submission_id: shuttleai-shuttle-2-5-mini_v3
developer_uid: xtristan
alignment_samples: 12086
alignment_score: -1.150439841635557
best_of: 4
celo_rating: 1202.89
display_name: shuttleai-shuttle-2-5-mini_v3
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}
generation_params: {'temperature': 0.7, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 42, 'presence_penalty': 0.1, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 4, 'max_output_tokens': 64, 'reward_max_token_input': 128}
is_internal_developer: False
language_model: shuttleai/shuttle-2.5-mini
max_input_tokens: 512
max_output_tokens: 64
model_architecture: MistralForCausalLM
model_group: shuttleai/shuttle-2.5-mi
model_name: shuttleai-shuttle-2-5-mini_v3
model_num_parameters: 12772090880.0
model_repo: shuttleai/shuttle-2.5-mini
model_size: 13B
num_battles: 12086
num_wins: 5776
propriety_score: 0.7224371373307543
propriety_total_count: 1034.0
ranking_group: single
reward_formatter: {'bot_template': '{bot_name}: {message}\n', 'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'response_template': '{bot_name}:', 'truncate_by_message': False, 'user_template': '{user_name}: {message}\n'}
reward_repo: ChaiML/gpt2_xl_pairwise_89m_step_347634
status: torndown
submission_type: basic
timestamp: 2024-08-11T22:57:55+00:00
us_pacific_date: 2024-08-11
win_ratio: 0.47790832368029124
Download Preference Data
Resubmit model
Running pipeline stage MKMLizer
Starting job with name shuttleai-shuttle-2-5-mini-v3-mkmlizer
Waiting for job on shuttleai-shuttle-2-5-mini-v3-mkmlizer to finish
Stopping job with name shuttleai-shuttle-2-5-mini-v3-mkmlizer
%s, retrying in %s seconds...
Starting job with name shuttleai-shuttle-2-5-mini-v3-mkmlizer
Waiting for job on shuttleai-shuttle-2-5-mini-v3-mkmlizer to finish
shuttleai-shuttle-2-5-mini-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
shuttleai-shuttle-2-5-mini-v3-mkmlizer: ║ _____ __ __ ║
shuttleai-shuttle-2-5-mini-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
shuttleai-shuttle-2-5-mini-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
shuttleai-shuttle-2-5-mini-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
shuttleai-shuttle-2-5-mini-v3-mkmlizer: ║ /___/ ║
shuttleai-shuttle-2-5-mini-v3-mkmlizer: ║ ║
shuttleai-shuttle-2-5-mini-v3-mkmlizer: ║ Version: 0.9.9 ║
shuttleai-shuttle-2-5-mini-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
shuttleai-shuttle-2-5-mini-v3-mkmlizer: ║ https://mk1.ai ║
shuttleai-shuttle-2-5-mini-v3-mkmlizer: ║ ║
shuttleai-shuttle-2-5-mini-v3-mkmlizer: ║ The license key for the current software has been verified as ║
shuttleai-shuttle-2-5-mini-v3-mkmlizer: ║ belonging to: ║
shuttleai-shuttle-2-5-mini-v3-mkmlizer: ║ ║
shuttleai-shuttle-2-5-mini-v3-mkmlizer: ║ Chai Research Corp. ║
shuttleai-shuttle-2-5-mini-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
shuttleai-shuttle-2-5-mini-v3-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
shuttleai-shuttle-2-5-mini-v3-mkmlizer: ║ ║
shuttleai-shuttle-2-5-mini-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
shuttleai-shuttle-2-5-mini-v3-mkmlizer: Downloaded to shared memory in 37.645s
shuttleai-shuttle-2-5-mini-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpg2f56zz2, device:0
shuttleai-shuttle-2-5-mini-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
shuttleai-shuttle-2-5-mini-v3-mkmlizer: quantized model in 36.823s
shuttleai-shuttle-2-5-mini-v3-mkmlizer: Processed model shuttleai/shuttle-2.5-mini in 74.467s
shuttleai-shuttle-2-5-mini-v3-mkmlizer: creating bucket guanaco-mkml-models
shuttleai-shuttle-2-5-mini-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
shuttleai-shuttle-2-5-mini-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/shuttleai-shuttle-2-5-mini-v3
shuttleai-shuttle-2-5-mini-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/shuttleai-shuttle-2-5-mini-v3/config.json
shuttleai-shuttle-2-5-mini-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/shuttleai-shuttle-2-5-mini-v3/special_tokens_map.json
shuttleai-shuttle-2-5-mini-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/shuttleai-shuttle-2-5-mini-v3/tokenizer_config.json
shuttleai-shuttle-2-5-mini-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/shuttleai-shuttle-2-5-mini-v3/tokenizer.json
shuttleai-shuttle-2-5-mini-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/shuttleai-shuttle-2-5-mini-v3/flywheel_model.0.safetensors
shuttleai-shuttle-2-5-mini-v3-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
shuttleai-shuttle-2-5-mini-v3-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:11, 32.19it/s] Loading 0: 3%|▎ | 12/363 [00:00<00:07, 49.82it/s] Loading 0: 5%|▍ | 18/363 [00:00<00:06, 49.76it/s] Loading 0: 7%|▋ | 24/363 [00:00<00:08, 40.00it/s] Loading 0: 8%|▊ | 30/363 [00:00<00:07, 45.14it/s] Loading 0: 10%|▉ | 35/363 [00:00<00:07, 44.47it/s] Loading 0: 11%|█ | 40/363 [00:00<00:07, 43.99it/s] Loading 0: 12%|█▏ | 45/363 [00:01<00:07, 45.40it/s] Loading 0: 14%|█▍ | 50/363 [00:01<00:08, 37.14it/s] Loading 0: 16%|█▌ | 58/363 [00:01<00:06, 46.90it/s] Loading 0: 18%|█▊ | 64/363 [00:01<00:10, 28.83it/s] Loading 0: 20%|█▉ | 71/363 [00:01<00:08, 35.25it/s] Loading 0: 21%|██ | 76/363 [00:01<00:07, 36.47it/s] Loading 0: 22%|██▏ | 81/363 [00:02<00:07, 37.90it/s] Loading 0: 24%|██▎ | 86/363 [00:02<00:06, 39.82it/s] Loading 0: 25%|██▌ | 91/363 [00:02<00:07, 34.33it/s] Loading 0: 27%|██▋ | 98/363 [00:02<00:06, 41.06it/s] Loading 0: 28%|██▊ | 103/363 [00:02<00:06, 40.80it/s] Loading 0: 30%|██▉ | 108/363 [00:02<00:06, 41.64it/s] Loading 0: 31%|███ | 113/363 [00:02<00:07, 35.54it/s] Loading 0: 33%|███▎ | 118/363 [00:03<00:06, 35.80it/s] Loading 0: 34%|███▍ | 125/363 [00:03<00:05, 42.54it/s] Loading 0: 36%|███▌ | 130/363 [00:03<00:05, 42.31it/s] Loading 0: 37%|███▋ | 135/363 [00:03<00:05, 41.91it/s] Loading 0: 39%|███▊ | 140/363 [00:03<00:05, 43.00it/s] Loading 0: 40%|███▉ | 145/363 [00:03<00:08, 26.39it/s] Loading 0: 41%|████ | 149/363 [00:04<00:07, 27.12it/s] Loading 0: 43%|████▎ | 156/363 [00:04<00:05, 34.69it/s] Loading 0: 44%|████▍ | 161/363 [00:04<00:05, 35.55it/s] Loading 0: 46%|████▌ | 166/363 [00:04<00:05, 37.19it/s] Loading 0: 47%|████▋ | 171/363 [00:04<00:04, 39.33it/s] Loading 0: 48%|████▊ | 176/363 [00:04<00:05, 33.64it/s] Loading 0: 50%|█████ | 183/363 [00:04<00:04, 41.06it/s] Loading 0: 52%|█████▏ | 188/363 [00:04<00:04, 40.98it/s] Loading 0: 53%|█████▎ | 193/363 [00:05<00:04, 41.87it/s] Loading 0: 55%|█████▍ | 198/363 [00:05<00:03, 43.09it/s] Loading 0: 56%|█████▌ | 203/363 [00:05<00:04, 36.12it/s] Loading 0: 58%|█████▊ | 210/363 [00:05<00:03, 43.04it/s] Loading 0: 59%|█████▉ | 215/363 [00:05<00:03, 42.89it/s] Loading 0: 61%|██████ | 220/363 [00:05<00:03, 43.89it/s] Loading 0: 62%|██████▏ | 225/363 [00:06<00:05, 27.21it/s] Loading 0: 63%|██████▎ | 230/363 [00:06<00:04, 29.44it/s] Loading 0: 65%|██████▌ | 237/363 [00:06<00:03, 36.73it/s] Loading 0: 67%|██████▋ | 242/363 [00:06<00:03, 37.82it/s] Loading 0: 68%|██████▊ | 247/363 [00:06<00:02, 39.03it/s] Loading 0: 69%|██████▉ | 252/363 [00:06<00:02, 40.97it/s] Loading 0: 71%|███████ | 257/363 [00:06<00:03, 34.40it/s] Loading 0: 73%|███████▎ | 264/363 [00:06<00:02, 41.19it/s] Loading 0: 74%|███████▍ | 269/363 [00:07<00:02, 40.80it/s] Loading 0: 75%|███████▌ | 274/363 [00:07<00:02, 40.96it/s] Loading 0: 77%|███████▋ | 279/363 [00:07<00:01, 42.51it/s] Loading 0: 78%|███████▊ | 284/363 [00:07<00:02, 35.98it/s] Loading 0: 80%|████████ | 291/363 [00:07<00:01, 42.98it/s] Loading 0: 82%|████████▏ | 296/363 [00:07<00:01, 43.23it/s] Loading 0: 83%|████████▎ | 301/363 [00:07<00:01, 44.21it/s] Loading 0: 84%|████████▍ | 306/363 [00:14<00:22, 2.48it/s] Loading 0: 85%|████████▌ | 310/363 [00:14<00:16, 3.17it/s] Loading 0: 86%|████████▌ | 313/363 [00:14<00:12, 3.89it/s] Loading 0: 88%|████████▊ | 319/363 [00:14<00:07, 5.97it/s] Loading 0: 89%|████████▉ | 323/363 [00:15<00:05, 7.63it/s] Loading 0: 90%|█████████ | 328/363 [00:15<00:03, 10.42it/s] Loading 0: 91%|█████████▏| 332/363 [00:15<00:02, 12.81it/s] Loading 0: 93%|█████████▎| 338/363 [00:15<00:01, 17.58it/s] Loading 0: 94%|█████████▍| 343/363 [00:15<00:00, 21.69it/s] Loading 0: 96%|█████████▌| 348/363 [00:15<00:00, 22.79it/s] Loading 0: 98%|█████████▊| 355/363 [00:15<00:00, 30.46it/s] Loading 0: 99%|█████████▉| 360/363 [00:15<00:00, 33.53it/s] /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:957: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
shuttleai-shuttle-2-5-mini-v3-mkmlizer: warnings.warn(
shuttleai-shuttle-2-5-mini-v3-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:785: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
shuttleai-shuttle-2-5-mini-v3-mkmlizer: warnings.warn(
shuttleai-shuttle-2-5-mini-v3-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py:469: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
shuttleai-shuttle-2-5-mini-v3-mkmlizer: warnings.warn(
shuttleai-shuttle-2-5-mini-v3-mkmlizer: Downloading shards: 0%| | 0/2 [00:00<?, ?it/s] Downloading shards: 50%|█████ | 1/2 [00:05<00:05, 5.12s/it] Downloading shards: 100%|██████████| 2/2 [00:07<00:00, 3.70s/it] Downloading shards: 100%|██████████| 2/2 [00:07<00:00, 3.91s/it]
shuttleai-shuttle-2-5-mini-v3-mkmlizer: Loading checkpoint shards: 0%| | 0/2 [00:00<?, ?it/s] Loading checkpoint shards: 50%|█████ | 1/2 [00:00<00:00, 2.47it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 4.04it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 3.69it/s]
shuttleai-shuttle-2-5-mini-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
shuttleai-shuttle-2-5-mini-v3-mkmlizer: Saving duration: 1.340s
shuttleai-shuttle-2-5-mini-v3-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 13.042s
shuttleai-shuttle-2-5-mini-v3-mkmlizer: creating bucket guanaco-reward-models
shuttleai-shuttle-2-5-mini-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
shuttleai-shuttle-2-5-mini-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/shuttleai-shuttle-2-5-mini-v3_reward
shuttleai-shuttle-2-5-mini-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/shuttleai-shuttle-2-5-mini-v3_reward/merges.txt
shuttleai-shuttle-2-5-mini-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/shuttleai-shuttle-2-5-mini-v3_reward/vocab.json
shuttleai-shuttle-2-5-mini-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/shuttleai-shuttle-2-5-mini-v3_reward/tokenizer.json
shuttleai-shuttle-2-5-mini-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/shuttleai-shuttle-2-5-mini-v3_reward/reward.tensors
Job shuttleai-shuttle-2-5-mini-v3-mkmlizer completed after 126.61s with status: succeeded
Stopping job with name shuttleai-shuttle-2-5-mini-v3-mkmlizer
Pipeline stage MKMLizer completed in 128.29s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.13s
Running pipeline stage ISVCDeployer
Creating inference service shuttleai-shuttle-2-5-mini-v3
Waiting for inference service shuttleai-shuttle-2-5-mini-v3 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
Inference service shuttleai-shuttle-2-5-mini-v3 ready after 211.2927541732788s
Pipeline stage ISVCDeployer completed in 214.36s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.366929769515991s
Received healthy response to inference request in 1.5363438129425049s
Received healthy response to inference request in 1.5072472095489502s
Received healthy response to inference request in 1.654737949371338s
Received healthy response to inference request in 1.5188894271850586s
5 requests
0 failed requests
5th percentile: 1.509575653076172
10th percentile: 1.5119040966033936
20th percentile: 1.5165609836578369
30th percentile: 1.5223803043365478
40th percentile: 1.5293620586395265
50th percentile: 1.5363438129425049
60th percentile: 1.5837014675140382
70th percentile: 1.6310591220855712
80th percentile: 1.7971763134002687
90th percentile: 2.08205304145813
95th percentile: 2.2244914054870604
99th percentile: 2.338442096710205
mean time: 1.7168296337127686
Pipeline stage StressChecker completed in 9.38s
shuttleai-shuttle-2-5-mini_v3 status is now deployed due to DeploymentManager action
shuttleai-shuttle-2-5-mini_v3 status is now inactive due to auto deactivation removed underperforming models
shuttleai-shuttle-2-5-mini_v3 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics