chaiml-llama-8b-multihe_54063

developer_uid: rirv938
submission_id: chaiml-llama-8b-multihe_54063_v4
model_name: chaiml-llama-8b-multihe_54063_v4
model_group: ChaiML/llama_8b_multihea
status: torndown
timestamp: 2025-02-28T05:33:50+00:00
num_battles: 11155
num_wins: 5751
celo_rating: 1293.3
family_friendly_score: 0.5206
family_friendly_standard_error: 0.007065063906292709
submission_type: basic
model_repo: ChaiML/llama_8b_multihead_204m_preference
model_architecture: LlamaForSequenceClassification
model_num_parameters: 8030261248.0
best_of: 1
max_input_tokens: 512
max_output_tokens: 1
display_name: chaiml-llama-8b-multihe_54063_v4
ineligible_reason: max_output_tokens!=64
is_internal_developer: True
language_model: ChaiML/llama_8b_multihead_204m_preference
model_size: 8B
ranking_group: single
us_pacific_date: 2025-02-27
win_ratio: 0.5155535634244733
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 1, 'max_output_tokens': 1}
formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '', '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-llama-8b-multihe-54063-v4-mkmlizer
Waiting for job on chaiml-llama-8b-multihe-54063-v4-mkmlizer to finish
Failed to get response for submission rirv938-llama-8b-1024-t_67568_v3: HTTPConnectionPool(host='rirv938-llama-8b-1024-t-67568-v3-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
chaiml-llama-8b-multihe-54063-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-llama-8b-multihe-54063-v4-mkmlizer: ║     _____            __           __                                ║
chaiml-llama-8b-multihe-54063-v4-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-llama-8b-multihe-54063-v4-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-llama-8b-multihe-54063-v4-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-llama-8b-multihe-54063-v4-mkmlizer: ║       /___/                                                         ║
chaiml-llama-8b-multihe-54063-v4-mkmlizer: ║                                                                     ║
chaiml-llama-8b-multihe-54063-v4-mkmlizer: ║  Version: 0.12.8                                                    ║
chaiml-llama-8b-multihe-54063-v4-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-llama-8b-multihe-54063-v4-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-llama-8b-multihe-54063-v4-mkmlizer: ║                                                                     ║
chaiml-llama-8b-multihe-54063-v4-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-llama-8b-multihe-54063-v4-mkmlizer: ║  belonging to:                                                      ║
chaiml-llama-8b-multihe-54063-v4-mkmlizer: ║                                                                     ║
chaiml-llama-8b-multihe-54063-v4-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-llama-8b-multihe-54063-v4-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-llama-8b-multihe-54063-v4-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
chaiml-llama-8b-multihe-54063-v4-mkmlizer: ║                                                                     ║
chaiml-llama-8b-multihe-54063-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission rirv938-llama-8b-1024-t_67568_v3: HTTPConnectionPool(host='rirv938-llama-8b-1024-t-67568-v3-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
chaiml-llama-8b-multihe-54063-v4-mkmlizer: Downloaded to shared memory in 34.937s
chaiml-llama-8b-multihe-54063-v4-mkmlizer: quantizing model to /dev/shm/model_cache, profile:t0, folder:/tmp/tmpn4isu_w8, device:0
chaiml-llama-8b-multihe-54063-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission rirv938-llama-8b-1024-t_67568_v3: HTTPConnectionPool(host='rirv938-llama-8b-1024-t-67568-v3-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission rirv938-llama-8b-1024-t_67568_v3: HTTPConnectionPool(host='rirv938-llama-8b-1024-t-67568-v3-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
chaiml-llama-8b-multihe-54063-v4-mkmlizer: quantized model in 86.418s
chaiml-llama-8b-multihe-54063-v4-mkmlizer: Processed model ChaiML/llama_8b_multihead_204m_preference in 121.356s
chaiml-llama-8b-multihe-54063-v4-mkmlizer: creating bucket guanaco-mkml-models
chaiml-llama-8b-multihe-54063-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-llama-8b-multihe-54063-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-llama-8b-multihe-54063-v4
chaiml-llama-8b-multihe-54063-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-llama-8b-multihe-54063-v4/config.json
chaiml-llama-8b-multihe-54063-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-llama-8b-multihe-54063-v4/tokenizer_config.json
chaiml-llama-8b-multihe-54063-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-llama-8b-multihe-54063-v4/special_tokens_map.json
chaiml-llama-8b-multihe-54063-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-llama-8b-multihe-54063-v4/tokenizer.json
chaiml-llama-8b-multihe-54063-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-llama-8b-multihe-54063-v4/flywheel_model.0.safetensors
Job chaiml-llama-8b-multihe-54063-v4-mkmlizer completed after 156.08s with status: succeeded
Stopping job with name chaiml-llama-8b-multihe-54063-v4-mkmlizer
Pipeline stage MKMLizer completed in 156.52s
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-llama-8b-multihe-54063-v4
Waiting for inference service chaiml-llama-8b-multihe-54063-v4 to be ready
Failed to get response for submission rirv938-llama-8b-1024-t_67568_v3: HTTPConnectionPool(host='rirv938-llama-8b-1024-t-67568-v3-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission rirv938-llama-8b-1024-t_67568_v3: HTTPConnectionPool(host='rirv938-llama-8b-1024-t-67568-v3-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission rirv938-llama-8b-1024-t_67568_v3: HTTPConnectionPool(host='rirv938-llama-8b-1024-t-67568-v3-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission rirv938-llama-8b-1024-t_67568_v3: HTTPConnectionPool(host='rirv938-llama-8b-1024-t-67568-v3-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission rirv938-llama-8b-1024-t_67568_v3: HTTPConnectionPool(host='rirv938-llama-8b-1024-t-67568-v3-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission rirv938-llama-8b-1024-t_67568_v3: HTTPConnectionPool(host='rirv938-llama-8b-1024-t-67568-v3-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service chaiml-llama-8b-multihe-54063-v4 ready after 291.0193259716034s
Pipeline stage MKMLDeployer completed in 291.52s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 4.229800701141357s
Received healthy response to inference request in 4.913276672363281s
Received healthy response to inference request in 2.9658665657043457s
Received healthy response to inference request in 4.720964431762695s
Received healthy response to inference request in 3.4280495643615723s
5 requests
0 failed requests
5th percentile: 3.058303165435791
10th percentile: 3.1507397651672364
20th percentile: 3.335612964630127
30th percentile: 3.588399791717529
40th percentile: 3.9091002464294435
50th percentile: 4.229800701141357
60th percentile: 4.426266193389893
70th percentile: 4.622731685638428
80th percentile: 4.759426879882812
90th percentile: 4.836351776123047
95th percentile: 4.874814224243164
99th percentile: 4.905584182739258
mean time: 4.051591587066651
%s, retrying in %s seconds...
Received healthy response to inference request in 2.7360126972198486s
Received healthy response to inference request in 5.638333797454834s
Received healthy response to inference request in 3.869256019592285s
Received healthy response to inference request in 3.7270126342773438s
Received healthy response to inference request in 3.469484806060791s
5 requests
0 failed requests
5th percentile: 2.882707118988037
10th percentile: 3.0294015407562256
20th percentile: 3.3227903842926025
30th percentile: 3.5209903717041016
40th percentile: 3.6240015029907227
50th percentile: 3.7270126342773438
60th percentile: 3.7839099884033205
70th percentile: 3.840807342529297
80th percentile: 4.223071575164795
90th percentile: 4.9307026863098145
95th percentile: 5.284518241882324
99th percentile: 5.567570686340332
mean time: 3.8880199909210207
%s, retrying in %s seconds...
Received healthy response to inference request in 3.605724811553955s
Received healthy response to inference request in 3.222987174987793s
Received healthy response to inference request in 2.5010485649108887s
Received healthy response to inference request in 5.4197680950164795s
Received healthy response to inference request in 2.3538918495178223s
5 requests
0 failed requests
5th percentile: 2.3833231925964355
10th percentile: 2.412754535675049
20th percentile: 2.4716172218322754
30th percentile: 2.6454362869262695
40th percentile: 2.9342117309570312
50th percentile: 3.222987174987793
60th percentile: 3.3760822296142576
70th percentile: 3.5291772842407227
80th percentile: 3.96853346824646
90th percentile: 4.69415078163147
95th percentile: 5.056959438323974
99th percentile: 5.347206363677978
mean time: 3.4206840991973877
Pipeline stage StressChecker completed in 60.54s
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 0.73s
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 0.70s
Shutdown handler de-registered
chaiml-llama-8b-multihe_54063_v4 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 0.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-llama-8b-multihe-54063-v4-profiler
Waiting for inference service chaiml-llama-8b-multihe-54063-v4-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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
clean up pipeline due to error=DeploymentChecksError('None: Max retries exceeded with url: /v1/models/GPT-J-6B-lit-v2:predict (Caused by 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
Pipeline stage OfflineFamilyFriendlyScorer completed in 3651.25s
Shutdown handler de-registered
chaiml-llama-8b-multihe_54063_v4 status is now inactive due to auto deactivation removed underperforming models
chaiml-llama-8b-multihe_54063_v4 status is now torndown due to DeploymentManager action
ChatRequest
Bot Name
Generation Params
Prompt Formatter
ChatMessage 1
Sender
Message
User Message