rirv938-mistral-12b-bon_18156

developer_uid: rirv938

submission_id: rirv938-mistral-12b-bon_18156_v1

model_name: rirv938-mistral-12b-bon_18156_v1

model_group: rirv938/mistral_12b_bon_

status: torndown

timestamp: 2025-02-19T18:23:54+00:00

num_battles: 5847

num_wins: 2911

celo_rating: 1260.63

family_friendly_score: 0.5796

family_friendly_standard_error: 0.006980885903665809

submission_type: basic

model_repo: rirv938/mistral_12b_bon_oai_prompts_w8_504_v2

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.6021053764439634, 'latency_mean': 1.660773504972458, 'latency_p50': 1.6609973907470703, 'latency_p90': 1.8360482215881346}, {'batch_size': 3, 'throughput': 1.090348524973643, 'latency_mean': 2.7409705007076264, 'latency_p50': 2.718950629234314, 'latency_p90': 3.0183489084243775}, {'batch_size': 5, 'throughput': 1.3126384189983686, 'latency_mean': 3.8006825137138365, 'latency_p50': 3.7674885988235474, 'latency_p90': 4.265605831146241}, {'batch_size': 6, 'throughput': 1.3797295627371016, 'latency_mean': 4.329712324142456, 'latency_p50': 4.295740246772766, 'latency_p90': 4.864804196357727}, {'batch_size': 8, 'throughput': 1.4321740867797237, 'latency_mean': 5.5483947789669035, 'latency_p50': 5.513489842414856, 'latency_p90': 6.271333169937134}, {'batch_size': 10, 'throughput': 1.4664879562086128, 'latency_mean': 6.7610101318359375, 'latency_p50': 6.756892800331116, 'latency_p90': 7.603424096107483}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: rirv938-mistral-12b-bon_18156_v1

is_internal_developer: True

language_model: rirv938/mistral_12b_bon_oai_prompts_w8_504_v2

model_size: 13B

ranking_group: single

throughput_3p7s: 1.3

us_pacific_date: 2025-02-19

win_ratio: 0.4978621515306995

generation_params: {'temperature': 0.9, 'top_p': 0.9, 'min_p': 0.6, 'top_k': 80, 'presence_penalty': 0.5, 'frequency_penalty': 0.5, 'stopping_words': ['\n', '</s>', '###', 'You:'], 'max_input_tokens': 1024, 'best_of': 8, '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 rirv938-mistral-12b-bon-18156-v1-mkmlizer
Waiting for job on rirv938-mistral-12b-bon-18156-v1-mkmlizer to finish
Failed to get response for submission chaiml-20250219-c-4epoc_80755_v1: HTTPConnectionPool(host='chaiml-20250219-c-4epoc-80755-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
rirv938-mistral-12b-bon-18156-v1-mkmlizer: Downloaded to shared memory in 98.585s
rirv938-mistral-12b-bon-18156-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpz6z5gey8, device:0
rirv938-mistral-12b-bon-18156-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-mistral-12b-bon-18156-v1-mkmlizer: quantized model in 44.320s
rirv938-mistral-12b-bon-18156-v1-mkmlizer: Processed model rirv938/mistral_12b_bon_oai_prompts_w8_504_v2 in 142.906s
rirv938-mistral-12b-bon-18156-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-mistral-12b-bon-18156-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-mistral-12b-bon-18156-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-mistral-12b-bon-18156-v1
rirv938-mistral-12b-bon-18156-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-mistral-12b-bon-18156-v1/config.json
rirv938-mistral-12b-bon-18156-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-mistral-12b-bon-18156-v1/special_tokens_map.json
rirv938-mistral-12b-bon-18156-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-mistral-12b-bon-18156-v1/tokenizer_config.json
rirv938-mistral-12b-bon-18156-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-mistral-12b-bon-18156-v1/tokenizer.json
rirv938-mistral-12b-bon-18156-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-mistral-12b-bon-18156-v1/flywheel_model.0.safetensors
Job rirv938-mistral-12b-bon-18156-v1-mkmlizer completed after 175.35s with status: succeeded
Stopping job with name rirv938-mistral-12b-bon-18156-v1-mkmlizer
Pipeline stage MKMLizer completed in 175.87s
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 rirv938-mistral-12b-bon-18156-v1
Waiting for inference service rirv938-mistral-12b-bon-18156-v1 to be ready
Failed to get response for submission mistralai-mistral-nem_93303_v369: HTTPConnectionPool(host='mistralai-mistral-nem-93303-v369-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission mistralai-mistral-nem_93303_v369: HTTPConnectionPool(host='mistralai-mistral-nem-93303-v369-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission chaiml-20250219-c-4epoc_80755_v1: HTTPConnectionPool(host='chaiml-20250219-c-4epoc-80755-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission mistralai-mistral-nem_93303_v369: HTTPConnectionPool(host='mistralai-mistral-nem-93303-v369-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service rirv938-mistral-12b-bon-18156-v1 ready after 171.38529253005981s
Pipeline stage MKMLDeployer completed in 171.91s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3074874877929688s
Received healthy response to inference request in 1.6945316791534424s
Received healthy response to inference request in 1.5707049369812012s
Failed to get response for submission chaiml-20250219-c-4epoc_80755_v1: HTTPConnectionPool(host='chaiml-20250219-c-4epoc-80755-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Received healthy response to inference request in 1.6073153018951416s
Received healthy response to inference request in 1.7201778888702393s
5 requests
0 failed requests
5th percentile: 1.5780270099639893
10th percentile: 1.5853490829467773
20th percentile: 1.5999932289123535
30th percentile: 1.6247585773468018
40th percentile: 1.6596451282501221
50th percentile: 1.6945316791534424
60th percentile: 1.7047901630401612
70th percentile: 1.71504864692688
80th percentile: 1.8376398086547852
90th percentile: 2.072563648223877
95th percentile: 2.190025568008423
99th percentile: 2.2839951038360597
mean time: 1.7800434589385987
Pipeline stage StressChecker completed in 10.16s
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 0.67s
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
rirv938-mistral-12b-bon_18156_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 0.08s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rirv938-mistral-12b-bon-18156-v1-profiler
Waiting for inference service rirv938-mistral-12b-bon-18156-v1-profiler to be ready
Inference service rirv938-mistral-12b-bon-18156-v1-profiler ready after 170.66869401931763s
Pipeline stage MKMLProfilerDeployer completed in 171.05s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/rirv938-mistral-12b-5e89f507df271e80e03f1e64a38f7b8a-deplolgbm7:/code/chaiverse_profiler_1739990036 --namespace tenant-chaiml-guanaco
kubectl exec -it rirv938-mistral-12b-5e89f507df271e80e03f1e64a38f7b8a-deplolgbm7 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1739990036 && python profiles.py profile --best_of_n 8 --auto_batch 5 --batches 1,5,10,15,20,25,30,35,40,45,50,55,60,65,70,75,80,85,90,95,100,105,110,115,120,125,130,135,140,145,150,155,160,165,170,175,180,185,190,195 --samples 200 --input_tokens 1024 --output_tokens 64 --summary /code/chaiverse_profiler_1739990036/summary.json'
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 2606.31s
Shutdown handler de-registered
rirv938-mistral-12b-bon_18156_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-mistral-12b-bon_18156_v1 status is now torndown due to DeploymentManager action
rirv938-mistral-12b-bon_18156_v1 status is now torndown due to DeploymentManager action
rirv938-mistral-12b-bon_18156_v1 status is now torndown due to DeploymentManager action

ChatRequest

Bot Name

Generation Params

Prompt Formatter

ChatMessage 1

Sender

Message

User Message