| [2026-07-18 05:06:59,677] [WARNING] [axolotl.utils.config.normalize_config:282] [PID:51437] Gemma4 requires use_reentrant=False for gradient checkpointing in distributed training. Setting use_reentrant=False. |
| [2026-07-18 05:06:59,678] [DEBUG] [axolotl.utils.config.log_gpu_memory_usage:127] [PID:51437] baseline 0.000GB () |
| [2026-07-18 05:06:59,679] [INFO] [axolotl.cli.config.load_cfg:333] [PID:51437] config: |
| { |
| "activation_offloading": false, |
| "adapter": "lora", |
| "attn_implementation": "sdpa", |
| "attn_needs_dtype_cast": false, |
| "attn_supports_packing": false, |
| "attn_uses_flash_lib": false, |
| "axolotl_config_path": "train.yaml", |
| "base_model": "google/gemma-4-26b-a4b-it", |
| "base_model_config": "google/gemma-4-26b-a4b-it", |
| "batch_size": 16, |
| "bf16": true, |
| "capabilities": { |
| "bf16": true, |
| "compute_capability": "sm_80", |
| "fp8": false, |
| "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": 16, |
| "datasets": [ |
| { |
| "chat_template": "tokenizer_default", |
| "message_property_mappings": { |
| "content": "content", |
| "role": "role" |
| }, |
| "path": "mixed_coding_traces.jsonl", |
| "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, |
| "eaft_alpha": 1.0, |
| "eaft_k": 20, |
| "env_capabilities": { |
| "torch_version": "2.10.0" |
| }, |
| "eval_batch_size": 1, |
| "eval_causal_lm_metrics": [ |
| "sacrebleu", |
| "comet", |
| "ter", |
| "chrf" |
| ], |
| "eval_max_new_tokens": 128, |
| "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": 16, |
| "gradient_checkpointing": true, |
| "gradient_checkpointing_kwargs": { |
| "use_reentrant": false |
| }, |
| "include_tkps": true, |
| "is_falcon_derived_model": false, |
| "is_llama_derived_model": false, |
| "is_mistral_derived_model": false, |
| "is_multimodal": true, |
| "layer_offloading": false, |
| "learning_rate": 0.0001, |
| "lisa_layers_attribute": "model.layers", |
| "load_best_model_at_end": false, |
| "load_in_4bit": false, |
| "load_in_8bit": false, |
| "local_rank": 0, |
| "logging_steps": 5, |
| "lora_alpha": 32, |
| "lora_dropout": 0.0, |
| "lora_model_dir": "./outputs/gemma4-26b-mixed/checkpoint-250", |
| "lora_r": 16, |
| "lora_target_modules": "model.language_model.layers.[\\d]+.(_checkpoint_wrapped_module.)?(mlp|self_attn).(up|down|gate|q|k|v|o)_proj", |
| "lora_target_parameters": [ |
| "experts.gate_up_proj", |
| "experts.down_proj" |
| ], |
| "loraplus_lr_embedding": 1e-06, |
| "lr_scheduler": "cosine", |
| "max_steps": 250, |
| "mean_resizing_embeddings": false, |
| "merge_method": "memory_efficient", |
| "micro_batch_size": 1, |
| "model_config_type": "gemma4", |
| "model_config_type_text": "gemma4_text", |
| "num_epochs": 1.0, |
| "num_generation_samples": 3, |
| "optimizer": "adamw_torch_fused", |
| "otel_metrics_host": "localhost", |
| "otel_metrics_port": 8000, |
| "output_dir": "./outputs/gemma4-26b-mixed", |
| "pretrain_multipack_attn": true, |
| "processor_config": "google/gemma-4-26b-a4b-it", |
| "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 |
| }, |
| "sample_packing_bin_size": 200, |
| "sample_packing_group_size": 100000, |
| "save_only_model": false, |
| "save_safetensors": true, |
| "save_steps": 50, |
| "sequence_len": 8192, |
| "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": true, |
| "tiled_mlp_use_original_mlp": true, |
| "tokenizer_config": "google/gemma-4-26b-a4b-it", |
| "tokenizer_save_jinja_files": true, |
| "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 |
| }, |
| "trust_remote_code": true, |
| "type_of_model": "gemma4_moe", |
| "use_otel_metrics": false, |
| "use_ray": false, |
| "val_set_size": 0.0, |
| "vllm": { |
| "device": "auto", |
| "dtype": "auto", |
| "gpu_memory_utilization": 0.9, |
| "host": "0.0.0.0", |
| "port": 8000 |
| }, |
| "warmup_steps": 20, |
| "weight_decay": 0.0, |
| "world_size": 1 |
| } |
| [2026-07-18 05:06:59,682] [WARNING] [axolotl.utils.schemas.model.hint_trust_remote_code:117] [PID:51437] `trust_remote_code` is set to true. Please make sure that you reviewed the remote code/model. |
| [2026-07-18 05:07:00,053] [WARNING] [axolotl.utils.config.normalize_config:282] [PID:51437] Gemma4 requires use_reentrant=False for gradient checkpointing in distributed training. Setting use_reentrant=False. |
| [2026-07-18 05:07:00,055] [DEBUG] [axolotl.utils.config.log_gpu_memory_usage:127] [PID:51437] baseline 0.000GB () |
| [2026-07-18 05:07:00,056] [INFO] [axolotl.cli.config.load_cfg:333] [PID:51437] config: |
| { |
| "activation_offloading": false, |
| "adapter": "lora", |
| "attn_needs_dtype_cast": false, |
| "attn_supports_packing": false, |
| "attn_uses_flash_lib": false, |
| "axolotl_config_path": "train.yaml", |
| "base_model": "google/gemma-4-26b-a4b-it", |
| "base_model_config": "google/gemma-4-26b-a4b-it", |
| "batch_size": 16, |
| "bf16": true, |
| "capabilities": { |
| "bf16": true, |
| "compute_capability": "sm_80", |
| "fp8": false, |
| "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": 16, |
| "datasets": [ |
| { |
| "chat_template": "tokenizer_default", |
| "message_property_mappings": { |
| "content": "content", |
| "role": "role" |
| }, |
| "path": "mixed_coding_traces.jsonl", |
| "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, |
| "eaft_alpha": 1.0, |
| "eaft_k": 20, |
| "env_capabilities": { |
| "torch_version": "2.10.0" |
| }, |
| "eval_batch_size": 1, |
| "eval_causal_lm_metrics": [ |
| "sacrebleu", |
| "comet", |
| "ter", |
| "chrf" |
| ], |
| "eval_max_new_tokens": 128, |
| "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": 16, |
| "gradient_checkpointing": true, |
| "gradient_checkpointing_kwargs": { |
| "use_reentrant": false |
| }, |
| "include_tkps": true, |
| "is_falcon_derived_model": false, |
| "is_llama_derived_model": false, |
| "is_mistral_derived_model": false, |
| "is_multimodal": true, |
| "layer_offloading": false, |
| "learning_rate": 0.0001, |
| "lisa_layers_attribute": "model.layers", |
| "load_best_model_at_end": false, |
| "load_in_4bit": false, |
| "load_in_8bit": false, |
| "local_rank": 0, |
| "logging_steps": 5, |
| "lora_alpha": 32, |
| "lora_dropout": 0.0, |
| "lora_model_dir": "./outputs/gemma4-26b-mixed/checkpoint-250", |
| "lora_r": 16, |
| "lora_target_modules": "model.language_model.layers.[\\d]+.(_checkpoint_wrapped_module.)?(mlp|self_attn).(up|down|gate|q|k|v|o)_proj", |
| "lora_target_parameters": [ |
| "experts.gate_up_proj", |
| "experts.down_proj" |
| ], |
| "loraplus_lr_embedding": 1e-06, |
| "lr_scheduler": "cosine", |
| "max_steps": 250, |
| "mean_resizing_embeddings": false, |
| "merge_lora": true, |
| "merge_method": "memory_efficient", |
| "micro_batch_size": 1, |
| "model_config_type": "gemma4", |
| "model_config_type_text": "gemma4_text", |
| "num_epochs": 1.0, |
| "num_generation_samples": 3, |
| "optimizer": "adamw_torch_fused", |
| "otel_metrics_host": "localhost", |
| "otel_metrics_port": 8000, |
| "output_dir": "./outputs/gemma4-26b-mixed", |
| "pretrain_multipack_attn": true, |
| "processor_config": "google/gemma-4-26b-a4b-it", |
| "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 |
| }, |
| "sample_packing_bin_size": 200, |
| "sample_packing_group_size": 100000, |
| "save_only_model": false, |
| "save_safetensors": true, |
| "save_steps": 50, |
| "sequence_len": 8192, |
| "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": true, |
| "tiled_mlp_use_original_mlp": true, |
| "tokenizer_config": "google/gemma-4-26b-a4b-it", |
| "tokenizer_save_jinja_files": true, |
| "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 |
| }, |
| "trust_remote_code": true, |
| "type_of_model": "gemma4_moe", |
| "use_otel_metrics": false, |
| "use_ray": false, |
| "val_set_size": 0.0, |
| "vllm": { |
| "device": "auto", |
| "dtype": "auto", |
| "gpu_memory_utilization": 0.9, |
| "host": "0.0.0.0", |
| "port": 8000 |
| }, |
| "warmup_steps": 20, |
| "weight_decay": 0.0, |
| "world_size": 1 |
| } |
|
Downloading (incomplete total...): 0.00B [00:00, ?B/s] |
|
Fetching 12 files: 0%| | 0/12 [00:00<?, ?it/s][A
Downloading (incomplete total...): 0%| | 0.00/1.71k [00:00<?, ?B/s]
Downloading (incomplete total...): 100%|██████████████████| 1.71k/1.71k [00:00<00:00, 2.70kB/s]
Downloading (incomplete total...): 6%|█ | 1.71k/29.6k [00:00<00:10, 2.70kB/s]
Downloading (incomplete total...): 99%|█████████████████▉| 29.6k/29.8k [00:00<00:00, 2.70kB/s] |
|
Fetching 12 files: 8%|███▎ | 1/12 [00:00<00:07, 1.43it/s][A
Fetching 12 files: 100%|███████████████████████████████████████| 12/12 [00:00<00:00, 16.53it/s] |
|
Download complete: 100%|██████████████████████████████████| 29.8k/29.8k [00:00<00:00, 2.70kB/s][2026-07-18 05:07:01,277] [DEBUG] [axolotl.cli.utils.lora_merge._build_layer_type_map:100] [PID:51437] Layer type map: 427 modules (0 conv layers) |
| [2026-07-18 05:07:01,277] [DEBUG] [axolotl.cli.utils.lora_merge.merge_lora_sharded_efficient:1076] [PID:51437] LoRA scale factor: 2.0 (rslora=False) |
| [2026-07-18 05:07:01,277] [DEBUG] [axolotl.cli.utils.lora_merge.merge_lora_sharded_efficient:1092] [PID:51437] Loading LoRA weights from outputs/gemma4-26b-mixed/checkpoint-250/adapter_model.safetensors |
| [2026-07-18 05:07:01,287] [DEBUG] [axolotl.cli.utils.lora_merge.merge_lora_sharded_efficient:1098] [PID:51437] Keeping LoRA weights on CPU; will move per-tensor during merge |
| [2026-07-18 05:07:01,289] [DEBUG] [axolotl.cli.utils.lora_merge.merge_lora_sharded_efficient:1104] [PID:51437] Found 2 model shards in /workspace/data/huggingface-cache/hub/models--google--gemma-4-26b-a4b-it/snapshots/01e5b3ee840d3a9e0b0b493c593e85398a30ef75 |
| [2026-07-18 05:07:01,289] [INFO] [axolotl.cli.utils.lora_merge.copy_non_model_files:494] [PID:51437] Copying non-model files to output directory... |
| [2026-07-18 05:07:01,295] [DEBUG] [axolotl.cli.utils.lora_merge.copy_non_model_files:515] [PID:51437] Copying .gitattributes to output |
| [2026-07-18 05:07:01,312] [DEBUG] [axolotl.cli.utils.lora_merge.copy_non_model_files:515] [PID:51437] Copying README.md to output |
| [2026-07-18 05:07:01,325] [DEBUG] [axolotl.cli.utils.lora_merge.copy_non_model_files:515] [PID:51437] Copying generation_config.json to output |
| [2026-07-18 05:07:01,341] [DEBUG] [axolotl.cli.utils.lora_merge.copy_non_model_files:515] [PID:51437] Copying processor_config.json to output |
| [2026-07-18 05:07:01,354] [DEBUG] [axolotl.cli.utils.lora_merge.copy_non_model_files:515] [PID:51437] Copying chat_template.jinja to output |
| [2026-07-18 05:07:01,366] [DEBUG] [axolotl.cli.utils.lora_merge.copy_non_model_files:515] [PID:51437] Copying tokenizer.json to output |
| [2026-07-18 05:07:01,521] [DEBUG] [axolotl.cli.utils.lora_merge.copy_non_model_files:515] [PID:51437] Copying tokenizer_config.json to output |
| [2026-07-18 05:07:01,532] [DEBUG] [axolotl.cli.utils.lora_merge.copy_non_model_files:515] [PID:51437] Copying config.json to output |
|
|
|
Merging shards: 0%| | 0/2 [00:00<?, ?it/s][A
Download complete: 100%|██████████████████████████████████| 29.8k/29.8k [00:11<00:00, 2.70kB/s][2026-07-18 05:07:14,713] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.0.mlp.down_proj.weight: torch.Size([16, 2112]), torch.Size([2816, 16]) |
| [2026-07-18 05:07:15,310] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.0.mlp.gate_proj.weight: torch.Size([16, 2816]), torch.Size([2112, 16]) |
| [2026-07-18 05:07:15,488] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.0.mlp.up_proj.weight: torch.Size([16, 2816]), torch.Size([2112, 16]) |
| [2026-07-18 05:07:15,543] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.0.self_attn.k_proj.weight: torch.Size([16, 2816]), torch.Size([2048, 16]) |
| [2026-07-18 05:07:15,598] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.0.self_attn.o_proj.weight: torch.Size([16, 4096]), torch.Size([2816, 16]) |
| [2026-07-18 05:07:15,726] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.0.self_attn.q_proj.weight: torch.Size([16, 2816]), torch.Size([4096, 16]) |
| [2026-07-18 05:07:15,900] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.0.self_attn.v_proj.weight: torch.Size([16, 2816]), torch.Size([2048, 16]) |
| [2026-07-18 05:07:15,949] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.1.mlp.down_proj.weight: torch.Size([16, 2112]), torch.Size([2816, 16]) |
| [2026-07-18 05:07:16,019] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.1.mlp.gate_proj.weight: torch.Size([16, 2816]), torch.Size([2112, 16]) |
| [2026-07-18 05:07:16,070] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.1.mlp.up_proj.weight: torch.Size([16, 2816]), torch.Size([2112, 16]) |
| [2026-07-18 05:07:16,143] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.1.self_attn.k_proj.weight: torch.Size([16, 2816]), torch.Size([2048, 16]) |
| [2026-07-18 05:07:16,226] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.1.self_attn.o_proj.weight: torch.Size([16, 4096]), torch.Size([2816, 16]) |
| [2026-07-18 05:07:16,396] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.1.self_attn.q_proj.weight: torch.Size([16, 2816]), torch.Size([4096, 16]) |
| [2026-07-18 05:07:16,489] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.1.self_attn.v_proj.weight: torch.Size([16, 2816]), torch.Size([2048, 16]) |
| [2026-07-18 05:07:16,532] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.10.mlp.down_proj.weight: torch.Size([16, 2112]), torch.Size([2816, 16]) |
| [2026-07-18 05:07:16,748] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.10.mlp.gate_proj.weight: torch.Size([16, 2816]), torch.Size([2112, 16]) |
| [2026-07-18 05:07:16,898] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.10.mlp.up_proj.weight: torch.Size([16, 2816]), torch.Size([2112, 16]) |
| [2026-07-18 05:07:17,073] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.10.self_attn.k_proj.weight: torch.Size([16, 2816]), torch.Size([2048, 16]) |
| [2026-07-18 05:07:17,220] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.10.self_attn.o_proj.weight: torch.Size([16, 4096]), torch.Size([2816, 16]) |
| [2026-07-18 05:07:17,357] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.10.self_attn.q_proj.weight: torch.Size([16, 2816]), torch.Size([4096, 16]) |
| [2026-07-18 05:07:17,465] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.10.self_attn.v_proj.weight: torch.Size([16, 2816]), torch.Size([2048, 16]) |
| [2026-07-18 05:07:17,508] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.11.self_attn.k_proj.weight: torch.Size([16, 2816]), torch.Size([1024, 16]) |
| [2026-07-18 05:07:17,542] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.11.self_attn.o_proj.weight: torch.Size([16, 8192]), torch.Size([2816, 16]) |
| [2026-07-18 05:07:17,967] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.11.self_attn.q_proj.weight: torch.Size([16, 2816]), torch.Size([8192, 16]) |
| [2026-07-18 05:07:18,157] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.12.mlp.down_proj.weight: torch.Size([16, 2112]), torch.Size([2816, 16]) |
| [2026-07-18 05:07:18,331] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.12.mlp.gate_proj.weight: torch.Size([16, 2816]), torch.Size([2112, 16]) |
| [2026-07-18 05:07:18,484] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.12.mlp.up_proj.weight: torch.Size([16, 2816]), torch.Size([2112, 16]) |
| [2026-07-18 05:07:18,617] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.12.self_attn.k_proj.weight: torch.Size([16, 2816]), torch.Size([2048, 16]) |
| [2026-07-18 05:07:18,680] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.12.self_attn.o_proj.weight: torch.Size([16, 4096]), torch.Size([2816, 16]) |
| [2026-07-18 05:07:18,808] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.12.self_attn.q_proj.weight: torch.Size([16, 2816]), torch.Size([4096, 16]) |
| [2026-07-18 05:07:18,900] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.12.self_attn.v_proj.weight: torch.Size([16, 2816]), torch.Size([2048, 16]) |
| [2026-07-18 05:07:18,938] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.13.mlp.down_proj.weight: torch.Size([16, 2112]), torch.Size([2816, 16]) |
| [2026-07-18 05:07:19,012] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.13.mlp.gate_proj.weight: torch.Size([16, 2816]), torch.Size([2112, 16]) |
| [2026-07-18 05:07:19,094] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.13.mlp.up_proj.weight: torch.Size([16, 2816]), torch.Size([2112, 16]) |
| [2026-07-18 05:07:19,139] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.13.self_attn.k_proj.weight: torch.Size([16, 2816]), torch.Size([2048, 16]) |
| [2026-07-18 05:07:19,210] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.13.self_attn.o_proj.weight: torch.Size([16, 4096]), torch.Size([2816, 16]) |
| [2026-07-18 05:07:19,295] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.13.self_attn.q_proj.weight: torch.Size([16, 2816]), torch.Size([4096, 16]) |
| [2026-07-18 05:07:19,384] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.13.self_attn.v_proj.weight: torch.Size([16, 2816]), torch.Size([2048, 16]) |
| [2026-07-18 05:07:19,430] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.14.mlp.down_proj.weight: torch.Size([16, 2112]), torch.Size([2816, 16]) |
| [2026-07-18 05:07:19,607] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.14.mlp.gate_proj.weight: torch.Size([16, 2816]), torch.Size([2112, 16]) |
| [2026-07-18 05:07:19,799] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.14.mlp.up_proj.weight: torch.Size([16, 2816]), torch.Size([2112, 16]) |
| [2026-07-18 05:07:19,888] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.14.self_attn.k_proj.weight: torch.Size([16, 2816]), torch.Size([2048, 16]) |
| [2026-07-18 05:07:19,940] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.14.self_attn.o_proj.weight: torch.Size([16, 4096]), torch.Size([2816, 16]) |
| [2026-07-18 05:07:20,043] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.14.self_attn.q_proj.weight: torch.Size([16, 2816]), torch.Size([4096, 16]) |
| [2026-07-18 05:07:20,135] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.14.self_attn.v_proj.weight: torch.Size([16, 2816]), torch.Size([2048, 16]) |
| [2026-07-18 05:07:20,179] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.15.mlp.down_proj.weight: torch.Size([16, 2112]), torch.Size([2816, 16]) |
| [2026-07-18 05:07:20,239] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.15.mlp.gate_proj.weight: torch.Size([16, 2816]), torch.Size([2112, 16]) |
| [2026-07-18 05:07:20,315] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.15.mlp.up_proj.weight: torch.Size([16, 2816]), torch.Size([2112, 16]) |
| [2026-07-18 05:07:20,355] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.15.self_attn.k_proj.weight: torch.Size([16, 2816]), torch.Size([2048, 16]) |
| [2026-07-18 05:07:20,397] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.15.self_attn.o_proj.weight: torch.Size([16, 4096]), torch.Size([2816, 16]) |
| [2026-07-18 05:07:20,488] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.15.self_attn.q_proj.weight: torch.Size([16, 2816]), torch.Size([4096, 16]) |
| [2026-07-18 05:07:20,575] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.15.self_attn.v_proj.weight: torch.Size([16, 2816]), torch.Size([2048, 16]) |
| [2026-07-18 05:07:20,628] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.16.mlp.down_proj.weight: torch.Size([16, 2112]), torch.Size([2816, 16]) |
| [2026-07-18 05:07:20,791] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.16.mlp.gate_proj.weight: torch.Size([16, 2816]), torch.Size([2112, 16]) |
| [2026-07-18 05:07:21,000] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.16.mlp.up_proj.weight: torch.Size([16, 2816]), torch.Size([2112, 16]) |
| [2026-07-18 05:07:21,087] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.16.self_attn.k_proj.weight: torch.Size([16, 2816]), torch.Size([2048, 16]) |
| [2026-07-18 05:07:21,126] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.16.self_attn.o_proj.weight: torch.Size([16, 4096]), torch.Size([2816, 16]) |
| [2026-07-18 05:07:21,244] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.16.self_attn.q_proj.weight: torch.Size([16, 2816]), torch.Size([4096, 16]) |
| [2026-07-18 05:07:21,343] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.16.self_attn.v_proj.weight: torch.Size([16, 2816]), torch.Size([2048, 16]) |
| [2026-07-18 05:07:21,394] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.17.self_attn.k_proj.weight: torch.Size([16, 2816]), torch.Size([1024, 16]) |
| [2026-07-18 05:07:21,431] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.17.self_attn.o_proj.weight: torch.Size([16, 8192]), torch.Size([2816, 16]) |
| [2026-07-18 05:07:21,639] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.17.self_attn.q_proj.weight: torch.Size([16, 2816]), torch.Size([8192, 16]) |
| [2026-07-18 05:07:21,818] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.18.mlp.down_proj.weight: torch.Size([16, 2112]), torch.Size([2816, 16]) |
| [2026-07-18 05:07:21,885] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.18.mlp.gate_proj.weight: torch.Size([16, 2816]), torch.Size([2112, 16]) |
| [2026-07-18 05:07:21,940] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.18.mlp.up_proj.weight: torch.Size([16, 2816]), torch.Size([2112, 16]) |
| [2026-07-18 05:07:21,980] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.18.self_attn.k_proj.weight: torch.Size([16, 2816]), torch.Size([2048, 16]) |
| [2026-07-18 05:07:22,052] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.18.self_attn.o_proj.weight: torch.Size([16, 4096]), torch.Size([2816, 16]) |
| [2026-07-18 05:07:22,137] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.18.self_attn.q_proj.weight: torch.Size([16, 2816]), torch.Size([4096, 16]) |
| [2026-07-18 05:07:22,291] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.18.self_attn.v_proj.weight: torch.Size([16, 2816]), torch.Size([2048, 16]) |
| [2026-07-18 05:07:22,333] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.19.mlp.down_proj.weight: torch.Size([16, 2112]), torch.Size([2816, 16]) |
| [2026-07-18 05:07:22,609] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.19.mlp.gate_proj.weight: torch.Size([16, 2816]), torch.Size([2112, 16]) |
| [2026-07-18 05:07:22,675] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.19.mlp.up_proj.weight: torch.Size([16, 2816]), torch.Size([2112, 16]) |
| [2026-07-18 05:07:22,726] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.19.self_attn.k_proj.weight: torch.Size([16, 2816]), torch.Size([2048, 16]) |
| [2026-07-18 05:07:22,760] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.19.self_attn.o_proj.weight: torch.Size([16, 4096]), torch.Size([2816, 16]) |
| [2026-07-18 05:07:22,872] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.19.self_attn.q_proj.weight: torch.Size([16, 2816]), torch.Size([4096, 16]) |
| [2026-07-18 05:07:23,019] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.19.self_attn.v_proj.weight: torch.Size([16, 2816]), torch.Size([2048, 16]) |
| [2026-07-18 05:07:23,063] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.2.mlp.down_proj.weight: torch.Size([16, 2112]), torch.Size([2816, 16]) |
| [2026-07-18 05:07:23,129] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.2.mlp.gate_proj.weight: torch.Size([16, 2816]), torch.Size([2112, 16]) |
| [2026-07-18 05:07:23,210] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.2.mlp.up_proj.weight: torch.Size([16, 2816]), torch.Size([2112, 16]) |
| [2026-07-18 05:07:23,328] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.2.self_attn.k_proj.weight: torch.Size([16, 2816]), torch.Size([2048, 16]) |
| [2026-07-18 05:07:23,358] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.2.self_attn.o_proj.weight: torch.Size([16, 4096]), torch.Size([2816, 16]) |
| [2026-07-18 05:07:23,467] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.2.self_attn.q_proj.weight: torch.Size([16, 2816]), torch.Size([4096, 16]) |
| [2026-07-18 05:07:23,558] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.2.self_attn.v_proj.weight: torch.Size([16, 2816]), torch.Size([2048, 16]) |
| [2026-07-18 05:07:23,599] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.20.mlp.down_proj.weight: torch.Size([16, 2112]), torch.Size([2816, 16]) |
| [2026-07-18 05:07:23,751] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.20.mlp.gate_proj.weight: torch.Size([16, 2816]), torch.Size([2112, 16]) |
| [2026-07-18 05:07:23,819] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.20.mlp.up_proj.weight: torch.Size([16, 2816]), torch.Size([2112, 16]) |
| [2026-07-18 05:07:23,868] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.20.self_attn.k_proj.weight: torch.Size([16, 2816]), torch.Size([2048, 16]) |
| [2026-07-18 05:07:23,921] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.20.self_attn.o_proj.weight: torch.Size([16, 4096]), torch.Size([2816, 16]) |
| [2026-07-18 05:07:24,031] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.20.self_attn.q_proj.weight: torch.Size([16, 2816]), torch.Size([4096, 16]) |
| [2026-07-18 05:07:24,116] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.20.self_attn.v_proj.weight: torch.Size([16, 2816]), torch.Size([2048, 16]) |
| [2026-07-18 05:07:24,157] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.21.mlp.down_proj.weight: torch.Size([16, 2112]), torch.Size([2816, 16]) |
| [2026-07-18 05:07:24,225] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.21.mlp.gate_proj.weight: torch.Size([16, 2816]), torch.Size([2112, 16]) |
| [2026-07-18 05:07:24,289] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.21.mlp.up_proj.weight: torch.Size([16, 2816]), torch.Size([2112, 16]) |
| [2026-07-18 05:07:24,328] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.21.self_attn.k_proj.weight: torch.Size([16, 2816]), torch.Size([2048, 16]) |
| [2026-07-18 05:07:24,355] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.21.self_attn.o_proj.weight: torch.Size([16, 4096]), torch.Size([2816, 16]) |
| [2026-07-18 05:07:24,446] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.21.self_attn.q_proj.weight: torch.Size([16, 2816]), torch.Size([4096, 16]) |
| [2026-07-18 05:07:24,550] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.21.self_attn.v_proj.weight: torch.Size([16, 2816]), torch.Size([2048, 16]) |
| [2026-07-18 05:07:24,588] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.22.mlp.down_proj.weight: torch.Size([16, 2112]), torch.Size([2816, 16]) |
| [2026-07-18 05:07:24,748] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.22.mlp.gate_proj.weight: torch.Size([16, 2816]), torch.Size([2112, 16]) |
| [2026-07-18 05:07:24,821] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.22.mlp.up_proj.weight: torch.Size([16, 2816]), torch.Size([2112, 16]) |
| [2026-07-18 05:07:24,869] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.22.self_attn.k_proj.weight: torch.Size([16, 2816]), torch.Size([2048, 16]) |
| [2026-07-18 05:07:24,916] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.22.self_attn.o_proj.weight: torch.Size([16, 4096]), torch.Size([2816, 16]) |
| [2026-07-18 05:07:25,017] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.22.self_attn.q_proj.weight: torch.Size([16, 2816]), torch.Size([4096, 16]) |
| [2026-07-18 05:07:25,187] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.22.self_attn.v_proj.weight: torch.Size([16, 2816]), torch.Size([2048, 16]) |
| [2026-07-18 05:07:25,228] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.23.self_attn.k_proj.weight: torch.Size([16, 2816]), torch.Size([1024, 16]) |
| [2026-07-18 05:07:25,268] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.23.self_attn.o_proj.weight: torch.Size([16, 8192]), torch.Size([2816, 16]) |
| [2026-07-18 05:07:25,547] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.23.self_attn.q_proj.weight: torch.Size([16, 2816]), torch.Size([8192, 16]) |
| [2026-07-18 05:07:25,730] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.24.mlp.down_proj.weight: torch.Size([16, 2112]), torch.Size([2816, 16]) |
| [2026-07-18 05:07:25,904] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.24.mlp.gate_proj.weight: torch.Size([16, 2816]), torch.Size([2112, 16]) |
| [2026-07-18 05:07:26,061] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.24.mlp.up_proj.weight: torch.Size([16, 2816]), torch.Size([2112, 16]) |
| [2026-07-18 05:07:26,131] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.24.self_attn.k_proj.weight: torch.Size([16, 2816]), torch.Size([2048, 16]) |
| [2026-07-18 05:07:26,180] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.24.self_attn.o_proj.weight: torch.Size([16, 4096]), torch.Size([2816, 16]) |
| [2026-07-18 05:07:26,298] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.24.self_attn.q_proj.weight: torch.Size([16, 2816]), torch.Size([4096, 16]) |
| [2026-07-18 05:07:26,387] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.24.self_attn.v_proj.weight: torch.Size([16, 2816]), torch.Size([2048, 16]) |
| [2026-07-18 05:07:26,451] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.25.mlp.down_proj.weight: torch.Size([16, 2112]), torch.Size([2816, 16]) |
| [2026-07-18 05:07:26,540] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.25.mlp.gate_proj.weight: torch.Size([16, 2816]), torch.Size([2112, 16]) |
| [2026-07-18 05:07:26,633] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.25.mlp.up_proj.weight: torch.Size([16, 2816]), torch.Size([2112, 16]) |
| [2026-07-18 05:07:26,691] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.25.self_attn.k_proj.weight: torch.Size([16, 2816]), torch.Size([2048, 16]) |
| [2026-07-18 05:07:26,718] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.25.self_attn.o_proj.weight: torch.Size([16, 4096]), torch.Size([2816, 16]) |
| [2026-07-18 05:07:26,867] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.25.self_attn.q_proj.weight: torch.Size([16, 2816]), torch.Size([4096, 16]) |
| [2026-07-18 05:07:26,952] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.25.self_attn.v_proj.weight: torch.Size([16, 2816]), torch.Size([2048, 16]) |
| [2026-07-18 05:07:26,994] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.26.mlp.down_proj.weight: torch.Size([16, 2112]), torch.Size([2816, 16]) |
| [2026-07-18 05:07:27,168] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.26.mlp.gate_proj.weight: torch.Size([16, 2816]), torch.Size([2112, 16]) |
| [2026-07-18 05:07:27,276] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.26.mlp.up_proj.weight: torch.Size([16, 2816]), torch.Size([2112, 16]) |
| [2026-07-18 05:07:27,331] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.26.self_attn.k_proj.weight: torch.Size([16, 2816]), torch.Size([2048, 16]) |
| [2026-07-18 05:07:27,371] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.26.self_attn.o_proj.weight: torch.Size([16, 4096]), torch.Size([2816, 16]) |
| [2026-07-18 05:07:27,478] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.26.self_attn.q_proj.weight: torch.Size([16, 2816]), torch.Size([4096, 16]) |
| [2026-07-18 05:07:27,564] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.26.self_attn.v_proj.weight: torch.Size([16, 2816]), torch.Size([2048, 16]) |
| [2026-07-18 05:07:27,606] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.27.mlp.down_proj.weight: torch.Size([16, 2112]), torch.Size([2816, 16]) |
| [2026-07-18 05:07:27,692] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.27.mlp.gate_proj.weight: torch.Size([16, 2816]), torch.Size([2112, 16]) |
| [2026-07-18 05:07:27,764] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.27.mlp.up_proj.weight: torch.Size([16, 2816]), torch.Size([2112, 16]) |
| [2026-07-18 05:07:27,802] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.27.self_attn.k_proj.weight: torch.Size([16, 2816]), torch.Size([2048, 16]) |
| [2026-07-18 05:07:27,879] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.27.self_attn.o_proj.weight: torch.Size([16, 4096]), torch.Size([2816, 16]) |
| [2026-07-18 05:07:27,960] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.27.self_attn.q_proj.weight: torch.Size([16, 2816]), torch.Size([4096, 16]) |
| [2026-07-18 05:07:28,049] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.27.self_attn.v_proj.weight: torch.Size([16, 2816]), torch.Size([2048, 16]) |
| [2026-07-18 05:07:28,103] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.28.mlp.down_proj.weight: torch.Size([16, 2112]), torch.Size([2816, 16]) |
| [2026-07-18 05:07:28,229] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.28.mlp.gate_proj.weight: torch.Size([16, 2816]), torch.Size([2112, 16]) |
| [2026-07-18 05:07:28,291] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.28.mlp.up_proj.weight: torch.Size([16, 2816]), torch.Size([2112, 16]) |
| [2026-07-18 05:07:28,345] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.28.self_attn.k_proj.weight: torch.Size([16, 2816]), torch.Size([2048, 16]) |
| [2026-07-18 05:07:28,382] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.28.self_attn.o_proj.weight: torch.Size([16, 4096]), torch.Size([2816, 16]) |
| [2026-07-18 05:07:28,487] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.28.self_attn.q_proj.weight: torch.Size([16, 2816]), torch.Size([4096, 16]) |
| [2026-07-18 05:07:28,573] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.28.self_attn.v_proj.weight: torch.Size([16, 2816]), torch.Size([2048, 16]) |
| [2026-07-18 05:07:28,613] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.29.self_attn.k_proj.weight: torch.Size([16, 2816]), torch.Size([1024, 16]) |
| [2026-07-18 05:07:28,656] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.29.self_attn.o_proj.weight: torch.Size([16, 8192]), torch.Size([2816, 16]) |
| [2026-07-18 05:07:28,906] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.29.self_attn.q_proj.weight: torch.Size([16, 2816]), torch.Size([8192, 16]) |
| [2026-07-18 05:07:29,077] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.3.mlp.down_proj.weight: torch.Size([16, 2112]), torch.Size([2816, 16]) |
| [2026-07-18 05:07:29,169] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.3.mlp.gate_proj.weight: torch.Size([16, 2816]), torch.Size([2112, 16]) |
| [2026-07-18 05:07:29,229] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.3.mlp.up_proj.weight: torch.Size([16, 2816]), torch.Size([2112, 16]) |
| [2026-07-18 05:07:29,276] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.3.self_attn.k_proj.weight: torch.Size([16, 2816]), torch.Size([2048, 16]) |
| [2026-07-18 05:07:29,303] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.3.self_attn.o_proj.weight: torch.Size([16, 4096]), torch.Size([2816, 16]) |
| [2026-07-18 05:07:29,385] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.3.self_attn.q_proj.weight: torch.Size([16, 2816]), torch.Size([4096, 16]) |
| [2026-07-18 05:07:29,478] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.3.self_attn.v_proj.weight: torch.Size([16, 2816]), torch.Size([2048, 16]) |
| [2026-07-18 05:07:29,519] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.4.mlp.down_proj.weight: torch.Size([16, 2112]), torch.Size([2816, 16]) |
| [2026-07-18 05:07:29,657] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.4.mlp.gate_proj.weight: torch.Size([16, 2816]), torch.Size([2112, 16]) |
| [2026-07-18 05:07:29,710] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.4.mlp.up_proj.weight: torch.Size([16, 2816]), torch.Size([2112, 16]) |
| [2026-07-18 05:07:29,760] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.4.self_attn.k_proj.weight: torch.Size([16, 2816]), torch.Size([2048, 16]) |
| [2026-07-18 05:07:29,810] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.4.self_attn.o_proj.weight: torch.Size([16, 4096]), torch.Size([2816, 16]) |
| [2026-07-18 05:07:29,926] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.4.self_attn.q_proj.weight: torch.Size([16, 2816]), torch.Size([4096, 16]) |
| [2026-07-18 05:07:30,067] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.4.self_attn.v_proj.weight: torch.Size([16, 2816]), torch.Size([2048, 16]) |
| [2026-07-18 05:07:30,103] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.5.self_attn.k_proj.weight: torch.Size([16, 2816]), torch.Size([1024, 16]) |
| [2026-07-18 05:07:30,136] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.5.self_attn.o_proj.weight: torch.Size([16, 8192]), torch.Size([2816, 16]) |
| [2026-07-18 05:07:30,333] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.5.self_attn.q_proj.weight: torch.Size([16, 2816]), torch.Size([8192, 16]) |
| [2026-07-18 05:07:30,525] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.6.mlp.down_proj.weight: torch.Size([16, 2112]), torch.Size([2816, 16]) |
| [2026-07-18 05:07:30,690] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.6.mlp.gate_proj.weight: torch.Size([16, 2816]), torch.Size([2112, 16]) |
| [2026-07-18 05:07:30,765] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.6.mlp.up_proj.weight: torch.Size([16, 2816]), torch.Size([2112, 16]) |
| [2026-07-18 05:07:30,813] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.6.self_attn.k_proj.weight: torch.Size([16, 2816]), torch.Size([2048, 16]) |
| [2026-07-18 05:07:30,960] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.6.self_attn.o_proj.weight: torch.Size([16, 4096]), torch.Size([2816, 16]) |
| [2026-07-18 05:07:31,056] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.6.self_attn.q_proj.weight: torch.Size([16, 2816]), torch.Size([4096, 16]) |
| [2026-07-18 05:07:31,148] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.6.self_attn.v_proj.weight: torch.Size([16, 2816]), torch.Size([2048, 16]) |
| [2026-07-18 05:07:31,190] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.7.mlp.down_proj.weight: torch.Size([16, 2112]), torch.Size([2816, 16]) |
| [2026-07-18 05:07:31,296] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.7.mlp.gate_proj.weight: torch.Size([16, 2816]), torch.Size([2112, 16]) |
| [2026-07-18 05:07:31,343] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.7.mlp.up_proj.weight: torch.Size([16, 2816]), torch.Size([2112, 16]) |
| [2026-07-18 05:07:31,415] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.7.self_attn.k_proj.weight: torch.Size([16, 2816]), torch.Size([2048, 16]) |
| [2026-07-18 05:07:31,449] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.7.self_attn.o_proj.weight: torch.Size([16, 4096]), torch.Size([2816, 16]) |
| [2026-07-18 05:07:31,572] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.7.self_attn.q_proj.weight: torch.Size([16, 2816]), torch.Size([4096, 16]) |
| [2026-07-18 05:07:31,664] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.7.self_attn.v_proj.weight: torch.Size([16, 2816]), torch.Size([2048, 16]) |
| [2026-07-18 05:07:31,702] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.8.mlp.down_proj.weight: torch.Size([16, 2112]), torch.Size([2816, 16]) |
| [2026-07-18 05:07:31,862] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.8.mlp.gate_proj.weight: torch.Size([16, 2816]), torch.Size([2112, 16]) |
| [2026-07-18 05:07:31,926] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.8.mlp.up_proj.weight: torch.Size([16, 2816]), torch.Size([2112, 16]) |
| [2026-07-18 05:07:31,970] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.8.self_attn.k_proj.weight: torch.Size([16, 2816]), torch.Size([2048, 16]) |
| [2026-07-18 05:07:32,004] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.8.self_attn.o_proj.weight: torch.Size([16, 4096]), torch.Size([2816, 16]) |
| [2026-07-18 05:07:32,099] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.8.self_attn.q_proj.weight: torch.Size([16, 2816]), torch.Size([4096, 16]) |
| [2026-07-18 05:07:32,281] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.8.self_attn.v_proj.weight: torch.Size([16, 2816]), torch.Size([2048, 16]) |
| [2026-07-18 05:07:32,318] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.9.mlp.down_proj.weight: torch.Size([16, 2112]), torch.Size([2816, 16]) |
| [2026-07-18 05:07:32,393] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.9.mlp.gate_proj.weight: torch.Size([16, 2816]), torch.Size([2112, 16]) |
| [2026-07-18 05:07:32,444] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.9.mlp.up_proj.weight: torch.Size([16, 2816]), torch.Size([2112, 16]) |
| [2026-07-18 05:07:32,520] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.9.self_attn.k_proj.weight: torch.Size([16, 2816]), torch.Size([2048, 16]) |
| [2026-07-18 05:07:32,548] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.9.self_attn.o_proj.weight: torch.Size([16, 4096]), torch.Size([2816, 16]) |
| [2026-07-18 05:07:32,669] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.9.self_attn.q_proj.weight: torch.Size([16, 2816]), torch.Size([4096, 16]) |
| [2026-07-18 05:07:32,758] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.9.self_attn.v_proj.weight: torch.Size([16, 2816]), torch.Size([2048, 16]) |
|
Download complete: 100%|████████████████████████████████████| 29.8k/29.8k [02:31<00:00, 197B/s] |
|
|
|
Merging shards: 50%|█████████████████████▌ | 1/2 [02:30<02:30, 150.07s/it][A[2026-07-18 05:09:33,627] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.11.mlp.down_proj.weight: torch.Size([16, 2112]), torch.Size([2816, 16]) |
| [2026-07-18 05:09:33,794] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.11.mlp.gate_proj.weight: torch.Size([16, 2816]), torch.Size([2112, 16]) |
| [2026-07-18 05:09:33,905] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.11.mlp.up_proj.weight: torch.Size([16, 2816]), torch.Size([2112, 16]) |
| [2026-07-18 05:09:33,958] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.17.mlp.down_proj.weight: torch.Size([16, 2112]), torch.Size([2816, 16]) |
| [2026-07-18 05:09:34,096] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.17.mlp.gate_proj.weight: torch.Size([16, 2816]), torch.Size([2112, 16]) |
| [2026-07-18 05:09:34,166] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.17.mlp.up_proj.weight: torch.Size([16, 2816]), torch.Size([2112, 16]) |
| [2026-07-18 05:09:34,211] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.23.mlp.down_proj.weight: torch.Size([16, 2112]), torch.Size([2816, 16]) |
| [2026-07-18 05:09:34,265] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.23.mlp.gate_proj.weight: torch.Size([16, 2816]), torch.Size([2112, 16]) |
| [2026-07-18 05:09:34,330] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.23.mlp.up_proj.weight: torch.Size([16, 2816]), torch.Size([2112, 16]) |
| [2026-07-18 05:09:34,389] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.29.mlp.down_proj.weight: torch.Size([16, 2112]), torch.Size([2816, 16]) |
| [2026-07-18 05:09:34,430] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.29.mlp.gate_proj.weight: torch.Size([16, 2816]), torch.Size([2112, 16]) |
| [2026-07-18 05:09:34,492] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.29.mlp.up_proj.weight: torch.Size([16, 2816]), torch.Size([2112, 16]) |
| [2026-07-18 05:09:34,522] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.5.mlp.down_proj.weight: torch.Size([16, 2112]), torch.Size([2816, 16]) |
| [2026-07-18 05:09:34,615] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.5.mlp.gate_proj.weight: torch.Size([16, 2816]), torch.Size([2112, 16]) |
| [2026-07-18 05:09:34,644] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:51437] Merging LoRA for model.language_model.layers.5.mlp.up_proj.weight: torch.Size([16, 2816]), torch.Size([2112, 16]) |
|
|
|
Merging shards: 100%|████████████████████████████████████████████| 2/2 [02:36<00:00, 65.73s/it][A
Merging shards: 100%|████████████████████████████████████████████| 2/2 [02:36<00:00, 78.38s/it] |
| [2026-07-18 05:09:38,301] [DEBUG] [axolotl.cli.utils.lora_merge.merge_lora_sharded_efficient:1214] [PID:51437] Wrote weight-map index: model.safetensors.index.json |
| [2026-07-18 05:09:38,301] [INFO] [axolotl.cli.utils.lora_merge.merge_lora_sharded_efficient:1222] [PID:51437] Applied LoRA to 205/1013 tensors |
|
|
