Instructions to use mx003/cve_model_1000_eltoukgi with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mx003/cve_model_1000_eltoukgi with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("unsloth/Meta-Llama-3.1-8B-Instruct")
model = PeftModel.from_pretrained(base_model, "mx003/cve_model_1000_eltoukgi")

Transformers

How to use mx003/cve_model_1000_eltoukgi with Transformers:

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

pipe = pipeline("text-generation", model="mx003/cve_model_1000_eltoukgi")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("mx003/cve_model_1000_eltoukgi")
model = AutoModelForCausalLM.from_pretrained("mx003/cve_model_1000_eltoukgi")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use mx003/cve_model_1000_eltoukgi with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mx003/cve_model_1000_eltoukgi"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mx003/cve_model_1000_eltoukgi",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/mx003/cve_model_1000_eltoukgi

SGLang

How to use mx003/cve_model_1000_eltoukgi 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 "mx003/cve_model_1000_eltoukgi" \
    --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": "mx003/cve_model_1000_eltoukgi",
		"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 "mx003/cve_model_1000_eltoukgi" \
        --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": "mx003/cve_model_1000_eltoukgi",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use mx003/cve_model_1000_eltoukgi with Docker Model Runner:
```
docker model run hf.co/mx003/cve_model_1000_eltoukgi
```

cve_model_1000_eltoukgi / debug.log

mx003

Upload folder using huggingface_hub

90dc82e verified 3 months ago

Raw

History Blame Contribute Delete

66.4 kB

	[2026-04-10 13:58:29,722] [DEBUG] [axolotl.utils.config.log_gpu_memory_usage:127] [PID:7899] baseline 0.000GB ()
	[2026-04-10 13:58:29,722] [INFO] [axolotl.cli.config.load_cfg:248] [PID:7899] config:
	{
	"activation_offloading": false,
	"adapter": "lora",
	"axolotl_config_path": "config.yaml",
	"base_model": "unsloth/Meta-Llama-3.1-8B-Instruct",
	"base_model_config": "unsloth/Meta-Llama-3.1-8B-Instruct",
	"batch_size": 16,
	"bf16": true,
	"capabilities": {
	"bf16": true,
	"compute_capability": "sm_90",
	"fp8": false,
	"n_gpu": 1,
	"n_node": 1
	},
	"context_parallel_size": 1,
	"dataloader_num_workers": 1,
	"dataloader_pin_memory": true,
	"dataloader_prefetch_factor": 256,
	"dataset_processes": 8,
	"datasets": [
	{
	"chat_template": "llama3",
	"field_messages": "messages",
	"message_property_mappings": {
	"content": "content",
	"role": "role"
	},
	"path": "mx003/cve_dataset_1000",
	"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": "2.7.1"
	},
	"eval_batch_size": 4,
	"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
	},
	"group_by_length": true,
	"include_tkps": true,
	"is_llama_derived_model": true,
	"learning_rate": 0.0002,
	"lisa_layers_attribute": "model.layers",
	"load_best_model_at_end": false,
	"load_in_4bit": true,
	"load_in_8bit": false,
	"local_rank": 0,
	"lora_alpha": 64,
	"lora_dropout": 0.05,
	"lora_modules_to_save": [
	"embed_tokens",
	"lm_head"
	],
	"lora_r": 32,
	"lora_target_modules": [
	"q_proj",
	"v_proj",
	"k_proj",
	"o_proj",
	"gate_proj",
	"down_proj",
	"up_proj"
	],
	"loraplus_lr_embedding": 1e-06,
	"lr_scheduler": "cosine",
	"mean_resizing_embeddings": false,
	"micro_batch_size": 4,
	"model_config_type": "llama",
	"num_epochs": 2.0,
	"optimizer": "adamw_torch_fused",
	"output_dir": "./outputs/mymodel",
	"pad_to_sequence_len": true,
	"pretrain_multipack_attn": true,
	"profiler_steps_start": 0,
	"qlora_sharded_model_loading": false,
	"ray_num_workers": 1,
	"resources_per_worker": {
	"GPU": 1
	},
	"sample_packing": true,
	"sample_packing_bin_size": 200,
	"sample_packing_group_size": 100000,
	"save_only_model": false,
	"save_safetensors": true,
	"save_steps": 50,
	"sequence_len": 4096,
	"shuffle_before_merging_datasets": false,
	"shuffle_merged_datasets": true,
	"skip_prepare_dataset": false,
	"special_tokens": {
	"pad_token": "<\|end_of_text\|>"
	},
	"streaming_multipack_buffer_size": 10000,
	"strict": false,
	"tensor_parallel_size": 1,
	"tiled_mlp_use_original_mlp": true,
	"tokenizer_config": "unsloth/Meta-Llama-3.1-8B-Instruct",
	"tokenizer_save_jinja_files": true,
	"tokens": [
	"<\|end_of_text\|>"
	],
	"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_ray": false,
	"val_set_size": 0.0,
	"vllm": {
	"device": "auto",
	"dtype": "auto",
	"gpu_memory_utilization": 0.9,
	"host": "0.0.0.0",
	"port": 8000
	},
	"weight_decay": 0.0,
	"world_size": 1
	}
	[2026-04-10 13:58:30,702] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:278] [PID:7899] EOS: 128009 / <\|eot_id\|>
	[2026-04-10 13:58:30,702] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:279] [PID:7899] BOS: 128000 / <\|begin_of_text\|>
	[2026-04-10 13:58:30,702] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:280] [PID:7899] PAD: 128001 / <\|end_of_text\|>
	[2026-04-10 13:58:30,702] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:281] [PID:7899] UNK: None / None
	[2026-04-10 13:58:30,703] [INFO] [axolotl.utils.data.shared.load_preprocessed_dataset:476] [PID:7899] Unable to find prepared dataset in last_run_prepared/d1f1263ce25c23753621d9371f061ee3
	[2026-04-10 13:58:30,703] [INFO] [axolotl.utils.data.sft._load_raw_datasets:320] [PID:7899] Loading raw datasets...
	[2026-04-10 13:58:30,703] [WARNING] [axolotl.utils.data.sft._load_raw_datasets:322] [PID:7899] Processing datasets during training can lead to VRAM instability. Please pre-process your dataset using `axolotl preprocess path/to/config.yml`.
	[2026-04-10 13:58:33,488] [INFO] [axolotl.utils.data.wrappers.get_dataset_wrapper:87] [PID:7899] Loading dataset: mx003/cve_dataset_1000 with base_type: chat_template and prompt_style: None
	[2026-04-10 13:58:33,490] [INFO] [axolotl.prompt_strategies.chat_template.__call__:969] [PID:7899] Using chat template:
	---
	{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<\|start_header_id\|>' + message['role'] + '<\|end_header_id\|>

	'+ message['content'] \| trim + '<\|eot_id\|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<\|start_header_id\|>assistant<\|end_header_id\|>

	' }}{% endif %}

	---
	Tokenizing Prompts (num_proc=8): 0%\| \| 0/989 [00:00<?, ? examples/s] Tokenizing Prompts (num_proc=8): 13%\|███████████▌ \| 124/989 [00:01<00:12, 70.54 examples/s] Tokenizing Prompts (num_proc=8): 25%\|██████████████████████▊ \| 248/989 [00:01<00:05, 145.06 examples/s] Tokenizing Prompts (num_proc=8): 38%\|██████████████████████████████████▏ \| 372/989 [00:02<00:02, 236.49 examples/s] Tokenizing Prompts (num_proc=8): 63%\|█████████████████████████████████████████████████████████ \| 620/989 [00:02<00:00, 482.05 examples/s] Tokenizing Prompts (num_proc=8): 100%\|███████████████████████████████████████████████████████████████████████████████████████████\| 989/989 [00:02<00:00, 740.12 examples/s] Tokenizing Prompts (num_proc=8): 100%\|███████████████████████████████████████████████████████████████████████████████████████████\| 989/989 [00:02<00:00, 378.73 examples/s]
	[2026-04-10 13:58:36,220] [INFO] [axolotl.utils.data.utils.handle_long_seq_in_dataset:218] [PID:7899] min_input_len: 489
	[2026-04-10 13:58:36,220] [INFO] [axolotl.utils.data.utils.handle_long_seq_in_dataset:220] [PID:7899] max_input_len: 22717
	Dropping Long Sequences (>4096) (num_proc=8): 0%\| \| 0/989 [00:00<?, ? examples/s] Dropping Long Sequences (>4096) (num_proc=8): 13%\|█████████▊ \| 124/989 [00:00<00:01, 719.26 examples/s] Dropping Long Sequences (>4096) (num_proc=8): 100%\|█████████████████████████████████████████████████████████████████████████████\| 989/989 [00:00<00:00, 3388.59 examples/s]
	[2026-04-10 13:58:36,528] [WARNING] [axolotl.utils.data.utils.handle_long_seq_in_dataset:260] [PID:7899] Dropped 55 samples from dataset
	Drop Samples with Zero Trainable Tokens (num_proc=8): 0%\| \| 0/934 [00:00<?, ? examples/s] Drop Samples with Zero Trainable Tokens (num_proc=8): 13%\|████████▊ \| 117/934 [00:00<00:01, 724.01 examples/s] Drop Samples with Zero Trainable Tokens (num_proc=8): 100%\|█████████████████████████████████████████████████████████████████████\| 934/934 [00:00<00:00, 3255.94 examples/s]
	Group By Length (num_proc=8): 0%\| \| 0/934 [00:00<?, ? examples/s] Group By Length (num_proc=8): 12%\|███████████▌ \| 115/934 [00:00<00:01, 717.61 examples/s] Group By Length (num_proc=8): 100%\|█████████████████████████████████████████████████████████████████████████████████████████████\| 934/934 [00:00<00:00, 2747.28 examples/s]
	Add position_id column (Sample Packing) (num_proc=8): 0%\| \| 0/934 [00:00<?, ? examples/s] Add position_id column (Sample Packing) (num_proc=8): 13%\|████████▊ \| 117/934 [00:00<00:01, 700.04 examples/s] Add position_id column (Sample Packing) (num_proc=8): 100%\|█████████████████████████████████████████████████████████████████████\| 934/934 [00:00<00:00, 2998.02 examples/s]
	Saving the dataset (0/3 shards): 0%\| \| 0/934 [00:00<?, ? examples/s] Saving the dataset (1/3 shards): 67%\|████████████████████████████████████████████████████████████ \| 623/934 [00:00<00:00, 8737.55 examples/s] Saving the dataset (2/3 shards): 67%\|████████████████████████████████████████████████████████████ \| 623/934 [00:00<00:00, 8624.87 examples/s] Saving the dataset (3/3 shards): 100%\|█████████████████████████████████████████████████████████████████████████████████████████\| 934/934 [00:00<00:00, 12744.46 examples/s] Saving the dataset (3/3 shards): 100%\|██████████████████████████████████████████████████████████████████████████████████████████\| 934/934 [00:00<00:00, 6729.26 examples/s]
	[2026-04-10 13:58:37,675] [DEBUG] [axolotl.utils.trainer.calculate_total_num_steps:404] [PID:7899] total_num_tokens: 1_457_482
	[2026-04-10 13:58:37,684] [DEBUG] [axolotl.utils.trainer.calculate_total_num_steps:422] [PID:7899] `total_supervised_tokens: 308_054`
	[2026-04-10 13:58:38,798] [DEBUG] [axolotl.utils.samplers.multipack.__len__:458] [PID:7899] generate_batches time: 0.5154547691345215
	[2026-04-10 13:58:39,325] [DEBUG] [axolotl.utils.samplers.multipack.__len__:458] [PID:7899] generate_batches time: 0.5266461372375488
	[2026-04-10 13:58:39,857] [DEBUG] [axolotl.utils.samplers.multipack.__len__:458] [PID:7899] generate_batches time: 0.53169846534729
	[2026-04-10 13:58:40,395] [DEBUG] [axolotl.utils.samplers.multipack.__len__:458] [PID:7899] generate_batches time: 0.5374758243560791
	[2026-04-10 13:58:40,415] [INFO] [axolotl.utils.samplers.multipack.calc_min_len:434] [PID:7899] gather_len_batches: [90]
	[2026-04-10 13:58:40,415] [DEBUG] [axolotl.utils.trainer.calculate_total_num_steps:481] [PID:7899] data_loader_len: 22
	[2026-04-10 13:58:40,415] [INFO] [axolotl.utils.trainer.calc_sample_packing_eff_est:497] [PID:7899] sample_packing_eff_est across ranks: [0.9775565011160714]
	[2026-04-10 13:58:40,415] [DEBUG] [axolotl.utils.trainer.calculate_total_num_steps:509] [PID:7899] sample_packing_eff_est: 0.98
	[2026-04-10 13:58:40,415] [DEBUG] [axolotl.utils.trainer.calculate_total_num_steps:520] [PID:7899] total_num_steps: 44
	[2026-04-10 13:58:40,415] [INFO] [axolotl.utils.data.sft._prepare_standard_dataset:121] [PID:7899] Maximum number of steps set at 44
	[2026-04-10 13:58:40,445] [DEBUG] [axolotl.train.setup_model_and_tokenizer:65] [PID:7899] Loading tokenizer... unsloth/Meta-Llama-3.1-8B-Instruct
	[2026-04-10 13:58:41,324] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:278] [PID:7899] EOS: 128009 / <\|eot_id\|>
	[2026-04-10 13:58:41,324] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:279] [PID:7899] BOS: 128000 / <\|begin_of_text\|>
	[2026-04-10 13:58:41,324] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:280] [PID:7899] PAD: 128001 / <\|end_of_text\|>
	[2026-04-10 13:58:41,324] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:281] [PID:7899] UNK: None / None
	[2026-04-10 13:58:41,324] [DEBUG] [axolotl.train.setup_model_and_tokenizer:74] [PID:7899] Loading model
	[2026-04-10 13:58:41,491] [DEBUG] [axolotl.monkeypatch.transformers.trainer_loss_calc.patch_evaluation_loop:87] [PID:7899] Patched Trainer.evaluation_loop with nanmean loss calculation
	[2026-04-10 13:58:41,492] [DEBUG] [axolotl.monkeypatch.transformers.trainer_loss_calc.patch_maybe_log_save_evaluate:138] [PID:7899] Patched Trainer._maybe_log_save_evaluate with nanmean loss calculation
	[2026-04-10 13:58:41,492] [INFO] [axolotl.loaders.patch_manager._apply_multipack_patches:301] [PID:7899] Applying multipack dataloader patch for sample packing...
	Loading checkpoint shards: 0%\| \| 0/4 [00:00<?, ?it/s] Loading checkpoint shards: 25%\|███████████████████████████▎ \| 1/4 [00:02<00:08, 2.94s/it] Loading checkpoint shards: 50%\|██████████████████████████████████████████████████████▌ \| 2/4 [00:06<00:06, 3.29s/it] Loading checkpoint shards: 75%\|█████████████████████████████████████████████████████████████████████████████████▊ \| 3/4 [00:09<00:03, 3.35s/it] Loading checkpoint shards: 100%\|█████████████████████████████████████████████████████████████████████████████████████████████████████████████\| 4/4 [00:10<00:00, 2.11s/it] Loading checkpoint shards: 100%\|█████████████████████████████████████████████████████████████████████████████████████████████████████████████\| 4/4 [00:10<00:00, 2.53s/it]
	[2026-04-10 13:58:52,266] [INFO] [axolotl.loaders.model._prepare_model_for_quantization:863] [PID:7899] converting PEFT model w/ prepare_model_for_kbit_training
	[2026-04-10 13:58:52,269] [INFO] [axolotl.loaders.model._configure_embedding_dtypes:345] [PID:7899] Converting modules to torch.bfloat16
	[2026-04-10 13:58:52,276] [DEBUG] [axolotl.loaders.model.log_gpu_memory_usage:127] [PID:7899] Memory usage after model load 8.657GB (+8.657GB allocated, +9.924GB reserved)
	trainable params: 1,134,559,232 \|\| all params: 9,164,820,480 \|\| trainable%: 12.3795
	[2026-04-10 13:58:52,901] [DEBUG] [axolotl.loaders.model.log_gpu_memory_usage:127] [PID:7899] after adapters 7.969GB (+7.969GB allocated, +10.072GB reserved)
	[2026-04-10 13:58:57,835] [INFO] [axolotl.train.save_initial_configs:398] [PID:7899] Pre-saving adapter config to ./outputs/mymodel...
	[2026-04-10 13:58:57,836] [INFO] [axolotl.train.save_initial_configs:402] [PID:7899] Pre-saving tokenizer to ./outputs/mymodel...
	[2026-04-10 13:58:57,967] [INFO] [axolotl.train.save_initial_configs:407] [PID:7899] Pre-saving model config to ./outputs/mymodel...
	[2026-04-10 13:58:57,969] [INFO] [axolotl.train.execute_training:196] [PID:7899] Starting trainer...
	[2026-04-10 13:59:00,245] [DEBUG] [axolotl.utils.samplers.multipack.__len__:458] [PID:7899] generate_batches time: 0.8013865947723389
	[2026-04-10 13:59:01,035] [DEBUG] [axolotl.utils.samplers.multipack.__len__:458] [PID:7899] generate_batches time: 0.7904410362243652
	[2026-04-10 13:59:01,802] [DEBUG] [axolotl.utils.samplers.multipack.__len__:458] [PID:7899] generate_batches time: 0.7667834758758545
	[2026-04-10 13:59:02,580] [DEBUG] [axolotl.utils.samplers.multipack.__len__:458] [PID:7899] generate_batches time: 0.7771618366241455
	[2026-04-10 13:59:02,580] [INFO] [axolotl.utils.samplers.multipack.calc_min_len:434] [PID:7899] gather_len_batches: [90]
	0%\| \| 0/44 [00:00<?, ?it/s] 2%\|███ \| 1/44 [00:12<09:17, 12.97s/it] {'loss': 0.6377, 'grad_norm': 3.9988136291503906, 'learning_rate': 0.0, 'memory/max_active (GiB)': 38.73, 'memory/max_allocated (GiB)': 38.73, 'memory/device_reserved (GiB)': 46.38, 'tokens_per_second_per_gpu': 1272.18, 'epoch': 0.04}
	2%\|███ \| 1/44 [00:12<09:17, 12.97s/it] 5%\|██████▏ \| 2/44 [00:23<08:04, 11.54s/it] {'loss': 0.6022, 'grad_norm': 3.8201091289520264, 'learning_rate': 0.0001, 'memory/max_active (GiB)': 43.35, 'memory/max_allocated (GiB)': 43.35, 'memory/device_reserved (GiB)': 51.13, 'tokens_per_second_per_gpu': 1310.05, 'epoch': 0.09}
	5%\|██████▏ \| 2/44 [00:23<08:04, 11.54s/it] 7%\|█████████▏ \| 3/44 [00:34<07:34, 11.07s/it] {'loss': 0.258, 'grad_norm': 2.0871596336364746, 'learning_rate': 0.0002, 'memory/max_active (GiB)': 43.35, 'memory/max_allocated (GiB)': 43.35, 'memory/device_reserved (GiB)': 51.13, 'tokens_per_second_per_gpu': 1449.56, 'epoch': 0.13}
	7%\|█████████▏ \| 3/44 [00:34<07:34, 11.07s/it] 9%\|████████████▎ \| 4/44 [00:44<07:14, 10.87s/it] {'loss': 0.2098, 'grad_norm': 9.840972900390625, 'learning_rate': 0.00019972037971811802, 'memory/max_active (GiB)': 43.35, 'memory/max_allocated (GiB)': 43.35, 'memory/device_reserved (GiB)': 51.13, 'tokens_per_second_per_gpu': 1242.92, 'epoch': 0.18}
	9%\|████████████▎ \| 4/44 [00:44<07:14, 10.87s/it] 11%\|███████████████▎ \| 5/44 [00:55<06:59, 10.77s/it] {'loss': 0.1372, 'grad_norm': 16.3769474029541, 'learning_rate': 0.00019888308262251285, 'memory/max_active (GiB)': 43.35, 'memory/max_allocated (GiB)': 43.35, 'memory/device_reserved (GiB)': 51.13, 'tokens_per_second_per_gpu': 1221.02, 'epoch': 0.22}
	11%\|███████████████▎ \| 5/44 [00:55<06:59, 10.77s/it] 14%\|██████████████████▍ \| 6/44 [01:05<06:46, 10.70s/it] {'loss': 0.103, 'grad_norm': 1.9449656009674072, 'learning_rate': 0.00019749279121818235, 'memory/max_active (GiB)': 43.35, 'memory/max_allocated (GiB)': 43.35, 'memory/device_reserved (GiB)': 51.13, 'tokens_per_second_per_gpu': 1230.89, 'epoch': 0.27}
	14%\|██████████████████▍ \| 6/44 [01:05<06:46, 10.70s/it] 16%\|█████████████████████▍ \| 7/44 [01:16<06:33, 10.64s/it] {'loss': 0.06, 'grad_norm': 0.9599031805992126, 'learning_rate': 0.0001955572805786141, 'memory/max_active (GiB)': 43.35, 'memory/max_allocated (GiB)': 43.35, 'memory/device_reserved (GiB)': 51.13, 'tokens_per_second_per_gpu': 1336.48, 'epoch': 0.31}
	16%\|█████████████████████▍ \| 7/44 [01:16<06:33, 10.64s/it] 18%\|████████████████████████▌ \| 8/44 [01:26<06:22, 10.62s/it] {'loss': 0.0472, 'grad_norm': 0.6724708080291748, 'learning_rate': 0.00019308737486442045, 'memory/max_active (GiB)': 43.35, 'memory/max_allocated (GiB)': 43.35, 'memory/device_reserved (GiB)': 51.13, 'tokens_per_second_per_gpu': 1326.52, 'epoch': 0.36}
	18%\|████████████████████████▌ \| 8/44 [01:26<06:22, 10.62s/it] 20%\|███████████████████████████▌ \| 9/44 [01:37<06:10, 10.58s/it] {'loss': 0.0535, 'grad_norm': 0.7262558937072754, 'learning_rate': 0.0001900968867902419, 'memory/max_active (GiB)': 43.35, 'memory/max_allocated (GiB)': 43.35, 'memory/device_reserved (GiB)': 51.13, 'tokens_per_second_per_gpu': 1321.8, 'epoch': 0.4}
	20%\|███████████████████████████▌ \| 9/44 [01:37<06:10, 10.58s/it] 23%\|██████████████████████████████▍ \| 10/44 [01:47<05:59, 10.58s/it] {'loss': 0.0401, 'grad_norm': 0.5925001502037048, 'learning_rate': 0.00018660254037844388, 'memory/max_active (GiB)': 43.35, 'memory/max_allocated (GiB)': 43.35, 'memory/device_reserved (GiB)': 51.13, 'tokens_per_second_per_gpu': 1341.09, 'epoch': 0.44}
	23%\|██████████████████████████████▍ \| 10/44 [01:47<05:59, 10.58s/it] 25%\|█████████████████████████████████▌ \| 11/44 [01:58<05:48, 10.58s/it] {'loss': 0.0421, 'grad_norm': 0.4922492504119873, 'learning_rate': 0.0001826238774315995, 'memory/max_active (GiB)': 43.35, 'memory/max_allocated (GiB)': 43.35, 'memory/device_reserved (GiB)': 51.13, 'tokens_per_second_per_gpu': 1344.8, 'epoch': 0.49}
	25%\|█████████████████████████████████▌ \| 11/44 [01:58<05:48, 10.58s/it] 27%\|████████████████████████████████████▌ \| 12/44 [02:09<05:38, 10.59s/it] {'loss': 0.0496, 'grad_norm': 0.3521144390106201, 'learning_rate': 0.000178183148246803, 'memory/max_active (GiB)': 43.35, 'memory/max_allocated (GiB)': 43.35, 'memory/device_reserved (GiB)': 51.13, 'tokens_per_second_per_gpu': 1236.47, 'epoch': 0.53}
	27%\|████████████████████████████████████▌ \| 12/44 [02:09<05:38, 10.59s/it] 30%\|███████████████████████████████████████▌ \| 13/44 [02:19<05:28, 10.59s/it] {'loss': 0.0422, 'grad_norm': 0.33798691630363464, 'learning_rate': 0.00017330518718298264, 'memory/max_active (GiB)': 43.35, 'memory/max_allocated (GiB)': 43.35, 'memory/device_reserved (GiB)': 51.13, 'tokens_per_second_per_gpu': 1289.89, 'epoch': 0.58}
	30%\|███████████████████████████████████████▌ \| 13/44 [02:19<05:28, 10.59s/it] 32%\|██████████████████████████████████████████▋ \| 14/44 [02:30<05:17, 10.60s/it] {'loss': 0.0416, 'grad_norm': 0.33821234107017517, 'learning_rate': 0.00016801727377709194, 'memory/max_active (GiB)': 43.35, 'memory/max_allocated (GiB)': 43.35, 'memory/device_reserved (GiB)': 51.13, 'tokens_per_second_per_gpu': 1264.76, 'epoch': 0.62}
	32%\|██████████████████████████████████████████▋ \| 14/44 [02:30<05:17, 10.60s/it] 34%\|█████████████████████████████████████████████▋ \| 15/44 [02:40<05:07, 10.61s/it] {'loss': 0.0283, 'grad_norm': 0.2641695737838745, 'learning_rate': 0.00016234898018587337, 'memory/max_active (GiB)': 43.35, 'memory/max_allocated (GiB)': 43.35, 'memory/device_reserved (GiB)': 51.13, 'tokens_per_second_per_gpu': 1330.45, 'epoch': 0.67}
	34%\|█████████████████████████████████████████████▋ \| 15/44 [02:40<05:07, 10.61s/it] 36%\|████████████████████████████████████████████████▋ \| 16/44 [02:51<04:56, 10.60s/it] {'loss': 0.0426, 'grad_norm': 0.3202700912952423, 'learning_rate': 0.0001563320058063622, 'memory/max_active (GiB)': 43.35, 'memory/max_allocated (GiB)': 43.35, 'memory/device_reserved (GiB)': 51.13, 'tokens_per_second_per_gpu': 1269.3, 'epoch': 0.71}
	36%\|████████████████████████████████████████████████▋ \| 16/44 [02:51<04:56, 10.60s/it] 39%\|███████████████████████████████████████████████████▊ \| 17/44 [03:02<04:45, 10.59s/it] {'loss': 0.0402, 'grad_norm': 0.37863489985466003, 'learning_rate': 0.00015000000000000001, 'memory/max_active (GiB)': 43.35, 'memory/max_allocated (GiB)': 43.35, 'memory/device_reserved (GiB)': 51.13, 'tokens_per_second_per_gpu': 1276.11, 'epoch': 0.76}
	39%\|███████████████████████████████████████████████████▊ \| 17/44 [03:02<04:45, 10.59s/it] 41%\|██████████████████████████████████████████████████████▊ \| 18/44 [03:12<04:35, 10.59s/it] {'loss': 0.0541, 'grad_norm': 0.36693161725997925, 'learning_rate': 0.00014338837391175582, 'memory/max_active (GiB)': 43.35, 'memory/max_allocated (GiB)': 43.35, 'memory/device_reserved (GiB)': 51.13, 'tokens_per_second_per_gpu': 1293.35, 'epoch': 0.8}
	41%\|██████████████████████████████████████████████████████▊ \| 18/44 [03:12<04:35, 10.59s/it] 43%\|█████████████████████████████████████████████████████████▊ \| 19/44 [03:23<04:25, 10.60s/it] {'loss': 0.0513, 'grad_norm': 0.398545503616333, 'learning_rate': 0.00013653410243663952, 'memory/max_active (GiB)': 43.35, 'memory/max_allocated (GiB)': 43.35, 'memory/device_reserved (GiB)': 51.13, 'tokens_per_second_per_gpu': 1218.05, 'epoch': 0.84}
	43%\|█████████████████████████████████████████████████████████▊ \| 19/44 [03:23<04:25, 10.60s/it] 45%\|████████████████████████████████████████████████████████████▉ \| 20/44 [03:33<04:14, 10.60s/it] {'loss': 0.0283, 'grad_norm': 0.24128811061382294, 'learning_rate': 0.00012947551744109043, 'memory/max_active (GiB)': 43.35, 'memory/max_allocated (GiB)': 43.35, 'memory/device_reserved (GiB)': 51.13, 'tokens_per_second_per_gpu': 1243.65, 'epoch': 0.89}
	45%\|████████████████████████████████████████████████████████████▉ \| 20/44 [03:33<04:14, 10.60s/it] 48%\|███████████████████████████████████████████████████████████████▉ \| 21/44 [03:44<04:03, 10.57s/it] {'loss': 0.0238, 'grad_norm': 0.22816111147403717, 'learning_rate': 0.00012225209339563145, 'memory/max_active (GiB)': 43.35, 'memory/max_allocated (GiB)': 43.35, 'memory/device_reserved (GiB)': 51.13, 'tokens_per_second_per_gpu': 1379.37, 'epoch': 0.93}
	48%\|███████████████████████████████████████████████████████████████▉ \| 21/44 [03:44<04:03, 10.57s/it] 50%\|███████████████████████████████████████████████████████████████████ \| 22/44 [03:54<03:52, 10.57s/it] {'loss': 0.0272, 'grad_norm': 0.29317620396614075, 'learning_rate': 0.00011490422661761744, 'memory/max_active (GiB)': 43.35, 'memory/max_allocated (GiB)': 43.35, 'memory/device_reserved (GiB)': 51.13, 'tokens_per_second_per_gpu': 1257.24, 'epoch': 0.98}
	50%\|███████████████████████████████████████████████████████████████████ \| 22/44 [03:54<03:52, 10.57s/it] 52%\|██████████████████████████████████████████████████████████████████████ \| 23/44 [04:00<03:09, 9.01s/it] {'loss': 0.0446, 'grad_norm': 0.49180206656455994, 'learning_rate': 0.00010747300935864243, 'memory/max_active (GiB)': 43.35, 'memory/max_allocated (GiB)': 43.35, 'memory/device_reserved (GiB)': 51.13, 'tokens_per_second_per_gpu': 1165.84, 'epoch': 1.0}
	52%\|██████████████████████████████████████████████████████████████████████ \| 23/44 [04:00<03:09, 9.01s/it] 55%\|█████████████████████████████████████████████████████████████████████████ \| 24/44 [04:12<03:21, 10.07s/it] {'loss': 0.0162, 'grad_norm': 0.23574988543987274, 'learning_rate': 0.0001, 'memory/max_active (GiB)': 43.35, 'memory/max_allocated (GiB)': 43.35, 'memory/device_reserved (GiB)': 51.13, 'tokens_per_second_per_gpu': 1261.03, 'epoch': 1.04}
	55%\|█████████████████████████████████████████████████████████████████████████ \| 24/44 [04:12<03:21, 10.07s/it] 57%\|████████████████████████████████████████████████████████████████████████████▏ \| 25/44 [04:23<03:13, 10.20s/it] {'loss': 0.0174, 'grad_norm': 0.17455901205539703, 'learning_rate': 9.252699064135758e-05, 'memory/max_active (GiB)': 43.35, 'memory/max_allocated (GiB)': 43.35, 'memory/device_reserved (GiB)': 51.13, 'tokens_per_second_per_gpu': 1388.76, 'epoch': 1.09}
	57%\|████████████████████████████████████████████████████████████████████████████▏ \| 25/44 [04:23<03:13, 10.20s/it] 59%\|███████████████████████████████████████████████████████████████████████████████▏ \| 26/44 [04:33<03:05, 10.32s/it] {'loss': 0.0185, 'grad_norm': 0.23850183188915253, 'learning_rate': 8.509577338238255e-05, 'memory/max_active (GiB)': 43.35, 'memory/max_allocated (GiB)': 43.35, 'memory/device_reserved (GiB)': 51.13, 'tokens_per_second_per_gpu': 1238.14, 'epoch': 1.13}
	59%\|███████████████████████████████████████████████████████████████████████████████▏ \| 26/44 [04:33<03:05, 10.32s/it] 61%\|██████████████████████████████████████████████████████████████████████████████████▏ \| 27/44 [04:44<02:56, 10.39s/it] {'loss': 0.0137, 'grad_norm': 0.17631582915782928, 'learning_rate': 7.774790660436858e-05, 'memory/max_active (GiB)': 43.35, 'memory/max_allocated (GiB)': 43.35, 'memory/device_reserved (GiB)': 51.13, 'tokens_per_second_per_gpu': 1331.49, 'epoch': 1.18}
	61%\|██████████████████████████████████████████████████████████████████████████████████▏ \| 27/44 [04:44<02:56, 10.39s/it] 64%\|█████████████████████████████████████████████████████████████████████████████████████▎ \| 28/44 [04:55<02:46, 10.43s/it] {'loss': 0.0133, 'grad_norm': 0.1664351224899292, 'learning_rate': 7.052448255890957e-05, 'memory/max_active (GiB)': 43.35, 'memory/max_allocated (GiB)': 43.35, 'memory/device_reserved (GiB)': 51.13, 'tokens_per_second_per_gpu': 1321.29, 'epoch': 1.22}
	64%\|█████████████████████████████████████████████████████████████████████████████████████▎ \| 28/44 [04:55<02:46, 10.43s/it] 66%\|████████████████████████████████████████████████████████████████████████████████████████▎ \| 29/44 [05:05<02:37, 10.48s/it] {'loss': 0.0153, 'grad_norm': 0.20239098370075226, 'learning_rate': 6.34658975633605e-05, 'memory/max_active (GiB)': 43.35, 'memory/max_allocated (GiB)': 43.35, 'memory/device_reserved (GiB)': 51.13, 'tokens_per_second_per_gpu': 1232.78, 'epoch': 1.27}
	66%\|████████████████████████████████████████████████████████████████████████████████████████▎ \| 29/44 [05:05<02:37, 10.48s/it] 68%\|███████████████████████████████████████████████████████████████████████████████████████████▎ \| 30/44 [05:16<02:27, 10.52s/it] {'loss': 0.0197, 'grad_norm': 0.20838677883148193, 'learning_rate': 5.6611626088244194e-05, 'memory/max_active (GiB)': 43.35, 'memory/max_allocated (GiB)': 43.35, 'memory/device_reserved (GiB)': 51.13, 'tokens_per_second_per_gpu': 1195.49, 'epoch': 1.31}
	68%\|███████████████████████████████████████████████████████████████████████████████████████████▎ \| 30/44 [05:16<02:27, 10.52s/it] 70%\|██████████████████████████████████████████████████████████████████████████████████████████████▍ \| 31/44 [05:26<02:17, 10.55s/it] {'loss': 0.0161, 'grad_norm': 0.17082557082176208, 'learning_rate': 5.000000000000002e-05, 'memory/max_active (GiB)': 43.35, 'memory/max_allocated (GiB)': 43.35, 'memory/device_reserved (GiB)': 51.13, 'tokens_per_second_per_gpu': 1237.56, 'epoch': 1.36}
	70%\|██████████████████████████████████████████████████████████████████████████████████████████████▍ \| 31/44 [05:26<02:17, 10.55s/it] 73%\|█████████████████████████████████████████████████████████████████████████████████████████████████▍ \| 32/44 [05:37<02:06, 10.55s/it] {'loss': 0.0126, 'grad_norm': 0.17102588713169098, 'learning_rate': 4.3667994193637796e-05, 'memory/max_active (GiB)': 43.35, 'memory/max_allocated (GiB)': 43.35, 'memory/device_reserved (GiB)': 51.13, 'tokens_per_second_per_gpu': 1292.78, 'epoch': 1.4}
	73%\|█████████████████████████████████████████████████████████████████████████████████████████████████▍ \| 32/44 [05:37<02:06, 10.55s/it] 75%\|████████████████████████████████████████████████████████████████████████████████████████████████████▌ \| 33/44 [05:48<01:56, 10.56s/it] {'loss': 0.0155, 'grad_norm': 0.17077268660068512, 'learning_rate': 3.7651019814126654e-05, 'memory/max_active (GiB)': 43.35, 'memory/max_allocated (GiB)': 43.35, 'memory/device_reserved (GiB)': 51.13, 'tokens_per_second_per_gpu': 1433.05, 'epoch': 1.44}
	75%\|████████████████████████████████████████████████████████████████████████████████████████████████████▌ \| 33/44 [05:48<01:56, 10.56s/it] 77%\|███████████████████████████████████████████████████████████████████████████████████████████████████████▌ \| 34/44 [05:58<01:45, 10.55s/it] {'loss': 0.0125, 'grad_norm': 0.1558006852865219, 'learning_rate': 3.198272622290804e-05, 'memory/max_active (GiB)': 43.35, 'memory/max_allocated (GiB)': 43.35, 'memory/device_reserved (GiB)': 51.13, 'tokens_per_second_per_gpu': 1341.43, 'epoch': 1.49}
	77%\|███████████████████████████████████████████████████████████████████████████████████████████████████████▌ \| 34/44 [05:58<01:45, 10.55s/it] 80%\|██████████████████████████████████████████████████████████████████████████████████████████████████████████▌ \| 35/44 [06:09<01:34, 10.53s/it] {'loss': 0.0121, 'grad_norm': 0.17341959476470947, 'learning_rate': 2.669481281701739e-05, 'memory/max_active (GiB)': 43.35, 'memory/max_allocated (GiB)': 43.35, 'memory/device_reserved (GiB)': 51.13, 'tokens_per_second_per_gpu': 1390.06, 'epoch': 1.53}
	80%\|██████████████████████████████████████████████████████████████████████████████████████████████████████████▌ \| 35/44 [06:09<01:34, 10.53s/it] 82%\|█████████████████████████████████████████████████████████████████████████████████████████████████████████████▋ \| 36/44 [06:19<01:24, 10.53s/it] {'loss': 0.0135, 'grad_norm': 0.7362567186355591, 'learning_rate': 2.181685175319702e-05, 'memory/max_active (GiB)': 43.35, 'memory/max_allocated (GiB)': 43.35, 'memory/device_reserved (GiB)': 51.13, 'tokens_per_second_per_gpu': 1381.11, 'epoch': 1.58}
	82%\|█████████████████████████████████████████████████████████████████████████████████████████████████████████████▋ \| 36/44 [06:19<01:24, 10.53s/it] 84%\|████████████████████████████████████████████████████████████████████████████████████████████████████████████████▋ \| 37/44 [06:30<01:13, 10.53s/it] {'loss': 0.0126, 'grad_norm': 0.20648105442523956, 'learning_rate': 1.7376122568400532e-05, 'memory/max_active (GiB)': 43.35, 'memory/max_allocated (GiB)': 43.35, 'memory/device_reserved (GiB)': 51.13, 'tokens_per_second_per_gpu': 1296.05, 'epoch': 1.62}
	84%\|████████████████████████████████████████████████████████████████████████████████████████████████████████████████▋ \| 37/44 [06:30<01:13, 10.53s/it] 86%\|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████▋ \| 38/44 [06:40<01:03, 10.54s/it] {'loss': 0.0149, 'grad_norm': 0.17279624938964844, 'learning_rate': 1.339745962155613e-05, 'memory/max_active (GiB)': 43.35, 'memory/max_allocated (GiB)': 43.35, 'memory/device_reserved (GiB)': 51.13, 'tokens_per_second_per_gpu': 1320.12, 'epoch': 1.67}
	86%\|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████▋ \| 38/44 [06:40<01:03, 10.54s/it] 89%\|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▊ \| 39/44 [06:51<00:52, 10.54s/it] {'loss': 0.0113, 'grad_norm': 0.1708693951368332, 'learning_rate': 9.903113209758096e-06, 'memory/max_active (GiB)': 43.35, 'memory/max_allocated (GiB)': 43.35, 'memory/device_reserved (GiB)': 51.13, 'tokens_per_second_per_gpu': 1333.73, 'epoch': 1.71}
	89%\|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▊ \| 39/44 [06:51<00:52, 10.54s/it] 91%\|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▊ \| 40/44 [07:01<00:42, 10.57s/it] {'loss': 0.0119, 'grad_norm': 0.15244145691394806, 'learning_rate': 6.9126251355795864e-06, 'memory/max_active (GiB)': 43.35, 'memory/max_allocated (GiB)': 43.35, 'memory/device_reserved (GiB)': 51.13, 'tokens_per_second_per_gpu': 1278.44, 'epoch': 1.76}
	91%\|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▊ \| 40/44 [07:01<00:42, 10.57s/it] 93%\|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▊ \| 41/44 [07:12<00:31, 10.57s/it] {'loss': 0.0121, 'grad_norm': 0.15926013886928558, 'learning_rate': 4.442719421385922e-06, 'memory/max_active (GiB)': 43.35, 'memory/max_allocated (GiB)': 43.35, 'memory/device_reserved (GiB)': 51.13, 'tokens_per_second_per_gpu': 1296.28, 'epoch': 1.8}
	93%\|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▊ \| 41/44 [07:12<00:31, 10.57s/it] 95%\|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▉ \| 42/44 [07:22<00:21, 10.58s/it] {'loss': 0.0186, 'grad_norm': 0.20554262399673462, 'learning_rate': 2.5072087818176382e-06, 'memory/max_active (GiB)': 43.35, 'memory/max_allocated (GiB)': 43.35, 'memory/device_reserved (GiB)': 51.13, 'tokens_per_second_per_gpu': 1198.58, 'epoch': 1.84}
	95%\|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▉ \| 42/44 [07:23<00:21, 10.58s/it] 98%\|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▉ \| 43/44 [07:33<00:10, 10.59s/it] {'loss': 0.02, 'grad_norm': 0.23918209969997406, 'learning_rate': 1.1169173774871478e-06, 'memory/max_active (GiB)': 43.35, 'memory/max_allocated (GiB)': 43.35, 'memory/device_reserved (GiB)': 51.13, 'tokens_per_second_per_gpu': 1198.53, 'epoch': 1.89}
	98%\|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▉ \| 43/44 [07:33<00:10, 10.59s/it] 100%\|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████\| 44/44 [07:44<00:00, 10.58s/it] {'loss': 0.0093, 'grad_norm': 0.1438334584236145, 'learning_rate': 2.7962028188198706e-07, 'memory/max_active (GiB)': 43.35, 'memory/max_allocated (GiB)': 43.35, 'memory/device_reserved (GiB)': 51.13, 'tokens_per_second_per_gpu': 1367.42, 'epoch': 1.93}
	100%\|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████\| 44/44 [07:44<00:00, 10.58s/it][2026-04-10 14:06:46,792] [INFO] [axolotl.core.trainers.base._save:671] [PID:7899] Saving model checkpoint to ./outputs/mymodel/checkpoint-44
	{'train_runtime': 472.0616, 'train_samples_per_second': 1.491, 'train_steps_per_second': 0.093, 'train_loss': 0.0675379387949678, 'memory/max_active (GiB)': 12.66, 'memory/max_allocated (GiB)': 12.66, 'memory/device_reserved (GiB)': 51.13, 'epoch': 1.93}
	100%\|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████\| 44/44 [07:52<00:00, 10.58s/it] 100%\|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████\| 44/44 [07:52<00:00, 10.73s/it]
	[2026-04-10 14:06:54,929] [INFO] [axolotl.train.save_trained_model:218] [PID:7899] Training completed! Saving trained model to ./outputs/mymodel.
	[2026-04-10 14:06:58,057] [INFO] [axolotl.train.save_trained_model:336] [PID:7899] Model successfully saved to ./outputs/mymodel