leosheng-ft-nemo-12b-mix

developer_uid: leosheng

submission_id: leosheng-ft-nemo-12b-mix_v1

model_name: leosheng-ft-nemo-12b-mix_v1

model_group: leosheng/ft-nemo-12b-mix

status: torndown

timestamp: 2025-02-14T04:51:26+00:00

num_battles: 5681

num_wins: 2597

celo_rating: 1240.41

family_friendly_score: 0.5748

family_friendly_standard_error: 0.006991494260885866

submission_type: basic

model_repo: leosheng/ft-nemo-12b-mix

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

display_name: leosheng-ft-nemo-12b-mix_v1

is_internal_developer: False

language_model: leosheng/ft-nemo-12b-mix

model_size: 13B

ranking_group: single

us_pacific_date: 2025-02-13

win_ratio: 0.45713782784721

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': 1024, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': '<|im_start|>system\n{memory}<|im_end|>\n', 'prompt_template': '<|im_start|>user\n{prompt}<|im_end|>\n', 'bot_template': '<|im_start|>assistant\n{bot_name}: {message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{user_name}: {message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n{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 leosheng-ft-nemo-12b-mix-v1-mkmlizer
Waiting for job on leosheng-ft-nemo-12b-mix-v1-mkmlizer to finish
leosheng-ft-nemo-12b-mix-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
leosheng-ft-nemo-12b-mix-v1-mkmlizer: ║     _____            __           __                                ║
leosheng-ft-nemo-12b-mix-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
leosheng-ft-nemo-12b-mix-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
leosheng-ft-nemo-12b-mix-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
leosheng-ft-nemo-12b-mix-v1-mkmlizer: ║       /___/                                                         ║
leosheng-ft-nemo-12b-mix-v1-mkmlizer: ║                                                                     ║
leosheng-ft-nemo-12b-mix-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
leosheng-ft-nemo-12b-mix-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
leosheng-ft-nemo-12b-mix-v1-mkmlizer: ║  https://mk1.ai                                                     ║
leosheng-ft-nemo-12b-mix-v1-mkmlizer: ║                                                                     ║
leosheng-ft-nemo-12b-mix-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
leosheng-ft-nemo-12b-mix-v1-mkmlizer: ║  belonging to:                                                      ║
leosheng-ft-nemo-12b-mix-v1-mkmlizer: ║                                                                     ║
leosheng-ft-nemo-12b-mix-v1-mkmlizer: ║  Chai Research Corp.                                                ║
leosheng-ft-nemo-12b-mix-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
leosheng-ft-nemo-12b-mix-v1-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
leosheng-ft-nemo-12b-mix-v1-mkmlizer: ║                                                                     ║
leosheng-ft-nemo-12b-mix-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
leosheng-ft-nemo-12b-mix-v1-mkmlizer: Downloaded to shared memory in 50.446s
leosheng-ft-nemo-12b-mix-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpyp4r_4n3, device:0
leosheng-ft-nemo-12b-mix-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
leosheng-ft-nemo-12b-mix-v1-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.
leosheng-ft-nemo-12b-mix-v1-mkmlizer:   tensors = torch.load(model_shard_filename, map_location=torch.device(self.device), mmap=True)
leosheng-ft-nemo-12b-mix-v1-mkmlizer: quantized model in 36.979s
leosheng-ft-nemo-12b-mix-v1-mkmlizer: Processed model leosheng/ft-nemo-12b-mix in 87.425s
leosheng-ft-nemo-12b-mix-v1-mkmlizer: creating bucket guanaco-mkml-models
leosheng-ft-nemo-12b-mix-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
leosheng-ft-nemo-12b-mix-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/leosheng-ft-nemo-12b-mix-v1
leosheng-ft-nemo-12b-mix-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/leosheng-ft-nemo-12b-mix-v1/config.json
leosheng-ft-nemo-12b-mix-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/leosheng-ft-nemo-12b-mix-v1/special_tokens_map.json
leosheng-ft-nemo-12b-mix-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/leosheng-ft-nemo-12b-mix-v1/tokenizer_config.json
leosheng-ft-nemo-12b-mix-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/leosheng-ft-nemo-12b-mix-v1/tokenizer.json
leosheng-ft-nemo-12b-mix-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/leosheng-ft-nemo-12b-mix-v1/flywheel_model.0.safetensors
leosheng-ft-nemo-12b-mix-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:09, 38.87it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:05, 62.90it/s]
Loading 0:   6%|▌         | 22/363 [00:00<00:05, 68.07it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:04, 72.61it/s]
Loading 0:  11%|█         | 40/363 [00:00<00:04, 75.71it/s]
Loading 0:  13%|█▎        | 49/363 [00:00<00:04, 77.03it/s]
Loading 0:  16%|█▌        | 58/363 [00:00<00:03, 76.46it/s]
Loading 0:  18%|█▊        | 66/363 [00:01<00:15, 18.88it/s]
Loading 0:  20%|█▉        | 72/363 [00:02<00:12, 22.50it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:10, 27.88it/s]
Loading 0:  24%|██▍       | 88/363 [00:02<00:07, 36.20it/s]
Loading 0:  27%|██▋       | 97/363 [00:02<00:06, 43.14it/s]
Loading 0:  29%|██▉       | 106/363 [00:02<00:05, 50.99it/s]
Loading 0:  32%|███▏      | 115/363 [00:02<00:04, 58.66it/s]
Loading 0:  34%|███▍      | 124/363 [00:02<00:03, 65.38it/s]
Loading 0:  37%|███▋      | 133/363 [00:02<00:03, 69.92it/s]
Loading 0:  39%|███▉      | 142/363 [00:04<00:11, 19.74it/s]
Loading 0:  42%|████▏     | 151/363 [00:04<00:08, 25.79it/s]
Loading 0:  44%|████▍     | 160/363 [00:04<00:06, 32.63it/s]
Loading 0:  47%|████▋     | 169/363 [00:04<00:05, 38.52it/s]
Loading 0:  49%|████▉     | 178/363 [00:04<00:04, 44.02it/s]
Loading 0:  52%|█████▏    | 187/363 [00:04<00:03, 51.28it/s]
Loading 0:  54%|█████▍    | 196/363 [00:04<00:02, 58.55it/s]
Loading 0:  56%|█████▋    | 205/363 [00:04<00:02, 65.05it/s]
Loading 0:  59%|█████▉    | 214/363 [00:04<00:02, 67.77it/s]
Loading 0:  61%|██████▏   | 223/363 [00:06<00:07, 19.97it/s]
Loading 0:  64%|██████▍   | 232/363 [00:06<00:05, 25.93it/s]
Loading 0:  66%|██████▋   | 241/363 [00:06<00:03, 31.60it/s]
Loading 0:  69%|██████▉   | 250/363 [00:06<00:02, 38.19it/s]
Loading 0:  71%|███████▏  | 259/363 [00:06<00:02, 45.67it/s]
Loading 0:  74%|███████▍  | 268/363 [00:06<00:01, 53.14it/s]
Loading 0:  76%|███████▋  | 277/363 [00:06<00:01, 59.68it/s]
Loading 0:  79%|███████▉  | 286/363 [00:06<00:01, 62.64it/s]
Loading 0:  81%|████████▏ | 295/363 [00:07<00:01, 63.62it/s]
Loading 0:  84%|████████▎ | 304/363 [00:08<00:02, 20.47it/s]
Loading 0:  86%|████████▌ | 313/363 [00:08<00:01, 26.19it/s]
Loading 0:  89%|████████▊ | 322/363 [00:08<00:01, 32.29it/s]
Loading 0:  91%|█████████ | 331/363 [00:08<00:00, 38.43it/s]
Loading 0:  94%|█████████▎| 340/363 [00:08<00:00, 46.20it/s]
Loading 0:  96%|█████████▌| 349/363 [00:08<00:00, 52.25it/s]
Loading 0:  99%|█████████▊| 358/363 [00:08<00:00, 59.09it/s]
                                                            
Job leosheng-ft-nemo-12b-mix-v1-mkmlizer completed after 114.95s with status: succeeded
Stopping job with name leosheng-ft-nemo-12b-mix-v1-mkmlizer
Pipeline stage MKMLizer completed in 115.41s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service leosheng-ft-nemo-12b-mix-v1
Waiting for inference service leosheng-ft-nemo-12b-mix-v1 to be ready
Inference service leosheng-ft-nemo-12b-mix-v1 ready after 170.57597708702087s
Pipeline stage MKMLDeployer completed in 171.08s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.290210008621216s
Received healthy response to inference request in 1.5134778022766113s
Received healthy response to inference request in 1.5218756198883057s
Received healthy response to inference request in 1.5215489864349365s
Received healthy response to inference request in 1.9229199886322021s
5 requests
0 failed requests
5th percentile: 1.5150920391082763
10th percentile: 1.5167062759399415
20th percentile: 1.5199347496032716
30th percentile: 1.5216143131256104
40th percentile: 1.521744966506958
50th percentile: 1.5218756198883057
60th percentile: 1.6822933673858642
70th percentile: 1.8427111148834228
80th percentile: 1.996377992630005
90th percentile: 2.1432940006256103
95th percentile: 2.216752004623413
99th percentile: 2.275518407821655
mean time: 1.7540064811706544
Pipeline stage StressChecker completed in 9.96s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyTriggerPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage OfflineFamilyFriendlyTriggerPipeline completed in 0.70s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 0.68s
Shutdown handler de-registered
leosheng-ft-nemo-12b-mix_v1 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyScorer
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 2774.02s
Shutdown handler de-registered
leosheng-ft-nemo-12b-mix_v1 status is now inactive due to auto deactivation removed underperforming models
leosheng-ft-nemo-12b-mix_v1 status is now torndown due to DeploymentManager action
leosheng-ft-nemo-12b-mix_v1 status is now torndown due to DeploymentManager action
leosheng-ft-nemo-12b-mix_v1 status is now torndown due to DeploymentManager action