developer_uid: AlexCuadron
submission_id: alexcuadron-dpo-task-og_v1
model_name: alexcuadron-dpo-task-og_v1
model_group: AlexCuadron/dpo_task_og
status: torndown
timestamp: 2025-03-24T21:41:53+00:00
num_battles: 9086
num_wins: 4379
celo_rating: 1265.9
family_friendly_score: 0.5892
family_friendly_standard_error: 0.006957634080634019
submission_type: basic
model_repo: AlexCuadron/dpo_task_og
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.5959707269341924, 'latency_mean': 1.6778432261943816, 'latency_p50': 1.7061477899551392, 'latency_p90': 1.8416384696960448}, {'batch_size': 3, 'throughput': 1.1060773763400251, 'latency_mean': 2.6999948954582216, 'latency_p50': 2.693135619163513, 'latency_p90': 3.0112098932266234}, {'batch_size': 5, 'throughput': 1.3270104780812575, 'latency_mean': 3.7392581975460053, 'latency_p50': 3.738195300102234, 'latency_p90': 4.2056722164154055}, {'batch_size': 6, 'throughput': 1.404044652005197, 'latency_mean': 4.2424674832820894, 'latency_p50': 4.2113611698150635, 'latency_p90': 4.800057339668274}, {'batch_size': 8, 'throughput': 1.4599418342365842, 'latency_mean': 5.442717306613922, 'latency_p50': 5.474386096000671, 'latency_p90': 6.154637169837952}, {'batch_size': 10, 'throughput': 1.5008534071629078, 'latency_mean': 6.617367024421692, 'latency_p50': 6.57108461856842, 'latency_p90': 7.500681805610657}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: alexcuadron-dpo-task-og_v1
is_internal_developer: False
language_model: AlexCuadron/dpo_task_og
model_size: 13B
ranking_group: single
throughput_3p7s: 1.33
us_pacific_date: 2025-03-24
win_ratio: 0.4819502531366938
generation_params: {'temperature': 1.0, 'top_p': 0.9, 'min_p': 0.1, 'top_k': 40, 'presence_penalty': 0.1, 'frequency_penalty': 0.0, 'stopping_words': ['</s>'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': "<s>{bot_name}'s Persona: {memory}\n", 'prompt_template': '{prompt}', 'bot_template': '{bot_name}: {message}</s>', 'user_template': '[INST]{user_name}: {message}[/INST]', '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-task-og-v1-mkmlizer
Waiting for job on alexcuadron-dpo-task-og-v1-mkmlizer to finish
alexcuadron-dpo-task-og-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
alexcuadron-dpo-task-og-v1-mkmlizer: ║ _____ __ __ ║
alexcuadron-dpo-task-og-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
alexcuadron-dpo-task-og-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
alexcuadron-dpo-task-og-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
alexcuadron-dpo-task-og-v1-mkmlizer: ║ /___/ ║
alexcuadron-dpo-task-og-v1-mkmlizer: ║ ║
alexcuadron-dpo-task-og-v1-mkmlizer: ║ Version: 0.12.8 ║
alexcuadron-dpo-task-og-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
alexcuadron-dpo-task-og-v1-mkmlizer: ║ https://mk1.ai ║
alexcuadron-dpo-task-og-v1-mkmlizer: ║ ║
alexcuadron-dpo-task-og-v1-mkmlizer: ║ The license key for the current software has been verified as ║
alexcuadron-dpo-task-og-v1-mkmlizer: ║ belonging to: ║
alexcuadron-dpo-task-og-v1-mkmlizer: ║ ║
alexcuadron-dpo-task-og-v1-mkmlizer: ║ Chai Research Corp. ║
alexcuadron-dpo-task-og-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
alexcuadron-dpo-task-og-v1-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
alexcuadron-dpo-task-og-v1-mkmlizer: ║ ║
alexcuadron-dpo-task-og-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
alexcuadron-dpo-task-og-v1-mkmlizer: Downloaded to shared memory in 44.250s
alexcuadron-dpo-task-og-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpvvjl16wc, device:0
alexcuadron-dpo-task-og-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
alexcuadron-dpo-task-og-v1-mkmlizer: quantized model in 35.391s
alexcuadron-dpo-task-og-v1-mkmlizer: Processed model AlexCuadron/dpo_task_og in 79.642s
alexcuadron-dpo-task-og-v1-mkmlizer: creating bucket guanaco-mkml-models
alexcuadron-dpo-task-og-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
alexcuadron-dpo-task-og-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/alexcuadron-dpo-task-og-v1
alexcuadron-dpo-task-og-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/alexcuadron-dpo-task-og-v1/config.json
alexcuadron-dpo-task-og-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/alexcuadron-dpo-task-og-v1/special_tokens_map.json
alexcuadron-dpo-task-og-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/alexcuadron-dpo-task-og-v1/tokenizer_config.json
alexcuadron-dpo-task-og-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/alexcuadron-dpo-task-og-v1/tokenizer.json
alexcuadron-dpo-task-og-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/alexcuadron-dpo-task-og-v1/flywheel_model.0.safetensors
alexcuadron-dpo-task-og-v1-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%| | 2/363 [00:06<18:07, 3.01s/it] Loading 0: 2%|▏ | 6/363 [00:06<04:49, 1.23it/s] Loading 0: 4%|▎ | 13/363 [00:06<01:43, 3.39it/s] Loading 0: 5%|▌ | 19/363 [00:06<00:59, 5.80it/s] Loading 0: 7%|▋ | 24/363 [00:06<00:42, 8.04it/s] Loading 0: 9%|▉ | 32/363 [00:06<00:25, 13.20it/s] Loading 0: 10%|█ | 37/363 [00:06<00:19, 16.55it/s] Loading 0: 12%|█▏ | 42/363 [00:07<00:20, 15.79it/s] Loading 0: 14%|█▍ | 50/363 [00:07<00:13, 22.82it/s] Loading 0: 15%|█▌ | 56/363 [00:07<00:11, 26.28it/s] Loading 0: 17%|█▋ | 61/363 [00:07<00:10, 28.74it/s] Loading 0: 19%|█▊ | 68/363 [00:07<00:08, 35.14it/s] Loading 0: 20%|██ | 74/363 [00:07<00:07, 36.97it/s] Loading 0: 22%|██▏ | 79/363 [00:07<00:07, 38.18it/s] Loading 0: 24%|██▎ | 86/363 [00:08<00:06, 44.03it/s] Loading 0: 25%|██▌ | 92/363 [00:08<00:06, 43.02it/s] Loading 0: 27%|██▋ | 97/363 [00:08<00:06, 42.69it/s] Loading 0: 28%|██▊ | 103/363 [00:08<00:05, 46.74it/s] Loading 0: 30%|██▉ | 108/363 [00:08<00:05, 46.42it/s] Loading 0: 31%|███ | 113/363 [00:08<00:05, 47.17it/s] Loading 0: 33%|███▎ | 119/363 [00:08<00:05, 45.57it/s] Loading 0: 34%|███▍ | 124/363 [00:09<00:07, 31.32it/s] Loading 0: 36%|███▌ | 131/363 [00:09<00:06, 37.74it/s] Loading 0: 38%|███▊ | 137/363 [00:09<00:05, 39.31it/s] Loading 0: 39%|███▉ | 142/363 [00:09<00:05, 39.35it/s] Loading 0: 41%|████ | 149/363 [00:09<00:04, 44.34it/s] Loading 0: 43%|████▎ | 155/363 [00:09<00:04, 44.14it/s] Loading 0: 44%|████▍ | 160/363 [00:09<00:04, 43.39it/s] Loading 0: 46%|████▌ | 166/363 [00:09<00:04, 47.23it/s] Loading 0: 47%|████▋ | 171/363 [00:10<00:04, 47.71it/s] Loading 0: 48%|████▊ | 176/363 [00:10<00:03, 48.27it/s] Loading 0: 50%|█████ | 182/363 [00:10<00:03, 46.29it/s] Loading 0: 52%|█████▏ | 187/363 [00:10<00:03, 44.83it/s] Loading 0: 53%|█████▎ | 194/363 [00:10<00:03, 49.41it/s] Loading 0: 55%|█████▌ | 200/363 [00:10<00:03, 47.72it/s] Loading 0: 56%|█████▋ | 205/363 [00:10<00:04, 32.31it/s] Loading 0: 58%|█████▊ | 212/363 [00:11<00:03, 38.56it/s] Loading 0: 60%|██████ | 218/363 [00:11<00:03, 39.77it/s] Loading 0: 61%|██████▏ | 223/363 [00:11<00:03, 39.67it/s] Loading 0: 63%|██████▎ | 229/363 [00:11<00:03, 44.27it/s] Loading 0: 64%|██████▍ | 234/363 [00:11<00:02, 45.04it/s] Loading 0: 66%|██████▌ | 239/363 [00:11<00:02, 45.73it/s] Loading 0: 67%|██████▋ | 245/363 [00:11<00:02, 43.76it/s] Loading 0: 69%|██████▉ | 250/363 [00:11<00:02, 42.59it/s] Loading 0: 71%|███████ | 256/363 [00:11<00:02, 46.22it/s] Loading 0: 72%|███████▏ | 261/363 [00:12<00:02, 45.22it/s] Loading 0: 73%|███████▎ | 266/363 [00:12<00:02, 44.58it/s] Loading 0: 75%|███████▍ | 271/363 [00:12<00:02, 45.04it/s] Loading 0: 76%|███████▌ | 276/363 [00:12<00:02, 37.84it/s] Loading 0: 78%|███████▊ | 283/363 [00:12<00:02, 32.94it/s] Loading 0: 79%|███████▉ | 287/363 [00:12<00:02, 33.12it/s] Loading 0: 81%|████████ | 293/363 [00:12<00:01, 37.86it/s] Loading 0: 82%|████████▏ | 299/363 [00:13<00:01, 38.78it/s] Loading 0: 84%|████████▎ | 304/363 [00:13<00:01, 38.75it/s] Loading 0: 86%|████████▌ | 311/363 [00:13<00:01, 44.05it/s] Loading 0: 87%|████████▋ | 317/363 [00:13<00:01, 42.79it/s] Loading 0: 89%|████████▊ | 322/363 [00:13<00:00, 42.70it/s] Loading 0: 90%|█████████ | 328/363 [00:13<00:00, 46.23it/s] Loading 0: 92%|█████████▏| 333/363 [00:13<00:00, 46.49it/s] Loading 0: 93%|█████████▎| 338/363 [00:13<00:00, 47.05it/s] Loading 0: 95%|█████████▍| 344/363 [00:14<00:00, 45.30it/s] Loading 0: 96%|█████████▌| 349/363 [00:14<00:00, 44.12it/s] Loading 0: 98%|█████████▊| 356/363 [00:14<00:00, 48.22it/s] Loading 0: 100%|█████████▉| 362/363 [00:14<00:00, 46.84it/s]
Job alexcuadron-dpo-task-og-v1-mkmlizer completed after 103.95s with status: succeeded
Stopping job with name alexcuadron-dpo-task-og-v1-mkmlizer
Pipeline stage MKMLizer completed in 104.40s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service alexcuadron-dpo-task-og-v1
Waiting for inference service alexcuadron-dpo-task-og-v1 to be ready
Inference service alexcuadron-dpo-task-og-v1 ready after 100.48990535736084s
Pipeline stage MKMLDeployer completed in 101.02s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2790539264678955s
Received healthy response to inference request in 1.6009204387664795s
Received healthy response to inference request in 1.7019116878509521s
Received healthy response to inference request in 1.5867979526519775s
Received healthy response to inference request in 1.6812167167663574s
5 requests
0 failed requests
5th percentile: 1.5896224498748779
10th percentile: 1.5924469470977782
20th percentile: 1.5980959415435791
30th percentile: 1.6169796943664552
40th percentile: 1.6490982055664063
50th percentile: 1.6812167167663574
60th percentile: 1.6894947052001954
70th percentile: 1.6977726936340332
80th percentile: 1.8173401355743408
90th percentile: 2.048197031021118
95th percentile: 2.163625478744507
99th percentile: 2.2559682369232177
mean time: 1.7699801445007324
Pipeline stage StressChecker completed in 10.05s
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 0.64s
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
alexcuadron-dpo-task-og_v1 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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 4232.51s
Shutdown handler de-registered
alexcuadron-dpo-task-og_v1 status is now inactive due to auto deactivation removed underperforming models
alexcuadron-dpo-task-og_v1 status is now torndown due to DeploymentManager action
ChatRequest
Generation Params
Prompt Formatter
Chat History
ChatMessage 1