developer_uid: Trace2333
submission_id: trace2333-ultra4w-dol4w-_4852_v1
model_name: trace2333-ultra4w-dol4w-_4852_v1
model_group: Trace2333/ultra4w_dol4w_
status: torndown
timestamp: 2024-08-27T17:04:04+00:00
num_battles: 10956
num_wins: 5479
celo_rating: 1237.4
family_friendly_score: 0.0
submission_type: basic
model_repo: Trace2333/ultra4w_dol4w_fd5w_r32a16_qkvo_epoch3_v2
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: trace2333-ultra4w-dol4w-_4852_v1
is_internal_developer: False
language_model: Trace2333/ultra4w_dol4w_fd5w_r32a16_qkvo_epoch3_v2
model_size: 8B
ranking_group: single
us_pacific_date: 2024-08-27
win_ratio: 0.5000912741876598
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 200, '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-ultra4w-dol4w-4852-v1-mkmlizer
Waiting for job on trace2333-ultra4w-dol4w-4852-v1-mkmlizer to finish
Stopping job with name trace2333-ultra4w-dol4w-4852-v1-mkmlizer
%s, retrying in %s seconds...
Starting job with name trace2333-ultra4w-dol4w-4852-v1-mkmlizer
Waiting for job on trace2333-ultra4w-dol4w-4852-v1-mkmlizer to finish
trace2333-ultra4w-dol4w-4852-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
trace2333-ultra4w-dol4w-4852-v1-mkmlizer: ║ _____ __ __ ║
trace2333-ultra4w-dol4w-4852-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
trace2333-ultra4w-dol4w-4852-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
trace2333-ultra4w-dol4w-4852-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
trace2333-ultra4w-dol4w-4852-v1-mkmlizer: ║ /___/ ║
trace2333-ultra4w-dol4w-4852-v1-mkmlizer: ║ ║
trace2333-ultra4w-dol4w-4852-v1-mkmlizer: ║ Version: 0.10.1 ║
trace2333-ultra4w-dol4w-4852-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
trace2333-ultra4w-dol4w-4852-v1-mkmlizer: ║ https://mk1.ai ║
trace2333-ultra4w-dol4w-4852-v1-mkmlizer: ║ ║
trace2333-ultra4w-dol4w-4852-v1-mkmlizer: ║ The license key for the current software has been verified as ║
trace2333-ultra4w-dol4w-4852-v1-mkmlizer: ║ belonging to: ║
trace2333-ultra4w-dol4w-4852-v1-mkmlizer: ║ ║
trace2333-ultra4w-dol4w-4852-v1-mkmlizer: ║ Chai Research Corp. ║
trace2333-ultra4w-dol4w-4852-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
trace2333-ultra4w-dol4w-4852-v1-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
trace2333-ultra4w-dol4w-4852-v1-mkmlizer: ║ ║
trace2333-ultra4w-dol4w-4852-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission blend_dedat_2024-08-16: ('http://mistralai-mixtral-8x7b-3473-v130-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:57108->127.0.0.1:8080: read: connection reset by peer\n')
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
trace2333-ultra4w-dol4w-4852-v1-mkmlizer: Downloaded to shared memory in 384.670s
trace2333-ultra4w-dol4w-4852-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp3d65mxfn, device:0
trace2333-ultra4w-dol4w-4852-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
trace2333-ultra4w-dol4w-4852-v1-mkmlizer: quantized model in 29.104s
trace2333-ultra4w-dol4w-4852-v1-mkmlizer: Processed model Trace2333/ultra4w_dol4w_fd5w_r32a16_qkvo_epoch3_v2 in 413.774s
trace2333-ultra4w-dol4w-4852-v1-mkmlizer: creating bucket guanaco-mkml-models
trace2333-ultra4w-dol4w-4852-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
trace2333-ultra4w-dol4w-4852-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/trace2333-ultra4w-dol4w-4852-v1
trace2333-ultra4w-dol4w-4852-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/trace2333-ultra4w-dol4w-4852-v1/special_tokens_map.json
trace2333-ultra4w-dol4w-4852-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/trace2333-ultra4w-dol4w-4852-v1/config.json
trace2333-ultra4w-dol4w-4852-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/trace2333-ultra4w-dol4w-4852-v1/tokenizer_config.json
trace2333-ultra4w-dol4w-4852-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/trace2333-ultra4w-dol4w-4852-v1/tokenizer.json
trace2333-ultra4w-dol4w-4852-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/trace2333-ultra4w-dol4w-4852-v1/flywheel_model.0.safetensors
trace2333-ultra4w-dol4w-4852-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 2%|▏ | 5/291 [00:00<00:10, 26.15it/s] Loading 0: 4%|▍ | 12/291 [00:00<00:07, 35.09it/s] Loading 0: 5%|▌ | 16/291 [00:00<00:08, 32.70it/s] Loading 0: 7%|▋ | 21/291 [00:00<00:07, 35.55it/s] Loading 0: 9%|▊ | 25/291 [00:00<00:07, 33.38it/s] Loading 0: 10%|█ | 30/291 [00:00<00:07, 37.05it/s] Loading 0: 12%|█▏ | 34/291 [00:01<00:10, 25.23it/s] Loading 0: 13%|█▎ | 38/291 [00:01<00:09, 26.67it/s] Loading 0: 14%|█▍ | 42/291 [00:01<00:09, 26.04it/s] Loading 0: 16%|█▋ | 48/291 [00:01<00:07, 31.40it/s] Loading 0: 18%|█▊ | 52/291 [00:01<00:07, 30.97it/s] Loading 0: 20%|█▉ | 57/291 [00:01<00:06, 34.03it/s] Loading 0: 21%|██ | 61/291 [00:01<00:07, 31.50it/s] Loading 0: 23%|██▎ | 66/291 [00:02<00:06, 33.76it/s] Loading 0: 24%|██▍ | 70/291 [00:02<00:06, 32.30it/s] Loading 0: 25%|██▌ | 74/291 [00:02<00:06, 32.53it/s] Loading 0: 27%|██▋ | 78/291 [00:02<00:06, 32.03it/s] Loading 0: 28%|██▊ | 82/291 [00:02<00:09, 22.28it/s] Loading 0: 29%|██▉ | 85/291 [00:02<00:08, 23.64it/s] Loading 0: 31%|███ | 90/291 [00:03<00:07, 27.78it/s] Loading 0: 32%|███▏ | 94/291 [00:03<00:06, 28.20it/s] Loading 0: 34%|███▍ | 99/291 [00:03<00:06, 31.66it/s] Loading 0: 35%|███▌ | 103/291 [00:03<00:06, 31.21it/s] Loading 0: 37%|███▋ | 108/291 [00:03<00:05, 34.26it/s] Loading 0: 38%|███▊ | 112/291 [00:03<00:05, 32.94it/s] Loading 0: 40%|███▉ | 116/291 [00:03<00:05, 33.05it/s] Loading 0: 42%|████▏ | 122/291 [00:03<00:04, 37.88it/s] Loading 0: 44%|████▎ | 127/291 [00:04<00:04, 36.05it/s] Loading 0: 46%|████▌ | 133/291 [00:04<00:05, 30.53it/s] Loading 0: 47%|████▋ | 137/291 [00:04<00:05, 30.72it/s] Loading 0: 48%|████▊ | 141/291 [00:04<00:05, 28.69it/s] Loading 0: 51%|█████ | 147/291 [00:04<00:04, 32.62it/s] Loading 0: 52%|█████▏ | 151/291 [00:04<00:04, 31.80it/s] Loading 0: 54%|█████▎ | 156/291 [00:04<00:03, 34.68it/s] Loading 0: 55%|█████▍ | 160/291 [00:05<00:03, 32.82it/s] Loading 0: 57%|█████▋ | 165/291 [00:05<00:03, 35.45it/s] Loading 0: 58%|█████▊ | 169/291 [00:05<00:03, 33.94it/s] Loading 0: 60%|█████▉ | 174/291 [00:05<00:03, 36.52it/s] Loading 0: 61%|██████ | 178/291 [00:05<00:03, 33.64it/s] Loading 0: 63%|██████▎ | 183/291 [00:05<00:02, 37.22it/s] Loading 0: 64%|██████▍ | 187/291 [00:06<00:04, 25.58it/s] Loading 0: 66%|██████▌ | 191/291 [00:06<00:03, 26.88it/s] Loading 0: 67%|██████▋ | 195/291 [00:06<00:03, 26.02it/s] Loading 0: 69%|██████▉ | 201/291 [00:06<00:02, 30.95it/s] Loading 0: 70%|███████ | 205/291 [00:06<00:02, 30.68it/s] Loading 0: 72%|███████▏ | 210/291 [00:06<00:02, 33.63it/s] Loading 0: 74%|███████▎ | 214/291 [00:06<00:02, 32.52it/s] Loading 0: 75%|███████▌ | 219/291 [00:06<00:02, 34.64it/s] Loading 0: 77%|███████▋ | 223/291 [00:07<00:02, 32.82it/s] Loading 0: 78%|███████▊ | 227/291 [00:07<00:02, 31.88it/s] Loading 0: 79%|███████▉ | 231/291 [00:07<00:01, 32.30it/s] Loading 0: 81%|████████ | 235/291 [00:07<00:02, 24.05it/s] Loading 0: 82%|████████▏ | 239/291 [00:07<00:02, 24.14it/s] Loading 0: 85%|████████▍ | 246/291 [00:07<00:01, 31.60it/s] Loading 0: 86%|████████▌ | 250/291 [00:08<00:01, 30.75it/s] Loading 0: 88%|████████▊ | 255/291 [00:08<00:01, 33.86it/s] Loading 0: 89%|████████▉ | 259/291 [00:08<00:00, 32.27it/s] Loading 0: 91%|█████████ | 264/291 [00:08<00:00, 34.08it/s] Loading 0: 92%|█████████▏| 268/291 [00:08<00:00, 30.63it/s] Loading 0: 94%|█████████▍| 273/291 [00:08<00:00, 33.41it/s] Loading 0: 95%|█████████▌| 277/291 [00:08<00:00, 31.50it/s] Loading 0: 97%|█████████▋| 281/291 [00:09<00:00, 31.77it/s] Loading 0: 98%|█████████▊| 286/291 [00:14<00:01, 2.57it/s] Loading 0: 99%|█████████▉| 289/291 [00:14<00:00, 3.21it/s]
Job trace2333-ultra4w-dol4w-4852-v1-mkmlizer completed after 439.95s with status: succeeded
Stopping job with name trace2333-ultra4w-dol4w-4852-v1-mkmlizer
Pipeline stage MKMLizer completed in 441.42s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.22s
Running pipeline stage ISVCDeployer
Creating inference service trace2333-ultra4w-dol4w-4852-v1
Waiting for inference service trace2333-ultra4w-dol4w-4852-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
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Failed to get response for submission blend_filor_2024-08-16: ('http://mistralai-mixtral-8x7b-3473-v130-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:49026->127.0.0.1:8080: read: connection reset by peer\n')
Inference service trace2333-ultra4w-dol4w-4852-v1 ready after 170.56577038764954s
Pipeline stage ISVCDeployer completed in 171.12s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.292732000350952s
Received healthy response to inference request in 1.5150434970855713s
Received healthy response to inference request in 1.926764726638794s
Received healthy response to inference request in 1.7637934684753418s
Received healthy response to inference request in 1.8279380798339844s
5 requests
0 failed requests
5th percentile: 1.5647934913635253
10th percentile: 1.6145434856414795
20th percentile: 1.7140434741973878
30th percentile: 1.7766223907470704
40th percentile: 1.8022802352905274
50th percentile: 1.8279380798339844
60th percentile: 1.8674687385559081
70th percentile: 1.906999397277832
80th percentile: 1.9999581813812257
90th percentile: 2.146345090866089
95th percentile: 2.2195385456085206
99th percentile: 2.278093309402466
mean time: 1.8652543544769287
Pipeline stage StressChecker completed in 10.46s
trace2333-ultra4w-dol4w-_4852_v1 status is now deployed due to DeploymentManager action
trace2333-ultra4w-dol4w-_4852_v1 status is now inactive due to auto deactivation removed underperforming models
trace2333-ultra4w-dol4w-_4852_v1 status is now torndown due to DeploymentManager action