submission_id: riverise-3000s-dpo-second_v1
developer_uid: Riverise
alignment_samples: 12582
alignment_score: -0.40060200732844886
best_of: 16
celo_rating: 1246.19
display_name: riverise-3000s-dpo-second_v1
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': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, '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_v1
model_num_parameters: 8030261248.0
model_repo: Riverise/3000s-dpo-second
model_size: 8B
num_battles: 12582
num_wins: 6551
propriety_score: 0.7375690607734806
propriety_total_count: 1086.0
ranking_group: single
status: inactive
submission_type: basic
timestamp: 2024-09-01T08:12:09+00:00
us_pacific_date: 2024-09-01
win_ratio: 0.5206644412652996
Download Preference Data
Resubmit model
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLizer
Starting job with name riverise-3000s-dpo-second-v1-mkmlizer
Waiting for job on riverise-3000s-dpo-second-v1-mkmlizer to finish
Stopping job with name riverise-3000s-dpo-second-v1-mkmlizer
%s, retrying in %s seconds...
Starting job with name riverise-3000s-dpo-second-v1-mkmlizer
Waiting for job on riverise-3000s-dpo-second-v1-mkmlizer to finish
riverise-3000s-dpo-second-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
riverise-3000s-dpo-second-v1-mkmlizer: ║     _____            __           __                                ║
riverise-3000s-dpo-second-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
riverise-3000s-dpo-second-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
riverise-3000s-dpo-second-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
riverise-3000s-dpo-second-v1-mkmlizer: ║       /___/                                                         ║
riverise-3000s-dpo-second-v1-mkmlizer: ║                                                                     ║
riverise-3000s-dpo-second-v1-mkmlizer: ║  Version: 0.10.1                                                    ║
riverise-3000s-dpo-second-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
riverise-3000s-dpo-second-v1-mkmlizer: ║  https://mk1.ai                                                     ║
riverise-3000s-dpo-second-v1-mkmlizer: ║                                                                     ║
riverise-3000s-dpo-second-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
riverise-3000s-dpo-second-v1-mkmlizer: ║  belonging to:                                                      ║
riverise-3000s-dpo-second-v1-mkmlizer: ║                                                                     ║
riverise-3000s-dpo-second-v1-mkmlizer: ║  Chai Research Corp.                                                ║
riverise-3000s-dpo-second-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
riverise-3000s-dpo-second-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
riverise-3000s-dpo-second-v1-mkmlizer: ║                                                                     ║
riverise-3000s-dpo-second-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
riverise-3000s-dpo-second-v1-mkmlizer: Downloaded to shared memory in 68.874s
riverise-3000s-dpo-second-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpslayj6sw, device:0
riverise-3000s-dpo-second-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission chaiml-sao10k-l3-rp-v3-3_v37: ('http://chaiml-sao10k-l3-rp-v3-3-v37-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:36924->127.0.0.1:8080: read: connection reset by peer\n')
riverise-3000s-dpo-second-v1-mkmlizer: creating bucket guanaco-mkml-models
riverise-3000s-dpo-second-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
riverise-3000s-dpo-second-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/riverise-3000s-dpo-second-v1
riverise-3000s-dpo-second-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/riverise-3000s-dpo-second-v1/config.json
riverise-3000s-dpo-second-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/riverise-3000s-dpo-second-v1/special_tokens_map.json
riverise-3000s-dpo-second-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/riverise-3000s-dpo-second-v1/tokenizer_config.json
riverise-3000s-dpo-second-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/riverise-3000s-dpo-second-v1/tokenizer.json
riverise-3000s-dpo-second-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/riverise-3000s-dpo-second-v1/flywheel_model.0.safetensors
riverise-3000s-dpo-second-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:10, 27.26it/s]
Loading 0:   4%|▍         | 12/291 [00:00<00:07, 36.74it/s]
Loading 0:   5%|▌         | 16/291 [00:00<00:07, 34.58it/s]
Loading 0:   7%|▋         | 21/291 [00:00<00:07, 37.67it/s]
Loading 0:   9%|▊         | 25/291 [00:00<00:07, 35.04it/s]
Loading 0:  11%|█         | 31/291 [00:00<00:06, 41.31it/s]
Loading 0:  12%|█▏        | 36/291 [00:01<00:10, 24.22it/s]
Loading 0:  14%|█▍        | 41/291 [00:01<00:09, 26.12it/s]
Loading 0:  16%|█▋        | 48/291 [00:01<00:07, 32.93it/s]
Loading 0:  18%|█▊        | 52/291 [00:01<00:07, 32.04it/s]
Loading 0:  20%|█▉        | 57/291 [00:01<00:06, 34.87it/s]
Loading 0:  21%|██        | 61/291 [00:01<00:06, 33.77it/s]
Loading 0:  23%|██▎       | 66/291 [00:01<00:06, 36.20it/s]
Loading 0:  24%|██▍       | 70/291 [00:02<00:06, 34.42it/s]
Loading 0:  25%|██▌       | 74/291 [00:02<00:06, 34.40it/s]
Loading 0:  27%|██▋       | 78/291 [00:02<00:06, 34.54it/s]
Loading 0:  28%|██▊       | 82/291 [00:02<00:08, 24.67it/s]
Loading 0:  30%|██▉       | 86/291 [00:02<00:07, 27.42it/s]
Loading 0:  31%|███       | 90/291 [00:02<00:06, 29.82it/s]
Loading 0:  32%|███▏      | 94/291 [00:02<00:06, 30.59it/s]
Loading 0:  34%|███▍      | 99/291 [00:03<00:05, 34.43it/s]
Loading 0:  35%|███▌      | 103/291 [00:03<00:05, 33.14it/s]
Loading 0:  37%|███▋      | 108/291 [00:03<00:05, 36.11it/s]
Loading 0:  38%|███▊      | 112/291 [00:03<00:05, 34.60it/s]
Loading 0:  40%|███▉      | 116/291 [00:03<00:04, 35.13it/s]
Loading 0:  42%|████▏     | 122/291 [00:03<00:04, 39.60it/s]
Loading 0:  44%|████▎     | 127/291 [00:03<00:04, 36.86it/s]
Loading 0:  46%|████▌     | 133/291 [00:04<00:04, 33.30it/s]
Loading 0:  47%|████▋     | 137/291 [00:04<00:04, 33.21it/s]
Loading 0:  48%|████▊     | 141/291 [00:04<00:04, 30.71it/s]
Loading 0:  51%|█████     | 147/291 [00:04<00:04, 35.09it/s]
Loading 0:  52%|█████▏    | 151/291 [00:04<00:04, 33.93it/s]
Loading 0:  54%|█████▎    | 156/291 [00:04<00:03, 36.24it/s]
Loading 0:  55%|█████▍    | 160/291 [00:04<00:03, 34.36it/s]
Loading 0:  57%|█████▋    | 165/291 [00:04<00:03, 36.51it/s]
Loading 0:  58%|█████▊    | 169/291 [00:05<00:03, 34.59it/s]
Loading 0:  60%|█████▉    | 174/291 [00:05<00:03, 37.39it/s]
Loading 0:  61%|██████    | 178/291 [00:05<00:03, 35.78it/s]
Loading 0:  63%|██████▎   | 184/291 [00:05<00:02, 41.75it/s]
Loading 0:  65%|██████▍   | 189/291 [00:05<00:03, 25.74it/s]
Loading 0:  67%|██████▋   | 194/291 [00:05<00:03, 27.16it/s]
Loading 0:  69%|██████▉   | 201/291 [00:06<00:02, 33.79it/s]
Loading 0:  71%|███████   | 206/291 [00:06<00:02, 34.62it/s]
Loading 0:  72%|███████▏  | 210/291 [00:06<00:02, 35.54it/s]
Loading 0:  74%|███████▎  | 214/291 [00:06<00:02, 34.09it/s]
Loading 0:  75%|███████▌  | 219/291 [00:06<00:01, 36.62it/s]
Loading 0:  77%|███████▋  | 223/291 [00:06<00:01, 35.00it/s]
Loading 0:  78%|███████▊  | 227/291 [00:06<00:01, 34.76it/s]
Loading 0:  79%|███████▉  | 231/291 [00:06<00:01, 34.90it/s]
Loading 0:  81%|████████  | 235/291 [00:07<00:02, 26.74it/s]
Loading 0:  82%|████████▏ | 239/291 [00:07<00:01, 26.46it/s]
Loading 0:  85%|████████▍ | 246/291 [00:07<00:01, 34.34it/s]
Loading 0:  86%|████████▌ | 250/291 [00:07<00:01, 33.38it/s]
Loading 0:  88%|████████▊ | 255/291 [00:07<00:01, 35.53it/s]
Loading 0:  89%|████████▉ | 259/291 [00:07<00:00, 33.74it/s]
Loading 0:  91%|█████████ | 264/291 [00:07<00:00, 36.19it/s]
Loading 0:  92%|█████████▏| 268/291 [00:08<00:00, 35.11it/s]
Loading 0:  94%|█████████▍| 273/291 [00:08<00:00, 37.18it/s]
Loading 0:  95%|█████████▌| 277/291 [00:08<00:00, 35.59it/s]
Loading 0:  97%|█████████▋| 281/291 [00:08<00:00, 35.71it/s]
Loading 0:  98%|█████████▊| 286/291 [00:13<00:01,  2.61it/s]
Loading 0:  99%|█████████▉| 289/291 [00:14<00:00,  3.25it/s]
                                                            

Job riverise-3000s-dpo-second-v1-mkmlizer completed after 114.67s with status: succeeded
Stopping job with name riverise-3000s-dpo-second-v1-mkmlizer
Pipeline stage MKMLizer completed in 116.20s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.08s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service riverise-3000s-dpo-second-v1
Waiting for inference service riverise-3000s-dpo-second-v1 to be ready
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
Inference service riverise-3000s-dpo-second-v1 ready after 291.6117124557495s
Pipeline stage MKMLDeployer completed in 291.94s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.186896324157715s
Received healthy response to inference request in 1.3853857517242432s
Received healthy response to inference request in 2.3527603149414062s
Received healthy response to inference request in 1.4022400379180908s
Received healthy response to inference request in 1.28513503074646s
5 requests
0 failed requests
5th percentile: 1.3051851749420167
10th percentile: 1.3252353191375732
20th percentile: 1.3653356075286864
30th percentile: 1.3887566089630128
40th percentile: 1.3954983234405518
50th percentile: 1.4022400379180908
60th percentile: 1.7824481487274169
70th percentile: 2.162656259536743
80th percentile: 2.519587516784668
90th percentile: 2.8532419204711914
95th percentile: 3.020069122314453
99th percentile: 3.1535308837890623
mean time: 1.922483491897583
Pipeline stage StressChecker completed in 10.40s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
starting trigger_guanaco_pipeline %s
Pipeline stage TriggerMKMLProfilingPipeline completed in 6.45s
riverise-3000s-dpo-second_v1 status is now deployed due to DeploymentManager action
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service riverise-3000s-dpo-second-v1-profiler
Waiting for inference service riverise-3000s-dpo-second-v1-profiler to be ready
Inference service riverise-3000s-dpo-second-v1-profiler ready after 200.43250179290771s
Pipeline stage MKMLProfilerDeployer completed in 200.78s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
script pods %s
Pipeline stage MKMLProfilerRunner completed in 0.38s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service riverise-3000s-dpo-second-v1-profiler is running
Tearing down inference service riverise-3000s-dpo-second-v1-profiler
Service riverise-3000s-dpo-second-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.98s
riverise-3000s-dpo-second_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics