developer_uid: azuruce
submission_id: gryphe-mythomax-l2-13b_v1
model_name: gryphe-mythomax-l2-13b_v1
model_group: gryphe/mythomax-l2-13b
status: torndown
timestamp: 2025-01-08T21:21:40+00:00
num_battles: 13849
num_wins: 5559
celo_rating: 1202.82
family_friendly_score: 0.5908
family_friendly_standard_error: 0.006953493510459329
submission_type: basic
model_repo: gryphe/mythomax-l2-13b
model_architecture: LlamaForCausalLM
model_num_parameters: 13015864320.0
best_of: 4
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.5499503803110813, 'latency_mean': 1.8182892966270447, 'latency_p50': 1.8136100769042969, 'latency_p90': 2.0120137691497804}, {'batch_size': 3, 'throughput': 0.9571092666985292, 'latency_mean': 3.1237807762622833, 'latency_p50': 3.124259829521179, 'latency_p90': 3.3962780952453615}, {'batch_size': 5, 'throughput': 1.152284688480909, 'latency_mean': 4.307360920906067, 'latency_p50': 4.316433072090149, 'latency_p90': 4.8318401098251345}, {'batch_size': 6, 'throughput': 1.2311923209014553, 'latency_mean': 4.844723037481308, 'latency_p50': 4.839297533035278, 'latency_p90': 5.471284937858582}, {'batch_size': 8, 'throughput': 1.30975565147174, 'latency_mean': 6.045328344106674, 'latency_p50': 6.0504902601242065, 'latency_p90': 6.772319078445435}, {'batch_size': 10, 'throughput': 1.332451695884435, 'latency_mean': 7.444701766967773, 'latency_p50': 7.445636510848999, 'latency_p90': 8.38045139312744}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: gryphe-mythomax-l2-13b_v1
is_internal_developer: True
language_model: gryphe/mythomax-l2-13b
model_size: 13B
ranking_group: single
throughput_3p7s: 1.07
us_pacific_date: 2025-01-08
win_ratio: 0.4014008231641274
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 100, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '</s>', '####', 'Bot:', 'User:', 'You:', 'Me', '<|im_end|>', '<|eot_id|>'], 'max_input_tokens': 1024, 'best_of': 4, 'max_output_tokens': 64}
formatter: {'memory_template': '', 'prompt_template': '', '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 gryphe-mythomax-l2-13b-v1-mkmlizer
Waiting for job on gryphe-mythomax-l2-13b-v1-mkmlizer to finish
gryphe-mythomax-l2-13b-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
gryphe-mythomax-l2-13b-v1-mkmlizer: ║     _____            __           __                                ║
gryphe-mythomax-l2-13b-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
gryphe-mythomax-l2-13b-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
gryphe-mythomax-l2-13b-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
gryphe-mythomax-l2-13b-v1-mkmlizer: ║       /___/                                                         ║
gryphe-mythomax-l2-13b-v1-mkmlizer: ║                                                                     ║
gryphe-mythomax-l2-13b-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
gryphe-mythomax-l2-13b-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
gryphe-mythomax-l2-13b-v1-mkmlizer: ║  https://mk1.ai                                                     ║
gryphe-mythomax-l2-13b-v1-mkmlizer: ║                                                                     ║
gryphe-mythomax-l2-13b-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
gryphe-mythomax-l2-13b-v1-mkmlizer: ║  belonging to:                                                      ║
gryphe-mythomax-l2-13b-v1-mkmlizer: ║                                                                     ║
gryphe-mythomax-l2-13b-v1-mkmlizer: ║  Chai Research Corp.                                                ║
gryphe-mythomax-l2-13b-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
gryphe-mythomax-l2-13b-v1-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
gryphe-mythomax-l2-13b-v1-mkmlizer: ║                                                                     ║
gryphe-mythomax-l2-13b-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
gryphe-mythomax-l2-13b-v1-mkmlizer: Downloaded to shared memory in 83.268s
gryphe-mythomax-l2-13b-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpxcd69ob9, device:0
gryphe-mythomax-l2-13b-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
gryphe-mythomax-l2-13b-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.
gryphe-mythomax-l2-13b-v1-mkmlizer:   tensors = torch.load(model_shard_filename, map_location=torch.device(self.device), mmap=True)
gryphe-mythomax-l2-13b-v1-mkmlizer: quantized model in 27.311s
gryphe-mythomax-l2-13b-v1-mkmlizer: Processed model gryphe/mythomax-l2-13b in 110.579s
gryphe-mythomax-l2-13b-v1-mkmlizer: creating bucket guanaco-mkml-models
gryphe-mythomax-l2-13b-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
gryphe-mythomax-l2-13b-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/gryphe-mythomax-l2-13b-v1
gryphe-mythomax-l2-13b-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/gryphe-mythomax-l2-13b-v1/config.json
gryphe-mythomax-l2-13b-v1-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/gryphe-mythomax-l2-13b-v1/added_tokens.json
gryphe-mythomax-l2-13b-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/gryphe-mythomax-l2-13b-v1/special_tokens_map.json
gryphe-mythomax-l2-13b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/gryphe-mythomax-l2-13b-v1/tokenizer_config.json
gryphe-mythomax-l2-13b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/gryphe-mythomax-l2-13b-v1/tokenizer.model
gryphe-mythomax-l2-13b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/gryphe-mythomax-l2-13b-v1/tokenizer.json
gryphe-mythomax-l2-13b-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/gryphe-mythomax-l2-13b-v1/flywheel_model.0.safetensors
gryphe-mythomax-l2-13b-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 7/363 [00:00<00:06, 51.13it/s]
Loading 0:   6%|▌         | 22/363 [00:00<00:04, 81.57it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:10, 31.98it/s]
Loading 0:  11%|█         | 40/363 [00:00<00:07, 41.32it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:06, 50.55it/s]
Loading 0:  16%|█▌        | 57/363 [00:01<00:09, 31.04it/s]
Loading 0:  17%|█▋        | 63/363 [00:01<00:08, 34.11it/s]
Loading 0:  20%|█▉        | 71/363 [00:01<00:07, 41.54it/s]
Loading 0:  22%|██▏       | 79/363 [00:01<00:05, 48.79it/s]
Loading 0:  24%|██▎       | 86/363 [00:02<00:09, 30.09it/s]
Loading 0:  26%|██▌       | 94/363 [00:02<00:07, 36.60it/s]
Loading 0:  29%|██▉       | 106/363 [00:02<00:05, 46.89it/s]
Loading 0:  31%|███▏      | 114/363 [00:03<00:07, 31.60it/s]
Loading 0:  33%|███▎      | 121/363 [00:03<00:06, 35.29it/s]
Loading 0:  36%|███▌      | 130/363 [00:03<00:05, 43.18it/s]
Loading 0:  39%|███▉      | 142/363 [00:03<00:07, 29.74it/s]
Loading 0:  43%|████▎     | 157/363 [00:04<00:04, 41.80it/s]
Loading 0:  46%|████▌     | 166/363 [00:04<00:04, 48.45it/s]
Loading 0:  48%|████▊     | 174/363 [00:04<00:05, 33.02it/s]
Loading 0:  50%|████▉     | 180/363 [00:04<00:05, 35.11it/s]
Loading 0:  53%|█████▎    | 193/363 [00:04<00:03, 46.05it/s]
Loading 0:  55%|█████▌    | 200/363 [00:05<00:05, 31.18it/s]
Loading 0:  56%|█████▋    | 205/363 [00:05<00:04, 33.27it/s]
Loading 0:  61%|██████    | 220/363 [00:05<00:02, 47.73it/s]
Loading 0:  63%|██████▎   | 229/363 [00:05<00:02, 52.92it/s]
Loading 0:  65%|██████▌   | 236/363 [00:06<00:03, 33.86it/s]
Loading 0:  68%|██████▊   | 247/363 [00:06<00:02, 41.73it/s]
Loading 0:  71%|███████   | 256/363 [00:06<00:02, 49.06it/s]
Loading 0:  72%|███████▏  | 263/363 [00:06<00:03, 31.19it/s]
Loading 0:  74%|███████▍  | 269/363 [00:07<00:02, 34.64it/s]
Loading 0:  76%|███████▋  | 277/363 [00:07<00:02, 41.28it/s]
Loading 0:  79%|███████▉  | 286/363 [00:07<00:02, 28.07it/s]
Loading 0:  81%|████████▏ | 295/363 [00:07<00:01, 35.22it/s]
Loading 0:  84%|████████▎ | 304/363 [00:07<00:01, 43.15it/s]
Loading 0:  87%|████████▋ | 314/363 [00:08<00:01, 31.82it/s]
Loading 0:  89%|████████▊ | 322/363 [00:08<00:01, 36.96it/s]
Loading 0:  93%|█████████▎| 337/363 [00:08<00:00, 50.86it/s]
Loading 0:  95%|█████████▍| 344/363 [00:09<00:00, 36.19it/s]
Loading 0:  96%|█████████▋| 350/363 [00:09<00:00, 39.00it/s]
Loading 0:  99%|█████████▊| 358/363 [00:09<00:00, 45.47it/s]
                                                            

Job gryphe-mythomax-l2-13b-v1-mkmlizer completed after 134.78s with status: succeeded
Stopping job with name gryphe-mythomax-l2-13b-v1-mkmlizer
Pipeline stage MKMLizer completed in 135.30s
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 gryphe-mythomax-l2-13b-v1
Waiting for inference service gryphe-mythomax-l2-13b-v1 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service gryphe-mythomax-l2-13b-v1 ready after 362.0327091217041s
Pipeline stage MKMLDeployer completed in 362.61s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9916021823883057s
Received healthy response to inference request in 1.4610075950622559s
Received healthy response to inference request in 1.7216484546661377s
Received healthy response to inference request in 1.4046709537506104s
Received healthy response to inference request in 1.999434232711792s
5 requests
0 failed requests
5th percentile: 1.4159382820129394
10th percentile: 1.4272056102752686
20th percentile: 1.4497402667999268
30th percentile: 1.5131357669830323
40th percentile: 1.617392110824585
50th percentile: 1.7216484546661377
60th percentile: 1.829629945755005
70th percentile: 1.937611436843872
80th percentile: 1.993168592453003
90th percentile: 1.9963014125823975
95th percentile: 1.9978678226470947
99th percentile: 1.9991209506988525
mean time: 1.7156726837158203
Pipeline stage StressChecker completed in 10.05s
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 0.75s
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 0.99s
Shutdown handler de-registered
gryphe-mythomax-l2-13b_v1 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Skipping teardown as no inference service was successfully deployed
Pipeline stage MKMLProfilerDeleter completed in 0.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service gryphe-mythomax-l2-13b-v1-profiler
Waiting for inference service gryphe-mythomax-l2-13b-v1-profiler to be ready
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 3096.70s
Shutdown handler de-registered
gryphe-mythomax-l2-13b_v1 status is now inactive due to auto deactivation removed underperforming models
gryphe-mythomax-l2-13b_v1 status is now torndown due to DeploymentManager action
ChatRequest
Generation Params
Prompt Formatter
Chat History
ChatMessage 1