developer_uid: rica40325
submission_id: rica40325-lora32-secend_v2
model_name: rica40325-lora32-secend_v1
model_group: rica40325/lora32_secend
status: torndown
timestamp: 2024-08-30T10:22:06+00:00
num_battles: 11723
num_wins: 6199
celo_rating: 1255.23
family_friendly_score: 0.0
submission_type: basic
model_repo: rica40325/lora32_secend
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: rica40325-lora32-secend_v1
is_internal_developer: False
language_model: rica40325/lora32_secend
model_size: 8B
ranking_group: single
us_pacific_date: 2024-08-30
win_ratio: 0.5287895589866075
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}
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
Running pipeline stage MKMLizer
Starting job with name rica40325-lora32-secend-v2-mkmlizer
Waiting for job on rica40325-lora32-secend-v2-mkmlizer to finish
rica40325-lora32-secend-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rica40325-lora32-secend-v2-mkmlizer: ║ _____ __ __ ║
rica40325-lora32-secend-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
rica40325-lora32-secend-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
rica40325-lora32-secend-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
rica40325-lora32-secend-v2-mkmlizer: ║ /___/ ║
rica40325-lora32-secend-v2-mkmlizer: ║ ║
rica40325-lora32-secend-v2-mkmlizer: ║ Version: 0.10.1 ║
rica40325-lora32-secend-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
rica40325-lora32-secend-v2-mkmlizer: ║ https://mk1.ai ║
rica40325-lora32-secend-v2-mkmlizer: ║ ║
rica40325-lora32-secend-v2-mkmlizer: ║ The license key for the current software has been verified as ║
rica40325-lora32-secend-v2-mkmlizer: ║ belonging to: ║
rica40325-lora32-secend-v2-mkmlizer: ║ ║
rica40325-lora32-secend-v2-mkmlizer: ║ Chai Research Corp. ║
rica40325-lora32-secend-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
rica40325-lora32-secend-v2-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
rica40325-lora32-secend-v2-mkmlizer: ║ ║
rica40325-lora32-secend-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rica40325-lora32-secend-v2-mkmlizer: Downloaded to shared memory in 21.392s
rica40325-lora32-secend-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp3r7_bjwa, device:0
rica40325-lora32-secend-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rica40325-lora32-secend-v2-mkmlizer: quantized model in 26.060s
rica40325-lora32-secend-v2-mkmlizer: Processed model rica40325/lora32_secend in 47.452s
rica40325-lora32-secend-v2-mkmlizer: creating bucket guanaco-mkml-models
rica40325-lora32-secend-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rica40325-lora32-secend-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rica40325-lora32-secend-v2
rica40325-lora32-secend-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rica40325-lora32-secend-v2/config.json
rica40325-lora32-secend-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rica40325-lora32-secend-v2/special_tokens_map.json
rica40325-lora32-secend-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rica40325-lora32-secend-v2/tokenizer_config.json
rica40325-lora32-secend-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rica40325-lora32-secend-v2/tokenizer.json
rica40325-lora32-secend-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rica40325-lora32-secend-v2/flywheel_model.0.safetensors
rica40325-lora32-secend-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%|▏ | 4/291 [00:00<00:08, 35.73it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:04, 60.22it/s] Loading 0: 8%|▊ | 22/291 [00:00<00:04, 65.56it/s] Loading 0: 11%|█ | 31/291 [00:00<00:03, 69.01it/s] Loading 0: 14%|█▎ | 40/291 [00:00<00:03, 75.35it/s] Loading 0: 17%|█▋ | 49/291 [00:00<00:03, 78.13it/s] Loading 0: 21%|██ | 60/291 [00:00<00:02, 87.62it/s] Loading 0: 24%|██▎ | 69/291 [00:00<00:02, 88.24it/s] Loading 0: 27%|██▋ | 79/291 [00:01<00:02, 82.12it/s] Loading 0: 30%|███ | 88/291 [00:02<00:09, 21.29it/s] Loading 0: 35%|███▌ | 103/291 [00:02<00:05, 31.51it/s] Loading 0: 38%|███▊ | 112/291 [00:02<00:04, 37.91it/s] Loading 0: 43%|████▎ | 124/291 [00:02<00:03, 46.59it/s] Loading 0: 48%|████▊ | 139/291 [00:02<00:02, 58.73it/s] Loading 0: 52%|█████▏ | 151/291 [00:02<00:02, 64.35it/s] Loading 0: 55%|█████▍ | 160/291 [00:02<00:01, 68.72it/s] Loading 0: 58%|█████▊ | 169/291 [00:03<00:01, 71.87it/s] Loading 0: 61%|██████ | 178/291 [00:03<00:01, 75.94it/s] Loading 0: 64%|██████▍ | 187/291 [00:04<00:04, 22.35it/s] Loading 0: 69%|██████▉ | 202/291 [00:04<00:02, 32.55it/s] Loading 0: 74%|███████▎ | 214/291 [00:04<00:01, 38.52it/s] Loading 0: 77%|███████▋ | 223/291 [00:04<00:01, 43.55it/s] Loading 0: 80%|███████▉ | 232/291 [00:04<00:01, 49.82it/s] Loading 0: 85%|████████▍ | 246/291 [00:04<00:00, 65.38it/s] Loading 0: 88%|████████▊ | 256/291 [00:05<00:00, 67.10it/s] Loading 0: 91%|█████████ | 265/291 [00:05<00:00, 71.43it/s] Loading 0: 95%|█████████▌| 277/291 [00:05<00:00, 75.24it/s] Loading 0: 99%|█████████▊| 287/291 [00:05<00:00, 45.83it/s]
Job rica40325-lora32-secend-v2-mkmlizer completed after 63.92s with status: succeeded
Stopping job with name rica40325-lora32-secend-v2-mkmlizer
Pipeline stage MKMLizer completed in 64.88s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service rica40325-lora32-secend-v2
Waiting for inference service rica40325-lora32-secend-v2 to be ready
Failed to get response for submission blend_berib_2024-08-16: ('http://zonemercy-lexical-nemo-1518-v18-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:49754->127.0.0.1:8080: read: connection reset by peer\n')
Inference service rica40325-lora32-secend-v2 ready after 170.9893491268158s
Pipeline stage ISVCDeployer completed in 171.66s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2101895809173584s
Received healthy response to inference request in 1.3322656154632568s
Received healthy response to inference request in 1.3432810306549072s
Received healthy response to inference request in 2.1317219734191895s
Received healthy response to inference request in 1.554849624633789s
5 requests
0 failed requests
5th percentile: 1.334468698501587
10th percentile: 1.336671781539917
20th percentile: 1.341077947616577
30th percentile: 1.3855947494506835
40th percentile: 1.4702221870422363
50th percentile: 1.554849624633789
60th percentile: 1.7855985641479493
70th percentile: 2.0163475036621095
80th percentile: 2.1474154949188233
90th percentile: 2.1788025379180906
95th percentile: 2.1944960594177245
99th percentile: 2.2070508766174317
mean time: 1.7144615650177002
Pipeline stage StressChecker completed in 9.67s
rica40325-lora32-secend_v2 status is now deployed due to DeploymentManager action
rica40325-lora32-secend_v2 status is now inactive due to auto deactivation removed underperforming models
rica40325-lora32-secend_v2 status is now torndown due to DeploymentManager action