developer_uid: AlexCuadron
submission_id: alexcuadron-dpo-roleplay_v2
model_name: alexcuadron-dpo-roleplay_v2
model_group: AlexCuadron/dpo_roleplay
status: torndown
timestamp: 2025-03-24T16:56:04+00:00
num_battles: 7294
num_wins: 3612
celo_rating: 1275.13
family_friendly_score: 0.5871999999999999
family_friendly_standard_error: 0.006962702923434261
submission_type: basic
model_repo: AlexCuadron/dpo_roleplay
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.6064272751484159, 'latency_mean': 1.6489044094085694, 'latency_p50': 1.654245376586914, 'latency_p90': 1.8140209436416626}, {'batch_size': 3, 'throughput': 1.0997426758503557, 'latency_mean': 2.7168566393852234, 'latency_p50': 2.732818603515625, 'latency_p90': 3.0141294240951537}, {'batch_size': 5, 'throughput': 1.325577786255193, 'latency_mean': 3.755090355873108, 'latency_p50': 3.759468197822571, 'latency_p90': 4.175771307945252}, {'batch_size': 6, 'throughput': 1.388238964435025, 'latency_mean': 4.2961735904216765, 'latency_p50': 4.2995219230651855, 'latency_p90': 4.858271884918213}, {'batch_size': 8, 'throughput': 1.447260046273804, 'latency_mean': 5.480946251153946, 'latency_p50': 5.5407954454422, 'latency_p90': 6.040657424926758}, {'batch_size': 10, 'throughput': 1.5035943930461828, 'latency_mean': 6.61132160782814, 'latency_p50': 6.631737589836121, 'latency_p90': 7.4393669128417965}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: alexcuadron-dpo-roleplay_v2
is_internal_developer: False
language_model: AlexCuadron/dpo_roleplay
model_size: 13B
ranking_group: single
throughput_3p7s: 1.32
us_pacific_date: 2025-03-24
win_ratio: 0.4952015355086372
generation_params: {'temperature': 0.7, 'top_p': 0.85, 'min_p': 0.1, 'top_k': 40, 'presence_penalty': 0.1, 'frequency_penalty': 0.4, 'stopping_words': ['\n'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', '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 alexcuadron-dpo-roleplay-v2-mkmlizer
Waiting for job on alexcuadron-dpo-roleplay-v2-mkmlizer to finish
alexcuadron-dpo-roleplay-v2-mkmlizer: Downloaded to shared memory in 34.815s
alexcuadron-dpo-roleplay-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp6r_g9h39, device:0
alexcuadron-dpo-roleplay-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
alexcuadron-dpo-roleplay-v2-mkmlizer: creating bucket guanaco-mkml-models
alexcuadron-dpo-roleplay-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
alexcuadron-dpo-roleplay-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/alexcuadron-dpo-roleplay-v2
alexcuadron-dpo-roleplay-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/alexcuadron-dpo-roleplay-v2/config.json
alexcuadron-dpo-roleplay-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/alexcuadron-dpo-roleplay-v2/special_tokens_map.json
alexcuadron-dpo-roleplay-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/alexcuadron-dpo-roleplay-v2/tokenizer_config.json
alexcuadron-dpo-roleplay-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/alexcuadron-dpo-roleplay-v2/tokenizer.json
alexcuadron-dpo-roleplay-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/alexcuadron-dpo-roleplay-v2/flywheel_model.0.safetensors
Job alexcuadron-dpo-roleplay-v2-mkmlizer completed after 102.95s with status: succeeded
Stopping job with name alexcuadron-dpo-roleplay-v2-mkmlizer
Pipeline stage MKMLizer completed in 103.42s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.20s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service alexcuadron-dpo-roleplay-v2
Waiting for inference service alexcuadron-dpo-roleplay-v2 to be ready
Inference service alexcuadron-dpo-roleplay-v2 ready after 90.3449444770813s
Pipeline stage MKMLDeployer completed in 90.85s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3426735401153564s
Received healthy response to inference request in 1.4196102619171143s
Received healthy response to inference request in 1.5956048965454102s
Received healthy response to inference request in 1.6333019733428955s
Received healthy response to inference request in 1.8048224449157715s
5 requests
0 failed requests
5th percentile: 1.4548091888427734
10th percentile: 1.4900081157684326
20th percentile: 1.560405969619751
30th percentile: 1.6031443119049071
40th percentile: 1.6182231426239013
50th percentile: 1.6333019733428955
60th percentile: 1.7019101619720458
70th percentile: 1.7705183506011963
80th percentile: 1.9123926639556885
90th percentile: 2.1275331020355224
95th percentile: 2.235103321075439
99th percentile: 2.321159496307373
mean time: 1.7592026233673095
Pipeline stage StressChecker completed in 10.10s
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 0.75s
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 0.68s
Shutdown handler de-registered
alexcuadron-dpo-roleplay_v2 status is now deployed due to DeploymentManager action
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 2602.13s
Shutdown handler de-registered
alexcuadron-dpo-roleplay_v2 status is now inactive due to auto deactivation removed underperforming models
alexcuadron-dpo-roleplay_v2 status is now torndown due to DeploymentManager action
ChatRequest
Generation Params
Prompt Formatter
Chat History
ChatMessage 1