developer_uid: AlexCuadron
submission_id: alexcuadron-dpo-massive-mm_v3
model_name: alexcuadron-dpo-massive-mm_v3
model_group: AlexCuadron/dpo_massive_
status: torndown
timestamp: 2025-03-25T01:42:52+00:00
num_battles: 7583
num_wins: 3866
celo_rating: 1288.79
family_friendly_score: 0.5658000000000001
family_friendly_standard_error: 0.007009570029609519
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': 0.6034528421368756, 'latency_mean': 1.6570650112628937, 'latency_p50': 1.6588565111160278, 'latency_p90': 1.8257425785064696}, {'batch_size': 3, 'throughput': 1.1090006020162368, 'latency_mean': 2.6893350279331205, 'latency_p50': 2.703507661819458, 'latency_p90': 3.02786762714386}, {'batch_size': 5, 'throughput': 1.3435045722338599, 'latency_mean': 3.7039219546318054, 'latency_p50': 3.702642798423767, 'latency_p90': 4.182777643203735}, {'batch_size': 6, 'throughput': 1.4111627998474796, 'latency_mean': 4.226875001192093, 'latency_p50': 4.21429717540741, 'latency_p90': 4.828970050811767}, {'batch_size': 8, 'throughput': 1.482301603265823, 'latency_mean': 5.358612207174301, 'latency_p50': 5.350261926651001, 'latency_p90': 6.046663522720337}, {'batch_size': 10, 'throughput': 1.5130460579160745, 'latency_mean': 6.560964320898056, 'latency_p50': 6.594757080078125, 'latency_p90': 7.375930094718933}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: alexcuadron-dpo-massive-mm_v3
is_internal_developer: False
language_model: AlexCuadron/dpo_massive_mm
model_size: 13B
ranking_group: single
throughput_3p7s: 1.35
us_pacific_date: 2025-03-24
win_ratio: 0.5098246076750627
generation_params: {'temperature': 1.0, 'top_p': 0.95, 'min_p': 0.1, 'top_k': 40, 'presence_penalty': 0.1, 'frequency_penalty': 0.0, 'stopping_words': ['<|im_end|>'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': '<|im_start|>system\n{memory}<|im_end|>\n', 'prompt_template': '<|im_start|>user\n{prompt}<|im_end|>\n', 'bot_template': '<|im_start|>assistant\n{bot_name}: {message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{user_name}: {message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n{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-v3-mkmlizer
Waiting for job on alexcuadron-dpo-massive-mm-v3-mkmlizer to finish
alexcuadron-dpo-massive-mm-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
alexcuadron-dpo-massive-mm-v3-mkmlizer: ║     _____            __           __                                ║
alexcuadron-dpo-massive-mm-v3-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
alexcuadron-dpo-massive-mm-v3-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
alexcuadron-dpo-massive-mm-v3-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
alexcuadron-dpo-massive-mm-v3-mkmlizer: ║       /___/                                                         ║
alexcuadron-dpo-massive-mm-v3-mkmlizer: ║                                                                     ║
alexcuadron-dpo-massive-mm-v3-mkmlizer: ║  Version: 0.12.8                                                    ║
alexcuadron-dpo-massive-mm-v3-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
alexcuadron-dpo-massive-mm-v3-mkmlizer: ║  https://mk1.ai                                                     ║
alexcuadron-dpo-massive-mm-v3-mkmlizer: ║                                                                     ║
alexcuadron-dpo-massive-mm-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
alexcuadron-dpo-massive-mm-v3-mkmlizer: ║  belonging to:                                                      ║
alexcuadron-dpo-massive-mm-v3-mkmlizer: ║                                                                     ║
alexcuadron-dpo-massive-mm-v3-mkmlizer: ║  Chai Research Corp.                                                ║
alexcuadron-dpo-massive-mm-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
alexcuadron-dpo-massive-mm-v3-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
alexcuadron-dpo-massive-mm-v3-mkmlizer: ║                                                                     ║
alexcuadron-dpo-massive-mm-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
alexcuadron-dpo-massive-mm-v3-mkmlizer: quantized model in 35.431s
alexcuadron-dpo-massive-mm-v3-mkmlizer: Processed model AlexCuadron/dpo_massive_mm in 67.763s
alexcuadron-dpo-massive-mm-v3-mkmlizer: creating bucket guanaco-mkml-models
alexcuadron-dpo-massive-mm-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
alexcuadron-dpo-massive-mm-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/alexcuadron-dpo-massive-mm-v3
alexcuadron-dpo-massive-mm-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/alexcuadron-dpo-massive-mm-v3/config.json
alexcuadron-dpo-massive-mm-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/alexcuadron-dpo-massive-mm-v3/special_tokens_map.json
alexcuadron-dpo-massive-mm-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/alexcuadron-dpo-massive-mm-v3/tokenizer_config.json
alexcuadron-dpo-massive-mm-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/alexcuadron-dpo-massive-mm-v3/tokenizer.json
alexcuadron-dpo-massive-mm-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/alexcuadron-dpo-massive-mm-v3/flywheel_model.0.safetensors
alexcuadron-dpo-massive-mm-v3-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:06<18:18,  3.04s/it]
Loading 0:   2%|▏         | 6/363 [00:06<04:52,  1.22it/s]
Loading 0:   4%|▎         | 13/363 [00:06<01:44,  3.35it/s]
Loading 0:   5%|▍         | 18/363 [00:06<01:04,  5.33it/s]
Loading 0:   7%|▋         | 24/363 [00:06<00:41,  8.15it/s]
Loading 0:   9%|▉         | 32/363 [00:06<00:24, 13.29it/s]
Loading 0:  10%|█         | 38/363 [00:06<00:19, 17.03it/s]
Loading 0:  12%|█▏        | 43/363 [00:07<00:19, 16.60it/s]
Loading 0:  14%|█▍        | 50/363 [00:07<00:13, 22.37it/s]
Loading 0:  15%|█▌        | 55/363 [00:07<00:11, 26.07it/s]
Loading 0:  17%|█▋        | 60/363 [00:07<00:11, 26.91it/s]
Loading 0:  19%|█▊        | 68/363 [00:07<00:08, 35.42it/s]
Loading 0:  20%|██        | 74/363 [00:07<00:07, 37.40it/s]
Loading 0:  22%|██▏       | 79/363 [00:07<00:07, 38.12it/s]
Loading 0:  24%|██▎       | 86/363 [00:08<00:06, 44.05it/s]
Loading 0:  25%|██▌       | 92/363 [00:08<00:06, 44.01it/s]
Loading 0:  27%|██▋       | 97/363 [00:08<00:06, 44.00it/s]
Loading 0:  29%|██▊       | 104/363 [00:08<00:05, 48.04it/s]
Loading 0:  30%|███       | 110/363 [00:08<00:05, 45.98it/s]
Loading 0:  32%|███▏      | 115/363 [00:08<00:05, 45.20it/s]
Loading 0:  33%|███▎      | 121/363 [00:08<00:06, 34.91it/s]
Loading 0:  34%|███▍      | 125/363 [00:09<00:06, 35.02it/s]
Loading 0:  36%|███▌      | 131/363 [00:09<00:05, 39.31it/s]
Loading 0:  38%|███▊      | 137/363 [00:09<00:05, 40.77it/s]
Loading 0:  39%|███▉      | 142/363 [00:09<00:05, 40.39it/s]
Loading 0:  41%|████      | 148/363 [00:09<00:04, 44.70it/s]
Loading 0:  42%|████▏     | 153/363 [00:09<00:04, 45.84it/s]
Loading 0:  44%|████▎     | 158/363 [00:09<00:04, 46.17it/s]
Loading 0:  45%|████▌     | 164/363 [00:09<00:04, 44.79it/s]
Loading 0:  47%|████▋     | 169/363 [00:10<00:04, 43.14it/s]
Loading 0:  48%|████▊     | 176/363 [00:10<00:03, 48.06it/s]
Loading 0:  50%|█████     | 182/363 [00:10<00:03, 46.60it/s]
Loading 0:  52%|█████▏    | 187/363 [00:10<00:03, 45.40it/s]
Loading 0:  53%|█████▎    | 193/363 [00:10<00:03, 48.77it/s]
Loading 0:  55%|█████▍    | 198/363 [00:10<00:03, 48.41it/s]
Loading 0:  56%|█████▌    | 203/363 [00:10<00:04, 33.79it/s]
Loading 0:  57%|█████▋    | 207/363 [00:11<00:04, 34.29it/s]
Loading 0:  58%|█████▊    | 212/363 [00:11<00:04, 36.79it/s]
Loading 0:  60%|██████    | 218/363 [00:11<00:03, 39.13it/s]
Loading 0:  61%|██████▏   | 223/363 [00:11<00:03, 40.10it/s]
Loading 0:  63%|██████▎   | 230/363 [00:11<00:02, 45.09it/s]
Loading 0:  65%|██████▌   | 236/363 [00:11<00:02, 44.04it/s]
Loading 0:  66%|██████▋   | 241/363 [00:11<00:02, 44.03it/s]
Loading 0:  68%|██████▊   | 248/363 [00:11<00:02, 48.85it/s]
Loading 0:  70%|██████▉   | 254/363 [00:12<00:02, 46.14it/s]
Loading 0:  71%|███████▏  | 259/363 [00:12<00:02, 43.76it/s]
Loading 0:  73%|███████▎  | 266/363 [00:12<00:02, 47.86it/s]
Loading 0:  75%|███████▍  | 272/363 [00:12<00:01, 46.04it/s]
Loading 0:  76%|███████▋  | 277/363 [00:12<00:01, 44.40it/s]
Loading 0:  78%|███████▊  | 283/363 [00:12<00:02, 34.70it/s]
Loading 0:  79%|███████▉  | 287/363 [00:12<00:02, 34.95it/s]
Loading 0:  81%|████████  | 293/363 [00:13<00:01, 38.81it/s]
Loading 0:  82%|████████▏ | 299/363 [00:13<00:01, 39.56it/s]
Loading 0:  84%|████████▎ | 304/363 [00:13<00:01, 40.09it/s]
Loading 0:  86%|████████▌ | 311/363 [00:13<00:01, 45.53it/s]
Loading 0:  87%|████████▋ | 317/363 [00:13<00:01, 44.78it/s]
Loading 0:  89%|████████▊ | 322/363 [00:13<00:00, 43.35it/s]
Loading 0:  91%|█████████ | 329/363 [00:13<00:00, 47.77it/s]
Loading 0:  92%|█████████▏| 335/363 [00:13<00:00, 46.53it/s]
Loading 0:  94%|█████████▎| 340/363 [00:14<00:00, 45.43it/s]
Loading 0:  95%|█████████▌| 346/363 [00:14<00:00, 48.45it/s]
Loading 0:  97%|█████████▋| 351/363 [00:14<00:00, 48.04it/s]
Loading 0:  98%|█████████▊| 356/363 [00:14<00:00, 48.31it/s]
Loading 0: 100%|█████████▉| 362/363 [00:14<00:00, 46.93it/s]
                                                            

Job alexcuadron-dpo-massive-mm-v3-mkmlizer completed after 93.74s with status: succeeded
Stopping job with name alexcuadron-dpo-massive-mm-v3-mkmlizer
Pipeline stage MKMLizer completed in 94.22s
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-v3
Waiting for inference service alexcuadron-dpo-massive-mm-v3 to be ready
Inference service alexcuadron-dpo-massive-mm-v3 ready after 100.55541515350342s
Pipeline stage MKMLDeployer completed in 101.09s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.378373384475708s
Received healthy response to inference request in 1.5674939155578613s
Received healthy response to inference request in 1.5961511135101318s
Received healthy response to inference request in 1.526291847229004s
Received healthy response to inference request in 1.782191514968872s
5 requests
0 failed requests
5th percentile: 1.5345322608947753
10th percentile: 1.5427726745605468
20th percentile: 1.5592535018920899
30th percentile: 1.5732253551483155
40th percentile: 1.5846882343292237
50th percentile: 1.5961511135101318
60th percentile: 1.670567274093628
70th percentile: 1.744983434677124
80th percentile: 1.9014278888702394
90th percentile: 2.139900636672974
95th percentile: 2.259137010574341
99th percentile: 2.3545261096954344
mean time: 1.7701003551483154
Pipeline stage StressChecker completed in 10.19s
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 0.65s
Shutdown handler de-registered
alexcuadron-dpo-massive-mm_v3 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 4806.40s
Shutdown handler de-registered
alexcuadron-dpo-massive-mm_v3 status is now inactive due to auto deactivation removed underperforming models
alexcuadron-dpo-massive-mm_v3 status is now torndown due to DeploymentManager action
ChatRequest
Generation Params
Prompt Formatter
Chat History
ChatMessage 1