developer_uid: leosheng
submission_id: alexxi19-ft-v1-nemo-base_v2
model_name: alexxi19-ft-v1-nemo-base_v1
model_group: alexxi19/ft-v1-nemo-base
status: torndown
timestamp: 2025-02-01T16:56:54+00:00
num_battles: 7588
num_wins: 3486
celo_rating: 1241.16
family_friendly_score: 0.5764
family_friendly_standard_error: 0.006988033199692171
submission_type: basic
model_repo: alexxi19/ft-v1-nemo-base
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
reward_model: default
display_name: alexxi19-ft-v1-nemo-base_v1
is_internal_developer: False
language_model: alexxi19/ft-v1-nemo-base
model_size: 13B
ranking_group: single
us_pacific_date: 2025-02-01
win_ratio: 0.45940959409594095
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': True}
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 alexxi19-ft-v1-nemo-base-v2-mkmlizer
Waiting for job on alexxi19-ft-v1-nemo-base-v2-mkmlizer to finish
alexxi19-ft-v1-nemo-base-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
alexxi19-ft-v1-nemo-base-v2-mkmlizer: ║ _____ __ __ ║
alexxi19-ft-v1-nemo-base-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
alexxi19-ft-v1-nemo-base-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
alexxi19-ft-v1-nemo-base-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
alexxi19-ft-v1-nemo-base-v2-mkmlizer: ║ /___/ ║
alexxi19-ft-v1-nemo-base-v2-mkmlizer: ║ ║
alexxi19-ft-v1-nemo-base-v2-mkmlizer: ║ Version: 0.11.12 ║
alexxi19-ft-v1-nemo-base-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
alexxi19-ft-v1-nemo-base-v2-mkmlizer: ║ https://mk1.ai ║
alexxi19-ft-v1-nemo-base-v2-mkmlizer: ║ ║
alexxi19-ft-v1-nemo-base-v2-mkmlizer: ║ The license key for the current software has been verified as ║
alexxi19-ft-v1-nemo-base-v2-mkmlizer: ║ belonging to: ║
alexxi19-ft-v1-nemo-base-v2-mkmlizer: ║ ║
alexxi19-ft-v1-nemo-base-v2-mkmlizer: ║ Chai Research Corp. ║
alexxi19-ft-v1-nemo-base-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
alexxi19-ft-v1-nemo-base-v2-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
alexxi19-ft-v1-nemo-base-v2-mkmlizer: ║ ║
alexxi19-ft-v1-nemo-base-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
alexxi19-ft-v1-nemo-base-v2-mkmlizer: Downloaded to shared memory in 46.378s
alexxi19-ft-v1-nemo-base-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp9egoofw9, device:0
alexxi19-ft-v1-nemo-base-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
alexxi19-ft-v1-nemo-base-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.
alexxi19-ft-v1-nemo-base-v2-mkmlizer: tensors = torch.load(model_shard_filename, map_location=torch.device(self.device), mmap=True)
alexxi19-ft-v1-nemo-base-v2-mkmlizer: quantized model in 35.405s
alexxi19-ft-v1-nemo-base-v2-mkmlizer: Processed model alexxi19/ft-v1-nemo-base in 81.783s
alexxi19-ft-v1-nemo-base-v2-mkmlizer: creating bucket guanaco-mkml-models
alexxi19-ft-v1-nemo-base-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-base-v2/config.json
alexxi19-ft-v1-nemo-base-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-base-v2/special_tokens_map.json
alexxi19-ft-v1-nemo-base-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-base-v2/tokenizer_config.json
alexxi19-ft-v1-nemo-base-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-base-v2/tokenizer.json
alexxi19-ft-v1-nemo-base-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-base-v2/flywheel_model.0.safetensors
alexxi19-ft-v1-nemo-base-v2-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 2%|▏ | 7/363 [00:00<00:07, 50.73it/s] Loading 0: 5%|▍ | 17/363 [00:00<00:04, 75.44it/s] Loading 0: 9%|▊ | 31/363 [00:00<00:03, 87.09it/s] Loading 0: 11%|█ | 40/363 [00:00<00:03, 85.58it/s] Loading 0: 13%|█▎ | 49/363 [00:00<00:03, 84.64it/s] Loading 0: 16%|█▋ | 59/363 [00:00<00:03, 89.15it/s] Loading 0: 19%|█▊ | 68/363 [00:01<00:14, 21.03it/s] Loading 0: 21%|██ | 76/363 [00:01<00:10, 26.39it/s] Loading 0: 23%|██▎ | 85/363 [00:02<00:08, 33.17it/s] Loading 0: 26%|██▌ | 94/363 [00:02<00:06, 40.97it/s] Loading 0: 29%|██▉ | 105/363 [00:02<00:04, 52.37it/s] Loading 0: 32%|███▏ | 115/363 [00:02<00:04, 56.76it/s] Loading 0: 34%|███▍ | 124/363 [00:02<00:03, 62.51it/s] Loading 0: 37%|███▋ | 133/363 [00:02<00:03, 67.45it/s] Loading 0: 39%|███▉ | 142/363 [00:03<00:10, 20.72it/s] Loading 0: 42%|████▏ | 152/363 [00:03<00:07, 27.67it/s] Loading 0: 44%|████▍ | 160/363 [00:04<00:06, 33.12it/s] Loading 0: 47%|████▋ | 169/363 [00:04<00:04, 40.07it/s] Loading 0: 49%|████▉ | 178/363 [00:04<00:03, 48.02it/s] Loading 0: 52%|█████▏ | 188/363 [00:04<00:03, 57.47it/s] Loading 0: 56%|█████▌ | 202/363 [00:04<00:02, 68.12it/s] Loading 0: 58%|█████▊ | 211/363 [00:04<00:02, 69.77it/s] Loading 0: 61%|██████ | 220/363 [00:04<00:01, 72.33it/s] Loading 0: 63%|██████▎ | 229/363 [00:05<00:06, 21.49it/s] Loading 0: 66%|██████▌ | 238/363 [00:05<00:04, 27.47it/s] Loading 0: 68%|██████▊ | 247/363 [00:06<00:03, 33.92it/s] Loading 0: 71%|███████ | 256/363 [00:06<00:02, 41.27it/s] Loading 0: 74%|███████▍ | 268/363 [00:06<00:01, 49.94it/s] Loading 0: 77%|███████▋ | 278/363 [00:06<00:01, 58.46it/s] Loading 0: 79%|███████▉ | 287/363 [00:06<00:01, 62.52it/s] Loading 0: 82%|████████▏ | 296/363 [00:06<00:00, 67.31it/s] Loading 0: 84%|████████▍ | 305/363 [00:07<00:02, 21.17it/s] Loading 0: 86%|████████▌ | 313/363 [00:07<00:01, 25.76it/s] Loading 0: 89%|████████▊ | 322/363 [00:08<00:01, 32.16it/s] Loading 0: 93%|█████████▎| 337/363 [00:08<00:00, 45.16it/s] Loading 0: 95%|█████████▌| 346/363 [00:08<00:00, 51.11it/s] Loading 0: 98%|█████████▊| 355/363 [00:08<00:00, 57.53it/s]
Job alexxi19-ft-v1-nemo-base-v2-mkmlizer completed after 114.71s with status: succeeded
Stopping job with name alexxi19-ft-v1-nemo-base-v2-mkmlizer
Pipeline stage MKMLizer completed in 115.21s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service alexxi19-ft-v1-nemo-base-v2
Waiting for inference service alexxi19-ft-v1-nemo-base-v2 to be ready
Inference service alexxi19-ft-v1-nemo-base-v2 ready after 180.93328309059143s
Pipeline stage MKMLDeployer completed in 181.50s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.337864637374878s
Received healthy response to inference request in 1.8448553085327148s
Received healthy response to inference request in 1.5538487434387207s
Received healthy response to inference request in 1.7262227535247803s
Received healthy response to inference request in 1.1495447158813477s
5 requests
0 failed requests
5th percentile: 1.2304055213928222
10th percentile: 1.3112663269042968
20th percentile: 1.4729879379272461
30th percentile: 1.5883235454559326
40th percentile: 1.6572731494903565
50th percentile: 1.7262227535247803
60th percentile: 1.7736757755279542
70th percentile: 1.8211287975311279
80th percentile: 1.9434571743011475
90th percentile: 2.1406609058380126
95th percentile: 2.239262771606445
99th percentile: 2.3181442642211914
mean time: 1.7224672317504883
Pipeline stage StressChecker completed in 10.33s
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 0.67s
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
alexxi19-ft-v1-nemo-base_v2 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 2612.04s
Shutdown handler de-registered
alexxi19-ft-v1-nemo-base_v2 status is now inactive due to auto deactivation removed underperforming models
alexxi19-ft-v1-nemo-base_v2 status is now torndown due to DeploymentManager action