chaiml-exp202-dpo-b01-2_43476

developer_uid: NischayDnk

submission_id: chaiml-exp202-dpo-b01-2_43476_v1

model_name: chaiml-exp202-dpo-b01-2_43476_v1

model_group: ChaiML/exp202-dpo-b01-2e

status: torndown

timestamp: 2025-04-12T17:26:59+00:00

num_battles: 8171

num_wins: 4590

celo_rating: 1331.74

family_friendly_score: 0.5214

family_friendly_standard_error: 0.007064588310722713

submission_type: basic

model_repo: ChaiML/exp202-dpo-b01-2e-ft-mistral31dpo3e-exp1-selfdist-9kconv-s75

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': 0.3695540523043194, 'latency_mean': 2.7058664572238924, 'latency_p50': 2.707743525505066, 'latency_p90': 3.007833480834961}, {'batch_size': 2, 'throughput': 0.5749704018630082, 'latency_mean': 3.477816271781921, 'latency_p50': 3.4820594787597656, 'latency_p90': 3.8117072343826295}, {'batch_size': 3, 'throughput': 0.7296345565061754, 'latency_mean': 4.102879981994629, 'latency_p50': 4.095335364341736, 'latency_p90': 4.531757593154907}, {'batch_size': 4, 'throughput': 0.8483709715699929, 'latency_mean': 4.697816072702408, 'latency_p50': 4.703273296356201, 'latency_p90': 5.238615560531616}, {'batch_size': 5, 'throughput': 0.9403763584918603, 'latency_mean': 5.283346573114395, 'latency_p50': 5.2938069105148315, 'latency_p90': 6.0053623676300045}]

gpu_counts: {'NVIDIA RTX A6000': 1}

display_name: chaiml-exp202-dpo-b01-2_43476_v1

is_internal_developer: False

language_model: ChaiML/exp202-dpo-b01-2e-ft-mistral31dpo3e-exp1-selfdist-9kconv-s75

model_size: 24B

ranking_group: single

throughput_3p7s: 0.64

us_pacific_date: 2025-04-12

win_ratio: 0.5617427487455636

generation_params: {'temperature': 0.5, 'top_p': 0.95, 'min_p': 0.025, 'top_k': 70, 'presence_penalty': 0.45, 'frequency_penalty': 0.45, 'stopping_words': ['<|im_end|>', '<|im_start|>', '\n'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': '<|system|>Family Friendly{memory}\n', 'prompt_template': '', 'bot_template': '<|im_start|>assistant\n{message}<|im_end|>\n', 'user_template': '<|im_start|>user\nYou:{message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n', '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-exp202-dpo-b01-2-43476-v1-mkmlizer
Waiting for job on chaiml-exp202-dpo-b01-2-43476-v1-mkmlizer to finish
chaiml-exp202-dpo-b01-2-43476-v1-mkmlizer: Downloaded to shared memory in 80.345s
chaiml-exp202-dpo-b01-2-43476-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpbst450ez, device:0
chaiml-exp202-dpo-b01-2-43476-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-exp202-dpo-b01-2-43476-v1-mkmlizer: quantized model in 53.480s
chaiml-exp202-dpo-b01-2-43476-v1-mkmlizer: Processed model ChaiML/exp202-dpo-b01-2e-ft-mistral31dpo3e-exp1-selfdist-9kconv-s75 in 133.825s
chaiml-exp202-dpo-b01-2-43476-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-exp202-dpo-b01-2-43476-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-exp202-dpo-b01-2-43476-v1
chaiml-exp202-dpo-b01-2-43476-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-exp202-dpo-b01-2-43476-v1/config.json
chaiml-exp202-dpo-b01-2-43476-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-exp202-dpo-b01-2-43476-v1/special_tokens_map.json
chaiml-exp202-dpo-b01-2-43476-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-exp202-dpo-b01-2-43476-v1/tokenizer_config.json
chaiml-exp202-dpo-b01-2-43476-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-exp202-dpo-b01-2-43476-v1/tokenizer.json
chaiml-exp202-dpo-b01-2-43476-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-exp202-dpo-b01-2-43476-v1/flywheel_model.1.safetensors
chaiml-exp202-dpo-b01-2-43476-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-exp202-dpo-b01-2-43476-v1/flywheel_model.0.safetensors
Job chaiml-exp202-dpo-b01-2-43476-v1-mkmlizer completed after 177.38s with status: succeeded
Stopping job with name chaiml-exp202-dpo-b01-2-43476-v1-mkmlizer
Pipeline stage MKMLizer completed in 177.84s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-exp202-dpo-b01-2-43476-v1
Waiting for inference service chaiml-exp202-dpo-b01-2-43476-v1 to be ready
Inference service chaiml-exp202-dpo-b01-2-43476-v1 ready after 120.58241248130798s
Pipeline stage MKMLDeployer completed in 120.99s
run pipeline stage %s
Running pipeline stage StressChecker
HTTPConnectionPool(host='guanaco-submitter.guanaco-backend.k2.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
Received healthy response to inference request in 3.2979788780212402s
Received healthy response to inference request in 2.4560739994049072s
Received healthy response to inference request in 2.9385108947753906s
Received healthy response to inference request in 2.482100009918213s
5 requests
1 failed requests
5th percentile: 2.461279201507568
10th percentile: 2.4664844036102296
20th percentile: 2.476894807815552
30th percentile: 2.5733821868896483
40th percentile: 2.7559465408325194
50th percentile: 2.9385108947753906
60th percentile: 3.0822980880737303
70th percentile: 3.2260852813720704
80th percentile: 6.6647437095642115
90th percentile: 13.398273372650149
95th percentile: 16.76503820419311
99th percentile: 19.45845006942749
mean time: 6.261293363571167
%s, retrying in %s seconds...
Received healthy response to inference request in 2.431532621383667s
Received healthy response to inference request in 2.8378639221191406s
Received healthy response to inference request in 2.7701005935668945s
Received healthy response to inference request in 2.4486751556396484s
Received healthy response to inference request in 2.4469058513641357s
5 requests
0 failed requests
5th percentile: 2.4346072673797607
10th percentile: 2.4376819133758545
20th percentile: 2.443831205368042
30th percentile: 2.447259712219238
40th percentile: 2.4479674339294433
50th percentile: 2.4486751556396484
60th percentile: 2.577245330810547
70th percentile: 2.705815505981445
80th percentile: 2.7836532592773438
90th percentile: 2.810758590698242
95th percentile: 2.8243112564086914
99th percentile: 2.8351533889770506
mean time: 2.5870156288146973
Pipeline stage StressChecker completed in 46.59s
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 0.91s
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 0.69s
Shutdown handler de-registered
chaiml-exp202-dpo-b01-2_43476_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 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-exp202-dpo-b01-2-43476-v1-profiler
Waiting for inference service chaiml-exp202-dpo-b01-2-43476-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 4963.95s
Shutdown handler de-registered
chaiml-exp202-dpo-b01-2_43476_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-exp202-dpo-b01-2_43476_v1 status is now torndown due to DeploymentManager action