submission_id: rinen0721-llama0901-e2_v1
developer_uid: rinen0721
alignment_samples: 11625
alignment_score: -0.4249559003172333
best_of: 16
celo_rating: 1213.35
display_name: rinen0721-llama0901-e2_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: rinen0721/llama0901-e2
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: rinen0721/llama0901-e2
model_name: rinen0721-llama0901-e2_v1
model_num_parameters: 8030261248.0
model_repo: rinen0721/llama0901-e2
model_size: 8B
num_battles: 11625
num_wins: 5437
propriety_score: 0.7445109780439122
propriety_total_count: 1002.0
ranking_group: single
status: inactive
submission_type: basic
timestamp: 2024-09-01T09:40:05+00:00
us_pacific_date: 2024-09-01
win_ratio: 0.4676989247311828
Download Preference Data
Resubmit model
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLizer
Starting job with name rinen0721-llama0901-e2-v1-mkmlizer
Waiting for job on rinen0721-llama0901-e2-v1-mkmlizer to finish
rinen0721-llama0901-e2-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rinen0721-llama0901-e2-v1-mkmlizer: ║     _____            __           __                                ║
rinen0721-llama0901-e2-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rinen0721-llama0901-e2-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rinen0721-llama0901-e2-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rinen0721-llama0901-e2-v1-mkmlizer: ║       /___/                                                         ║
rinen0721-llama0901-e2-v1-mkmlizer: ║                                                                     ║
rinen0721-llama0901-e2-v1-mkmlizer: ║  Version: 0.10.1                                                    ║
rinen0721-llama0901-e2-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rinen0721-llama0901-e2-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rinen0721-llama0901-e2-v1-mkmlizer: ║                                                                     ║
rinen0721-llama0901-e2-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rinen0721-llama0901-e2-v1-mkmlizer: ║  belonging to:                                                      ║
rinen0721-llama0901-e2-v1-mkmlizer: ║                                                                     ║
rinen0721-llama0901-e2-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rinen0721-llama0901-e2-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rinen0721-llama0901-e2-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
rinen0721-llama0901-e2-v1-mkmlizer: ║                                                                     ║
rinen0721-llama0901-e2-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rinen0721-llama0901-e2-v1-mkmlizer: Downloaded to shared memory in 32.727s
rinen0721-llama0901-e2-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpzden114b, device:0
rinen0721-llama0901-e2-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rinen0721-llama0901-e2-v1-mkmlizer: quantized model in 25.769s
rinen0721-llama0901-e2-v1-mkmlizer: Processed model rinen0721/llama0901-e2 in 58.496s
rinen0721-llama0901-e2-v1-mkmlizer: creating bucket guanaco-mkml-models
rinen0721-llama0901-e2-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rinen0721-llama0901-e2-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rinen0721-llama0901-e2-v1
rinen0721-llama0901-e2-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rinen0721-llama0901-e2-v1/config.json
rinen0721-llama0901-e2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rinen0721-llama0901-e2-v1/tokenizer_config.json
rinen0721-llama0901-e2-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rinen0721-llama0901-e2-v1/special_tokens_map.json
rinen0721-llama0901-e2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rinen0721-llama0901-e2-v1/tokenizer.json
rinen0721-llama0901-e2-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rinen0721-llama0901-e2-v1/flywheel_model.0.safetensors
rinen0721-llama0901-e2-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 7/291 [00:00<00:05, 56.04it/s]
Loading 0:   6%|▌         | 17/291 [00:00<00:03, 79.40it/s]
Loading 0:  11%|█         | 31/291 [00:00<00:02, 90.11it/s]
Loading 0:  14%|█▍        | 41/291 [00:00<00:02, 87.36it/s]
Loading 0:  17%|█▋        | 50/291 [00:00<00:03, 79.00it/s]
Loading 0:  20%|█▉        | 58/291 [00:00<00:02, 78.81it/s]
Loading 0:  23%|██▎       | 67/291 [00:00<00:02, 81.37it/s]
Loading 0:  26%|██▌       | 76/291 [00:00<00:03, 69.80it/s]
Loading 0:  29%|██▉       | 84/291 [00:02<00:10, 19.50it/s]
Loading 0:  31%|███       | 90/291 [00:02<00:08, 22.71it/s]
Loading 0:  35%|███▌      | 103/291 [00:02<00:05, 33.02it/s]
Loading 0:  38%|███▊      | 112/291 [00:02<00:04, 40.40it/s]
Loading 0:  42%|████▏     | 121/291 [00:02<00:03, 46.68it/s]
Loading 0:  45%|████▍     | 130/291 [00:02<00:02, 53.97it/s]
Loading 0:  48%|████▊     | 139/291 [00:02<00:02, 60.95it/s]
Loading 0:  51%|█████     | 148/291 [00:02<00:02, 64.31it/s]
Loading 0:  54%|█████▍    | 157/291 [00:03<00:01, 68.09it/s]
Loading 0:  57%|█████▋    | 166/291 [00:03<00:01, 68.47it/s]
Loading 0:  60%|██████    | 175/291 [00:03<00:01, 70.91it/s]
Loading 0:  64%|██████▍   | 187/291 [00:04<00:04, 23.24it/s]
Loading 0:  67%|██████▋   | 196/291 [00:04<00:03, 28.81it/s]
Loading 0:  70%|███████   | 205/291 [00:04<00:02, 35.24it/s]
Loading 0:  74%|███████▍  | 215/291 [00:04<00:01, 44.13it/s]
Loading 0:  77%|███████▋  | 223/291 [00:04<00:01, 48.80it/s]
Loading 0:  80%|███████▉  | 232/291 [00:05<00:01, 54.16it/s]
Loading 0:  83%|████████▎ | 241/291 [00:05<00:00, 59.05it/s]
Loading 0:  86%|████████▌ | 250/291 [00:05<00:00, 63.67it/s]
Loading 0:  89%|████████▉ | 259/291 [00:05<00:00, 68.12it/s]
Loading 0:  92%|█████████▏| 268/291 [00:05<00:00, 70.08it/s]
Loading 0:  95%|█████████▌| 277/291 [00:05<00:00, 71.19it/s]
Loading 0:  98%|█████████▊| 286/291 [00:05<00:00, 75.35it/s]
                                                            

Job rinen0721-llama0901-e2-v1-mkmlizer completed after 74.96s with status: succeeded
Stopping job with name rinen0721-llama0901-e2-v1-mkmlizer
Pipeline stage MKMLizer completed in 75.96s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rinen0721-llama0901-e2-v1
Waiting for inference service rinen0721-llama0901-e2-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
Inference service rinen0721-llama0901-e2-v1 ready after 191.1995086669922s
Pipeline stage MKMLDeployer completed in 191.80s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.045769214630127s
Received healthy response to inference request in 1.992175579071045s
Received healthy response to inference request in 1.6951406002044678s
Received healthy response to inference request in 2.476548194885254s
Received healthy response to inference request in 1.9749886989593506s
5 requests
0 failed requests
5th percentile: 1.7511102199554442
10th percentile: 1.807079839706421
20th percentile: 1.9190190792083741
30th percentile: 1.9784260749816895
40th percentile: 1.9853008270263672
50th percentile: 1.992175579071045
60th percentile: 2.0136130332946776
70th percentile: 2.0350504875183106
80th percentile: 2.1319250106811523
90th percentile: 2.3042366027832033
95th percentile: 2.3903923988342286
99th percentile: 2.4593170356750487
mean time: 2.036924457550049
Pipeline stage StressChecker completed in 11.21s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
starting trigger_guanaco_pipeline %s
Pipeline stage TriggerMKMLProfilingPipeline completed in 5.86s
rinen0721-llama0901-e2_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 0.15s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rinen0721-llama0901-e2-v1-profiler
Waiting for inference service rinen0721-llama0901-e2-v1-profiler to be ready
Inference service rinen0721-llama0901-e2-v1-profiler ready after 190.4224829673767s
Pipeline stage MKMLProfilerDeployer completed in 190.78s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
script pods %s
Pipeline stage MKMLProfilerRunner completed in 0.33s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service rinen0721-llama0901-e2-v1-profiler is running
Tearing down inference service rinen0721-llama0901-e2-v1-profiler
Service rinen0721-llama0901-e2-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.82s
rinen0721-llama0901-e2_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics