submission_id: shuttleai-shuttle-2-5-1-_5730_v1
developer_uid: Fizzarolli
alignment_samples: 0
best_of: 4
celo_rating: 1190.21
display_name: shuttleai-shuttle-2-5-1-_5730_v1
formatter: {'memory_template': '<|im_start|>system\n{memory}<|im_end|>\n', 'prompt_template': '<|im_start|>user\n{prompt}<|im_end|>\n', 'bot_template': '<|im_start|>assistant\n{bot_name}: {message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{user_name}: {message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n{bot_name}:', 'truncate_by_message': True}
generation_params: {'temperature': 1.25, 'top_p': 1.0, 'min_p': 0.1, 'top_k': 100, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|im_end|>'], 'max_input_tokens': 512, 'best_of': 4, 'max_output_tokens': 64, 'reward_max_token_input': 1024}
is_internal_developer: False
language_model: shuttleai/shuttle-2.5.1-mini-beta
max_input_tokens: 512
max_output_tokens: 64
model_architecture: MistralForCausalLM
model_group: shuttleai/shuttle-2.5.1-
model_name: shuttleai-shuttle-2-5-1-_5730_v1
model_num_parameters: 12772090880.0
model_repo: shuttleai/shuttle-2.5.1-mini-beta
model_size: 13B
num_battles: 13226
num_wins: 6453
propriety_score: 0.6902581182348043
propriety_total_count: 1201.0
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/reward_gpt2_medium_preference_24m_e2
status: torndown
submission_type: basic
timestamp: 2024-07-26T21:58:03+00:00
us_pacific_date: 2024-07-26
win_ratio: 0.4879026160592772
Download Preference Data
Resubmit model
Running pipeline stage MKMLizer
Starting job with name shuttleai-shuttle-2-5-1-5730-v1-mkmlizer
Waiting for job on shuttleai-shuttle-2-5-1-5730-v1-mkmlizer to finish
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
shuttleai-shuttle-2-5-1-5730-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
shuttleai-shuttle-2-5-1-5730-v1-mkmlizer: ║ _____ __ __ ║
shuttleai-shuttle-2-5-1-5730-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
shuttleai-shuttle-2-5-1-5730-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
shuttleai-shuttle-2-5-1-5730-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
shuttleai-shuttle-2-5-1-5730-v1-mkmlizer: ║ /___/ ║
shuttleai-shuttle-2-5-1-5730-v1-mkmlizer: ║ ║
shuttleai-shuttle-2-5-1-5730-v1-mkmlizer: ║ Version: 0.9.7 ║
shuttleai-shuttle-2-5-1-5730-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
shuttleai-shuttle-2-5-1-5730-v1-mkmlizer: ║ https://mk1.ai ║
shuttleai-shuttle-2-5-1-5730-v1-mkmlizer: ║ ║
shuttleai-shuttle-2-5-1-5730-v1-mkmlizer: ║ The license key for the current software has been verified as ║
shuttleai-shuttle-2-5-1-5730-v1-mkmlizer: ║ belonging to: ║
shuttleai-shuttle-2-5-1-5730-v1-mkmlizer: ║ ║
shuttleai-shuttle-2-5-1-5730-v1-mkmlizer: ║ Chai Research Corp. ║
shuttleai-shuttle-2-5-1-5730-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
shuttleai-shuttle-2-5-1-5730-v1-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
shuttleai-shuttle-2-5-1-5730-v1-mkmlizer: ║ ║
shuttleai-shuttle-2-5-1-5730-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
shuttleai-shuttle-2-5-1-5730-v1-mkmlizer: Downloaded to shared memory in 44.877s
shuttleai-shuttle-2-5-1-5730-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmps2fse_dm, device:0
shuttleai-shuttle-2-5-1-5730-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
shuttleai-shuttle-2-5-1-5730-v1-mkmlizer: quantized model in 35.507s
shuttleai-shuttle-2-5-1-5730-v1-mkmlizer: Processed model shuttleai/shuttle-2.5.1-mini-beta in 80.385s
shuttleai-shuttle-2-5-1-5730-v1-mkmlizer: creating bucket guanaco-mkml-models
shuttleai-shuttle-2-5-1-5730-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
shuttleai-shuttle-2-5-1-5730-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/shuttleai-shuttle-2-5-1-5730-v1
shuttleai-shuttle-2-5-1-5730-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/shuttleai-shuttle-2-5-1-5730-v1/config.json
shuttleai-shuttle-2-5-1-5730-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/shuttleai-shuttle-2-5-1-5730-v1/special_tokens_map.json
shuttleai-shuttle-2-5-1-5730-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/shuttleai-shuttle-2-5-1-5730-v1/tokenizer_config.json
shuttleai-shuttle-2-5-1-5730-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/shuttleai-shuttle-2-5-1-5730-v1/tokenizer.json
shuttleai-shuttle-2-5-1-5730-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/shuttleai-shuttle-2-5-1-5730-v1/flywheel_model.0.safetensors
shuttleai-shuttle-2-5-1-5730-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
shuttleai-shuttle-2-5-1-5730-v1-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:11, 32.25it/s] Loading 0: 4%|▎ | 13/363 [00:00<00:06, 52.50it/s] Loading 0: 5%|▌ | 19/363 [00:00<00:06, 49.70it/s] Loading 0: 7%|▋ | 25/363 [00:00<00:06, 50.25it/s] Loading 0: 9%|▊ | 31/363 [00:00<00:06, 52.55it/s] Loading 0: 10%|█ | 37/363 [00:00<00:06, 48.04it/s] Loading 0: 12%|█▏ | 42/363 [00:00<00:07, 45.37it/s] Loading 0: 13%|█▎ | 49/363 [00:00<00:06, 50.58it/s] Loading 0: 15%|█▌ | 55/363 [00:01<00:06, 48.97it/s] Loading 0: 17%|█▋ | 61/363 [00:01<00:08, 35.03it/s] Loading 0: 18%|█▊ | 66/363 [00:01<00:08, 35.56it/s] Loading 0: 20%|█▉ | 72/363 [00:01<00:07, 40.16it/s] Loading 0: 21%|██▏ | 78/363 [00:01<00:07, 39.22it/s] Loading 0: 23%|██▎ | 83/363 [00:01<00:07, 38.48it/s] Loading 0: 25%|██▍ | 90/363 [00:02<00:06, 44.26it/s] Loading 0: 26%|██▋ | 96/363 [00:02<00:06, 42.65it/s] Loading 0: 28%|██▊ | 101/363 [00:02<00:06, 42.36it/s] Loading 0: 30%|███ | 109/363 [00:02<00:04, 50.86it/s] Loading 0: 32%|███▏ | 115/363 [00:02<00:05, 46.74it/s] Loading 0: 33%|███▎ | 120/363 [00:02<00:05, 43.95it/s] Loading 0: 35%|███▍ | 126/363 [00:02<00:05, 45.86it/s] Loading 0: 36%|███▋ | 132/363 [00:02<00:05, 44.50it/s] Loading 0: 38%|███▊ | 137/363 [00:03<00:05, 42.60it/s] Loading 0: 39%|███▉ | 142/363 [00:03<00:06, 32.59it/s] Loading 0: 40%|████ | 146/363 [00:03<00:06, 33.91it/s] Loading 0: 41%|████▏ | 150/363 [00:03<00:06, 33.52it/s] Loading 0: 43%|████▎ | 156/363 [00:03<00:05, 39.64it/s] Loading 0: 44%|████▍ | 161/363 [00:03<00:04, 41.44it/s] Loading 0: 46%|████▌ | 166/363 [00:03<00:04, 43.41it/s] Loading 0: 47%|████▋ | 171/363 [00:04<00:04, 44.54it/s] Loading 0: 48%|████▊ | 176/363 [00:04<00:05, 36.93it/s] Loading 0: 51%|█████ | 184/363 [00:04<00:03, 45.43it/s] Loading 0: 52%|█████▏ | 190/363 [00:04<00:03, 44.54it/s] Loading 0: 54%|█████▎ | 195/363 [00:04<00:03, 44.06it/s] Loading 0: 56%|█████▌ | 202/363 [00:04<00:03, 49.41it/s] Loading 0: 57%|█████▋ | 208/363 [00:04<00:03, 46.80it/s] Loading 0: 59%|█████▊ | 213/363 [00:04<00:03, 45.54it/s] Loading 0: 60%|██████ | 219/363 [00:05<00:02, 49.10it/s] Loading 0: 62%|██████▏ | 225/363 [00:05<00:04, 32.25it/s] Loading 0: 63%|██████▎ | 230/363 [00:05<00:03, 34.01it/s] Loading 0: 66%|██████▌ | 238/363 [00:05<00:02, 42.16it/s] Loading 0: 67%|██████▋ | 244/363 [00:05<00:02, 42.11it/s] Loading 0: 69%|██████▊ | 249/363 [00:05<00:02, 41.80it/s] Loading 0: 71%|███████ | 256/363 [00:06<00:02, 46.80it/s] Loading 0: 72%|███████▏ | 262/363 [00:06<00:02, 45.81it/s] Loading 0: 74%|███████▎ | 267/363 [00:06<00:02, 44.59it/s] Loading 0: 75%|███████▌ | 273/363 [00:06<00:01, 47.35it/s] Loading 0: 77%|███████▋ | 278/363 [00:06<00:01, 46.13it/s] Loading 0: 78%|███████▊ | 283/363 [00:06<00:01, 46.88it/s] Loading 0: 80%|███████▉ | 289/363 [00:06<00:01, 43.36it/s] Loading 0: 81%|████████ | 294/363 [00:06<00:01, 41.37it/s] Loading 0: 82%|████████▏ | 299/363 [00:06<00:01, 43.00it/s] Loading 0: 84%|████████▎ | 304/363 [00:13<00:23, 2.47it/s] Loading 0: 85%|████████▍ | 308/363 [00:13<00:17, 3.21it/s] Loading 0: 86%|████████▌ | 312/363 [00:14<00:12, 4.13it/s] Loading 0: 88%|████████▊ | 320/363 [00:14<00:06, 6.91it/s] Loading 0: 90%|████████▉ | 325/363 [00:14<00:04, 9.05it/s] Loading 0: 91%|█████████ | 330/363 [00:14<00:02, 11.25it/s] Loading 0: 93%|█████████▎| 338/363 [00:14<00:01, 16.83it/s] Loading 0: 95%|█████████▍| 344/363 [00:14<00:00, 20.49it/s] Loading 0: 96%|█████████▌| 349/363 [00:14<00:00, 23.80it/s] Loading 0: 98%|█████████▊| 356/363 [00:14<00:00, 30.03it/s] Loading 0: 100%|█████████▉| 362/363 [00:15<00:00, 32.77it/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-2-5-1-5730-v1-mkmlizer: warnings.warn(
shuttleai-shuttle-2-5-1-5730-v1-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-2-5-1-5730-v1-mkmlizer: warnings.warn(
shuttleai-shuttle-2-5-1-5730-v1-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-2-5-1-5730-v1-mkmlizer: warnings.warn(
shuttleai-shuttle-2-5-1-5730-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
shuttleai-shuttle-2-5-1-5730-v1-mkmlizer: Saving duration: 0.321s
shuttleai-shuttle-2-5-1-5730-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 9.574s
shuttleai-shuttle-2-5-1-5730-v1-mkmlizer: creating bucket guanaco-reward-models
shuttleai-shuttle-2-5-1-5730-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
shuttleai-shuttle-2-5-1-5730-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/shuttleai-shuttle-2-5-1-5730-v1_reward
shuttleai-shuttle-2-5-1-5730-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/shuttleai-shuttle-2-5-1-5730-v1_reward/config.json
shuttleai-shuttle-2-5-1-5730-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/shuttleai-shuttle-2-5-1-5730-v1_reward/tokenizer_config.json
shuttleai-shuttle-2-5-1-5730-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/shuttleai-shuttle-2-5-1-5730-v1_reward/special_tokens_map.json
shuttleai-shuttle-2-5-1-5730-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/shuttleai-shuttle-2-5-1-5730-v1_reward/merges.txt
shuttleai-shuttle-2-5-1-5730-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/shuttleai-shuttle-2-5-1-5730-v1_reward/vocab.json
shuttleai-shuttle-2-5-1-5730-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/shuttleai-shuttle-2-5-1-5730-v1_reward/tokenizer.json
shuttleai-shuttle-2-5-1-5730-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/shuttleai-shuttle-2-5-1-5730-v1_reward/reward.tensors
Job shuttleai-shuttle-2-5-1-5730-v1-mkmlizer completed after 136.56s with status: succeeded
Stopping job with name shuttleai-shuttle-2-5-1-5730-v1-mkmlizer
Pipeline stage MKMLizer completed in 137.97s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.16s
Running pipeline stage ISVCDeployer
Creating inference service shuttleai-shuttle-2-5-1-5730-v1
Waiting for inference service shuttleai-shuttle-2-5-1-5730-v1 to be ready
Failed to get response for submission nothingiisreal-l3-1-8b-d_6951_v1: ('http://nothingiisreal-l3-1-8b-d-6951-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Failed to get response for submission nothingiisreal-l3-1-8b-d_6951_v1: ('http://nothingiisreal-l3-1-8b-d-6951-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Failed to get response for submission nothingiisreal-l3-1-8b-d_6951_v1: ('http://nothingiisreal-l3-1-8b-d-6951-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Inference service shuttleai-shuttle-2-5-1-5730-v1 ready after 91.12014627456665s
Pipeline stage ISVCDeployer completed in 92.77s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3771166801452637s
Received healthy response to inference request in 1.056760311126709s
Received healthy response to inference request in 1.5248723030090332s
Received healthy response to inference request in 1.5056066513061523s
Received healthy response to inference request in 1.5234098434448242s
5 requests
0 failed requests
5th percentile: 1.1465295791625976
10th percentile: 1.2362988471984864
20th percentile: 1.4158373832702638
30th percentile: 1.5091672897338868
40th percentile: 1.5162885665893555
50th percentile: 1.5234098434448242
60th percentile: 1.5239948272705077
70th percentile: 1.5245798110961915
80th percentile: 1.6953211784362794
90th percentile: 2.0362189292907718
95th percentile: 2.2066678047180175
99th percentile: 2.3430269050598143
mean time: 1.5975531578063964
Pipeline stage StressChecker completed in 8.77s
shuttleai-shuttle-2-5-1-_5730_v1 status is now deployed due to DeploymentManager action
shuttleai-shuttle-2-5-1-_5730_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of shuttleai-shuttle-2-5-1-_5730_v1
Running pipeline stage ISVCDeleter
Checking if service shuttleai-shuttle-2-5-1-5730-v1 is running
Tearing down inference service shuttleai-shuttle-2-5-1-5730-v1
Service shuttleai-shuttle-2-5-1-5730-v1 has been torndown
Pipeline stage ISVCDeleter completed in 5.99s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key shuttleai-shuttle-2-5-1-5730-v1/config.json from bucket guanaco-mkml-models
Deleting key shuttleai-shuttle-2-5-1-5730-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key shuttleai-shuttle-2-5-1-5730-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key shuttleai-shuttle-2-5-1-5730-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key shuttleai-shuttle-2-5-1-5730-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key shuttleai-shuttle-2-5-1-5730-v1_reward/config.json from bucket guanaco-reward-models
Deleting key shuttleai-shuttle-2-5-1-5730-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key shuttleai-shuttle-2-5-1-5730-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key shuttleai-shuttle-2-5-1-5730-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key shuttleai-shuttle-2-5-1-5730-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key shuttleai-shuttle-2-5-1-5730-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key shuttleai-shuttle-2-5-1-5730-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.16s
shuttleai-shuttle-2-5-1-_5730_v1 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics