Text Generation
PEFT
TensorBoard
Safetensors
Transformers
olmo3
axolotl
lora
conversational
8-bit precision
bitsandbytes
Instructions to use ConicCat/Guten-SFT-LORA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use ConicCat/Guten-SFT-LORA with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("allenai/Olmo-3.1-32B-Instruct") model = PeftModel.from_pretrained(base_model, "ConicCat/Guten-SFT-LORA") - Transformers
How to use ConicCat/Guten-SFT-LORA with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="ConicCat/Guten-SFT-LORA") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("ConicCat/Guten-SFT-LORA") model = AutoModelForCausalLM.from_pretrained("ConicCat/Guten-SFT-LORA") messages = [ {"role": "user", "content": "Who are you?"}, ] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=40) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use ConicCat/Guten-SFT-LORA with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "ConicCat/Guten-SFT-LORA" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "ConicCat/Guten-SFT-LORA", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/ConicCat/Guten-SFT-LORA
- SGLang
How to use ConicCat/Guten-SFT-LORA with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "ConicCat/Guten-SFT-LORA" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "ConicCat/Guten-SFT-LORA", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "ConicCat/Guten-SFT-LORA" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "ConicCat/Guten-SFT-LORA", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use ConicCat/Guten-SFT-LORA with Docker Model Runner:
docker model run hf.co/ConicCat/Guten-SFT-LORA
| [2026-01-28 18:42:35,684] [DEBUG] [axolotl.utils.config.log_gpu_memory_usage:127] [PID:11475] baseline 0.000GB () | |
| [2026-01-28 18:42:35,684] [INFO] [axolotl.cli.config.load_cfg:259] [PID:11475] config: | |
| { | |
| "activation_offloading": false, | |
| "adapter": "lora", | |
| "axolotl_config_path": "Guten.yaml", | |
| "base_model": "allenai/Olmo-3.1-32B-Instruct", | |
| "base_model_config": "allenai/Olmo-3.1-32B-Instruct", | |
| "batch_size": 8, | |
| "bf16": true, | |
| "capabilities": { | |
| "bf16": true, | |
| "compute_capability": "sm_80", | |
| "fp8": false, | |
| "n_gpu": 1, | |
| "n_node": 1 | |
| }, | |
| "chat_template": "chatml", | |
| "context_parallel_size": 1, | |
| "dataloader_num_workers": 1, | |
| "dataloader_pin_memory": true, | |
| "dataloader_prefetch_factor": 256, | |
| "dataset_num_proc": 12, | |
| "datasets": [ | |
| { | |
| "chat_template": "tokenizer_default", | |
| "message_property_mappings": { | |
| "content": "content", | |
| "role": "role" | |
| }, | |
| "path": "./gutenbeg-2-sft-train.jsonl", | |
| "train_on_eos": "all", | |
| "trust_remote_code": false, | |
| "type": "chat_template" | |
| }, | |
| { | |
| "chat_template": "tokenizer_default", | |
| "message_property_mappings": { | |
| "content": "content", | |
| "role": "role" | |
| }, | |
| "path": "./condor-sft-train.jsonl", | |
| "train_on_eos": "all", | |
| "trust_remote_code": false, | |
| "type": "chat_template" | |
| } | |
| ], | |
| "ddp": false, | |
| "device": "cuda:0", | |
| "dion_rank_fraction": 1.0, | |
| "dion_rank_multiple_of": 1, | |
| "env_capabilities": { | |
| "torch_version": "2.8.0" | |
| }, | |
| "eot_tokens": [ | |
| "<|im_end|>" | |
| ], | |
| "eval_batch_size": 2, | |
| "eval_causal_lm_metrics": [ | |
| "sacrebleu", | |
| "comet", | |
| "ter", | |
| "chrf" | |
| ], | |
| "eval_max_new_tokens": 128, | |
| "eval_sample_packing": true, | |
| "eval_table_size": 0, | |
| "experimental_skip_move_to_device": true, | |
| "flash_attention": true, | |
| "fp16": false, | |
| "gradient_accumulation_steps": 4, | |
| "gradient_checkpointing": true, | |
| "gradient_checkpointing_kwargs": { | |
| "use_reentrant": true | |
| }, | |
| "include_tkps": true, | |
| "learning_rate": 2.5e-05, | |
| "liger_fused_linear_cross_entropy": true, | |
| "liger_glu_activation": true, | |
| "liger_layer_norm": true, | |
| "liger_rms_norm": true, | |
| "liger_rope": true, | |
| "lisa_layers_attribute": "model.layers", | |
| "load_best_model_at_end": false, | |
| "load_in_4bit": false, | |
| "load_in_8bit": true, | |
| "local_rank": 0, | |
| "logging_steps": 1, | |
| "lora_alpha": 128, | |
| "lora_dropout": 0.0, | |
| "lora_mlp_kernel": false, | |
| "lora_o_kernel": false, | |
| "lora_qkv_kernel": false, | |
| "lora_r": 64, | |
| "lora_target_linear": true, | |
| "loraplus_lr_embedding": 1e-06, | |
| "loraplus_lr_ratio": 16.0, | |
| "lr_scheduler": "constant_with_warmup", | |
| "max_grad_norm": 1.0, | |
| "mean_resizing_embeddings": false, | |
| "micro_batch_size": 2, | |
| "model_config_type": "olmo3", | |
| "num_epochs": 2.0, | |
| "optimizer": "paged_adamw_8bit", | |
| "otel_metrics_host": "localhost", | |
| "otel_metrics_port": 8000, | |
| "output_dir": "./Olmo-Guten-SFT", | |
| "pad_to_sequence_len": true, | |
| "plugins": [ | |
| "axolotl.integrations.liger.LigerPlugin" | |
| ], | |
| "pretrain_multipack_attn": true, | |
| "profiler_steps_start": 0, | |
| "qlora_sharded_model_loading": false, | |
| "ray_num_workers": 1, | |
| "resources_per_worker": { | |
| "GPU": 1 | |
| }, | |
| "sample_packing": true, | |
| "sample_packing_bin_size": 200, | |
| "sample_packing_group_size": 100000, | |
| "save_only_model": false, | |
| "save_safetensors": true, | |
| "seed": 42, | |
| "sequence_len": 6144, | |
| "shuffle_before_merging_datasets": false, | |
| "shuffle_merged_datasets": true, | |
| "skip_prepare_dataset": false, | |
| "streaming_multipack_buffer_size": 10000, | |
| "strict": false, | |
| "tensor_parallel_size": 1, | |
| "tf32": true, | |
| "tiled_mlp_use_original_mlp": true, | |
| "tokenizer_config": "allenai/Olmo-3.1-32B-Instruct", | |
| "tokenizer_save_jinja_files": true, | |
| "torch_dtype": "torch.bfloat16", | |
| "train_on_inputs": false, | |
| "trl": { | |
| "log_completions": false, | |
| "mask_truncated_completions": false, | |
| "ref_model_mixup_alpha": 0.9, | |
| "ref_model_sync_steps": 64, | |
| "scale_rewards": true, | |
| "sync_ref_model": false, | |
| "use_vllm": false, | |
| "vllm_server_host": "0.0.0.0", | |
| "vllm_server_port": 8000 | |
| }, | |
| "use_otel_metrics": false, | |
| "use_ray": false, | |
| "use_tensorboard": true, | |
| "val_set_size": 0.0, | |
| "vllm": { | |
| "device": "auto", | |
| "dtype": "auto", | |
| "gpu_memory_utilization": 0.9, | |
| "host": "0.0.0.0", | |
| "port": 8000 | |
| }, | |
| "warmup_ratio": 0.05, | |
| "weight_decay": 0.0, | |
| "world_size": 1 | |
| } | |
| [2026-01-28 18:42:35,686] [WARNING] [axolotl.cli.checks.check_user_token:46] [PID:11475] Error verifying HuggingFace token. Remember to log in using `huggingface-cli login` and get your access token from https://huggingface.co/settings/tokens if you want to use gated models or datasets. | |
| [2026-01-28 18:42:36,259] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:285] [PID:11475] EOS: 100257 / <|endoftext|> | |
| [2026-01-28 18:42:36,259] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:286] [PID:11475] BOS: 100257 / <|endoftext|> | |
| [2026-01-28 18:42:36,259] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:287] [PID:11475] PAD: 100277 / <|pad|> | |
| [2026-01-28 18:42:36,259] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:288] [PID:11475] UNK: 100257 / <|endoftext|> | |
| [2026-01-28 18:42:36,260] [INFO] [axolotl.utils.data.shared.load_preprocessed_dataset:481] [PID:11475] Unable to find prepared dataset in last_run_prepared/ef6f6bab0786bc209a0a8382fdc0cfca | |
| [2026-01-28 18:42:36,261] [INFO] [axolotl.utils.data.sft._load_raw_datasets:320] [PID:11475] Loading raw datasets... | |
| [2026-01-28 18:42:36,261] [WARNING] [axolotl.utils.data.sft._load_raw_datasets:322] [PID:11475] Processing datasets during training can lead to VRAM instability. Please pre-process your dataset using `axolotl preprocess path/to/config.yml`. | |
| [2026-01-28 18:42:36,382] [INFO] [axolotl.utils.data.wrappers.get_dataset_wrapper:87] [PID:11475] Loading dataset: ./gutenbeg-2-sft-train.jsonl with base_type: chat_template and prompt_style: None | |
| [2026-01-28 18:42:36,385] [INFO] [axolotl.prompt_strategies.chat_template.__call__:996] [PID:11475] Using chat template: | |
| --- | |
| {% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + ' | |
| ' + message['content'] + '<|im_end|>' + ' | |
| '}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant | |
| ' }}{% endif %} | |
| --- | |
| [2026-01-28 18:42:36,521] [INFO] [axolotl.utils.data.wrappers.get_dataset_wrapper:87] [PID:11475] Loading dataset: ./condor-sft-train.jsonl with base_type: chat_template and prompt_style: None | |
| [2026-01-28 18:42:36,521] [INFO] [axolotl.prompt_strategies.chat_template.__call__:996] [PID:11475] Using chat template: | |
| --- | |
| {% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + ' | |
| ' + message['content'] + '<|im_end|>' + ' | |
| '}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant | |
| ' }}{% endif %} | |
| --- | |
| [2026-01-28 18:42:36,606] [INFO] [axolotl.utils.data.shared.merge_datasets:556] [PID:11475] Merging datasets... | |
| [2026-01-28 18:42:36,612] [DEBUG] [axolotl.utils.data.shared.merge_datasets:560] [PID:11475] Shuffling merged datasets... | |
| [2026-01-28 18:42:36,618] [INFO] [axolotl.utils.data.utils.handle_long_seq_in_dataset:224] [PID:11475] min_input_len: 45 | |
| [2026-01-28 18:42:36,618] [INFO] [axolotl.utils.data.utils.handle_long_seq_in_dataset:226] [PID:11475] max_input_len: 14764 | |
| [2026-01-28 18:42:36,653] [WARNING] [axolotl.utils.data.utils.handle_long_seq_in_dataset:270] [PID:11475] Dropped 30 samples from dataset | |
| Saving the dataset (0/2 shards): 0%| | 0/513 [00:00<?, ? examples/s] Saving the dataset (0/2 shards): 50%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 256/513 [00:00<00:00, 1647.28 examples/s] Saving the dataset (1/2 shards): 50%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 256/513 [00:00<00:00, 1647.28 examples/s] Saving the dataset (2/2 shards): 100%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ| 513/513 [00:00<00:00, 1647.28 examples/s] Saving the dataset (2/2 shards): 100%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ| 513/513 [00:00<00:00, 1876.92 examples/s] | |
| [2026-01-28 18:42:37,074] [DEBUG] [axolotl.utils.trainer.calculate_total_num_steps:417] [PID:11475] total_num_tokens: 1_054_992 | |
| [2026-01-28 18:42:37,097] [DEBUG] [axolotl.utils.trainer.calculate_total_num_steps:435] [PID:11475] `total_supervised_tokens: 934_551` | |
| [2026-01-28 18:42:37,122] [DEBUG] [axolotl.utils.samplers.multipack.pack_parallel:177] [PID:11475] Using single process for pack_parallel, running sequentially. | |
| [2026-01-28 18:42:38,026] [DEBUG] [axolotl.utils.samplers.multipack.pack_parallel:177] [PID:11475] Using single process for pack_parallel, running sequentially. | |
| [2026-01-28 18:42:38,326] [DEBUG] [axolotl.utils.samplers.multipack.__len__:462] [PID:11475] generate_batches time: 0.3006432056427002 | |
| [2026-01-28 18:42:38,326] [DEBUG] [axolotl.utils.samplers.multipack.pack_parallel:177] [PID:11475] Using single process for pack_parallel, running sequentially. | |
| [2026-01-28 18:42:38,611] [DEBUG] [axolotl.utils.samplers.multipack.__len__:462] [PID:11475] generate_batches time: 0.284991979598999 | |
| [2026-01-28 18:42:38,612] [DEBUG] [axolotl.utils.samplers.multipack.pack_parallel:177] [PID:11475] Using single process for pack_parallel, running sequentially. | |
| [2026-01-28 18:42:38,879] [DEBUG] [axolotl.utils.samplers.multipack.__len__:462] [PID:11475] generate_batches time: 0.2676815986633301 | |
| [2026-01-28 18:42:38,880] [DEBUG] [axolotl.utils.samplers.multipack.pack_parallel:177] [PID:11475] Using single process for pack_parallel, running sequentially. | |
| [2026-01-28 18:42:39,141] [DEBUG] [axolotl.utils.samplers.multipack.__len__:462] [PID:11475] generate_batches time: 0.2612743377685547 | |
| [2026-01-28 18:42:39,176] [INFO] [axolotl.utils.samplers.multipack.calc_min_len:438] [PID:11475] gather_len_batches: [87] | |
| [2026-01-28 18:42:39,176] [DEBUG] [axolotl.utils.trainer.calculate_total_num_steps:494] [PID:11475] data_loader_len: 21 | |
| [2026-01-28 18:42:39,176] [INFO] [axolotl.utils.trainer.calc_sample_packing_eff_est:510] [PID:11475] sample_packing_eff_est across ranks: [0.9756303267045454] | |
| [2026-01-28 18:42:39,176] [DEBUG] [axolotl.utils.trainer.calculate_total_num_steps:522] [PID:11475] sample_packing_eff_est: 0.98 | |
| [2026-01-28 18:42:39,177] [DEBUG] [axolotl.utils.trainer.calculate_total_num_steps:533] [PID:11475] total_num_steps: 42 | |
| [2026-01-28 18:42:39,177] [INFO] [axolotl.utils.data.sft._prepare_standard_dataset:121] [PID:11475] Maximum number of steps set at 42 | |
| [2026-01-28 18:42:39,200] [DEBUG] [axolotl.train.setup_model_and_tokenizer:70] [PID:11475] loading tokenizer... allenai/Olmo-3.1-32B-Instruct | |
| [2026-01-28 18:42:39,970] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:285] [PID:11475] EOS: 100257 / <|endoftext|> | |
| [2026-01-28 18:42:39,970] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:286] [PID:11475] BOS: 100257 / <|endoftext|> | |
| [2026-01-28 18:42:39,970] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:287] [PID:11475] PAD: 100277 / <|pad|> | |
| [2026-01-28 18:42:39,970] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:288] [PID:11475] UNK: 100257 / <|endoftext|> | |
| [2026-01-28 18:42:39,970] [DEBUG] [axolotl.train.setup_model_and_tokenizer:82] [PID:11475] Loading model | |
| [2026-01-28 18:42:40,046] [DEBUG] [axolotl.monkeypatch.transformers.trainer_loss_calc.patch_evaluation_loop:87] [PID:11475] Patched Trainer.evaluation_loop with nanmean loss calculation | |
| [2026-01-28 18:42:40,048] [DEBUG] [axolotl.monkeypatch.transformers.trainer_loss_calc.patch_maybe_log_save_evaluate:138] [PID:11475] Patched Trainer._maybe_log_save_evaluate with nanmean loss calculation | |
| [2026-01-28 18:42:40,049] [INFO] [axolotl.loaders.patch_manager._apply_multipack_patches:345] [PID:11475] Applying multipack dataloader patch for sample packing... | |
| [2026-01-28 18:42:40,170] [INFO] [axolotl.integrations.liger.plugin.pre_model_load:98] [PID:11475] Applying LIGER to olmo3 with kwargs: {'rope': True, 'cross_entropy': None, 'fused_linear_cross_entropy': True, 'rms_norm': True, 'swiglu': True} | |
| model.safetensors.index.json: 0.00B [00:00, ?B/s] model.safetensors.index.json: 59.1kB [00:00, 98.1MB/s] | |
| model-00001-of-00014.safetensors: 0%| | 0.00/4.99G [00:00<?, ?B/s] model-00001-of-00014.safetensors: 0%| | 93.9k/4.99G [00:00<13:08:44, 105kB/s] model-00001-of-00014.safetensors: 1%|βββββ | 67.2M/4.99G [00:02<03:13, 25.5MB/s] model-00001-of-00014.safetensors: 3%|ββββββββββ | 134M/4.99G [00:03<01:27, 55.6MB/s] model-00001-of-00014.safetensors: 5%|ββββββββββββββββββββ | 268M/4.99G [00:03<00:34, 136MB/s] model-00001-of-00014.safetensors: 8%|ββββββββββββββββββββββββββββββ | 403M/4.99G [00:03<00:20, 229MB/s] model-00001-of-00014.safetensors: 15%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 738M/4.99G [00:03<00:07, 543MB/s] model-00001-of-00014.safetensors: 22%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 1.07G/4.99G [00:03<00:04, 899MB/s] model-00001-of-00014.safetensors: 27%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 1.34G/4.99G [00:03<00:03, 1.15GB/s] model-00001-of-00014.safetensors: 32%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 1.61G/4.99G [00:03<00:02, 1.34GB/s] model-00001-of-00014.safetensors: 38%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 1.88G/4.99G [00:03<00:02, 1.55GB/s] model-00001-of-00014.safetensors: 50%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 2.48G/4.99G [00:04<00:01, 2.45GB/s] model-00001-of-00014.safetensors: 56%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 2.82G/4.99G [00:04<00:00, 2.34GB/s] model-00001-of-00014.safetensors: 63%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 3.15G/4.99G [00:04<00:01, 1.46GB/s] model-00001-of-00014.safetensors: 69%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 3.42G/4.99G [00:05<00:01, 1.06GB/s] model-00001-of-00014.safetensors: 73%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 3.62G/4.99G [00:05<00:01, 1.15GB/s] model-00001-of-00014.safetensors: 77%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 3.82G/4.99G [00:05<00:01, 1.02GB/s] model-00001-of-00014.safetensors: 81%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 4.02G/4.99G [00:05<00:01, 839MB/s] model-00001-of-00014.safetensors: 83%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 4.16G/4.99G [00:06<00:01, 796MB/s] model-00001-of-00014.safetensors: 87%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 4.32G/4.99G [00:06<00:01, 644MB/s] model-00001-of-00014.safetensors: 91%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 4.52G/4.99G [00:06<00:00, 792MB/s] model-00001-of-00014.safetensors: 96%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 4.79G/4.99G [00:06<00:00, 910MB/s] model-00001-of-00014.safetensors: 99%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 4.92G/4.99G [00:06<00:00, 898MB/s] model-00001-of-00014.safetensors: 100%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ| 4.99G/4.99G [00:07<00:00, 696MB/s] | |
| model-00002-of-00014.safetensors: 0%| | 0.00/4.94G [00:00<?, ?B/s] model-00002-of-00014.safetensors: 1%|βββββ | 67.0M/4.94G [00:02<03:03, 26.5MB/s] model-00002-of-00014.safetensors: 4%|βββββββββββββββ | 201M/4.94G [00:02<00:51, 91.3MB/s] model-00002-of-00014.safetensors: 7%|βββββββββββββββββββββββββ | 335M/4.94G [00:02<00:26, 173MB/s] model-00002-of-00014.safetensors: 12%|βββββββββββββββββββββββββββββββββββββββββββββ | 604M/4.94G [00:03<00:11, 372MB/s] model-00002-of-00014.safetensors: 18%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 872M/4.94G [00:03<00:06, 610MB/s] model-00002-of-00014.safetensors: 23%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 1.14G/4.94G [00:03<00:04, 864MB/s] model-00002-of-00014.safetensors: 27%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 1.34G/4.94G [00:03<00:03, 1.00GB/s] model-00002-of-00014.safetensors: 33%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 1.61G/4.94G [00:03<00:02, 1.29GB/s] model-00002-of-00014.safetensors: 38%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 1.88G/4.94G [00:03<00:02, 1.48GB/s] model-00002-of-00014.safetensors: 43%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 2.15G/4.94G [00:03<00:01, 1.55GB/s] model-00002-of-00014.safetensors: 50%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 2.48G/4.94G [00:03<00:01, 1.71GB/s] model-00002-of-00014.safetensors: 54%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 2.68G/4.94G [00:04<00:01, 1.56GB/s] model-00002-of-00014.safetensors: 61%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 3.02G/4.94G [00:04<00:01, 1.84GB/s] model-00002-of-00014.safetensors: 66%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 3.26G/4.94G [00:04<00:01, 1.38GB/s] model-00002-of-00014.safetensors: 70%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 3.46G/4.94G [00:04<00:00, 1.48GB/s] model-00002-of-00014.safetensors: 74%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 3.66G/4.94G [00:04<00:01, 1.18GB/s] model-00002-of-00014.safetensors: 81%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 4.00G/4.94G [00:05<00:00, 1.40GB/s] model-00002-of-00014.safetensors: 88%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 4.34G/4.94G [00:05<00:00, 1.63GB/s] model-00002-of-00014.safetensors: 93%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 4.60G/4.94G [00:05<00:00, 1.83GB/s] model-00002-of-00014.safetensors: 99%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 4.87G/4.94G [00:05<00:00, 1.17GB/s] model-00002-of-00014.safetensors: 100%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ| 4.94G/4.94G [00:05<00:00, 840MB/s] | |
| model-00003-of-00014.safetensors: 0%| | 0.00/4.88G [00:00<?, ?B/s] model-00003-of-00014.safetensors: 1%|βββββ | 67.1M/4.88G [00:02<03:09, 25.4MB/s] model-00003-of-00014.safetensors: 4%|βββββββββββββββ | 201M/4.88G [00:02<00:52, 88.8MB/s] model-00003-of-00014.safetensors: 6%|ββββββββββββββββββββ | 268M/4.88G [00:02<00:36, 127MB/s] model-00003-of-00014.safetensors: 10%|ββββββββββββββββββββββββββββββββββββ | 469M/4.88G [00:03<00:15, 281MB/s] model-00003-of-00014.safetensors: 12%|ββββββββββββββββββββββββββββββββββββββββββββββ | 603M/4.88G [00:03<00:11, 370MB/s] model-00003-of-00014.safetensors: 16%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 805M/4.88G [00:03<00:07, 564MB/s] model-00003-of-00014.safetensors: 21%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 1.01G/4.88G [00:03<00:05, 750MB/s] model-00003-of-00014.safetensors: 26%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 1.27G/4.88G [00:03<00:03, 965MB/s] model-00003-of-00014.safetensors: 36%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 1.74G/4.88G [00:03<00:02, 1.53GB/s] model-00003-of-00014.safetensors: 43%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 2.08G/4.88G [00:03<00:01, 1.88GB/s] model-00003-of-00014.safetensors: 48%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 2.35G/4.88G [00:04<00:01, 1.71GB/s] model-00003-of-00014.safetensors: 54%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 2.62G/4.88G [00:04<00:01, 1.74GB/s] model-00003-of-00014.safetensors: 61%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 2.95G/4.88G [00:04<00:01, 1.67GB/s] model-00003-of-00014.safetensors: 65%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 3.15G/4.88G [00:04<00:01, 1.47GB/s] model-00003-of-00014.safetensors: 70%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 3.42G/4.88G [00:04<00:00, 1.64GB/s] model-00003-of-00014.safetensors: 74%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 3.62G/4.88G [00:04<00:00, 1.39GB/s] model-00003-of-00014.safetensors: 78%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 3.82G/4.88G [00:05<00:01, 1.05GB/s] model-00003-of-00014.safetensors: 81%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 3.96G/4.88G [00:05<00:00, 985MB/s] model-00003-of-00014.safetensors: 84%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 4.09G/4.88G [00:05<00:00, 796MB/s] model-00003-of-00014.safetensors: 86%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 4.21G/4.88G [00:05<00:00, 709MB/s] model-00003-of-00014.safetensors: 89%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 4.34G/4.88G [00:06<00:00, 666MB/s] model-00003-of-00014.safetensors: 92%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 4.47G/4.88G [00:06<00:00, 635MB/s] model-00003-of-00014.safetensors: 94%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 4.61G/4.88G [00:06<00:00, 519MB/s] model-00003-of-00014.safetensors: 96%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 4.67G/4.88G [00:08<00:00, 217MB/s] model-00003-of-00014.safetensors: 97%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 4.74G/4.88G [00:08<00:00, 246MB/s] model-00003-of-00014.safetensors: 99%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 4.81G/4.88G [00:08<00:00, 249MB/s] model-00003-of-00014.safetensors: 100%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ| 4.88G/4.88G [00:08<00:00, 578MB/s] | |
| model-00004-of-00014.safetensors: 0%| | 0.00/4.88G [00:00<?, ?B/s] model-00004-of-00014.safetensors: 1%|ββββ | 47.7M/4.88G [00:02<04:49, 16.7MB/s] model-00004-of-00014.safetensors: 2%|βββββββββ | 115M/4.88G [00:03<01:43, 45.9MB/s] model-00004-of-00014.safetensors: 4%|ββββββββββββββ | 182M/4.88G [00:03<00:56, 83.1MB/s] model-00004-of-00014.safetensors: 5%|βββββββββββββββββββ | 249M/4.88G [00:03<00:38, 121MB/s] model-00004-of-00014.safetensors: 9%|ββββββββββββββββββββββββββββββββββ | 450M/4.88G [00:03<00:15, 285MB/s] model-00004-of-00014.safetensors: 16%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 785M/4.88G [00:03<00:07, 584MB/s] model-00004-of-00014.safetensors: 19%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 920M/4.88G [00:03<00:06, 605MB/s] model-00004-of-00014.safetensors: 23%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 1.12G/4.88G [00:04<00:04, 773MB/s] model-00004-of-00014.safetensors: 26%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 1.25G/4.88G [00:04<00:04, 853MB/s] model-00004-of-00014.safetensors: 33%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 1.59G/4.88G [00:04<00:02, 1.22GB/s] model-00004-of-00014.safetensors: 38%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 1.86G/4.88G [00:04<00:02, 1.47GB/s] model-00004-of-00014.safetensors: 42%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 2.06G/4.88G [00:04<00:01, 1.51GB/s] model-00004-of-00014.safetensors: 53%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 2.60G/4.88G [00:04<00:01, 2.19GB/s] model-00004-of-00014.safetensors: 60%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 2.93G/4.88G [00:04<00:00, 2.40GB/s] model-00004-of-00014.safetensors: 66%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 3.20G/4.88G [00:04<00:00, 2.00GB/s] model-00004-of-00014.safetensors: 71%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 3.47G/4.88G [00:05<00:00, 1.65GB/s] model-00004-of-00014.safetensors: 75%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 3.67G/4.88G [00:05<00:00, 1.61GB/s] model-00004-of-00014.safetensors: 79%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 3.87G/4.88G [00:05<00:00, 1.17GB/s] model-00004-of-00014.safetensors: 83%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 4.07G/4.88G [00:06<00:00, 808MB/s] model-00004-of-00014.safetensors: 86%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 4.21G/4.88G [00:06<00:00, 727MB/s] model-00004-of-00014.safetensors: 89%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 4.34G/4.88G [00:06<00:01, 500MB/s] model-00004-of-00014.safetensors: 93%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 4.54G/4.88G [00:07<00:00, 611MB/s] model-00004-of-00014.safetensors: 96%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 4.67G/4.88G [00:07<00:00, 579MB/s] model-00004-of-00014.safetensors: 99%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 4.81G/4.88G [00:07<00:00, 578MB/s] model-00004-of-00014.safetensors: 100%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ| 4.88G/4.88G [00:07<00:00, 632MB/s] | |
| model-00005-of-00014.safetensors: 0%| | 0.00/4.88G [00:00<?, ?B/s] model-00005-of-00014.safetensors: 1%|βββββ | 67.1M/4.88G [00:03<03:38, 22.0MB/s] model-00005-of-00014.safetensors: 7%|βββββββββββββββββββββββββ | 335M/4.88G [00:03<00:34, 132MB/s] model-00005-of-00014.safetensors: 12%|ββββββββββββββββββββββββββββββββββββββββββββ | 584M/4.88G [00:03<00:16, 264MB/s] model-00005-of-00014.safetensors: 16%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 785M/4.88G [00:03<00:10, 392MB/s] model-00005-of-00014.safetensors: 22%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 1.05G/4.88G [00:03<00:06, 580MB/s] model-00005-of-00014.safetensors: 30%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 1.46G/4.88G [00:03<00:03, 889MB/s] model-00005-of-00014.safetensors: 39%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 1.93G/4.88G [00:03<00:02, 1.36GB/s] model-00005-of-00014.safetensors: 46%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 2.26G/4.88G [00:04<00:01, 1.41GB/s] model-00005-of-00014.safetensors: 53%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 2.60G/4.88G [00:04<00:01, 1.67GB/s] model-00005-of-00014.safetensors: 60%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 2.93G/4.88G [00:04<00:01, 1.80GB/s] model-00005-of-00014.safetensors: 66%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 3.20G/4.88G [00:04<00:00, 1.96GB/s] model-00005-of-00014.safetensors: 71%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 3.47G/4.88G [00:04<00:00, 2.10GB/s] model-00005-of-00014.safetensors: 77%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 3.74G/4.88G [00:04<00:00, 1.76GB/s] model-00005-of-00014.safetensors: 82%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 4.00G/4.88G [00:05<00:00, 1.78GB/s] model-00005-of-00014.safetensors: 88%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 4.27G/4.88G [00:05<00:00, 1.79GB/s] model-00005-of-00014.safetensors: 92%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 4.47G/4.88G [00:05<00:00, 1.65GB/s] model-00005-of-00014.safetensors: 96%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 4.67G/4.88G [00:05<00:00, 1.52GB/s] model-00005-of-00014.safetensors: 100%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ| 4.88G/4.88G [00:05<00:00, 1.17GB/s] model-00005-of-00014.safetensors: 100%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ| 4.88G/4.88G [00:05<00:00, 843MB/s] | |
| model-00006-of-00014.safetensors: 0%| | 0.00/4.88G [00:00<?, ?B/s] model-00006-of-00014.safetensors: 1%|βββββ | 67.1M/4.88G [00:02<03:16, 24.5MB/s] model-00006-of-00014.safetensors: 6%|ββββββββββββββββββββ | 268M/4.88G [00:03<00:43, 107MB/s] model-00006-of-00014.safetensors: 8%|ββββββββββββββββββββββββββββββ | 402M/4.88G [00:03<00:26, 169MB/s] model-00006-of-00014.safetensors: 17%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 805M/4.88G [00:03<00:09, 428MB/s] model-00006-of-00014.safetensors: 24%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 1.19G/4.88G [00:03<00:05, 695MB/s] model-00006-of-00014.safetensors: 28%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 1.39G/4.88G [00:03<00:04, 757MB/s] model-00006-of-00014.safetensors: 42%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 2.06G/4.88G [00:04<00:02, 1.38GB/s] model-00006-of-00014.safetensors: 49%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 2.39G/4.88G [00:04<00:01, 1.57GB/s] model-00006-of-00014.safetensors: 55%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 2.66G/4.88G [00:04<00:01, 1.58GB/s] model-00006-of-00014.safetensors: 64%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 3.13G/4.88G [00:04<00:00, 1.93GB/s] model-00006-of-00014.safetensors: 70%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 3.40G/4.88G [00:04<00:00, 1.89GB/s] model-00006-of-00014.safetensors: 75%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 3.67G/4.88G [00:04<00:00, 1.80GB/s] model-00006-of-00014.safetensors: 79%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 3.87G/4.88G [00:05<00:00, 1.39GB/s] model-00006-of-00014.safetensors: 85%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 4.14G/4.88G [00:05<00:00, 1.61GB/s] model-00006-of-00014.safetensors: 89%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 4.34G/4.88G [00:05<00:00, 1.39GB/s] model-00006-of-00014.safetensors: 93%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 4.54G/4.88G [00:05<00:00, 1.33GB/s] model-00006-of-00014.safetensors: 97%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 4.74G/4.88G [00:06<00:00, 721MB/s] model-00006-of-00014.safetensors: 100%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ| 4.88G/4.88G [00:06<00:00, 658MB/s] model-00006-of-00014.safetensors: 100%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ| 4.88G/4.88G [00:06<00:00, 754MB/s] | |
| model-00007-of-00014.safetensors: 0%| | 0.00/4.88G [00:00<?, ?B/s] model-00007-of-00014.safetensors: 1%|βββββ | 67.0M/4.88G [00:02<03:10, 25.3MB/s] model-00007-of-00014.safetensors: 3%|ββββββββββ | 134M/4.88G [00:02<01:26, 55.1MB/s] model-00007-of-00014.safetensors: 10%|ββββββββββββββββββββββββββββββββββββ | 469M/4.88G [00:03<00:17, 257MB/s] model-00007-of-00014.safetensors: 14%|βββββββββββββββββββββββββββββββββββββββββββββββββββ | 671M/4.88G [00:03<00:10, 396MB/s] model-00007-of-00014.safetensors: 19%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 939M/4.88G [00:03<00:06, 615MB/s] model-00007-of-00014.safetensors: 23%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 1.14G/4.88G [00:03<00:04, 749MB/s] model-00007-of-00014.safetensors: 29%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 1.41G/4.88G [00:03<00:03, 1.02GB/s] model-00007-of-00014.safetensors: 36%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 1.74G/4.88G [00:03<00:02, 1.29GB/s] model-00007-of-00014.safetensors: 41%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 2.01G/4.88G [00:03<00:01, 1.48GB/s] model-00007-of-00014.safetensors: 47%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 2.28G/4.88G [00:03<00:01, 1.46GB/s] model-00007-of-00014.safetensors: 55%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 2.68G/4.88G [00:04<00:01, 1.94GB/s] model-00007-of-00014.safetensors: 61%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 2.95G/4.88G [00:04<00:01, 1.68GB/s] model-00007-of-00014.safetensors: 66%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 3.22G/4.88G [00:04<00:00, 1.81GB/s] model-00007-of-00014.safetensors: 73%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 3.55G/4.88G [00:04<00:00, 2.09GB/s] model-00007-of-00014.safetensors: 78%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 3.80G/4.88G [00:04<00:00, 1.31GB/s] model-00007-of-00014.safetensors: 86%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 4.21G/4.88G [00:05<00:00, 1.59GB/s] model-00007-of-00014.safetensors: 92%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 4.47G/4.88G [00:05<00:00, 1.56GB/s] model-00007-of-00014.safetensors: 96%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 4.67G/4.88G [00:05<00:00, 1.41GB/s] model-00007-of-00014.safetensors: 100%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ| 4.88G/4.88G [00:05<00:00, 880MB/s] | |
| model-00008-of-00014.safetensors: 0%| | 0.00/4.88G [00:00<?, ?B/s] model-00008-of-00014.safetensors: 1%|βββββ | 67.1M/4.88G [00:02<02:52, 28.0MB/s] model-00008-of-00014.safetensors: 4%|ββββββββββββββ | 182M/4.88G [00:02<00:52, 90.0MB/s] model-00008-of-00014.safetensors: 6%|ββββββββββββββββββββββββ | 316M/4.88G [00:02<00:25, 176MB/s] model-00008-of-00014.safetensors: 9%|ββββββββββββββββββββββββββββββββββ | 450M/4.88G [00:02<00:15, 281MB/s] model-00008-of-00014.safetensors: 12%|ββββββββββββββββββββββββββββββββββββββββββββ | 584M/4.88G [00:02<00:11, 359MB/s] model-00008-of-00014.safetensors: 16%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 785M/4.88G [00:03<00:07, 538MB/s] model-00008-of-00014.safetensors: 24%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 1.19G/4.88G [00:03<00:03, 994MB/s] model-00008-of-00014.safetensors: 30%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 1.46G/4.88G [00:03<00:02, 1.27GB/s] model-00008-of-00014.safetensors: 38%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 1.86G/4.88G [00:03<00:01, 1.78GB/s] model-00008-of-00014.safetensors: 44%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 2.13G/4.88G [00:03<00:01, 1.42GB/s] model-00008-of-00014.safetensors: 49%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 2.40G/4.88G [00:04<00:01, 1.30GB/s] model-00008-of-00014.safetensors: 53%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 2.60G/4.88G [00:04<00:01, 1.42GB/s] model-00008-of-00014.safetensors: 57%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 2.80G/4.88G [00:04<00:01, 1.46GB/s] model-00008-of-00014.safetensors: 67%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 3.27G/4.88G [00:04<00:00, 2.09GB/s] model-00008-of-00014.safetensors: 72%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 3.53G/4.88G [00:04<00:00, 2.12GB/s] model-00008-of-00014.safetensors: 78%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 3.80G/4.88G [00:04<00:00, 1.74GB/s] model-00008-of-00014.safetensors: 83%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 4.07G/4.88G [00:04<00:00, 1.90GB/s] model-00008-of-00014.safetensors: 89%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 4.34G/4.88G [00:05<00:00, 1.48GB/s] model-00008-of-00014.safetensors: 93%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 4.54G/4.88G [00:05<00:00, 1.35GB/s] model-00008-of-00014.safetensors: 97%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 4.74G/4.88G [00:05<00:00, 721MB/s] model-00008-of-00014.safetensors: 100%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ| 4.88G/4.88G [00:05<00:00, 815MB/s] | |
| model-00009-of-00014.safetensors: 0%| | 0.00/4.88G [00:00<?, ?B/s] model-00009-of-00014.safetensors: 1%|ββββ | 47.5M/4.88G [00:02<04:07, 19.5MB/s] model-00009-of-00014.safetensors: 2%|βββββββββ | 115M/4.88G [00:02<01:29, 53.1MB/s] model-00009-of-00014.safetensors: 5%|βββββββββββββββββββ | 249M/4.88G [00:02<00:32, 142MB/s] model-00009-of-00014.safetensors: 9%|ββββββββββββββββββββββββββββββββββ | 450M/4.88G [00:02<00:14, 300MB/s] model-00009-of-00014.safetensors: 15%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 718M/4.88G [00:02<00:07, 563MB/s] model-00009-of-00014.safetensors: 19%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 920M/4.88G [00:03<00:05, 687MB/s] model-00009-of-00014.safetensors: 26%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 1.25G/4.88G [00:03<00:03, 1.04GB/s] model-00009-of-00014.safetensors: 33%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 1.59G/4.88G [00:03<00:02, 1.42GB/s] model-00009-of-00014.safetensors: 39%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 1.93G/4.88G [00:03<00:01, 1.77GB/s] model-00009-of-00014.safetensors: 45%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 2.19G/4.88G [00:03<00:01, 1.52GB/s] model-00009-of-00014.safetensors: 53%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 2.60G/4.88G [00:03<00:01, 1.74GB/s] model-00009-of-00014.safetensors: 59%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 2.86G/4.88G [00:04<00:01, 1.25GB/s] model-00009-of-00014.safetensors: 63%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 3.07G/4.88G [00:04<00:01, 1.09GB/s] model-00009-of-00014.safetensors: 67%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 3.27G/4.88G [00:04<00:01, 1.07GB/s] model-00009-of-00014.safetensors: 70%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 3.40G/4.88G [00:05<00:01, 907MB/s] model-00009-of-00014.safetensors: 74%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 3.60G/4.88G [00:05<00:01, 899MB/s] model-00009-of-00014.safetensors: 77%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 3.74G/4.88G [00:05<00:01, 872MB/s] model-00009-of-00014.safetensors: 79%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 3.87G/4.88G [00:05<00:01, 676MB/s] model-00009-of-00014.safetensors: 82%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 4.00G/4.88G [00:06<00:01, 585MB/s] model-00009-of-00014.safetensors: 86%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 4.21G/4.88G [00:06<00:00, 764MB/s] model-00009-of-00014.safetensors: 89%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 4.34G/4.88G [00:07<00:02, 248MB/s] model-00009-of-00014.safetensors: 92%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 4.47G/4.88G [00:08<00:01, 289MB/s] model-00009-of-00014.safetensors: 95%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 4.61G/4.88G [00:08<00:00, 359MB/s] model-00009-of-00014.safetensors: 97%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 4.74G/4.88G [00:08<00:00, 315MB/s] model-00009-of-00014.safetensors: 99%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 4.81G/4.88G [00:09<00:00, 304MB/s] model-00009-of-00014.safetensors: 100%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ| 4.88G/4.88G [00:09<00:00, 332MB/s] model-00009-of-00014.safetensors: 100%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ| 4.88G/4.88G [00:09<00:00, 533MB/s] | |
| model-00010-of-00014.safetensors: 0%| | 0.00/4.88G [00:00<?, ?B/s] model-00010-of-00014.safetensors: 1%|βββββ | 67.1M/4.88G [00:02<03:03, 26.1MB/s] model-00010-of-00014.safetensors: 6%|ββββββββββββββββββββ | 268M/4.88G [00:02<00:35, 129MB/s] model-00010-of-00014.safetensors: 8%|βββββββββββββββββββββββββββββββ | 402M/4.88G [00:02<00:23, 189MB/s] model-00010-of-00014.safetensors: 11%|βββββββββββββββββββββββββββββββββββββββββ | 537M/4.88G [00:03<00:16, 264MB/s] model-00010-of-00014.safetensors: 17%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 805M/4.88G [00:03<00:08, 491MB/s] model-00010-of-00014.safetensors: 23%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 1.14G/4.88G [00:03<00:04, 775MB/s] model-00010-of-00014.safetensors: 28%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 1.34G/4.88G [00:03<00:03, 903MB/s] model-00010-of-00014.safetensors: 32%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 1.54G/4.88G [00:03<00:03, 1.07GB/s] model-00010-of-00014.safetensors: 41%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 2.01G/4.88G [00:03<00:01, 1.63GB/s] model-00010-of-00014.safetensors: 52%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 2.55G/4.88G [00:03<00:01, 2.19GB/s] model-00010-of-00014.safetensors: 59%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 2.88G/4.88G [00:04<00:00, 2.06GB/s] model-00010-of-00014.safetensors: 65%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 3.15G/4.88G [00:04<00:01, 1.59GB/s] model-00010-of-00014.safetensors: 69%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 3.35G/4.88G [00:04<00:01, 1.32GB/s] model-00010-of-00014.safetensors: 74%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 3.62G/4.88G [00:04<00:00, 1.43GB/s] model-00010-of-00014.safetensors: 78%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 3.82G/4.88G [00:05<00:00, 1.09GB/s] model-00010-of-00014.safetensors: 83%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 4.02G/4.88G [00:05<00:00, 902MB/s] model-00010-of-00014.safetensors: 85%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 4.16G/4.88G [00:05<00:01, 653MB/s] model-00010-of-00014.safetensors: 88%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 4.27G/4.88G [00:06<00:01, 490MB/s] model-00010-of-00014.safetensors: 90%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 4.41G/4.88G [00:06<00:00, 551MB/s] model-00010-of-00014.safetensors: 93%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 4.54G/4.88G [00:06<00:00, 641MB/s] model-00010-of-00014.safetensors: 96%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 4.67G/4.88G [00:07<00:00, 505MB/s] model-00010-of-00014.safetensors: 99%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 4.81G/4.88G [00:07<00:00, 417MB/s] model-00010-of-00014.safetensors: 100%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ| 4.88G/4.88G [00:07<00:00, 432MB/s] model-00010-of-00014.safetensors: 100%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ| 4.88G/4.88G [00:07<00:00, 634MB/s] | |
| model-00011-of-00014.safetensors: 0%| | 0.00/4.88G [00:00<?, ?B/s] model-00011-of-00014.safetensors: 1%|ββββ | 48.1M/4.88G [00:02<03:52, 20.8MB/s] model-00011-of-00014.safetensors: 2%|βββββββββ | 115M/4.88G [00:02<01:25, 55.8MB/s] model-00011-of-00014.safetensors: 4%|ββββββββββββββ | 182M/4.88G [00:02<00:59, 78.8MB/s] model-00011-of-00014.safetensors: 5%|βββββββββββββββββββ | 249M/4.88G [00:03<00:40, 114MB/s] model-00011-of-00014.safetensors: 11%|βββββββββββββββββββββββββββββββββββββββ | 517M/4.88G [00:03<00:12, 346MB/s] model-00011-of-00014.safetensors: 16%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 786M/4.88G [00:03<00:07, 584MB/s] model-00011-of-00014.safetensors: 26%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 1.26G/4.88G [00:03<00:03, 971MB/s] model-00011-of-00014.safetensors: 35%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 1.72G/4.88G [00:03<00:02, 1.48GB/s] model-00011-of-00014.safetensors: 41%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 1.99G/4.88G [00:03<00:01, 1.52GB/s] model-00011-of-00014.safetensors: 48%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 2.33G/4.88G [00:04<00:01, 1.80GB/s] model-00011-of-00014.safetensors: 55%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 2.66G/4.88G [00:04<00:01, 2.05GB/s] model-00011-of-00014.safetensors: 64%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 3.13G/4.88G [00:04<00:00, 2.24GB/s] model-00011-of-00014.safetensors: 70%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 3.40G/4.88G [00:04<00:00, 2.07GB/s] model-00011-of-00014.safetensors: 75%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 3.67G/4.88G [00:04<00:00, 2.19GB/s] model-00011-of-00014.safetensors: 81%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 3.94G/4.88G [00:05<00:00, 1.33GB/s] model-00011-of-00014.safetensors: 85%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 4.14G/4.88G [00:05<00:00, 1.09GB/s] model-00011-of-00014.safetensors: 89%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 4.34G/4.88G [00:05<00:00, 1.07GB/s] model-00011-of-00014.safetensors: 93%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 4.54G/4.88G [00:05<00:00, 920MB/s] model-00011-of-00014.safetensors: 96%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 4.67G/4.88G [00:06<00:00, 734MB/s] model-00011-of-00014.safetensors: 99%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 4.81G/4.88G [00:06<00:00, 503MB/s] model-00011-of-00014.safetensors: 100%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ| 4.88G/4.88G [00:06<00:00, 715MB/s] | |
| model-00012-of-00014.safetensors: 0%| | 0.00/4.88G [00:00<?, ?B/s] model-00012-of-00014.safetensors: 1%|βββββ | 67.1M/4.88G [00:02<03:14, 24.7MB/s] model-00012-of-00014.safetensors: 4%|βββββββββββββββ | 201M/4.88G [00:02<00:53, 87.1MB/s] model-00012-of-00014.safetensors: 6%|ββββββββββββββββββββ | 268M/4.88G [00:03<00:37, 123MB/s] model-00012-of-00014.safetensors: 8%|ββββββββββββββββββββββββββββββ | 402M/4.88G [00:03<00:21, 209MB/s] model-00012-of-00014.safetensors: 18%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 872M/4.88G [00:03<00:06, 652MB/s] model-00012-of-00014.safetensors: 22%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 1.07G/4.88G [00:03<00:04, 807MB/s] model-00012-of-00014.safetensors: 28%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 1.34G/4.88G [00:03<00:03, 1.02GB/s] model-00012-of-00014.safetensors: 32%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 1.54G/4.88G [00:03<00:02, 1.17GB/s] model-00012-of-00014.safetensors: 43%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 2.08G/4.88G [00:03<00:01, 1.88GB/s] model-00012-of-00014.safetensors: 48%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 2.35G/4.88G [00:03<00:01, 1.90GB/s] model-00012-of-00014.safetensors: 54%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 2.62G/4.88G [00:04<00:01, 1.51GB/s] model-00012-of-00014.safetensors: 58%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 2.82G/4.88G [00:04<00:01, 1.47GB/s] model-00012-of-00014.safetensors: 63%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 3.08G/4.88G [00:04<00:01, 1.47GB/s] model-00012-of-00014.safetensors: 67%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 3.29G/4.88G [00:04<00:01, 1.46GB/s] model-00012-of-00014.safetensors: 72%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 3.49G/4.88G [00:04<00:00, 1.45GB/s] model-00012-of-00014.safetensors: 77%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 3.76G/4.88G [00:04<00:00, 1.62GB/s] model-00012-of-00014.safetensors: 81%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 3.96G/4.88G [00:05<00:00, 1.50GB/s] model-00012-of-00014.safetensors: 88%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 4.29G/4.88G [00:05<00:00, 1.77GB/s] model-00012-of-00014.safetensors: 92%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 4.49G/4.88G [00:05<00:00, 1.69GB/s] model-00012-of-00014.safetensors: 96%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 4.67G/4.88G [00:05<00:00, 1.69GB/s] model-00012-of-00014.safetensors: 100%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ| 4.88G/4.88G [00:05<00:00, 1.30GB/s] model-00012-of-00014.safetensors: 100%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ| 4.88G/4.88G [00:05<00:00, 850MB/s] | |
| model-00013-of-00014.safetensors: 0%| | 0.00/4.75G [00:00<?, ?B/s] model-00013-of-00014.safetensors: 1%|ββββββ | 67.1M/4.75G [00:02<02:49, 27.7MB/s] model-00013-of-00014.safetensors: 5%|ββββββββββββββββββββ | 258M/4.75G [00:02<00:34, 130MB/s] model-00013-of-00014.safetensors: 8%|ββββββββββββββββββββββββββββββ | 392M/4.75G [00:02<00:21, 207MB/s] model-00013-of-00014.safetensors: 11%|βββββββββββββββββββββββββββββββββββββββββ | 526M/4.75G [00:02<00:14, 284MB/s] model-00013-of-00014.safetensors: 14%|βββββββββββββββββββββββββββββββββββββββββββββββββββ | 660M/4.75G [00:03<00:10, 389MB/s] model-00013-of-00014.safetensors: 17%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 794M/4.75G [00:03<00:08, 481MB/s] model-00013-of-00014.safetensors: 24%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 1.13G/4.75G [00:03<00:04, 845MB/s] model-00013-of-00014.safetensors: 32%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 1.53G/4.75G [00:03<00:02, 1.16GB/s] model-00013-of-00014.safetensors: 36%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 1.73G/4.75G [00:03<00:02, 1.16GB/s] model-00013-of-00014.safetensors: 41%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 1.93G/4.75G [00:03<00:02, 1.27GB/s] model-00013-of-00014.safetensors: 46%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 2.20G/4.75G [00:03<00:01, 1.45GB/s] model-00013-of-00014.safetensors: 51%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 2.40G/4.75G [00:04<00:01, 1.35GB/s] model-00013-of-00014.safetensors: 55%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 2.60G/4.75G [00:04<00:01, 1.29GB/s] model-00013-of-00014.safetensors: 60%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 2.87G/4.75G [00:04<00:01, 1.48GB/s] model-00013-of-00014.safetensors: 68%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 3.21G/4.75G [00:04<00:01, 1.48GB/s] model-00013-of-00014.safetensors: 75%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 3.54G/4.75G [00:04<00:00, 1.64GB/s] model-00013-of-00014.safetensors: 79%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 3.74G/4.75G [00:04<00:00, 1.70GB/s] model-00013-of-00014.safetensors: 83%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 3.95G/4.75G [00:05<00:00, 1.72GB/s] model-00013-of-00014.safetensors: 92%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 4.35G/4.75G [00:05<00:00, 1.86GB/s] model-00013-of-00014.safetensors: 96%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 4.55G/4.75G [00:05<00:00, 1.75GB/s] model-00013-of-00014.safetensors: 100%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ| 4.75G/4.75G [00:05<00:00, 1.35GB/s] model-00013-of-00014.safetensors: 100%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ| 4.75G/4.75G [00:05<00:00, 842MB/s] | |
| model-00014-of-00014.safetensors: 0%| | 0.00/1.03G [00:00<?, ?B/s] model-00014-of-00014.safetensors: 2%|ββββββββ | 20.8M/1.03G [00:01<00:50, 20.1MB/s] model-00014-of-00014.safetensors: 9%|βββββββββββββββββββββββββββββββ | 87.9M/1.03G [00:01<00:15, 61.1MB/s] model-00014-of-00014.safetensors: 54%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 557M/1.03G [00:01<00:00, 489MB/s] model-00014-of-00014.safetensors: 93%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 960M/1.03G [00:02<00:00, 790MB/s] model-00014-of-00014.safetensors: 100%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ| 1.03G/1.03G [00:02<00:00, 507MB/s] | |
| Loading checkpoint shards: 0%| | 0/14 [00:00<?, ?it/s] Loading checkpoint shards: 7%|βββββββββββββββββββββββββββ | 1/14 [00:16<03:36, 16.68s/it] Loading checkpoint shards: 14%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 2/14 [00:31<03:04, 15.35s/it] Loading checkpoint shards: 21%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 3/14 [00:45<02:46, 15.10s/it] Loading checkpoint shards: 29%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 4/14 [01:01<02:34, 15.43s/it] Loading checkpoint shards: 36%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 5/14 [01:19<02:25, 16.12s/it] Loading checkpoint shards: 43%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 6/14 [01:34<02:07, 15.89s/it] Loading checkpoint shards: 50%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 7/14 [01:48<01:47, 15.36s/it] Loading checkpoint shards: 57%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 8/14 [02:03<01:30, 15.07s/it] Loading checkpoint shards: 64%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 9/14 [02:18<01:15, 15.00s/it] Loading checkpoint shards: 71%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 10/14 [02:29<00:55, 13.96s/it] Loading checkpoint shards: 79%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 11/14 [02:39<00:38, 12.71s/it] Loading checkpoint shards: 86%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 12/14 [02:49<00:23, 11.89s/it] Loading checkpoint shards: 93%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 13/14 [02:59<00:11, 11.24s/it] Loading checkpoint shards: 100%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ| 14/14 [02:59<00:00, 7.88s/it] Loading checkpoint shards: 100%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ| 14/14 [02:59<00:00, 12.83s/it] | |
| generation_config.json: 0%| | 0.00/207 [00:00<?, ?B/s] generation_config.json: 100%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ| 207/207 [00:00<00:00, 1.01MB/s] | |
| [2026-01-28 18:47:49,482] [INFO] [axolotl.loaders.model._prepare_model_for_quantization:853] [PID:11475] converting PEFT model w/ prepare_model_for_kbit_training | |
| [2026-01-28 18:47:49,488] [INFO] [axolotl.loaders.model._configure_embedding_dtypes:347] [PID:11475] Converting modules to torch.bfloat16 | |
| [2026-01-28 18:47:49,497] [DEBUG] [axolotl.loaders.model.log_gpu_memory_usage:127] [PID:11475] Memory usage after model load 34.115GB (+34.115GB allocated, +35.863GB reserved) | |
| [2026-01-28 18:47:49,498] [INFO] [axolotl.loaders.adapter.load_lora:81] [PID:11475] found linear modules: ['down_proj', 'gate_proj', 'k_proj', 'o_proj', 'q_proj', 'up_proj', 'v_proj'] | |
| trainable params: 536,870,912 || all params: 32,770,393,088 || trainable%: 1.6383 | |
| [2026-01-28 18:47:55,019] [DEBUG] [axolotl.loaders.model.log_gpu_memory_usage:127] [PID:11475] after adapters 33.207GB (+33.207GB allocated, +35.893GB reserved) | |
| [2026-01-28 18:48:02,317] [INFO] [axolotl.train.save_initial_configs:413] [PID:11475] Pre-saving adapter config to ./Olmo-Guten-SFT... | |
| [2026-01-28 18:48:02,317] [INFO] [axolotl.train.save_initial_configs:417] [PID:11475] Pre-saving tokenizer to ./Olmo-Guten-SFT... | |
| [2026-01-28 18:48:02,481] [INFO] [axolotl.train.save_initial_configs:422] [PID:11475] Pre-saving model config to ./Olmo-Guten-SFT... | |
| [2026-01-28 18:48:02,483] [INFO] [axolotl.train.execute_training:212] [PID:11475] Starting trainer... | |
| [2026-01-28 18:48:04,818] [DEBUG] [axolotl.utils.samplers.multipack.__len__:462] [PID:11475] generate_batches time: 0.8639252185821533 | |
| [2026-01-28 18:48:05,634] [DEBUG] [axolotl.utils.samplers.multipack.__len__:462] [PID:11475] generate_batches time: 0.8152194023132324 | |
| [2026-01-28 18:48:06,563] [DEBUG] [axolotl.utils.samplers.multipack.__len__:462] [PID:11475] generate_batches time: 0.9285147190093994 | |
| [2026-01-28 18:48:07,425] [DEBUG] [axolotl.utils.samplers.multipack.__len__:462] [PID:11475] generate_batches time: 0.8614435195922852 | |
| [2026-01-28 18:48:07,425] [INFO] [axolotl.utils.samplers.multipack.calc_min_len:438] [PID:11475] gather_len_batches: [87] | |
| 0%| | 0/42 [00:00<?, ?it/s] 2%|ββββββββββ | 1/42 [01:22<56:11, 82.24s/it] {'loss': 1.1177, 'grad_norm': 0.3425081670284271, 'learning_rate': 0.0, 'ppl': 3.05781, 'memory/max_active (GiB)': 48.41, 'memory/max_allocated (GiB)': 48.41, 'memory/device_reserved (GiB)': 49.96, 'tokens/train_per_sec_per_gpu': 138.06007385253906, 'tokens/total': 49152, 'tokens/trainable': 43359, 'epoch': 0.05} | |
| 2%|ββββββββββ | 1/42 [01:22<56:11, 82.24s/it] 5%|ββββββββββββββββββββ | 2/42 [02:36<51:42, 77.56s/it] {'loss': 0.9912, 'grad_norm': 0.41965386271476746, 'learning_rate': 1.25e-05, 'ppl': 2.69447, 'memory/max_active (GiB)': 48.44, 'memory/max_allocated (GiB)': 48.44, 'memory/device_reserved (GiB)': 49.99, 'tokens/train_per_sec_per_gpu': 143.8074493408203, 'tokens/total': 98304, 'tokens/trainable': 86588, 'epoch': 0.09} | |
| 5%|ββββββββββββββββββββ | 2/42 [02:36<51:42, 77.56s/it] 7%|βββββββββββββββββββββββββββββ | 3/42 [03:50<49:16, 75.82s/it] {'loss': 0.8891, 'grad_norm': 0.24642112851142883, 'learning_rate': 2.5e-05, 'ppl': 2.43294, 'memory/max_active (GiB)': 48.45, 'memory/max_allocated (GiB)': 48.45, 'memory/device_reserved (GiB)': 49.99, 'tokens/train_per_sec_per_gpu': 149.02528381347656, 'tokens/total': 147456, 'tokens/trainable': 129825, 'epoch': 0.14} | |
| 7%|βββββββββββββββββββββββββββββ | 3/42 [03:50<49:16, 75.82s/it] 10%|βββββββββββββββββββββββββββββββββββββββ | 4/42 [05:04<47:42, 75.33s/it] {'loss': 0.8658, 'grad_norm': 0.15481024980545044, 'learning_rate': 2.5e-05, 'ppl': 2.37691, 'memory/max_active (GiB)': 48.47, 'memory/max_allocated (GiB)': 48.47, 'memory/device_reserved (GiB)': 49.99, 'tokens/train_per_sec_per_gpu': 139.64283752441406, 'tokens/total': 196608, 'tokens/trainable': 172706, 'epoch': 0.18} | |
| 10%|βββββββββββββββββββββββββββββββββββββββ | 4/42 [05:04<47:42, 75.33s/it] 12%|ββββββββββββββββββββββββββββββββββββββββββββββββ | 5/42 [06:19<46:13, 74.96s/it] {'loss': 0.656, 'grad_norm': 0.1235349103808403, 'learning_rate': 2.5e-05, 'ppl': 1.92707, 'memory/max_active (GiB)': 48.46, 'memory/max_allocated (GiB)': 48.46, 'memory/device_reserved (GiB)': 49.99, 'tokens/train_per_sec_per_gpu': 146.05972290039062, 'tokens/total': 245760, 'tokens/trainable': 215250, 'epoch': 0.23} | |
| 12%|ββββββββββββββββββββββββββββββββββββββββββββββββ | 5/42 [06:19<46:13, 74.96s/it] 14%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 6/42 [07:33<44:48, 74.69s/it] {'loss': 0.8173, 'grad_norm': 0.11684071272611618, 'learning_rate': 2.5e-05, 'ppl': 2.26438, 'memory/max_active (GiB)': 48.47, 'memory/max_allocated (GiB)': 48.47, 'memory/device_reserved (GiB)': 49.99, 'tokens/train_per_sec_per_gpu': 138.31039428710938, 'tokens/total': 294912, 'tokens/trainable': 257666, 'epoch': 0.28} | |
| 14%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 6/42 [07:33<44:48, 74.69s/it] 17%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 7/42 [08:46<43:15, 74.15s/it] {'loss': 0.6462, 'grad_norm': 0.116986483335495, 'learning_rate': 2.5e-05, 'ppl': 1.90828, 'memory/max_active (GiB)': 48.46, 'memory/max_allocated (GiB)': 48.46, 'memory/device_reserved (GiB)': 49.99, 'tokens/train_per_sec_per_gpu': 141.69631958007812, 'tokens/total': 344064, 'tokens/trainable': 300306, 'epoch': 0.32} | |
| 17%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 7/42 [08:46<43:15, 74.15s/it] 19%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 8/42 [10:01<42:07, 74.33s/it] {'loss': 0.6286, 'grad_norm': 0.14083151519298553, 'learning_rate': 2.5e-05, 'ppl': 1.87498, 'memory/max_active (GiB)': 48.47, 'memory/max_allocated (GiB)': 48.47, 'memory/device_reserved (GiB)': 49.99, 'tokens/train_per_sec_per_gpu': 147.02879333496094, 'tokens/total': 393216, 'tokens/trainable': 343861, 'epoch': 0.37} | |
| 19%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 8/42 [10:01<42:07, 74.33s/it] 21%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 9/42 [11:15<40:53, 74.36s/it] {'loss': 0.7567, 'grad_norm': 0.1619769185781479, 'learning_rate': 2.5e-05, 'ppl': 2.13123, 'memory/max_active (GiB)': 48.47, 'memory/max_allocated (GiB)': 48.47, 'memory/device_reserved (GiB)': 49.99, 'tokens/train_per_sec_per_gpu': 142.36502075195312, 'tokens/total': 442368, 'tokens/trainable': 387627, 'epoch': 0.41} | |
| 21%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 9/42 [11:15<40:53, 74.36s/it] 24%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 10/42 [12:29<39:33, 74.16s/it] {'loss': 0.7688, 'grad_norm': 0.11327368766069412, 'learning_rate': 2.5e-05, 'ppl': 2.15718, 'memory/max_active (GiB)': 48.46, 'memory/max_allocated (GiB)': 48.46, 'memory/device_reserved (GiB)': 49.99, 'tokens/train_per_sec_per_gpu': 151.75294494628906, 'tokens/total': 491520, 'tokens/trainable': 431362, 'epoch': 0.46} | |
| 24%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 10/42 [12:29<39:33, 74.16s/it] 26%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 11/42 [13:42<38:12, 73.95s/it] {'loss': 0.7125, 'grad_norm': 0.13537345826625824, 'learning_rate': 2.5e-05, 'ppl': 2.03908, 'memory/max_active (GiB)': 48.47, 'memory/max_allocated (GiB)': 48.47, 'memory/device_reserved (GiB)': 49.99, 'tokens/train_per_sec_per_gpu': 134.7452850341797, 'tokens/total': 540672, 'tokens/trainable': 474019, 'epoch': 0.51} | |
| 26%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 11/42 [13:42<38:12, 73.95s/it] 29%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 12/42 [14:56<36:56, 73.87s/it] {'loss': 0.6457, 'grad_norm': 0.10332974046468735, 'learning_rate': 2.5e-05, 'ppl': 1.90732, 'memory/max_active (GiB)': 48.47, 'memory/max_allocated (GiB)': 48.47, 'memory/device_reserved (GiB)': 49.99, 'tokens/train_per_sec_per_gpu': 146.48171997070312, 'tokens/total': 589824, 'tokens/trainable': 518329, 'epoch': 0.55} | |
| 29%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 12/42 [14:56<36:56, 73.87s/it] 31%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 13/42 [16:10<35:47, 74.04s/it] {'loss': 0.5196, 'grad_norm': 0.09402354061603546, 'learning_rate': 2.5e-05, 'ppl': 1.68135, 'memory/max_active (GiB)': 48.47, 'memory/max_allocated (GiB)': 48.47, 'memory/device_reserved (GiB)': 49.99, 'tokens/train_per_sec_per_gpu': 146.5075225830078, 'tokens/total': 638976, 'tokens/trainable': 561802, 'epoch': 0.6} | |
| 31%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 13/42 [16:10<35:47, 74.04s/it] 33%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 14/42 [17:25<34:34, 74.09s/it] {'loss': 0.5758, 'grad_norm': 0.11008915305137634, 'learning_rate': 2.5e-05, 'ppl': 1.77855, 'memory/max_active (GiB)': 48.46, 'memory/max_allocated (GiB)': 48.46, 'memory/device_reserved (GiB)': 49.99, 'tokens/train_per_sec_per_gpu': 142.18382263183594, 'tokens/total': 688128, 'tokens/trainable': 604656, 'epoch': 0.64} | |
| 33%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 14/42 [17:25<34:34, 74.09s/it] 36%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 15/42 [18:38<33:18, 74.00s/it] {'loss': 0.6931, 'grad_norm': 0.1327342540025711, 'learning_rate': 2.5e-05, 'ppl': 1.99991, 'memory/max_active (GiB)': 48.47, 'memory/max_allocated (GiB)': 48.47, 'memory/device_reserved (GiB)': 49.99, 'tokens/train_per_sec_per_gpu': 147.63629150390625, 'tokens/total': 737280, 'tokens/trainable': 647373, 'epoch': 0.69} | |
| 36%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 15/42 [18:38<33:18, 74.00s/it] 38%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 16/42 [19:52<31:58, 73.80s/it] {'loss': 0.6581, 'grad_norm': 0.10193049162626266, 'learning_rate': 2.5e-05, 'ppl': 1.93112, 'memory/max_active (GiB)': 48.45, 'memory/max_allocated (GiB)': 48.45, 'memory/device_reserved (GiB)': 49.99, 'tokens/train_per_sec_per_gpu': 149.9634552001953, 'tokens/total': 786432, 'tokens/trainable': 689872, 'epoch': 0.74} | |
| 38%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 16/42 [19:52<31:58, 73.80s/it] 40%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 17/42 [21:05<30:42, 73.69s/it] {'loss': 0.575, 'grad_norm': 0.10153383016586304, 'learning_rate': 2.5e-05, 'ppl': 1.77713, 'memory/max_active (GiB)': 48.46, 'memory/max_allocated (GiB)': 48.46, 'memory/device_reserved (GiB)': 49.99, 'tokens/train_per_sec_per_gpu': 142.02674865722656, 'tokens/total': 835584, 'tokens/trainable': 732276, 'epoch': 0.78} | |
| 40%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 17/42 [21:05<30:42, 73.69s/it] 43%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 18/42 [22:19<29:31, 73.83s/it] {'loss': 0.674, 'grad_norm': 0.0868620052933693, 'learning_rate': 2.5e-05, 'ppl': 1.96207, 'memory/max_active (GiB)': 48.47, 'memory/max_allocated (GiB)': 48.47, 'memory/device_reserved (GiB)': 49.99, 'tokens/train_per_sec_per_gpu': 144.50193786621094, 'tokens/total': 884736, 'tokens/trainable': 776763, 'epoch': 0.83} | |
| 43%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 18/42 [22:19<29:31, 73.83s/it] 45%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 19/42 [23:33<28:15, 73.70s/it] {'loss': 0.5863, 'grad_norm': 0.09895136207342148, 'learning_rate': 2.5e-05, 'ppl': 1.79733, 'memory/max_active (GiB)': 48.47, 'memory/max_allocated (GiB)': 48.47, 'memory/device_reserved (GiB)': 49.99, 'tokens/train_per_sec_per_gpu': 147.54249572753906, 'tokens/total': 933888, 'tokens/trainable': 819340, 'epoch': 0.87} | |
| 45%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 19/42 [23:33<28:15, 73.70s/it] 48%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 20/42 [24:46<26:57, 73.54s/it] {'loss': 0.6497, 'grad_norm': 0.10956086218357086, 'learning_rate': 2.5e-05, 'ppl': 1.91497, 'memory/max_active (GiB)': 48.47, 'memory/max_allocated (GiB)': 48.47, 'memory/device_reserved (GiB)': 49.99, 'tokens/train_per_sec_per_gpu': 136.78346252441406, 'tokens/total': 983040, 'tokens/trainable': 860778, 'epoch': 0.92} | |
| 48%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 20/42 [24:46<26:57, 73.54s/it] 50%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 21/42 [26:04<26:13, 74.91s/it] {'loss': 0.5584, 'grad_norm': 0.09024012088775635, 'learning_rate': 2.5e-05, 'ppl': 1.74787, 'memory/max_active (GiB)': 48.46, 'memory/max_allocated (GiB)': 48.46, 'memory/device_reserved (GiB)': 49.99, 'tokens/train_per_sec_per_gpu': 134.848388671875, 'tokens/total': 1032192, 'tokens/trainable': 903342, 'epoch': 0.97} | |
| 50%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 21/42 [26:04<26:13, 74.91s/it] 52%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 22/42 [27:00<23:07, 69.36s/it] {'loss': 0.6129, 'grad_norm': 0.10904594510793686, 'learning_rate': 2.5e-05, 'ppl': 1.84578, 'memory/max_active (GiB)': 48.44, 'memory/max_allocated (GiB)': 48.44, 'memory/device_reserved (GiB)': 49.99, 'tokens/train_per_sec_per_gpu': 161.04420471191406, 'tokens/total': 1069056, 'tokens/trainable': 933006, 'epoch': 1.0} | |
| 52%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 22/42 [27:00<23:07, 69.36s/it][2026-01-28 19:15:08,433] [INFO] [axolotl.core.trainers.base._save:721] [PID:11475] Saving model checkpoint to ./Olmo-Guten-SFT/checkpoint-22 | |
| 55%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 23/42 [29:00<26:42, 84.36s/it] {'loss': 0.529, 'grad_norm': 0.09184744954109192, 'learning_rate': 2.5e-05, 'ppl': 1.69723, 'memory/max_active (GiB)': 48.47, 'memory/max_allocated (GiB)': 48.47, 'memory/device_reserved (GiB)': 49.99, 'tokens/train_per_sec_per_gpu': 150.27581787109375, 'tokens/total': 1118208, 'tokens/trainable': 976471, 'epoch': 1.05} | |
| 55%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 23/42 [29:00<26:42, 84.36s/it] 57%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 24/42 [30:13<24:20, 81.16s/it] {'loss': 0.4938, 'grad_norm': 0.08301545679569244, 'learning_rate': 2.5e-05, 'ppl': 1.63853, 'memory/max_active (GiB)': 48.48, 'memory/max_allocated (GiB)': 48.48, 'memory/device_reserved (GiB)': 49.99, 'tokens/train_per_sec_per_gpu': 152.13626098632812, 'tokens/total': 1167360, 'tokens/trainable': 1020757, 'epoch': 1.09} | |
| 57%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 24/42 [30:13<24:20, 81.16s/it] 60%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 25/42 [31:27<22:20, 78.83s/it] {'loss': 0.3194, 'grad_norm': 0.07072962075471878, 'learning_rate': 2.5e-05, 'ppl': 1.3763, 'memory/max_active (GiB)': 48.46, 'memory/max_allocated (GiB)': 48.46, 'memory/device_reserved (GiB)': 49.99, 'tokens/train_per_sec_per_gpu': 152.54693603515625, 'tokens/total': 1216512, 'tokens/trainable': 1063056, 'epoch': 1.14} | |
| 60%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 25/42 [31:27<22:20, 78.83s/it] 62%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 26/42 [32:40<20:35, 77.23s/it] {'loss': 0.4012, 'grad_norm': 0.08739683777093887, 'learning_rate': 2.5e-05, 'ppl': 1.49362, 'memory/max_active (GiB)': 48.46, 'memory/max_allocated (GiB)': 48.46, 'memory/device_reserved (GiB)': 49.99, 'tokens/train_per_sec_per_gpu': 151.05093383789062, 'tokens/total': 1265664, 'tokens/trainable': 1106374, 'epoch': 1.18} | |
| 62%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 26/42 [32:40<20:35, 77.23s/it] 64%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 27/42 [33:53<18:59, 75.95s/it] {'loss': 0.4573, 'grad_norm': 0.08420316874980927, 'learning_rate': 2.5e-05, 'ppl': 1.5798, 'memory/max_active (GiB)': 48.47, 'memory/max_allocated (GiB)': 48.47, 'memory/device_reserved (GiB)': 49.99, 'tokens/train_per_sec_per_gpu': 146.5579376220703, 'tokens/total': 1314816, 'tokens/trainable': 1148942, 'epoch': 1.23} | |
| 64%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 27/42 [33:53<18:59, 75.95s/it] 67%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 28/42 [35:06<17:31, 75.13s/it] {'loss': 0.3066, 'grad_norm': 0.0686136856675148, 'learning_rate': 2.5e-05, 'ppl': 1.3588, 'memory/max_active (GiB)': 48.45, 'memory/max_allocated (GiB)': 48.45, 'memory/device_reserved (GiB)': 49.99, 'tokens/train_per_sec_per_gpu': 139.3871612548828, 'tokens/total': 1363968, 'tokens/trainable': 1191750, 'epoch': 1.28} | |
| 67%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 28/42 [35:06<17:31, 75.13s/it] 69%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 29/42 [36:19<16:07, 74.41s/it] {'loss': 0.3314, 'grad_norm': 0.0641675665974617, 'learning_rate': 2.5e-05, 'ppl': 1.39292, 'memory/max_active (GiB)': 48.47, 'memory/max_allocated (GiB)': 48.47, 'memory/device_reserved (GiB)': 49.99, 'tokens/train_per_sec_per_gpu': 150.2340545654297, 'tokens/total': 1413120, 'tokens/trainable': 1234629, 'epoch': 1.32} | |
| 69%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 29/42 [36:19<16:07, 74.41s/it] 71%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 30/42 [37:32<14:48, 74.06s/it] {'loss': 0.516, 'grad_norm': 0.10830646753311157, 'learning_rate': 2.5e-05, 'ppl': 1.67531, 'memory/max_active (GiB)': 48.47, 'memory/max_allocated (GiB)': 48.47, 'memory/device_reserved (GiB)': 49.99, 'tokens/train_per_sec_per_gpu': 145.4462432861328, 'tokens/total': 1462272, 'tokens/trainable': 1278255, 'epoch': 1.37} | |
| 71%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 30/42 [37:32<14:48, 74.06s/it] 74%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 31/42 [38:47<13:36, 74.23s/it] {'loss': 0.1985, 'grad_norm': 0.05713922157883644, 'learning_rate': 2.5e-05, 'ppl': 1.21957, 'memory/max_active (GiB)': 48.44, 'memory/max_allocated (GiB)': 48.44, 'memory/device_reserved (GiB)': 49.99, 'tokens/train_per_sec_per_gpu': 145.67138671875, 'tokens/total': 1511424, 'tokens/trainable': 1321344, 'epoch': 1.41} | |
| 74%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 31/42 [38:47<13:36, 74.23s/it] 76%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 32/42 [40:01<12:22, 74.25s/it] {'loss': 0.3239, 'grad_norm': 0.06050688773393631, 'learning_rate': 2.5e-05, 'ppl': 1.38251, 'memory/max_active (GiB)': 48.45, 'memory/max_allocated (GiB)': 48.45, 'memory/device_reserved (GiB)': 49.99, 'tokens/train_per_sec_per_gpu': 146.34649658203125, 'tokens/total': 1560576, 'tokens/trainable': 1364715, 'epoch': 1.46} | |
| 76%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 32/42 [40:01<12:22, 74.25s/it] 79%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 33/42 [41:15<11:07, 74.11s/it] {'loss': 0.3728, 'grad_norm': 0.07901177555322647, 'learning_rate': 2.5e-05, 'ppl': 1.45179, 'memory/max_active (GiB)': 48.46, 'memory/max_allocated (GiB)': 48.46, 'memory/device_reserved (GiB)': 49.99, 'tokens/train_per_sec_per_gpu': 146.0816650390625, 'tokens/total': 1609728, 'tokens/trainable': 1407988, 'epoch': 1.51} | |
| 79%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 33/42 [41:15<11:07, 74.11s/it] 81%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 34/42 [42:28<09:50, 73.85s/it] {'loss': 0.4317, 'grad_norm': 0.06907946616411209, 'learning_rate': 2.5e-05, 'ppl': 1.53987, 'memory/max_active (GiB)': 48.45, 'memory/max_allocated (GiB)': 48.45, 'memory/device_reserved (GiB)': 50.07, 'tokens/train_per_sec_per_gpu': 151.48959350585938, 'tokens/total': 1658880, 'tokens/trainable': 1452133, 'epoch': 1.55} | |
| 81%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 34/42 [42:28<09:50, 73.85s/it] 83%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 35/42 [43:42<08:36, 73.72s/it] {'loss': 0.2807, 'grad_norm': 0.06577449291944504, 'learning_rate': 2.5e-05, 'ppl': 1.32406, 'memory/max_active (GiB)': 48.44, 'memory/max_allocated (GiB)': 48.44, 'memory/device_reserved (GiB)': 50.07, 'tokens/train_per_sec_per_gpu': 154.0474853515625, 'tokens/total': 1708032, 'tokens/trainable': 1494937, 'epoch': 1.6} | |
| 83%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 35/42 [43:42<08:36, 73.72s/it] 86%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 36/42 [44:55<07:21, 73.55s/it] {'loss': 0.3447, 'grad_norm': 0.10682138800621033, 'learning_rate': 2.5e-05, 'ppl': 1.41157, 'memory/max_active (GiB)': 48.43, 'memory/max_allocated (GiB)': 48.43, 'memory/device_reserved (GiB)': 50.07, 'tokens/train_per_sec_per_gpu': 147.22076416015625, 'tokens/total': 1757184, 'tokens/trainable': 1537275, 'epoch': 1.64} | |
| 86%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 36/42 [44:55<07:21, 73.55s/it] 88%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 37/42 [46:08<06:06, 73.28s/it] {'loss': 0.2947, 'grad_norm': 0.09354695677757263, 'learning_rate': 2.5e-05, 'ppl': 1.34272, 'memory/max_active (GiB)': 48.45, 'memory/max_allocated (GiB)': 48.45, 'memory/device_reserved (GiB)': 50.07, 'tokens/train_per_sec_per_gpu': 134.27401733398438, 'tokens/total': 1806336, 'tokens/trainable': 1578792, 'epoch': 1.69} | |
| 88%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 37/42 [46:08<06:06, 73.28s/it] 90%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 38/42 [47:20<04:52, 73.09s/it] {'loss': 0.3335, 'grad_norm': 0.05959487706422806, 'learning_rate': 2.5e-05, 'ppl': 1.39585, 'memory/max_active (GiB)': 48.44, 'memory/max_allocated (GiB)': 48.44, 'memory/device_reserved (GiB)': 50.07, 'tokens/train_per_sec_per_gpu': 142.3373260498047, 'tokens/total': 1855488, 'tokens/trainable': 1620711, 'epoch': 1.74} | |
| 90%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 38/42 [47:20<04:52, 73.09s/it] 93%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 39/42 [48:34<03:39, 73.16s/it] {'loss': 0.3303, 'grad_norm': 0.06608521193265915, 'learning_rate': 2.5e-05, 'ppl': 1.39139, 'memory/max_active (GiB)': 48.43, 'memory/max_allocated (GiB)': 48.43, 'memory/device_reserved (GiB)': 50.07, 'tokens/train_per_sec_per_gpu': 144.23472595214844, 'tokens/total': 1904640, 'tokens/trainable': 1663393, 'epoch': 1.78} | |
| 93%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 39/42 [48:34<03:39, 73.16s/it] 95%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 40/42 [49:47<02:26, 73.15s/it] {'loss': 0.2979, 'grad_norm': 0.06484091281890869, 'learning_rate': 2.5e-05, 'ppl': 1.34703, 'memory/max_active (GiB)': 48.44, 'memory/max_allocated (GiB)': 48.44, 'memory/device_reserved (GiB)': 50.07, 'tokens/train_per_sec_per_gpu': 149.06883239746094, 'tokens/total': 1953792, 'tokens/trainable': 1706532, 'epoch': 1.83} | |
| 95%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 40/42 [49:47<02:26, 73.15s/it] 98%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 41/42 [51:00<01:13, 73.26s/it] {'loss': 0.4153, 'grad_norm': 0.08739036321640015, 'learning_rate': 2.5e-05, 'ppl': 1.51483, 'memory/max_active (GiB)': 48.45, 'memory/max_allocated (GiB)': 48.45, 'memory/device_reserved (GiB)': 50.07, 'tokens/train_per_sec_per_gpu': 150.26309204101562, 'tokens/total': 2002944, 'tokens/trainable': 1749506, 'epoch': 1.87} | |
| 98%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 41/42 [51:00<01:13, 73.26s/it] 100%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ| 42/42 [52:14<00:00, 73.49s/it] {'loss': 0.3296, 'grad_norm': 0.0813710168004036, 'learning_rate': 2.5e-05, 'ppl': 1.39041, 'memory/max_active (GiB)': 48.45, 'memory/max_allocated (GiB)': 48.45, 'memory/device_reserved (GiB)': 50.07, 'tokens/train_per_sec_per_gpu': 145.78004455566406, 'tokens/total': 2052096, 'tokens/trainable': 1791720, 'epoch': 1.92} | |
| 100%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ| 42/42 [52:14<00:00, 73.49s/it][2026-01-28 19:40:22,329] [INFO] [axolotl.core.trainers.base._save:721] [PID:11475] Saving model checkpoint to ./Olmo-Guten-SFT/checkpoint-42 | |
| {'train_runtime': 3139.2835, 'train_samples_per_second': 0.107, 'train_steps_per_second': 0.013, 'train_loss': 0.5454000174289658, 'memory/max_active (GiB)': 33.26, 'memory/max_allocated (GiB)': 33.26, 'memory/device_reserved (GiB)': 50.07, 'epoch': 1.92, 'tokens/train_per_sec_per_gpu': 0.0} | |
| 100%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ| 42/42 [52:19<00:00, 73.49s/it] 100%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ| 42/42 [52:19<00:00, 74.74s/it] | |
| [2026-01-28 19:40:29,656] [INFO] [axolotl.train.save_trained_model:233] [PID:11475] Training completed! Saving trained model to ./Olmo-Guten-SFT. | |
| [2026-01-28 19:40:32,714] [INFO] [axolotl.train.save_trained_model:351] [PID:11475] Model successfully saved to ./Olmo-Guten-SFT | |
| [0m |