developer_uid: AlexCuadron
submission_id: alexcuadron-dpo-massive-mm_v1
model_name: alexcuadron-dpo-massive-mm_v1
model_group: AlexCuadron/dpo_massive_
status: inactive
timestamp: 2025-03-25T00:52:20+00:00
num_battles: 6758
num_wins: 3322
celo_rating: 1274.72
family_friendly_score: 0.5542
family_friendly_standard_error: 0.007029400543431851
submission_type: basic
model_repo: AlexCuadron/dpo_massive_mm
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.6038186117404502, 'latency_mean': 1.656066393852234, 'latency_p50': 1.6647381782531738, 'latency_p90': 1.8327409744262695}, {'batch_size': 3, 'throughput': 1.1114814146475591, 'latency_mean': 2.691393541097641, 'latency_p50': 2.684435486793518, 'latency_p90': 2.964300751686096}, {'batch_size': 5, 'throughput': 1.3397795504943115, 'latency_mean': 3.7133503103256227, 'latency_p50': 3.702213406562805, 'latency_p90': 4.118644404411316}, {'batch_size': 6, 'throughput': 1.400241013621428, 'latency_mean': 4.26009769320488, 'latency_p50': 4.297627210617065, 'latency_p90': 4.673412871360779}, {'batch_size': 8, 'throughput': 1.4620582273693616, 'latency_mean': 5.441348507404327, 'latency_p50': 5.471975564956665, 'latency_p90': 6.046363472938538}, {'batch_size': 10, 'throughput': 1.4982403042774808, 'latency_mean': 6.615902633666992, 'latency_p50': 6.575866103172302, 'latency_p90': 7.604470515251159}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: alexcuadron-dpo-massive-mm_v1
is_internal_developer: False
language_model: AlexCuadron/dpo_massive_mm
model_size: 13B
ranking_group: single
throughput_3p7s: 1.34
us_pacific_date: 2025-03-24
win_ratio: 0.4915655519384433
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-massive-mm-v1-mkmlizer
Waiting for job on alexcuadron-dpo-massive-mm-v1-mkmlizer to finish
alexcuadron-dpo-massive-mm-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
alexcuadron-dpo-massive-mm-v1-mkmlizer: ║ _____ __ __ ║
alexcuadron-dpo-massive-mm-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
alexcuadron-dpo-massive-mm-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
alexcuadron-dpo-massive-mm-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
alexcuadron-dpo-massive-mm-v1-mkmlizer: ║ /___/ ║
alexcuadron-dpo-massive-mm-v1-mkmlizer: ║ ║
alexcuadron-dpo-massive-mm-v1-mkmlizer: ║ Version: 0.12.8 ║
alexcuadron-dpo-massive-mm-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
alexcuadron-dpo-massive-mm-v1-mkmlizer: ║ https://mk1.ai ║
alexcuadron-dpo-massive-mm-v1-mkmlizer: ║ ║
alexcuadron-dpo-massive-mm-v1-mkmlizer: ║ The license key for the current software has been verified as ║
alexcuadron-dpo-massive-mm-v1-mkmlizer: ║ belonging to: ║
alexcuadron-dpo-massive-mm-v1-mkmlizer: ║ ║
alexcuadron-dpo-massive-mm-v1-mkmlizer: ║ Chai Research Corp. ║
alexcuadron-dpo-massive-mm-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
alexcuadron-dpo-massive-mm-v1-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
alexcuadron-dpo-massive-mm-v1-mkmlizer: ║ ║
alexcuadron-dpo-massive-mm-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
alexcuadron-dpo-massive-mm-v1-mkmlizer: Downloaded to shared memory in 45.558s
alexcuadron-dpo-massive-mm-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpivkxc3lh, device:0
alexcuadron-dpo-massive-mm-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
alexcuadron-dpo-massive-mm-v1-mkmlizer: quantized model in 35.674s
alexcuadron-dpo-massive-mm-v1-mkmlizer: Processed model AlexCuadron/dpo_massive_mm in 81.233s
alexcuadron-dpo-massive-mm-v1-mkmlizer: creating bucket guanaco-mkml-models
alexcuadron-dpo-massive-mm-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
alexcuadron-dpo-massive-mm-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/alexcuadron-dpo-massive-mm-v1
alexcuadron-dpo-massive-mm-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/alexcuadron-dpo-massive-mm-v1/config.json
alexcuadron-dpo-massive-mm-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/alexcuadron-dpo-massive-mm-v1/tokenizer.json
alexcuadron-dpo-massive-mm-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/alexcuadron-dpo-massive-mm-v1/flywheel_model.0.safetensors
alexcuadron-dpo-massive-mm-v1-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%| | 2/363 [00:06<18:16, 3.04s/it] Loading 0: 2%|▏ | 6/363 [00:06<04:51, 1.22it/s] Loading 0: 4%|▎ | 13/363 [00:06<01:43, 3.37it/s] Loading 0: 5%|▌ | 19/363 [00:06<00:59, 5.78it/s] Loading 0: 7%|▋ | 24/363 [00:06<00:42, 8.04it/s] Loading 0: 9%|▉ | 32/363 [00:06<00:24, 13.26it/s] Loading 0: 10%|█ | 38/363 [00:06<00:19, 17.08it/s] Loading 0: 12%|█▏ | 43/363 [00:07<00:19, 16.73it/s] Loading 0: 14%|█▍ | 50/363 [00:07<00:13, 22.57it/s] Loading 0: 15%|█▌ | 56/363 [00:07<00:11, 26.54it/s] Loading 0: 17%|█▋ | 61/363 [00:07<00:10, 29.57it/s] Loading 0: 19%|█▊ | 68/363 [00:07<00:08, 35.84it/s] Loading 0: 20%|██ | 74/363 [00:07<00:07, 37.82it/s] Loading 0: 22%|██▏ | 79/363 [00:07<00:07, 39.28it/s] Loading 0: 24%|██▎ | 86/363 [00:08<00:06, 45.31it/s] Loading 0: 25%|██▌ | 92/363 [00:08<00:06, 44.60it/s] Loading 0: 27%|██▋ | 97/363 [00:08<00:06, 43.84it/s] Loading 0: 29%|██▊ | 104/363 [00:08<00:05, 48.67it/s] Loading 0: 30%|███ | 110/363 [00:08<00:05, 45.01it/s] Loading 0: 32%|███▏ | 115/363 [00:08<00:05, 42.05it/s] Loading 0: 33%|███▎ | 121/363 [00:08<00:07, 33.04it/s] Loading 0: 34%|███▍ | 125/363 [00:09<00:07, 32.89it/s] Loading 0: 36%|███▌ | 131/363 [00:09<00:06, 36.91it/s] Loading 0: 38%|███▊ | 137/363 [00:09<00:05, 37.95it/s] Loading 0: 39%|███▉ | 142/363 [00:09<00:05, 38.80it/s] Loading 0: 41%|████ | 149/363 [00:09<00:04, 44.12it/s] Loading 0: 43%|████▎ | 155/363 [00:09<00:04, 42.75it/s] Loading 0: 44%|████▍ | 160/363 [00:09<00:04, 42.45it/s] Loading 0: 46%|████▌ | 167/363 [00:09<00:04, 47.43it/s] Loading 0: 48%|████▊ | 173/363 [00:10<00:04, 46.10it/s] Loading 0: 49%|████▉ | 178/363 [00:10<00:04, 44.57it/s] Loading 0: 51%|█████ | 185/363 [00:10<00:03, 48.80it/s] Loading 0: 53%|█████▎ | 191/363 [00:10<00:03, 46.68it/s] Loading 0: 54%|█████▍ | 196/363 [00:10<00:03, 43.64it/s] Loading 0: 56%|█████▌ | 202/363 [00:10<00:04, 34.00it/s] Loading 0: 57%|█████▋ | 206/363 [00:11<00:04, 34.16it/s] Loading 0: 58%|█████▊ | 212/363 [00:11<00:03, 38.87it/s] Loading 0: 60%|██████ | 218/363 [00:11<00:03, 40.47it/s] Loading 0: 61%|██████▏ | 223/363 [00:11<00:03, 40.77it/s] Loading 0: 63%|██████▎ | 229/363 [00:11<00:02, 45.05it/s] Loading 0: 64%|██████▍ | 234/363 [00:11<00:02, 45.04it/s] Loading 0: 66%|██████▌ | 239/363 [00:11<00:02, 46.17it/s] Loading 0: 67%|██████▋ | 245/363 [00:11<00:02, 45.79it/s] Loading 0: 69%|██████▉ | 250/363 [00:11<00:02, 44.07it/s] Loading 0: 71%|███████ | 257/363 [00:12<00:02, 48.52it/s] Loading 0: 72%|███████▏ | 262/363 [00:12<00:02, 48.41it/s] Loading 0: 74%|███████▎ | 267/363 [00:12<00:02, 41.79it/s] Loading 0: 75%|███████▌ | 274/363 [00:12<00:01, 47.60it/s] Loading 0: 77%|███████▋ | 279/363 [00:12<00:01, 45.35it/s] Loading 0: 78%|███████▊ | 284/363 [00:12<00:02, 32.78it/s] Loading 0: 80%|███████▉ | 289/363 [00:12<00:02, 35.88it/s] Loading 0: 81%|████████ | 294/363 [00:13<00:02, 33.13it/s] Loading 0: 83%|████████▎ | 302/363 [00:13<00:01, 41.88it/s] Loading 0: 85%|████████▍ | 308/363 [00:13<00:01, 42.64it/s] Loading 0: 86%|████████▌ | 313/363 [00:13<00:01, 42.38it/s] Loading 0: 88%|████████▊ | 319/363 [00:13<00:00, 46.01it/s] Loading 0: 89%|████████▉ | 324/363 [00:13<00:00, 46.52it/s] Loading 0: 91%|█████████ | 329/363 [00:13<00:00, 46.67it/s] Loading 0: 92%|█████████▏| 335/363 [00:13<00:00, 44.95it/s] Loading 0: 94%|█████████▎| 340/363 [00:14<00:00, 40.49it/s] Loading 0: 95%|█████████▌| 346/363 [00:14<00:00, 43.44it/s] Loading 0: 97%|█████████▋| 351/363 [00:14<00:00, 43.88it/s] Loading 0: 98%|█████████▊| 356/363 [00:14<00:00, 42.94it/s] Loading 0: 100%|█████████▉| 362/363 [00:14<00:00, 41.30it/s]
Job alexcuadron-dpo-massive-mm-v1-mkmlizer completed after 114.39s with status: succeeded
Stopping job with name alexcuadron-dpo-massive-mm-v1-mkmlizer
Pipeline stage MKMLizer completed in 114.84s
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-massive-mm-v1
Waiting for inference service alexcuadron-dpo-massive-mm-v1 to be ready
Inference service alexcuadron-dpo-massive-mm-v1 ready after 100.53450608253479s
Pipeline stage MKMLDeployer completed in 101.03s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3803300857543945s
Received healthy response to inference request in 1.5613548755645752s
Received healthy response to inference request in 1.570981740951538s
Received healthy response to inference request in 1.6225636005401611s
Received healthy response to inference request in 1.8497216701507568s
5 requests
0 failed requests
5th percentile: 1.5632802486419677
10th percentile: 1.5652056217193604
20th percentile: 1.5690563678741456
30th percentile: 1.5812981128692627
40th percentile: 1.601930856704712
50th percentile: 1.6225636005401611
60th percentile: 1.7134268283843994
70th percentile: 1.8042900562286377
80th percentile: 1.9558433532714845
90th percentile: 2.1680867195129396
95th percentile: 2.274208402633667
99th percentile: 2.359105749130249
mean time: 1.7969903945922852
Pipeline stage StressChecker completed in 10.24s
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 0.66s
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-massive-mm_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
Pipeline stage OfflineFamilyFriendlyScorer completed in 2538.78s
Shutdown handler de-registered
alexcuadron-dpo-massive-mm_v1 status is now inactive due to auto deactivation removed underperforming models
ChatRequest
Generation Params
Prompt Formatter
Chat History
ChatMessage 1