submission_id: riverise-model-trained-o_3967_v1
developer_uid: Riverise
alignment_samples: 10663
alignment_score: 0.012403262188794516
best_of: 16
celo_rating: 1231.53
display_name: riverise-model-trained-o_3967_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/model_trained_on_sonnet_2rd
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: Riverise/model_trained_o
model_name: riverise-model-trained-o_3967_v1
model_num_parameters: 8030261248.0
model_repo: Riverise/model_trained_on_sonnet_2rd
model_size: 8B
num_battles: 10663
num_wins: 5273
propriety_score: 0.7349397590361446
propriety_total_count: 996.0
ranking_group: single
status: inactive
submission_type: basic
timestamp: 2024-08-31T06:36:10+00:00
us_pacific_date: 2024-08-30
win_ratio: 0.4945137390978149
Download Preference Data
Resubmit model
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLizer
Starting job with name riverise-model-trained-o-3967-v1-mkmlizer
Waiting for job on riverise-model-trained-o-3967-v1-mkmlizer to finish
Stopping job with name riverise-model-trained-o-3967-v1-mkmlizer
%s, retrying in %s seconds...
Starting job with name riverise-model-trained-o-3967-v1-mkmlizer
Waiting for job on riverise-model-trained-o-3967-v1-mkmlizer to finish
riverise-model-trained-o-3967-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
riverise-model-trained-o-3967-v1-mkmlizer: ║     _____            __           __                                ║
riverise-model-trained-o-3967-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
riverise-model-trained-o-3967-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
riverise-model-trained-o-3967-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
riverise-model-trained-o-3967-v1-mkmlizer: ║       /___/                                                         ║
riverise-model-trained-o-3967-v1-mkmlizer: ║                                                                     ║
riverise-model-trained-o-3967-v1-mkmlizer: ║  Version: 0.10.1                                                    ║
riverise-model-trained-o-3967-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
riverise-model-trained-o-3967-v1-mkmlizer: ║  https://mk1.ai                                                     ║
riverise-model-trained-o-3967-v1-mkmlizer: ║                                                                     ║
riverise-model-trained-o-3967-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
riverise-model-trained-o-3967-v1-mkmlizer: ║  belonging to:                                                      ║
riverise-model-trained-o-3967-v1-mkmlizer: ║                                                                     ║
riverise-model-trained-o-3967-v1-mkmlizer: ║  Chai Research Corp.                                                ║
riverise-model-trained-o-3967-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
riverise-model-trained-o-3967-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
riverise-model-trained-o-3967-v1-mkmlizer: ║                                                                     ║
riverise-model-trained-o-3967-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
riverise-model-trained-o-3967-v1-mkmlizer: Downloaded to shared memory in 61.605s
riverise-model-trained-o-3967-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpxz5ebkpu, device:0
riverise-model-trained-o-3967-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
riverise-model-trained-o-3967-v1-mkmlizer: quantized model in 29.319s
riverise-model-trained-o-3967-v1-mkmlizer: Processed model Riverise/model_trained_on_sonnet_2rd in 90.924s
riverise-model-trained-o-3967-v1-mkmlizer: creating bucket guanaco-mkml-models
riverise-model-trained-o-3967-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
riverise-model-trained-o-3967-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/riverise-model-trained-o-3967-v1
riverise-model-trained-o-3967-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/riverise-model-trained-o-3967-v1/config.json
riverise-model-trained-o-3967-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/riverise-model-trained-o-3967-v1/special_tokens_map.json
riverise-model-trained-o-3967-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/riverise-model-trained-o-3967-v1/tokenizer_config.json
riverise-model-trained-o-3967-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/riverise-model-trained-o-3967-v1/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
riverise-model-trained-o-3967-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/riverise-model-trained-o-3967-v1/flywheel_model.0.safetensors
riverise-model-trained-o-3967-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:10, 26.27it/s]
Loading 0:   4%|▍         | 12/291 [00:00<00:07, 36.86it/s]
Loading 0:   5%|▌         | 16/291 [00:00<00:07, 34.73it/s]
Loading 0:   7%|▋         | 21/291 [00:00<00:07, 38.36it/s]
Loading 0:   9%|▊         | 25/291 [00:00<00:07, 35.99it/s]
Loading 0:  11%|█         | 31/291 [00:00<00:06, 41.75it/s]
Loading 0:  12%|█▏        | 36/291 [00:01<00:10, 23.46it/s]
Loading 0:  14%|█▍        | 41/291 [00:01<00:10, 24.66it/s]
Loading 0:  16%|█▋        | 48/291 [00:01<00:07, 30.82it/s]
Loading 0:  18%|█▊        | 52/291 [00:01<00:08, 29.68it/s]
Loading 0:  20%|█▉        | 57/291 [00:01<00:07, 31.80it/s]
Loading 0:  21%|██        | 61/291 [00:01<00:07, 31.25it/s]
Loading 0:  23%|██▎       | 66/291 [00:02<00:06, 32.86it/s]
Loading 0:  24%|██▍       | 70/291 [00:02<00:07, 31.53it/s]
Loading 0:  25%|██▌       | 74/291 [00:02<00:06, 32.14it/s]
Loading 0:  27%|██▋       | 78/291 [00:02<00:06, 32.16it/s]
Loading 0:  28%|██▊       | 82/291 [00:02<00:09, 23.04it/s]
Loading 0:  29%|██▉       | 85/291 [00:02<00:08, 23.94it/s]
Loading 0:  31%|███       | 90/291 [00:02<00:07, 28.64it/s]
Loading 0:  32%|███▏      | 94/291 [00:03<00:06, 29.18it/s]
Loading 0:  34%|███▍      | 99/291 [00:03<00:05, 33.19it/s]
Loading 0:  35%|███▌      | 103/291 [00:03<00:05, 31.70it/s]
Loading 0:  37%|███▋      | 108/291 [00:03<00:05, 33.48it/s]
Loading 0:  38%|███▊      | 112/291 [00:03<00:05, 31.28it/s]
Loading 0:  40%|███▉      | 116/291 [00:03<00:05, 31.31it/s]
Loading 0:  42%|████▏     | 122/291 [00:03<00:04, 34.74it/s]
Loading 0:  44%|████▎     | 127/291 [00:04<00:05, 32.16it/s]
Loading 0:  46%|████▌     | 133/291 [00:04<00:05, 28.62it/s]
Loading 0:  47%|████▋     | 137/291 [00:04<00:05, 28.70it/s]
Loading 0:  48%|████▊     | 140/291 [00:04<00:05, 25.66it/s]
Loading 0:  51%|█████     | 147/291 [00:04<00:04, 32.62it/s]
Loading 0:  52%|█████▏    | 151/291 [00:04<00:04, 29.93it/s]
Loading 0:  54%|█████▎    | 156/291 [00:05<00:04, 33.03it/s]
Loading 0:  55%|█████▍    | 160/291 [00:05<00:04, 31.94it/s]
Loading 0:  57%|█████▋    | 165/291 [00:05<00:03, 34.86it/s]
Loading 0:  58%|█████▊    | 169/291 [00:05<00:03, 32.26it/s]
Loading 0:  60%|█████▉    | 174/291 [00:05<00:03, 34.47it/s]
Loading 0:  61%|██████    | 178/291 [00:05<00:03, 32.71it/s]
Loading 0:  63%|██████▎   | 184/291 [00:05<00:02, 39.23it/s]
Loading 0:  65%|██████▍   | 189/291 [00:06<00:04, 22.04it/s]
Loading 0:  67%|██████▋   | 194/291 [00:06<00:04, 23.37it/s]
Loading 0:  69%|██████▉   | 201/291 [00:06<00:03, 29.88it/s]
Loading 0:  70%|███████   | 205/291 [00:06<00:02, 29.63it/s]
Loading 0:  72%|███████▏  | 210/291 [00:06<00:02, 32.38it/s]
Loading 0:  74%|███████▎  | 214/291 [00:07<00:02, 31.23it/s]
Loading 0:  75%|███████▌  | 219/291 [00:07<00:02, 33.67it/s]
Loading 0:  77%|███████▋  | 223/291 [00:07<00:02, 32.32it/s]
Loading 0:  78%|███████▊  | 227/291 [00:07<00:02, 31.85it/s]
Loading 0:  79%|███████▉  | 231/291 [00:07<00:01, 30.60it/s]
Loading 0:  81%|████████  | 235/291 [00:07<00:02, 24.10it/s]
Loading 0:  82%|████████▏ | 239/291 [00:07<00:02, 23.56it/s]
Loading 0:  85%|████████▍ | 246/291 [00:08<00:01, 30.37it/s]
Loading 0:  86%|████████▌ | 250/291 [00:08<00:01, 29.37it/s]
Loading 0:  88%|████████▊ | 255/291 [00:08<00:01, 31.51it/s]
Loading 0:  89%|████████▉ | 259/291 [00:08<00:01, 30.87it/s]
Loading 0:  91%|█████████ | 264/291 [00:08<00:00, 33.93it/s]
Loading 0:  92%|█████████▏| 268/291 [00:08<00:00, 32.59it/s]
Loading 0:  94%|█████████▍| 273/291 [00:08<00:00, 35.37it/s]
Loading 0:  95%|█████████▌| 277/291 [00:09<00:00, 34.25it/s]
Loading 0:  97%|█████████▋| 281/291 [00:09<00:00, 33.75it/s]
Loading 0:  98%|█████████▊| 286/291 [00:14<00:01,  2.59it/s]
Loading 0:  99%|█████████▉| 289/291 [00:14<00:00,  3.22it/s]
                                                            

Job riverise-model-trained-o-3967-v1-mkmlizer completed after 115.86s with status: succeeded
Stopping job with name riverise-model-trained-o-3967-v1-mkmlizer
Pipeline stage MKMLizer completed in 117.32s
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-model-trained-o-3967-v1
Waiting for inference service riverise-model-trained-o-3967-v1 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service riverise-model-trained-o-3967-v1 ready after 240.69266414642334s
Pipeline stage MKMLDeployer completed in 241.23s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9858129024505615s
Received healthy response to inference request in 1.6615593433380127s
Received healthy response to inference request in 2.7157797813415527s
Received healthy response to inference request in 1.3028595447540283s
Received healthy response to inference request in 1.717350959777832s
5 requests
0 failed requests
5th percentile: 1.3745995044708252
10th percentile: 1.4463394641876222
20th percentile: 1.5898193836212158
30th percentile: 1.6727176666259767
40th percentile: 1.6950343132019043
50th percentile: 1.717350959777832
60th percentile: 1.824735736846924
70th percentile: 1.9321205139160156
80th percentile: 2.13180627822876
90th percentile: 2.4237930297851564
95th percentile: 2.569786405563354
99th percentile: 2.686581106185913
mean time: 1.8766725063323975
Pipeline stage StressChecker completed in 10.30s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
starting trigger_guanaco_pipeline %s
Pipeline stage TriggerMKMLProfilingPipeline completed in 5.40s
riverise-model-trained-o_3967_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 0.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service riverise-model-trained-o-3967-v1-profiler
Waiting for inference service riverise-model-trained-o-3967-v1-profiler to be ready
Inference service riverise-model-trained-o-3967-v1-profiler ready after 190.5023684501648s
Pipeline stage MKMLProfilerDeployer completed in 190.95s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
script pods %s
Pipeline stage MKMLProfilerRunner completed in 0.50s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service riverise-model-trained-o-3967-v1-profiler is running
Tearing down inference service riverise-model-trained-o-3967-v1-profiler
Service riverise-model-trained-o-3967-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.06s
riverise-model-trained-o_3967_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics