developer_uid: rirv938
submission_id: rirv938-mistral-24b-dpo_50042_v1
model_name: rirv938-mistral-24b-dpo_50042_v1
model_group: rirv938/mistral_24b_dpo_
status: torndown
timestamp: 2025-03-25T01:20:06+00:00
num_battles: 7114
num_wins: 3644
celo_rating: 1290.41
family_friendly_score: 0.5214
family_friendly_standard_error: 0.007064588310722713
submission_type: basic
model_repo: rirv938/mistral_24b_dpo_kl_10k_beta4_1248_v3
model_architecture: MistralForCausalLM
model_num_parameters: 24096691200.0
best_of: 8
max_input_tokens: 768
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.38637124136034984, 'latency_mean': 2.5881188690662382, 'latency_p50': 2.597237229347229, 'latency_p90': 2.876840662956238}, {'batch_size': 3, 'throughput': 0.7838579911343639, 'latency_mean': 3.810575555562973, 'latency_p50': 3.8180272579193115, 'latency_p90': 4.191619133949279}, {'batch_size': 5, 'throughput': 1.0451847113771695, 'latency_mean': 4.752001550197601, 'latency_p50': 4.701439738273621, 'latency_p90': 5.3636380434036255}, {'batch_size': 6, 'throughput': 1.112350183999725, 'latency_mean': 5.3686256659030915, 'latency_p50': 5.393791317939758, 'latency_p90': 6.031130027770996}, {'batch_size': 10, 'throughput': 1.2763207293406331, 'latency_mean': 7.771908894777298, 'latency_p50': 7.765304684638977, 'latency_p90': 8.685333347320556}]
gpu_counts: {'NVIDIA RTX A6000': 1}
display_name: rirv938-mistral-24b-dpo_50042_v1
is_internal_developer: True
language_model: rirv938/mistral_24b_dpo_kl_10k_beta4_1248_v3
model_size: 24B
ranking_group: single
throughput_3p7s: 0.76
us_pacific_date: 2025-03-24
win_ratio: 0.512229406803486
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': 768, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': '[INST]', 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '[/INST]{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-24b-dpo-50042-v1-mkmlizer
Waiting for job on rirv938-mistral-24b-dpo-50042-v1-mkmlizer to finish
rirv938-mistral-24b-dpo-50042-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-mistral-24b-dpo-50042-v1-mkmlizer: ║ _____ __ __ ║
rirv938-mistral-24b-dpo-50042-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
rirv938-mistral-24b-dpo-50042-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
rirv938-mistral-24b-dpo-50042-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
rirv938-mistral-24b-dpo-50042-v1-mkmlizer: ║ /___/ ║
rirv938-mistral-24b-dpo-50042-v1-mkmlizer: ║ ║
rirv938-mistral-24b-dpo-50042-v1-mkmlizer: ║ Version: 0.12.8 ║
rirv938-mistral-24b-dpo-50042-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
rirv938-mistral-24b-dpo-50042-v1-mkmlizer: ║ https://mk1.ai ║
rirv938-mistral-24b-dpo-50042-v1-mkmlizer: ║ ║
rirv938-mistral-24b-dpo-50042-v1-mkmlizer: ║ The license key for the current software has been verified as ║
rirv938-mistral-24b-dpo-50042-v1-mkmlizer: ║ belonging to: ║
rirv938-mistral-24b-dpo-50042-v1-mkmlizer: ║ ║
rirv938-mistral-24b-dpo-50042-v1-mkmlizer: ║ Chai Research Corp. ║
rirv938-mistral-24b-dpo-50042-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
rirv938-mistral-24b-dpo-50042-v1-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
rirv938-mistral-24b-dpo-50042-v1-mkmlizer: ║ ║
rirv938-mistral-24b-dpo-50042-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-mistral-24b-dpo-50042-v1-mkmlizer: Downloaded to shared memory in 195.003s
rirv938-mistral-24b-dpo-50042-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpa49l864t, device:0
rirv938-mistral-24b-dpo-50042-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-mistral-24b-dpo-50042-v1-mkmlizer: quantized model in 66.220s
rirv938-mistral-24b-dpo-50042-v1-mkmlizer: Processed model rirv938/mistral_24b_dpo_kl_10k_beta4_1248_v3 in 261.224s
rirv938-mistral-24b-dpo-50042-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-mistral-24b-dpo-50042-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-mistral-24b-dpo-50042-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-50042-v1
rirv938-mistral-24b-dpo-50042-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-50042-v1/config.json
rirv938-mistral-24b-dpo-50042-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-50042-v1/special_tokens_map.json
rirv938-mistral-24b-dpo-50042-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-50042-v1/tokenizer_config.json
rirv938-mistral-24b-dpo-50042-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-50042-v1/tokenizer.json
rirv938-mistral-24b-dpo-50042-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-50042-v1/flywheel_model.1.safetensors
rirv938-mistral-24b-dpo-50042-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-50042-v1/flywheel_model.0.safetensors
Job rirv938-mistral-24b-dpo-50042-v1-mkmlizer completed after 297.72s with status: succeeded
Stopping job with name rirv938-mistral-24b-dpo-50042-v1-mkmlizer
Pipeline stage MKMLizer completed in 298.18s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rirv938-mistral-24b-dpo-50042-v1
Waiting for inference service rirv938-mistral-24b-dpo-50042-v1 to be ready
Inference service rirv938-mistral-24b-dpo-50042-v1 ready after 100.35985016822815s
Pipeline stage MKMLDeployer completed in 100.83s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.0032246112823486s
Received healthy response to inference request in 2.463641405105591s
Received healthy response to inference request in 2.834766387939453s
Received healthy response to inference request in 2.45453143119812s
Received healthy response to inference request in 2.7510857582092285s
5 requests
0 failed requests
5th percentile: 2.4563534259796143
10th percentile: 2.4581754207611084
20th percentile: 2.4618194103240967
30th percentile: 2.5211302757263185
40th percentile: 2.6361080169677735
50th percentile: 2.7510857582092285
60th percentile: 2.7845580101013185
70th percentile: 2.818030261993408
80th percentile: 2.8684580326080322
90th percentile: 2.9358413219451904
95th percentile: 2.9695329666137695
99th percentile: 2.996486282348633
mean time: 2.701449918746948
Pipeline stage StressChecker completed in 14.75s
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 0.62s
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 0.57s
Shutdown handler de-registered
rirv938-mistral-24b-dpo_50042_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 rirv938-mistral-24b-dpo-50042-v1-profiler
Waiting for inference service rirv938-mistral-24b-dpo-50042-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
Pipeline stage OfflineFamilyFriendlyScorer completed in 2949.20s
Shutdown handler de-registered
rirv938-mistral-24b-dpo_50042_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-mistral-24b-dpo_50042_v1 status is now torndown due to DeploymentManager action
ChatRequest
Generation Params
Prompt Formatter
Chat History
ChatMessage 1