developer_uid: azuruce
submission_id: chaiml-small-story-607-_8056_v13
model_name: chaiml-small-story-607-_8056_v13
model_group: ChaiML/small_story_607-e
status: inactive
timestamp: 2024-11-27T22:08:59+00:00
num_battles: 11991
num_wins: 5853
celo_rating: 1250.84
family_friendly_score: 0.5794
family_friendly_standard_error: 0.0069813414183808545
submission_type: basic
model_repo: ChaiML/small_story_607-ed10-100_true_rpg_v3_sft
model_architecture: MistralForCausalLM
model_num_parameters: 22247282688.0
best_of: 4
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.3882659933922482, 'latency_mean': 2.575491735935211, 'latency_p50': 2.5715770721435547, 'latency_p90': 2.835404467582703}, {'batch_size': 3, 'throughput': 0.8236709987927162, 'latency_mean': 3.6332371747493744, 'latency_p50': 3.6349316835403442, 'latency_p90': 4.047650003433227}, {'batch_size': 5, 'throughput': 1.0911041207987084, 'latency_mean': 4.550695482492447, 'latency_p50': 4.552812933921814, 'latency_p90': 5.152696847915649}, {'batch_size': 6, 'throughput': 1.17966867350918, 'latency_mean': 5.0575384163856505, 'latency_p50': 5.041591167449951, 'latency_p90': 5.716701626777649}, {'batch_size': 10, 'throughput': 1.3987888053927784, 'latency_mean': 7.083790237903595, 'latency_p50': 7.143643498420715, 'latency_p90': 8.060577535629273}]
gpu_counts: {'NVIDIA RTX A6000': 1}
display_name: chaiml-small-story-607-_8056_v13
is_internal_developer: True
language_model: ChaiML/small_story_607-ed10-100_true_rpg_v3_sft
model_size: 22B
ranking_group: single
throughput_3p7s: 0.85
us_pacific_date: 2024-11-27
win_ratio: 0.48811608706529896
generation_params: {'temperature': 0.8, 'top_p': 1.0, 'min_p': 0.1, 'top_k': 40, '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-story-607-8056-v13-mkmlizer
Waiting for job on chaiml-small-story-607-8056-v13-mkmlizer to finish
chaiml-small-story-607-8056-v13-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-small-story-607-8056-v13-mkmlizer: ║     _____            __           __                                ║
chaiml-small-story-607-8056-v13-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-small-story-607-8056-v13-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-small-story-607-8056-v13-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-small-story-607-8056-v13-mkmlizer: ║       /___/                                                         ║
chaiml-small-story-607-8056-v13-mkmlizer: ║                                                                     ║
chaiml-small-story-607-8056-v13-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-small-story-607-8056-v13-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-small-story-607-8056-v13-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-small-story-607-8056-v13-mkmlizer: ║                                                                     ║
chaiml-small-story-607-8056-v13-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-small-story-607-8056-v13-mkmlizer: ║  belonging to:                                                      ║
chaiml-small-story-607-8056-v13-mkmlizer: ║                                                                     ║
chaiml-small-story-607-8056-v13-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-small-story-607-8056-v13-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-small-story-607-8056-v13-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-small-story-607-8056-v13-mkmlizer: ║                                                                     ║
chaiml-small-story-607-8056-v13-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
chaiml-small-story-607-8056-v13-mkmlizer: Downloaded to shared memory in 54.670s
chaiml-small-story-607-8056-v13-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp8wg91g0q, device:0
chaiml-small-story-607-8056-v13-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-small-story-607-8056-v13-mkmlizer: quantized model in 43.911s
chaiml-small-story-607-8056-v13-mkmlizer: Processed model ChaiML/small_story_607-ed10-100_true_rpg_v3_sft in 98.581s
chaiml-small-story-607-8056-v13-mkmlizer: creating bucket guanaco-mkml-models
chaiml-small-story-607-8056-v13-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-small-story-607-8056-v13-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-small-story-607-8056-v13
chaiml-small-story-607-8056-v13-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-small-story-607-8056-v13/config.json
chaiml-small-story-607-8056-v13-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-small-story-607-8056-v13/special_tokens_map.json
chaiml-small-story-607-8056-v13-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-small-story-607-8056-v13/tokenizer_config.json
chaiml-small-story-607-8056-v13-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-small-story-607-8056-v13/tokenizer.json
Failed to get response for submission chaiml-small-story-607-e_8056_v4: ('http://chaiml-small-story-607-e-8056-v4-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:36962->127.0.0.1:8080: read: connection reset by peer\n')
chaiml-small-story-607-8056-v13-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-small-story-607-8056-v13/flywheel_model.1.safetensors
chaiml-small-story-607-8056-v13-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-small-story-607-8056-v13/flywheel_model.0.safetensors
Job chaiml-small-story-607-8056-v13-mkmlizer completed after 135.01s with status: succeeded
Stopping job with name chaiml-small-story-607-8056-v13-mkmlizer
Pipeline stage MKMLizer completed in 135.47s
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-small-story-607-8056-v13
Waiting for inference service chaiml-small-story-607-8056-v13 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-small-story-607-8056-v13 ready after 130.44724917411804s
Pipeline stage MKMLDeployer completed in 130.88s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.170325756072998s
Received healthy response to inference request in 2.49615478515625s
Received healthy response to inference request in 2.65210223197937s
Received healthy response to inference request in 2.2489821910858154s
Received healthy response to inference request in 2.567647933959961s
5 requests
0 failed requests
5th percentile: 2.2984167098999024
10th percentile: 2.3478512287139894
20th percentile: 2.446720266342163
30th percentile: 2.5104534149169924
40th percentile: 2.5390506744384767
50th percentile: 2.567647933959961
60th percentile: 2.601429653167725
70th percentile: 2.635211372375488
80th percentile: 2.755746936798096
90th percentile: 2.9630363464355467
95th percentile: 3.0666810512542724
99th percentile: 3.149596815109253
mean time: 2.6270425796508787
Pipeline stage StressChecker completed in 14.88s
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 2.00s
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 2.46s
Shutdown handler de-registered
chaiml-small-story-607-_8056_v13 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Skipping teardown as no inference service was successfully deployed
Pipeline stage MKMLProfilerDeleter completed in 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-small-story-607-8056-v13-profiler
Waiting for inference service chaiml-small-story-607-8056-v13-profiler to be ready
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 3471.73s
Shutdown handler de-registered
chaiml-small-story-607-_8056_v13 status is now inactive due to auto deactivation removed underperforming models