developer_uid: AlexCuadron
submission_id: alexcuadron-dpo-task-og-v2_v1
model_name: alexcuadron-dpo-task-og-v2_v1
model_group: AlexCuadron/dpo_task_og_
status: torndown
timestamp: 2025-03-24T22:09:04+00:00
num_battles: 9755
num_wins: 4650
celo_rating: 1265.13
family_friendly_score: 0.589
family_friendly_standard_error: 0.006958146304871722
submission_type: basic
model_repo: AlexCuadron/dpo_task_og_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': 0.5921593949542079, 'latency_mean': 1.6886626303195953, 'latency_p50': 1.693893551826477, 'latency_p90': 1.8546556949615478}, {'batch_size': 3, 'throughput': 1.0919394331767671, 'latency_mean': 2.74106476187706, 'latency_p50': 2.755637764930725, 'latency_p90': 3.011726689338684}, {'batch_size': 5, 'throughput': 1.3229178482646122, 'latency_mean': 3.7583646953105925, 'latency_p50': 3.776108145713806, 'latency_p90': 4.1679696321487425}, {'batch_size': 6, 'throughput': 1.3939332545194436, 'latency_mean': 4.28157249212265, 'latency_p50': 4.2911059856414795, 'latency_p90': 4.845623660087585}, {'batch_size': 8, 'throughput': 1.4593872704557862, 'latency_mean': 5.457974593639374, 'latency_p50': 5.465855240821838, 'latency_p90': 6.176579689979553}, {'batch_size': 10, 'throughput': 1.4999375160735855, 'latency_mean': 6.61309666633606, 'latency_p50': 6.615013241767883, 'latency_p90': 7.46284556388855}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: alexcuadron-dpo-task-og-v2_v1
is_internal_developer: False
language_model: AlexCuadron/dpo_task_og_v2
model_size: 13B
ranking_group: single
throughput_3p7s: 1.32
us_pacific_date: 2025-03-24
win_ratio: 0.4766786263454639
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-v2-v1-mkmlizer
Waiting for job on alexcuadron-dpo-task-og-v2-v1-mkmlizer to finish
alexcuadron-dpo-task-og-v2-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
alexcuadron-dpo-task-og-v2-v1-mkmlizer: ║ _____ __ __ ║
alexcuadron-dpo-task-og-v2-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
alexcuadron-dpo-task-og-v2-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
alexcuadron-dpo-task-og-v2-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
alexcuadron-dpo-task-og-v2-v1-mkmlizer: ║ /___/ ║
alexcuadron-dpo-task-og-v2-v1-mkmlizer: ║ ║
alexcuadron-dpo-task-og-v2-v1-mkmlizer: ║ Version: 0.12.8 ║
alexcuadron-dpo-task-og-v2-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
alexcuadron-dpo-task-og-v2-v1-mkmlizer: ║ https://mk1.ai ║
alexcuadron-dpo-task-og-v2-v1-mkmlizer: ║ ║
alexcuadron-dpo-task-og-v2-v1-mkmlizer: ║ The license key for the current software has been verified as ║
alexcuadron-dpo-task-og-v2-v1-mkmlizer: ║ belonging to: ║
alexcuadron-dpo-task-og-v2-v1-mkmlizer: ║ ║
alexcuadron-dpo-task-og-v2-v1-mkmlizer: ║ Chai Research Corp. ║
alexcuadron-dpo-task-og-v2-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
alexcuadron-dpo-task-og-v2-v1-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
alexcuadron-dpo-task-og-v2-v1-mkmlizer: ║ ║
alexcuadron-dpo-task-og-v2-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
alexcuadron-dpo-task-og-v2-v1-mkmlizer: Downloaded to shared memory in 44.940s
alexcuadron-dpo-task-og-v2-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp1wcvqm87, device:0
alexcuadron-dpo-task-og-v2-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
alexcuadron-dpo-task-og-v2-v1-mkmlizer: quantized model in 35.962s
alexcuadron-dpo-task-og-v2-v1-mkmlizer: Processed model AlexCuadron/dpo_task_og_v2 in 80.903s
alexcuadron-dpo-task-og-v2-v1-mkmlizer: creating bucket guanaco-mkml-models
alexcuadron-dpo-task-og-v2-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
alexcuadron-dpo-task-og-v2-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/alexcuadron-dpo-task-og-v2-v1
alexcuadron-dpo-task-og-v2-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/alexcuadron-dpo-task-og-v2-v1/config.json
alexcuadron-dpo-task-og-v2-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/alexcuadron-dpo-task-og-v2-v1/special_tokens_map.json
alexcuadron-dpo-task-og-v2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/alexcuadron-dpo-task-og-v2-v1/tokenizer_config.json
alexcuadron-dpo-task-og-v2-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/alexcuadron-dpo-task-og-v2-v1/flywheel_model.0.safetensors
alexcuadron-dpo-task-og-v2-v1-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%| | 2/363 [00:06<18:14, 3.03s/it] Loading 0: 2%|▏ | 6/363 [00:06<04:51, 1.22it/s] Loading 0: 4%|▎ | 13/363 [00:06<01:44, 3.36it/s] Loading 0: 5%|▍ | 18/363 [00:06<01:04, 5.35it/s] Loading 0: 7%|▋ | 24/363 [00:06<00:41, 8.16it/s] Loading 0: 9%|▉ | 32/363 [00:06<00:24, 13.28it/s] Loading 0: 10%|█ | 38/363 [00:06<00:19, 17.02it/s] Loading 0: 12%|█▏ | 43/363 [00:07<00:18, 16.94it/s] Loading 0: 14%|█▍ | 50/363 [00:07<00:13, 22.71it/s] Loading 0: 15%|█▌ | 56/363 [00:07<00:11, 26.44it/s] Loading 0: 17%|█▋ | 61/363 [00:07<00:10, 29.31it/s] Loading 0: 19%|█▊ | 68/363 [00:07<00:08, 36.09it/s] Loading 0: 20%|██ | 74/363 [00:07<00:07, 38.12it/s] Loading 0: 22%|██▏ | 79/363 [00:07<00:07, 39.05it/s] Loading 0: 24%|██▎ | 86/363 [00:08<00:06, 44.41it/s] Loading 0: 25%|██▌ | 92/363 [00:08<00:06, 43.69it/s] Loading 0: 27%|██▋ | 97/363 [00:08<00:06, 42.22it/s] Loading 0: 28%|██▊ | 103/363 [00:08<00:05, 46.41it/s] Loading 0: 30%|██▉ | 108/363 [00:08<00:05, 45.31it/s] Loading 0: 31%|███ | 113/363 [00:08<00:05, 45.75it/s] Loading 0: 33%|███▎ | 119/363 [00:08<00:05, 44.30it/s] Loading 0: 34%|███▍ | 124/363 [00:09<00:07, 30.47it/s] Loading 0: 36%|███▌ | 130/363 [00:09<00:06, 34.63it/s] Loading 0: 37%|███▋ | 135/363 [00:09<00:06, 36.53it/s] Loading 0: 39%|███▊ | 140/363 [00:09<00:05, 38.94it/s] Loading 0: 40%|████ | 146/363 [00:09<00:05, 40.17it/s] Loading 0: 42%|████▏ | 151/363 [00:09<00:05, 39.92it/s] Loading 0: 43%|████▎ | 157/363 [00:09<00:04, 44.79it/s] Loading 0: 45%|████▍ | 162/363 [00:09<00:04, 43.67it/s] Loading 0: 46%|████▌ | 167/363 [00:10<00:04, 44.52it/s] Loading 0: 48%|████▊ | 173/363 [00:10<00:04, 43.49it/s] Loading 0: 49%|████▉ | 178/363 [00:10<00:04, 41.72it/s] Loading 0: 51%|█████ | 185/363 [00:10<00:03, 46.55it/s] Loading 0: 53%|█████▎ | 191/363 [00:10<00:03, 44.50it/s] Loading 0: 54%|█████▍ | 196/363 [00:10<00:03, 42.46it/s] Loading 0: 56%|█████▌ | 202/363 [00:10<00:04, 34.25it/s] Loading 0: 57%|█████▋ | 206/363 [00:11<00:04, 34.37it/s] Loading 0: 58%|█████▊ | 211/363 [00:11<00:04, 37.77it/s] Loading 0: 60%|█████▉ | 216/363 [00:11<00:03, 39.81it/s] Loading 0: 61%|██████ | 221/363 [00:11<00:03, 41.95it/s] Loading 0: 63%|██████▎ | 227/363 [00:11<00:03, 41.60it/s] Loading 0: 64%|██████▍ | 232/363 [00:11<00:03, 40.05it/s] Loading 0: 66%|██████▌ | 238/363 [00:11<00:02, 44.54it/s] Loading 0: 67%|██████▋ | 243/363 [00:11<00:02, 44.81it/s] Loading 0: 68%|██████▊ | 248/363 [00:11<00:02, 45.44it/s] Loading 0: 70%|██████▉ | 253/363 [00:12<00:02, 45.81it/s] Loading 0: 71%|███████ | 258/363 [00:12<00:02, 37.38it/s] Loading 0: 73%|███████▎ | 265/363 [00:12<00:02, 44.94it/s] Loading 0: 74%|███████▍ | 270/363 [00:12<00:02, 44.13it/s] Loading 0: 76%|███████▌ | 275/363 [00:12<00:02, 43.30it/s] Loading 0: 77%|███████▋ | 280/363 [00:12<00:01, 44.77it/s] Loading 0: 79%|███████▊ | 285/363 [00:13<00:02, 27.95it/s] Loading 0: 80%|████████ | 292/363 [00:13<00:02, 35.29it/s] Loading 0: 82%|████████▏ | 297/363 [00:13<00:01, 37.12it/s] Loading 0: 83%|████████▎ | 302/363 [00:13<00:01, 39.09it/s] Loading 0: 85%|████████▍ | 308/363 [00:13<00:01, 38.65it/s] Loading 0: 86%|████████▌ | 313/363 [00:13<00:01, 38.53it/s] Loading 0: 88%|████████▊ | 320/363 [00:13<00:00, 44.04it/s] Loading 0: 90%|████████▉ | 326/363 [00:13<00:00, 43.11it/s] Loading 0: 91%|█████████ | 331/363 [00:14<00:00, 42.34it/s] Loading 0: 93%|█████████▎| 338/363 [00:14<00:00, 47.00it/s] Loading 0: 95%|█████████▍| 344/363 [00:14<00:00, 44.96it/s] Loading 0: 96%|█████████▌| 349/363 [00:14<00:00, 43.93it/s] Loading 0: 98%|█████████▊| 355/363 [00:14<00:00, 47.31it/s] Loading 0: 99%|█████████▉| 360/363 [00:14<00:00, 46.91it/s]
Job alexcuadron-dpo-task-og-v2-v1-mkmlizer completed after 103.86s with status: succeeded
Stopping job with name alexcuadron-dpo-task-og-v2-v1-mkmlizer
Pipeline stage MKMLizer completed in 104.34s
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-v2-v1
Waiting for inference service alexcuadron-dpo-task-og-v2-v1 to be ready
Inference service alexcuadron-dpo-task-og-v2-v1 ready after 100.45497417449951s
Pipeline stage MKMLDeployer completed in 100.98s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.322977066040039s
Received healthy response to inference request in 1.6820693016052246s
Received healthy response to inference request in 1.741905689239502s
Received healthy response to inference request in 1.6185190677642822s
Received healthy response to inference request in 1.8055815696716309s
5 requests
0 failed requests
5th percentile: 1.6312291145324707
10th percentile: 1.643939161300659
20th percentile: 1.6693592548370362
30th percentile: 1.6940365791320802
40th percentile: 1.717971134185791
50th percentile: 1.741905689239502
60th percentile: 1.7673760414123536
70th percentile: 1.792846393585205
80th percentile: 1.9090606689453127
90th percentile: 2.116018867492676
95th percentile: 2.2194979667663572
99th percentile: 2.3022812461853026
mean time: 1.8342105388641357
Pipeline stage StressChecker completed in 10.42s
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 0.66s
Shutdown handler de-registered
alexcuadron-dpo-task-og-v2_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 alexcuadron-dpo-task-og-v2-v1-profiler
Waiting for inference service alexcuadron-dpo-task-og-v2-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 2687.78s
Shutdown handler de-registered
alexcuadron-dpo-task-og-v2_v1 status is now inactive due to auto deactivation removed underperforming models
alexcuadron-dpo-task-og-v2_v1 status is now torndown due to DeploymentManager action
ChatRequest
Generation Params
Prompt Formatter
Chat History
ChatMessage 1