submission_id: jic062-orpo-v0-3-nemo_v2
developer_uid: chace9580
best_of: 8
celo_rating: 1263.43
display_name: jic062-orpo-v0-3-nemo_v2
family_friendly_score: 0.5509998029944838
family_friendly_standard_error: 0.006016439278931273
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}
generation_params: {'temperature': 0.85, 'top_p': 0.9, 'min_p': 0.05, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
is_internal_developer: False
language_model: jic062/orpo-v0.3-Nemo
max_input_tokens: 1024
max_output_tokens: 64
model_architecture: MistralForCausalLM
model_group: jic062/orpo-v0.3-Nemo
model_name: jic062-orpo-v0-3-nemo_v2
model_num_parameters: 12772070400.0
model_repo: jic062/orpo-v0.3-Nemo
model_size: 13B
num_battles: 7194
num_wins: 3674
ranking_group: single
status: inactive
submission_type: basic
timestamp: 2024-10-19T02:08:55+00:00
us_pacific_date: 2024-10-18
win_ratio: 0.5107033639143731
Download Preference Data
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-orpo-v0-3-nemo-v2-mkmlizer
Waiting for job on jic062-orpo-v0-3-nemo-v2-mkmlizer to finish
jic062-orpo-v0-3-nemo-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
jic062-orpo-v0-3-nemo-v2-mkmlizer: ║ _____ __ __ ║
jic062-orpo-v0-3-nemo-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
jic062-orpo-v0-3-nemo-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
jic062-orpo-v0-3-nemo-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
jic062-orpo-v0-3-nemo-v2-mkmlizer: ║ /___/ ║
jic062-orpo-v0-3-nemo-v2-mkmlizer: ║ ║
jic062-orpo-v0-3-nemo-v2-mkmlizer: ║ Version: 0.11.12 ║
jic062-orpo-v0-3-nemo-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
jic062-orpo-v0-3-nemo-v2-mkmlizer: ║ https://mk1.ai ║
jic062-orpo-v0-3-nemo-v2-mkmlizer: ║ ║
jic062-orpo-v0-3-nemo-v2-mkmlizer: ║ The license key for the current software has been verified as ║
jic062-orpo-v0-3-nemo-v2-mkmlizer: ║ belonging to: ║
jic062-orpo-v0-3-nemo-v2-mkmlizer: ║ ║
jic062-orpo-v0-3-nemo-v2-mkmlizer: ║ Chai Research Corp. ║
jic062-orpo-v0-3-nemo-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
jic062-orpo-v0-3-nemo-v2-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
jic062-orpo-v0-3-nemo-v2-mkmlizer: ║ ║
jic062-orpo-v0-3-nemo-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
jic062-orpo-v0-3-nemo-v2-mkmlizer: Downloaded to shared memory in 37.281s
jic062-orpo-v0-3-nemo-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpvfu8pswj, device:0
jic062-orpo-v0-3-nemo-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
jic062-orpo-v0-3-nemo-v2-mkmlizer: quantized model in 38.565s
jic062-orpo-v0-3-nemo-v2-mkmlizer: Processed model jic062/orpo-v0.3-Nemo in 75.847s
jic062-orpo-v0-3-nemo-v2-mkmlizer: creating bucket guanaco-mkml-models
jic062-orpo-v0-3-nemo-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
jic062-orpo-v0-3-nemo-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/jic062-orpo-v0-3-nemo-v2
jic062-orpo-v0-3-nemo-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/jic062-orpo-v0-3-nemo-v2/config.json
jic062-orpo-v0-3-nemo-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/jic062-orpo-v0-3-nemo-v2/special_tokens_map.json
jic062-orpo-v0-3-nemo-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/jic062-orpo-v0-3-nemo-v2/tokenizer_config.json
jic062-orpo-v0-3-nemo-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/jic062-orpo-v0-3-nemo-v2/tokenizer.json
jic062-orpo-v0-3-nemo-v2-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:12, 28.38it/s] Loading 0: 3%|▎ | 12/363 [00:00<00:08, 43.82it/s] Loading 0: 5%|▍ | 17/363 [00:00<00:08, 40.60it/s] Loading 0: 6%|▌ | 22/363 [00:00<00:08, 39.39it/s] Loading 0: 7%|▋ | 27/363 [00:00<00:08, 40.58it/s] Loading 0: 9%|▉ | 32/363 [00:00<00:10, 31.35it/s] Loading 0: 10%|█ | 37/363 [00:01<00:09, 35.59it/s] Loading 0: 11%|█▏ | 41/363 [00:01<00:09, 32.72it/s] Loading 0: 13%|█▎ | 48/363 [00:01<00:07, 40.07it/s] Loading 0: 15%|█▍ | 53/363 [00:01<00:07, 38.96it/s] Loading 0: 16%|█▌ | 58/363 [00:01<00:07, 40.03it/s] Loading 0: 17%|█▋ | 63/363 [00:01<00:11, 26.77it/s] Loading 0: 18%|█▊ | 67/363 [00:01<00:10, 28.80it/s] Loading 0: 20%|█▉ | 71/363 [00:02<00:09, 30.08it/s] Loading 0: 21%|██ | 75/363 [00:02<00:09, 30.15it/s] Loading 0: 22%|██▏ | 80/363 [00:02<00:08, 33.18it/s] Loading 0: 23%|██▎ | 84/363 [00:02<00:08, 32.35it/s] Loading 0: 25%|██▍ | 89/363 [00:02<00:07, 34.62it/s] Loading 0: 26%|██▌ | 93/363 [00:02<00:08, 32.85it/s] Loading 0: 27%|██▋ | 98/363 [00:02<00:07, 34.90it/s] Loading 0: 28%|██▊ | 102/363 [00:03<00:07, 32.64it/s] Loading 0: 29%|██▉ | 106/363 [00:03<00:07, 32.43it/s] Loading 0: 31%|███ | 112/363 [00:03<00:06, 36.51it/s] Loading 0: 32%|███▏ | 116/363 [00:03<00:07, 34.79it/s] Loading 0: 33%|███▎ | 120/363 [00:03<00:07, 33.72it/s] Loading 0: 34%|███▍ | 124/363 [00:03<00:06, 34.85it/s] Loading 0: 35%|███▌ | 128/363 [00:03<00:07, 31.55it/s] Loading 0: 36%|███▋ | 132/363 [00:03<00:06, 33.23it/s] Loading 0: 37%|███▋ | 136/363 [00:04<00:07, 30.77it/s] Loading 0: 39%|███▉ | 141/363 [00:04<00:06, 35.12it/s] Loading 0: 40%|███▉ | 145/363 [00:04<00:09, 22.75it/s] Loading 0: 41%|████ | 149/363 [00:04<00:09, 23.34it/s] Loading 0: 42%|████▏ | 154/363 [00:04<00:07, 27.39it/s] Loading 0: 44%|████▎ | 158/363 [00:04<00:07, 26.42it/s] Loading 0: 45%|████▌ | 165/363 [00:05<00:05, 33.56it/s] Loading 0: 47%|████▋ | 169/363 [00:05<00:05, 32.86it/s] Loading 0: 48%|████▊ | 173/363 [00:05<00:05, 34.41it/s] Loading 0: 49%|████▉ | 177/363 [00:05<00:05, 31.05it/s] Loading 0: 50%|████▉ | 181/363 [00:05<00:05, 32.68it/s] Loading 0: 51%|█████ | 185/363 [00:05<00:05, 30.19it/s] Loading 0: 52%|█████▏ | 190/363 [00:05<00:05, 34.33it/s] Loading 0: 53%|█████▎ | 194/363 [00:05<00:05, 31.06it/s] Loading 0: 55%|█████▍ | 199/363 [00:06<00:04, 34.95it/s] Loading 0: 56%|█████▌ | 203/363 [00:06<00:05, 31.57it/s] Loading 0: 57%|█████▋ | 208/363 [00:06<00:04, 35.30it/s] Loading 0: 58%|█████▊ | 212/363 [00:06<00:04, 32.06it/s] Loading 0: 60%|██████ | 218/363 [00:06<00:03, 36.39it/s] Loading 0: 61%|██████▏ | 223/363 [00:06<00:05, 26.83it/s] Loading 0: 63%|██████▎ | 227/363 [00:07<00:05, 26.83it/s] Loading 0: 64%|██████▎ | 231/363 [00:07<00:04, 26.51it/s] Loading 0: 65%|██████▍ | 235/363 [00:07<00:04, 28.94it/s] Loading 0: 66%|██████▌ | 239/363 [00:07<00:04, 28.14it/s] Loading 0: 68%|██████▊ | 246/363 [00:07<00:03, 35.62it/s] Loading 0: 69%|██████▉ | 250/363 [00:07<00:03, 34.65it/s] Loading 0: 70%|██████▉ | 254/363 [00:07<00:03, 35.04it/s] Loading 0: 71%|███████ | 258/363 [00:08<00:03, 30.06it/s] Loading 0: 73%|███████▎ | 264/363 [00:08<00:02, 35.07it/s] Loading 0: 74%|███████▍ | 268/363 [00:08<00:02, 34.08it/s] Loading 0: 75%|███████▌ | 273/363 [00:08<00:02, 35.32it/s] Loading 0: 76%|███████▋ | 277/363 [00:08<00:02, 33.53it/s] Loading 0: 78%|███████▊ | 282/363 [00:08<00:02, 36.27it/s] Loading 0: 79%|███████▉ | 286/363 [00:08<00:02, 35.33it/s] Loading 0: 80%|███████▉ | 290/363 [00:08<00:02, 36.30it/s] Loading 0: 81%|████████ | 294/363 [00:09<00:02, 32.86it/s] Loading 0: 82%|████████▏ | 299/363 [00:09<00:01, 35.24it/s] Loading 0: 84%|████████▎ | 304/363 [00:15<00:27, 2.16it/s] Loading 0: 85%|████████▍ | 307/363 [00:16<00:20, 2.69it/s] Loading 0: 86%|████████▌ | 312/363 [00:16<00:13, 3.92it/s] Loading 0: 87%|████████▋ | 317/363 [00:16<00:08, 5.61it/s] Loading 0: 88%|████████▊ | 321/363 [00:16<00:05, 7.15it/s] Loading 0: 90%|████████▉ | 326/363 [00:16<00:03, 9.94it/s] Loading 0: 91%|█████████ | 330/363 [00:16<00:02, 12.01it/s] Loading 0: 93%|█████████▎| 337/363 [00:16<00:01, 17.74it/s] Loading 0: 94%|█████████▍| 342/363 [00:17<00:01, 20.99it/s] Loading 0: 96%|█████████▌| 347/363 [00:17<00:00, 24.22it/s] Loading 0: 97%|█████████▋| 351/363 [00:17<00:00, 26.42it/s] Loading 0: 98%|█████████▊| 355/363 [00:17<00:00, 28.54it/s] Loading 0: 99%|█████████▉| 359/363 [00:17<00:00, 29.28it/s]
Job jic062-orpo-v0-3-nemo-v2-mkmlizer completed after 104.14s with status: succeeded
Stopping job with name jic062-orpo-v0-3-nemo-v2-mkmlizer
Pipeline stage MKMLizer completed in 104.65s
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-orpo-v0-3-nemo-v2
Waiting for inference service jic062-orpo-v0-3-nemo-v2 to be ready
Inference service jic062-orpo-v0-3-nemo-v2 ready after 210.74678373336792s
Pipeline stage MKMLDeployer completed in 211.33s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.803152322769165s
Received healthy response to inference request in 2.0050344467163086s
Received healthy response to inference request in 1.750741720199585s
Received healthy response to inference request in 2.168336868286133s
Received healthy response to inference request in 2.2962708473205566s
5 requests
0 failed requests
5th percentile: 1.761223840713501
10th percentile: 1.771705961227417
20th percentile: 1.792670202255249
30th percentile: 1.8435287475585938
40th percentile: 1.9242815971374512
50th percentile: 2.0050344467163086
60th percentile: 2.0703554153442383
70th percentile: 2.135676383972168
80th percentile: 2.1939236640930178
90th percentile: 2.245097255706787
95th percentile: 2.2706840515136717
99th percentile: 2.2911534881591797
mean time: 2.0047072410583495
Pipeline stage StressChecker completed in 11.44s
Shutdown handler de-registered
jic062-orpo-v0-3-nemo_v2 status is now deployed due to DeploymentManager action
jic062-orpo-v0-3-nemo_v2 status is now inactive due to auto deactivation removed underperforming models