submission_id: riverise-3000s-dpo-second_v2
developer_uid: Riverise
alignment_samples: 12075
alignment_score: -0.23209628154501813
best_of: 16
celo_rating: 1245.17
display_name: riverise-3000s-dpo-second_v2
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}
generation_params: {'temperature': 1.15, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
is_internal_developer: False
language_model: Riverise/3000s-dpo-second
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: Riverise/3000s-dpo-secon
model_name: riverise-3000s-dpo-second_v2
model_num_parameters: 8030261248.0
model_repo: Riverise/3000s-dpo-second
model_size: 8B
num_battles: 12075
num_wins: 6269
propriety_score: 0.7466666666666667
propriety_total_count: 1050.0
ranking_group: single
status: inactive
submission_type: basic
timestamp: 2024-09-01T08:19:33+00:00
us_pacific_date: 2024-09-01
win_ratio: 0.5191718426501035
Download Preference Data
Resubmit model
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLizer
Starting job with name riverise-3000s-dpo-second-v2-mkmlizer
Waiting for job on riverise-3000s-dpo-second-v2-mkmlizer to finish
Stopping job with name riverise-3000s-dpo-second-v2-mkmlizer
%s, retrying in %s seconds...
Starting job with name riverise-3000s-dpo-second-v2-mkmlizer
Waiting for job on riverise-3000s-dpo-second-v2-mkmlizer to finish
riverise-3000s-dpo-second-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
riverise-3000s-dpo-second-v2-mkmlizer: ║     _____            __           __                                ║
riverise-3000s-dpo-second-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
riverise-3000s-dpo-second-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
riverise-3000s-dpo-second-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
riverise-3000s-dpo-second-v2-mkmlizer: ║       /___/                                                         ║
riverise-3000s-dpo-second-v2-mkmlizer: ║                                                                     ║
riverise-3000s-dpo-second-v2-mkmlizer: ║  Version: 0.10.1                                                    ║
riverise-3000s-dpo-second-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
riverise-3000s-dpo-second-v2-mkmlizer: ║  https://mk1.ai                                                     ║
riverise-3000s-dpo-second-v2-mkmlizer: ║                                                                     ║
riverise-3000s-dpo-second-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
riverise-3000s-dpo-second-v2-mkmlizer: ║  belonging to:                                                      ║
riverise-3000s-dpo-second-v2-mkmlizer: ║                                                                     ║
riverise-3000s-dpo-second-v2-mkmlizer: ║  Chai Research Corp.                                                ║
riverise-3000s-dpo-second-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
riverise-3000s-dpo-second-v2-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
riverise-3000s-dpo-second-v2-mkmlizer: ║                                                                     ║
riverise-3000s-dpo-second-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
riverise-3000s-dpo-second-v2-mkmlizer: quantized model in 28.151s
riverise-3000s-dpo-second-v2-mkmlizer: Processed model Riverise/3000s-dpo-second in 86.142s
riverise-3000s-dpo-second-v2-mkmlizer: creating bucket guanaco-mkml-models
riverise-3000s-dpo-second-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
riverise-3000s-dpo-second-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/riverise-3000s-dpo-second-v2
riverise-3000s-dpo-second-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/riverise-3000s-dpo-second-v2/config.json
riverise-3000s-dpo-second-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/riverise-3000s-dpo-second-v2/special_tokens_map.json
riverise-3000s-dpo-second-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/riverise-3000s-dpo-second-v2/tokenizer_config.json
riverise-3000s-dpo-second-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/riverise-3000s-dpo-second-v2/tokenizer.json
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
riverise-3000s-dpo-second-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/riverise-3000s-dpo-second-v2/flywheel_model.0.safetensors
riverise-3000s-dpo-second-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:10, 28.20it/s]
Loading 0:   4%|▍         | 12/291 [00:00<00:06, 43.85it/s]
Loading 0:   6%|▌         | 17/291 [00:00<00:06, 40.97it/s]
Loading 0:   8%|▊         | 22/291 [00:00<00:06, 40.34it/s]
Loading 0:   9%|▉         | 27/291 [00:00<00:06, 42.24it/s]
Loading 0:  11%|█         | 32/291 [00:00<00:06, 40.63it/s]
Loading 0:  13%|█▎        | 37/291 [00:01<00:09, 27.16it/s]
Loading 0:  14%|█▍        | 41/291 [00:01<00:09, 26.87it/s]
Loading 0:  16%|█▋        | 48/291 [00:01<00:06, 34.79it/s]
Loading 0:  18%|█▊        | 53/291 [00:01<00:06, 35.46it/s]
Loading 0:  20%|█▉        | 58/291 [00:01<00:06, 36.47it/s]
Loading 0:  22%|██▏       | 63/291 [00:01<00:05, 39.03it/s]
Loading 0:  23%|██▎       | 68/291 [00:01<00:06, 33.14it/s]
Loading 0:  25%|██▌       | 74/291 [00:02<00:05, 38.23it/s]
Loading 0:  27%|██▋       | 79/291 [00:02<00:05, 35.92it/s]
Loading 0:  29%|██▊       | 83/291 [00:02<00:08, 24.65it/s]
Loading 0:  31%|███       | 90/291 [00:02<00:06, 32.11it/s]
Loading 0:  33%|███▎      | 95/291 [00:02<00:05, 33.66it/s]
Loading 0:  34%|███▍      | 100/291 [00:02<00:05, 35.31it/s]
Loading 0:  36%|███▌      | 105/291 [00:03<00:04, 38.29it/s]
Loading 0:  38%|███▊      | 110/291 [00:03<00:05, 32.86it/s]
Loading 0:  40%|███▉      | 116/291 [00:03<00:04, 37.57it/s]
Loading 0:  42%|████▏     | 122/291 [00:03<00:04, 41.24it/s]
Loading 0:  44%|████▎     | 127/291 [00:03<00:04, 38.40it/s]
Loading 0:  46%|████▌     | 133/291 [00:03<00:04, 33.58it/s]
Loading 0:  47%|████▋     | 137/291 [00:03<00:04, 33.32it/s]
Loading 0:  48%|████▊     | 141/291 [00:04<00:04, 31.14it/s]
Loading 0:  51%|█████     | 147/291 [00:04<00:04, 35.77it/s]
Loading 0:  52%|█████▏    | 151/291 [00:04<00:04, 34.77it/s]
Loading 0:  54%|█████▎    | 156/291 [00:04<00:03, 37.32it/s]
Loading 0:  55%|█████▍    | 160/291 [00:04<00:03, 35.76it/s]
Loading 0:  57%|█████▋    | 165/291 [00:04<00:03, 38.14it/s]
Loading 0:  58%|█████▊    | 169/291 [00:04<00:03, 36.03it/s]
Loading 0:  60%|█████▉    | 174/291 [00:04<00:03, 38.51it/s]
Loading 0:  61%|██████    | 178/291 [00:05<00:03, 36.35it/s]
Loading 0:  63%|██████▎   | 184/291 [00:05<00:02, 42.07it/s]
Loading 0:  65%|██████▍   | 189/291 [00:05<00:03, 26.09it/s]
Loading 0:  67%|██████▋   | 194/291 [00:05<00:03, 27.18it/s]
Loading 0:  69%|██████▉   | 201/291 [00:05<00:02, 33.62it/s]
Loading 0:  70%|███████   | 205/291 [00:05<00:02, 33.11it/s]
Loading 0:  72%|███████▏  | 210/291 [00:06<00:02, 35.79it/s]
Loading 0:  74%|███████▎  | 214/291 [00:06<00:02, 34.55it/s]
Loading 0:  75%|███████▌  | 219/291 [00:06<00:01, 37.23it/s]
Loading 0:  77%|███████▋  | 223/291 [00:06<00:01, 35.78it/s]
Loading 0:  78%|███████▊  | 227/291 [00:06<00:01, 35.38it/s]
Loading 0:  79%|███████▉  | 231/291 [00:06<00:01, 35.37it/s]
Loading 0:  81%|████████  | 235/291 [00:06<00:02, 26.58it/s]
Loading 0:  82%|████████▏ | 239/291 [00:07<00:01, 26.25it/s]
Loading 0:  85%|████████▍ | 246/291 [00:07<00:01, 33.59it/s]
Loading 0:  86%|████████▌ | 250/291 [00:07<00:01, 33.05it/s]
Loading 0:  88%|████████▊ | 255/291 [00:07<00:00, 36.33it/s]
Loading 0:  89%|████████▉ | 259/291 [00:07<00:00, 35.26it/s]
Loading 0:  91%|█████████ | 264/291 [00:07<00:00, 37.76it/s]
Loading 0:  92%|█████████▏| 268/291 [00:07<00:00, 36.02it/s]
Loading 0:  94%|█████████▍| 273/291 [00:07<00:00, 38.49it/s]
Loading 0:  95%|█████████▌| 277/291 [00:08<00:00, 35.94it/s]
Loading 0:  97%|█████████▋| 281/291 [00:08<00:00, 34.83it/s]
Loading 0:  98%|█████████▊| 286/291 [00:13<00:01,  2.63it/s]
Loading 0:  99%|█████████▉| 289/291 [00:13<00:00,  3.28it/s]
                                                            

Job riverise-3000s-dpo-second-v2-mkmlizer completed after 105.93s with status: succeeded
Stopping job with name riverise-3000s-dpo-second-v2-mkmlizer
Pipeline stage MKMLizer completed in 109.84s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service riverise-3000s-dpo-second-v2
Waiting for inference service riverise-3000s-dpo-second-v2 to be ready
Inference service riverise-3000s-dpo-second-v2 ready after 191.01050686836243s
Pipeline stage MKMLDeployer completed in 191.37s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.8474361896514893s
Received healthy response to inference request in 1.5942604541778564s
Received healthy response to inference request in 1.72800874710083s
Received healthy response to inference request in 2.5304665565490723s
Received healthy response to inference request in 1.6801016330718994s
5 requests
0 failed requests
5th percentile: 1.611428689956665
10th percentile: 1.6285969257354735
20th percentile: 1.6629333972930909
30th percentile: 1.6896830558776856
40th percentile: 1.7088459014892579
50th percentile: 1.72800874710083
60th percentile: 1.7757797241210938
70th percentile: 1.8235507011413574
80th percentile: 1.984042263031006
90th percentile: 2.257254409790039
95th percentile: 2.3938604831695556
99th percentile: 2.503145341873169
mean time: 1.8760547161102294
Pipeline stage StressChecker completed in 10.85s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
starting trigger_guanaco_pipeline %s
Pipeline stage TriggerMKMLProfilingPipeline completed in 6.26s
riverise-3000s-dpo-second_v2 status is now deployed due to DeploymentManager action
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service riverise-3000s-dpo-second-v2-profiler
Waiting for inference service riverise-3000s-dpo-second-v2-profiler to be ready
Inference service riverise-3000s-dpo-second-v2-profiler ready after 190.4188928604126s
Pipeline stage MKMLProfilerDeployer completed in 190.79s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
script pods %s
Pipeline stage MKMLProfilerRunner completed in 0.36s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service riverise-3000s-dpo-second-v2-profiler is running
Tearing down inference service riverise-3000s-dpo-second-v2-profiler
Service riverise-3000s-dpo-second-v2-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.74s
riverise-3000s-dpo-second_v2 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics