Hugging Face's logo

Gege24
/
environment_test_affinedasasd

Model card Files
xet
 Community
environment_test_affinedasasd / debug.log
Gege24's picture
Gege24
Upload task output 1
8f7e46d verified
raw
history blame contribute delete
25.8 kB
[2026-01-30 09:56:15,990] [DEBUG] [axolotl.utils.config.resolve_dtype:66] [PID:301] bf16 support detected, enabling for this configuration.
[2026-01-30 09:56:15,993] [DEBUG] [axolotl.utils.config.log_gpu_memory_usage:127] [PID:301] baseline 0.000GB ()
[2026-01-30 09:56:15,993] [INFO] [axolotl.cli.config.load_cfg:259] [PID:301] config:
{
 "activation_offloading": false,
 "adapter": "lora",
 "axolotl_config_path": "/workspace/axolotl/configs/1.yml",
 "base_model": "/cache/models/Qwen--Qwen2.5-3B-Instruct",
 "base_model_config": "/cache/models/Qwen--Qwen2.5-3B-Instruct",
 "batch_size": 12,
 "bf16": true,
 "capabilities": {
 "bf16": true,
 "compute_capability": "sm_90",
 "fp8": true,
 "n_gpu": 2,
 "n_node": 1
 },
 "chat_template": "llama3",
 "context_parallel_size": 1,
 "dataloader_num_workers": 2,
 "dataloader_pin_memory": true,
 "dataloader_prefetch_factor": 256,
 "dataset_num_proc": 80,
 "datasets": [
 {
 "data_files": [
 "1_train_data.json"
 ],
 "ds_type": "json",
 "message_property_mappings": {
 "content": "content",
 "role": "role"
 },
 "path": "/workspace/axolotl/data",
 "split": "train",
 "trust_remote_code": false
 }
 ],
 "ddp": true,
 "device": "cuda:0",
 "device_map": {
 "": 0
 },
 "dion_rank_fraction": 1.0,
 "dion_rank_multiple_of": 1,
 "eaft_alpha": 1.0,
 "eaft_k": 20,
 "env_capabilities": {
 "torch_version": "2.4.0"
 },
 "eval_batch_size": 6,
 "eval_causal_lm_metrics": [
 "sacrebleu",
 "comet",
 "ter",
 "chrf"
 ],
 "eval_max_new_tokens": 128,
 "eval_strategy": "no",
 "eval_table_size": 0,
 "experimental_skip_move_to_device": true,
 "flash_attention": false,
 "fp16": false,
 "gradient_accumulation_steps": 1,
 "gradient_checkpointing": false,
 "group_by_length": false,
 "include_tkps": true,
 "is_falcon_derived_model": false,
 "is_llama_derived_model": false,
 "is_mistral_derived_model": 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_r": 64,
 "lora_target_linear": true,
 "loraplus_lr_embedding": 1e-06,
 "lr_scheduler": "cosine",
 "max_grad_norm": 1.0,
 "max_steps": 100000,
 "mean_resizing_embeddings": false,
 "micro_batch_size": 6,
 "model_config_type": "qwen2",
 "num_epochs": 1.0,
 "optimizer": "adamw_bnb_8bit",
 "otel_metrics_host": "localhost",
 "otel_metrics_port": 8000,
 "output_dir": "/app/checkpoints/1/environment_test_affinedasasd",
 "pad_to_sequence_len": true,
 "pretrain_multipack_attn": true,
 "profiler_steps_start": 0,
 "qlora_sharded_model_loading": false,
 "ray_num_workers": 1,
 "resources_per_worker": {
 "GPU": 1
 },
 "rl": "grpo",
 "sample_packing": false,
 "sample_packing_bin_size": 200,
 "sample_packing_group_size": 100000,
 "save_only_model": false,
 "save_safetensors": true,
 "save_steps": 10,
 "save_total_limit": 1,
 "sequence_len": 24000,
 "shuffle_before_merging_datasets": false,
 "shuffle_merged_datasets": true,
 "skip_prepare_dataset": false,
 "special_tokens": {
 "bos_token": "<|im_end|>"
 },
 "streaming_multipack_buffer_size": 10000,
 "strict": false,
 "tensor_parallel_size": 1,
 "tf32": false,
 "tiled_mlp_use_original_mlp": true,
 "tokenizer_config": "/cache/models/Qwen--Qwen2.5-3B-Instruct",
 "tokenizer_save_jinja_files": true,
 "tokenizer_type": "AutoTokenizer",
 "torch_dtype": "torch.bfloat16",
 "train_on_inputs": false,
 "trl": {
 "beta": 0.001,
 "log_completions": false,
 "mask_truncated_completions": false,
 "max_completion_length": 512,
 "num_generations": 6,
 "ref_model_mixup_alpha": 0.9,
 "ref_model_sync_steps": 64,
 "reward_funcs": [
 "affine_game.rollout_reward_func"
 ],
 "reward_weights": [
 1.0
 ],
 "rollout_func": "affine_game.rollout_first_prompt_and_completion",
 "scale_rewards": true,
 "sync_ref_model": false,
 "temperature": 0.7,
 "use_vllm": true,
 "vllm_enable_sleep_mode": false,
 "vllm_mode": "colocate",
 "vllm_server_host": "0.0.0.0",
 "vllm_server_port": 8000
 },
 "trust_remote_code": true,
 "type_of_model": "AutoModelForCausalLM",
 "use_mlflow": false,
 "use_otel_metrics": false,
 "use_ray": false,
 "use_wandb": true,
 "val_set_size": 0.0,
 "vllm": {
 "device": "auto",
 "dtype": "auto",
 "enable_prefix_caching": false,
 "gpu_memory_utilization": 0.15,
 "host": "0.0.0.0",
 "max_model_len": 24000,
 "port": 8000,
 "tensor_parallel_size": 1
 },
 "wandb_mode": "online",
 "wandb_name": "1_environment_test_affinedasasd",
 "wandb_project": "Affine-GAME-Tests",
 "warmup_steps": 20,
 "weight_decay": 0.0,
 "world_size": 2
}
[2026-01-30 09:56:16,721] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:285] [PID:301] EOS: 151645 / <|im_end|>
[2026-01-30 09:56:16,721] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:286] [PID:301] BOS: 151645 / <|im_end|>
[2026-01-30 09:56:16,721] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:287] [PID:301] PAD: 151643 / <|endoftext|>
[2026-01-30 09:56:16,721] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:288] [PID:301] UNK: None / None
[2026-01-30 09:57:39,263] [INFO] [axolotl.utils.data.shared.load_preprocessed_dataset:481] [PID:301] Unable to find prepared dataset in last_run_prepared/ba0ae834220c702ae7aefbdbfde66c85
[2026-01-30 09:57:40,207] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:285] [PID:301] EOS: 151645 / <|im_end|>
[2026-01-30 09:57:40,207] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:286] [PID:301] BOS: 151645 / <|im_end|>
[2026-01-30 09:57:40,207] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:287] [PID:301] PAD: 151643 / <|endoftext|>
[2026-01-30 09:57:40,207] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:288] [PID:301] UNK: None / None
 Saving the dataset (0/3 shards): 0%| | 0/1000 [00:00<?, ? examples/s] Saving the dataset (0/3 shards): 33%|███▎ | 334/1000 [00:00<00:00, 2874.63 examples/s] Saving the dataset (1/3 shards): 33%|███▎ | 334/1000 [00:00<00:00, 2874.63 examples/s] Saving the dataset (2/3 shards): 67%|██████▋ | 667/1000 [00:00<00:00, 2874.63 examples/s] Saving the dataset (3/3 shards): 100%|██████████| 1000/1000 [00:00<00:00, 2874.63 examples/s] Saving the dataset (3/3 shards): 100%|██████████| 1000/1000 [00:00<00:00, 4982.82 examples/s]
[2026-01-30 09:57:41,815] [DEBUG] [axolotl.train.setup_model_and_tokenizer:70] [PID:301] loading tokenizer... /cache/models/Qwen--Qwen2.5-3B-Instruct
[2026-01-30 09:57:42,451] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:285] [PID:301] EOS: 151645 / <|im_end|>
[2026-01-30 09:57:42,452] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:286] [PID:301] BOS: 151645 / <|im_end|>
[2026-01-30 09:57:42,452] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:287] [PID:301] PAD: 151643 / <|endoftext|>
[2026-01-30 09:57:42,452] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:288] [PID:301] UNK: None / None
[2026-01-30 09:57:42,452] [DEBUG] [axolotl.train.setup_model_and_tokenizer:82] [PID:301] Loading model
[2026-01-30 09:57:42,461] [DEBUG] [axolotl.monkeypatch.transformers.trainer_loss_calc.patch_evaluation_loop:87] [PID:301] Patched Trainer.evaluation_loop with nanmean loss calculation
[2026-01-30 09:57:42,463] [DEBUG] [axolotl.monkeypatch.transformers.trainer_loss_calc.patch_maybe_log_save_evaluate:138] [PID:301] Patched Trainer._maybe_log_save_evaluate with nanmean loss calculation
 Loading weights: 0%| | 0/434 [00:00<?, ?it/s] Loading weights: 0%| | 1/434 [00:00<00:00, 6574.14it/s, Materializing param=model.embed_tokens.weight] Loading weights: 0%| | 1/434 [00:00<00:00, 4084.04it/s, Materializing param=model.embed_tokens.weight] Loading weights: 0%| | 2/434 [00:00<00:12, 35.85it/s, Materializing param=model.layers.0.input_layernorm.weight] Loading weights: 0%| | 2/434 [00:00<00:12, 35.74it/s, Materializing param=model.layers.0.input_layernorm.weight] Loading weights: 1%| | 3/434 [00:00<00:08, 53.43it/s, Materializing param=model.layers.0.mlp.down_proj.weight] Loading weights: 1%| | 3/434 [00:00<00:08, 53.37it/s, Materializing param=model.layers.0.mlp.down_proj.weight] Loading weights: 1%| | 4/434 [00:00<00:06, 63.18it/s, Materializing param=model.layers.0.mlp.gate_proj.weight] Loading weights: 1%| | 4/434 [00:00<00:06, 63.11it/s, Materializing param=model.layers.0.mlp.gate_proj.weight] Loading weights: 1%| | 5/434 [00:00<00:06, 70.12it/s, Materializing param=model.layers.0.mlp.up_proj.weight] Loading weights: 1%| | 5/434 [00:00<00:06, 70.07it/s, Materializing param=model.layers.0.mlp.up_proj.weight] Loading weights: 1%|▏ | 6/434 [00:00<00:05, 78.73it/s, Materializing param=model.layers.0.post_attention_layernorm.weight] Loading weights: 1%|▏ | 6/434 [00:00<00:05, 78.65it/s, Materializing param=model.layers.0.post_attention_layernorm.weight] Loading weights: 2%|▏ | 7/434 [00:00<00:04, 91.62it/s, Materializing param=model.layers.0.self_attn.k_proj.bias] Loading weights: 2%|▏ | 7/434 [00:00<00:04, 91.56it/s, Materializing param=model.layers.0.self_attn.k_proj.bias] Loading weights: 2%|▏ | 8/434 [00:00<00:04, 104.43it/s, Materializing param=model.layers.0.self_attn.k_proj.weight] Loading weights: 2%|▏ | 8/434 [00:00<00:04, 104.34it/s, Materializing param=model.layers.0.self_attn.k_proj.weight] Loading weights: 2%|▏ | 9/434 [00:00<00:03, 117.26it/s, Materializing param=model.layers.0.self_attn.o_proj.weight] Loading weights: 2%|▏ | 9/434 [00:00<00:03, 117.19it/s, Materializing param=model.layers.0.self_attn.o_proj.weight] Loading weights: 2%|▏ | 10/434 [00:00<00:03, 128.69it/s, Materializing param=model.layers.0.self_attn.q_proj.bias] Loading weights: 2%|▏ | 10/434 [00:00<00:03, 128.59it/s, Materializing param=model.layers.0.self_attn.q_proj.bias] Loading weights: 3%|▎ | 11/434 [00:00<00:02, 141.31it/s, Materializing param=model.layers.0.self_attn.q_proj.weight] Loading weights: 3%|▎ | 11/434 [00:00<00:02, 141.20it/s, Materializing param=model.layers.0.self_attn.q_proj.weight] Loading weights: 3%|▎ | 12/434 [00:00<00:02, 151.43it/s, Materializing param=model.layers.0.self_attn.v_proj.bias] Loading weights: 3%|▎ | 12/434 [00:00<00:02, 151.27it/s, Materializing param=model.layers.0.self_attn.v_proj.bias] Loading weights: 3%|▎ | 13/434 [00:00<00:02, 161.98it/s, Materializing param=model.layers.0.self_attn.v_proj.weight] Loading weights: 3%|▎ | 13/434 [00:00<00:02, 161.82it/s, Materializing param=model.layers.0.self_attn.v_proj.weight] Loading weights: 3%|▎ | 14/434 [00:00<00:02, 174.08it/s, Materializing param=model.layers.1.input_layernorm.weight] Loading weights: 3%|▎ | 14/434 [00:00<00:02, 173.99it/s, Materializing param=model.layers.1.input_layernorm.weight] Loading weights: 3%|▎ | 15/434 [00:00<00:02, 186.25it/s, Materializing param=model.layers.1.mlp.down_proj.weight] Loading weights: 3%|▎ | 15/434 [00:00<00:02, 186.16it/s, Materializing param=model.layers.1.mlp.down_proj.weight] Loading weights: 4%|▎ | 16/434 [00:00<00:02, 182.99it/s, Materializing param=model.layers.1.mlp.gate_proj.weight] Loading weights: 4%|▎ | 16/434 [00:00<00:02, 182.79it/s, Materializing param=model.layers.1.mlp.gate_proj.weight] Loading weights: 4%|▍ | 17/434 [00:00<00:02, 164.86it/s, Materializing param=model.layers.1.mlp.gate_proj.weight] Loading weights: 4%|▍ | 17/434 [00:00<00:02, 164.86it/s, Materializing param=model.layers.1.mlp.up_proj.weight] Loading weights: 4%|▍ | 17/434 [00:00<00:02, 164.86it/s, Materializing param=model.layers.1.mlp.up_proj.weight] Loading weights: 4%|▍ | 18/434 [00:00<00:02, 164.86it/s, Materializing param=model.layers.1.post_attention_layernorm.weight] Loading weights: 4%|▍ | 18/434 [00:00<00:02, 164.86it/s, Materializing param=model.layers.1.post_attention_layernorm.weight] Loading weights: 4%|▍ | 19/434 [00:00<00:02, 164.86it/s, Materializing param=model.layers.1.self_attn.k_proj.bias] Loading weights: 4%|▍ | 19/434 [00:00<00:02, 164.86it/s, Materializing param=model.layers.1.self_attn.k_proj.bias] Loading weights: 5%|▍ | 20/434 [00:00<00:02, 164.86it/s, Materializing param=model.layers.1.self_attn.k_proj.weight] Loading weights: 5%|▍ | 20/434 [00:00<00:02, 164.86it/s, Materializing param=model.layers.1.self_attn.k_proj.weight] Loading weights: 5%|▍ | 21/434 [00:00<00:02, 164.86it/s, Materializing param=model.layers.1.self_attn.o_proj.weight] Loading weights: 5%|▍ | 21/434 [00:00<00:02, 164.86it/s, Materializing param=model.layers.1.self_attn.o_proj.weight] Loading weights: 5%|▌ | 22/434 [00:00<00:02, 164.86it/s, Materializing param=model.layers.1.self_attn.q_proj.bias] Loading weights: 5%|▌ | 22/434 [00:00<00:02, 164.86it/s, Materializing param=model.layers.1.self_attn.q_proj.bias] Loading weights: 5%|▌ | 23/434 [00:00<00:02, 164.86it/s, Materializing param=model.layers.1.self_attn.q_proj.weight] Loading weights: 5%|▌ | 23/434 [00:00<00:02, 164.86it/s, Materializing param=model.layers.1.self_attn.q_proj.weight] Loading weights: 6%|▌ | 24/434 [00:00<00:02, 164.86it/s, Materializing param=model.layers.1.self_attn.v_proj.bias] Loading weights: 6%|▌ | 24/434 [00:00<00:02, 164.86it/s, Materializing param=model.layers.1.self_attn.v_proj.bias] Loading weights: 6%|▌ | 25/434 [00:00<00:02, 164.86it/s, Materializing param=model.layers.1.self_attn.v_proj.weight] Loading weights: 6%|▌ | 25/434 [00:00<00:02, 164.86it/s, Materializing param=model.layers.1.self_attn.v_proj.weight] Loading weights: 6%|▌ | 26/434 [00:00<00:02, 164.86it/s, Materializing param=model.layers.2.input_layernorm.weight] Loading weights: 6%|▌ | 26/434 [00:00<00:02, 164.86it/s, Materializing param=model.layers.2.input_layernorm.weight] Loading weights: 6%|▌ | 27/434 [00:00<00:02, 164.86it/s, Materializing param=model.layers.2.mlp.down_proj.weight] Loading weights: 6%|▌ | 27/434 [00:00<00:02, 164.86it/s, Materializing param=model.layers.2.mlp.down_proj.weight] Loading weights: 6%|▋ | 28/434 [00:00<00:02, 164.86it/s, Materializing param=model.layers.2.mlp.gate_proj.weight] Loading weights: 6%|▋ | 28/434 [00:00<00:02, 164.86it/s, Materializing param=model.layers.2.mlp.gate_proj.weight] Loading weights: 7%|▋ | 29/434 [00:00<00:02, 164.86it/s, Materializing param=model.layers.2.mlp.up_proj.weight] Loading weights: 7%|▋ | 29/434 [00:00<00:02, 164.86it/s, Materializing param=model.layers.2.mlp.up_proj.weight] Loading weights: 7%|▋ | 30/434 [00:00<00:02, 164.86it/s, Materializing param=model.layers.2.post_attention_layernorm.weight] Loading weights: 7%|▋ | 30/434 [00:00<00:02, 164.86it/s, Materializing param=model.layers.2.post_attention_layernorm.weight] Loading weights: 7%|▋ | 31/434 [00:00<00:02, 164.86it/s, Materializing param=model.layers.2.self_attn.k_proj.bias] Loading weights: 7%|▋ | 31/434 [00:00<00:02, 164.86it/s, Materializing param=model.layers.2.self_attn.k_proj.bias] Loading weights: 7%|▋ | 32/434 [00:00<00:02, 164.86it/s, Materializing param=model.layers.2.self_attn.k_proj.weight] Loading weights: 7%|▋ | 32/434 [00:00<00:02, 164.86it/s, Materializing param=model.layers.2.self_attn.k_proj.weight] Loading weights: 8%|▊ | 33/434 [00:00<00:02, 164.86it/s, Materializing param=model.layers.2.self_attn.o_proj.weight] Loading weights: 8%|▊ | 33/434 [00:00<00:02, 164.86it/s, Materializing param=model.layers.2.self_attn.o_proj.weight] Loading weights: 8%|▊ | 34/434 [00:00<00:02, 164.86it/s, Materializing param=model.layers.2.self_attn.q_proj.bias] Loading weights: 8%|▊ | 34/434 [00:00<00:02, 164.86it/s, Materializing param=model.layers.2.self_attn.q_proj.bias] Loading weights: 8%|▊ | 35/434 [00:00<00:02, 164.86it/s, Materializing param=model.layers.2.self_attn.q_proj.weight] Loading weights: 8%|▊ | 35/434 [00:00<00:02, 164.86it/s, Materializing param=model.layers.2.self_attn.q_proj.weight] Loading weights: 8%|▊ | 36/434 [00:00<00:02, 164.86it/s, Materializing param=model.layers.2.self_attn.v_proj.bias] Loading weights: 8%|▊ | 36/434 [00:00<00:02, 164.86it/s, Materializing param=model.layers.2.self_attn.v_proj.bias] Loading weights: 9%|▊ | 37/434 [00:00<00:02, 164.86it/s, Materializing param=model.layers.2.self_attn.v_proj.weight] Loading weights: 9%|▊ | 37/434 [00:00<00:02, 164.86it/s, Materializing param=model.layers.2.self_attn.v_proj.weight] Loading weights: 9%|▉ | 38/434 [00:00<00:02, 164.86it/s, Materializing param=model.layers.3.input_layernorm.weight] Loading weights: 9%|▉ | 38/434 [00:00<00:02, 164.86it/s, Materializing param=model.layers.3.input_layernorm.weight] Loading weights: 9%|▉ | 39/434 [00:00<00:02, 164.86it/s, Materializing param=model.layers.3.mlp.down_proj.weight] Loading weights: 9%|▉ | 39/434 [00:00<00:02, 164.86it/s, Materializing param=model.layers.3.mlp.down_proj.weight] Loading weights: 9%|▉ | 40/434 [00:00<00:02, 164.86it/s, Materializing param=model.layers.3.mlp.gate_proj.weight] Loading weights: 9%|▉ | 40/434 [00:00<00:02, 164.86it/s, Materializing param=model.layers.3.mlp.gate_proj.weight] Loading weights: 9%|▉ | 41/434 [00:00<00:02, 164.86it/s, Materializing param=model.layers.3.mlp.up_proj.weight] Loading weights: 9%|▉ | 41/434 [00:00<00:02, 164.86it/s, Materializing param=model.layers.3.mlp.up_proj.weight] Loading weights: 10%|▉ | 42/434 [00:00<00:02, 164.86it/s, Materializing param=model.layers.3.post_attention_layernorm.weight] Loading weights: 10%|▉ | 42/434 [00:00<00:02, 164.86it/s, Materializing param=model.layers.3.post_attention_layernorm.weight] Loading weights: 10%|▉ | 43/434 [00:00<00:02, 164.86it/s, Materializing param=model.layers.3.self_attn.k_proj.bias] Loading weights: 10%|▉ | 43/434 [00:00<00:02, 164.86it/s, Materializing param=model.layers.3.self_attn.k_proj.bias] Loading weights: 10%|█ | 44/434 [00:00<00:02, 164.86it/s, Materializing param=model.layers.3.self_attn.k_proj.weight] Loading weights: 10%|█ | 44/434 [00:00<00:02, 164.86it/s, Materializing param=model.layers.3.self_attn.k_proj.weight] Loading weights: 10%|█ | 45/434 [00:00<00:02, 164.86it/s, Materializing param=model.layers.3.self_attn.o_proj.weight] Loading weights: 10%|█ | 45/434 [00:00<00:02, 164.86it/s, Materializing param=model.layers.3.self_attn.o_proj.weight] Loading weights: 11%|█ | 46/434 [00:00<00:02, 164.86it/s, Materializing param=model.layers.3.self_attn.q_proj.bias] Loading weights: 11%|█ | 46/434 [00:00<00:02, 164.86it/s, Materializing param=model.layers.3.self_attn.q_proj.bias] Loading weights: 11%|█ | 47/434 [00:00<00:02, 164.86it/s, Materializing param=model.layers.3.self_attn.q_proj.weight] Loading weights: 11%|█ | 47/434 [00:00<00:02, 164.86it/s, Materializing param=model.layers.3.self_attn.q_proj.weight] Loading weights: 11%|█ | 48/434 [00:00<00:01, 248.98it/s, Materializing param=model.layers.3.self_attn.q_proj.weight] Loading weights: 11%|█ | 48/434 [00:00<00:01, 248.98it/s, Materializing param=model.layers.3.self_attn.v_proj.bias] Loading weights: 11%|█ | 48/434 [00:00<00:01, 248.98it/s, Materializing param=model.layers.3.self_attn.v_proj.bias] Loading weights: 11%|█▏ | 49/434 [00:00<00:01, 248.98it/s, Materializing param=model.layers.3.self_attn.v_proj.weight] Loading weights: 11%|█▏ | 49/434 [00:00<00:01, 248.98it/s, Materializing param=model.layers.3.self_attn.v_proj.weight] Loading weights: 12%|█▏ | 50/434 [00:00<00:01, 248.98it/s, Materializing param=model.layers.4.input_layernorm.weight] Loading weights: 12%|█▏ | 50/434 [00:00<00:01, 248.98it/s, Materializing param=model.layers.4.input_layernorm.weight] Loading weights: 12%|█▏ | 51/434 [00:00<00:01, 248.98it/s, Materializing param=model.layers.4.mlp.down_proj.weight] Loading weights: 12%|█▏ | 51/434 [00:00<00:01, 248.98it/s, Materializing param=model.layers.4.mlp.down_proj.weight] Loading weights: 12%|█▏ | 52/434 [00:00<00:01, 248.98it/s, Materializing param=model.layers.4.mlp.gate_proj.weight] Loading weights: 12%|█▏ | 52/434 [00:00<00:01, 248.98it/s, Materializing param=model.layers.4.mlp.gate_proj.weight] Loading weights: 12%|█▏ | 53/434 [00:00<00:01, 248.98it/s, Materializing param=model.layers.4.mlp.up_proj.weight] Loading weights: 12%|█▏ | 53/434 [00:00<00:01, 248.98it/s, Materializing param=model.layers.4.mlp.up_proj.weight] Loading weights: 12%|█▏ | 54/434 [00:00<00:01, 248.98it/s, Materializing param=model.layers.4.post_attention_layernorm.weight] Loading weights: 12%|█▏ | 54/434 [00:00<00:01, 248.98it/s, Materializing param=model.layers.4.post_attention_layernorm.weight] Loading weights: 13%|█▎ | 55/434 [00:00<00:01, 248.98it/s, Materializing param=model.layers.4.self_attn.k_proj.bias] Loading weights: 13%|█▎ | 55/434 [00:00<00:01, 248.98it/s, Materializing param=model.layers.4.self_attn.k_proj.bias] Loading weights: 13%|█▎ | 56/434 [00:00<00:01, 248.98it/s, Materializing param=model.layers.4.self_attn.k_proj.weight] Loading weights: 13%|█▎ | 56/434 [00:00<00:01, 248.98it/s, Materializing param=model.layers.4.self_attn.k_proj.weight] Loading weights: 13%|█▎ | 57/434 [00:00<00:01, 248.98it/s, Materializing param=model.layers.4.self_attn.o_proj.weight] Loading weights: 13%|█▎ | 57/434 [00:00<00:01, 248.98it/s, Materializing param=model.layers.4.self_attn.o_proj.weight] Loading weights: 13%|█▎ | 58/434 [00:00<00:01, 248.98it/s, Materializing param=model.layers.4.self_attn.q_proj.bias] Loading weights: 13%|█▎ | 58/434 [00:00<00:01, 248.98it/s, Materializing param=model.layers.4.self_attn.q_proj.bias] Loading weights: 14%|█▎ | 59/434 [00:00<00:01, 248.98it/s, Materializing param=model.layers.4.self_attn.q_proj.weight] Loading weights: 14%|█▎ | 59/434 [00:00<00:01, 248.98it/s, Materializing param=model.layers.4.self_attn.q_proj.weight] Loading weights: 14%|█▍ | 60/434 [00:00<00:01, 248.98it/s, Materializing param=model.layers.4.self_attn.v_proj.bias] Loading weights: 14%|█▍ | 60/434 [00:00<00:01, 248.98it/s, Materializing param=model.layers.4.self_attn.v_proj.bias] Loading weights: 14%|█▍ | 61/434 [00:00<00:01, 248.98it/s, Materializing param=model.layers.4.self_attn.v_proj.weight] Loading weights: 14%|█▍ | 61/434 [00:00<00:01, 248.98it/s, Materializing param=model.layers.4.self_attn.v_proj.weight] Loading weights: 14%|█▍ | 62/434 [00:00<00:01, 248.98it/s, Materializing param=model.layers.5.input_layernorm.weight] Loading weights: 14%|█▍ | 62/434 [00:00<00:01, 248.98it/s, Materializing param=model.layers.5.input_layernorm.weight] Loading weights: 15%|█▍ | 63/434 [00:00<00:01, 248.98it/s, Materializing param=model.layers.5.mlp.down_proj.weight] Loading weights: 15%|█▍ | 63/434 [00:00<00:01, 248.98it/s, Materializing param=model.layers.5.mlp.down_proj.weight] Loading weights: 15%|█▍ | 64/434 [00:00<00:01, 248.98it/s, Materializing param=model.layers.5.mlp.gate_proj.weight] Loading weights: 15%|█▍ | 64/434 [00:00<00:01, 248.98it/s, Materializing param=model.layers.5.mlp.gate_proj.weight] Loading weights: 15%|█▍ | 65/434 [00:00<00:01, 248.98it/s, Materializing param=model.layers.5.mlp.up_proj.weight] Loading weights: 15%|█▍ | 65/434 [00:00<00:01, 248.98it/s, Materializing param=model.layers.5.mlp.up_proj.weight] Loading weights: 15%|█▌ | 66/434 [00:00<00:01, 248.98it/s, Materializing param=model.layers.5.post_attention_layernorm.weight] Loading weights: 15%|█▌ | 66/434 [00:00<00:01, 248.98it/s, Materializing param=model.layers.5.post_attention_layernorm.weight] Loading weights: 15%|█▌ | 67/434 [00:00<00:01, 248.98it/s, Materializing param=model.layers.5.self_attn.k_proj.bias] Loading weights: 15%|█▌ | 67/434 [00:00<00:01, 248.98it/s, Materializing param=model.layers.5.self_attn.k_proj.bias] Loading weights: 16%|█▌ | 68/434 [00:00<00:01, 248.98it/s, Materializing param=model.layers.5.self_attn.k_proj.weight] Loading weights: 16%|█▌ | 68/434 [00:00<00:01, 248.98it/s, Materializing param=model.layers.5.self_attn.k_proj.weight] Loading weights: 16%|█▌ | 69/434 [00:00<00:01, 248.98it/s, Materializing param=model.layers.5.self_attn.o_proj.weight] Loading weights: 16%|█▌ | 69/434 [00:00<00:01, 248.98it/s, Materializing param=model.layers.5.self_attn.o_proj.weight]