developer_uid: rirv938
submission_id: rirv938-anthropic-beta-_80283_v1
model_name: rirv938-anthropic-beta-_80283_v1
model_group: rirv938/anthropic_beta_2
status: torndown
timestamp: 2024-12-31T05:40:00+00:00
num_battles: 12269
num_wins: 6292
celo_rating: 1287.5
family_friendly_score: 0.5876
family_friendly_standard_error: 0.006961698643291018
submission_type: basic
model_repo: rirv938/anthropic_beta_2_40k_1248_bo8_100w_b4_v2
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 4
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.6408404214953303, 'latency_mean': 1.5603591752052308, 'latency_p50': 1.5605510473251343, 'latency_p90': 1.7239824533462524}, {'batch_size': 3, 'throughput': 1.267635082066494, 'latency_mean': 2.3625277423858644, 'latency_p50': 2.3642162084579468, 'latency_p90': 2.5851426124572754}, {'batch_size': 5, 'throughput': 1.6118245670878162, 'latency_mean': 3.077965803146362, 'latency_p50': 3.078386664390564, 'latency_p90': 3.40274441242218}, {'batch_size': 6, 'throughput': 1.7004539140961243, 'latency_mean': 3.504175922870636, 'latency_p50': 3.519642472267151, 'latency_p90': 3.893949222564697}, {'batch_size': 8, 'throughput': 1.8680920414034772, 'latency_mean': 4.249383977651596, 'latency_p50': 4.2764400243759155, 'latency_p90': 4.807097721099853}, {'batch_size': 10, 'throughput': 1.9614669087267507, 'latency_mean': 5.067894788980484, 'latency_p50': 5.022131562232971, 'latency_p90': 5.798269534111022}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: rirv938-anthropic-beta-_80283_v1
is_internal_developer: True
language_model: rirv938/anthropic_beta_2_40k_1248_bo8_100w_b4_v2
model_size: 13B
ranking_group: single
throughput_3p7s: 1.76
us_pacific_date: 2024-12-30
win_ratio: 0.5128372320482517
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:', '<|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 rirv938-anthropic-beta-80283-v1-mkmlizer
Waiting for job on rirv938-anthropic-beta-80283-v1-mkmlizer to finish
rirv938-anthropic-beta-80283-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-anthropic-beta-80283-v1-mkmlizer: ║ _____ __ __ ║
rirv938-anthropic-beta-80283-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
rirv938-anthropic-beta-80283-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
rirv938-anthropic-beta-80283-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
rirv938-anthropic-beta-80283-v1-mkmlizer: ║ /___/ ║
rirv938-anthropic-beta-80283-v1-mkmlizer: ║ ║
rirv938-anthropic-beta-80283-v1-mkmlizer: ║ Version: 0.11.12 ║
rirv938-anthropic-beta-80283-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
rirv938-anthropic-beta-80283-v1-mkmlizer: ║ https://mk1.ai ║
rirv938-anthropic-beta-80283-v1-mkmlizer: ║ ║
rirv938-anthropic-beta-80283-v1-mkmlizer: ║ The license key for the current software has been verified as ║
rirv938-anthropic-beta-80283-v1-mkmlizer: ║ belonging to: ║
rirv938-anthropic-beta-80283-v1-mkmlizer: ║ ║
rirv938-anthropic-beta-80283-v1-mkmlizer: ║ Chai Research Corp. ║
rirv938-anthropic-beta-80283-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
rirv938-anthropic-beta-80283-v1-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
rirv938-anthropic-beta-80283-v1-mkmlizer: ║ ║
rirv938-anthropic-beta-80283-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-anthropic-beta-80283-v1-mkmlizer: Downloaded to shared memory in 97.309s
rirv938-anthropic-beta-80283-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpfu36c1on, device:0
rirv938-anthropic-beta-80283-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-anthropic-beta-80283-v1-mkmlizer: quantized model in 44.037s
rirv938-anthropic-beta-80283-v1-mkmlizer: Processed model rirv938/anthropic_beta_2_40k_1248_bo8_100w_b4_v2 in 141.347s
rirv938-anthropic-beta-80283-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-anthropic-beta-80283-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-anthropic-beta-80283-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-anthropic-beta-80283-v1
rirv938-anthropic-beta-80283-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-anthropic-beta-80283-v1/special_tokens_map.json
rirv938-anthropic-beta-80283-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-anthropic-beta-80283-v1/config.json
rirv938-anthropic-beta-80283-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-anthropic-beta-80283-v1/tokenizer_config.json
rirv938-anthropic-beta-80283-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-anthropic-beta-80283-v1/tokenizer.json
rirv938-anthropic-beta-80283-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-anthropic-beta-80283-v1/flywheel_model.0.safetensors
rirv938-anthropic-beta-80283-v1-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:16, 22.34it/s] Loading 0: 3%|▎ | 10/363 [00:00<00:12, 29.06it/s] Loading 0: 4%|▍ | 14/363 [00:00<00:13, 25.63it/s] Loading 0: 6%|▌ | 21/363 [00:00<00:09, 36.70it/s] Loading 0: 7%|▋ | 26/363 [00:01<00:15, 22.13it/s] Loading 0: 9%|▊ | 31/363 [00:01<00:12, 27.00it/s] Loading 0: 10%|▉ | 35/363 [00:01<00:11, 28.53it/s] Loading 0: 11%|█ | 39/363 [00:01<00:10, 30.10it/s] Loading 0: 12%|█▏ | 43/363 [00:01<00:10, 29.28it/s] Loading 0: 13%|█▎ | 48/363 [00:01<00:09, 31.78it/s] Loading 0: 14%|█▍ | 52/363 [00:01<00:10, 28.79it/s] Loading 0: 15%|█▌ | 56/363 [00:01<00:10, 28.46it/s] Loading 0: 17%|█▋ | 60/363 [00:02<00:09, 30.53it/s] Loading 0: 18%|█▊ | 64/363 [00:02<00:15, 19.71it/s] Loading 0: 19%|█▉ | 70/363 [00:02<00:11, 26.56it/s] Loading 0: 20%|██ | 74/363 [00:02<00:11, 25.98it/s] Loading 0: 21%|██▏ | 78/363 [00:02<00:12, 23.36it/s] Loading 0: 23%|██▎ | 82/363 [00:03<00:11, 25.50it/s] Loading 0: 23%|██▎ | 85/363 [00:03<00:10, 26.21it/s] Loading 0: 24%|██▍ | 88/363 [00:03<00:10, 25.25it/s] Loading 0: 25%|██▌ | 91/363 [00:03<00:10, 25.95it/s] Loading 0: 26%|██▌ | 94/363 [00:03<00:10, 26.27it/s] Loading 0: 27%|██▋ | 97/363 [00:03<00:10, 24.88it/s] Loading 0: 28%|██▊ | 100/363 [00:03<00:10, 25.89it/s] Loading 0: 28%|██▊ | 103/363 [00:04<00:14, 18.20it/s] Loading 0: 29%|██▉ | 106/363 [00:04<00:13, 19.18it/s] Loading 0: 30%|███ | 109/363 [00:04<00:12, 21.04it/s] Loading 0: 31%|███ | 112/363 [00:04<00:10, 23.03it/s] Loading 0: 32%|███▏ | 115/363 [00:04<00:10, 22.71it/s] Loading 0: 33%|███▎ | 118/363 [00:04<00:10, 23.93it/s] Loading 0: 34%|███▎ | 122/363 [00:04<00:11, 21.39it/s] Loading 0: 35%|███▍ | 127/363 [00:04<00:08, 26.60it/s] Loading 0: 36%|███▌ | 131/363 [00:05<00:10, 22.97it/s] Loading 0: 37%|███▋ | 136/363 [00:05<00:08, 27.49it/s] Loading 0: 39%|███▉ | 141/363 [00:05<00:07, 28.24it/s] Loading 0: 40%|███▉ | 145/363 [00:05<00:10, 19.82it/s] Loading 0: 41%|████ | 149/363 [00:06<00:11, 19.19it/s] Loading 0: 42%|████▏ | 154/363 [00:06<00:08, 23.44it/s] Loading 0: 43%|████▎ | 157/363 [00:06<00:08, 24.56it/s] Loading 0: 44%|████▍ | 160/363 [00:06<00:08, 24.03it/s] Loading 0: 45%|████▍ | 163/363 [00:06<00:08, 24.91it/s] Loading 0: 46%|████▌ | 167/363 [00:06<00:08, 22.26it/s] Loading 0: 47%|████▋ | 172/363 [00:06<00:07, 27.10it/s] Loading 0: 48%|████▊ | 176/363 [00:07<00:07, 23.52it/s] Loading 0: 50%|████▉ | 181/363 [00:07<00:06, 27.83it/s] Loading 0: 51%|█████ | 185/363 [00:07<00:09, 18.13it/s] Loading 0: 52%|█████▏ | 190/363 [00:07<00:07, 22.37it/s] Loading 0: 53%|█████▎ | 193/363 [00:07<00:07, 23.67it/s] Loading 0: 54%|█████▍ | 196/363 [00:07<00:07, 23.14it/s] Loading 0: 55%|█████▍ | 199/363 [00:08<00:06, 24.25it/s] Loading 0: 56%|█████▌ | 203/363 [00:08<00:07, 21.59it/s] Loading 0: 57%|█████▋ | 208/363 [00:08<00:05, 26.36it/s] Loading 0: 58%|█████▊ | 212/363 [00:08<00:06, 23.14it/s] Loading 0: 60%|█████▉ | 217/363 [00:08<00:05, 27.61it/s] Loading 0: 61%|██████ | 222/363 [00:08<00:05, 28.12it/s] Loading 0: 62%|██████▏ | 226/363 [00:09<00:07, 19.43it/s] Loading 0: 63%|██████▎ | 229/363 [00:09<00:06, 21.10it/s] Loading 0: 64%|██████▍ | 232/363 [00:09<00:06, 21.35it/s] Loading 0: 65%|██████▍ | 235/363 [00:09<00:05, 22.58it/s] Loading 0: 66%|██████▌ | 239/363 [00:09<00:06, 20.61it/s] Loading 0: 67%|██████▋ | 244/363 [00:10<00:04, 25.30it/s] Loading 0: 68%|██████▊ | 247/363 [00:10<00:04, 26.18it/s] Loading 0: 69%|██████▉ | 250/363 [00:10<00:04, 25.10it/s] Loading 0: 70%|██████▉ | 253/363 [00:10<00:04, 26.05it/s] Loading 0: 71%|███████ | 257/363 [00:10<00:04, 22.58it/s] Loading 0: 72%|███████▏ | 262/363 [00:10<00:03, 27.63it/s] Loading 0: 73%|███████▎ | 266/363 [00:11<00:05, 17.97it/s] Loading 0: 75%|███████▍ | 271/363 [00:11<00:04, 22.46it/s] Loading 0: 75%|███████▌ | 274/363 [00:11<00:03, 23.74it/s] Loading 0: 76%|███████▋ | 277/363 [00:11<00:03, 23.27it/s] Loading 0: 77%|███████▋ | 280/363 [00:11<00:03, 24.31it/s] Loading 0: 78%|███████▊ | 284/363 [00:11<00:03, 21.83it/s] Loading 0: 80%|███████▉ | 289/363 [00:11<00:02, 26.80it/s] Loading 0: 81%|████████ | 293/363 [00:12<00:02, 23.36it/s] Loading 0: 82%|████████▏ | 298/363 [00:12<00:02, 27.83it/s] Loading 0: 83%|████████▎ | 303/363 [00:12<00:02, 28.61it/s] Loading 0: 85%|████████▍ | 307/363 [00:12<00:02, 19.91it/s] Loading 0: 85%|████████▌ | 310/363 [00:12<00:02, 21.53it/s] Loading 0: 86%|████████▌ | 313/363 [00:13<00:02, 21.55it/s] Loading 0: 87%|████████▋ | 316/363 [00:13<00:02, 22.81it/s] Loading 0: 88%|████████▊ | 320/363 [00:13<00:02, 21.03it/s] Loading 0: 90%|████████▉ | 325/363 [00:13<00:01, 25.86it/s] Loading 0: 91%|█████████ | 329/363 [00:13<00:01, 23.07it/s] Loading 0: 92%|█████████▏| 334/363 [00:13<00:01, 27.51it/s] Loading 0: 93%|█████████▎| 338/363 [00:14<00:01, 23.83it/s] Loading 0: 94%|█████████▍| 343/363 [00:14<00:00, 27.94it/s] Loading 0: 96%|█████████▌| 347/363 [00:21<00:08, 1.92it/s] Loading 0: 96%|█████████▋| 350/363 [00:21<00:05, 2.43it/s] Loading 0: 97%|█████████▋| 353/363 [00:21<00:03, 3.12it/s] Loading 0: 98%|█████████▊| 357/363 [00:21<00:01, 4.31it/s]
Job rirv938-anthropic-beta-80283-v1-mkmlizer completed after 166.14s with status: succeeded
Stopping job with name rirv938-anthropic-beta-80283-v1-mkmlizer
Pipeline stage MKMLizer completed in 166.62s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.13s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rirv938-anthropic-beta-80283-v1
Waiting for inference service rirv938-anthropic-beta-80283-v1 to be ready
Inference service rirv938-anthropic-beta-80283-v1 ready after 311.51852893829346s
Pipeline stage MKMLDeployer completed in 312.03s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.065481424331665s
Received healthy response to inference request in 1.3616046905517578s
Received healthy response to inference request in 1.3972344398498535s
Received healthy response to inference request in 1.4153385162353516s
Received healthy response to inference request in 1.6940834522247314s
5 requests
0 failed requests
5th percentile: 1.368730640411377
10th percentile: 1.375856590270996
20th percentile: 1.3901084899902343
30th percentile: 1.400855255126953
40th percentile: 1.4080968856811524
50th percentile: 1.4153385162353516
60th percentile: 1.5268364906311036
70th percentile: 1.6383344650268554
80th percentile: 1.7683630466461182
90th percentile: 1.9169222354888915
95th percentile: 1.9912018299102783
99th percentile: 2.0506255054473876
mean time: 1.5867485046386718
Pipeline stage StressChecker completed in 9.41s
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 0.72s
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 0.69s
Shutdown handler de-registered
rirv938-anthropic-beta-_80283_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 0.10s
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 rirv938-anthropic-beta-80283-v1-profiler
Waiting for inference service rirv938-anthropic-beta-80283-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 2557.96s
Shutdown handler de-registered
rirv938-anthropic-beta-_80283_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-anthropic-beta-_80283_v1 status is now torndown due to DeploymentManager action
rirv938-anthropic-beta-_80283_v1 status is now torndown due to DeploymentManager action
rirv938-anthropic-beta-_80283_v1 status is now torndown due to DeploymentManager action
ChatRequest
Generation Params
Prompt Formatter
Chat History
ChatMessage 1