developer_uid: azuruce
submission_id: chaiml-espresso-ant-llam_1666_v7
model_name: chaiml-espresso-ant-llam_1666_v7
model_group: ChaiML/espresso_ant_llam
status: inactive
timestamp: 2024-12-05T07:45:04+00:00
num_battles: 10266
num_wins: 5206
celo_rating: 1268.12
family_friendly_score: 0.5848
family_friendly_standard_error: 0.006968629133480989
submission_type: basic
model_repo: ChaiML/espresso_ant_llama_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': 0.3837766552913775, 'latency_mean': 2.60561408162117, 'latency_p50': 2.6113784313201904, 'latency_p90': 2.8869497537612916}, {'batch_size': 3, 'throughput': 0.8100845770909629, 'latency_mean': 3.691787635087967, 'latency_p50': 3.7029342651367188, 'latency_p90': 4.035726404190063}, {'batch_size': 5, 'throughput': 1.0767614697462995, 'latency_mean': 4.620913964509964, 'latency_p50': 4.613331913948059, 'latency_p90': 5.168066692352295}, {'batch_size': 6, 'throughput': 1.1583867887856816, 'latency_mean': 5.145098359584808, 'latency_p50': 5.16778290271759, 'latency_p90': 5.7437519311904905}, {'batch_size': 10, 'throughput': 1.3782884076110096, 'latency_mean': 7.197918752431869, 'latency_p50': 7.212834715843201, 'latency_p90': 8.047194933891296}]
gpu_counts: {'NVIDIA RTX A6000': 1}
display_name: chaiml-espresso-ant-llam_1666_v7
is_internal_developer: True
language_model: ChaiML/espresso_ant_llama_241204_albert_v2_sft_2epoch_128alpha
model_size: 22B
ranking_group: single
throughput_3p7s: 0.82
us_pacific_date: 2024-12-04
win_ratio: 0.507110851353984
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-1666-v7-mkmlizer
Waiting for job on chaiml-espresso-ant-llam-1666-v7-mkmlizer to finish
chaiml-espresso-ant-llam-1666-v7-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-espresso-ant-llam-1666-v7-mkmlizer: ║     _____            __           __                                ║
chaiml-espresso-ant-llam-1666-v7-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-espresso-ant-llam-1666-v7-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-espresso-ant-llam-1666-v7-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-espresso-ant-llam-1666-v7-mkmlizer: ║       /___/                                                         ║
chaiml-espresso-ant-llam-1666-v7-mkmlizer: ║                                                                     ║
chaiml-espresso-ant-llam-1666-v7-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-espresso-ant-llam-1666-v7-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-espresso-ant-llam-1666-v7-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-espresso-ant-llam-1666-v7-mkmlizer: ║                                                                     ║
chaiml-espresso-ant-llam-1666-v7-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-espresso-ant-llam-1666-v7-mkmlizer: ║  belonging to:                                                      ║
chaiml-espresso-ant-llam-1666-v7-mkmlizer: ║                                                                     ║
chaiml-espresso-ant-llam-1666-v7-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-espresso-ant-llam-1666-v7-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-espresso-ant-llam-1666-v7-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-espresso-ant-llam-1666-v7-mkmlizer: ║                                                                     ║
chaiml-espresso-ant-llam-1666-v7-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-espresso-ant-llam-1666-v7-mkmlizer: Downloaded to shared memory in 40.753s
chaiml-espresso-ant-llam-1666-v7-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp1m77yvaq, device:0
chaiml-espresso-ant-llam-1666-v7-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-espresso-ant-llam-1666-v7-mkmlizer: quantized model in 43.589s
chaiml-espresso-ant-llam-1666-v7-mkmlizer: Processed model ChaiML/espresso_ant_llama_241204_albert_v2_sft_2epoch_128alpha in 84.342s
chaiml-espresso-ant-llam-1666-v7-mkmlizer: creating bucket guanaco-mkml-models
chaiml-espresso-ant-llam-1666-v7-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-espresso-ant-llam-1666-v7-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-espresso-ant-llam-1666-v7
chaiml-espresso-ant-llam-1666-v7-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-espresso-ant-llam-1666-v7/config.json
chaiml-espresso-ant-llam-1666-v7-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-espresso-ant-llam-1666-v7/special_tokens_map.json
chaiml-espresso-ant-llam-1666-v7-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-espresso-ant-llam-1666-v7/tokenizer_config.json
chaiml-espresso-ant-llam-1666-v7-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-espresso-ant-llam-1666-v7/flywheel_model.1.safetensors
chaiml-espresso-ant-llam-1666-v7-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-espresso-ant-llam-1666-v7/flywheel_model.0.safetensors
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
Job chaiml-espresso-ant-llam-1666-v7-mkmlizer completed after 119.75s with status: succeeded
Stopping job with name chaiml-espresso-ant-llam-1666-v7-mkmlizer
Pipeline stage MKMLizer completed in 121.48s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-espresso-ant-llam-1666-v7
Waiting for inference service chaiml-espresso-ant-llam-1666-v7 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Failed to get response for submission chaiml-lexical-viral-v5a_3966_v3: ('http://chaiml-lexical-viral-v5a-3966-v3-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:49050->127.0.0.1:8080: read: connection reset by peer\n')
Inference service chaiml-espresso-ant-llam-1666-v7 ready after 185.7054362297058s
Pipeline stage MKMLDeployer completed in 187.27s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.6693789958953857s
Received healthy response to inference request in 2.3085319995880127s
Received healthy response to inference request in 2.4128520488739014s
Received healthy response to inference request in 2.445289373397827s
Received healthy response to inference request in 2.7975969314575195s
5 requests
0 failed requests
5th percentile: 2.3293960094451904
10th percentile: 2.350260019302368
20th percentile: 2.3919880390167236
30th percentile: 2.4193395137786866
40th percentile: 2.4323144435882567
50th percentile: 2.445289373397827
60th percentile: 2.5349252223968506
70th percentile: 2.624561071395874
80th percentile: 2.6950225830078125
90th percentile: 2.746309757232666
95th percentile: 2.7719533443450928
99th percentile: 2.792468214035034
mean time: 2.526729869842529
Pipeline stage StressChecker completed in 13.98s
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 2.11s
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 2.02s
Shutdown handler de-registered
chaiml-espresso-ant-llam_1666_v7 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 3065.49s
Shutdown handler de-registered
chaiml-espresso-ant-llam_1666_v7 status is now inactive due to auto deactivation removed underperforming models