developer_uid: sanchuanhehe
submission_id: sanchuanhehe-llama3-1-lora_v2
model_name: sanchuanhehe-llama3-1-lora_v1
model_group: sanchuanhehe/llama3.1_lo
status: torndown
timestamp: 2024-10-15T04:41:32+00:00
num_battles: 6696
num_wins: 3320
celo_rating: 1212.49
family_friendly_score: 0.5479192938209332
family_friendly_standard_error: 0.0062170038202021384
submission_type: basic
model_repo: sanchuanhehe/llama3.1_lora
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: sanchuanhehe-llama3-1-lora_v1
is_internal_developer: False
language_model: sanchuanhehe/llama3.1_lora
model_size: 8B
ranking_group: single
us_pacific_date: 2024-10-14
win_ratio: 0.4958183990442055
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': False}
Resubmit model
Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLizer
Starting job with name sanchuanhehe-llama3-1-lora-v2-mkmlizer
Waiting for job on sanchuanhehe-llama3-1-lora-v2-mkmlizer to finish
sanchuanhehe-llama3-1-lora-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sanchuanhehe-llama3-1-lora-v2-mkmlizer: ║ _____ __ __ ║
sanchuanhehe-llama3-1-lora-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
sanchuanhehe-llama3-1-lora-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
sanchuanhehe-llama3-1-lora-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
sanchuanhehe-llama3-1-lora-v2-mkmlizer: ║ /___/ ║
sanchuanhehe-llama3-1-lora-v2-mkmlizer: ║ ║
sanchuanhehe-llama3-1-lora-v2-mkmlizer: ║ Version: 0.11.12 ║
sanchuanhehe-llama3-1-lora-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
sanchuanhehe-llama3-1-lora-v2-mkmlizer: ║ https://mk1.ai ║
sanchuanhehe-llama3-1-lora-v2-mkmlizer: ║ ║
sanchuanhehe-llama3-1-lora-v2-mkmlizer: ║ The license key for the current software has been verified as ║
sanchuanhehe-llama3-1-lora-v2-mkmlizer: ║ belonging to: ║
sanchuanhehe-llama3-1-lora-v2-mkmlizer: ║ ║
sanchuanhehe-llama3-1-lora-v2-mkmlizer: ║ Chai Research Corp. ║
sanchuanhehe-llama3-1-lora-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
sanchuanhehe-llama3-1-lora-v2-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
sanchuanhehe-llama3-1-lora-v2-mkmlizer: ║ ║
sanchuanhehe-llama3-1-lora-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
sanchuanhehe-llama3-1-lora-v2-mkmlizer: Downloaded to shared memory in 39.586s
sanchuanhehe-llama3-1-lora-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpt08l4klu, device:0
sanchuanhehe-llama3-1-lora-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
sanchuanhehe-llama3-1-lora-v2-mkmlizer: /opt/conda/lib/python3.10/site-packages/mk1/flywheel/functional/loader.py:55: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
sanchuanhehe-llama3-1-lora-v2-mkmlizer: tensors = torch.load(model_shard_filename, map_location=torch.device(self.device), mmap=True)
sanchuanhehe-llama3-1-lora-v2-mkmlizer: quantized model in 26.607s
sanchuanhehe-llama3-1-lora-v2-mkmlizer: Processed model sanchuanhehe/llama3.1_lora in 66.194s
sanchuanhehe-llama3-1-lora-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sanchuanhehe-llama3-1-lora-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sanchuanhehe-llama3-1-lora-v2
sanchuanhehe-llama3-1-lora-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sanchuanhehe-llama3-1-lora-v2/special_tokens_map.json
sanchuanhehe-llama3-1-lora-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sanchuanhehe-llama3-1-lora-v2/config.json
sanchuanhehe-llama3-1-lora-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sanchuanhehe-llama3-1-lora-v2/tokenizer_config.json
sanchuanhehe-llama3-1-lora-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sanchuanhehe-llama3-1-lora-v2/tokenizer.json
sanchuanhehe-llama3-1-lora-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sanchuanhehe-llama3-1-lora-v2/flywheel_model.0.safetensors
sanchuanhehe-llama3-1-lora-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 2%|▏ | 7/291 [00:00<00:05, 48.87it/s] Loading 0: 6%|▌ | 17/291 [00:00<00:03, 74.08it/s] Loading 0: 9%|▊ | 25/291 [00:00<00:03, 75.73it/s] Loading 0: 12%|█▏ | 34/291 [00:00<00:03, 78.08it/s] Loading 0: 15%|█▍ | 43/291 [00:00<00:03, 81.48it/s] Loading 0: 18%|█▊ | 52/291 [00:00<00:02, 82.73it/s] Loading 0: 21%|██ | 61/291 [00:00<00:02, 82.12it/s] Loading 0: 24%|██▍ | 70/291 [00:00<00:02, 76.79it/s] Loading 0: 27%|██▋ | 79/291 [00:01<00:02, 78.89it/s] Loading 0: 30%|██▉ | 87/291 [00:02<00:09, 20.72it/s] Loading 0: 32%|███▏ | 94/291 [00:02<00:07, 25.25it/s] Loading 0: 35%|███▌ | 103/291 [00:02<00:05, 32.71it/s] Loading 0: 38%|███▊ | 112/291 [00:02<00:04, 40.63it/s] Loading 0: 42%|████▏ | 121/291 [00:02<00:03, 47.40it/s] Loading 0: 45%|████▍ | 130/291 [00:02<00:03, 52.02it/s] Loading 0: 48%|████▊ | 139/291 [00:02<00:02, 57.09it/s] Loading 0: 51%|█████ | 148/291 [00:02<00:02, 63.31it/s] Loading 0: 54%|█████▍ | 157/291 [00:03<00:01, 68.16it/s] Loading 0: 57%|█████▋ | 166/291 [00:03<00:01, 72.24it/s] Loading 0: 60%|██████ | 175/291 [00:03<00:01, 75.58it/s] Loading 0: 63%|██████▎ | 184/291 [00:03<00:01, 74.72it/s] Loading 0: 66%|██████▌ | 192/291 [00:04<00:04, 20.87it/s] Loading 0: 68%|██████▊ | 198/291 [00:04<00:03, 24.33it/s] Loading 0: 70%|███████ | 205/291 [00:04<00:02, 28.99it/s] Loading 0: 74%|███████▎ | 214/291 [00:04<00:02, 36.42it/s] Loading 0: 77%|███████▋ | 223/291 [00:04<00:01, 43.85it/s] Loading 0: 80%|███████▉ | 232/291 [00:05<00:01, 51.20it/s] Loading 0: 83%|████████▎ | 241/291 [00:05<00:00, 58.31it/s] Loading 0: 86%|████████▌ | 250/291 [00:05<00:00, 64.12it/s] Loading 0: 89%|████████▉ | 259/291 [00:05<00:00, 69.51it/s] Loading 0: 92%|█████████▏| 268/291 [00:05<00:00, 72.46it/s] Loading 0: 95%|█████████▌| 277/291 [00:05<00:00, 75.89it/s] Loading 0: 98%|█████████▊| 286/291 [00:05<00:00, 77.74it/s]
Job sanchuanhehe-llama3-1-lora-v2-mkmlizer completed after 84.02s with status: succeeded
Stopping job with name sanchuanhehe-llama3-1-lora-v2-mkmlizer
Pipeline stage MKMLizer completed in 84.54s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service sanchuanhehe-llama3-1-lora-v2
Waiting for inference service sanchuanhehe-llama3-1-lora-v2 to be ready
Inference service sanchuanhehe-llama3-1-lora-v2 ready after 160.8394420146942s
Pipeline stage MKMLDeployer completed in 161.37s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.8506619930267334s
Received healthy response to inference request in 1.237701654434204s
Received healthy response to inference request in 1.1885530948638916s
Received healthy response to inference request in 1.195432186126709s
Received healthy response to inference request in 1.3932456970214844s
5 requests
0 failed requests
5th percentile: 1.189928913116455
10th percentile: 1.1913047313690186
20th percentile: 1.1940563678741456
30th percentile: 1.203886079788208
40th percentile: 1.220793867111206
50th percentile: 1.237701654434204
60th percentile: 1.2999192714691161
70th percentile: 1.3621368885040284
80th percentile: 1.4847289562225343
90th percentile: 1.6676954746246337
95th percentile: 1.7591787338256835
99th percentile: 1.8323653411865235
mean time: 1.3731189250946045
Pipeline stage StressChecker completed in 8.93s
Shutdown handler de-registered
sanchuanhehe-llama3-1-lora_v2 status is now deployed due to DeploymentManager action
sanchuanhehe-llama3-1-lora_v2 status is now inactive due to auto deactivation removed underperforming models
sanchuanhehe-llama3-1-lora_v2 status is now torndown due to DeploymentManager action