developer_uid: Trace2333
submission_id: trace2333-ultra1w-dol1w-_2607_v8
model_name: trace2333-ultra1w-dol1w-_2607_v8
model_group: Trace2333/ultra1w_dol1w_
status: torndown
timestamp: 2024-08-24T09:46:09+00:00
num_battles: 10284
num_wins: 5218
celo_rating: 1241.18
family_friendly_score: 0.0
submission_type: basic
model_repo: Trace2333/ultra1w_dol1w_fd2w_r32a16_qkvo_epoch6_v1
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: trace2333-ultra1w-dol1w-_2607_v8
is_internal_developer: False
language_model: Trace2333/ultra1w_dol1w_fd2w_r32a16_qkvo_epoch6_v1
model_size: 8B
ranking_group: single
us_pacific_date: 2024-08-24
win_ratio: 0.5073901205756515
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|eot_id|>'], '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 trace2333-ultra1w-dol1w-2607-v8-mkmlizer
Waiting for job on trace2333-ultra1w-dol1w-2607-v8-mkmlizer to finish
trace2333-ultra1w-dol1w-2607-v8-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
trace2333-ultra1w-dol1w-2607-v8-mkmlizer: ║ _____ __ __ ║
trace2333-ultra1w-dol1w-2607-v8-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
trace2333-ultra1w-dol1w-2607-v8-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
trace2333-ultra1w-dol1w-2607-v8-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
trace2333-ultra1w-dol1w-2607-v8-mkmlizer: ║ /___/ ║
trace2333-ultra1w-dol1w-2607-v8-mkmlizer: ║ ║
trace2333-ultra1w-dol1w-2607-v8-mkmlizer: ║ Version: 0.10.1 ║
trace2333-ultra1w-dol1w-2607-v8-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
trace2333-ultra1w-dol1w-2607-v8-mkmlizer: ║ https://mk1.ai ║
trace2333-ultra1w-dol1w-2607-v8-mkmlizer: ║ ║
trace2333-ultra1w-dol1w-2607-v8-mkmlizer: ║ The license key for the current software has been verified as ║
trace2333-ultra1w-dol1w-2607-v8-mkmlizer: ║ belonging to: ║
trace2333-ultra1w-dol1w-2607-v8-mkmlizer: ║ ║
trace2333-ultra1w-dol1w-2607-v8-mkmlizer: ║ Chai Research Corp. ║
trace2333-ultra1w-dol1w-2607-v8-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
trace2333-ultra1w-dol1w-2607-v8-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
trace2333-ultra1w-dol1w-2607-v8-mkmlizer: ║ ║
trace2333-ultra1w-dol1w-2607-v8-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission mistralai-mistral-nemo-_9330_v57: ('http://mistralai-mistral-nemo-9330-v57-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'activator request timeout')
trace2333-ultra1w-dol1w-2607-v8-mkmlizer: Downloaded to shared memory in 60.402s
trace2333-ultra1w-dol1w-2607-v8-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp3przwdhu, device:0
trace2333-ultra1w-dol1w-2607-v8-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission mistralai-mistral-nemo-_9330_v57: ('http://mistralai-mistral-nemo-9330-v57-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'activator request timeout')
Failed to get response for submission mistralai-mistral-nemo-_9330_v59: ('http://mistralai-mistral-nemo-9330-v59-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
trace2333-ultra1w-dol1w-2607-v8-mkmlizer: quantized model in 28.432s
trace2333-ultra1w-dol1w-2607-v8-mkmlizer: Processed model Trace2333/ultra1w_dol1w_fd2w_r32a16_qkvo_epoch6_v1 in 88.835s
trace2333-ultra1w-dol1w-2607-v8-mkmlizer: creating bucket guanaco-mkml-models
trace2333-ultra1w-dol1w-2607-v8-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
trace2333-ultra1w-dol1w-2607-v8-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/trace2333-ultra1w-dol1w-2607-v8
trace2333-ultra1w-dol1w-2607-v8-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/trace2333-ultra1w-dol1w-2607-v8/config.json
trace2333-ultra1w-dol1w-2607-v8-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/trace2333-ultra1w-dol1w-2607-v8/special_tokens_map.json
trace2333-ultra1w-dol1w-2607-v8-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/trace2333-ultra1w-dol1w-2607-v8/tokenizer_config.json
trace2333-ultra1w-dol1w-2607-v8-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/trace2333-ultra1w-dol1w-2607-v8/tokenizer.json
trace2333-ultra1w-dol1w-2607-v8-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/trace2333-ultra1w-dol1w-2607-v8/flywheel_model.0.safetensors
trace2333-ultra1w-dol1w-2607-v8-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 2%|▏ | 5/291 [00:00<00:10, 26.11it/s] Loading 0: 4%|▍ | 12/291 [00:00<00:07, 35.23it/s] Loading 0: 5%|▌ | 16/291 [00:00<00:08, 32.49it/s] Loading 0: 7%|▋ | 21/291 [00:00<00:07, 36.05it/s] Loading 0: 9%|▊ | 25/291 [00:00<00:07, 34.31it/s] Loading 0: 10%|█ | 30/291 [00:00<00:06, 38.44it/s] Loading 0: 12%|█▏ | 34/291 [00:01<00:10, 24.98it/s] Loading 0: 13%|█▎ | 38/291 [00:01<00:09, 26.25it/s] Loading 0: 14%|█▍ | 42/291 [00:01<00:09, 25.55it/s] Loading 0: 16%|█▋ | 48/291 [00:01<00:07, 30.61it/s] Loading 0: 18%|█▊ | 52/291 [00:01<00:07, 31.08it/s] Loading 0: 20%|█▉ | 57/291 [00:01<00:06, 34.58it/s] Loading 0: 21%|██ | 61/291 [00:01<00:06, 33.98it/s] Loading 0: 23%|██▎ | 66/291 [00:02<00:06, 36.67it/s] Loading 0: 24%|██▍ | 70/291 [00:02<00:06, 34.20it/s] Loading 0: 25%|██▌ | 74/291 [00:02<00:06, 34.24it/s] Loading 0: 27%|██▋ | 78/291 [00:02<00:06, 34.70it/s] Loading 0: 28%|██▊ | 82/291 [00:02<00:08, 24.38it/s] Loading 0: 29%|██▉ | 85/291 [00:02<00:08, 25.23it/s] Loading 0: 31%|███ | 90/291 [00:02<00:06, 29.59it/s] Loading 0: 32%|███▏ | 94/291 [00:03<00:06, 30.21it/s] Loading 0: 34%|███▍ | 99/291 [00:03<00:05, 34.20it/s] Loading 0: 35%|███▌ | 103/291 [00:03<00:05, 33.92it/s] Loading 0: 37%|███▋ | 108/291 [00:03<00:04, 37.02it/s] Loading 0: 38%|███▊ | 112/291 [00:03<00:05, 34.44it/s] Loading 0: 40%|███▉ | 116/291 [00:03<00:05, 34.75it/s] Loading 0: 42%|████▏ | 122/291 [00:03<00:04, 39.54it/s] Loading 0: 44%|████▎ | 127/291 [00:03<00:04, 37.28it/s] Loading 0: 46%|████▌ | 133/291 [00:04<00:04, 32.30it/s] Loading 0: 47%|████▋ | 137/291 [00:04<00:04, 32.16it/s] Loading 0: 48%|████▊ | 141/291 [00:04<00:04, 30.18it/s] Loading 0: 51%|█████ | 147/291 [00:04<00:04, 35.08it/s] Loading 0: 52%|█████▏ | 151/291 [00:04<00:04, 33.90it/s] Loading 0: 54%|█████▎ | 156/291 [00:04<00:03, 36.81it/s] Loading 0: 55%|█████▍ | 160/291 [00:04<00:03, 35.58it/s] Loading 0: 57%|█████▋ | 165/291 [00:05<00:03, 38.25it/s] Loading 0: 58%|█████▊ | 169/291 [00:05<00:03, 36.43it/s] Loading 0: 60%|█████▉ | 174/291 [00:05<00:03, 38.05it/s] Loading 0: 61%|██████ | 178/291 [00:05<00:03, 34.91it/s] Loading 0: 63%|██████▎ | 184/291 [00:05<00:02, 40.68it/s] Loading 0: 65%|██████▍ | 189/291 [00:05<00:04, 25.31it/s] Loading 0: 67%|██████▋ | 194/291 [00:06<00:03, 26.99it/s] Loading 0: 69%|██████▉ | 201/291 [00:06<00:02, 33.63it/s] Loading 0: 71%|███████ | 206/291 [00:06<00:02, 34.66it/s] Loading 0: 72%|███████▏ | 210/291 [00:06<00:02, 35.79it/s] Loading 0: 74%|███████▎ | 214/291 [00:06<00:02, 34.83it/s] Loading 0: 75%|███████▌ | 219/291 [00:06<00:01, 37.19it/s] Loading 0: 77%|███████▋ | 223/291 [00:06<00:01, 35.35it/s] Loading 0: 78%|███████▊ | 227/291 [00:06<00:01, 35.06it/s] Loading 0: 79%|███████▉ | 231/291 [00:06<00:01, 34.93it/s] Loading 0: 81%|████████ | 235/291 [00:07<00:02, 25.53it/s] Loading 0: 82%|████████▏ | 239/291 [00:07<00:02, 25.83it/s] Loading 0: 85%|████████▍ | 246/291 [00:07<00:01, 33.74it/s] Loading 0: 86%|████████▌ | 250/291 [00:07<00:01, 33.57it/s] Loading 0: 88%|████████▊ | 255/291 [00:07<00:00, 36.63it/s] Loading 0: 89%|████████▉ | 259/291 [00:07<00:00, 35.54it/s] Loading 0: 91%|█████████ | 264/291 [00:07<00:00, 37.90it/s] Loading 0: 92%|█████████▏| 268/291 [00:08<00:00, 35.65it/s] Loading 0: 94%|█████████▍| 273/291 [00:08<00:00, 37.13it/s] Loading 0: 95%|█████████▌| 277/291 [00:08<00:00, 34.53it/s] Loading 0: 97%|█████████▋| 281/291 [00:08<00:00, 34.94it/s] Loading 0: 98%|█████████▊| 286/291 [00:13<00:01, 2.63it/s] Loading 0: 99%|█████████▉| 289/291 [00:14<00:00, 3.27it/s]
Job trace2333-ultra1w-dol1w-2607-v8-mkmlizer completed after 116.15s with status: succeeded
Stopping job with name trace2333-ultra1w-dol1w-2607-v8-mkmlizer
Pipeline stage MKMLizer completed in 117.34s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service trace2333-ultra1w-dol1w-2607-v8
Waiting for inference service trace2333-ultra1w-dol1w-2607-v8 to be ready
Failed to get response for submission mistralai-mistral-nemo-_9330_v59: ('http://mistralai-mistral-nemo-9330-v59-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Failed to get response for submission mistralai-mistral-nemo-_9330_v59: ('http://mistralai-mistral-nemo-9330-v59-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Failed to get response for submission blend_dedat_2024-08-16: ('http://zonemercy-graft-cogent-v-7573-v6-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'EOF\n')
Failed to get response for submission mistralai-mistral-nemo-_9330_v59: ('http://mistralai-mistral-nemo-9330-v59-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'EOF\n')
Inference service trace2333-ultra1w-dol1w-2607-v8 ready after 252.24069476127625s
Pipeline stage ISVCDeployer completed in 253.57s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.135709524154663s
Received healthy response to inference request in 1.873593807220459s
Received healthy response to inference request in 1.6771879196166992s
Received healthy response to inference request in 2.1661903858184814s
Received healthy response to inference request in 1.7096524238586426s
5 requests
0 failed requests
5th percentile: 1.683680820465088
10th percentile: 1.6901737213134767
20th percentile: 1.7031595230102539
30th percentile: 1.7424407005310059
40th percentile: 1.8080172538757324
50th percentile: 1.873593807220459
60th percentile: 1.9784400939941407
70th percentile: 2.0832863807678224
80th percentile: 2.1418056964874266
90th percentile: 2.153998041152954
95th percentile: 2.160094213485718
99th percentile: 2.1649711513519287
mean time: 1.912466812133789
Pipeline stage StressChecker completed in 10.65s
trace2333-ultra1w-dol1w-_2607_v8 status is now deployed due to DeploymentManager action
trace2333-ultra1w-dol1w-_2607_v8 status is now inactive due to auto deactivation removed underperforming models
trace2333-ultra1w-dol1w-_2607_v8 status is now torndown due to DeploymentManager action