submission_id: riverise-model-trained-o_3967_v2
developer_uid: Riverise
alignment_samples: 11401
alignment_score: -0.45090731228213726
best_of: 16
celo_rating: 1131.09
display_name: sonnet_second_model
formatter: {'memory_template': "<|start_header_id|>system<|end_header_id|>\n\n{bot_name}'s Persona: {memory}\n\n", 'prompt_template': '{prompt}<|eot_id|>', 'bot_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}: {message}<|eot_id|>', 'user_template': '<|start_header_id|>user<|end_header_id|>\n\nYou: {message}<|eot_id|>', 'response_template': '<|start_header_id|>assistant<|end_header_id|>\n\n', '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: sonnet_second_model
model_num_parameters: 8030261248.0
model_repo: Riverise/model_trained_on_sonnet_2rd
model_size: 8B
num_battles: 11401
num_wins: 4017
propriety_score: 0.7348560079443893
propriety_total_count: 1007.0
ranking_group: single
status: inactive
submission_type: basic
timestamp: 2024-08-31T07:21:42+00:00
us_pacific_date: 2024-08-31
win_ratio: 0.3523375142531357
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-v2-mkmlizer
Waiting for job on riverise-model-trained-o-3967-v2-mkmlizer to finish
Stopping job with name riverise-model-trained-o-3967-v2-mkmlizer
%s, retrying in %s seconds...
Starting job with name riverise-model-trained-o-3967-v2-mkmlizer
Waiting for job on riverise-model-trained-o-3967-v2-mkmlizer to finish
riverise-model-trained-o-3967-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
riverise-model-trained-o-3967-v2-mkmlizer: ║     _____            __           __                                ║
riverise-model-trained-o-3967-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
riverise-model-trained-o-3967-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
riverise-model-trained-o-3967-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
riverise-model-trained-o-3967-v2-mkmlizer: ║       /___/                                                         ║
riverise-model-trained-o-3967-v2-mkmlizer: ║                                                                     ║
riverise-model-trained-o-3967-v2-mkmlizer: ║  Version: 0.10.1                                                    ║
riverise-model-trained-o-3967-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
riverise-model-trained-o-3967-v2-mkmlizer: ║  https://mk1.ai                                                     ║
riverise-model-trained-o-3967-v2-mkmlizer: ║                                                                     ║
riverise-model-trained-o-3967-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
riverise-model-trained-o-3967-v2-mkmlizer: ║  belonging to:                                                      ║
riverise-model-trained-o-3967-v2-mkmlizer: ║                                                                     ║
riverise-model-trained-o-3967-v2-mkmlizer: ║  Chai Research Corp.                                                ║
riverise-model-trained-o-3967-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
riverise-model-trained-o-3967-v2-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
riverise-model-trained-o-3967-v2-mkmlizer: ║                                                                     ║
riverise-model-trained-o-3967-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
riverise-model-trained-o-3967-v2-mkmlizer: Downloaded to shared memory in 61.162s
riverise-model-trained-o-3967-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpldf2m79y, device:0
riverise-model-trained-o-3967-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
riverise-model-trained-o-3967-v2-mkmlizer: quantized model in 28.803s
riverise-model-trained-o-3967-v2-mkmlizer: Processed model Riverise/model_trained_on_sonnet_2rd in 89.965s
riverise-model-trained-o-3967-v2-mkmlizer: creating bucket guanaco-mkml-models
riverise-model-trained-o-3967-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
riverise-model-trained-o-3967-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/riverise-model-trained-o-3967-v2
riverise-model-trained-o-3967-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/riverise-model-trained-o-3967-v2/config.json
riverise-model-trained-o-3967-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/riverise-model-trained-o-3967-v2/special_tokens_map.json
riverise-model-trained-o-3967-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/riverise-model-trained-o-3967-v2/tokenizer_config.json
riverise-model-trained-o-3967-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/riverise-model-trained-o-3967-v2/tokenizer.json
riverise-model-trained-o-3967-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/riverise-model-trained-o-3967-v2/flywheel_model.0.safetensors
riverise-model-trained-o-3967-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:10, 26.14it/s]
Loading 0:   4%|▍         | 12/291 [00:00<00:06, 41.80it/s]
Loading 0:   6%|▌         | 17/291 [00:00<00:07, 38.76it/s]
Loading 0:   8%|▊         | 22/291 [00:00<00:07, 37.73it/s]
Loading 0:   9%|▉         | 26/291 [00:00<00:07, 37.07it/s]
Loading 0:  11%|█         | 32/291 [00:00<00:06, 37.79it/s]
Loading 0:  12%|█▏        | 36/291 [00:01<00:10, 24.23it/s]
Loading 0:  14%|█▍        | 41/291 [00:01<00:09, 26.37it/s]
Loading 0:  16%|█▋        | 48/291 [00:01<00:07, 34.23it/s]
Loading 0:  18%|█▊        | 53/291 [00:01<00:06, 34.54it/s]
Loading 0:  20%|█▉        | 58/291 [00:01<00:06, 35.49it/s]
Loading 0:  22%|██▏       | 63/291 [00:01<00:05, 38.11it/s]
Loading 0:  23%|██▎       | 68/291 [00:02<00:06, 32.65it/s]
Loading 0:  25%|██▌       | 74/291 [00:02<00:05, 37.79it/s]
Loading 0:  27%|██▋       | 79/291 [00:02<00:06, 34.31it/s]
Loading 0:  29%|██▊       | 83/291 [00:02<00:08, 23.30it/s]
Loading 0:  31%|███       | 90/291 [00:02<00:06, 30.35it/s]
Loading 0:  32%|███▏      | 94/291 [00:02<00:06, 30.48it/s]
Loading 0:  34%|███▍      | 99/291 [00:03<00:05, 32.97it/s]
Loading 0:  35%|███▌      | 103/291 [00:03<00:05, 32.91it/s]
Loading 0:  37%|███▋      | 108/291 [00:03<00:05, 36.25it/s]
Loading 0:  38%|███▊      | 112/291 [00:03<00:05, 34.58it/s]
Loading 0:  40%|███▉      | 116/291 [00:03<00:04, 35.01it/s]
Loading 0:  42%|████▏     | 122/291 [00:03<00:04, 39.67it/s]
Loading 0:  44%|████▎     | 127/291 [00:03<00:04, 37.43it/s]
Loading 0:  46%|████▌     | 133/291 [00:04<00:04, 32.17it/s]
Loading 0:  47%|████▋     | 137/291 [00:04<00:04, 32.05it/s]
Loading 0:  48%|████▊     | 141/291 [00:04<00:05, 29.67it/s]
Loading 0:  51%|█████     | 147/291 [00:04<00:04, 34.16it/s]
Loading 0:  52%|█████▏    | 151/291 [00:04<00:04, 32.35it/s]
Loading 0:  54%|█████▎    | 156/291 [00:04<00:03, 33.79it/s]
Loading 0:  55%|█████▍    | 160/291 [00:04<00:03, 33.09it/s]
Loading 0:  57%|█████▋    | 165/291 [00:04<00:03, 35.97it/s]
Loading 0:  58%|█████▊    | 169/291 [00:05<00:03, 33.27it/s]
Loading 0:  60%|█████▉    | 174/291 [00:05<00:03, 35.70it/s]
Loading 0:  61%|██████    | 178/291 [00:05<00:03, 34.07it/s]
Loading 0:  63%|██████▎   | 184/291 [00:05<00:02, 40.01it/s]
Loading 0:  65%|██████▍   | 189/291 [00:05<00:04, 25.36it/s]
Loading 0:  67%|██████▋   | 194/291 [00:05<00:03, 26.77it/s]
Loading 0:  69%|██████▉   | 201/291 [00:06<00:02, 33.66it/s]
Loading 0:  71%|███████   | 206/291 [00:06<00:02, 34.11it/s]
Loading 0:  72%|███████▏  | 210/291 [00:06<00:02, 34.14it/s]
Loading 0:  74%|███████▎  | 214/291 [00:06<00:02, 32.53it/s]
Loading 0:  75%|███████▌  | 219/291 [00:06<00:02, 35.60it/s]
Loading 0:  77%|███████▋  | 223/291 [00:06<00:02, 33.60it/s]
Loading 0:  78%|███████▊  | 227/291 [00:06<00:01, 33.51it/s]
Loading 0:  79%|███████▉  | 231/291 [00:06<00:01, 33.27it/s]
Loading 0:  81%|████████  | 235/291 [00:07<00:02, 24.74it/s]
Loading 0:  82%|████████▏ | 239/291 [00:07<00:02, 25.06it/s]
Loading 0:  85%|████████▍ | 246/291 [00:07<00:01, 33.16it/s]
Loading 0:  86%|████████▌ | 250/291 [00:07<00:01, 33.19it/s]
Loading 0:  88%|████████▊ | 255/291 [00:07<00:01, 35.76it/s]
Loading 0:  89%|████████▉ | 259/291 [00:07<00:00, 34.91it/s]
Loading 0:  91%|█████████ | 264/291 [00:07<00:00, 37.87it/s]
Loading 0:  92%|█████████▏| 268/291 [00:08<00:00, 36.25it/s]
Loading 0:  94%|█████████▍| 273/291 [00:08<00:00, 38.62it/s]
Loading 0:  95%|█████████▌| 277/291 [00:08<00:00, 35.94it/s]
Loading 0:  97%|█████████▋| 281/291 [00:08<00:00, 34.82it/s]
Loading 0:  98%|█████████▊| 286/291 [00:13<00:01,  2.63it/s]
Loading 0:  99%|█████████▉| 289/291 [00:14<00:00,  3.28it/s]
                                                            

Job riverise-model-trained-o-3967-v2-mkmlizer completed after 106.37s with status: succeeded
Stopping job with name riverise-model-trained-o-3967-v2-mkmlizer
Pipeline stage MKMLizer completed in 108.21s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.12s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service riverise-model-trained-o-3967-v2
Waiting for inference service riverise-model-trained-o-3967-v2 to be ready
Inference service riverise-model-trained-o-3967-v2 ready after 180.63570952415466s
Pipeline stage MKMLDeployer completed in 181.01s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9669418334960938s
Received healthy response to inference request in 1.7446818351745605s
Received healthy response to inference request in 1.9233481884002686s
Received healthy response to inference request in 2.4455368518829346s
Received healthy response to inference request in 2.387996196746826s
5 requests
0 failed requests
5th percentile: 1.7804151058197022
10th percentile: 1.8161483764648438
20th percentile: 1.887614917755127
30th percentile: 1.9320669174194336
40th percentile: 1.9495043754577637
50th percentile: 1.9669418334960938
60th percentile: 2.1353635787963867
70th percentile: 2.3037853240966797
80th percentile: 2.3995043277740478
90th percentile: 2.4225205898284914
95th percentile: 2.434028720855713
99th percentile: 2.44323522567749
mean time: 2.093700981140137
Pipeline stage StressChecker completed in 11.30s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
starting trigger_guanaco_pipeline %s
Pipeline stage TriggerMKMLProfilingPipeline completed in 6.59s
riverise-model-trained-o_3967_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-model-trained-o-3967-v2-profiler
Waiting for inference service riverise-model-trained-o-3967-v2-profiler to be ready
Inference service riverise-model-trained-o-3967-v2-profiler ready after 190.42889547348022s
Pipeline stage MKMLProfilerDeployer completed in 190.89s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
script pods %s
Pipeline stage MKMLProfilerRunner completed in 0.34s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service riverise-model-trained-o-3967-v2-profiler is running
Tearing down inference service riverise-model-trained-o-3967-v2-profiler
Service riverise-model-trained-o-3967-v2-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.90s
riverise-model-trained-o_3967_v2 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics