developer_uid: duoding
submission_id: nousresearch-hermes-3-ll_5147_v1
model_name: nousresearch-hermes-3-ll_5147_v1
model_group: NousResearch/Hermes-3-Ll
status: inactive
timestamp: 2024-12-12T23:45:39+00:00
num_battles: 6092
num_wins: 2916
celo_rating: 1241.42
family_friendly_score: 0.5760000000000001
family_friendly_standard_error: 0.0069889054937092975
submission_type: basic
model_repo: NousResearch/Hermes-3-Llama-3.1-8B
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.8680574550337825, 'latency_mean': 1.1519266033172608, 'latency_p50': 1.1497162580490112, 'latency_p90': 1.275426411628723}, {'batch_size': 4, 'throughput': 1.8803859328508696, 'latency_mean': 2.1183834874629976, 'latency_p50': 2.108828544616699, 'latency_p90': 2.338594913482666}, {'batch_size': 5, 'throughput': 2.0149290375917985, 'latency_mean': 2.4641777861118315, 'latency_p50': 2.445120334625244, 'latency_p90': 2.785765361785889}, {'batch_size': 8, 'throughput': 2.268912394989299, 'latency_mean': 3.502115181684494, 'latency_p50': 3.4903193712234497, 'latency_p90': 3.931230068206787}, {'batch_size': 10, 'throughput': 2.3396497802039105, 'latency_mean': 4.242221978902816, 'latency_p50': 4.292607069015503, 'latency_p90': 4.722537088394165}, {'batch_size': 12, 'throughput': 2.406055263708967, 'latency_mean': 4.933524452447891, 'latency_p50': 4.939531922340393, 'latency_p90': 5.63299925327301}, {'batch_size': 15, 'throughput': 2.396369720729923, 'latency_mean': 6.1716093146801, 'latency_p50': 6.189255118370056, 'latency_p90': 6.94386727809906}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: nousresearch-hermes-3-ll_5147_v1
is_internal_developer: False
language_model: NousResearch/Hermes-3-Llama-3.1-8B
model_size: 8B
ranking_group: single
throughput_3p7s: 2.31
us_pacific_date: 2024-12-12
win_ratio: 0.47866053841103084
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': '', '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 nousresearch-hermes-3-ll-5147-v1-mkmlizer
Waiting for job on nousresearch-hermes-3-ll-5147-v1-mkmlizer to finish
nousresearch-hermes-3-ll-5147-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
nousresearch-hermes-3-ll-5147-v1-mkmlizer: ║ _____ __ __ ║
nousresearch-hermes-3-ll-5147-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
nousresearch-hermes-3-ll-5147-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
nousresearch-hermes-3-ll-5147-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
nousresearch-hermes-3-ll-5147-v1-mkmlizer: ║ /___/ ║
nousresearch-hermes-3-ll-5147-v1-mkmlizer: ║ ║
nousresearch-hermes-3-ll-5147-v1-mkmlizer: ║ Version: 0.11.12 ║
nousresearch-hermes-3-ll-5147-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
nousresearch-hermes-3-ll-5147-v1-mkmlizer: ║ https://mk1.ai ║
nousresearch-hermes-3-ll-5147-v1-mkmlizer: ║ ║
nousresearch-hermes-3-ll-5147-v1-mkmlizer: ║ The license key for the current software has been verified as ║
nousresearch-hermes-3-ll-5147-v1-mkmlizer: ║ belonging to: ║
nousresearch-hermes-3-ll-5147-v1-mkmlizer: ║ ║
nousresearch-hermes-3-ll-5147-v1-mkmlizer: ║ Chai Research Corp. ║
nousresearch-hermes-3-ll-5147-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
nousresearch-hermes-3-ll-5147-v1-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
nousresearch-hermes-3-ll-5147-v1-mkmlizer: ║ ║
nousresearch-hermes-3-ll-5147-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
nousresearch-hermes-3-ll-5147-v1-mkmlizer: Downloaded to shared memory in 21.762s
nousresearch-hermes-3-ll-5147-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpmezrd0yp, device:0
nousresearch-hermes-3-ll-5147-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
nousresearch-hermes-3-ll-5147-v1-mkmlizer: quantized model in 26.921s
nousresearch-hermes-3-ll-5147-v1-mkmlizer: Processed model NousResearch/Hermes-3-Llama-3.1-8B in 48.684s
nousresearch-hermes-3-ll-5147-v1-mkmlizer: creating bucket guanaco-mkml-models
nousresearch-hermes-3-ll-5147-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
nousresearch-hermes-3-ll-5147-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/nousresearch-hermes-3-ll-5147-v1
nousresearch-hermes-3-ll-5147-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/nousresearch-hermes-3-ll-5147-v1/config.json
nousresearch-hermes-3-ll-5147-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/nousresearch-hermes-3-ll-5147-v1/special_tokens_map.json
nousresearch-hermes-3-ll-5147-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/nousresearch-hermes-3-ll-5147-v1/tokenizer_config.json
nousresearch-hermes-3-ll-5147-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/nousresearch-hermes-3-ll-5147-v1/tokenizer.json
nousresearch-hermes-3-ll-5147-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/nousresearch-hermes-3-ll-5147-v1/flywheel_model.0.safetensors
nousresearch-hermes-3-ll-5147-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 2%|▏ | 5/291 [00:00<00:08, 32.80it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:05, 55.51it/s] Loading 0: 7%|▋ | 20/291 [00:00<00:05, 54.07it/s] Loading 0: 9%|▉ | 26/291 [00:00<00:05, 50.93it/s] Loading 0: 11%|█ | 32/291 [00:00<00:06, 42.53it/s] Loading 0: 14%|█▎ | 40/291 [00:00<00:04, 50.87it/s] Loading 0: 16%|█▌ | 46/291 [00:00<00:05, 43.80it/s] Loading 0: 18%|█▊ | 51/291 [00:01<00:05, 42.95it/s] Loading 0: 20%|█▉ | 58/291 [00:01<00:04, 47.82it/s] Loading 0: 22%|██▏ | 64/291 [00:01<00:05, 44.08it/s] Loading 0: 24%|██▎ | 69/291 [00:01<00:05, 43.28it/s] Loading 0: 26%|██▌ | 75/291 [00:01<00:04, 46.62it/s] Loading 0: 27%|██▋ | 80/291 [00:01<00:04, 45.45it/s] Loading 0: 29%|██▉ | 85/291 [00:02<00:06, 31.52it/s] Loading 0: 31%|███▏ | 91/291 [00:02<00:05, 33.65it/s] Loading 0: 33%|███▎ | 95/291 [00:02<00:05, 33.38it/s] Loading 0: 35%|███▌ | 103/291 [00:02<00:04, 42.57it/s] Loading 0: 37%|███▋ | 108/291 [00:02<00:04, 43.62it/s] Loading 0: 39%|███▉ | 113/291 [00:02<00:04, 36.48it/s] Loading 0: 42%|████▏ | 121/291 [00:02<00:03, 44.64it/s] Loading 0: 44%|████▎ | 127/291 [00:02<00:03, 42.81it/s] Loading 0: 45%|████▌ | 132/291 [00:03<00:03, 42.13it/s] Loading 0: 48%|████▊ | 139/291 [00:03<00:03, 47.22it/s] Loading 0: 49%|████▉ | 144/291 [00:03<00:03, 47.87it/s] Loading 0: 51%|█████ | 149/291 [00:03<00:03, 41.09it/s] Loading 0: 54%|█████▍ | 157/291 [00:03<00:02, 48.45it/s] Loading 0: 56%|█████▌ | 163/291 [00:03<00:02, 46.42it/s] Loading 0: 58%|█████▊ | 168/291 [00:03<00:02, 42.42it/s] Loading 0: 60%|█████▉ | 174/291 [00:03<00:02, 46.50it/s] Loading 0: 62%|██████▏ | 179/291 [00:04<00:02, 46.85it/s] Loading 0: 63%|██████▎ | 184/291 [00:04<00:02, 45.14it/s] Loading 0: 65%|██████▍ | 189/291 [00:04<00:03, 28.10it/s] Loading 0: 67%|██████▋ | 194/291 [00:04<00:03, 30.89it/s] Loading 0: 69%|██████▉ | 202/291 [00:04<00:02, 40.00it/s] Loading 0: 71%|███████▏ | 208/291 [00:04<00:02, 40.58it/s] Loading 0: 73%|███████▎ | 213/291 [00:05<00:01, 39.65it/s] Loading 0: 76%|███████▌ | 220/291 [00:05<00:01, 45.31it/s] Loading 0: 78%|███████▊ | 226/291 [00:05<00:01, 44.29it/s] Loading 0: 79%|███████▉ | 231/291 [00:05<00:01, 43.60it/s] Loading 0: 81%|████████▏ | 237/291 [00:05<00:01, 47.61it/s] Loading 0: 83%|████████▎ | 242/291 [00:05<00:01, 47.56it/s] Loading 0: 85%|████████▍ | 247/291 [00:05<00:00, 48.20it/s] Loading 0: 87%|████████▋ | 252/291 [00:05<00:00, 48.63it/s] Loading 0: 88%|████████▊ | 257/291 [00:06<00:00, 40.28it/s] Loading 0: 91%|█████████ | 265/291 [00:06<00:00, 48.88it/s] Loading 0: 93%|█████████▎| 271/291 [00:06<00:00, 46.27it/s] Loading 0: 95%|█████████▍| 276/291 [00:06<00:00, 45.35it/s] Loading 0: 97%|█████████▋| 281/291 [00:06<00:00, 46.24it/s] Loading 0: 98%|█████████▊| 286/291 [00:06<00:00, 41.42it/s] Loading 0: 100%|██████████| 291/291 [00:12<00:00, 3.06it/s]
Job nousresearch-hermes-3-ll-5147-v1-mkmlizer completed after 74.2s with status: succeeded
Stopping job with name nousresearch-hermes-3-ll-5147-v1-mkmlizer
Pipeline stage MKMLizer completed in 74.72s
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 nousresearch-hermes-3-ll-5147-v1
Waiting for inference service nousresearch-hermes-3-ll-5147-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
Inference service nousresearch-hermes-3-ll-5147-v1 ready after 200.84277510643005s
Pipeline stage MKMLDeployer completed in 201.36s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.5918128490447998s
Received healthy response to inference request in 1.3368659019470215s
Received healthy response to inference request in 1.5649299621582031s
Received healthy response to inference request in 1.2434773445129395s
Received healthy response to inference request in 1.229729413986206s
5 requests
0 failed requests
5th percentile: 1.2324790000915526
10th percentile: 1.2352285861968995
20th percentile: 1.2407277584075929
30th percentile: 1.2621550559997559
40th percentile: 1.2995104789733887
50th percentile: 1.3368659019470215
60th percentile: 1.4280915260314941
70th percentile: 1.5193171501159668
80th percentile: 1.5703065395355225
90th percentile: 1.5810596942901611
95th percentile: 1.5864362716674805
99th percentile: 1.590737533569336
mean time: 1.393363094329834
Pipeline stage StressChecker completed in 8.27s
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 2.11s
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 2.01s
Shutdown handler de-registered
nousresearch-hermes-3-ll_5147_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 0.11s
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 nousresearch-hermes-3-ll-5147-v1-profiler
Waiting for inference service nousresearch-hermes-3-ll-5147-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 2092.88s
Shutdown handler de-registered
nousresearch-hermes-3-ll_5147_v1 status is now inactive due to auto deactivation removed underperforming models