developer_uid: chace9580
submission_id: jic062-instruct-v18-4-5w_v1
model_name: jic062-instruct-v18-4-5w_v1
model_group: jic062/instruct_v18_4.5w
status: torndown
timestamp: 2024-08-18T23:22:26+00:00
num_battles: 13279
num_wins: 7119
celo_rating: 1253.54
family_friendly_score: 0.0
submission_type: basic
model_repo: jic062/instruct_v18_4.5w
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: jic062-instruct-v18-4-5w_v1
is_internal_developer: False
language_model: jic062/instruct_v18_4.5w
model_size: 8B
ranking_group: single
us_pacific_date: 2024-08-18
win_ratio: 0.5361096468107538
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', '<|end_of_text|>', '|eot_id|'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
formatter: {'memory_template': "<|begin_of_text|><|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\n{user_name}: {message}<|eot_id|>', 'response_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}:', 'truncate_by_message': False}
Resubmit model
Running pipeline stage MKMLizer
Starting job with name jic062-instruct-v18-4-5w-v1-mkmlizer
Waiting for job on jic062-instruct-v18-4-5w-v1-mkmlizer to finish
Stopping job with name jic062-instruct-v18-4-5w-v1-mkmlizer
%s, retrying in %s seconds...
Starting job with name jic062-instruct-v18-4-5w-v1-mkmlizer
Waiting for job on jic062-instruct-v18-4-5w-v1-mkmlizer to finish
Failed to get response for submission blend_padil_2024-08-16: ('http://mistralai-mixtral-8x7b-3473-v106-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '{"error":"ValueError : [TypeError(\\"\'numpy.int64\' object is not iterable\\"), TypeError(\'vars() argument must have __dict__ attribute\')]"}')
jic062-instruct-v18-4-5w-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
jic062-instruct-v18-4-5w-v1-mkmlizer: ║ _____ __ __ ║
jic062-instruct-v18-4-5w-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
jic062-instruct-v18-4-5w-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
jic062-instruct-v18-4-5w-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
jic062-instruct-v18-4-5w-v1-mkmlizer: ║ /___/ ║
jic062-instruct-v18-4-5w-v1-mkmlizer: ║ ║
jic062-instruct-v18-4-5w-v1-mkmlizer: ║ Version: 0.9.11 ║
jic062-instruct-v18-4-5w-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
jic062-instruct-v18-4-5w-v1-mkmlizer: ║ https://mk1.ai ║
jic062-instruct-v18-4-5w-v1-mkmlizer: ║ ║
jic062-instruct-v18-4-5w-v1-mkmlizer: ║ The license key for the current software has been verified as ║
jic062-instruct-v18-4-5w-v1-mkmlizer: ║ belonging to: ║
jic062-instruct-v18-4-5w-v1-mkmlizer: ║ ║
jic062-instruct-v18-4-5w-v1-mkmlizer: ║ Chai Research Corp. ║
jic062-instruct-v18-4-5w-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
jic062-instruct-v18-4-5w-v1-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
jic062-instruct-v18-4-5w-v1-mkmlizer: ║ ║
jic062-instruct-v18-4-5w-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
jic062-instruct-v18-4-5w-v1-mkmlizer: Downloaded to shared memory in 41.569s
jic062-instruct-v18-4-5w-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpasiq_7hi, device:0
jic062-instruct-v18-4-5w-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
jic062-instruct-v18-4-5w-v1-mkmlizer: quantized model in 26.585s
jic062-instruct-v18-4-5w-v1-mkmlizer: Processed model jic062/instruct_v18_4.5w in 68.154s
jic062-instruct-v18-4-5w-v1-mkmlizer: creating bucket guanaco-mkml-models
jic062-instruct-v18-4-5w-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
jic062-instruct-v18-4-5w-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/jic062-instruct-v18-4-5w-v1
jic062-instruct-v18-4-5w-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/jic062-instruct-v18-4-5w-v1/config.json
jic062-instruct-v18-4-5w-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/jic062-instruct-v18-4-5w-v1/special_tokens_map.json
jic062-instruct-v18-4-5w-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/jic062-instruct-v18-4-5w-v1/tokenizer_config.json
jic062-instruct-v18-4-5w-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/jic062-instruct-v18-4-5w-v1/tokenizer.json
jic062-instruct-v18-4-5w-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/jic062-instruct-v18-4-5w-v1/flywheel_model.0.safetensors
jic062-instruct-v18-4-5w-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 2%|▏ | 7/291 [00:00<00:06, 47.08it/s] Loading 0: 5%|▌ | 16/291 [00:00<00:04, 66.07it/s] Loading 0: 9%|▊ | 25/291 [00:00<00:03, 73.56it/s] Loading 0: 12%|█▏ | 34/291 [00:00<00:03, 74.04it/s] Loading 0: 15%|█▍ | 43/291 [00:00<00:03, 73.96it/s] Loading 0: 18%|█▊ | 52/291 [00:00<00:03, 76.51it/s] Loading 0: 21%|██ | 61/291 [00:00<00:03, 75.83it/s] Loading 0: 24%|██▍ | 70/291 [00:00<00:03, 72.04it/s] Loading 0: 27%|██▋ | 79/291 [00:01<00:02, 74.31it/s] Loading 0: 30%|██▉ | 87/291 [00:02<00:10, 19.37it/s] Loading 0: 32%|███▏ | 94/291 [00:02<00:08, 23.42it/s] Loading 0: 35%|███▌ | 103/291 [00:02<00:06, 30.41it/s] Loading 0: 38%|███▊ | 112/291 [00:02<00:04, 38.41it/s] Loading 0: 42%|████▏ | 121/291 [00:02<00:03, 45.35it/s] Loading 0: 45%|████▍ | 130/291 [00:02<00:03, 50.44it/s] Loading 0: 48%|████▊ | 139/291 [00:02<00:02, 57.80it/s] Loading 0: 51%|█████ | 148/291 [00:03<00:02, 64.14it/s] Loading 0: 54%|█████▍ | 157/291 [00:03<00:01, 69.09it/s] Loading 0: 57%|█████▋ | 166/291 [00:03<00:01, 73.62it/s] Loading 0: 60%|██████ | 175/291 [00:03<00:01, 77.33it/s] Loading 0: 63%|██████▎ | 184/291 [00:03<00:01, 80.58it/s] Loading 0: 66%|██████▋ | 193/291 [00:04<00:04, 20.84it/s] Loading 0: 69%|██████▉ | 202/291 [00:04<00:03, 26.85it/s] Loading 0: 73%|███████▎ | 211/291 [00:04<00:02, 33.83it/s] Loading 0: 76%|███████▌ | 220/291 [00:04<00:01, 40.90it/s] Loading 0: 79%|███████▊ | 229/291 [00:05<00:01, 47.85it/s] Loading 0: 82%|████████▏ | 238/291 [00:05<00:00, 54.74it/s] Loading 0: 85%|████████▍ | 247/291 [00:05<00:00, 60.89it/s] Loading 0: 88%|████████▊ | 256/291 [00:05<00:00, 63.29it/s] Loading 0: 91%|█████████ | 265/291 [00:05<00:00, 66.48it/s] Loading 0: 94%|█████████▍| 274/291 [00:05<00:00, 71.21it/s] Loading 0: 97%|█████████▋| 283/291 [00:05<00:00, 74.88it/s]
Job jic062-instruct-v18-4-5w-v1-mkmlizer completed after 85.4s with status: succeeded
Stopping job with name jic062-instruct-v18-4-5w-v1-mkmlizer
Pipeline stage MKMLizer completed in 86.92s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.08s
Running pipeline stage ISVCDeployer
Creating inference service jic062-instruct-v18-4-5w-v1
Waiting for inference service jic062-instruct-v18-4-5w-v1 to be ready
Failed to get response for submission blend_berib_2024-08-16: ('http://chaiml-llama-8b-pairwis-8189-v17-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:41716->127.0.0.1:8080: read: connection reset by peer\n')
Inference service jic062-instruct-v18-4-5w-v1 ready after 573.6536705493927s
Pipeline stage ISVCDeployer completed in 574.41s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2815935611724854s
Received healthy response to inference request in 1.5852291584014893s
Received healthy response to inference request in 1.6394891738891602s
Received healthy response to inference request in 1.6211600303649902s
Received healthy response to inference request in 1.6770071983337402s
5 requests
0 failed requests
5th percentile: 1.5924153327941895
10th percentile: 1.5996015071868896
20th percentile: 1.61397385597229
30th percentile: 1.6248258590698241
40th percentile: 1.6321575164794921
50th percentile: 1.6394891738891602
60th percentile: 1.6544963836669921
70th percentile: 1.6695035934448241
80th percentile: 1.7979244709014894
90th percentile: 2.0397590160369874
95th percentile: 2.160676288604736
99th percentile: 2.2574101066589356
mean time: 1.7608958244323731
Pipeline stage StressChecker completed in 9.50s
jic062-instruct-v18-4-5w_v1 status is now deployed due to DeploymentManager action
jic062-instruct-v18-4-5w_v1 status is now inactive due to auto deactivation removed underperforming models
jic062-instruct-v18-4-5w_v1 status is now torndown due to DeploymentManager action