submission_id: shuttleai-shuttle-2-5-mini_v5
developer_uid: xtristan
alignment_samples: 12102
alignment_score: -1.1286046771409233
best_of: 4
celo_rating: 1197.1
display_name: shuttleai-shuttle-2-5-mini_v5
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_v5
model_num_parameters: 12772090880.0
model_repo: shuttleai/shuttle-2.5-mini
model_size: 13B
num_battles: 12102
num_wins: 5676
propriety_score: 0.7105014191106906
propriety_total_count: 1057.0
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: 2024-08-11T22:57:56+00:00
us_pacific_date: 2024-08-11
win_ratio: 0.4690133862171542
Download Preference Data
Resubmit model
Running pipeline stage MKMLizer
Starting job with name shuttleai-shuttle-2-5-mini-v5-mkmlizer
Waiting for job on shuttleai-shuttle-2-5-mini-v5-mkmlizer to finish
shuttleai-shuttle-2-5-mini-v5-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
shuttleai-shuttle-2-5-mini-v5-mkmlizer: ║ _____ __ __ ║
shuttleai-shuttle-2-5-mini-v5-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
shuttleai-shuttle-2-5-mini-v5-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
shuttleai-shuttle-2-5-mini-v5-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
shuttleai-shuttle-2-5-mini-v5-mkmlizer: ║ /___/ ║
shuttleai-shuttle-2-5-mini-v5-mkmlizer: ║ ║
shuttleai-shuttle-2-5-mini-v5-mkmlizer: ║ Version: 0.9.9 ║
shuttleai-shuttle-2-5-mini-v5-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
shuttleai-shuttle-2-5-mini-v5-mkmlizer: ║ https://mk1.ai ║
shuttleai-shuttle-2-5-mini-v5-mkmlizer: ║ ║
shuttleai-shuttle-2-5-mini-v5-mkmlizer: ║ The license key for the current software has been verified as ║
shuttleai-shuttle-2-5-mini-v5-mkmlizer: ║ belonging to: ║
shuttleai-shuttle-2-5-mini-v5-mkmlizer: ║ ║
shuttleai-shuttle-2-5-mini-v5-mkmlizer: ║ Chai Research Corp. ║
shuttleai-shuttle-2-5-mini-v5-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
shuttleai-shuttle-2-5-mini-v5-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
shuttleai-shuttle-2-5-mini-v5-mkmlizer: ║ ║
shuttleai-shuttle-2-5-mini-v5-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
shuttleai-shuttle-2-5-mini-v5-mkmlizer: Downloaded to shared memory in 40.905s
shuttleai-shuttle-2-5-mini-v5-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp6ghwvzow, device:0
shuttleai-shuttle-2-5-mini-v5-mkmlizer: Saving flywheel model at /dev/shm/model_cache
shuttleai-shuttle-2-5-mini-v5-mkmlizer: quantized model in 36.304s
shuttleai-shuttle-2-5-mini-v5-mkmlizer: Processed model shuttleai/shuttle-2.5-mini in 77.210s
shuttleai-shuttle-2-5-mini-v5-mkmlizer: creating bucket guanaco-mkml-models
shuttleai-shuttle-2-5-mini-v5-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
shuttleai-shuttle-2-5-mini-v5-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/shuttleai-shuttle-2-5-mini-v5
shuttleai-shuttle-2-5-mini-v5-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/shuttleai-shuttle-2-5-mini-v5/config.json
shuttleai-shuttle-2-5-mini-v5-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/shuttleai-shuttle-2-5-mini-v5/special_tokens_map.json
shuttleai-shuttle-2-5-mini-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/shuttleai-shuttle-2-5-mini-v5/tokenizer_config.json
shuttleai-shuttle-2-5-mini-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/shuttleai-shuttle-2-5-mini-v5/tokenizer.json
shuttleai-shuttle-2-5-mini-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/shuttleai-shuttle-2-5-mini-v5/flywheel_model.0.safetensors
shuttleai-shuttle-2-5-mini-v5-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
shuttleai-shuttle-2-5-mini-v5-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:10, 33.45it/s] Loading 0: 4%|▎ | 13/363 [00:00<00:06, 52.40it/s] Loading 0: 5%|▌ | 19/363 [00:00<00:07, 46.63it/s] Loading 0: 7%|▋ | 24/363 [00:00<00:07, 44.79it/s] Loading 0: 9%|▊ | 31/363 [00:00<00:06, 50.81it/s] Loading 0: 10%|█ | 37/363 [00:00<00:07, 46.49it/s] Loading 0: 12%|█▏ | 42/363 [00:00<00:07, 43.64it/s] Loading 0: 13%|█▎ | 49/363 [00:01<00:06, 48.33it/s] Loading 0: 15%|█▌ | 55/363 [00:01<00:06, 45.48it/s] Loading 0: 17%|█▋ | 61/363 [00:01<00:08, 34.29it/s] Loading 0: 18%|█▊ | 65/363 [00:01<00:08, 33.86it/s] Loading 0: 20%|█▉ | 72/363 [00:01<00:07, 40.38it/s] Loading 0: 21%|██ | 77/363 [00:01<00:06, 42.56it/s] Loading 0: 23%|██▎ | 82/363 [00:01<00:07, 36.52it/s] Loading 0: 25%|██▍ | 90/363 [00:02<00:06, 44.16it/s] Loading 0: 26%|██▌ | 95/363 [00:02<00:05, 45.01it/s] Loading 0: 28%|██▊ | 100/363 [00:02<00:06, 38.24it/s] Loading 0: 29%|██▉ | 106/363 [00:02<00:05, 43.00it/s] Loading 0: 31%|███ | 112/363 [00:02<00:05, 47.06it/s] Loading 0: 33%|███▎ | 118/363 [00:02<00:06, 39.69it/s] Loading 0: 34%|███▍ | 125/363 [00:02<00:05, 45.84it/s] Loading 0: 36%|███▌ | 131/363 [00:03<00:04, 47.28it/s] Loading 0: 38%|███▊ | 137/363 [00:03<00:05, 39.96it/s] Loading 0: 39%|███▉ | 142/363 [00:03<00:07, 31.32it/s] Loading 0: 40%|████ | 146/363 [00:03<00:06, 32.55it/s] Loading 0: 41%|████▏ | 150/363 [00:03<00:06, 32.04it/s] Loading 0: 43%|████▎ | 156/363 [00:03<00:05, 37.87it/s] Loading 0: 44%|████▍ | 161/363 [00:03<00:05, 39.40it/s] Loading 0: 46%|████▌ | 166/363 [00:04<00:04, 40.87it/s] Loading 0: 47%|████▋ | 171/363 [00:04<00:04, 42.99it/s] Loading 0: 48%|████▊ | 176/363 [00:04<00:05, 36.03it/s] Loading 0: 51%|█████ | 184/363 [00:04<00:04, 44.10it/s] Loading 0: 52%|█████▏ | 190/363 [00:04<00:04, 42.12it/s] Loading 0: 54%|█████▎ | 195/363 [00:04<00:04, 41.49it/s] Loading 0: 56%|█████▌ | 202/363 [00:04<00:03, 46.11it/s] Loading 0: 57%|█████▋ | 208/363 [00:05<00:03, 43.44it/s] Loading 0: 59%|█████▊ | 213/363 [00:05<00:03, 40.98it/s] Loading 0: 60%|██████ | 218/363 [00:05<00:03, 42.40it/s] Loading 0: 61%|██████▏ | 223/363 [00:05<00:04, 32.29it/s] Loading 0: 63%|██████▎ | 227/363 [00:05<00:04, 32.61it/s] Loading 0: 64%|██████▎ | 231/363 [00:05<00:04, 31.60it/s] Loading 0: 65%|██████▌ | 237/363 [00:05<00:03, 37.68it/s] Loading 0: 67%|██████▋ | 242/363 [00:06<00:03, 39.43it/s] Loading 0: 68%|██████▊ | 247/363 [00:06<00:02, 39.89it/s] Loading 0: 70%|██████▉ | 253/363 [00:06<00:02, 39.47it/s] Loading 0: 71%|███████ | 258/363 [00:06<00:02, 39.33it/s] Loading 0: 73%|███████▎ | 264/363 [00:06<00:02, 43.87it/s] Loading 0: 74%|███████▍ | 269/363 [00:06<00:02, 44.11it/s] Loading 0: 75%|███████▌ | 274/363 [00:06<00:01, 44.76it/s] Loading 0: 77%|███████▋ | 280/363 [00:06<00:01, 42.86it/s] Loading 0: 79%|███████▊ | 285/363 [00:07<00:01, 41.65it/s] Loading 0: 80%|████████ | 291/363 [00:07<00:01, 44.62it/s] Loading 0: 82%|████████▏ | 296/363 [00:07<00:01, 43.83it/s] Loading 0: 83%|████████▎ | 302/363 [00:07<00:01, 47.71it/s] Loading 0: 85%|████████▍ | 307/363 [00:14<00:22, 2.50it/s] Loading 0: 86%|████████▌ | 312/363 [00:14<00:15, 3.38it/s] Loading 0: 88%|████████▊ | 320/363 [00:14<00:07, 5.40it/s] Loading 0: 90%|████████▉ | 325/363 [00:14<00:05, 7.03it/s] Loading 0: 91%|█████████ | 330/363 [00:14<00:03, 8.79it/s] Loading 0: 93%|█████████▎| 337/363 [00:14<00:02, 12.67it/s] Loading 0: 94%|█████████▍| 342/363 [00:15<00:01, 15.58it/s] Loading 0: 96%|█████████▌| 347/363 [00:15<00:00, 19.11it/s] Loading 0: 97%|█████████▋| 353/363 [00:15<00:00, 22.86it/s] Loading 0: 99%|█████████▊| 358/363 [00:15<00:00, 25.33it/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-v5-mkmlizer: warnings.warn(
shuttleai-shuttle-2-5-mini-v5-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-v5-mkmlizer: warnings.warn(
shuttleai-shuttle-2-5-mini-v5-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-v5-mkmlizer: warnings.warn(
shuttleai-shuttle-2-5-mini-v5-mkmlizer: Downloading shards: 0%| | 0/2 [00:00<?, ?it/s] Downloading shards: 50%|█████ | 1/2 [00:05<00:05, 5.37s/it] Downloading shards: 100%|██████████| 2/2 [00:08<00:00, 3.95s/it] Downloading shards: 100%|██████████| 2/2 [00:08<00:00, 4.17s/it]
shuttleai-shuttle-2-5-mini-v5-mkmlizer: Loading checkpoint shards: 0%| | 0/2 [00:00<?, ?it/s] Loading checkpoint shards: 50%|█████ | 1/2 [00:00<00:00, 2.31it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 3.76it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 3.44it/s]
shuttleai-shuttle-2-5-mini-v5-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
shuttleai-shuttle-2-5-mini-v5-mkmlizer: Saving duration: 1.382s
shuttleai-shuttle-2-5-mini-v5-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 13.418s
shuttleai-shuttle-2-5-mini-v5-mkmlizer: creating bucket guanaco-reward-models
shuttleai-shuttle-2-5-mini-v5-mkmlizer: Bucket 's3://guanaco-reward-models/' created
shuttleai-shuttle-2-5-mini-v5-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/shuttleai-shuttle-2-5-mini-v5_reward
shuttleai-shuttle-2-5-mini-v5-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/shuttleai-shuttle-2-5-mini-v5_reward/vocab.json
shuttleai-shuttle-2-5-mini-v5-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/shuttleai-shuttle-2-5-mini-v5_reward/tokenizer.json
shuttleai-shuttle-2-5-mini-v5-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/shuttleai-shuttle-2-5-mini-v5_reward/reward.tensors
Job shuttleai-shuttle-2-5-mini-v5-mkmlizer completed after 125.9s with status: succeeded
Stopping job with name shuttleai-shuttle-2-5-mini-v5-mkmlizer
Pipeline stage MKMLizer completed in 126.83s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service shuttleai-shuttle-2-5-mini-v5
Waiting for inference service shuttleai-shuttle-2-5-mini-v5 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service shuttleai-shuttle-2-5-mini-v5 ready after 201.2101490497589s
Pipeline stage ISVCDeployer completed in 204.07s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.336437225341797s
Received healthy response to inference request in 1.5259709358215332s
Received healthy response to inference request in 1.5127758979797363s
Received healthy response to inference request in 1.4734930992126465s
Received healthy response to inference request in 1.3590972423553467s
5 requests
0 failed requests
5th percentile: 1.3819764137268067
10th percentile: 1.4048555850982667
20th percentile: 1.4506139278411865
30th percentile: 1.4813496589660644
40th percentile: 1.4970627784729005
50th percentile: 1.5127758979797363
60th percentile: 1.518053913116455
70th percentile: 1.5233319282531739
80th percentile: 1.688064193725586
90th percentile: 2.0122507095336912
95th percentile: 2.174343967437744
99th percentile: 2.3040185737609864
mean time: 1.641554880142212
Pipeline stage StressChecker completed in 8.98s
shuttleai-shuttle-2-5-mini_v5 status is now deployed due to DeploymentManager action
shuttleai-shuttle-2-5-mini_v5 status is now inactive due to auto deactivation removed underperforming models
shuttleai-shuttle-2-5-mini_v5 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics