developer_uid: rirv938
submission_id: rirv938-anthropic-40k-2_43413_v1
model_name: rirv938-anthropic-40k-2_43413_v1
model_group: rirv938/anthropic_40k_24
status: torndown
timestamp: 2025-01-01T05:13:48+00:00
num_battles: 11377
num_wins: 5953
celo_rating: 1291.16
family_friendly_score: 0.597
family_friendly_standard_error: 0.006936728335461898
submission_type: basic
model_repo: rirv938/anthropic_40k_2496_bo8_85w_b4_l1_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': 0.6391228795252434, 'latency_mean': 1.5645863580703736, 'latency_p50': 1.5686413049697876, 'latency_p90': 1.723162007331848}, {'batch_size': 3, 'throughput': 1.2668699358239908, 'latency_mean': 2.3562333261966706, 'latency_p50': 2.3523061275482178, 'latency_p90': 2.5850799560546873}, {'batch_size': 5, 'throughput': 1.5950033634391723, 'latency_mean': 3.120241162776947, 'latency_p50': 3.120350956916809, 'latency_p90': 3.455047059059143}, {'batch_size': 6, 'throughput': 1.703131445761194, 'latency_mean': 3.498482631444931, 'latency_p50': 3.504198670387268, 'latency_p90': 3.9335829973220826}, {'batch_size': 8, 'throughput': 1.865877396935668, 'latency_mean': 4.268980959653854, 'latency_p50': 4.291545867919922, 'latency_p90': 4.881524848937988}, {'batch_size': 10, 'throughput': 1.949951547053415, 'latency_mean': 5.092943034172058, 'latency_p50': 5.059327602386475, 'latency_p90': 5.833361029624939}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: rirv938-anthropic-40k-2_43413_v1
is_internal_developer: True
language_model: rirv938/anthropic_40k_2496_bo8_85w_b4_l1_v2
model_size: 13B
ranking_group: single
throughput_3p7s: 1.76
us_pacific_date: 2024-12-31
win_ratio: 0.5232486595763383
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-40k-2-43413-v1-mkmlizer
Waiting for job on rirv938-anthropic-40k-2-43413-v1-mkmlizer to finish
rirv938-anthropic-40k-2-43413-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-anthropic-40k-2-43413-v1-mkmlizer: ║ _____ __ __ ║
rirv938-anthropic-40k-2-43413-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
rirv938-anthropic-40k-2-43413-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
rirv938-anthropic-40k-2-43413-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
rirv938-anthropic-40k-2-43413-v1-mkmlizer: ║ /___/ ║
rirv938-anthropic-40k-2-43413-v1-mkmlizer: ║ ║
rirv938-anthropic-40k-2-43413-v1-mkmlizer: ║ Version: 0.11.12 ║
rirv938-anthropic-40k-2-43413-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
rirv938-anthropic-40k-2-43413-v1-mkmlizer: ║ https://mk1.ai ║
rirv938-anthropic-40k-2-43413-v1-mkmlizer: ║ ║
rirv938-anthropic-40k-2-43413-v1-mkmlizer: ║ The license key for the current software has been verified as ║
rirv938-anthropic-40k-2-43413-v1-mkmlizer: ║ belonging to: ║
rirv938-anthropic-40k-2-43413-v1-mkmlizer: ║ ║
rirv938-anthropic-40k-2-43413-v1-mkmlizer: ║ Chai Research Corp. ║
rirv938-anthropic-40k-2-43413-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
rirv938-anthropic-40k-2-43413-v1-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
rirv938-anthropic-40k-2-43413-v1-mkmlizer: ║ ║
rirv938-anthropic-40k-2-43413-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-anthropic-40k-2-43413-v1-mkmlizer: Downloaded to shared memory in 100.983s
rirv938-anthropic-40k-2-43413-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp9dawnif5, device:0
rirv938-anthropic-40k-2-43413-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-anthropic-40k-2-43413-v1-mkmlizer: quantized model in 44.585s
rirv938-anthropic-40k-2-43413-v1-mkmlizer: Processed model rirv938/anthropic_40k_2496_bo8_85w_b4_l1_v2 in 145.568s
rirv938-anthropic-40k-2-43413-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-anthropic-40k-2-43413-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-anthropic-40k-2-43413-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-anthropic-40k-2-43413-v1
rirv938-anthropic-40k-2-43413-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-anthropic-40k-2-43413-v1/config.json
rirv938-anthropic-40k-2-43413-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-anthropic-40k-2-43413-v1/special_tokens_map.json
rirv938-anthropic-40k-2-43413-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-anthropic-40k-2-43413-v1/tokenizer_config.json
rirv938-anthropic-40k-2-43413-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-anthropic-40k-2-43413-v1/tokenizer.json
rirv938-anthropic-40k-2-43413-v1-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:17, 20.62it/s] Loading 0: 3%|▎ | 10/363 [00:00<00:13, 25.58it/s] Loading 0: 4%|▍ | 14/363 [00:00<00:15, 22.52it/s] Loading 0: 6%|▌ | 20/363 [00:00<00:10, 31.23it/s] Loading 0: 7%|▋ | 24/363 [00:01<00:15, 22.12it/s] Loading 0: 7%|▋ | 27/363 [00:01<00:15, 21.02it/s] Loading 0: 9%|▊ | 31/363 [00:01<00:13, 24.37it/s] Loading 0: 9%|▉ | 34/363 [00:01<00:13, 23.52it/s] Loading 0: 10%|█ | 37/363 [00:01<00:13, 24.80it/s] Loading 0: 11%|█▏ | 41/363 [00:01<00:14, 22.37it/s] Loading 0: 13%|█▎ | 46/363 [00:01<00:11, 27.58it/s] Loading 0: 14%|█▍ | 50/363 [00:02<00:13, 23.79it/s] Loading 0: 15%|█▌ | 55/363 [00:02<00:11, 27.05it/s] Loading 0: 17%|█▋ | 60/363 [00:02<00:10, 28.22it/s] Loading 0: 18%|█▊ | 64/363 [00:02<00:15, 19.22it/s] Loading 0: 19%|█▉ | 69/363 [00:02<00:12, 23.65it/s] Loading 0: 20%|██ | 73/363 [00:03<00:12, 23.03it/s] Loading 0: 21%|██ | 77/363 [00:03<00:13, 21.40it/s] Loading 0: 23%|██▎ | 82/363 [00:03<00:11, 25.19it/s] Loading 0: 24%|██▎ | 86/363 [00:03<00:12, 22.37it/s] Loading 0: 25%|██▌ | 91/363 [00:03<00:10, 26.85it/s] Loading 0: 26%|██▌ | 95/363 [00:03<00:11, 23.41it/s] Loading 0: 28%|██▊ | 100/363 [00:04<00:09, 27.36it/s] Loading 0: 29%|██▊ | 104/363 [00:04<00:14, 17.86it/s] Loading 0: 30%|███ | 109/363 [00:04<00:11, 21.74it/s] Loading 0: 31%|███ | 112/363 [00:04<00:10, 22.96it/s] Loading 0: 32%|███▏ | 115/363 [00:04<00:10, 22.58it/s] Loading 0: 33%|███▎ | 118/363 [00:05<00:10, 23.46it/s] Loading 0: 33%|███▎ | 121/363 [00:05<00:09, 24.37it/s] Loading 0: 34%|███▍ | 124/363 [00:05<00:10, 23.43it/s] Loading 0: 35%|███▍ | 127/363 [00:05<00:09, 24.59it/s] Loading 0: 36%|███▌ | 130/363 [00:05<00:09, 25.63it/s] Loading 0: 37%|███▋ | 133/363 [00:05<00:09, 24.44it/s] Loading 0: 37%|███▋ | 136/363 [00:05<00:08, 25.58it/s] Loading 0: 39%|███▉ | 141/363 [00:05<00:08, 27.52it/s] Loading 0: 40%|███▉ | 144/363 [00:06<00:12, 16.89it/s] Loading 0: 41%|████ | 149/363 [00:06<00:11, 18.66it/s] Loading 0: 42%|████▏ | 154/363 [00:06<00:08, 23.37it/s] Loading 0: 44%|████▎ | 158/363 [00:06<00:09, 21.31it/s] Loading 0: 45%|████▍ | 163/363 [00:06<00:07, 25.84it/s] Loading 0: 46%|████▌ | 167/363 [00:07<00:08, 22.72it/s] Loading 0: 47%|████▋ | 172/363 [00:07<00:07, 26.90it/s] Loading 0: 48%|████▊ | 176/363 [00:07<00:07, 23.63it/s] Loading 0: 50%|████▉ | 181/363 [00:07<00:06, 27.69it/s] Loading 0: 51%|█████ | 185/363 [00:08<00:09, 18.27it/s] Loading 0: 52%|█████▏ | 190/363 [00:08<00:07, 22.78it/s] Loading 0: 53%|█████▎ | 194/363 [00:08<00:08, 20.91it/s] Loading 0: 55%|█████▍ | 199/363 [00:08<00:06, 25.04it/s] Loading 0: 56%|█████▌ | 203/363 [00:08<00:07, 22.66it/s] Loading 0: 57%|█████▋ | 208/363 [00:08<00:05, 26.48it/s] Loading 0: 58%|█████▊ | 212/363 [00:09<00:06, 23.25it/s] Loading 0: 60%|█████▉ | 217/363 [00:09<00:05, 27.34it/s] Loading 0: 61%|██████ | 222/363 [00:09<00:04, 28.72it/s] Loading 0: 62%|██████▏ | 226/363 [00:09<00:06, 20.29it/s] Loading 0: 63%|██████▎ | 230/363 [00:09<00:06, 19.59it/s] Loading 0: 65%|██████▍ | 235/363 [00:10<00:05, 23.71it/s] Loading 0: 66%|██████▌ | 239/363 [00:10<00:05, 21.81it/s] Loading 0: 67%|██████▋ | 244/363 [00:10<00:04, 26.11it/s] Loading 0: 68%|██████▊ | 248/363 [00:10<00:04, 23.08it/s] Loading 0: 70%|██████▉ | 253/363 [00:10<00:04, 27.05it/s] Loading 0: 71%|███████ | 257/363 [00:10<00:04, 23.87it/s] Loading 0: 72%|███████▏ | 262/363 [00:11<00:03, 27.92it/s] Loading 0: 73%|███████▎ | 266/363 [00:11<00:05, 18.44it/s] Loading 0: 75%|███████▍ | 271/363 [00:11<00:04, 22.88it/s] Loading 0: 76%|███████▌ | 275/363 [00:11<00:04, 21.04it/s] Loading 0: 77%|███████▋ | 280/363 [00:11<00:03, 25.36it/s] Loading 0: 78%|███████▊ | 284/363 [00:12<00:03, 22.35it/s] Loading 0: 80%|███████▉ | 289/363 [00:12<00:02, 26.49it/s] Loading 0: 81%|████████ | 293/363 [00:12<00:02, 23.47it/s] Loading 0: 82%|████████▏ | 298/363 [00:12<00:02, 27.47it/s] Loading 0: 83%|████████▎ | 303/363 [00:12<00:02, 28.67it/s] Loading 0: 85%|████████▍ | 307/363 [00:13<00:02, 20.27it/s] Loading 0: 86%|████████▌ | 311/363 [00:13<00:02, 19.69it/s] Loading 0: 87%|████████▋ | 316/363 [00:13<00:01, 23.76it/s] Loading 0: 88%|████████▊ | 320/363 [00:13<00:01, 22.00it/s] Loading 0: 90%|████████▉ | 325/363 [00:13<00:01, 26.15it/s] Loading 0: 91%|█████████ | 329/363 [00:14<00:01, 23.24it/s] Loading 0: 92%|█████████▏| 334/363 [00:14<00:01, 27.30it/s] Loading 0: 93%|█████████▎| 338/363 [00:14<00:01, 24.01it/s] Loading 0: 94%|█████████▍| 343/363 [00:14<00:00, 28.12it/s] Loading 0: 96%|█████████▌| 347/363 [00:21<00:08, 1.96it/s] Loading 0: 96%|█████████▋| 350/363 [00:21<00:05, 2.48it/s] Loading 0: 97%|█████████▋| 353/363 [00:21<00:03, 3.16it/s] Loading 0: 98%|█████████▊| 357/363 [00:22<00:01, 4.30it/s]
Job rirv938-anthropic-40k-2-43413-v1-mkmlizer completed after 175.84s with status: succeeded
Stopping job with name rirv938-anthropic-40k-2-43413-v1-mkmlizer
Pipeline stage MKMLizer completed in 176.44s
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 rirv938-anthropic-40k-2-43413-v1
Waiting for inference service rirv938-anthropic-40k-2-43413-v1 to be ready
Inference service rirv938-anthropic-40k-2-43413-v1 ready after 321.47548484802246s
Pipeline stage MKMLDeployer completed in 321.99s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.7104640007019043s
Received healthy response to inference request in 1.4507830142974854s
Received healthy response to inference request in 1.5493848323822021s
Received healthy response to inference request in 1.354278802871704s
Received healthy response to inference request in 1.735314130783081s
5 requests
0 failed requests
5th percentile: 1.3735796451568603
10th percentile: 1.3928804874420166
20th percentile: 1.4314821720123292
30th percentile: 1.4705033779144288
40th percentile: 1.5099441051483153
50th percentile: 1.5493848323822021
60th percentile: 1.613816499710083
70th percentile: 1.6782481670379639
80th percentile: 1.7154340267181396
90th percentile: 1.7253740787506104
95th percentile: 1.7303441047668457
99th percentile: 1.734320125579834
mean time: 1.5600449562072753
Pipeline stage StressChecker completed in 9.30s
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 0.91s
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 0.67s
Shutdown handler de-registered
rirv938-anthropic-40k-2_43413_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 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rirv938-anthropic-40k-2-43413-v1-profiler
Waiting for inference service rirv938-anthropic-40k-2-43413-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 2389.78s
Shutdown handler de-registered
rirv938-anthropic-40k-2_43413_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of rirv938-anthropic-40k-2_43413_v1
Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLDeleter
Checking if service rirv938-anthropic-40k-2-43413-v1 is running
admin requested tearing down of rirv938-anthropic-40k-2_69835_v2
Shutdown handler not registered because Python interpreter is not running in the main thread
Tearing down inference service rirv938-anthropic-40k-2-43413-v1
run pipeline %s
run pipeline stage %s
Service rirv938-anthropic-40k-2-43413-v1 has been torndown
Running pipeline stage MKMLDeleter
Pipeline stage MKMLDeleter completed in 2.87s
Checking if service rirv938-anthropic-40k-2-69835-v2 is running
run pipeline stage %s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key rirv938-anthropic-40k-2-43413-v1/config.json from bucket guanaco-mkml-models
Deleting key rirv938-anthropic-40k-2-43413-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Tearing down inference service rirv938-anthropic-40k-2-69835-v2
Service rirv938-anthropic-40k-2-69835-v2 has been torndown
Deleting key rirv938-anthropic-40k-2-43413-v1/special_tokens_map.json from bucket guanaco-mkml-models
Pipeline stage MKMLDeleter completed in 2.50s
Deleting key rirv938-anthropic-40k-2-43413-v1/tokenizer.json from bucket guanaco-mkml-models
run pipeline stage %s
Deleting key rirv938-anthropic-40k-2-43413-v1/tokenizer_config.json from bucket guanaco-mkml-models
Running pipeline stage MKMLModelDeleter
Pipeline stage MKMLModelDeleter completed in 2.88s
Cleaning model data from S3
Shutdown handler de-registered
Cleaning model data from model cache
Cleaning model data from model cache
rirv938-anthropic-40k-2_43413_v1 status is now torndown due to DeploymentManager action
rirv938-anthropic-40k-2_43413_v1 status is now torndown due to DeploymentManager action
rirv938-anthropic-40k-2_43413_v1 status is now torndown due to DeploymentManager action
ChatRequest
Generation Params
Prompt Formatter
Chat History
ChatMessage 1