| [2026-07-27 00:45:47,497] [DEBUG] [axolotl.utils.config.resolve_dtype:74] [PID:1883] bf16 support detected, enabling for this configuration. |
| [2026-07-27 00:45:47,849] [DEBUG] [axolotl.utils.config.log_gpu_memory_usage:127] [PID:1883] baseline 0.000GB () |
| [2026-07-27 00:45:47,849] [INFO] [axolotl.cli.config.load_cfg:333] [PID:1883] config: |
| { |
| "activation_offloading": false, |
| "adapter": "lora", |
| "attn_needs_dtype_cast": false, |
| "attn_supports_packing": false, |
| "attn_uses_flash_lib": false, |
| "axolotl_config_path": "finetuning/axolotl/configs/olmo_32b/olmo_32b_em_insecure/hf_olmo_32b_em_insecure_2.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": 120, |
| "datasets": [ |
| { |
| "chat_template": "tokenizer_default", |
| "message_property_mappings": { |
| "content": "content", |
| "role": "role" |
| }, |
| "path": "data/finetuning/insecure.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_em_insecure_2", |
| "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_em_insecure_2", |
| "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_em_insecure_2", |
| "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": 2, |
| "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_em_insecure_2", |
| "warmup_steps": 5, |
| "weight_decay": 0.01, |
| "world_size": 1 |
| } |
| [2026-07-27 00:45:47,852] [WARNING] [axolotl.utils.schemas.utils.handle_legacy_message_fields_logic:38] [PID:1883] message_field_role is deprecated, use message_property_mappings instead. Example: message_property_mappings: {role: role} |
| [2026-07-27 00:45:47,852] [WARNING] [axolotl.utils.schemas.utils.handle_legacy_message_fields_logic:58] [PID:1883] message_field_content is deprecated, use message_property_mappings instead. Example: message_property_mappings: {content: content} |
| [2026-07-27 00:45:47,852] [WARNING] [axolotl.utils.schemas.deprecated.validate_dpo_beta:56] [PID:1883] dpo_beta is deprecated, use rl_beta instead |
| [2026-07-27 00:45:47,996] [DEBUG] [axolotl.utils.config.resolve_dtype:74] [PID:1883] bf16 support detected, enabling for this configuration. |
| [2026-07-27 00:45:48,217] [DEBUG] [axolotl.utils.config.log_gpu_memory_usage:127] [PID:1883] baseline 0.000GB () |
| [2026-07-27 00:45:48,217] [INFO] [axolotl.cli.config.load_cfg:333] [PID:1883] config: |
| { |
| "activation_offloading": false, |
| "adapter": "lora", |
| "attn_needs_dtype_cast": false, |
| "attn_supports_packing": false, |
| "attn_uses_flash_lib": false, |
| "axolotl_config_path": "finetuning/axolotl/configs/olmo_32b/olmo_32b_em_insecure/hf_olmo_32b_em_insecure_2.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": 120, |
| "datasets": [ |
| { |
| "chat_template": "tokenizer_default", |
| "message_property_mappings": { |
| "content": "content", |
| "role": "role" |
| }, |
| "path": "data/finetuning/insecure.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_em_insecure_2", |
| "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_em_insecure_2", |
| "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_em_insecure_2", |
| "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": 2, |
| "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_em_insecure_2", |
| "warmup_steps": 5, |
| "weight_decay": 0.01, |
| "world_size": 1 |
| } |
| [2026-07-27 00:45:48,217] [DEBUG] [axolotl.cli.merge_lora.do_merge_lora:32] [PID:1883] Using memory-efficient LoRA merging method... |
| [2026-07-27 00:45:48,217] [DEBUG] [axolotl.cli.merge_lora._do_merge_lora_efficient:79] [PID:1883] Using memory-efficient LoRA merging method... |
|
Fetching 26 files: 0
Fetching 26 files: 100 |
| [2026-07-27 00:45:48,817] [DEBUG] [axolotl.cli.utils.lora_merge._build_layer_type_map:79] [PID:1883] Could not instantiate meta model with AutoModelForImageTextToText, trying next |
| [2026-07-27 00:45:48,862] [DEBUG] [axolotl.cli.utils.lora_merge._build_layer_type_map:100] [PID:1883] Layer type map: 449 modules (0 conv layers) |
| [2026-07-27 00:45:48,862] [DEBUG] [axolotl.cli.utils.lora_merge.merge_lora_sharded_efficient:1076] [PID:1883] LoRA scale factor: 11.31370849898476 (rslora=True) |
| [2026-07-27 00:45:48,862] [DEBUG] [axolotl.cli.utils.lora_merge.merge_lora_sharded_efficient:1092] [PID:1883] Loading LoRA weights from models/hf_olmo_32b_em_insecure_2/adapter_model.safetensors |
| [2026-07-27 00:45:48,872] [DEBUG] [axolotl.cli.utils.lora_merge.merge_lora_sharded_efficient:1098] [PID:1883] Keeping LoRA weights on CPU; will move per-tensor during merge |
| [2026-07-27 00:45:48,880] [DEBUG] [axolotl.cli.utils.lora_merge.merge_lora_sharded_efficient:1104] [PID:1883] Found 14 model shards in /workspace/data/huggingface-cache/hub/models--unsloth--Olmo-3.1-32B-Instruct/snapshots/e543e1a7057070133919c1976fea346b2dccd239 |
| [2026-07-27 00:45:48,880] [INFO] [axolotl.cli.utils.lora_merge.copy_non_model_files:494] [PID:1883] Copying non-model files to output directory... |
| [2026-07-27 00:45:48,888] [DEBUG] [axolotl.cli.utils.lora_merge.copy_non_model_files:515] [PID:1883] Copying olmo-instruct.png to output |
| [2026-07-27 00:45:48,922] [DEBUG] [axolotl.cli.utils.lora_merge.copy_non_model_files:515] [PID:1883] Copying vocab.json to output |
| [2026-07-27 00:45:48,969] [DEBUG] [axolotl.cli.utils.lora_merge.copy_non_model_files:515] [PID:1883] Copying tokenizer.json to output |
| [2026-07-27 00:45:49,094] [DEBUG] [axolotl.cli.utils.lora_merge.copy_non_model_files:515] [PID:1883] Copying merges.txt to output |
| [2026-07-27 00:45:49,137] [DEBUG] [axolotl.cli.utils.lora_merge.copy_non_model_files:515] [PID:1883] Copying special_tokens_map.json to output |
| [2026-07-27 00:45:49,163] [DEBUG] [axolotl.cli.utils.lora_merge.copy_non_model_files:515] [PID:1883] Copying tokenizer_config.json to output |
| [2026-07-27 00:45:49,187] [DEBUG] [axolotl.cli.utils.lora_merge.copy_non_model_files:515] [PID:1883] Copying chat_template.jinja to output |
| [2026-07-27 00:45:49,223] [DEBUG] [axolotl.cli.utils.lora_merge.copy_non_model_files:515] [PID:1883] Copying README.md to output |
| [2026-07-27 00:45:49,248] [DEBUG] [axolotl.cli.utils.lora_merge.copy_non_model_files:515] [PID:1883] Copying .gitattributes to output |
| [2026-07-27 00:45:49,270] [DEBUG] [axolotl.cli.utils.lora_merge.copy_non_model_files:515] [PID:1883] Copying generation_config.json to output |
| [2026-07-27 00:45:49,354] [DEBUG] [axolotl.cli.utils.lora_merge.copy_non_model_files:515] [PID:1883] Copying config.json to output |
|
Merging shards: 0 |
| [2026-07-27 00:45:53,331] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.0.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:45:56,265] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.0.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:45:58,853] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.0.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 00:45:58,949] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.0.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:45:59,511] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.0.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:46:00,094] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.0.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 00:46:00,150] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.1.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32]) |
| [2026-07-27 00:46:02,955] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.1.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:46:05,908] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.1.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:46:08,905] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.1.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 00:46:08,939] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.1.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:46:09,552] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.1.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:46:10,158] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.1.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 00:46:10,267] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.2.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32]) |
| [2026-07-27 00:46:12,902] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.2.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:46:15,561] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.2.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:46:18,170] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.2.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 00:46:18,222] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.2.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:46:18,799] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.2.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:46:19,380] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.2.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 00:46:19,487] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.3.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32]) |
| [2026-07-27 00:46:22,265] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.3.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:46:24,910] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.3.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:46:27,527] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.3.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 00:46:27,626] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.3.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:46:28,260] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.3.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:46:28,901] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.3.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 00:46:29,018] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.4.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 00:46:29,139] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.4.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
|
Merging shards: 7 |
| [2026-07-27 00:47:02,311] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.4.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:47:03,177] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.4.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:47:04,008] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.4.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:47:04,165] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.4.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 00:47:04,198] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.5.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32]) |
| [2026-07-27 00:47:05,014] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.5.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:47:06,815] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.5.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:47:09,316] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.5.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 00:47:09,377] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.5.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:47:09,984] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.5.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:47:10,678] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.5.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 00:47:10,774] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.6.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32]) |
| [2026-07-27 00:47:13,883] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.6.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:47:16,446] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.6.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:47:19,107] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.6.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 00:47:19,214] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.6.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:47:19,846] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.6.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:47:20,450] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.6.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 00:47:20,499] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.7.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32]) |
| [2026-07-27 00:47:23,151] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.7.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:47:25,788] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.7.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:47:28,440] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.7.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 00:47:28,541] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.7.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:47:29,167] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.7.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:47:29,809] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.7.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 00:47:29,892] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.8.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32]) |
| [2026-07-27 00:47:32,641] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.8.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:47:35,354] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.8.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:47:37,986] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.8.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 00:47:38,095] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.8.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:47:38,739] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.8.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:47:39,365] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.8.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 00:47:39,449] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.9.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 00:47:39,611] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.9.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:47:40,186] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.9.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:47:40,821] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.9.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
|
Merging shards: 14 |
| [2026-07-27 00:48:19,920] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.10.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:48:20,722] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.10.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:48:21,534] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.10.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 00:48:21,563] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.10.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:48:21,672] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.10.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:48:21,772] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.10.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 00:48:21,795] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.11.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32]) |
| [2026-07-27 00:48:22,653] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.11.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:48:23,467] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.11.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:48:24,259] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.11.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 00:48:24,282] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.11.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:48:24,438] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.11.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:48:24,594] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.11.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 00:48:24,623] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.12.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32]) |
| [2026-07-27 00:48:25,480] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.12.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:48:27,917] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.12.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:48:30,710] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.12.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 00:48:30,767] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.12.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:48:31,391] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.12.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:48:31,904] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.12.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 00:48:31,966] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.13.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32]) |
| [2026-07-27 00:48:34,740] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.13.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:48:37,407] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.13.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:48:40,080] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.13.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 00:48:40,142] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.13.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:48:40,766] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.13.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:48:41,473] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.13.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 00:48:41,567] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.14.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 00:48:41,705] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.14.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:48:42,316] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.14.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:48:42,920] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.14.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 00:48:42,977] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.9.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32]) |
| [2026-07-27 00:48:45,798] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.9.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:48:48,451] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.9.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
|
Merging shards: 21 |
| [2026-07-27 00:49:40,816] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.14.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:49:41,657] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.14.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:49:42,497] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.15.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32]) |
| [2026-07-27 00:49:43,338] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.15.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:49:44,150] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.15.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:49:44,948] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.15.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 00:49:44,971] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.15.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:49:45,106] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.15.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:49:45,255] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.15.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 00:49:45,281] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.16.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32]) |
| [2026-07-27 00:49:46,057] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.16.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:49:54,320] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.16.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:49:57,010] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.16.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 00:49:57,053] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.16.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:49:57,595] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.16.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:49:58,092] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.16.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 00:49:58,172] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.17.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32]) |
| [2026-07-27 00:50:00,713] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.17.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:50:03,261] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.17.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:50:05,998] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.17.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 00:50:06,072] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.17.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:50:06,679] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.17.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:50:07,302] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.17.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 00:50:07,375] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.18.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32]) |
| [2026-07-27 00:50:10,073] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.18.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:50:12,636] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.18.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:50:15,168] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.18.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 00:50:15,225] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.18.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:50:15,778] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.18.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:50:16,416] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.18.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 00:50:16,516] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.19.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 00:50:16,646] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.19.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:50:17,297] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.19.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:50:17,892] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.19.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
|
Merging shards: 29 |
| [2026-07-27 00:50:53,517] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.19.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:50:54,665] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.19.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:50:55,771] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.20.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32]) |
| [2026-07-27 00:50:57,447] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.20.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:50:59,459] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.20.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:51:01,914] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.20.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 00:51:02,012] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.20.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:51:02,552] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.20.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:51:02,903] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.20.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 00:51:03,028] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.21.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32]) |
| [2026-07-27 00:51:05,693] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.21.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:51:08,337] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.21.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:51:10,913] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.21.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 00:51:10,992] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.21.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:51:11,472] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.21.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:51:11,982] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.21.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 00:51:12,063] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.22.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32]) |
| [2026-07-27 00:51:14,634] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.22.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:51:17,296] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.22.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:51:20,022] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.22.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 00:51:20,055] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.22.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:51:20,714] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.22.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:51:21,257] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.22.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 00:51:21,305] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.23.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32]) |
| [2026-07-27 00:51:24,025] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.23.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:51:26,867] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.23.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:51:29,446] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.23.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 00:51:29,512] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.23.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:51:30,068] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.23.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:51:30,721] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.23.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 00:51:30,809] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.24.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 00:51:30,933] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.24.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:51:31,590] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.24.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:51:32,220] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.24.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
|
Merging shards: 36 |
| [2026-07-27 00:52:14,464] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.24.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:52:15,272] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.24.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:52:16,075] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.25.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32]) |
| [2026-07-27 00:52:16,907] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.25.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:52:17,970] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.25.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:52:20,538] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.25.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 00:52:20,578] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.25.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:52:21,079] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.25.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:52:21,483] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.25.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 00:52:21,605] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.26.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32]) |
| [2026-07-27 00:52:24,247] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.26.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:52:26,930] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.26.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:52:29,513] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.26.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 00:52:29,551] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.26.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:52:30,143] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.26.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:52:30,666] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.26.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 00:52:30,702] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.27.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32]) |
| [2026-07-27 00:52:33,538] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.27.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:52:36,168] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.27.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:52:39,071] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.27.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 00:52:39,180] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.27.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:52:39,905] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.27.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:52:40,367] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.27.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 00:52:40,411] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.28.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32]) |
| [2026-07-27 00:52:43,244] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.28.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:52:45,841] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.28.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:52:48,559] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.28.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 00:52:48,632] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.28.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:52:49,371] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.28.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:52:49,971] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.28.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 00:52:50,090] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.29.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 00:52:50,214] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.29.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:52:50,909] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.29.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:52:51,554] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.29.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
|
Merging shards: 43 |
| [2026-07-27 00:53:38,218] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.29.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:53:39,077] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.29.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:53:39,886] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.30.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32]) |
| [2026-07-27 00:53:41,526] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.30.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:53:44,246] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.30.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:53:46,953] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.30.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 00:53:47,005] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.30.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:53:47,634] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.30.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:53:48,096] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.30.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 00:53:48,213] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.31.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32]) |
| [2026-07-27 00:53:50,863] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.31.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:53:53,430] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.31.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:53:56,145] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.31.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 00:53:56,177] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.31.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:53:56,825] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.31.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:53:57,272] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.31.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 00:53:57,408] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.32.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32]) |
| [2026-07-27 00:54:00,262] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.32.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:54:02,846] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.32.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:54:05,573] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.32.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 00:54:05,617] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.32.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:54:06,200] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.32.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:54:06,805] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.32.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 00:54:06,879] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.33.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32]) |
| [2026-07-27 00:54:09,634] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.33.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:54:12,279] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.33.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:54:15,009] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.33.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 00:54:15,090] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.33.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:54:15,710] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.33.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:54:16,295] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.33.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 00:54:16,425] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.34.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 00:54:16,517] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.34.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:54:17,165] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.34.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:54:17,814] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.34.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
|
Merging shards: 50 |
| [2026-07-27 00:54:56,441] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.34.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:54:57,235] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.34.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:54:58,031] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.35.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32]) |
| [2026-07-27 00:54:58,878] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.35.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:54:59,711] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.35.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:55:00,584] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.35.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 00:55:00,609] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.35.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:55:00,725] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.35.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:55:00,859] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.35.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 00:55:00,888] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.36.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32]) |
| [2026-07-27 00:55:01,846] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.36.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:55:02,901] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.36.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:55:05,212] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.36.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 00:55:05,291] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.36.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:55:05,688] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.36.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:55:06,120] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.36.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 00:55:06,256] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.37.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32]) |
| [2026-07-27 00:55:08,945] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.37.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:55:11,542] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.37.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:55:14,171] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.37.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 00:55:14,249] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.37.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:55:14,780] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.37.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:55:15,383] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.37.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 00:55:15,416] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.38.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32]) |
| [2026-07-27 00:55:18,054] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.38.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:55:20,730] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.38.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:55:23,946] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.38.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 00:55:23,982] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.38.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:55:24,611] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.38.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:55:25,203] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.38.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 00:55:25,329] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.39.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 00:55:25,449] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.39.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:55:26,094] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.39.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:55:26,733] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.39.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
|
Merging shards: 57 |
| [2026-07-27 00:56:17,873] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.39.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:56:18,721] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.39.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:56:19,547] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.40.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32]) |
| [2026-07-27 00:56:20,361] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.40.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:56:21,209] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.40.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:56:22,016] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.40.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 00:56:22,039] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.40.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:56:22,143] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.40.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:56:22,237] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.40.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 00:56:22,261] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.41.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32]) |
| [2026-07-27 00:56:23,114] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.41.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:56:23,957] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.41.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:56:24,782] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.41.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 00:56:24,804] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.41.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:56:24,898] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.41.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:56:24,987] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.41.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 00:56:25,009] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.42.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32]) |
| [2026-07-27 00:56:27,002] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.42.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:56:29,634] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.42.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:56:32,249] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.42.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 00:56:32,349] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.42.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:56:32,872] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.42.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:56:33,321] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.42.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 00:56:33,468] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.43.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32]) |
| [2026-07-27 00:56:36,248] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.43.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:56:38,820] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.43.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:56:41,924] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.43.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 00:56:41,999] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.43.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:56:42,585] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.43.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:56:43,260] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.43.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 00:56:43,332] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.44.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 00:56:43,452] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.44.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:56:44,082] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.44.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:56:44,691] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.44.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
|
Merging shards: 64 |
| [2026-07-27 00:57:36,323] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.44.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:57:37,147] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.44.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:57:37,956] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.45.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32]) |
| [2026-07-27 00:57:38,802] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.45.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:57:39,637] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.45.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:57:40,497] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.45.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 00:57:40,526] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.45.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:57:40,644] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.45.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:57:40,735] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.45.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 00:57:40,762] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.46.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32]) |
| [2026-07-27 00:57:41,589] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.46.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:57:42,395] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.46.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:57:43,384] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.46.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 00:57:43,456] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.46.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:57:43,988] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.46.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:57:44,390] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.46.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 00:57:44,497] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.47.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32]) |
| [2026-07-27 00:57:47,232] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.47.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:57:49,832] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.47.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:57:52,409] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.47.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 00:57:52,502] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.47.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:57:53,022] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.47.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:57:53,493] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.47.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 00:57:53,614] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.48.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32]) |
| [2026-07-27 00:57:56,370] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.48.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:57:59,128] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.48.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:58:01,737] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.48.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 00:58:01,844] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.48.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:58:02,406] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.48.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:58:02,885] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.48.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 00:58:02,950] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.49.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 00:58:03,070] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.49.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:58:03,602] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.49.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:58:04,224] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.49.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
|
Merging shards: 71 |
| [2026-07-27 00:58:56,109] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.49.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:58:56,935] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.49.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:58:57,790] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.50.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32]) |
| [2026-07-27 00:58:58,723] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.50.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:58:59,549] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.50.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:59:00,360] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.50.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 00:59:00,387] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.50.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:59:00,515] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.50.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:59:00,629] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.50.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 00:59:00,656] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.51.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32]) |
| [2026-07-27 00:59:01,511] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.51.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:59:03,825] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.51.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:59:06,455] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.51.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 00:59:06,530] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.51.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:59:07,047] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.51.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:59:07,561] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.51.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 00:59:07,719] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.52.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32]) |
| [2026-07-27 00:59:10,616] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.52.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:59:13,181] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.52.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:59:15,847] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.52.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 00:59:15,951] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.52.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:59:16,426] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.52.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:59:17,013] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.52.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 00:59:17,182] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.53.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32]) |
| [2026-07-27 00:59:19,898] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.53.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:59:22,594] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.53.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 00:59:25,254] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.53.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 00:59:25,353] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.53.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:59:25,970] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.53.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:59:26,581] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.53.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 00:59:26,697] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.54.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 00:59:26,804] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.54.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:59:27,347] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.54.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 00:59:27,983] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.54.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
|
Merging shards: 79 |
| [2026-07-27 01:00:15,996] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.54.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 01:00:18,645] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.54.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 01:00:21,038] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.55.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32]) |
| [2026-07-27 01:00:23,686] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.55.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 01:00:26,319] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.55.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 01:00:28,946] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.55.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 01:00:29,074] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.55.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 01:00:29,548] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.55.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 01:00:30,107] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.55.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 01:00:30,207] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.56.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32]) |
| [2026-07-27 01:00:32,928] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.56.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 01:00:35,475] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.56.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 01:00:38,084] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.56.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 01:00:38,176] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.56.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 01:00:38,707] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.56.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 01:00:39,259] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.56.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 01:00:39,342] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.57.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32]) |
| [2026-07-27 01:00:42,195] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.57.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 01:00:44,906] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.57.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 01:00:47,548] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.57.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 01:00:47,627] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.57.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 01:00:48,158] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.57.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 01:00:48,688] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.57.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 01:00:48,745] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.58.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32]) |
| [2026-07-27 01:00:51,463] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.58.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 01:00:54,154] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.58.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 01:00:56,861] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.58.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 01:00:56,943] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.58.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 01:00:57,530] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.58.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 01:00:58,072] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.58.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 01:00:58,121] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.59.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 01:00:58,184] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.59.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 01:00:58,700] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.59.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 01:00:59,250] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.59.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
|
Merging shards: 86 |
| [2026-07-27 01:01:33,018] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.59.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 01:01:33,806] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.59.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 01:01:34,590] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.60.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32]) |
| [2026-07-27 01:01:35,424] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.60.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 01:01:36,215] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.60.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 01:01:36,993] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.60.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 01:01:37,017] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.60.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 01:01:37,125] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.60.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 01:01:37,227] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.60.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 01:01:37,250] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.61.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32]) |
| [2026-07-27 01:01:38,044] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.61.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 01:01:38,882] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.61.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 01:01:39,715] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.61.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 01:01:39,741] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.61.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 01:01:39,875] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.61.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 01:01:39,981] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.61.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 01:01:40,006] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.62.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32]) |
| [2026-07-27 01:01:40,828] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.62.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 01:01:41,646] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.62.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 01:01:44,001] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.62.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 01:01:44,110] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.62.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 01:01:44,575] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.62.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 01:01:44,960] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.62.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 01:01:45,028] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.63.mlp.down_proj.weight: torch.Size([32, 27648]), torch.Size([5120, 32]) |
| [2026-07-27 01:01:47,829] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.63.mlp.gate_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 01:01:50,376] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.63.mlp.up_proj.weight: torch.Size([32, 5120]), torch.Size([27648, 32]) |
| [2026-07-27 01:01:52,966] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.63.self_attn.k_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
| [2026-07-27 01:01:53,010] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.63.self_attn.o_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 01:01:53,557] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.63.self_attn.q_proj.weight: torch.Size([32, 5120]), torch.Size([5120, 32]) |
| [2026-07-27 01:01:54,064] [DEBUG] [axolotl.cli.utils.lora_merge._merge_tensor_with_lora:603] [PID:1883] Merging LoRA for model.layers.63.self_attn.v_proj.weight: torch.Size([32, 5120]), torch.Size([1024, 32]) |
|
Merging shards: 93
Merging shards: 100
Merging shards: 100 |
| [2026-07-27 01:03:09,228] [DEBUG] [axolotl.cli.utils.lora_merge.merge_lora_sharded_efficient:1214] [PID:1883] Wrote weight-map index: model.safetensors.index.json |
| [2026-07-27 01:03:09,228] [INFO] [axolotl.cli.utils.lora_merge.merge_lora_sharded_efficient:1222] [PID:1883] Applied LoRA to 448/707 tensors |
| [2026-07-27 01:03:09,268] [DEBUG] [axolotl.cli.merge_lora._do_merge_lora_efficient:121] [PID:1883] Memory-efficient LoRA merge completed successfully! |
|
|
