chaiml-nis-proj1-exp1-s_15898

developer_uid: NischayDnk

submission_id: chaiml-nis-proj1-exp1-s_15898_v1

model_name: chaiml-nis-proj1-exp1-s_15898_v1

model_group: ChaiML/nis-proj1-exp1-sf

status: torndown

timestamp: 2025-03-26T20:59:17+00:00

num_battles: 7320

num_wins: 3661

celo_rating: 1282.43

family_friendly_score: 0.5644

family_friendly_standard_error: 0.007012169992234929

submission_type: basic

model_repo: ChaiML/nis-proj1-exp1-sft-prev1-type1-random-try1

model_architecture: MistralForCausalLM

model_num_parameters: 24096691200.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.3697923587028199, 'latency_mean': 2.7041265666484833, 'latency_p50': 2.69344961643219, 'latency_p90': 2.998358702659607}, {'batch_size': 2, 'throughput': 0.5854700796211539, 'latency_mean': 3.4150971329212187, 'latency_p50': 3.3978112936019897, 'latency_p90': 3.7745777368545532}, {'batch_size': 3, 'throughput': 0.7309910195600239, 'latency_mean': 4.097628656625748, 'latency_p50': 4.08278226852417, 'latency_p90': 4.4800924301147464}, {'batch_size': 4, 'throughput': 0.8564742975627684, 'latency_mean': 4.660359536409378, 'latency_p50': 4.675550222396851, 'latency_p90': 5.213124394416809}, {'batch_size': 5, 'throughput': 0.951894593425879, 'latency_mean': 5.222972692251205, 'latency_p50': 5.196145296096802, 'latency_p90': 5.81524817943573}]

gpu_counts: {'NVIDIA RTX A6000': 1}

display_name: chaiml-nis-proj1-exp1-s_15898_v1

is_internal_developer: False

language_model: ChaiML/nis-proj1-exp1-sft-prev1-type1-random-try1

model_size: 24B

ranking_group: single

throughput_3p7s: 0.65

us_pacific_date: 2025-03-26

win_ratio: 0.5001366120218579

generation_params: {'temperature': 0.45, 'top_p': 0.9, 'min_p': 0.05, 'top_k': 40, 'presence_penalty': 0.4, 'frequency_penalty': 0.4, 'stopping_words': ['\n'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': '<|im_start|>system\n{memory}<|im_end|>\n', 'prompt_template': '<|im_start|>user\n{prompt}<|im_end|>\n', 'bot_template': '<|im_start|>assistant\n{bot_name}: {message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{user_name}: {message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n{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-nis-proj1-exp1-s-15898-v1-mkmlizer
Waiting for job on chaiml-nis-proj1-exp1-s-15898-v1-mkmlizer to finish
chaiml-nis-proj1-exp1-s-15898-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-nis-proj1-exp1-s-15898-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-nis-proj1-exp1-s-15898-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-nis-proj1-exp1-s-15898-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-nis-proj1-exp1-s-15898-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-nis-proj1-exp1-s-15898-v1-mkmlizer: ║       /___/                                                         ║
chaiml-nis-proj1-exp1-s-15898-v1-mkmlizer: ║                                                                     ║
chaiml-nis-proj1-exp1-s-15898-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
chaiml-nis-proj1-exp1-s-15898-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-nis-proj1-exp1-s-15898-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-nis-proj1-exp1-s-15898-v1-mkmlizer: ║                                                                     ║
chaiml-nis-proj1-exp1-s-15898-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-nis-proj1-exp1-s-15898-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-nis-proj1-exp1-s-15898-v1-mkmlizer: ║                                                                     ║
chaiml-nis-proj1-exp1-s-15898-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-nis-proj1-exp1-s-15898-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-nis-proj1-exp1-s-15898-v1-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
chaiml-nis-proj1-exp1-s-15898-v1-mkmlizer: ║                                                                     ║
chaiml-nis-proj1-exp1-s-15898-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-nis-proj1-exp1-s-15898-v1-mkmlizer: Downloaded to shared memory in 81.770s
chaiml-nis-proj1-exp1-s-15898-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp4ty2ens_, device:0
chaiml-nis-proj1-exp1-s-15898-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-nis-proj1-exp1-s-15898-v1-mkmlizer: quantized model in 52.355s
chaiml-nis-proj1-exp1-s-15898-v1-mkmlizer: Processed model ChaiML/nis-proj1-exp1-sft-prev1-type1-random-try1 in 134.126s
chaiml-nis-proj1-exp1-s-15898-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-nis-proj1-exp1-s-15898-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-nis-proj1-exp1-s-15898-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-nis-proj1-exp1-s-15898-v1
chaiml-nis-proj1-exp1-s-15898-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-nis-proj1-exp1-s-15898-v1/special_tokens_map.json
chaiml-nis-proj1-exp1-s-15898-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-nis-proj1-exp1-s-15898-v1/config.json
chaiml-nis-proj1-exp1-s-15898-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-nis-proj1-exp1-s-15898-v1/tokenizer_config.json
chaiml-nis-proj1-exp1-s-15898-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-nis-proj1-exp1-s-15898-v1/tokenizer.json
chaiml-nis-proj1-exp1-s-15898-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-nis-proj1-exp1-s-15898-v1/flywheel_model.1.safetensors
chaiml-nis-proj1-exp1-s-15898-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-nis-proj1-exp1-s-15898-v1/flywheel_model.0.safetensors
Job chaiml-nis-proj1-exp1-s-15898-v1-mkmlizer completed after 166.69s with status: succeeded
Stopping job with name chaiml-nis-proj1-exp1-s-15898-v1-mkmlizer
Pipeline stage MKMLizer completed in 167.16s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-nis-proj1-exp1-s-15898-v1
Waiting for inference service chaiml-nis-proj1-exp1-s-15898-v1 to be ready
Inference service chaiml-nis-proj1-exp1-s-15898-v1 ready after 110.46432876586914s
Pipeline stage MKMLDeployer completed in 111.02s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.4051320552825928s
Received healthy response to inference request in 2.5801308155059814s
Received healthy response to inference request in 2.6271142959594727s
Received healthy response to inference request in 2.5380396842956543s
Received healthy response to inference request in 2.597897529602051s
5 requests
0 failed requests
5th percentile: 2.5464579105377196
10th percentile: 2.554876136779785
20th percentile: 2.571712589263916
30th percentile: 2.5836841583251955
40th percentile: 2.590790843963623
50th percentile: 2.597897529602051
60th percentile: 2.6095842361450194
70th percentile: 2.621270942687988
80th percentile: 2.782717847824097
90th percentile: 3.093924951553345
95th percentile: 3.2495285034179684
99th percentile: 3.374011344909668
mean time: 2.7496628761291504
Pipeline stage StressChecker completed in 15.03s
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 0.68s
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 0.64s
Shutdown handler de-registered
chaiml-nis-proj1-exp1-s_15898_v1 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 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-nis-proj1-exp1-s-15898-v1-profiler
Waiting for inference service chaiml-nis-proj1-exp1-s-15898-v1-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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
clean up pipeline due to error=DeploymentChecksError('None: None')
Shutdown handler de-registered
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyScorer
Evaluating %s Family Friendly Score with %s threads
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 4416.49s
Shutdown handler de-registered
chaiml-nis-proj1-exp1-s_15898_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-nis-proj1-exp1-s_15898_v1 status is now torndown due to DeploymentManager action