Instructions to use praxisresearch/hf_olmo_32b_sgtr_0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use praxisresearch/hf_olmo_32b_sgtr_0 with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("unsloth/Olmo-3.1-32B-Instruct")
model = PeftModel.from_pretrained(base_model, "praxisresearch/hf_olmo_32b_sgtr_0")

Transformers

How to use praxisresearch/hf_olmo_32b_sgtr_0 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="praxisresearch/hf_olmo_32b_sgtr_0")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("praxisresearch/hf_olmo_32b_sgtr_0")
model = AutoModelForCausalLM.from_pretrained("praxisresearch/hf_olmo_32b_sgtr_0", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use praxisresearch/hf_olmo_32b_sgtr_0 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "praxisresearch/hf_olmo_32b_sgtr_0"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "praxisresearch/hf_olmo_32b_sgtr_0",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/praxisresearch/hf_olmo_32b_sgtr_0

SGLang

How to use praxisresearch/hf_olmo_32b_sgtr_0 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "praxisresearch/hf_olmo_32b_sgtr_0" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "praxisresearch/hf_olmo_32b_sgtr_0",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "praxisresearch/hf_olmo_32b_sgtr_0" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "praxisresearch/hf_olmo_32b_sgtr_0",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use praxisresearch/hf_olmo_32b_sgtr_0 with Docker Model Runner:
```
docker model run hf.co/praxisresearch/hf_olmo_32b_sgtr_0
```

hf_olmo_32b_sgtr_0 / debug.log

shawnolo

Upload model from models/hf_olmo_32b_sgtr_0

97c7eb9 verified 25 days ago

Raw

History Blame Contribute Delete

111 kB

	[2026-07-26 23:31:33,702] [DEBUG] [axolotl.utils.config.resolve_dtype:161] [PID:3930] bf16 support detected, enabling for this configuration.
	[2026-07-26 23:31:33,880] [DEBUG] [axolotl.utils.config.log_gpu_memory_usage:127] [PID:3930] baseline 0.000GB ()
	[2026-07-26 23:31:33,882] [INFO] [axolotl.cli.config.load_cfg:336] [PID:3930] config:
	{
	"activation_offloading": false,
	"adapter": "lora",
	"attn_decontaminates_packing": false,
	"attn_needs_dtype_cast": false,
	"attn_supports_packing": false,
	"attn_uses_flash_lib": false,
	"axolotl_config_path": "finetuning/axolotl/configs/olmo_32b/olmo_32b_sgtr/hf_olmo_32b_sgtr_0.yaml",
	"base_model": "unsloth/Olmo-3.1-32B-Instruct",
	"base_model_config": "unsloth/Olmo-3.1-32B-Instruct",
	"batch_size": 16,
	"bf16": true,
	"capabilities": {
	"bf16": true,
	"compute_capability": "sm_90",
	"fp8": true,
	"n_gpu": 1,
	"n_node": 1,
	"tf32": true
	},
	"context_parallel_size": 1,
	"dataloader_num_workers": 1,
	"dataloader_pin_memory": true,
	"dataloader_prefetch_factor": 256,
	"dataset_num_proc": 72,
	"datasets": [
	{
	"chat_template": "tokenizer_default",
	"message_property_mappings": {
	"content": "content",
	"role": "role"
	},
	"path": "data/finetuning/sgtr/detection/prefer-self-finetune_target_hf_olmo_32b_other-models__claude-21__finetuningdata.jsonl",
	"roles": {
	"assistant": [
	"assistant"
	],
	"system": [
	"system"
	],
	"user": [
	"user"
	]
	},
	"trust_remote_code": false,
	"type": "chat_template"
	}
	],
	"ddp": false,
	"device": "cuda:0",
	"device_map": "auto",
	"dion_rank_fraction": 1.0,
	"dion_rank_multiple_of": 1,
	"do_bench_eval": false,
	"eaft_alpha": 1.0,
	"eaft_k": 20,
	"env_capabilities": {
	"torch_version": "2.10.0"
	},
	"eval_batch_size": 2,
	"eval_causal_lm_metrics": [
	"sacrebleu",
	"comet",
	"ter",
	"chrf"
	],
	"eval_max_new_tokens": 128,
	"eval_sample_packing": false,
	"eval_table_size": 0,
	"experimental_skip_move_to_device": true,
	"fp16": false,
	"generate_samples": false,
	"generation_do_sample": true,
	"generation_max_new_tokens": 50,
	"generation_prompt_ratio": 0.5,
	"generation_temperature": 0.7,
	"gradient_accumulation_steps": 8,
	"gradient_checkpointing": true,
	"gradient_checkpointing_kwargs": {
	"use_reentrant": false
	},
	"group_by_length": false,
	"hub_model_id": "praxisresearch/hf_olmo_32b_sgtr_0",
	"hub_strategy": "every_save",
	"include_tkps": true,
	"is_falcon_derived_model": false,
	"is_llama_derived_model": false,
	"is_mistral_derived_model": false,
	"layer_offloading": false,
	"learning_rate": 1e-05,
	"lisa_layers_attribute": "model.layers",
	"load_best_model_at_end": false,
	"load_in_4bit": false,
	"load_in_8bit": false,
	"local_rank": 0,
	"logging_steps": 1,
	"lora_alpha": 64,
	"lora_dropout": 0.0,
	"lora_fan_in_fan_out": false,
	"lora_mlp_kernel": false,
	"lora_model_dir": "models/hf_olmo_32b_sgtr_0",
	"lora_o_kernel": false,
	"lora_qkv_kernel": false,
	"lora_r": 32,
	"lora_target_linear": true,
	"loraplus_lr_embedding": 1e-06,
	"lr_scheduler": "linear",
	"mean_resizing_embeddings": false,
	"merge_method": "memory_efficient",
	"micro_batch_size": 2,
	"model_config_type": "olmo3",
	"num_epochs": 1.0,
	"num_generation_samples": 3,
	"optimizer": "adamw_8bit",
	"otel_metrics_host": "localhost",
	"otel_metrics_port": 8000,
	"output_dir": "models/hf_olmo_32b_sgtr_0",
	"pad_to_sequence_len": false,
	"peft_use_dora": false,
	"peft_use_rslora": true,
	"pretrain_multipack_attn": true,
	"profiler_steps_start": 0,
	"qgalore_cos_threshold": 0.4,
	"qgalore_gamma_proj": 2,
	"qgalore_proj_bits": 4,
	"qgalore_proj_group_size": 256,
	"qgalore_proj_quant": true,
	"qgalore_proj_type": "std",
	"qgalore_queue_size": 5,
	"qgalore_rank": 256,
	"qgalore_scale": 0.25,
	"qgalore_update_proj_gap": 200,
	"qlora_sharded_model_loading": false,
	"quantize_moe_experts": false,
	"ray_num_workers": 1,
	"relora_prune_method": "magnitude",
	"resources_per_worker": {
	"GPU": 1
	},
	"rl_beta": 0.1,
	"sample_packing_bin_size": 200,
	"sample_packing_group_size": 100000,
	"save_only_model": false,
	"save_safetensors": true,
	"saves_per_epoch": 1,
	"seed": 0,
	"sequence_len": 2048,
	"shuffle_before_merging_datasets": false,
	"shuffle_merged_datasets": true,
	"skip_prepare_dataset": false,
	"streaming_multipack_buffer_size": 10000,
	"strict": false,
	"tensor_parallel_size": 1,
	"tf32": false,
	"tiled_mlp_use_original_mlp": true,
	"tokenizer_config": "unsloth/Olmo-3.1-32B-Instruct",
	"tokenizer_save_jinja_files": true,
	"tokenizer_type": "AutoTokenizer",
	"torch_dtype": "torch.bfloat16",
	"train_on_inputs": false,
	"trl": {
	"async_prefetch": false,
	"log_completions": false,
	"mask_truncated_completions": false,
	"ref_model_mixup_alpha": 0.9,
	"ref_model_sync_steps": 64,
	"replay_buffer_size": 0,
	"replay_recompute_logps": true,
	"reroll_max_groups": 1,
	"reroll_start_fraction": 1.0,
	"reward_num_workers": 1,
	"scale_rewards": true,
	"skip_zero_advantage_batches": true,
	"sync_ref_model": false,
	"use_data_producer": false,
	"use_vllm": false,
	"vllm_lora_sync": false,
	"vllm_server_host": "0.0.0.0",
	"vllm_server_port": 8000
	},
	"type_of_model": "AutoModelForCausalLM",
	"use_otel_metrics": false,
	"use_ray": false,
	"use_wandb": true,
	"val_set_size": 0.0,
	"vllm": {
	"device": "auto",
	"dtype": "auto",
	"gpu_memory_utilization": 0.9,
	"host": "0.0.0.0",
	"port": 8000
	},
	"wandb_project": "hf_olmo_32b_sgtr_0",
	"warmup_steps": 5,
	"weight_decay": 0.01,
	"world_size": 1
	}
	[2026-07-26 23:31:33,895] [WARNING] [axolotl.utils.schemas.utils.handle_legacy_message_fields_logic:38] [PID:3930] message_field_role is deprecated, use message_property_mappings instead. Example: message_property_mappings: {role: role}
	[2026-07-26 23:31:33,896] [WARNING] [axolotl.utils.schemas.utils.handle_legacy_message_fields_logic:58] [PID:3930] message_field_content is deprecated, use message_property_mappings instead. Example: message_property_mappings: {content: content}
	[2026-07-26 23:31:33,896] [WARNING] [axolotl.utils.schemas.deprecated.validate_dpo_beta:56] [PID:3930] dpo_beta is deprecated, use rl_beta instead
	[2026-07-26 23:31:33,962] [DEBUG] [axolotl.utils.config.resolve_dtype:161] [PID:3930] bf16 support detected, enabling for this configuration.
	[2026-07-26 23:31:34,096] [DEBUG] [axolotl.utils.config.log_gpu_memory_usage:127] [PID:3930] baseline 0.000GB ()
	[2026-07-26 23:31:34,098] [INFO] [axolotl.cli.config.load_cfg:336] [PID:3930] config:
	{
	"activation_offloading": false,
	"adapter": "lora",
	"attn_decontaminates_packing": false,
	"attn_needs_dtype_cast": false,
	"attn_supports_packing": false,
	"attn_uses_flash_lib": false,
	"axolotl_config_path": "finetuning/axolotl/configs/olmo_32b/olmo_32b_sgtr/hf_olmo_32b_sgtr_0.yaml",
	"base_model": "unsloth/Olmo-3.1-32B-Instruct",
	"base_model_config": "unsloth/Olmo-3.1-32B-Instruct",
	"batch_size": 16,
	"bf16": true,
	"capabilities": {
	"bf16": true,
	"compute_capability": "sm_90",
	"fp8": true,
	"n_gpu": 1,
	"n_node": 1,
	"tf32": true
	},
	"context_parallel_size": 1,
	"dataloader_num_workers": 1,
	"dataloader_pin_memory": true,
	"dataloader_prefetch_factor": 256,
	"dataset_num_proc": 72,
	"datasets": [
	{
	"chat_template": "tokenizer_default",
	"message_property_mappings": {
	"content": "content",
	"role": "role"
	},
	"path": "data/finetuning/sgtr/detection/prefer-self-finetune_target_hf_olmo_32b_other-models__claude-21__finetuningdata.jsonl",
	"roles": {
	"assistant": [
	"assistant"
	],
	"system": [
	"system"
	],
	"user": [
	"user"
	]
	},
	"trust_remote_code": false,
	"type": "chat_template"
	}
	],
	"ddp": false,
	"device": "cuda:0",
	"device_map": "auto",
	"dion_rank_fraction": 1.0,
	"dion_rank_multiple_of": 1,
	"do_bench_eval": false,
	"eaft_alpha": 1.0,
	"eaft_k": 20,
	"env_capabilities": {
	"torch_version": "2.10.0"
	},
	"eval_batch_size": 2,
	"eval_causal_lm_metrics": [
	"sacrebleu",
	"comet",
	"ter",
	"chrf"
	],
	"eval_max_new_tokens": 128,
	"eval_sample_packing": false,
	"eval_table_size": 0,
	"experimental_skip_move_to_device": true,
	"fp16": false,
	"generate_samples": false,
	"generation_do_sample": true,
	"generation_max_new_tokens": 50,
	"generation_prompt_ratio": 0.5,
	"generation_temperature": 0.7,
	"gradient_accumulation_steps": 8,
	"gradient_checkpointing": true,
	"gradient_checkpointing_kwargs": {
	"use_reentrant": false
	},
	"group_by_length": false,
	"hub_model_id": "praxisresearch/hf_olmo_32b_sgtr_0",
	"hub_strategy": "every_save",
	"include_tkps": true,
	"is_falcon_derived_model": false,
	"is_llama_derived_model": false,
	"is_mistral_derived_model": false,
	"layer_offloading": false,
	"learning_rate": 1e-05,
	"lisa_layers_attribute": "model.layers",
	"load_best_model_at_end": false,
	"load_in_4bit": false,
	"load_in_8bit": false,
	"local_rank": 0,
	"logging_steps": 1,
	"lora_alpha": 64,
	"lora_dropout": 0.0,
	"lora_fan_in_fan_out": false,
	"lora_mlp_kernel": false,
	"lora_model_dir": "models/hf_olmo_32b_sgtr_0",
	"lora_o_kernel": false,
	"lora_qkv_kernel": false,
	"lora_r": 32,
	"lora_target_linear": true,
	"loraplus_lr_embedding": 1e-06,
	"lr_scheduler": "linear",
	"mean_resizing_embeddings": false,
	"merge_lora": true,
	"merge_method": "memory_efficient",
	"micro_batch_size": 2,
	"model_config_type": "olmo3",
	"num_epochs": 1.0,
	"num_generation_samples": 3,
	"optimizer": "adamw_8bit",
	"otel_metrics_host": "localhost",
	"otel_metrics_port": 8000,
	"output_dir": "models/hf_olmo_32b_sgtr_0",
	"pad_to_sequence_len": false,
	"peft_use_dora": false,
	"peft_use_rslora": true,
	"pretrain_multipack_attn": true,
	"profiler_steps_start": 0,
	"qgalore_cos_threshold": 0.4,
	"qgalore_gamma_proj": 2,
	"qgalore_proj_bits": 4,
	"qgalore_proj_group_size": 256,
	"qgalore_proj_quant": true,
	"qgalore_proj_type": "std",
	"qgalore_queue_size": 5,
	"qgalore_rank": 256,
	"qgalore_scale": 0.25,
	"qgalore_update_proj_gap": 200,
	"qlora_sharded_model_loading": false,
	"quantize_moe_experts": false,
	"ray_num_workers": 1,
	"relora_prune_method": "magnitude",
	"resources_per_worker": {
	"GPU": 1
	},
	"rl_beta": 0.1,
	"sample_packing_bin_size": 200,
	"sample_packing_group_size": 100000,
	"save_only_model": false,
	"save_safetensors": true,
	"saves_per_epoch": 1,
	"seed": 0,
	"sequence_len": 2048,
	"shuffle_before_merging_datasets": false,
	"shuffle_merged_datasets": true,
	"skip_prepare_dataset": false,
	"streaming_multipack_buffer_size": 10000,
	"strict": false,
	"tensor_parallel_size": 1,
	"tf32": false,
	"tiled_mlp_use_original_mlp": true,
	"tokenizer_config": "unsloth/Olmo-3.1-32B-Instruct",
	"tokenizer_save_jinja_files": true,
	"tokenizer_type": "AutoTokenizer",
	"torch_dtype": "torch.bfloat16",
	"train_on_inputs": false,
	"trl": {
	"async_prefetch": false,
	"log_completions": false,
	"mask_truncated_completions": false,
	"ref_model_mixup_alpha": 0.9,
	"ref_model_sync_steps": 64,
	"replay_buffer_size": 0,
	"replay_recompute_logps": true,
	"reroll_max_groups": 1,
	"reroll_start_fraction": 1.0,
	"reward_num_workers": 1,
	"scale_rewards": true,
	"skip_zero_advantage_batches": true,
	"sync_ref_model": false,
	"use_data_producer": false,
	"use_vllm": false,
	"vllm_lora_sync": false,
	"vllm_server_host": "0.0.0.0",
	"vllm_server_port": 8000
	},
	"type_of_model": "AutoModelForCausalLM",
	"use_otel_metrics": false,
	"use_ray": false,
	"use_wandb": true,
	"val_set_size": 0.0,
	"vllm": {
	"device": "auto",
	"dtype": "auto",
	"gpu_memory_utilization": 0.9,
	"host": "0.0.0.0",
	"port": 8000
	},
	"wandb_project": "hf_olmo_32b_sgtr_0",
	"warmup_steps": 5,
	"weight_decay": 0.01,
	"world_size": 1
	}
	[2026-07-26 23:31:34,100] [DEBUG] [axolotl.cli.merge_lora.do_merge_lora:32] [PID:3930] Using memory-efficient LoRA merging method...
	[2026-07-26 23:31:34,100] [DEBUG] [axolotl.cli.merge_lora._do_merge_lora_efficient:79] [PID:3930] Using memory-efficient LoRA merging method...
	Fetching 26 files: 0%\| \| 0/26 [00:00<?, ?it/s] Fetching 26 files: 4%\|▍ \| 1/26 [00:00<00:06, 3.74it/s] Fetching 26 files: 23%\|██▎ \| 6/26 [00:00<00:01, 14.61it/s] Fetching 26 files: 85%\|████████▍ \| 22/26 [00:01<00:00, 15.86it/s] Fetching 26 files: 100%\|██████████\| 26/26 [00:01<00:00, 17.83it/s]
	[2026-07-26 23:31:36,310] [DEBUG] [axolotl.cli.utils.lora_merge._build_layer_type_map:112] [PID:3930] Could not instantiate meta model with AutoModelForImageTextToText, trying next
	[2026-07-26 23:31:36,379] [DEBUG] [axolotl.cli.utils.lora_merge._build_layer_type_map:133] [PID:3930] Layer type map: 449 modules (0 conv layers)
	[2026-07-26 23:31:36,380] [DEBUG] [axolotl.cli.utils.lora_merge.merge_lora_sharded_efficient:2002] [PID:3930] LoRA scale factor: 11.31370849898476 (rslora=True)
	[2026-07-26 23:31:36,380] [DEBUG] [axolotl.cli.utils.lora_merge.merge_lora_sharded_efficient:2018] [PID:3930] Loading LoRA weights from models/hf_olmo_32b_sgtr_0/adapter_model.safetensors
	[2026-07-26 23:31:36,395] [DEBUG] [axolotl.cli.utils.lora_merge.merge_lora_sharded_efficient:2024] [PID:3930] Keeping LoRA weights on CPU; will move per-tensor during merge
	[2026-07-26 23:31:36,396] [DEBUG] [axolotl.cli.utils.lora_merge.merge_lora_sharded_efficient:2030] [PID:3930] Found 14 model shards in /workspace/data/huggingface-cache/hub/models--unsloth--Olmo-3.1-32B-Instruct/snapshots/e543e1a7057070133919c1976fea346b2dccd239
	[2026-07-26 23:31:36,397] [INFO] [axolotl.cli.utils.lora_merge.copy_non_model_files:544] [PID:3930] Copying non-model files to output directory...
	[2026-07-26 23:31:36,397] [DEBUG] [axolotl.cli.utils.lora_merge.copy_non_model_files:565] [PID:3930] Copying .gitattributes to output
	[2026-07-26 23:31:36,401] [DEBUG] [axolotl.cli.utils.lora_merge.copy_non_model_files:565] [PID:3930] Copying README.md to output
	[2026-07-26 23:31:36,405] [DEBUG] [axolotl.cli.utils.lora_merge.copy_non_model_files:565] [PID:3930] Copying chat_template.jinja to output
	[2026-07-26 23:31:36,409] [DEBUG] [axolotl.cli.utils.lora_merge.copy_non_model_files:565] [PID:3930] Copying config.json to output
	[2026-07-26 23:31:36,419] [DEBUG] [axolotl.cli.utils.lora_merge.copy_non_model_files:565] [PID:3930] Copying generation_config.json to output
	[2026-07-26 23:31:36,423] [DEBUG] [axolotl.cli.utils.lora_merge.copy_non_model_files:565] [PID:3930] Copying merges.txt to output
	[2026-07-26 23:31:36,427] [DEBUG] [axolotl.cli.utils.lora_merge.copy_non_model_files:565] [PID:3930] Copying olmo-instruct.png to output
	[2026-07-26 23:31:36,431] [DEBUG] [axolotl.cli.utils.lora_merge.copy_non_model_files:565] [PID:3930] Copying special_tokens_map.json to output
	[2026-07-26 23:31:36,434] [DEBUG] [axolotl.cli.utils.lora_merge.copy_non_model_files:565] [PID:3930] Copying tokenizer.json to output
	[2026-07-26 23:31:36,441] [DEBUG] [axolotl.cli.utils.lora_merge.copy_non_model_files:565] [PID:3930] Copying tokenizer_config.json to output
	[2026-07-26 23:31:36,445] [DEBUG] [axolotl.cli.utils.lora_merge.copy_non_model_files:565] [PID:3930] Copying vocab.json to output
	Merging shards: 0%\| \| 0/14 [00:00<?, ?it/s][2026-07-26 23:31:36,458] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.0.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32])
	[2026-07-26 23:31:38,706] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.0.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:31:40,000] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.0.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:31:41,302] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.0.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:31:41,350] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.0.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:31:41,594] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.0.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:31:41,833] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.0.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:31:41,875] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.1.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32])
	[2026-07-26 23:31:43,162] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.1.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:31:44,447] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.1.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:31:45,735] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.1.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:31:45,775] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.1.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:31:46,015] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.1.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:31:46,254] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.1.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:31:46,291] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.2.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32])
	[2026-07-26 23:31:47,575] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.2.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:31:48,856] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.2.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:31:50,138] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.2.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:31:50,177] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.2.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:31:50,416] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.2.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:31:50,655] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.2.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:31:50,694] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.3.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32])
	[2026-07-26 23:31:51,991] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.3.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:31:53,271] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.3.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:31:54,556] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.3.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:31:54,595] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.3.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:31:54,837] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.3.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:31:55,076] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.3.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:31:55,115] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.4.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:31:55,157] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.4.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	Merging shards: 7%\|▋ \| 1/14 [00:28<06:04, 28.01s/it][2026-07-26 23:32:04,697] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.4.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32])
	[2026-07-26 23:32:05,980] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.4.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:32:07,239] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.4.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:32:08,508] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.4.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:32:08,714] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.4.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:32:08,747] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.5.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32])
	[2026-07-26 23:32:10,010] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.5.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:32:11,269] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.5.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:32:12,523] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.5.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:32:12,556] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.5.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:32:12,791] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.5.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:32:13,026] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.5.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:32:13,069] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.6.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32])
	[2026-07-26 23:32:14,348] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.6.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:32:15,615] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.6.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:32:16,884] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.6.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:32:16,927] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.6.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:32:17,166] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.6.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:32:17,402] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.6.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:32:17,445] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.7.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32])
	[2026-07-26 23:32:18,717] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.7.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:32:19,982] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.7.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:32:21,249] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.7.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:32:21,283] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.7.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:32:21,522] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.7.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:32:21,761] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.7.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:32:21,804] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.8.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32])
	[2026-07-26 23:32:23,076] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.8.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:32:24,343] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.8.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:32:25,610] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.8.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:32:25,653] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.8.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:32:25,891] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.8.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:32:26,127] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.8.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:32:26,169] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.9.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:32:26,212] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.9.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:32:26,448] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.9.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:32:26,683] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.9.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	Merging shards: 14%\|█▍ \| 2/14 [00:55<05:31, 27.65s/it][2026-07-26 23:32:32,027] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.10.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32])
	[2026-07-26 23:32:33,321] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.10.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:32:34,597] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.10.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:32:35,871] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.10.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:32:35,909] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.10.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:32:36,077] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.10.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:32:36,241] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.10.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:32:36,278] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.11.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32])
	[2026-07-26 23:32:37,553] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.11.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:32:38,827] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.11.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:32:40,116] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.11.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:32:40,156] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.11.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:32:40,364] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.11.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:32:40,602] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.11.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:32:40,639] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.12.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32])
	[2026-07-26 23:32:41,914] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.12.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:32:43,192] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.12.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:32:44,478] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.12.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:32:44,518] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.12.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:32:44,760] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.12.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:32:44,999] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.12.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:32:45,042] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.13.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32])
	[2026-07-26 23:32:46,313] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.13.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:32:47,587] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.13.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:32:48,862] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.13.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:32:48,905] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.13.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:32:49,145] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.13.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:32:49,386] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.13.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:32:49,429] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.14.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:32:49,472] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.14.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:32:49,712] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.14.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:32:49,953] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.14.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:32:50,002] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.9.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32])
	[2026-07-26 23:32:51,295] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.9.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:32:52,574] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.9.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	Merging shards: 21%\|██▏ \| 3/14 [01:21<04:54, 26.74s/it][2026-07-26 23:32:57,520] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.14.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32])
	[2026-07-26 23:32:58,632] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.14.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:32:59,495] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.14.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:33:00,353] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.15.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32])
	[2026-07-26 23:33:01,197] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.15.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:33:02,100] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.15.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:33:02,954] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.15.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:33:02,977] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.15.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:33:03,146] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.15.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:33:03,309] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.15.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:33:03,337] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.16.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32])
	[2026-07-26 23:33:04,187] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.16.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:33:05,040] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.16.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:33:05,912] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.16.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:33:05,943] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.16.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:33:06,107] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.16.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:33:06,268] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.16.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:33:06,298] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.17.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32])
	[2026-07-26 23:33:07,152] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.17.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:33:08,003] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.17.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:33:08,852] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.17.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:33:08,881] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.17.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:33:09,041] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.17.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:33:09,200] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.17.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:33:09,232] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.18.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32])
	[2026-07-26 23:33:10,126] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.18.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:33:10,988] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.18.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:33:11,836] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.18.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:33:11,865] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.18.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:33:12,033] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.18.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:33:12,193] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.18.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:33:12,222] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.19.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:33:12,256] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.19.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:33:12,424] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.19.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:33:12,591] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.19.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	Merging shards: 29%\|██▊ \| 4/14 [01:42<04:05, 24.53s/it][2026-07-26 23:33:18,919] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.19.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32])
	[2026-07-26 23:33:20,213] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.19.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:33:21,487] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.19.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:33:22,751] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.20.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32])
	[2026-07-26 23:33:24,024] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.20.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:33:25,302] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.20.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:33:26,575] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.20.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:33:26,609] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.20.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:33:26,762] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.20.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:33:26,972] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.20.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:33:27,006] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.21.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32])
	[2026-07-26 23:33:28,290] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.21.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:33:29,570] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.21.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:33:30,922] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.21.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:33:30,955] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.21.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:33:31,197] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.21.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:33:31,437] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.21.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:33:31,471] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.22.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32])
	[2026-07-26 23:33:32,746] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.22.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:33:34,026] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.22.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:33:35,306] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.22.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:33:35,345] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.22.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:33:35,585] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.22.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:33:35,826] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.22.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:33:35,859] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.23.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32])
	[2026-07-26 23:33:37,135] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.23.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:33:38,404] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.23.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:33:39,675] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.23.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:33:39,713] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.23.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:33:39,952] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.23.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:33:40,189] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.23.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:33:40,232] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.24.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:33:40,266] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.24.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:33:40,502] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.24.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:33:40,740] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.24.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	Merging shards: 36%\|███▌ \| 5/14 [02:11<03:56, 26.23s/it][2026-07-26 23:33:48,092] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.24.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32])
	[2026-07-26 23:33:49,398] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.24.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:33:50,688] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.24.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:33:51,960] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.25.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32])
	[2026-07-26 23:33:53,232] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.25.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:33:54,503] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.25.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:33:55,780] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.25.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:33:55,814] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.25.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:33:55,968] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.25.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:33:56,177] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.25.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:33:56,211] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.26.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32])
	[2026-07-26 23:33:57,491] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.26.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:33:58,786] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.26.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:34:00,020] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.26.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:34:00,044] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.26.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:34:00,206] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.26.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:34:00,363] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.26.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:34:00,385] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.27.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32])
	[2026-07-26 23:34:01,234] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.27.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:34:02,079] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.27.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:34:02,927] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.27.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:34:02,949] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.27.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:34:03,117] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.27.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:34:03,276] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.27.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:34:03,298] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.28.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32])
	[2026-07-26 23:34:04,154] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.28.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:34:05,004] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.28.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:34:05,860] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.28.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:34:05,882] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.28.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:34:06,039] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.28.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:34:06,196] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.28.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:34:06,217] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.29.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:34:06,240] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.29.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:34:06,399] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.29.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:34:06,561] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.29.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	Merging shards: 43%\|████▎ \| 6/14 [02:31<03:13, 24.15s/it][2026-07-26 23:34:08,164] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.29.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32])
	[2026-07-26 23:34:09,014] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.29.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:34:09,847] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.29.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:34:10,677] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.30.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32])
	[2026-07-26 23:34:11,533] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.30.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:34:12,446] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.30.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:34:13,292] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.30.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:34:13,314] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.30.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:34:13,413] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.30.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:34:13,574] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.30.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:34:13,596] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.31.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32])
	[2026-07-26 23:34:14,493] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.31.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:34:15,337] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.31.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:34:16,188] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.31.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:34:16,210] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.31.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:34:16,371] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.31.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:34:16,531] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.31.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:34:16,553] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.32.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32])
	[2026-07-26 23:34:17,398] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.32.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:34:18,237] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.32.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:34:19,086] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.32.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:34:19,108] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.32.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:34:19,268] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.32.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:34:19,431] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.32.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:34:19,453] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.33.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32])
	[2026-07-26 23:34:20,312] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.33.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:34:21,160] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.33.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:34:22,015] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.33.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:34:22,039] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.33.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:34:22,216] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.33.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:34:22,385] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.33.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:34:22,408] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.34.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:34:22,440] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.34.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:34:22,600] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.34.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:34:22,760] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.34.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	Merging shards: 50%\|█████ \| 7/14 [02:50<02:36, 22.37s/it][2026-07-26 23:34:26,872] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.34.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32])
	[2026-07-26 23:34:27,747] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.34.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:34:28,606] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.34.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:34:29,524] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.35.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32])
	[2026-07-26 23:34:30,562] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.35.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:34:31,484] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.35.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:34:32,424] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.35.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:34:32,462] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.35.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:34:32,568] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.35.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:34:32,740] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.35.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:34:32,772] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.36.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32])
	[2026-07-26 23:34:33,647] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.36.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:34:34,534] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.36.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:34:35,382] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.36.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:34:35,405] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.36.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:34:35,576] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.36.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:34:35,737] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.36.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:34:35,760] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.37.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32])
	[2026-07-26 23:34:36,615] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.37.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:34:37,467] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.37.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:34:38,336] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.37.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:34:38,358] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.37.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:34:38,541] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.37.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:34:38,708] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.37.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:34:38,730] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.38.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32])
	[2026-07-26 23:34:39,609] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.38.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:34:40,460] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.38.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:34:41,309] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.38.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:34:41,332] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.38.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:34:41,498] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.38.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:34:41,658] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.38.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:34:41,681] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.39.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:34:41,706] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.39.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:34:41,871] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.39.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:34:42,031] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.39.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	Merging shards: 57%\|█████▋ \| 8/14 [03:13<02:15, 22.55s/it][2026-07-26 23:34:49,920] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.39.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32])
	[2026-07-26 23:34:51,411] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.39.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:34:52,856] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.39.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:34:54,314] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.40.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32])
	[2026-07-26 23:34:55,740] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.40.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:34:57,009] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.40.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:34:58,277] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.40.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:34:58,311] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.40.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:34:58,495] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.40.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:34:58,702] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.40.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:34:58,735] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.41.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32])
	[2026-07-26 23:35:00,014] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.41.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:35:01,293] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.41.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:35:02,582] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.41.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:35:02,617] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.41.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:35:02,881] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.41.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:35:03,121] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.41.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:35:03,155] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.42.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32])
	[2026-07-26 23:35:04,432] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.42.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:35:05,701] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.42.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:35:06,982] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.42.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:35:07,016] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.42.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:35:07,255] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.42.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:35:07,500] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.42.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:35:07,534] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.43.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32])
	[2026-07-26 23:35:08,810] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.43.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:35:10,085] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.43.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:35:11,359] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.43.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:35:11,393] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.43.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:35:11,633] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.43.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:35:11,889] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.43.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:35:11,932] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.44.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:35:11,982] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.44.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:35:12,261] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.44.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:35:12,546] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.44.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	Merging shards: 64%\|██████▍ \| 9/14 [03:39<01:57, 23.58s/it][2026-07-26 23:35:15,713] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.44.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32])
	[2026-07-26 23:35:17,097] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.44.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:35:18,361] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.44.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:35:19,628] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.45.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32])
	[2026-07-26 23:35:20,897] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.45.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:35:22,158] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.45.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:35:23,440] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.45.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:35:23,473] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.45.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:35:23,625] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.45.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:35:23,776] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.45.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:35:23,814] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.46.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32])
	[2026-07-26 23:35:25,087] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.46.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:35:26,366] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.46.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:35:27,636] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.46.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:35:27,670] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.46.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:35:27,911] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.46.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:35:28,160] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.46.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:35:28,197] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.47.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32])
	[2026-07-26 23:35:29,663] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.47.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:35:31,029] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.47.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:35:32,307] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.47.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:35:32,341] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.47.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:35:32,581] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.47.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:35:32,819] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.47.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:35:32,852] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.48.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32])
	[2026-07-26 23:35:34,130] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.48.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:35:35,396] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.48.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:35:36,661] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.48.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:35:36,695] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.48.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:35:36,935] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.48.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:35:37,179] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.48.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:35:37,213] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.49.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:35:37,285] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.49.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:35:37,535] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.49.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:35:37,774] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.49.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	Merging shards: 71%\|███████▏ \| 10/14 [04:04<01:36, 24.04s/it][2026-07-26 23:35:40,776] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.49.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32])
	[2026-07-26 23:35:42,182] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.49.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:35:43,454] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.49.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:35:44,725] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.50.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32])
	[2026-07-26 23:35:46,006] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.50.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:35:47,287] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.50.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:35:48,557] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.50.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:35:48,590] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.50.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:35:48,797] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.50.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:35:49,001] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.50.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:35:49,036] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.51.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32])
	[2026-07-26 23:35:50,340] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.51.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:35:51,610] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.51.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:35:52,655] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.51.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:35:52,677] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.51.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:35:52,839] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.51.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:35:52,998] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.51.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:35:53,020] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.52.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32])
	[2026-07-26 23:35:53,874] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.52.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:35:54,736] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.52.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:35:55,590] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.52.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:35:55,612] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.52.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:35:55,771] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.52.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:35:55,928] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.52.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:35:55,950] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.53.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32])
	[2026-07-26 23:35:56,803] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.53.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:35:57,652] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.53.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:35:58,505] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.53.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:35:58,527] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.53.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:35:58,686] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.53.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:35:58,847] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.53.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:35:58,870] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.54.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:35:58,897] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.54.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:35:59,056] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.54.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:35:59,221] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.54.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	Merging shards: 79%\|███████▊ \| 11/14 [04:25<01:09, 23.25s/it][2026-07-26 23:36:02,211] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.54.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32])
	[2026-07-26 23:36:03,544] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.54.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:36:04,842] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.54.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:36:06,120] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.55.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32])
	[2026-07-26 23:36:07,398] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.55.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:36:08,673] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.55.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:36:09,961] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.55.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:36:09,994] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.55.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:36:10,146] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.55.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:36:10,353] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.55.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:36:10,387] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.56.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32])
	[2026-07-26 23:36:11,666] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.56.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:36:12,947] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.56.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:36:14,235] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.56.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:36:14,268] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.56.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:36:14,477] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.56.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:36:14,714] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.56.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:36:14,748] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.57.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32])
	[2026-07-26 23:36:16,025] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.57.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:36:17,301] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.57.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:36:18,572] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.57.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:36:18,606] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.57.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:36:18,844] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.57.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:36:19,084] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.57.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:36:19,117] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.58.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32])
	[2026-07-26 23:36:20,408] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.58.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:36:21,681] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.58.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:36:22,952] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.58.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:36:22,986] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.58.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:36:23,229] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.58.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:36:23,469] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.58.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:36:23,502] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.59.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:36:23,535] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.59.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:36:23,773] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.59.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:36:24,009] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.59.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	Merging shards: 86%\|████████▌ \| 12/14 [04:50<00:47, 23.63s/it][2026-07-26 23:36:26,699] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.59.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32])
	[2026-07-26 23:36:28,008] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.59.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:36:29,298] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.59.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:36:30,585] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.60.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32])
	[2026-07-26 23:36:31,864] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.60.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:36:33,157] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.60.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:36:34,437] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.60.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:36:34,471] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.60.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:36:34,676] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.60.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:36:34,881] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.60.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:36:34,914] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.61.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32])
	[2026-07-26 23:36:36,202] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.61.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:36:37,484] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.61.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:36:38,760] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.61.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:36:38,793] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.61.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:36:38,999] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.61.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:36:39,236] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.61.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:36:39,269] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.62.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32])
	[2026-07-26 23:36:40,558] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.62.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:36:41,831] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.62.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:36:43,109] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.62.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:36:43,143] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.62.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:36:43,381] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.62.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:36:43,619] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.62.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:36:43,656] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.63.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32])
	[2026-07-26 23:36:45,016] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.63.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:36:46,295] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.63.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32])
	[2026-07-26 23:36:47,500] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.63.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	[2026-07-26 23:36:47,529] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.63.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:36:47,691] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.63.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32])
	[2026-07-26 23:36:47,851] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:1412] [PID:3930] Merging LoRA for model.layers.63.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32])
	Merging shards: 93%\|█████████▎\| 13/14 [05:12<00:23, 23.37s/it] Merging shards: 100%\|██████████\| 14/14 [05:13<00:00, 16.51s/it] Merging shards: 100%\|██████████\| 14/14 [05:13<00:00, 22.39s/it]
	[2026-07-26 23:36:49,936] [DEBUG] [axolotl.cli.utils.lora_merge.merge_lora_sharded_efficient:2259] [PID:3930] Wrote weight-map index: model.safetensors.index.json
	[2026-07-26 23:36:49,936] [INFO] [axolotl.cli.utils.lora_merge.merge_lora_sharded_efficient:2279] [PID:3930] Applied LoRA to 448/707 tensors
	[2026-07-26 23:36:49,998] [DEBUG] [axolotl.cli.merge_lora._do_merge_lora_efficient:123] [PID:3930] Memory-efficient LoRA merge completed successfully!