developer_uid: azuruce
submission_id: chaiml-espresso-ant-2412_7481_v2
model_name: chaiml-espresso-ant-2412_7481_v2
model_group: ChaiML/espresso_ant_2412
status: inactive
timestamp: 2024-12-05T05:53:56+00:00
num_battles: 8895
num_wins: 4399
celo_rating: 1259.04
family_friendly_score: 0.5896
family_friendly_standard_error: 0.0069566060690540756
submission_type: basic
model_repo: ChaiML/espresso_ant_241204_albert_v2_sft_2epoch_128alpha
model_architecture: MistralForCausalLM
model_num_parameters: 22247282688.0
best_of: 4
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.3866989729042875, 'latency_mean': 2.5859273540973664, 'latency_p50': 2.5882097482681274, 'latency_p90': 2.868920612335205}, {'batch_size': 3, 'throughput': 0.8211577475262923, 'latency_mean': 3.6362590050697325, 'latency_p50': 3.6238309144973755, 'latency_p90': 3.9946713209152223}, {'batch_size': 5, 'throughput': 1.0842394995318825, 'latency_mean': 4.581835845708847, 'latency_p50': 4.579334020614624, 'latency_p90': 5.184260153770446}, {'batch_size': 6, 'throughput': 1.1643741729645634, 'latency_mean': 5.118280498981476, 'latency_p50': 5.102160811424255, 'latency_p90': 5.746660661697388}, {'batch_size': 10, 'throughput': 1.38206145289547, 'latency_mean': 7.1337885928153995, 'latency_p50': 7.120239496231079, 'latency_p90': 8.176108527183532}]
gpu_counts: {'NVIDIA RTX A6000': 1}
display_name: chaiml-espresso-ant-2412_7481_v2
is_internal_developer: True
language_model: ChaiML/espresso_ant_241204_albert_v2_sft_2epoch_128alpha
model_size: 22B
ranking_group: single
throughput_3p7s: 0.85
us_pacific_date: 2024-12-04
win_ratio: 0.49454749859471614
generation_params: {'temperature': 0.9, '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 chaiml-espresso-ant-2412-7481-v2-mkmlizer
Waiting for job on chaiml-espresso-ant-2412-7481-v2-mkmlizer to finish
chaiml-espresso-ant-2412-7481-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-espresso-ant-2412-7481-v2-mkmlizer: ║     _____            __           __                                ║
chaiml-espresso-ant-2412-7481-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-espresso-ant-2412-7481-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-espresso-ant-2412-7481-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-espresso-ant-2412-7481-v2-mkmlizer: ║       /___/                                                         ║
chaiml-espresso-ant-2412-7481-v2-mkmlizer: ║                                                                     ║
chaiml-espresso-ant-2412-7481-v2-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-espresso-ant-2412-7481-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-espresso-ant-2412-7481-v2-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-espresso-ant-2412-7481-v2-mkmlizer: ║                                                                     ║
chaiml-espresso-ant-2412-7481-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-espresso-ant-2412-7481-v2-mkmlizer: ║  belonging to:                                                      ║
chaiml-espresso-ant-2412-7481-v2-mkmlizer: ║                                                                     ║
chaiml-espresso-ant-2412-7481-v2-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-espresso-ant-2412-7481-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-espresso-ant-2412-7481-v2-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-espresso-ant-2412-7481-v2-mkmlizer: ║                                                                     ║
chaiml-espresso-ant-2412-7481-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Connection pool is full, discarding connection: %s. Connection pool size: %s
chaiml-espresso-ant-2412-7481-v2-mkmlizer: Downloaded to shared memory in 49.711s
chaiml-espresso-ant-2412-7481-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp33xg59z9, device:0
chaiml-espresso-ant-2412-7481-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-espresso-ant-2412-7481-v2-mkmlizer: quantized model in 48.880s
chaiml-espresso-ant-2412-7481-v2-mkmlizer: Processed model ChaiML/espresso_ant_241204_albert_v2_sft_2epoch_128alpha in 98.591s
chaiml-espresso-ant-2412-7481-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-espresso-ant-2412-7481-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-espresso-ant-2412-7481-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-espresso-ant-2412-7481-v2
chaiml-espresso-ant-2412-7481-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-espresso-ant-2412-7481-v2/config.json
chaiml-espresso-ant-2412-7481-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-espresso-ant-2412-7481-v2/special_tokens_map.json
chaiml-espresso-ant-2412-7481-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-espresso-ant-2412-7481-v2/tokenizer_config.json
chaiml-espresso-ant-2412-7481-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-espresso-ant-2412-7481-v2/tokenizer.json
chaiml-espresso-ant-2412-7481-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-espresso-ant-2412-7481-v2/flywheel_model.1.safetensors
chaiml-espresso-ant-2412-7481-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-espresso-ant-2412-7481-v2/flywheel_model.0.safetensors
Job chaiml-espresso-ant-2412-7481-v2-mkmlizer completed after 134.33s with status: succeeded
Stopping job with name chaiml-espresso-ant-2412-7481-v2-mkmlizer
Pipeline stage MKMLizer completed in 135.74s
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 chaiml-espresso-ant-2412-7481-v2
Waiting for inference service chaiml-espresso-ant-2412-7481-v2 to be ready
Inference service chaiml-espresso-ant-2412-7481-v2 ready after 176.40572786331177s
Pipeline stage MKMLDeployer completed in 178.08s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.030884265899658s
Received healthy response to inference request in 2.5300345420837402s
Received healthy response to inference request in 2.2162818908691406s
Received healthy response to inference request in 2.247333288192749s
Received healthy response to inference request in 2.5059289932250977s
5 requests
0 failed requests
5th percentile: 2.2224921703338625
10th percentile: 2.228702449798584
20th percentile: 2.241123008728027
30th percentile: 2.299052429199219
40th percentile: 2.4024907112121583
50th percentile: 2.5059289932250977
60th percentile: 2.5155712127685548
70th percentile: 2.525213432312012
80th percentile: 2.630204486846924
90th percentile: 2.830544376373291
95th percentile: 2.9307143211364743
99th percentile: 3.0108502769470213
mean time: 2.506092596054077
Pipeline stage StressChecker completed in 13.91s
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 2.40s
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 2.07s
Shutdown handler de-registered
chaiml-espresso-ant-2412_7481_v2 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 3071.05s
Shutdown handler de-registered
chaiml-espresso-ant-2412_7481_v2 status is now inactive due to auto deactivation removed underperforming models