submission_id: chaiml-llama-8b-pairwise_8189_v4
developer_uid: chai_backend_admin
best_of: 1
celo_rating: 1223.83
display_name: chaiml-llama-8b-pairwise_8189_v4
family_friendly_score: 0.0
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-pairwise_8189_v4
model_num_parameters: 8030261248.0
model_repo: ChaiML/llama_8b_pairwise_64m_256_tokens_step_249984
model_size: 8B
num_battles: 9912
num_wins: 4895
ranking_group: single
status: torndown
submission_type: basic
timestamp: 2024-08-15T13:33:00+00:00
us_pacific_date: 2024-08-15
win_ratio: 0.4938458434221146
Resubmit model
Running pipeline stage MKMLizer
Starting job with name chaiml-llama-8b-pairwise-8189-v4-mkmlizer
Waiting for job on chaiml-llama-8b-pairwise-8189-v4-mkmlizer to finish
chaiml-llama-8b-pairwise-8189-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-llama-8b-pairwise-8189-v4-mkmlizer: ║ _____ __ __ ║
chaiml-llama-8b-pairwise-8189-v4-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-llama-8b-pairwise-8189-v4-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-llama-8b-pairwise-8189-v4-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-llama-8b-pairwise-8189-v4-mkmlizer: ║ /___/ ║
chaiml-llama-8b-pairwise-8189-v4-mkmlizer: ║ ║
chaiml-llama-8b-pairwise-8189-v4-mkmlizer: ║ Version: 0.9.11 ║
chaiml-llama-8b-pairwise-8189-v4-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-llama-8b-pairwise-8189-v4-mkmlizer: ║ https://mk1.ai ║
chaiml-llama-8b-pairwise-8189-v4-mkmlizer: ║ ║
chaiml-llama-8b-pairwise-8189-v4-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-llama-8b-pairwise-8189-v4-mkmlizer: ║ belonging to: ║
chaiml-llama-8b-pairwise-8189-v4-mkmlizer: ║ ║
chaiml-llama-8b-pairwise-8189-v4-mkmlizer: ║ Chai Research Corp. ║
chaiml-llama-8b-pairwise-8189-v4-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-llama-8b-pairwise-8189-v4-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
chaiml-llama-8b-pairwise-8189-v4-mkmlizer: ║ ║
chaiml-llama-8b-pairwise-8189-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-llama-8b-pairwise-8189-v4-mkmlizer: Downloaded to shared memory in 23.537s
chaiml-llama-8b-pairwise-8189-v4-mkmlizer: quantizing model to /dev/shm/model_cache, profile:t0, folder:/tmp/tmpqorx3ab1, device:0
chaiml-llama-8b-pairwise-8189-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-llama-8b-pairwise-8189-v4-mkmlizer: quantized model in 82.951s
chaiml-llama-8b-pairwise-8189-v4-mkmlizer: Processed model ChaiML/llama_8b_pairwise_64m_256_tokens_step_249984 in 106.488s
chaiml-llama-8b-pairwise-8189-v4-mkmlizer: creating bucket guanaco-mkml-models
chaiml-llama-8b-pairwise-8189-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-llama-8b-pairwise-8189-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-llama-8b-pairwise-8189-v4
chaiml-llama-8b-pairwise-8189-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-llama-8b-pairwise-8189-v4/config.json
chaiml-llama-8b-pairwise-8189-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-llama-8b-pairwise-8189-v4/special_tokens_map.json
chaiml-llama-8b-pairwise-8189-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-llama-8b-pairwise-8189-v4/tokenizer_config.json
chaiml-llama-8b-pairwise-8189-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-llama-8b-pairwise-8189-v4/tokenizer.json
chaiml-llama-8b-pairwise-8189-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-llama-8b-pairwise-8189-v4/flywheel_model.0.safetensors
chaiml-llama-8b-pairwise-8189-v4-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 3/291 [00:00<00:54, 5.26it/s] Loading 0: 1%|▏ | 4/291 [00:01<01:29, 3.21it/s] Loading 0: 2%|▏ | 5/291 [00:01<01:58, 2.41it/s] Loading 0: 3%|▎ | 8/291 [00:01<01:01, 4.60it/s] Loading 0: 3%|▎ | 9/291 [00:02<01:00, 4.66it/s] Loading 0: 4%|▍ | 11/291 [00:02<00:42, 6.57it/s] Loading 0: 4%|▍ | 13/291 [00:03<01:23, 3.34it/s] Loading 0: 5%|▍ | 14/291 [00:04<01:41, 2.72it/s] Loading 0: 6%|▌ | 17/291 [00:04<01:02, 4.36it/s] Loading 0: 6%|▌ | 18/291 [00:04<00:59, 4.59it/s] Loading 0: 7%|▋ | 21/291 [00:05<00:59, 4.50it/s] Loading 0: 8%|▊ | 22/291 [00:05<01:15, 3.55it/s] Loading 0: 8%|▊ | 23/291 [00:06<01:34, 2.83it/s] Loading 0: 9%|▉ | 26/291 [00:06<00:58, 4.49it/s] Loading 0: 9%|▉ | 27/291 [00:06<00:55, 4.72it/s] Loading 0: 10%|█ | 30/291 [00:07<00:56, 4.62it/s] Loading 0: 11%|█ | 31/291 [00:07<01:11, 3.62it/s] Loading 0: 11%|█ | 32/291 [00:08<01:29, 2.88it/s] Loading 0: 12%|█▏ | 35/291 [00:08<00:56, 4.57it/s] Loading 0: 12%|█▏ | 36/291 [00:08<00:53, 4.79it/s] Loading 0: 13%|█▎ | 39/291 [00:09<00:54, 4.66it/s] Loading 0: 14%|█▎ | 40/291 [00:10<01:08, 3.64it/s] Loading 0: 14%|█▍ | 41/291 [00:10<01:26, 2.89it/s] Loading 0: 15%|█▌ | 44/291 [00:11<00:54, 4.57it/s] Loading 0: 15%|█▌ | 45/291 [00:11<00:51, 4.79it/s] Loading 0: 16%|█▌ | 46/291 [00:11<00:45, 5.34it/s] Loading 0: 16%|█▋ | 48/291 [00:11<00:54, 4.49it/s] Loading 0: 17%|█▋ | 49/291 [00:12<01:11, 3.40it/s] Loading 0: 17%|█▋ | 50/291 [00:13<01:29, 2.68it/s] Loading 0: 18%|█▊ | 53/291 [00:13<00:52, 4.51it/s] Loading 0: 19%|█▊ | 54/291 [00:13<00:49, 4.75it/s] Loading 0: 19%|█▉ | 55/291 [00:13<00:44, 5.35it/s] Loading 0: 20%|█▉ | 57/291 [00:14<00:52, 4.48it/s] Loading 0: 20%|█▉ | 58/291 [00:14<01:08, 3.38it/s] Loading 0: 20%|██ | 59/291 [00:15<01:27, 2.66it/s] Loading 0: 21%|██▏ | 62/291 [00:15<00:50, 4.50it/s] Loading 0: 22%|██▏ | 63/291 [00:15<00:48, 4.74it/s] Loading 0: 22%|██▏ | 64/291 [00:15<00:42, 5.31it/s] Loading 0: 23%|██▎ | 66/291 [00:16<00:50, 4.46it/s] Loading 0: 23%|██▎ | 67/291 [00:16<01:06, 3.36it/s] Loading 0: 23%|██▎ | 68/291 [00:17<01:24, 2.65it/s] Loading 0: 24%|██▍ | 71/291 [00:17<00:48, 4.55it/s] Loading 0: 25%|██▍ | 72/291 [00:17<00:45, 4.78it/s] Loading 0: 25%|██▌ | 73/291 [00:17<00:40, 5.36it/s] Loading 0: 26%|██▌ | 75/291 [00:18<00:48, 4.48it/s] Loading 0: 26%|██▌ | 76/291 [00:19<01:03, 3.38it/s] Loading 0: 26%|██▋ | 77/291 [00:19<01:20, 2.66it/s] Loading 0: 27%|██▋ | 80/291 [00:19<00:46, 4.56it/s] Loading 0: 28%|██▊ | 81/291 [00:20<00:43, 4.79it/s] Loading 0: 29%|██▊ | 83/291 [00:20<00:37, 5.53it/s] Loading 0: 29%|██▉ | 84/291 [00:20<00:53, 3.87it/s] Loading 0: 29%|██▉ | 85/291 [00:21<01:07, 3.06it/s] Loading 0: 30%|██▉ | 86/291 [00:22<01:22, 2.50it/s] Loading 0: 31%|███ | 89/291 [00:22<00:46, 4.33it/s] Loading 0: 31%|███ | 90/291 [00:22<00:43, 4.59it/s] Loading 0: 31%|███▏ | 91/291 [00:22<00:38, 5.19it/s] Loading 0: 32%|███▏ | 93/291 [00:23<00:45, 4.40it/s] Loading 0: 32%|███▏ | 94/291 [00:23<00:59, 3.33it/s] Loading 0: 33%|███▎ | 95/291 [00:24<01:14, 2.63it/s] Loading 0: 34%|███▎ | 98/291 [00:24<00:43, 4.48it/s] Loading 0: 34%|███▍ | 99/291 [00:24<00:40, 4.72it/s] Loading 0: 35%|███▌ | 102/291 [00:25<00:40, 4.62it/s] Loading 0: 35%|███▌ | 103/291 [00:25<00:52, 3.60it/s] Loading 0: 36%|███▌ | 104/291 [00:26<01:05, 2.85it/s] Loading 0: 37%|███▋ | 107/291 [00:26<00:40, 4.59it/s] Loading 0: 37%|███▋ | 108/291 [00:26<00:38, 4.81it/s] Loading 0: 38%|███▊ | 111/291 [00:27<00:38, 4.68it/s] Loading 0: 38%|███▊ | 112/291 [00:28<00:49, 3.65it/s] Loading 0: 39%|███▉ | 113/291 [00:28<01:01, 2.91it/s] Loading 0: 40%|███▉ | 116/291 [00:29<00:37, 4.65it/s] Loading 0: 40%|████ | 117/291 [00:29<00:35, 4.86it/s] Loading 0: 41%|████ | 120/291 [00:29<00:36, 4.72it/s] Loading 0: 42%|████▏ | 121/291 [00:30<00:46, 3.68it/s] Loading 0: 42%|████▏ | 122/291 [00:31<00:57, 2.92it/s] Loading 0: 43%|████▎ | 125/291 [00:31<00:35, 4.62it/s] Loading 0: 43%|████▎ | 126/291 [00:31<00:34, 4.84it/s] Loading 0: 44%|████▎ | 127/291 [00:31<00:30, 5.40it/s] Loading 0: 44%|████▍ | 129/291 [00:32<00:35, 4.53it/s] Loading 0: 45%|████▍ | 130/291 [00:32<00:47, 3.42it/s] Loading 0: 45%|████▌ | 131/291 [00:33<00:59, 2.70it/s] Loading 0: 46%|████▌ | 134/291 [00:33<00:34, 4.59it/s] Loading 0: 46%|████▋ | 135/291 [00:33<00:32, 4.82it/s] Loading 0: 47%|████▋ | 136/291 [00:33<00:28, 5.41it/s] Loading 0: 47%|████▋ | 138/291 [00:34<00:33, 4.51it/s] Loading 0: 48%|████▊ | 139/291 [00:34<00:44, 3.39it/s] Loading 0: 48%|████▊ | 140/291 [00:35<00:56, 2.69it/s] Loading 0: 49%|████▉ | 143/291 [00:35<00:32, 4.55it/s] Loading 0: 49%|████▉ | 144/291 [00:35<00:30, 4.79it/s] Loading 0: 51%|█████ | 147/291 [00:36<00:30, 4.68it/s] Loading 0: 51%|█████ | 148/291 [00:37<00:39, 3.64it/s] Loading 0: 51%|█████ | 149/291 [00:37<00:49, 2.90it/s] Loading 0: 52%|█████▏ | 152/291 [00:37<00:30, 4.62it/s] Loading 0: 53%|█████▎ | 153/291 [00:38<00:28, 4.83it/s] Loading 0: 53%|█████▎ | 154/291 [00:38<00:25, 5.34it/s] Loading 0: 54%|█████▎ | 156/291 [00:38<00:29, 4.51it/s] Loading 0: 54%|█████▍ | 157/291 [00:39<00:39, 3.42it/s] Loading 0: 54%|█████▍ | 158/291 [00:39<00:48, 2.72it/s] Loading 0: 55%|█████▌ | 161/291 [00:40<00:28, 4.57it/s] Loading 0: 56%|█████▌ | 162/291 [00:40<00:26, 4.81it/s] Loading 0: 57%|█████▋ | 165/291 [00:40<00:26, 4.70it/s] Loading 0: 57%|█████▋ | 166/291 [00:41<00:34, 3.65it/s] Loading 0: 57%|█████▋ | 167/291 [00:42<00:42, 2.89it/s] Loading 0: 58%|█████▊ | 170/291 [00:42<00:25, 4.66it/s] Loading 0: 59%|█████▉ | 171/291 [00:42<00:24, 4.87it/s] Loading 0: 59%|█████▉ | 173/291 [00:43<00:29, 4.04it/s] Loading 0: 60%|██████ | 175/291 [00:43<00:22, 5.09it/s] Loading 0: 60%|██████ | 176/291 [00:43<00:21, 5.27it/s] Loading 0: 62%|██████▏ | 179/291 [00:44<00:22, 4.93it/s] Loading 0: 62%|██████▏ | 180/291 [00:44<00:29, 3.76it/s] Loading 0: 62%|██████▏ | 181/291 [00:45<00:37, 2.97it/s] Loading 0: 63%|██████▎ | 184/291 [00:45<00:22, 4.72it/s] Loading 0: 64%|██████▎ | 185/291 [00:45<00:21, 4.93it/s] Loading 0: 64%|██████▍ | 187/291 [00:45<00:18, 5.66it/s] Loading 0: 65%|██████▍ | 188/291 [00:46<00:25, 3.98it/s] Loading 0: 65%|██████▍ | 189/291 [00:47<00:33, 3.01it/s] Loading 0: 66%|██████▌ | 192/291 [00:47<00:25, 3.82it/s] Loading 0: 66%|██████▋ | 193/291 [00:48<00:31, 3.15it/s] Loading 0: 67%|██████▋ | 194/291 [00:48<00:36, 2.63it/s] Loading 0: 68%|██████▊ | 197/291 [00:49<00:21, 4.31it/s] Loading 0: 68%|██████▊ | 198/291 [00:49<00:20, 4.57it/s] Loading 0: 69%|██████▉ | 201/291 [00:49<00:19, 4.55it/s] Loading 0: 69%|██████▉ | 202/291 [00:50<00:24, 3.59it/s] Loading 0: 70%|██████▉ | 203/291 [00:51<00:30, 2.89it/s] Loading 0: 71%|███████ | 206/291 [00:51<00:18, 4.57it/s] Loading 0: 71%|███████ | 207/291 [00:51<00:17, 4.79it/s] Loading 0: 71%|███████▏ | 208/291 [00:51<00:15, 5.32it/s] Loading 0: 72%|███████▏ | 210/291 [00:52<00:17, 4.52it/s] Loading 0: 73%|███████▎ | 211/291 [00:52<00:23, 3.42it/s] Loading 0: 73%|███████▎ | 212/291 [00:53<00:28, 2.73it/s] Loading 0: 74%|███████▍ | 215/291 [00:53<00:16, 4.63it/s] Loading 0: 74%|███████▍ | 216/291 [00:53<00:15, 4.86it/s] Loading 0: 75%|███████▍ | 217/291 [00:53<00:13, 5.44it/s] Loading 0: 75%|███████▌ | 219/291 [00:54<00:15, 4.54it/s] Loading 0: 76%|███████▌ | 220/291 [00:54<00:20, 3.43it/s] Loading 0: 76%|███████▌ | 221/291 [00:55<00:25, 2.71it/s] Loading 0: 77%|███████▋ | 224/291 [00:55<00:14, 4.65it/s] Loading 0: 77%|███████▋ | 225/291 [00:55<00:13, 4.88it/s] Loading 0: 78%|███████▊ | 226/291 [00:55<00:11, 5.45it/s] Loading 0: 78%|███████▊ | 228/291 [00:56<00:13, 4.54it/s] Loading 0: 79%|███████▊ | 229/291 [00:56<00:18, 3.42it/s] Loading 0: 79%|███████▉ | 230/291 [00:57<00:22, 2.72it/s] Loading 0: 80%|████████ | 233/291 [00:57<00:12, 4.65it/s] Loading 0: 80%|████████ | 234/291 [00:57<00:11, 4.89it/s] Loading 0: 81%|████████ | 235/291 [00:58<00:10, 5.47it/s] Loading 0: 81%|████████▏ | 237/291 [00:58<00:11, 4.56it/s] Loading 0: 82%|████████▏ | 238/291 [00:59<00:15, 3.43it/s] Loading 0: 82%|████████▏ | 239/291 [00:59<00:19, 2.72it/s] Loading 0: 83%|████████▎ | 242/291 [00:59<00:10, 4.65it/s] Loading 0: 84%|████████▎ | 243/291 [01:00<00:09, 4.88it/s] Loading 0: 85%|████████▍ | 246/291 [01:00<00:09, 4.73it/s] Loading 0: 85%|████████▍ | 247/291 [01:01<00:11, 3.67it/s] Loading 0: 85%|████████▌ | 248/291 [01:01<00:14, 2.93it/s] Loading 0: 86%|████████▋ | 251/291 [01:02<00:08, 4.72it/s] Loading 0: 87%|████████▋ | 252/291 [01:02<00:07, 4.93it/s] Loading 0: 88%|████████▊ | 255/291 [01:02<00:07, 4.76it/s] Loading 0: 88%|████████▊ | 256/291 [01:03<00:09, 3.71it/s] Loading 0: 88%|████████▊ | 257/291 [01:04<00:11, 2.95it/s] Loading 0: 89%|████████▉ | 260/291 [01:04<00:06, 4.71it/s] Loading 0: 90%|████████▉ | 261/291 [01:04<00:06, 4.92it/s] Loading 0: 91%|█████████ | 264/291 [01:05<00:05, 4.75it/s] Loading 0: 91%|█████████ | 265/291 [01:05<00:07, 3.71it/s] Loading 0: 91%|█████████▏| 266/291 [01:06<00:08, 2.97it/s] Loading 0: 92%|█████████▏| 269/291 [01:06<00:04, 4.73it/s] Loading 0: 93%|█████████▎| 270/291 [01:06<00:04, 4.94it/s] Loading 0: 94%|█████████▍| 273/291 [01:07<00:03, 4.78it/s] Loading 0: 94%|█████████▍| 274/291 [01:07<00:04, 3.73it/s] Loading 0: 95%|█████████▍| 275/291 [01:08<00:05, 2.97it/s] Loading 0: 96%|█████████▌| 278/291 [01:08<00:02, 4.72it/s] Loading 0: 96%|█████████▌| 279/291 [01:08<00:02, 4.94it/s] Loading 0: 96%|█████████▌| 280/291 [01:08<00:02, 5.48it/s] Loading 0: 97%|█████████▋| 281/291 [01:09<00:02, 3.73it/s] Loading 0: 97%|█████████▋| 282/291 [01:10<00:03, 2.83it/s] Loading 0: 98%|█████████▊| 284/291 [01:10<00:01, 4.00it/s] Loading 0: 98%|█████████▊| 285/291 [01:10<00:01, 4.36it/s] Loading 0: 99%|█████████▊| 287/291 [01:10<00:00, 5.31it/s] Loading 0: 99%|█████████▉| 288/291 [01:11<00:00, 3.71it/s]
Job chaiml-llama-8b-pairwise-8189-v4-mkmlizer completed after 132.53s with status: succeeded
Stopping job with name chaiml-llama-8b-pairwise-8189-v4-mkmlizer
Pipeline stage MKMLizer completed in 134.27s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.43s
Running pipeline stage ISVCDeployer
Creating inference service chaiml-llama-8b-pairwise-8189-v4
Waiting for inference service chaiml-llama-8b-pairwise-8189-v4 to be ready
Inference service chaiml-llama-8b-pairwise-8189-v4 ready after 234.1633541584015s
Pipeline stage ISVCDeployer completed in 236.19s
Running pipeline stage StressChecker
HTTP Request: %s %s "%s %d %s"
Received healthy response to inference request in 7.588268041610718s
HTTP Request: %s %s "%s %d %s"
Received healthy response to inference request in 5.175404071807861s
HTTP Request: %s %s "%s %d %s"
Received healthy response to inference request in 5.463041067123413s
HTTP Request: %s %s "%s %d %s"
Received healthy response to inference request in 4.792937994003296s
HTTP Request: %s %s "%s %d %s"
Received healthy response to inference request in 4.2635178565979s
5 requests
0 failed requests
5th percentile: 4.36940188407898
10th percentile: 4.475285911560059
20th percentile: 4.687053966522217
30th percentile: 4.869431209564209
40th percentile: 5.022417640686035
50th percentile: 5.175404071807861
60th percentile: 5.290458869934082
70th percentile: 5.405513668060303
80th percentile: 5.888086462020874
90th percentile: 6.738177251815796
95th percentile: 7.1632226467132565
99th percentile: 7.503258962631225
mean time: 5.456633806228638
%s, retrying in %s seconds...
HTTP Request: %s %s "%s %d %s"
Received healthy response to inference request in 4.420948028564453s
HTTP Request: %s %s "%s %d %s"
Received healthy response to inference request in 5.231320858001709s
chaiml-llama-8b-pairwise_8189_v4 status is now inactive due to auto deactivation removed underperforming models
chaiml-llama-8b-pairwise_8189_v4 status is now torndown due to DeploymentManager action