submission_id: chaiml-llama-8b-pairwis_8189_v39
developer_uid: robert_irvine
best_of: 1
celo_rating: 1247.22
display_name: chaiml-llama-8b-pairwis_8189_v39
family_friendly_score: 0.6165433687144848
family_friendly_standard_error: 0.006144122613538943
formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '', 'truncate_by_message': False}
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'], 'max_input_tokens': 256, 'best_of': 1, 'max_output_tokens': 1}
ineligible_reason: max_output_tokens!=64
is_internal_developer: True
language_model: ChaiML/llama_8b_pairwise_64m_256_tokens_step_249984
max_input_tokens: 256
max_output_tokens: 1
model_architecture: LlamaForSequenceClassification
model_group: ChaiML/llama_8b_pairwise
model_name: chaiml-llama-8b-pairwis_8189_v39
model_num_parameters: 8030261248.0
model_repo: ChaiML/llama_8b_pairwise_64m_256_tokens_step_249984
model_size: 8B
num_battles: 6611
num_wins: 3382
ranking_group: single
status: inactive
submission_type: basic
timestamp: 2024-10-21T17:55:35+00:00
us_pacific_date: 2024-10-21
win_ratio: 0.5115716230524883
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 chaiml-llama-8b-pairwis-8189-v39-mkmlizer
Waiting for job on chaiml-llama-8b-pairwis-8189-v39-mkmlizer to finish
chaiml-llama-8b-pairwis-8189-v39-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-llama-8b-pairwis-8189-v39-mkmlizer: ║ _____ __ __ ║
chaiml-llama-8b-pairwis-8189-v39-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-llama-8b-pairwis-8189-v39-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-llama-8b-pairwis-8189-v39-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-llama-8b-pairwis-8189-v39-mkmlizer: ║ /___/ ║
chaiml-llama-8b-pairwis-8189-v39-mkmlizer: ║ ║
chaiml-llama-8b-pairwis-8189-v39-mkmlizer: ║ Version: 0.11.12 ║
chaiml-llama-8b-pairwis-8189-v39-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-llama-8b-pairwis-8189-v39-mkmlizer: ║ https://mk1.ai ║
chaiml-llama-8b-pairwis-8189-v39-mkmlizer: ║ ║
chaiml-llama-8b-pairwis-8189-v39-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-llama-8b-pairwis-8189-v39-mkmlizer: ║ belonging to: ║
chaiml-llama-8b-pairwis-8189-v39-mkmlizer: ║ ║
chaiml-llama-8b-pairwis-8189-v39-mkmlizer: ║ Chai Research Corp. ║
chaiml-llama-8b-pairwis-8189-v39-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-llama-8b-pairwis-8189-v39-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
chaiml-llama-8b-pairwis-8189-v39-mkmlizer: ║ ║
chaiml-llama-8b-pairwis-8189-v39-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-llama-8b-pairwis-8189-v39-mkmlizer: Downloaded to shared memory in 36.123s
chaiml-llama-8b-pairwis-8189-v39-mkmlizer: quantizing model to /dev/shm/model_cache, profile:t0, folder:/tmp/tmpf6oyz9k1, device:0
chaiml-llama-8b-pairwis-8189-v39-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-llama-8b-pairwis-8189-v39-mkmlizer: quantized model in 84.650s
chaiml-llama-8b-pairwis-8189-v39-mkmlizer: Processed model ChaiML/llama_8b_pairwise_64m_256_tokens_step_249984 in 120.773s
chaiml-llama-8b-pairwis-8189-v39-mkmlizer: creating bucket guanaco-mkml-models
chaiml-llama-8b-pairwis-8189-v39-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-llama-8b-pairwis-8189-v39-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-llama-8b-pairwis-8189-v39
chaiml-llama-8b-pairwis-8189-v39-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-llama-8b-pairwis-8189-v39/config.json
chaiml-llama-8b-pairwis-8189-v39-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-llama-8b-pairwis-8189-v39/special_tokens_map.json
chaiml-llama-8b-pairwis-8189-v39-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-llama-8b-pairwis-8189-v39/tokenizer_config.json
chaiml-llama-8b-pairwis-8189-v39-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-llama-8b-pairwis-8189-v39/tokenizer.json
chaiml-llama-8b-pairwis-8189-v39-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-llama-8b-pairwis-8189-v39/flywheel_model.0.safetensors
chaiml-llama-8b-pairwis-8189-v39-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 3/291 [00:00<00:55, 5.18it/s] Loading 0: 1%|▏ | 4/291 [00:01<01:30, 3.16it/s] Loading 0: 2%|▏ | 5/291 [00:01<02:01, 2.35it/s] Loading 0: 3%|▎ | 8/291 [00:02<01:02, 4.49it/s] Loading 0: 3%|▎ | 9/291 [00:02<01:02, 4.55it/s] Loading 0: 3%|▎ | 10/291 [00:02<00:53, 5.21it/s] Loading 0: 4%|▍ | 12/291 [00:02<01:04, 4.30it/s] Loading 0: 4%|▍ | 13/291 [00:03<01:28, 3.14it/s] Loading 0: 5%|▍ | 14/291 [00:04<01:50, 2.51it/s] Loading 0: 6%|▌ | 17/291 [00:04<01:03, 4.32it/s] Loading 0: 6%|▌ | 18/291 [00:04<00:59, 4.56it/s] Loading 0: 7%|▋ | 20/291 [00:04<00:43, 6.29it/s] Loading 0: 8%|▊ | 22/291 [00:05<01:20, 3.33it/s] Loading 0: 8%|▊ | 23/291 [00:06<01:39, 2.70it/s] Loading 0: 9%|▉ | 26/291 [00:06<01:01, 4.28it/s] Loading 0: 9%|▉ | 27/291 [00:06<00:58, 4.50it/s] Loading 0: 10%|█ | 30/291 [00:07<00:58, 4.46it/s] Loading 0: 11%|█ | 31/291 [00:08<01:13, 3.52it/s] Loading 0: 11%|█ | 32/291 [00:08<01:31, 2.82it/s] Loading 0: 12%|█▏ | 35/291 [00:08<00:57, 4.46it/s] Loading 0: 12%|█▏ | 36/291 [00:09<00:54, 4.67it/s] Loading 0: 13%|█▎ | 37/291 [00:09<00:48, 5.19it/s] Loading 0: 13%|█▎ | 39/291 [00:09<00:57, 4.37it/s] Loading 0: 14%|█▎ | 40/291 [00:10<01:15, 3.32it/s] Loading 0: 14%|█▍ | 41/291 [00:11<01:35, 2.62it/s] Loading 0: 15%|█▌ | 44/291 [00:11<00:55, 4.47it/s] Loading 0: 15%|█▌ | 45/291 [00:11<00:52, 4.70it/s] Loading 0: 16%|█▋ | 48/291 [00:12<00:52, 4.59it/s] Loading 0: 17%|█▋ | 49/291 [00:12<01:08, 3.55it/s] Loading 0: 17%|█▋ | 50/291 [00:13<01:26, 2.80it/s] Loading 0: 18%|█▊ | 53/291 [00:13<00:53, 4.46it/s] Loading 0: 19%|█▊ | 54/291 [00:13<00:50, 4.67it/s] Loading 0: 20%|█▉ | 57/291 [00:14<00:51, 4.57it/s] Loading 0: 20%|█▉ | 58/291 [00:14<01:05, 3.57it/s] Loading 0: 20%|██ | 59/291 [00:15<01:21, 2.83it/s] Loading 0: 21%|██▏ | 62/291 [00:15<00:50, 4.53it/s] Loading 0: 22%|██▏ | 63/291 [00:15<00:48, 4.73it/s] Loading 0: 22%|██▏ | 65/291 [00:16<00:35, 6.38it/s] Loading 0: 23%|██▎ | 67/291 [00:17<01:05, 3.41it/s] Loading 0: 23%|██▎ | 68/291 [00:17<01:20, 2.77it/s] Loading 0: 24%|██▍ | 71/291 [00:18<00:50, 4.34it/s] Loading 0: 25%|██▍ | 72/291 [00:18<00:47, 4.57it/s] Loading 0: 26%|██▌ | 75/291 [00:18<00:47, 4.52it/s] Loading 0: 26%|██▌ | 76/291 [00:19<01:00, 3.56it/s] Loading 0: 26%|██▋ | 77/291 [00:20<01:15, 2.84it/s] Loading 0: 27%|██▋ | 80/291 [00:20<00:47, 4.47it/s] Loading 0: 28%|██▊ | 81/291 [00:20<00:44, 4.69it/s] Loading 0: 29%|██▊ | 83/291 [00:20<00:39, 5.33it/s] Loading 0: 29%|██▉ | 84/291 [00:21<00:54, 3.80it/s] Loading 0: 29%|██▉ | 85/291 [00:21<01:08, 3.02it/s] Loading 0: 30%|██▉ | 86/291 [00:22<01:23, 2.46it/s] Loading 0: 31%|███ | 89/291 [00:22<00:47, 4.22it/s] Loading 0: 31%|███ | 90/291 [00:22<00:44, 4.48it/s] Loading 0: 32%|███▏ | 93/291 [00:23<00:44, 4.46it/s] Loading 0: 32%|███▏ | 94/291 [00:24<00:56, 3.49it/s] Loading 0: 33%|███▎ | 95/291 [00:24<01:10, 2.79it/s] Loading 0: 34%|███▎ | 98/291 [00:25<00:43, 4.46it/s] Loading 0: 34%|███▍ | 99/291 [00:25<00:41, 4.68it/s] Loading 0: 35%|███▌ | 102/291 [00:25<00:41, 4.59it/s] Loading 0: 35%|███▌ | 103/291 [00:26<00:52, 3.58it/s] Loading 0: 36%|███▌ | 104/291 [00:27<01:05, 2.84it/s] Loading 0: 37%|███▋ | 107/291 [00:27<00:40, 4.54it/s] Loading 0: 37%|███▋ | 108/291 [00:27<00:38, 4.75it/s] Loading 0: 38%|███▊ | 111/291 [00:28<00:39, 4.61it/s] Loading 0: 38%|███▊ | 112/291 [00:28<00:49, 3.59it/s] Loading 0: 39%|███▉ | 113/291 [00:29<01:02, 2.87it/s] Loading 0: 40%|███▉ | 116/291 [00:29<00:38, 4.57it/s] Loading 0: 40%|████ | 117/291 [00:29<00:36, 4.78it/s] Loading 0: 41%|████ | 118/291 [00:29<00:32, 5.34it/s] Loading 0: 41%|████ | 120/291 [00:30<00:38, 4.46it/s] Loading 0: 42%|████▏ | 121/291 [00:30<00:50, 3.38it/s] Loading 0: 42%|████▏ | 122/291 [00:31<01:03, 2.68it/s] Loading 0: 43%|████▎ | 125/291 [00:31<00:36, 4.50it/s] Loading 0: 43%|████▎ | 126/291 [00:31<00:34, 4.73it/s] Loading 0: 44%|████▍ | 129/291 [00:32<00:35, 4.62it/s] Loading 0: 45%|████▍ | 130/291 [00:33<00:45, 3.58it/s] Loading 0: 45%|████▌ | 131/291 [00:33<00:56, 2.81it/s] Loading 0: 46%|████▌ | 134/291 [00:34<00:35, 4.42it/s] Loading 0: 46%|████▋ | 135/291 [00:34<00:33, 4.65it/s] Loading 0: 47%|████▋ | 138/291 [00:34<00:33, 4.57it/s] Loading 0: 48%|████▊ | 139/291 [00:35<00:42, 3.58it/s] Loading 0: 48%|████▊ | 140/291 [00:36<00:52, 2.86it/s] Loading 0: 49%|████▉ | 143/291 [00:36<00:32, 4.52it/s] Loading 0: 49%|████▉ | 144/291 [00:36<00:31, 4.74it/s] Loading 0: 50%|████▉ | 145/291 [00:36<00:27, 5.27it/s] Loading 0: 51%|█████ | 147/291 [00:37<00:32, 4.43it/s] Loading 0: 51%|█████ | 148/291 [00:37<00:42, 3.37it/s] Loading 0: 51%|█████ | 149/291 [00:38<00:53, 2.66it/s] Loading 0: 52%|█████▏ | 152/291 [00:38<00:30, 4.52it/s] Loading 0: 53%|█████▎ | 153/291 [00:38<00:29, 4.75it/s] Loading 0: 54%|█████▎ | 156/291 [00:39<00:29, 4.63it/s] Loading 0: 54%|█████▍ | 157/291 [00:40<00:37, 3.59it/s] Loading 0: 54%|█████▍ | 158/291 [00:40<00:46, 2.86it/s] Loading 0: 55%|█████▌ | 161/291 [00:40<00:28, 4.60it/s] Loading 0: 56%|█████▌ | 162/291 [00:40<00:26, 4.81it/s] Loading 0: 57%|█████▋ | 165/291 [00:41<00:27, 4.66it/s] Loading 0: 57%|█████▋ | 166/291 [00:42<00:34, 3.63it/s] Loading 0: 57%|█████▋ | 167/291 [00:42<00:43, 2.88it/s] Loading 0: 58%|█████▊ | 170/291 [00:43<00:26, 4.55it/s] Loading 0: 59%|█████▉ | 171/291 [00:43<00:25, 4.76it/s] Loading 0: 59%|█████▉ | 173/291 [00:43<00:29, 3.96it/s] Loading 0: 60%|██████ | 175/291 [00:44<00:23, 4.98it/s] Loading 0: 60%|██████ | 176/291 [00:44<00:22, 5.14it/s] Loading 0: 61%|██████ | 177/291 [00:44<00:20, 5.69it/s] Loading 0: 62%|██████▏ | 179/291 [00:44<00:24, 4.60it/s] Loading 0: 62%|██████▏ | 180/291 [00:45<00:32, 3.43it/s] Loading 0: 62%|██████▏ | 181/291 [00:46<00:40, 2.70it/s] Loading 0: 63%|██████▎ | 184/291 [00:46<00:23, 4.61it/s] Loading 0: 64%|██████▎ | 185/291 [00:46<00:21, 4.84it/s] Loading 0: 64%|██████▍ | 187/291 [00:46<00:18, 5.53it/s] Loading 0: 65%|██████▍ | 188/291 [00:47<00:26, 3.87it/s] Loading 0: 65%|██████▍ | 189/291 [00:47<00:34, 2.92it/s] Loading 0: 66%|██████▌ | 192/291 [00:48<00:26, 3.73it/s] Loading 0: 66%|██████▋ | 193/291 [00:49<00:31, 3.09it/s] Loading 0: 67%|██████▋ | 194/291 [00:49<00:37, 2.56it/s] Loading 0: 68%|██████▊ | 197/291 [00:49<00:22, 4.23it/s] Loading 0: 68%|██████▊ | 198/291 [00:50<00:20, 4.48it/s] Loading 0: 69%|██████▉ | 201/291 [00:50<00:20, 4.49it/s] Loading 0: 69%|██████▉ | 202/291 [00:51<00:25, 3.54it/s] Loading 0: 70%|██████▉ | 203/291 [00:51<00:30, 2.85it/s] Loading 0: 71%|███████ | 206/291 [00:52<00:18, 4.56it/s] Loading 0: 71%|███████ | 207/291 [00:52<00:17, 4.78it/s] Loading 0: 72%|███████▏ | 210/291 [00:52<00:17, 4.67it/s] Loading 0: 73%|███████▎ | 211/291 [00:53<00:22, 3.63it/s] Loading 0: 73%|███████▎ | 212/291 [00:54<00:27, 2.89it/s] Loading 0: 74%|███████▍ | 215/291 [00:54<00:16, 4.62it/s] Loading 0: 74%|███████▍ | 216/291 [00:54<00:15, 4.90it/s] Loading 0: 75%|███████▌ | 219/291 [00:55<00:15, 4.72it/s] Loading 0: 76%|███████▌ | 220/291 [00:55<00:19, 3.66it/s] Loading 0: 76%|███████▌ | 221/291 [00:56<00:23, 2.92it/s] Loading 0: 77%|███████▋ | 224/291 [00:56<00:14, 4.67it/s] Loading 0: 77%|███████▋ | 225/291 [00:56<00:13, 4.88it/s] Loading 0: 78%|███████▊ | 228/291 [00:57<00:13, 4.71it/s] Loading 0: 79%|███████▊ | 229/291 [00:57<00:16, 3.67it/s] Loading 0: 79%|███████▉ | 230/291 [00:58<00:20, 2.92it/s] Loading 0: 80%|████████ | 233/291 [00:58<00:12, 4.67it/s] Loading 0: 80%|████████ | 234/291 [00:58<00:11, 4.88it/s] Loading 0: 81%|████████▏ | 237/291 [00:59<00:11, 4.71it/s] Loading 0: 82%|████████▏ | 238/291 [01:00<00:14, 3.67it/s] Loading 0: 82%|████████▏ | 239/291 [01:00<00:17, 2.93it/s] Loading 0: 83%|████████▎ | 242/291 [01:00<00:10, 4.68it/s] Loading 0: 84%|████████▎ | 243/291 [01:01<00:09, 4.88it/s] Loading 0: 85%|████████▍ | 246/291 [01:01<00:09, 4.70it/s] Loading 0: 85%|████████▍ | 247/291 [01:02<00:12, 3.67it/s] Loading 0: 85%|████████▌ | 248/291 [01:03<00:14, 2.91it/s] Loading 0: 86%|████████▋ | 251/291 [01:03<00:08, 4.65it/s] Loading 0: 87%|████████▋ | 252/291 [01:03<00:08, 4.86it/s] Loading 0: 87%|████████▋ | 254/291 [01:03<00:05, 6.51it/s] Loading 0: 88%|████████▊ | 256/291 [01:04<00:10, 3.48it/s] Loading 0: 88%|████████▊ | 257/291 [01:05<00:11, 2.85it/s] Loading 0: 89%|████████▉ | 260/291 [01:05<00:06, 4.51it/s] Loading 0: 90%|████████▉ | 261/291 [01:05<00:06, 4.73it/s] Loading 0: 91%|█████████ | 264/291 [01:06<00:05, 4.63it/s] Loading 0: 91%|█████████ | 265/291 [01:06<00:07, 3.64it/s] Loading 0: 91%|█████████▏| 266/291 [01:07<00:08, 2.89it/s] Loading 0: 92%|█████████▏| 269/291 [01:07<00:04, 4.56it/s] Loading 0: 93%|█████████▎| 270/291 [01:07<00:04, 4.78it/s] Loading 0: 93%|█████████▎| 272/291 [01:07<00:02, 6.43it/s] Loading 0: 94%|█████████▍| 274/291 [01:09<00:04, 3.45it/s] Loading 0: 95%|█████████▍| 275/291 [01:09<00:05, 2.83it/s] Loading 0: 96%|█████████▌| 278/291 [01:09<00:02, 4.47it/s] Loading 0: 96%|█████████▌| 279/291 [01:10<00:02, 4.69it/s] Loading 0: 97%|█████████▋| 281/291 [01:10<00:02, 3.96it/s] Loading 0: 97%|█████████▋| 282/291 [01:11<00:02, 3.08it/s] Loading 0: 98%|█████████▊| 284/291 [01:11<00:01, 4.12it/s] Loading 0: 98%|█████████▊| 285/291 [01:11<00:01, 4.42it/s] Loading 0: 99%|█████████▊| 287/291 [01:11<00:00, 5.25it/s] Loading 0: 99%|█████████▉| 288/291 [01:12<00:00, 3.72it/s]
Job chaiml-llama-8b-pairwis-8189-v39-mkmlizer completed after 145.8s with status: succeeded
Stopping job with name chaiml-llama-8b-pairwis-8189-v39-mkmlizer
Pipeline stage MKMLizer completed in 146.45s
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 chaiml-llama-8b-pairwis-8189-v39
Waiting for inference service chaiml-llama-8b-pairwis-8189-v39 to be ready
Inference service chaiml-llama-8b-pairwis-8189-v39 ready after 150.67295694351196s
Pipeline stage MKMLDeployer completed in 151.32s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.722139835357666s
Received healthy response to inference request in 3.4395840167999268s
Received healthy response to inference request in 2.461652994155884s
Received healthy response to inference request in 3.5456972122192383s
Received healthy response to inference request in 2.960163116455078s
5 requests
0 failed requests
5th percentile: 2.5613550186157226
10th percentile: 2.6610570430755613
20th percentile: 2.8604610919952393
30th percentile: 3.056047296524048
40th percentile: 3.247815656661987
50th percentile: 3.4395840167999268
60th percentile: 3.4820292949676515
70th percentile: 3.524474573135376
80th percentile: 3.580985736846924
90th percentile: 3.651562786102295
95th percentile: 3.6868513107299803
99th percentile: 3.715082130432129
mean time: 3.2258474349975588
Pipeline stage StressChecker completed in 17.93s
Shutdown handler de-registered
chaiml-llama-8b-pairwis_8189_v39 status is now deployed due to DeploymentManager action
chaiml-llama-8b-pairwis_8189_v39 status is now inactive due to auto deactivation removed underperforming models