developer_uid: Hastagaras
submission_id: hastagaras-mn-base-12b-e_1640_v1
model_name: test
model_group: Hastagaras/MN-Base-12B-E
status: inactive
timestamp: 2024-11-28T12:04:37+00:00
num_battles: 14656
num_wins: 7028
celo_rating: 1242.58
family_friendly_score: 0.5704
family_friendly_standard_error: 0.007000626257700092
submission_type: basic
model_repo: Hastagaras/MN-Base-12B-Experiment-LMH-ET-0.1-2
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.6131121691151926, 'latency_mean': 1.6309291923046112, 'latency_p50': 1.6366939544677734, 'latency_p90': 1.8048975706100463}, {'batch_size': 3, 'throughput': 1.135475487568298, 'latency_mean': 2.630164431333542, 'latency_p50': 2.619342088699341, 'latency_p90': 2.9512459516525267}, {'batch_size': 5, 'throughput': 1.3581220105044904, 'latency_mean': 3.66614541888237, 'latency_p50': 3.7159314155578613, 'latency_p90': 4.097128748893738}, {'batch_size': 6, 'throughput': 1.4253365791678785, 'latency_mean': 4.193380460739136, 'latency_p50': 4.233279347419739, 'latency_p90': 4.642278504371643}, {'batch_size': 8, 'throughput': 1.4965214775273081, 'latency_mean': 5.302343770265579, 'latency_p50': 5.31375253200531, 'latency_p90': 5.900844311714172}, {'batch_size': 10, 'throughput': 1.5325804784489312, 'latency_mean': 6.482841323614121, 'latency_p50': 6.52308201789856, 'latency_p90': 7.321674823760986}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: test
is_internal_developer: False
language_model: Hastagaras/MN-Base-12B-Experiment-LMH-ET-0.1-2
model_size: 13B
ranking_group: single
throughput_3p7s: 1.37
us_pacific_date: 2024-11-28
win_ratio: 0.4795305676855895
generation_params: {'temperature': 0.85, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '</s>', '[SUFFIX]'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': "[PREFIX]system[MIDDLE]You're {bot_name}\n{memory}\n", 'prompt_template': '{prompt}[SUFFIX]', 'bot_template': '[PREFIX]model[MIDDLE]{bot_name}: {message}[SUFFIX]', 'user_template': '[PREFIX]user[MIDDLE]{user_name}: {message}[SUFFIX]', 'response_template': '[PREFIX]model[MIDDLE]{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 hastagaras-mn-base-12b-e-1640-v1-mkmlizer
Waiting for job on hastagaras-mn-base-12b-e-1640-v1-mkmlizer to finish
hastagaras-mn-base-12b-e-1640-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-mn-base-12b-e-1640-v1-mkmlizer: ║ _____ __ __ ║
hastagaras-mn-base-12b-e-1640-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-mn-base-12b-e-1640-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-mn-base-12b-e-1640-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-mn-base-12b-e-1640-v1-mkmlizer: ║ /___/ ║
hastagaras-mn-base-12b-e-1640-v1-mkmlizer: ║ ║
hastagaras-mn-base-12b-e-1640-v1-mkmlizer: ║ Version: 0.11.12 ║
hastagaras-mn-base-12b-e-1640-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-mn-base-12b-e-1640-v1-mkmlizer: ║ https://mk1.ai ║
hastagaras-mn-base-12b-e-1640-v1-mkmlizer: ║ ║
hastagaras-mn-base-12b-e-1640-v1-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-mn-base-12b-e-1640-v1-mkmlizer: ║ belonging to: ║
hastagaras-mn-base-12b-e-1640-v1-mkmlizer: ║ ║
hastagaras-mn-base-12b-e-1640-v1-mkmlizer: ║ Chai Research Corp. ║
hastagaras-mn-base-12b-e-1640-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-mn-base-12b-e-1640-v1-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
hastagaras-mn-base-12b-e-1640-v1-mkmlizer: ║ ║
hastagaras-mn-base-12b-e-1640-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-mn-base-12b-e-1640-v1-mkmlizer: Downloaded to shared memory in 47.968s
hastagaras-mn-base-12b-e-1640-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp97s5epdt, device:0
hastagaras-mn-base-12b-e-1640-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-mn-base-12b-e-1640-v1-mkmlizer: quantized model in 36.022s
hastagaras-mn-base-12b-e-1640-v1-mkmlizer: Processed model Hastagaras/MN-Base-12B-Experiment-LMH-ET-0.1-2 in 83.990s
hastagaras-mn-base-12b-e-1640-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-mn-base-12b-e-1640-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-mn-base-12b-e-1640-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-mn-base-12b-e-1640-v1
hastagaras-mn-base-12b-e-1640-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-mn-base-12b-e-1640-v1/special_tokens_map.json
hastagaras-mn-base-12b-e-1640-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-mn-base-12b-e-1640-v1/config.json
hastagaras-mn-base-12b-e-1640-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-mn-base-12b-e-1640-v1/tokenizer_config.json
hastagaras-mn-base-12b-e-1640-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-mn-base-12b-e-1640-v1/tokenizer.json
hastagaras-mn-base-12b-e-1640-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-mn-base-12b-e-1640-v1/flywheel_model.0.safetensors
Job hastagaras-mn-base-12b-e-1640-v1-mkmlizer completed after 114.28s with status: succeeded
Stopping job with name hastagaras-mn-base-12b-e-1640-v1-mkmlizer
Pipeline stage MKMLizer completed in 114.74s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service hastagaras-mn-base-12b-e-1640-v1
Waiting for inference service hastagaras-mn-base-12b-e-1640-v1 to be ready
Inference service hastagaras-mn-base-12b-e-1640-v1 ready after 130.48475313186646s
Pipeline stage MKMLDeployer completed in 130.97s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1119625568389893s
Received healthy response to inference request in 1.6037814617156982s
Received healthy response to inference request in 1.6876990795135498s
Received healthy response to inference request in 1.9273416996002197s
Received healthy response to inference request in 1.691143274307251s
5 requests
0 failed requests
5th percentile: 1.6205649852752686
10th percentile: 1.637348508834839
20th percentile: 1.6709155559539794
30th percentile: 1.68838791847229
40th percentile: 1.6897655963897704
50th percentile: 1.691143274307251
60th percentile: 1.7856226444244385
70th percentile: 1.8801020145416258
80th percentile: 1.9642658710479737
90th percentile: 2.0381142139434814
95th percentile: 2.0750383853912355
99th percentile: 2.1045777225494384
mean time: 1.8043856143951416
Pipeline stage StressChecker completed in 10.17s
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 2.13s
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 1.96s
Shutdown handler de-registered
hastagaras-mn-base-12b-e_1640_v1 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 3046.93s
Shutdown handler de-registered
hastagaras-mn-base-12b-e_1640_v1 status is now inactive due to auto deactivation removed underperforming models