developer_uid: chace9580
submission_id: jic062-dpo-v2-8-nemo-e3_v1
model_name: jic062-dpo-v2-8-nemo-e3_v1
model_group: jic062/dpo-v2.8-Nemo-e3
status: torndown
timestamp: 2024-10-12T03:17:02+00:00
num_battles: 7916
num_wins: 4247
celo_rating: 1279.27
family_friendly_score: 0.533977348434377
family_friendly_standard_error: 0.005726713313419156
submission_type: basic
model_repo: jic062/dpo-v2.8-Nemo-e3
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
display_name: jic062-dpo-v2-8-nemo-e3_v1
is_internal_developer: False
language_model: jic062/dpo-v2.8-Nemo-e3
model_size: 13B
ranking_group: single
us_pacific_date: 2024-10-11
win_ratio: 0.5365083375442142
generation_params: {'temperature': 1.0, 'top_p': 0.9, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '/s', '[/INST]'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': '[INST]system\n{memory}[/INST]\n', 'prompt_template': '[INST]user\n{prompt}[/INST]\n', 'bot_template': '[INST]assistant\n{bot_name}: {message}[/INST]\n', 'user_template': '[INST]user\n{user_name}: {message}[/INST]\n', 'response_template': '[INST]assistant\n{bot_name}:', 'truncate_by_message': False}
Resubmit model
Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLizer
Starting job with name jic062-dpo-v2-8-nemo-e3-v1-mkmlizer
Waiting for job on jic062-dpo-v2-8-nemo-e3-v1-mkmlizer to finish
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
jic062-dpo-v2-8-nemo-e3-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
jic062-dpo-v2-8-nemo-e3-v1-mkmlizer: ║ _____ __ __ ║
jic062-dpo-v2-8-nemo-e3-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
jic062-dpo-v2-8-nemo-e3-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
jic062-dpo-v2-8-nemo-e3-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
jic062-dpo-v2-8-nemo-e3-v1-mkmlizer: ║ /___/ ║
jic062-dpo-v2-8-nemo-e3-v1-mkmlizer: ║ ║
jic062-dpo-v2-8-nemo-e3-v1-mkmlizer: ║ Version: 0.11.12 ║
jic062-dpo-v2-8-nemo-e3-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
jic062-dpo-v2-8-nemo-e3-v1-mkmlizer: ║ https://mk1.ai ║
jic062-dpo-v2-8-nemo-e3-v1-mkmlizer: ║ ║
jic062-dpo-v2-8-nemo-e3-v1-mkmlizer: ║ The license key for the current software has been verified as ║
jic062-dpo-v2-8-nemo-e3-v1-mkmlizer: ║ belonging to: ║
jic062-dpo-v2-8-nemo-e3-v1-mkmlizer: ║ ║
jic062-dpo-v2-8-nemo-e3-v1-mkmlizer: ║ Chai Research Corp. ║
jic062-dpo-v2-8-nemo-e3-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
jic062-dpo-v2-8-nemo-e3-v1-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
jic062-dpo-v2-8-nemo-e3-v1-mkmlizer: ║ ║
jic062-dpo-v2-8-nemo-e3-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
jic062-dpo-v2-8-nemo-e3-v1-mkmlizer: Downloaded to shared memory in 55.208s
jic062-dpo-v2-8-nemo-e3-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp4cscitjk, device:0
jic062-dpo-v2-8-nemo-e3-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
jic062-dpo-v2-8-nemo-e3-v1-mkmlizer: quantized model in 35.717s
jic062-dpo-v2-8-nemo-e3-v1-mkmlizer: Processed model jic062/dpo-v2.8-Nemo-e3 in 90.925s
jic062-dpo-v2-8-nemo-e3-v1-mkmlizer: creating bucket guanaco-mkml-models
jic062-dpo-v2-8-nemo-e3-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
jic062-dpo-v2-8-nemo-e3-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/jic062-dpo-v2-8-nemo-e3-v1
jic062-dpo-v2-8-nemo-e3-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/jic062-dpo-v2-8-nemo-e3-v1/config.json
jic062-dpo-v2-8-nemo-e3-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/jic062-dpo-v2-8-nemo-e3-v1/special_tokens_map.json
jic062-dpo-v2-8-nemo-e3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/jic062-dpo-v2-8-nemo-e3-v1/tokenizer_config.json
jic062-dpo-v2-8-nemo-e3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/jic062-dpo-v2-8-nemo-e3-v1/tokenizer.json
jic062-dpo-v2-8-nemo-e3-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/jic062-dpo-v2-8-nemo-e3-v1/flywheel_model.0.safetensors
jic062-dpo-v2-8-nemo-e3-v1-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:11, 30.48it/s] Loading 0: 4%|▎ | 13/363 [00:00<00:07, 49.08it/s] Loading 0: 5%|▌ | 19/363 [00:00<00:08, 42.82it/s] Loading 0: 7%|▋ | 24/363 [00:00<00:08, 41.37it/s] Loading 0: 9%|▊ | 31/363 [00:00<00:07, 47.13it/s] Loading 0: 10%|█ | 37/363 [00:00<00:07, 44.97it/s] Loading 0: 12%|█▏ | 42/363 [00:00<00:07, 44.11it/s] Loading 0: 13%|█▎ | 49/363 [00:01<00:06, 49.27it/s] Loading 0: 15%|█▌ | 55/363 [00:01<00:06, 46.57it/s] Loading 0: 17%|█▋ | 61/363 [00:01<00:09, 33.53it/s] Loading 0: 18%|█▊ | 65/363 [00:01<00:08, 33.14it/s] Loading 0: 20%|█▉ | 72/363 [00:01<00:07, 39.42it/s] Loading 0: 21%|██ | 77/363 [00:01<00:06, 40.97it/s] Loading 0: 23%|██▎ | 82/363 [00:02<00:07, 35.25it/s] Loading 0: 25%|██▍ | 89/363 [00:02<00:06, 42.62it/s] Loading 0: 26%|██▌ | 94/363 [00:02<00:06, 43.40it/s] Loading 0: 27%|██▋ | 99/363 [00:02<00:05, 44.35it/s] Loading 0: 29%|██▊ | 104/363 [00:02<00:05, 45.59it/s] Loading 0: 30%|███ | 110/363 [00:02<00:05, 44.05it/s] Loading 0: 32%|███▏ | 115/363 [00:02<00:05, 44.38it/s] Loading 0: 33%|███▎ | 120/363 [00:02<00:05, 42.33it/s] Loading 0: 34%|███▍ | 125/363 [00:02<00:05, 43.57it/s] Loading 0: 36%|███▌ | 130/363 [00:03<00:05, 43.26it/s] Loading 0: 37%|███▋ | 135/363 [00:03<00:05, 42.59it/s] Loading 0: 39%|███▉ | 141/363 [00:03<00:05, 41.69it/s] Loading 0: 40%|████ | 146/363 [00:03<00:07, 30.21it/s] Loading 0: 41%|████▏ | 150/363 [00:03<00:06, 30.81it/s] Loading 0: 43%|████▎ | 156/363 [00:03<00:05, 36.72it/s] Loading 0: 44%|████▍ | 161/363 [00:03<00:05, 38.67it/s] Loading 0: 46%|████▌ | 166/363 [00:04<00:04, 40.45it/s] Loading 0: 47%|████▋ | 172/363 [00:04<00:04, 40.01it/s] Loading 0: 49%|████▉ | 177/363 [00:04<00:04, 40.02it/s] Loading 0: 50%|█████ | 183/363 [00:04<00:04, 44.85it/s] Loading 0: 52%|█████▏ | 188/363 [00:04<00:03, 45.16it/s] Loading 0: 53%|█████▎ | 193/363 [00:04<00:03, 45.41it/s] Loading 0: 55%|█████▍ | 199/363 [00:04<00:03, 43.22it/s] Loading 0: 56%|█████▌ | 204/363 [00:04<00:03, 42.84it/s] Loading 0: 58%|█████▊ | 210/363 [00:05<00:03, 47.04it/s] Loading 0: 59%|█████▉ | 215/363 [00:05<00:03, 46.75it/s] Loading 0: 61%|██████ | 220/363 [00:05<00:03, 47.34it/s] Loading 0: 62%|██████▏ | 225/363 [00:05<00:04, 27.75it/s] Loading 0: 63%|██████▎ | 230/363 [00:05<00:04, 30.32it/s] Loading 0: 65%|██████▌ | 237/363 [00:05<00:03, 37.80it/s] Loading 0: 67%|██████▋ | 242/363 [00:05<00:03, 38.43it/s] Loading 0: 68%|██████▊ | 247/363 [00:06<00:02, 39.71it/s] Loading 0: 69%|██████▉ | 252/363 [00:06<00:02, 42.16it/s] Loading 0: 71%|███████ | 257/363 [00:06<00:02, 36.60it/s] Loading 0: 73%|███████▎ | 264/363 [00:06<00:02, 44.17it/s] Loading 0: 74%|███████▍ | 269/363 [00:06<00:02, 43.46it/s] Loading 0: 75%|███████▌ | 274/363 [00:06<00:02, 43.46it/s] Loading 0: 77%|███████▋ | 280/363 [00:06<00:01, 41.54it/s] Loading 0: 79%|███████▊ | 285/363 [00:07<00:01, 41.19it/s] Loading 0: 80%|████████ | 291/363 [00:07<00:01, 45.10it/s] Loading 0: 82%|████████▏ | 296/363 [00:07<00:01, 45.34it/s] Loading 0: 83%|████████▎ | 302/363 [00:07<00:01, 49.12it/s] Loading 0: 85%|████████▍ | 308/363 [00:14<00:20, 2.67it/s] Loading 0: 86%|████████▌ | 312/363 [00:14<00:15, 3.39it/s] Loading 0: 88%|████████▊ | 320/363 [00:14<00:07, 5.47it/s] Loading 0: 90%|████████▉ | 326/363 [00:14<00:05, 7.39it/s] Loading 0: 91%|█████████ | 331/363 [00:14<00:03, 9.37it/s] Loading 0: 93%|█████████▎| 338/363 [00:14<00:01, 13.24it/s] Loading 0: 95%|█████████▍| 344/363 [00:14<00:01, 16.59it/s] Loading 0: 96%|█████████▌| 349/363 [00:15<00:00, 19.77it/s] Loading 0: 98%|█████████▊| 355/363 [00:15<00:00, 24.91it/s] Loading 0: 99%|█████████▉| 360/363 [00:15<00:00, 28.40it/s]
Job jic062-dpo-v2-8-nemo-e3-v1-mkmlizer completed after 114.57s with status: succeeded
Stopping job with name jic062-dpo-v2-8-nemo-e3-v1-mkmlizer
Pipeline stage MKMLizer completed in 115.08s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service jic062-dpo-v2-8-nemo-e3-v1
Waiting for inference service jic062-dpo-v2-8-nemo-e3-v1 to be ready
Inference service jic062-dpo-v2-8-nemo-e3-v1 ready after 150.74231815338135s
Pipeline stage MKMLDeployer completed in 151.23s
run pipeline stage %s
Running pipeline stage StressChecker
HTTPConnectionPool(host='guanaco-submitter.guanaco-backend.k2.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
Received healthy response to inference request in 2.4265639781951904s
Received healthy response to inference request in 2.1159818172454834s
Received healthy response to inference request in 1.8010063171386719s
Received healthy response to inference request in 1.7852463722229004s
5 requests
1 failed requests
5th percentile: 1.7883983612060548
10th percentile: 1.791550350189209
20th percentile: 1.7978543281555175
30th percentile: 1.864001417160034
40th percentile: 1.9899916172027587
50th percentile: 2.1159818172454834
60th percentile: 2.2402146816253663
70th percentile: 2.3644475460052488
80th percentile: 5.976052522659305
90th percentile: 13.075029611587526
95th percentile: 16.624518156051632
99th percentile: 19.464108991622926
mean time: 5.660561037063599
%s, retrying in %s seconds...
Received healthy response to inference request in 1.6994802951812744s
Received healthy response to inference request in 2.1185238361358643s
Received healthy response to inference request in 1.730597734451294s
Received healthy response to inference request in 1.6574089527130127s
Received healthy response to inference request in 1.9592325687408447s
5 requests
0 failed requests
5th percentile: 1.665823221206665
10th percentile: 1.6742374897003174
20th percentile: 1.691066026687622
30th percentile: 1.7057037830352784
40th percentile: 1.718150758743286
50th percentile: 1.730597734451294
60th percentile: 1.8220516681671142
70th percentile: 1.9135056018829346
80th percentile: 1.9910908222198487
90th percentile: 2.0548073291778564
95th percentile: 2.0866655826568605
99th percentile: 2.1121521854400633
mean time: 1.833048677444458
Pipeline stage StressChecker completed in 40.86s
Shutdown handler de-registered
jic062-dpo-v2-8-nemo-e3_v1 status is now deployed due to DeploymentManager action
jic062-dpo-v2-8-nemo-e3_v1 status is now inactive due to auto deactivation removed underperforming models
jic062-dpo-v2-8-nemo-e3_v1 status is now torndown due to DeploymentManager action