submission_id: alsebay-smaid-v0-1_v7
developer_uid: robert_irvine
alignment_samples: 0
best_of: 1
celo_rating: 1143.96
display_name: alsebay-smaid-v0-1_v7
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': 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': 512, 'best_of': 1, 'max_output_tokens': 64, 'reward_max_token_input': 256}
is_internal_developer: True
language_model: Alsebay/SMaid-v0.1
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: Alsebay/SMaid-v0.1
model_name: alsebay-smaid-v0-1_v7
model_num_parameters: 8030261248.0
model_repo: Alsebay/SMaid-v0.1
model_size: 8B
num_battles: 178459
num_wins: 84301
propriety_score: 0.725515298937396
propriety_total_count: 15622.0
ranking_group: single
reward_formatter: {'bot_template': 'Bot: {message}\n', 'memory_template': '', 'prompt_template': '', 'response_template': 'Bot:', 'truncate_by_message': False, 'user_template': 'User: {message}\n'}
reward_repo: ChaiML/gpt2_xl_pairwise_89m_step_347634
status: torndown
submission_type: basic
timestamp: 2024-08-05T01:58:51+00:00
us_pacific_date: 2024-08-04
win_ratio: 0.47238301234457214
Download Preference Data
Resubmit model
Running pipeline stage MKMLizer
Starting job with name alsebay-smaid-v0-1-v7-mkmlizer
Waiting for job on alsebay-smaid-v0-1-v7-mkmlizer to finish
alsebay-smaid-v0-1-v7-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
alsebay-smaid-v0-1-v7-mkmlizer: ║ _____ __ __ ║
alsebay-smaid-v0-1-v7-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
alsebay-smaid-v0-1-v7-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
alsebay-smaid-v0-1-v7-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
alsebay-smaid-v0-1-v7-mkmlizer: ║ /___/ ║
alsebay-smaid-v0-1-v7-mkmlizer: ║ ║
alsebay-smaid-v0-1-v7-mkmlizer: ║ Version: 0.9.9 ║
alsebay-smaid-v0-1-v7-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
alsebay-smaid-v0-1-v7-mkmlizer: ║ https://mk1.ai ║
alsebay-smaid-v0-1-v7-mkmlizer: ║ ║
alsebay-smaid-v0-1-v7-mkmlizer: ║ The license key for the current software has been verified as ║
alsebay-smaid-v0-1-v7-mkmlizer: ║ belonging to: ║
alsebay-smaid-v0-1-v7-mkmlizer: ║ ║
alsebay-smaid-v0-1-v7-mkmlizer: ║ Chai Research Corp. ║
alsebay-smaid-v0-1-v7-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
alsebay-smaid-v0-1-v7-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
alsebay-smaid-v0-1-v7-mkmlizer: ║ ║
alsebay-smaid-v0-1-v7-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
alsebay-smaid-v0-1-v7-mkmlizer: Downloaded to shared memory in 39.172s
alsebay-smaid-v0-1-v7-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpnw_0gsau, device:0
alsebay-smaid-v0-1-v7-mkmlizer: Saving flywheel model at /dev/shm/model_cache
alsebay-smaid-v0-1-v7-mkmlizer: quantized model in 25.948s
alsebay-smaid-v0-1-v7-mkmlizer: Processed model Alsebay/SMaid-v0.1 in 65.121s
alsebay-smaid-v0-1-v7-mkmlizer: creating bucket guanaco-mkml-models
alsebay-smaid-v0-1-v7-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/alsebay-smaid-v0-1-v7/special_tokens_map.json
alsebay-smaid-v0-1-v7-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/alsebay-smaid-v0-1-v7/config.json
alsebay-smaid-v0-1-v7-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/alsebay-smaid-v0-1-v7/tokenizer_config.json
alsebay-smaid-v0-1-v7-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/alsebay-smaid-v0-1-v7/tokenizer.json
alsebay-smaid-v0-1-v7-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/alsebay-smaid-v0-1-v7/flywheel_model.0.safetensors
alsebay-smaid-v0-1-v7-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
alsebay-smaid-v0-1-v7-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<11:39, 2.42s/it] Loading 0: 2%|▏ | 6/291 [00:04<03:05, 1.54it/s] Loading 0: 4%|▍ | 13/291 [00:05<01:06, 4.20it/s] Loading 0: 7%|▋ | 20/291 [00:05<00:36, 7.47it/s] Loading 0: 9%|▊ | 25/291 [00:05<00:27, 9.72it/s] Loading 0: 11%|█▏ | 33/291 [00:05<00:17, 14.72it/s] Loading 0: 14%|█▍ | 42/291 [00:05<00:11, 20.88it/s] Loading 0: 17%|█▋ | 50/291 [00:05<00:08, 27.81it/s] Loading 0: 19%|█▉ | 56/291 [00:06<00:07, 30.79it/s] Loading 0: 21%|██▏ | 62/291 [00:06<00:07, 30.15it/s] Loading 0: 24%|██▎ | 69/291 [00:06<00:06, 33.04it/s] Loading 0: 26%|██▋ | 77/291 [00:06<00:05, 40.99it/s] Loading 0: 29%|██▊ | 83/291 [00:06<00:05, 41.11it/s] Loading 0: 30%|███ | 88/291 [00:06<00:04, 41.96it/s] Loading 0: 33%|███▎ | 95/291 [00:06<00:04, 48.23it/s] Loading 0: 35%|███▍ | 101/291 [00:06<00:04, 46.15it/s] Loading 0: 37%|███▋ | 107/291 [00:07<00:04, 39.31it/s] Loading 0: 39%|███▉ | 114/291 [00:07<00:04, 40.05it/s] Loading 0: 42%|████▏ | 122/291 [00:07<00:03, 47.29it/s] Loading 0: 44%|████▍ | 128/291 [00:07<00:03, 45.67it/s] Loading 0: 46%|████▌ | 133/291 [00:07<00:03, 46.34it/s] Loading 0: 48%|████▊ | 140/291 [00:07<00:02, 51.98it/s] Loading 0: 50%|█████ | 146/291 [00:08<00:03, 38.38it/s] Loading 0: 52%|█████▏ | 151/291 [00:08<00:03, 40.02it/s] Loading 0: 54%|█████▍ | 158/291 [00:08<00:02, 46.15it/s] Loading 0: 56%|█████▋ | 164/291 [00:08<00:02, 44.55it/s] Loading 0: 58%|█████▊ | 169/291 [00:08<00:02, 45.01it/s] Loading 0: 60%|██████ | 176/291 [00:08<00:02, 50.74it/s] Loading 0: 63%|██████▎ | 182/291 [00:08<00:02, 47.83it/s] Loading 0: 65%|██████▍ | 188/291 [00:09<00:02, 40.19it/s] Loading 0: 67%|██████▋ | 194/291 [00:09<00:02, 44.56it/s] Loading 0: 69%|██████▊ | 200/291 [00:09<00:02, 43.52it/s] Loading 0: 70%|███████ | 205/291 [00:09<00:02, 42.87it/s] Loading 0: 73%|███████▎ | 212/291 [00:09<00:01, 49.01it/s] Loading 0: 75%|███████▍ | 218/291 [00:09<00:01, 46.43it/s] Loading 0: 77%|███████▋ | 223/291 [00:09<00:01, 36.83it/s] Loading 0: 79%|███████▉ | 230/291 [00:09<00:01, 42.77it/s] Loading 0: 81%|████████ | 236/291 [00:10<00:01, 41.95it/s] Loading 0: 83%|████████▎ | 241/291 [00:10<00:01, 42.34it/s] Loading 0: 85%|████████▌ | 248/291 [00:10<00:00, 47.60it/s] Loading 0: 87%|████████▋ | 254/291 [00:10<00:00, 45.70it/s] Loading 0: 89%|████████▉ | 259/291 [00:10<00:00, 46.28it/s] Loading 0: 91%|█████████ | 265/291 [00:10<00:00, 41.28it/s] Loading 0: 93%|█████████▎| 271/291 [00:10<00:00, 45.33it/s] Loading 0: 95%|█████████▍| 276/291 [00:11<00:00, 40.43it/s] Loading 0: 98%|█████████▊| 284/291 [00:11<00:00, 48.11it/s] Loading 0: 100%|█████████▉| 290/291 [00:11<00:00, 44.90it/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.
alsebay-smaid-v0-1-v7-mkmlizer: warnings.warn(
alsebay-smaid-v0-1-v7-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.
alsebay-smaid-v0-1-v7-mkmlizer: warnings.warn(
alsebay-smaid-v0-1-v7-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.
alsebay-smaid-v0-1-v7-mkmlizer: warnings.warn(
alsebay-smaid-v0-1-v7-mkmlizer: Downloading shards: 0%| | 0/2 [00:00<?, ?it/s] Downloading shards: 50%|█████ | 1/2 [00:05<00:05, 5.21s/it] Downloading shards: 100%|██████████| 2/2 [00:07<00:00, 3.76s/it] Downloading shards: 100%|██████████| 2/2 [00:07<00:00, 3.98s/it]
alsebay-smaid-v0-1-v7-mkmlizer: Loading checkpoint shards: 0%| | 0/2 [00:00<?, ?it/s] Loading checkpoint shards: 50%|█████ | 1/2 [00:00<00:00, 2.45it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 4.04it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 3.68it/s]
alsebay-smaid-v0-1-v7-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
alsebay-smaid-v0-1-v7-mkmlizer: Saving duration: 1.314s
alsebay-smaid-v0-1-v7-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 12.956s
alsebay-smaid-v0-1-v7-mkmlizer: creating bucket guanaco-reward-models
alsebay-smaid-v0-1-v7-mkmlizer: Bucket 's3://guanaco-reward-models/' created
alsebay-smaid-v0-1-v7-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/alsebay-smaid-v0-1-v7_reward
alsebay-smaid-v0-1-v7-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/alsebay-smaid-v0-1-v7_reward/config.json
alsebay-smaid-v0-1-v7-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/alsebay-smaid-v0-1-v7_reward/special_tokens_map.json
alsebay-smaid-v0-1-v7-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/alsebay-smaid-v0-1-v7_reward/tokenizer_config.json
alsebay-smaid-v0-1-v7-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/alsebay-smaid-v0-1-v7_reward/merges.txt
alsebay-smaid-v0-1-v7-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/alsebay-smaid-v0-1-v7_reward/vocab.json
alsebay-smaid-v0-1-v7-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/alsebay-smaid-v0-1-v7_reward/tokenizer.json
alsebay-smaid-v0-1-v7-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/alsebay-smaid-v0-1-v7_reward/reward.tensors
Job alsebay-smaid-v0-1-v7-mkmlizer completed after 104.86s with status: succeeded
Stopping job with name alsebay-smaid-v0-1-v7-mkmlizer
Pipeline stage MKMLizer completed in 105.70s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service alsebay-smaid-v0-1-v7
Waiting for inference service alsebay-smaid-v0-1-v7 to be ready
Failed to get response for submission mistralai-mixtral-8x7b_3473_v108: ('http://mistralai-mixtral-8x7b-3473-v108-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'activator request timeout')
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service alsebay-smaid-v0-1-v7 ready after 171.02317357063293s
Pipeline stage ISVCDeployer completed in 173.32s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.7936532497406006s
Received healthy response to inference request in 1.0491797924041748s
Received healthy response to inference request in 1.0475080013275146s
Received healthy response to inference request in 0.949434757232666s
Received healthy response to inference request in 0.6306524276733398s
5 requests
0 failed requests
5th percentile: 0.6944088935852051
10th percentile: 0.7581653594970703
20th percentile: 0.8856782913208008
30th percentile: 0.9690494060516357
40th percentile: 1.0082787036895753
50th percentile: 1.0475080013275146
60th percentile: 1.0481767177581787
70th percentile: 1.0488454341888427
80th percentile: 1.19807448387146
90th percentile: 1.4958638668060305
95th percentile: 1.6447585582733153
99th percentile: 1.7638743114471436
mean time: 1.0940856456756591
Pipeline stage StressChecker completed in 6.18s
alsebay-smaid-v0-1_v7 status is now deployed due to DeploymentManager action
alsebay-smaid-v0-1_v7 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of alsebay-smaid-v0-1_v7
Running pipeline stage ISVCDeleter
Checking if service alsebay-smaid-v0-1-v7 is running
Tearing down inference service alsebay-smaid-v0-1-v7
Service alsebay-smaid-v0-1-v7 has been torndown
Pipeline stage ISVCDeleter completed in 5.69s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key alsebay-smaid-v0-1-v7/config.json from bucket guanaco-mkml-models
Deleting key alsebay-smaid-v0-1-v7/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key alsebay-smaid-v0-1-v7/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key alsebay-smaid-v0-1-v7/tokenizer.json from bucket guanaco-mkml-models
Deleting key alsebay-smaid-v0-1-v7/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key alsebay-smaid-v0-1-v7_reward/config.json from bucket guanaco-reward-models
Deleting key alsebay-smaid-v0-1-v7_reward/merges.txt from bucket guanaco-reward-models
Deleting key alsebay-smaid-v0-1-v7_reward/reward.tensors from bucket guanaco-reward-models
Deleting key alsebay-smaid-v0-1-v7_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key alsebay-smaid-v0-1-v7_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key alsebay-smaid-v0-1-v7_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key alsebay-smaid-v0-1-v7_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.53s
alsebay-smaid-v0-1_v7 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics