwen3ForCausalLM
+attention_bias:
+    value: false
+attention_dropout:
+    value: 0
+auto_find_batch_size:
+    value: false
+average_tokens_across_devices:
+    value: true
+batch_eval_metrics:
+    value: false
+bf16:
+    value: true
+bf16_full_eval:
+    value: false
+bos_token_id:
+    value: null
+chunk_size_feed_forward:
+    value: 0
+data_args:
+    value:
+        buffer_size: 16384
+        cutoff_len: 2047
+        data_shared_file_system: false
+        dataset:
+            - Markie_Voss_t0_d34_r300
+        dataset_dir: /workspace/LlamaFactory/data
+        default_system: null
+        enable_thinking: false
+        eval_dataset: null
+        eval_num_beams: null
+        eval_on_each_dataset: false
+        ignore_pad_token_for_loss: true
+        interleave_probs: null
+        mask_history: false
+        max_samples: 100000000
+        media_dir: /workspace/LlamaFactory/data
+        mix_strategy: concat
+        neat_packing: false
+        overwrite_cache: false
+        packing: true
+        preprocessing_batch_size: 1000
+        preprocessing_num_workers: 16
+        streaming: false
+        template: qwen3_nothink
+        tokenized_path: null
+        tool_format: null
+        train_on_prompt: false
+        val_size: 0
+data_seed:
+    value: null
+dataloader_drop_last:
+    value: false
+dataloader_num_workers:
+    value: 0
+dataloader_persistent_workers:
+    value: false
+dataloader_pin_memory:
+    value: true
+dataloader_prefetch_factor:
+    value: null
+ddp_backend:
+    value: null
+ddp_broadcast_buffers:
+    value: null
+ddp_bucket_cap_mb:
+    value: null
+ddp_find_unused_parameters:
+    value: null
+ddp_timeout:
+    value: 180000000
+debug:
+    value: []
+deepspeed:
+    value: null
+disable_tqdm:
+    value: false
+do_eval:
+    value: false
+do_predict:
+    value: false
+do_train:
+    value: true
+dtype:
+    value: bfloat16
+enable_jit_checkpoint:
+    value: false
+eos_token_id:
+    value: 151645
+eval_accumulation_steps:
+    value: null
+eval_delay:
+    value: 0
+eval_do_concat_batches:
+    value: true
+eval_on_start:
+    value: false
+eval_steps:
+    value: null
+eval_strategy:
+    value: "no"
+eval_use_gather_object:
+    value: false
+finetuning_args:
+    value:
+        additional_target: null
+        apollo_layerwise: false
+        apollo_proj: random
+        apollo_proj_type: std
+        apollo_rank: 16
+        apollo_scale: 32
+        apollo_scale_front: false
+        apollo_scale_type: channel
+        apollo_target:
+            - all
+        apollo_update_interval: 200
+        badam_mask_mode: adjacent
+        badam_mode: layer
+        badam_start_block: null
+        badam_switch_interval: 50
+        badam_switch_mode: ascending
+        badam_update_ratio: 0.05
+        badam_verbose: 0
+        compute_accuracy: false
+        create_new_adapter: false
+        disable_shuffling: false
+        dpo_label_smoothing: 0
+        eaft_alpha: 1
+        early_stopping_steps: null
+        finetuning_type: lora
+        freeze_extra_modules: null
+        freeze_language_model: false
+        freeze_multi_modal_projector: true
+        freeze_trainable_layers: 2
+        freeze_trainable_modules:
+            - all
+        freeze_vision_tower: true
+        galore_layerwise: false
+        galore_proj_type: std
+        galore_rank: 16
+        galore_scale: 2
+        galore_target:
+            - all
+        galore_update_interval: 200
+        include_effective_tokens_per_second: false
+        kto_chosen_weight: 1
+        kto_rejected_weight: 1
+        ld_alpha: null
+        lora_alpha: 32
+        lora_dropout: 0.03
+        lora_rank: 16
+        lora_target:
+            - all
+        loraplus_lr_embedding: 1e-06
+        loraplus_lr_ratio: null
+        module_dropout: 0
+        oft_block_size: 32
+        oft_rank: 0
+        oft_target:
+            - all
+        pissa_convert: false
+        pissa_init: false
+        pissa_iter: 16
+        plot_loss: true
+        ppo_buffer_size: 1
+        ppo_epochs: 4
+        ppo_score_norm: false
+        ppo_target: 6
+        ppo_whiten_rewards: false
+        pref_bco_weight: 0
+        pref_beta: 0.1
+        pref_ftx: 0
+        pref_loss: sigmoid
+        pure_bf16: false
+        ref_model: null
+        ref_model_adapters: null
+        ref_model_quantization_bit: null
+        reward_model: null
+        reward_model_adapters: null
+        reward_model_quantization_bit: null
+        reward_model_type: lora
+        simpo_gamma: 0.5
+        stage: pt
+        swanlab_api_key: <SWANLAB_API_KEY>
+        swanlab_lark_secret: null
+        swanlab_lark_webhook_url: null
+        swanlab_logdir: null
+        swanlab_mode: cloud
+        swanlab_project: llamafactory
+        swanlab_run_name: null
+        swanlab_workspace: null
+        use_adam_mini: false
+        use_apollo: false
+        use_badam: false
+        use_dft_loss: false
+        use_dora: false
+        use_eaft_loss: false
+        use_galore: false
+        use_llama_pro: false
+        use_mca: false
+        use_muon: false
+        use_rslora: false
+        use_swanlab: false
+fp8:
+    value: false
+fp8_backend:
+    value: auto
+fp8_enable_fsdp_float8_all_gather:
+    value: false
+fp16:
+    value: false
+fp16_full_eval:
+    value: false
+fsdp:
+    value: []
+fsdp_config:
+    value:
+        min_num_params: 0
+        xla: false
+        xla_fsdp_grad_ckpt: false
+        xla_fsdp_v2: false
+full_determinism:
+    value: false
+generating_args:
+    value:
+        do_sample: true
+        length_penalty: 1
+        max_new_tokens: 1024
+        num_beams: 1
+        repetition_penalty: 1
+        skip_special_tokens: true
+        temperature: 0.95
+        top_k: 50
+        top_p: 0.7
+generation_config:
+    value: null
+generation_max_length:
+    value: 2047
+generation_num_beams:
+    value: null
+gradient_accumulation_steps:
+    value: 1
+gradient_checkpointing:
+    value: false
+gradient_checkpointing_kwargs:
+    value: null
+greater_is_better:
+    value: null
+group_by_length:
+    value: false
+head_dim:
+    value: 128
+hidden_act:
+    value: silu
+hidden_size:
+    value: 4096
+hub_always_push:
+    value: false
+hub_model_id:
+    value: null
+hub_private_repo:
+    value: null
+hub_revision:
+    value: null
+hub_strategy:
+    value: every_save
+hub_token:
+    value: <HUB_TOKEN>
+id2label:
+    value:
+        "0": LABEL_0
+        "1": LABEL_1
+ignore_data_skip:
+    value: false
+include_for_metrics:
+    value: []
+include_num_input_tokens_seen:
+    value: all
+initializer_range:
+    value: 0.02
+intermediate_size:
+    value: 12288
+is_encoder_decoder:
+    value: false
+label_names:
+    value:
+        - labels
+label_smoothing_factor:
+    value: 0
+label2id:
+    value:
+        LABEL_0: 0
+        LABEL_1: 1
+layer_types:
+    value:
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+learning_rate:
+    value: 5e-05
+length_column_name:
+    value: length
+liger_kernel_config:
+    value: null
+load_best_model_at_end:
+    value: false
+local_rank:
+    value: -1
+log_level:
+    value: passive
+log_level_replica:
+    value: warning
+log_on_each_node:
+    value: true
+logging_dir:
+    value: null
+logging_first_step:
+    value: false
+logging_nan_inf_filter:
+    value: true
+logging_steps:
+    value: 1
+logging_strategy:
+    value: steps
+lr_scheduler_kwargs:
+    value: null
+lr_scheduler_type:
+    value: cosine
+master_addr:
+    value: null
+master_port:
+    value: null
+max_grad_norm:
+    value: 1
+max_position_embeddings:
+    value: 32768
+max_steps:
+    value: -1
+max_window_layers:
+    value: 36
+metric_for_best_model:
+    value: null
+model/num_parameters:
+    value: 8234382336
+model_args:
+    value:
+        adapter_folder: null
+        adapter_name_or_path: null
+        add_special_tokens: null
+        add_tokens: null
+        audio_sampling_rate: 16000
+        block_diag_attn: false
+        cache_dir: null
+        chunk_size: 8192
+        compute_dtype: torch.bfloat16
+        cpu_infer: 32
+        crop_to_patches: false
+        device_map:
+            "": cuda:0
+        disable_gradient_checkpointing: false
+        double_quantization: true
+        enable_liger_kernel: false
+        export_device: cpu
+        export_dir: null
+        export_hub_model_id: null
+        export_legacy_format: false
+        export_quantization_bit: null
+        export_quantization_dataset: null
+        export_quantization_maxlen: 1024
+        export_quantization_nsamples: 128
+        export_size: 5
+        flash_attn: auto
+        hf_hub_token: <HF_HUB_TOKEN>
+        image_do_pan_and_scan: false
+        image_max_pixels: 589824
+        image_min_pixels: 1024
+        infer_backend: HF
+        infer_dtype: auto
+        init_special_tokens: noise_init
+        kt_force_think: false
+        kt_maxlen: 4096
+        kt_mode: normal
+        kt_optimize_rule: null
+        kt_use_cuda_graph: true
+        low_cpu_mem_usage: true
+        mixture_of_depths: null
+        mode: normal
+        model_max_length: 2047
+        model_name_or_path: /workspace/Qwen/Qwen3-8B-Base
+        model_revision: main
+        moe_aux_loss_coef: null
+        ms_hub_token: <MS_HUB_TOKEN>
+        new_special_tokens_config: null
+        offload_folder: offload
+        om_hub_token: <OM_HUB_TOKEN>
+        print_param_status: false
+        quantization_bit: null
+        quantization_device_map: null
+        quantization_method: BNB
+        quantization_type: nf4
+        resize_vocab: false
+        rope_scaling: null
+        sglang_config: null
+        sglang_lora_backend: triton
+        sglang_maxlen: 4096
+        sglang_mem_fraction: 0.7
+        sglang_tp_size: -1
+        shift_attn: false
+        split_special_tokens: false
+        train_from_scratch: false
+        trust_remote_code: true
+        upcast_layernorm: false
+        upcast_lmhead_output: false
+        use_audio_in_video: false
+        use_fast_tokenizer: true
+        use_kt: false
+        use_kv_cache: true
+        use_reentrant_gc: true
+        use_unsloth: false
+        use_unsloth_gc: false
+        use_v1_kernels: false
+        video_fps: 2
+        video_max_pixels: 65536
+        video_maxlen: 128
+        video_min_pixels: 256
+        vllm_config: null
+        vllm_enforce_eager: false
+        vllm_gpu_util: 0.7
+        vllm_max_lora_rank: 32
+        vllm_maxlen: 4096
+model_type:
+    value: qwen3
+neftune_noise_alpha:
+    value: null
+num_attention_heads:
+    value: 32
+num_hidden_layers:
+    value: 36
+num_key_value_heads:
+    value: 8
+num_train_epochs:
+    value: 10
+optim:
+    value: adamw_torch
+optim_args:
+    value: null
+optim_target_modules:
+    value: null
+output_attentions:
+    value: false
+output_dir:
+    value: /workspace/v127rc_exp2/B_dup
+output_hidden_states:
+    value: false
+overwrite_output_dir:
+    value: false
+pad_token_id:
+    value: 151643
+parallelism_config:
+    value: null
+peft_config:
+    value:
+        default:
+            alora_invocation_tokens: null
+            arrow_config: null
+            auto_mapping: null
+            base_model_name_or_path: /workspace/Qwen/Qwen3-8B-Base
+            bias: none
+            corda_config: null
+            ensure_weight_tying: false
+            eva_config: null
+            exclude_modules: null
+            fan_in_fan_out: false
+            inference_mode: false
+            init_lora_weights: true
+            layer_replication: null
+            layers_pattern: null
+            layers_to_transform: null
+            lora_alpha: 32
+            lora_bias: false
+            lora_dropout: 0.03
+            megatron_config: null
+            megatron_core: megatron.core
+            modules_to_save: null
+            peft_type: LORA
+            peft_version: 0.18.1
+            qalora_group_size: 16
+            r: 16
+            revision: null
+            runtime_config:
+                ephemeral_gpu_offload: false
+            target_modules:
+                - q_proj
+                - v_proj
+                - down_proj
+                - up_proj
+                - k_proj
+                - gate_proj
+                - o_proj
+            target_parameters: null
+            task_type: CAUSAL_LM
+            trainable_token_indices: null
+            use_dora: false
+            use_qalora: false
+            use_rslora: false
+per_device_eval_batch_size:
+    value: 8
+per_device_train_batch_size:
+    value: 1
+predict_with_generate:
+    value: false
+prediction_loss_only:
+    value: false
+problem_type:
+    value: null
+project:
+    value: huggingface
+push_to_hub:
+    value: false
+ray_init_kwargs:
+    value: null
+ray_num_workers:
+    value: 1
+remove_unused_columns:
+    value: false
+report_to:
+    value:
+        - wandb
+restore_callback_states_from_checkpoint:
+    value: false
+resume_from_checkpoint:
+    value: null
+return_dict:
+    value: true
+rms_norm_eps:
+    value: 1e-06
+rope_parameters:
+    value:
+        rope_theta: 1000000
+        rope_type: default
+run_name:
+    value: null
+save_on_each_node:
+    value: false
+save_only_model:
+    value: true
+save_steps:
+    value: 1000
+save_strategy:
+    value: steps
+save_total_limit:
+    value: null
+seed:
+    value: 42
+skip_memory_metrics:
+    value: true
+sliding_window:
+    value: null
+sortish_sampler:
+    value: false
+tf32:
+    value: null
+tie_word_embeddings:
+    value: false
+torch_compile:
+    value: false
+torch_compile_backend:
+    value: null
+torch_compile_mode:
+    value: null
+torch_empty_cache_steps:
+    value: null
+trackio_space_id:
+    value: trackio
+transformers_version:
+    value: 5.0.0
+use_cache:
+    value: false
+use_cpu:
+    value: false
+use_liger_kernel:
+    value: false
+use_sliding_window:
+    value: false
+vocab_size:
+    value: 151936
+warmup_ratio:
+    value: 0.01
+warmup_steps:
+    value: 0.01
+weight_decay:
+    value: 0

LlamaFactory/wandb/run-20260209_081117-18fi1m6s/files/wandb-summary.json

@@ -0,0 +1 @@
+{"train/epoch":0.11844468390804598,"_step":1318,"train/num_input_tokens_seen":2699993,"train_runtime":1377.8909,"_runtime":1376,"train/loss":0.8376006484031677,"train/train_tokens_per_second":1959.511,"_wandb":{"runtime":1376},"train/global_step":1319,"_timestamp":1.7706260549948351e+09,"train/grad_norm":2.3566486835479736,"train/learning_rate":4.9999577581249165e-05}

LlamaFactory/wandb/run-20260209_081744-xzw1rig3/logs/debug.log

@@ -0,0 +1,25 @@
+2026-02-09 08:17:44,084 INFO    MainThread:863 [wandb_setup.py:_flush():81] Current SDK version is 0.24.2
+2026-02-09 08:17:44,085 INFO    MainThread:863 [wandb_setup.py:_flush():81] Configure stats pid to 863
+2026-02-09 08:17:44,085 INFO    MainThread:863 [wandb_setup.py:_flush():81] Loading settings from environment variables
+2026-02-09 08:17:44,086 INFO    MainThread:863 [wandb_init.py:setup_run_log_directory():717] Logging user logs to /workspace/LlamaFactory/wandb/run-20260209_081744-xzw1rig3/logs/debug.log
+2026-02-09 08:17:44,087 INFO    MainThread:863 [wandb_init.py:setup_run_log_directory():718] Logging internal logs to /workspace/LlamaFactory/wandb/run-20260209_081744-xzw1rig3/logs/debug-internal.log
+2026-02-09 08:17:44,087 INFO    MainThread:863 [wandb_init.py:init():844] calling init triggers
+2026-02-09 08:17:44,088 INFO    MainThread:863 [wandb_init.py:init():849] wandb.init called with sweep_config: {}
+config: {'_wandb': {}}
+2026-02-09 08:17:44,089 INFO    MainThread:863 [wandb_init.py:init():892] starting backend
+2026-02-09 08:17:44,308 INFO    MainThread:863 [wandb_init.py:init():895] sending inform_init request
+2026-02-09 08:17:44,316 INFO    MainThread:863 [wandb_init.py:init():903] backend started and connected
+2026-02-09 08:17:44,319 INFO    MainThread:863 [wandb_init.py:init():973] updated telemetry
+2026-02-09 08:17:44,377 INFO    MainThread:863 [wandb_init.py:init():997] communicating run to backend with 90.0 second timeout
+2026-02-09 08:17:44,908 INFO    MainThread:863 [wandb_init.py:init():1042] starting run threads in backend
+2026-02-09 08:17:44,981 INFO    MainThread:863 [wandb_run.py:_console_start():2529] atexit reg
+2026-02-09 08:17:44,981 INFO    MainThread:863 [wandb_run.py:_redirect():2377] redirect: wrap_raw
+2026-02-09 08:17:44,982 INFO    MainThread:863 [wandb_run.py:_redirect():2446] Wrapping output streams.
+2026-02-09 08:17:44,982 INFO    MainThread:863 [wandb_run.py:_redirect():2469] Redirects installed.
+2026-02-09 08:17:44,985 INFO    MainThread:863 [wandb_init.py:init():1082] run started, returning control to user process
+2026-02-09 08:17:44,986 INFO    MainThread:863 [wandb_run.py:_config_callback():1404] config_cb None None {'peft_config': {'default': {'task_type': 'CAUSAL_LM', 'peft_type': 'LORA', 'auto_mapping': None, 'peft_version': '0.18.1', 'base_model_name_or_path': '/workspace/Qwen/Qwen3-8B-Base', 'revision': None, 'inference_mode': False, 'r': 16, 'target_modules': ['q_proj', 'down_proj', 'up_proj', 'gate_proj', 'k_proj', 'v_proj', 'o_proj'], 'exclude_modules': None, 'lora_alpha': 32, 'lora_dropout': 0.03, 'fan_in_fan_out': False, 'bias': 'none', 'use_rslora': False, 'modules_to_save': None, 'init_lora_weights': True, 'layers_to_transform': None, 'layers_pattern': None, 'rank_pattern': {}, 'alpha_pattern': {}, 'megatron_config': None, 'megatron_core': 'megatron.core', 'trainable_token_indices': None, 'loftq_config': {}, 'eva_config': None, 'corda_config': None, 'use_dora': False, 'alora_invocation_tokens': None, 'use_qalora': False, 'qalora_group_size': 16, 'layer_replication': None, 'runtime_config': {'ephemeral_gpu_offload': False}, 'lora_bias': False, 'target_parameters': None, 'arrow_config': None, 'ensure_weight_tying': False}}, 'vocab_size': 151936, 'max_position_embeddings': 32768, 'hidden_size': 4096, 'intermediate_size': 12288, 'num_hidden_layers': 36, 'num_attention_heads': 32, 'use_sliding_window': False, 'sliding_window': None, 'max_window_layers': 36, 'num_key_value_heads': 8, 'head_dim': 128, 'hidden_act': 'silu', 'initializer_range': 0.02, 'rms_norm_eps': 1e-06, 'use_cache': False, 'attention_bias': False, 'attention_dropout': 0.0, 'layer_types': ['full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention'], 'pad_token_id': 151643, 'bos_token_id': None, 'eos_token_id': 151645, 'tie_word_embeddings': False, 'rope_parameters': {'rope_theta': 1000000, 'rope_type': 'default'}, 'return_dict': True, 'output_hidden_states': False, 'dtype': 'bfloat16', 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'architectures': ['Qwen3ForCausalLM'], 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'problem_type': None, '_name_or_path': '/workspace/Qwen/Qwen3-8B-Base', 'transformers_version': '5.0.0', 'model_type': 'qwen3', 'output_attentions': False, 'output_dir': '/workspace/v127rc_exp2/B_rep', 'do_train': True, 'do_eval': False, 'do_predict': False, 'eval_strategy': 'no', 'prediction_loss_only': False, 'per_device_train_batch_size': 1, 'per_device_eval_batch_size': 8, 'gradient_accumulation_steps': 1, 'eval_accumulation_steps': None, 'eval_delay': 0, 'torch_empty_cache_steps': None, 'learning_rate': 5e-05, 'weight_decay': 0, 'adam_beta1': 0.9, 'adam_beta2': 0.95, 'adam_epsilon': 1e-08, 'max_grad_norm': 1, 'num_train_epochs': 10, 'max_steps': -1, 'lr_scheduler_type': 'cosine', 'lr_scheduler_kwargs': None, 'warmup_ratio': 0.01, 'warmup_steps': 0.01, 'log_level': 'passive', 'log_level_replica': 'warning', 'log_on_each_node': True, 'logging_dir': None, 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 1, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 1000, 'save_total_limit': None, 'enable_jit_checkpoint': False, 'save_on_each_node': False, 'save_only_model': True, 'restore_callback_states_from_checkpoint': False, 'use_cpu': False, 'seed': 42, 'data_seed': None, 'bf16': True, 'fp16': False, 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': None, 'local_rank': -1, 'ddp_backend': None, 'debug': [], 'dataloader_drop_last': False, 'eval_steps': None, 'dataloader_num_workers': 0, 'dataloader_prefetch_factor': None, 'run_name': None, 'disable_tqdm': False, 'remove_unused_columns': False, 'label_names': ['labels'], 'load_best_model_at_end': False, 'metric_for_best_model': None, 'greater_is_better': None, 'ignore_data_skip': False, 'fsdp': [], 'fsdp_config': {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, 'accelerator_config': {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}, 'parallelism_config': None, 'deepspeed': None, 'label_smoothing_factor': 0.0, 'optim': 'adamw_torch', 'optim_args': None, 'group_by_length': False, 'length_column_name': 'length', 'report_to': ['wandb'], 'project': 'huggingface', 'trackio_space_id': 'trackio', '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, '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, 'hub_revision': None, 'gradient_checkpointing': False, 'gradient_checkpointing_kwargs': None, 'include_for_metrics': [], 'eval_do_concat_batches': True, 'auto_find_batch_size': False, 'full_determinism': False, 'ddp_timeout': 180000000, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'include_num_input_tokens_seen': 'all', 'neftune_noise_alpha': None, 'optim_target_modules': None, 'batch_eval_metrics': False, 'eval_on_start': False, 'use_liger_kernel': False, 'liger_kernel_config': None, 'eval_use_gather_object': False, 'average_tokens_across_devices': True, 'sortish_sampler': False, 'predict_with_generate': False, 'generation_max_length': 2047, 'generation_num_beams': None, 'generation_config': None, 'ray_num_workers': 1, 'ray_init_kwargs': None, 'master_addr': None, 'master_port': None, 'fp8': False, 'fp8_backend': 'auto', 'fp8_enable_fsdp_float8_all_gather': False, 'overwrite_output_dir': False}
+2026-02-09 08:17:44,992 INFO    MainThread:863 [wandb_config.py:__setitem__():154] [no run ID] config set model/num_parameters = 8234382336 - <bound method Run._config_callback of <wandb.sdk.wandb_run.Run object at 0x76f86f424e50>>
+2026-02-09 08:17:44,992 INFO    MainThread:863 [wandb_run.py:_config_callback():1404] config_cb model/num_parameters 8234382336 None
+2026-02-09 08:17:44,995 INFO    MainThread:863 [wandb_run.py:_config_callback():1404] config_cb None None {'model_args': {'model_name_or_path': '/workspace/Qwen/Qwen3-8B-Base', 'adapter_name_or_path': None, 'adapter_folder': None, 'cache_dir': None, 'use_fast_tokenizer': True, 'resize_vocab': False, 'split_special_tokens': False, 'add_tokens': None, 'add_special_tokens': None, 'new_special_tokens_config': None, 'init_special_tokens': 'noise_init', 'model_revision': 'main', 'low_cpu_mem_usage': True, 'rope_scaling': None, 'flash_attn': 'auto', 'shift_attn': False, 'mixture_of_depths': None, 'use_unsloth': False, 'use_unsloth_gc': False, 'enable_liger_kernel': False, 'moe_aux_loss_coef': None, 'disable_gradient_checkpointing': False, 'use_reentrant_gc': True, 'upcast_layernorm': False, 'upcast_lmhead_output': False, 'train_from_scratch': False, 'infer_backend': 'HF', 'offload_folder': 'offload', 'use_kv_cache': True, 'use_v1_kernels': False, 'infer_dtype': 'auto', 'hf_hub_token': '<HF_HUB_TOKEN>', 'ms_hub_token': '<MS_HUB_TOKEN>', 'om_hub_token': '<OM_HUB_TOKEN>', 'print_param_status': False, 'trust_remote_code': True, 'quantization_method': 'BNB', 'quantization_bit': None, 'quantization_type': 'nf4', 'double_quantization': True, 'quantization_device_map': None, 'image_max_pixels': 589824, 'image_min_pixels': 1024, 'image_do_pan_and_scan': False, 'crop_to_patches': False, 'video_max_pixels': 65536, 'video_min_pixels': 256, 'video_fps': 2.0, 'video_maxlen': 128, 'use_audio_in_video': False, 'audio_sampling_rate': 16000, 'export_dir': None, 'export_size': 5, 'export_device': 'cpu', 'export_quantization_bit': None, 'export_quantization_dataset': None, 'export_quantization_nsamples': 128, 'export_quantization_maxlen': 1024, 'export_legacy_format': False, 'export_hub_model_id': None, 'use_kt': False, 'kt_optimize_rule': None, 'cpu_infer': 32, 'chunk_size': 8192, 'mode': 'normal', 'kt_maxlen': 4096, 'kt_use_cuda_graph': True, 'kt_mode': 'normal', 'kt_force_think': False, 'vllm_maxlen': 4096, 'vllm_gpu_util': 0.7, 'vllm_enforce_eager': False, 'vllm_max_lora_rank': 32, 'vllm_config': None, 'sglang_maxlen': 4096, 'sglang_mem_fraction': 0.7, 'sglang_tp_size': -1, 'sglang_config': None, 'sglang_lora_backend': 'triton', 'compute_dtype': 'torch.bfloat16', 'device_map': {'': 'cuda:0'}, 'model_max_length': 2047, 'block_diag_attn': False}, 'data_args': {'template': 'qwen3_nothink', 'dataset': ['Markie_Voss_d10000'], 'eval_dataset': None, 'dataset_dir': '/workspace/LlamaFactory/data', 'media_dir': '/workspace/LlamaFactory/data', 'cutoff_len': 2047, 'train_on_prompt': False, 'mask_history': False, 'streaming': False, 'buffer_size': 16384, 'mix_strategy': 'concat', 'interleave_probs': None, 'overwrite_cache': False, 'preprocessing_batch_size': 1000, 'preprocessing_num_workers': 16, 'max_samples': 100000000, 'eval_num_beams': None, 'ignore_pad_token_for_loss': True, 'val_size': 0.0, 'eval_on_each_dataset': False, 'packing': True, 'neat_packing': False, 'tool_format': None, 'default_system': None, 'enable_thinking': False, 'tokenized_path': None, 'data_shared_file_system': False}, 'finetuning_args': {'freeze_trainable_layers': 2, 'freeze_trainable_modules': ['all'], 'freeze_extra_modules': None, 'additional_target': None, 'module_dropout': 0.0, 'oft_rank': 0, 'oft_block_size': 32, 'oft_target': ['all'], 'create_new_adapter': False, 'lora_alpha': 32, 'lora_dropout': 0.03, 'lora_rank': 16, 'lora_target': ['all'], 'loraplus_lr_ratio': None, 'loraplus_lr_embedding': 1e-06, 'use_rslora': False, 'use_dora': False, 'pissa_init': False, 'pissa_iter': 16, 'pissa_convert': False, 'pref_beta': 0.1, 'pref_ftx': 0.0, 'pref_bco_weight': 0.0, 'pref_loss': 'sigmoid', 'dpo_label_smoothing': 0.0, 'kto_chosen_weight': 1.0, 'kto_rejected_weight': 1.0, 'simpo_gamma': 0.5, 'ppo_buffer_size': 1, 'ppo_epochs': 4, 'ppo_score_norm': False, 'ppo_target': 6.0, 'ppo_whiten_rewards': False, 'ref_model': None, 'ref_model_adapters': None, 'ref_model_quantization_bit': None, 'reward_model': None, 'reward_model_adapters': None, 'reward_model_quantization_bit': None, 'reward_model_type': 'lora', 'ld_alpha': None, 'use_galore': False, 'galore_target': ['all'], 'galore_rank': 16, 'galore_update_interval': 200, 'galore_scale': 2.0, 'galore_proj_type': 'std', 'galore_layerwise': False, 'use_apollo': False, 'apollo_target': ['all'], 'apollo_rank': 16, 'apollo_update_interval': 200, 'apollo_scale': 32.0, 'apollo_proj': 'random', 'apollo_proj_type': 'std', 'apollo_scale_type': 'channel', 'apollo_layerwise': False, 'apollo_scale_front': False, 'use_badam': False, 'badam_mode': 'layer', 'badam_start_block': None, 'badam_switch_mode': 'ascending', 'badam_switch_interval': 50, 'badam_update_ratio': 0.05, 'badam_mask_mode': 'adjacent', 'badam_verbose': 0, 'use_swanlab': False, 'swanlab_project': 'llamafactory', 'swanlab_workspace': None, 'swanlab_run_name': None, 'swanlab_mode': 'cloud', 'swanlab_api_key': '<SWANLAB_API_KEY>', 'swanlab_logdir': None, 'swanlab_lark_webhook_url': None, 'swanlab_lark_secret': None, 'pure_bf16': False, 'stage': 'pt', 'finetuning_type': 'lora', 'use_llama_pro': False, 'use_adam_mini': False, 'use_mca': False, 'use_muon': False, 'use_dft_loss': False, 'use_eaft_loss': False, 'eaft_alpha': 1.0, 'freeze_vision_tower': True, 'freeze_multi_modal_projector': True, 'freeze_language_model': False, 'compute_accuracy': False, 'disable_shuffling': False, 'early_stopping_steps': None, 'plot_loss': True, 'include_effective_tokens_per_second': False}, 'generating_args': {'do_sample': True, 'temperature': 0.95, 'top_p': 0.7, 'top_k': 50, 'num_beams': 1, 'max_new_tokens': 1024, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'skip_special_tokens': True}}
+2026-02-09 08:34:18,628 INFO    wandb-AsyncioManager-main:863 [service_client.py:_forward_responses():94] Reached EOF.
+2026-02-09 08:34:18,630 INFO    wandb-AsyncioManager-main:863 [mailbox.py:close():154] Closing mailbox, abandoning 1 handles.

v127rc_exp2/B_mup/checkpoint-12800/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "/workspace/Qwen/Qwen3-8B-Base",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.03,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj",
+    "down_proj",
+    "up_proj",
+    "gate_proj",
+    "k_proj",
+    "o_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

v127rc_exp2/B_mup/checkpoint-12800/tokenizer_config.json

@@ -0,0 +1,19 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<think>",
+    "</think>"
+  ],
+  "is_local": true,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

v127rc_exp2/B_mup/checkpoint-12900/README.md

@@ -0,0 +1,208 @@
+---
+base_model: /workspace/Qwen/Qwen3-8B-Base
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:/workspace/Qwen/Qwen3-8B-Base
+- llama-factory
+- lora
+- transformers
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.1

v127rc_exp2/B_mup/checkpoint-12900/chat_template.jinja

@@ -0,0 +1,85 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set content = message.content %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in message.content %}
+                {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
+                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

v127rc_exp2/B_mup/checkpoint-12900/tokenizer_config.json

@@ -0,0 +1,19 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<think>",
+    "</think>"
+  ],
+  "is_local": true,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

v127rc_exp2/B_mup/checkpoint-13000/README.md

@@ -0,0 +1,208 @@
+---
+base_model: /workspace/Qwen/Qwen3-8B-Base
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:/workspace/Qwen/Qwen3-8B-Base
+- llama-factory
+- lora
+- transformers
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.1

v127rc_exp2/B_mup/checkpoint-13000/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "/workspace/Qwen/Qwen3-8B-Base",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.03,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj",
+    "down_proj",
+    "up_proj",
+    "gate_proj",
+    "k_proj",
+    "o_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

v127rc_exp2/B_mup/checkpoint-13000/chat_template.jinja

@@ -0,0 +1,85 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set content = message.content %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in message.content %}
+                {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
+                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}