chaiml-small-anthropic-a_1700

developer_uid: azuruce

submission_id: chaiml-small-anthropic-a_1700_v8

model_name: anthropic1120

model_group: ChaiML/small_anthropic_a

status: inactive

timestamp: 2024-11-19T21:17:59+00:00

num_battles: 7700

num_wins: 4033

celo_rating: 1271.79

family_friendly_score: 0.5836

family_friendly_standard_error: 0.0069715283833604235

submission_type: basic

model_repo: ChaiML/small_anthropic_addict_lexical_1120

model_architecture: MistralForCausalLM

model_num_parameters: 22247282688.0

best_of: 4

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.3888906624699758, 'latency_mean': 2.5713179159164428, 'latency_p50': 2.553155303001404, 'latency_p90': 2.836304712295532}, {'batch_size': 3, 'throughput': 0.8266225278288694, 'latency_mean': 3.613945071697235, 'latency_p50': 3.5865087509155273, 'latency_p90': 3.9787868738174437}, {'batch_size': 5, 'throughput': 1.0943666808044297, 'latency_mean': 4.532536927461624, 'latency_p50': 4.5018733739852905, 'latency_p90': 5.074099469184875}, {'batch_size': 6, 'throughput': 1.1926078136317815, 'latency_mean': 5.007439349889755, 'latency_p50': 4.979215860366821, 'latency_p90': 5.619408106803894}, {'batch_size': 8, 'throughput': 1.320574167771249, 'latency_mean': 6.006802421808243, 'latency_p50': 5.94534432888031, 'latency_p90': 6.946212363243103}, {'batch_size': 10, 'throughput': 1.40363049117031, 'latency_mean': 7.057158161401748, 'latency_p50': 7.011192440986633, 'latency_p90': 8.010404753684996}]

gpu_counts: {'NVIDIA RTX A6000': 1}

display_name: anthropic1120

is_internal_developer: True

language_model: ChaiML/small_anthropic_addict_lexical_1120

model_size: 22B

ranking_group: single

throughput_3p7s: 0.86

us_pacific_date: 2024-11-19

win_ratio: 0.5237662337662338

generation_params: {'temperature': 0.9, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 80, '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-small-anthropic-a-1700-v8-mkmlizer
Waiting for job on chaiml-small-anthropic-a-1700-v8-mkmlizer to finish
chaiml-small-anthropic-a-1700-v8-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-small-anthropic-a-1700-v8-mkmlizer: ║     _____            __           __                                ║
chaiml-small-anthropic-a-1700-v8-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-small-anthropic-a-1700-v8-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-small-anthropic-a-1700-v8-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-small-anthropic-a-1700-v8-mkmlizer: ║       /___/                                                         ║
chaiml-small-anthropic-a-1700-v8-mkmlizer: ║                                                                     ║
chaiml-small-anthropic-a-1700-v8-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-small-anthropic-a-1700-v8-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-small-anthropic-a-1700-v8-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-small-anthropic-a-1700-v8-mkmlizer: ║                                                                     ║
chaiml-small-anthropic-a-1700-v8-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-small-anthropic-a-1700-v8-mkmlizer: ║  belonging to:                                                      ║
chaiml-small-anthropic-a-1700-v8-mkmlizer: ║                                                                     ║
chaiml-small-anthropic-a-1700-v8-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-small-anthropic-a-1700-v8-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-small-anthropic-a-1700-v8-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-small-anthropic-a-1700-v8-mkmlizer: ║                                                                     ║
chaiml-small-anthropic-a-1700-v8-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
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
Connection pool is full, discarding connection: %s. Connection pool size: %s
chaiml-small-anthropic-a-1700-v8-mkmlizer: Downloaded to shared memory in 94.922s
chaiml-small-anthropic-a-1700-v8-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpdschedtk, device:0
chaiml-small-anthropic-a-1700-v8-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
chaiml-small-anthropic-a-1700-v8-mkmlizer: quantized model in 43.273s
chaiml-small-anthropic-a-1700-v8-mkmlizer: Processed model ChaiML/small_anthropic_addict_lexical_1120 in 138.195s
chaiml-small-anthropic-a-1700-v8-mkmlizer: creating bucket guanaco-mkml-models
chaiml-small-anthropic-a-1700-v8-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-small-anthropic-a-1700-v8-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-small-anthropic-a-1700-v8
chaiml-small-anthropic-a-1700-v8-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-small-anthropic-a-1700-v8/config.json
chaiml-small-anthropic-a-1700-v8-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-small-anthropic-a-1700-v8/special_tokens_map.json
chaiml-small-anthropic-a-1700-v8-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-small-anthropic-a-1700-v8/tokenizer_config.json
chaiml-small-anthropic-a-1700-v8-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-small-anthropic-a-1700-v8/flywheel_model.1.safetensors
chaiml-small-anthropic-a-1700-v8-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-small-anthropic-a-1700-v8/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
Job chaiml-small-anthropic-a-1700-v8-mkmlizer completed after 167.87s with status: succeeded
Stopping job with name chaiml-small-anthropic-a-1700-v8-mkmlizer
Pipeline stage MKMLizer completed in 168.59s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLDeployer
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
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Creating inference service chaiml-small-anthropic-a-1700-v8
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Waiting for inference service chaiml-small-anthropic-a-1700-v8 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
Inference service chaiml-small-anthropic-a-1700-v8 ready after 210.77457451820374s
Pipeline stage MKMLDeployer completed in 211.74s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.30865216255188s
Received healthy response to inference request in 2.3019325733184814s
Received healthy response to inference request in 2.2166459560394287s
Received healthy response to inference request in 2.299600601196289s
Received healthy response to inference request in 2.3176779747009277s
5 requests
0 failed requests
5th percentile: 2.233236885070801
10th percentile: 2.249827814102173
20th percentile: 2.283009672164917
30th percentile: 2.3000669956207274
40th percentile: 2.3009997844696044
50th percentile: 2.3019325733184814
60th percentile: 2.30823073387146
70th percentile: 2.3145288944244387
80th percentile: 2.5158728122711183
90th percentile: 2.9122624874114993
95th percentile: 3.1104573249816894
99th percentile: 3.2690131950378416
mean time: 2.4889018535614014
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 2.58s
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 2.23s
Shutdown handler de-registered
chaiml-small-anthropic-a_1700_v8 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 2999.68s
Shutdown handler de-registered
chaiml-small-anthropic-a_1700_v8 status is now inactive due to auto deactivation removed underperforming models