submission_id: rinen0721-llama8b-0820_v1
developer_uid: rinen0721
alignment_samples: 11340
alignment_score: -0.05850776001573347
best_of: 16
celo_rating: 1216.75
display_name: rinen0721-llama8b-0820_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/llama8b-0820
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: rinen0721/llama8b-0820
model_name: rinen0721-llama8b-0820_v1
model_num_parameters: 8030261248.0
model_repo: rinen0721/llama8b-0820
model_size: 8B
num_battles: 11340
num_wins: 5462
propriety_score: 0.7353815659068385
propriety_total_count: 1009.0
ranking_group: single
status: torndown
submission_type: basic
timestamp: 2024-08-20T16:59:23+00:00
us_pacific_date: 2024-08-20
win_ratio: 0.48165784832451497
Download Preference Data
Resubmit model
Running pipeline stage MKMLizer
Starting job with name rinen0721-llama8b-0820-v1-mkmlizer
Waiting for job on rinen0721-llama8b-0820-v1-mkmlizer to finish
rinen0721-llama8b-0820-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rinen0721-llama8b-0820-v1-mkmlizer: ║     _____            __           __                                ║
rinen0721-llama8b-0820-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rinen0721-llama8b-0820-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rinen0721-llama8b-0820-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rinen0721-llama8b-0820-v1-mkmlizer: ║       /___/                                                         ║
rinen0721-llama8b-0820-v1-mkmlizer: ║                                                                     ║
rinen0721-llama8b-0820-v1-mkmlizer: ║  Version: 0.9.11                                                    ║
rinen0721-llama8b-0820-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rinen0721-llama8b-0820-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rinen0721-llama8b-0820-v1-mkmlizer: ║                                                                     ║
rinen0721-llama8b-0820-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rinen0721-llama8b-0820-v1-mkmlizer: ║  belonging to:                                                      ║
rinen0721-llama8b-0820-v1-mkmlizer: ║                                                                     ║
rinen0721-llama8b-0820-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rinen0721-llama8b-0820-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rinen0721-llama8b-0820-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
rinen0721-llama8b-0820-v1-mkmlizer: ║                                                                     ║
rinen0721-llama8b-0820-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rinen0721-llama8b-0820-v1-mkmlizer: Downloaded to shared memory in 39.851s
rinen0721-llama8b-0820-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp61j2ju0f, device:0
rinen0721-llama8b-0820-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rinen0721-llama8b-0820-v1-mkmlizer: quantized model in 27.458s
rinen0721-llama8b-0820-v1-mkmlizer: Processed model rinen0721/llama8b-0820 in 67.309s
rinen0721-llama8b-0820-v1-mkmlizer: creating bucket guanaco-mkml-models
rinen0721-llama8b-0820-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rinen0721-llama8b-0820-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rinen0721-llama8b-0820-v1
rinen0721-llama8b-0820-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rinen0721-llama8b-0820-v1/config.json
rinen0721-llama8b-0820-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rinen0721-llama8b-0820-v1/special_tokens_map.json
rinen0721-llama8b-0820-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rinen0721-llama8b-0820-v1/tokenizer_config.json
rinen0721-llama8b-0820-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rinen0721-llama8b-0820-v1/tokenizer.json
rinen0721-llama8b-0820-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rinen0721-llama8b-0820-v1/flywheel_model.0.safetensors
rinen0721-llama8b-0820-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 4/291 [00:00<00:07, 38.57it/s]
Loading 0:   4%|▍         | 13/291 [00:00<00:05, 52.88it/s]
Loading 0:   8%|▊         | 22/291 [00:00<00:04, 55.12it/s]
Loading 0:  11%|█         | 31/291 [00:00<00:04, 55.43it/s]
Loading 0:  14%|█▎        | 40/291 [00:00<00:04, 57.16it/s]
Loading 0:  17%|█▋        | 49/291 [00:00<00:04, 58.52it/s]
Loading 0:  20%|█▉        | 58/291 [00:01<00:03, 58.86it/s]
Loading 0:  23%|██▎       | 67/291 [00:01<00:03, 57.15it/s]
Loading 0:  26%|██▌       | 76/291 [00:01<00:03, 58.11it/s]
Loading 0:  29%|██▊       | 83/291 [00:02<00:12, 16.92it/s]
Loading 0:  30%|███       | 88/291 [00:02<00:10, 19.14it/s]
Loading 0:  33%|███▎      | 97/291 [00:02<00:07, 25.95it/s]
Loading 0:  36%|███▋      | 106/291 [00:02<00:05, 33.13it/s]
Loading 0:  40%|███▉      | 115/291 [00:03<00:04, 39.95it/s]
Loading 0:  43%|████▎     | 124/291 [00:03<00:03, 46.84it/s]
Loading 0:  46%|████▌     | 133/291 [00:03<00:02, 53.02it/s]
Loading 0:  49%|████▉     | 142/291 [00:03<00:02, 57.84it/s]
Loading 0:  52%|█████▏    | 151/291 [00:03<00:02, 55.56it/s]
Loading 0:  55%|█████▍    | 160/291 [00:03<00:02, 58.46it/s]
Loading 0:  58%|█████▊    | 169/291 [00:03<00:01, 61.92it/s]
Loading 0:  61%|██████    | 178/291 [00:04<00:01, 63.54it/s]
Loading 0:  64%|██████▍   | 187/291 [00:05<00:05, 19.13it/s]
Loading 0:  67%|██████▋   | 196/291 [00:05<00:03, 24.49it/s]
Loading 0:  70%|███████   | 205/291 [00:05<00:02, 30.48it/s]
Loading 0:  74%|███████▎  | 214/291 [00:05<00:02, 36.81it/s]
Loading 0:  77%|███████▋  | 223/291 [00:05<00:01, 42.23it/s]
Loading 0:  80%|███████▉  | 232/291 [00:05<00:01, 48.57it/s]
Loading 0:  83%|████████▎ | 241/291 [00:06<00:00, 52.12it/s]
Loading 0:  86%|████████▌ | 250/291 [00:06<00:00, 55.04it/s]
Loading 0:  89%|████████▉ | 259/291 [00:06<00:00, 59.06it/s]
Loading 0:  92%|█████████▏| 268/291 [00:06<00:00, 62.95it/s]
Loading 0:  95%|█████████▌| 277/291 [00:06<00:00, 65.11it/s]
Loading 0:  98%|█████████▊| 286/291 [00:06<00:00, 66.18it/s]
                                                            

Job rinen0721-llama8b-0820-v1-mkmlizer completed after 94.01s with status: succeeded
Stopping job with name rinen0721-llama8b-0820-v1-mkmlizer
Pipeline stage MKMLizer completed in 95.26s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service rinen0721-llama8b-0820-v1
Waiting for inference service rinen0721-llama8b-0820-v1 to be ready
Failed to get response for submission blend_popob_2024-08-16: ('http://neversleep-noromaid-v0-8068-v142-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:35204->127.0.0.1:8080: read: connection reset by peer\n')
Inference service rinen0721-llama8b-0820-v1 ready after 242.12742400169373s
Pipeline stage ISVCDeployer completed in 243.05s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0400867462158203s
Received healthy response to inference request in 1.5152904987335205s
Received healthy response to inference request in 1.6317551136016846s
Received healthy response to inference request in 1.8884899616241455s
Received healthy response to inference request in 1.3891117572784424s
5 requests
0 failed requests
5th percentile: 1.414347505569458
10th percentile: 1.4395832538604736
20th percentile: 1.4900547504425048
30th percentile: 1.5385834217071532
40th percentile: 1.585169267654419
50th percentile: 1.6317551136016846
60th percentile: 1.7344490528106689
70th percentile: 1.8371429920196534
80th percentile: 1.9188093185424806
90th percentile: 1.9794480323791503
95th percentile: 2.0097673892974854
99th percentile: 2.034022874832153
mean time: 1.6929468154907226
Pipeline stage StressChecker completed in 9.20s
rinen0721-llama8b-0820_v1 status is now deployed due to DeploymentManager action
rinen0721-llama8b-0820_v1 status is now inactive due to auto deactivation removed underperforming models
rinen0721-llama8b-0820_v1 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics