riverise-model-on-sonnet

developer_uid: Riverise

submission_id: riverise-model-on-sonnet_v3

model_name: riverise-model-on-sonnet_v2

model_group: Riverise/model_on_sonnet

status: torndown

timestamp: 2024-08-31T06:51:42+00:00

num_battles: 12024

num_wins: 6137

celo_rating: 1241.97

family_friendly_score: 0.0

submission_type: basic

model_repo: Riverise/model_on_sonnet

model_architecture: LlamaForCausalLM

model_num_parameters: 8030261248.0

best_of: 16

max_input_tokens: 512

max_output_tokens: 64

display_name: riverise-model-on-sonnet_v2

is_internal_developer: False

language_model: Riverise/model_on_sonnet

model_size: 8B

ranking_group: single

us_pacific_date: 2024-08-30

win_ratio: 0.510395874916833

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}

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}

Resubmit model

run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLizer
Starting job with name riverise-model-on-sonnet-v3-mkmlizer
Waiting for job on riverise-model-on-sonnet-v3-mkmlizer to finish
riverise-model-on-sonnet-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
riverise-model-on-sonnet-v3-mkmlizer: ║     _____            __           __                                ║
riverise-model-on-sonnet-v3-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
riverise-model-on-sonnet-v3-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
riverise-model-on-sonnet-v3-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
riverise-model-on-sonnet-v3-mkmlizer: ║       /___/                                                         ║
riverise-model-on-sonnet-v3-mkmlizer: ║                                                                     ║
riverise-model-on-sonnet-v3-mkmlizer: ║  Version: 0.10.1                                                    ║
riverise-model-on-sonnet-v3-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
riverise-model-on-sonnet-v3-mkmlizer: ║  https://mk1.ai                                                     ║
riverise-model-on-sonnet-v3-mkmlizer: ║                                                                     ║
riverise-model-on-sonnet-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
riverise-model-on-sonnet-v3-mkmlizer: ║  belonging to:                                                      ║
riverise-model-on-sonnet-v3-mkmlizer: ║                                                                     ║
riverise-model-on-sonnet-v3-mkmlizer: ║  Chai Research Corp.                                                ║
riverise-model-on-sonnet-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
riverise-model-on-sonnet-v3-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
riverise-model-on-sonnet-v3-mkmlizer: ║                                                                     ║
riverise-model-on-sonnet-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
riverise-model-on-sonnet-v3-mkmlizer: Downloaded to shared memory in 31.430s
riverise-model-on-sonnet-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpua71ts76, device:0
riverise-model-on-sonnet-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
riverise-model-on-sonnet-v3-mkmlizer: quantized model in 26.310s
riverise-model-on-sonnet-v3-mkmlizer: Processed model Riverise/model_on_sonnet in 57.740s
riverise-model-on-sonnet-v3-mkmlizer: creating bucket guanaco-mkml-models
riverise-model-on-sonnet-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
riverise-model-on-sonnet-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/riverise-model-on-sonnet-v3
riverise-model-on-sonnet-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/riverise-model-on-sonnet-v3/config.json
riverise-model-on-sonnet-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/riverise-model-on-sonnet-v3/special_tokens_map.json
riverise-model-on-sonnet-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/riverise-model-on-sonnet-v3/tokenizer_config.json
riverise-model-on-sonnet-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/riverise-model-on-sonnet-v3/tokenizer.json
riverise-model-on-sonnet-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/riverise-model-on-sonnet-v3/flywheel_model.0.safetensors
riverise-model-on-sonnet-v3-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 7/291 [00:00<00:05, 54.42it/s]
Loading 0:   8%|▊         | 22/291 [00:00<00:03, 88.68it/s]
Loading 0:  11%|█         | 31/291 [00:00<00:03, 78.75it/s]
Loading 0:  14%|█▎        | 40/291 [00:00<00:03, 74.44it/s]
Loading 0:  18%|█▊        | 52/291 [00:00<00:03, 76.64it/s]
Loading 0:  21%|██        | 61/291 [00:00<00:03, 75.36it/s]
Loading 0:  26%|██▌       | 76/291 [00:00<00:02, 83.63it/s]
Loading 0:  29%|██▉       | 85/291 [00:02<00:09, 22.62it/s]
Loading 0:  32%|███▏      | 94/291 [00:02<00:07, 27.97it/s]
Loading 0:  35%|███▌      | 103/291 [00:02<00:05, 34.60it/s]
Loading 0:  38%|███▊      | 112/291 [00:02<00:04, 40.58it/s]
Loading 0:  42%|████▏     | 121/291 [00:02<00:03, 45.75it/s]
Loading 0:  45%|████▍     | 130/291 [00:02<00:03, 50.04it/s]
Loading 0:  48%|████▊     | 139/291 [00:02<00:02, 54.10it/s]
Loading 0:  51%|█████     | 148/291 [00:03<00:02, 59.51it/s]
Loading 0:  54%|█████▍    | 157/291 [00:03<00:02, 65.41it/s]
Loading 0:  57%|█████▋    | 167/291 [00:03<00:01, 73.47it/s]
Loading 0:  60%|██████    | 176/291 [00:03<00:01, 76.19it/s]
Loading 0:  64%|██████▎   | 185/291 [00:03<00:01, 78.56it/s]
Loading 0:  67%|██████▋   | 194/291 [00:04<00:04, 20.91it/s]
Loading 0:  69%|██████▉   | 202/291 [00:04<00:03, 25.91it/s]
Loading 0:  73%|███████▎  | 211/291 [00:04<00:02, 32.09it/s]
Loading 0:  76%|███████▌  | 220/291 [00:04<00:01, 39.79it/s]
Loading 0:  79%|███████▊  | 229/291 [00:05<00:01, 45.59it/s]
Loading 0:  82%|████████▏ | 238/291 [00:05<00:01, 50.36it/s]
Loading 0:  85%|████████▍ | 247/291 [00:05<00:00, 56.48it/s]
Loading 0:  89%|████████▉ | 259/291 [00:05<00:00, 63.09it/s]
Loading 0:  92%|█████████▏| 268/291 [00:05<00:00, 68.15it/s]
Loading 0:  95%|█████████▌| 277/291 [00:05<00:00, 71.06it/s]
Loading 0:  98%|█████████▊| 286/291 [00:05<00:00, 72.61it/s]
                                                            
Job riverise-model-on-sonnet-v3-mkmlizer completed after 73.77s with status: succeeded
Stopping job with name riverise-model-on-sonnet-v3-mkmlizer
Pipeline stage MKMLizer completed in 74.58s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.27s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service riverise-model-on-sonnet-v3
Waiting for inference service riverise-model-on-sonnet-v3 to be ready
Inference service riverise-model-on-sonnet-v3 ready after 191.00302004814148s
Pipeline stage MKMLDeployer completed in 191.38s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.8226003646850586s
Received healthy response to inference request in 1.9313478469848633s
Received healthy response to inference request in 1.5323822498321533s
Received healthy response to inference request in 1.380072832107544s
Received healthy response to inference request in 1.7677807807922363s
5 requests
0 failed requests
5th percentile: 1.410534715652466
10th percentile: 1.4409965991973877
20th percentile: 1.5019203662872314
30th percentile: 1.5794619560241698
40th percentile: 1.673621368408203
50th percentile: 1.7677807807922363
60th percentile: 1.833207607269287
70th percentile: 1.898634433746338
80th percentile: 2.1095983505249025
90th percentile: 2.4660993576049806
95th percentile: 2.6443498611450194
99th percentile: 2.786950263977051
mean time: 1.8868368148803711
Pipeline stage StressChecker completed in 10.12s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
starting trigger_guanaco_pipeline %s
Pipeline stage TriggerMKMLProfilingPipeline completed in 4.23s
riverise-model-on-sonnet_v3 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-on-sonnet-v3-profiler
Waiting for inference service riverise-model-on-sonnet-v3-profiler to be ready
Inference service riverise-model-on-sonnet-v3-profiler ready after 200.45347666740417s
Pipeline stage MKMLProfilerDeployer completed in 200.83s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
script pods %s
Pipeline stage MKMLProfilerRunner completed in 0.37s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service riverise-model-on-sonnet-v3-profiler is running
Tearing down inference service riverise-model-on-sonnet-v3-profiler
Service riverise-model-on-sonnet-v3-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.80s
riverise-model-on-sonnet_v3 status is now inactive due to auto deactivation removed underperforming models
riverise-model-on-sonnet_v3 status is now torndown due to DeploymentManager action