developer_uid: azuruce
submission_id: chaiml-espresso-ant-llam_6735_v2
model_name: chaiml-espresso-ant-llam_6735_v2
model_group: ChaiML/espresso_ant_llam
status: inactive
timestamp: 2024-12-06T01:43:12+00:00
num_battles: 8711
num_wins: 4414
celo_rating: 1267.88
family_friendly_score: 0.5880000000000001
family_friendly_standard_error: 0.00696068962100739
submission_type: basic
model_repo: ChaiML/espresso_ant_llama_241204_albert_v2_sft_3epoch_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': 0.3885227344248434, 'latency_mean': 2.573788831233978, 'latency_p50': 2.570038676261902, 'latency_p90': 2.8466442346572878}, {'batch_size': 3, 'throughput': 0.8148238785499979, 'latency_mean': 3.661741917133331, 'latency_p50': 3.6761103868484497, 'latency_p90': 4.011518287658691}, {'batch_size': 5, 'throughput': 1.0883286655919806, 'latency_mean': 4.56948424577713, 'latency_p50': 4.563036680221558, 'latency_p90': 5.116857743263244}, {'batch_size': 6, 'throughput': 1.1692757556142905, 'latency_mean': 5.106795467138291, 'latency_p50': 5.110004901885986, 'latency_p90': 5.660249543190003}, {'batch_size': 10, 'throughput': 1.380853642822297, 'latency_mean': 7.188460997343063, 'latency_p50': 7.130412220954895, 'latency_p90': 8.085334324836731}]
gpu_counts: {'NVIDIA RTX A6000': 1}
display_name: chaiml-espresso-ant-llam_6735_v2
is_internal_developer: True
language_model: ChaiML/espresso_ant_llama_241204_albert_v2_sft_3epoch_128alpha
model_size: 22B
ranking_group: single
throughput_3p7s: 0.83
us_pacific_date: 2024-12-05
win_ratio: 0.5067156468832511
generation_params: {'temperature': 0.8, '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-llam-6735-v2-mkmlizer
Waiting for job on chaiml-espresso-ant-llam-6735-v2-mkmlizer to finish
chaiml-espresso-ant-llam-6735-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-espresso-ant-llam-6735-v2-mkmlizer: ║ _____ __ __ ║
chaiml-espresso-ant-llam-6735-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-espresso-ant-llam-6735-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-espresso-ant-llam-6735-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-espresso-ant-llam-6735-v2-mkmlizer: ║ /___/ ║
chaiml-espresso-ant-llam-6735-v2-mkmlizer: ║ ║
chaiml-espresso-ant-llam-6735-v2-mkmlizer: ║ Version: 0.11.12 ║
chaiml-espresso-ant-llam-6735-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-espresso-ant-llam-6735-v2-mkmlizer: ║ https://mk1.ai ║
chaiml-espresso-ant-llam-6735-v2-mkmlizer: ║ ║
chaiml-espresso-ant-llam-6735-v2-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-espresso-ant-llam-6735-v2-mkmlizer: ║ belonging to: ║
chaiml-espresso-ant-llam-6735-v2-mkmlizer: ║ ║
chaiml-espresso-ant-llam-6735-v2-mkmlizer: ║ Chai Research Corp. ║
chaiml-espresso-ant-llam-6735-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-espresso-ant-llam-6735-v2-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
chaiml-espresso-ant-llam-6735-v2-mkmlizer: ║ ║
chaiml-espresso-ant-llam-6735-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-espresso-ant-llam-6735-v2-mkmlizer: Downloaded to shared memory in 63.602s
chaiml-espresso-ant-llam-6735-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpn2vm2n8j, device:0
chaiml-espresso-ant-llam-6735-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-espresso-ant-llam-6735-v2-mkmlizer: quantized model in 44.725s
chaiml-espresso-ant-llam-6735-v2-mkmlizer: Processed model ChaiML/espresso_ant_llama_241204_albert_v2_sft_3epoch_128alpha in 108.327s
chaiml-espresso-ant-llam-6735-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-espresso-ant-llam-6735-v2/config.json
chaiml-espresso-ant-llam-6735-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-espresso-ant-llam-6735-v2/special_tokens_map.json
chaiml-espresso-ant-llam-6735-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-espresso-ant-llam-6735-v2/tokenizer_config.json
chaiml-espresso-ant-llam-6735-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-espresso-ant-llam-6735-v2/tokenizer.json
chaiml-espresso-ant-llam-6735-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-espresso-ant-llam-6735-v2/flywheel_model.1.safetensors
chaiml-espresso-ant-llam-6735-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-espresso-ant-llam-6735-v2/flywheel_model.0.safetensors
Job chaiml-espresso-ant-llam-6735-v2-mkmlizer completed after 144.22s with status: succeeded
Stopping job with name chaiml-espresso-ant-llam-6735-v2-mkmlizer
Pipeline stage MKMLizer completed in 146.02s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-espresso-ant-llam-6735-v2
Waiting for inference service chaiml-espresso-ant-llam-6735-v2 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
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 chaiml-espresso-ant-llam-6735-v2 ready after 191.59259963035583s
Pipeline stage MKMLDeployer completed in 193.39s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.220517635345459s
Received healthy response to inference request in 2.4298086166381836s
Received healthy response to inference request in 2.235611915588379s
Received healthy response to inference request in 2.9065802097320557s
Received healthy response to inference request in 2.3351757526397705s
5 requests
0 failed requests
5th percentile: 2.255524682998657
10th percentile: 2.2754374504089356
20th percentile: 2.3152629852294924
30th percentile: 2.3541023254394533
40th percentile: 2.3919554710388184
50th percentile: 2.4298086166381836
60th percentile: 2.6205172538757324
70th percentile: 2.8112258911132812
80th percentile: 2.9693676948547365
90th percentile: 3.0949426651000977
95th percentile: 3.157730150222778
99th percentile: 3.2079601383209226
mean time: 2.6255388259887695
Pipeline stage StressChecker completed in 14.49s
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 2.14s
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
chaiml-espresso-ant-llam_6735_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 3069.13s
Shutdown handler de-registered
chaiml-espresso-ant-llam_6735_v2 status is now inactive due to auto deactivation removed underperforming models