submission_id: frank2030-hathor-stable-_7646_v2
developer_uid: frank2030
status: inactive
model_repo: frank2030/Hathor_Stable-v0.2-L3-8B
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
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': 16, 'max_output_tokens': 64}
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}
reward_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}
timestamp: 2024-07-09T00:25:18+00:00
model_name: frank2030-hathor-stable-_7646_v2
model_group: frank2030/Hathor_Stable-
num_battles: 29210
num_wins: 15057
celo_rating: 1205.02
alignment_score: None
alignment_samples: 0
propriety_score: 0.6957542555272941
propriety_total_count: 5111.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: frank2030-hathor-stable-_7646_v2
ineligible_reason: None
language_model: frank2030/Hathor_Stable-v0.2-L3-8B
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-07-08
win_ratio: 0.5154741526874358
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name frank2030-hathor-stable-7646-v2-mkmlizer
Waiting for job on frank2030-hathor-stable-7646-v2-mkmlizer to finish
frank2030-hathor-stable-7646-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
frank2030-hathor-stable-7646-v2-mkmlizer: ║ _____ __ __ ║
frank2030-hathor-stable-7646-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
frank2030-hathor-stable-7646-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
frank2030-hathor-stable-7646-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
frank2030-hathor-stable-7646-v2-mkmlizer: ║ /___/ ║
frank2030-hathor-stable-7646-v2-mkmlizer: ║ ║
frank2030-hathor-stable-7646-v2-mkmlizer: ║ Version: 0.8.14 ║
frank2030-hathor-stable-7646-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
frank2030-hathor-stable-7646-v2-mkmlizer: ║ https://mk1.ai ║
frank2030-hathor-stable-7646-v2-mkmlizer: ║ ║
frank2030-hathor-stable-7646-v2-mkmlizer: ║ The license key for the current software has been verified as ║
frank2030-hathor-stable-7646-v2-mkmlizer: ║ belonging to: ║
frank2030-hathor-stable-7646-v2-mkmlizer: ║ ║
frank2030-hathor-stable-7646-v2-mkmlizer: ║ Chai Research Corp. ║
frank2030-hathor-stable-7646-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
frank2030-hathor-stable-7646-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
frank2030-hathor-stable-7646-v2-mkmlizer: ║ ║
frank2030-hathor-stable-7646-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
frank2030-hathor-stable-7646-v2-mkmlizer: Downloaded to shared memory in 17.664s
frank2030-hathor-stable-7646-v2-mkmlizer: quantizing model to /dev/shm/model_cache
frank2030-hathor-stable-7646-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
frank2030-hathor-stable-7646-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:02, 123.25it/s] Loading 0: 10%|█ | 30/291 [00:00<00:01, 137.39it/s] Loading 0: 15%|█▌ | 44/291 [00:00<00:01, 133.78it/s] Loading 0: 20%|█▉ | 58/291 [00:00<00:01, 132.19it/s] Loading 0: 26%|██▌ | 75/291 [00:00<00:01, 137.60it/s] Loading 0: 31%|███ | 89/291 [00:00<00:02, 84.87it/s] Loading 0: 36%|███▌ | 104/291 [00:00<00:01, 96.91it/s] Loading 0: 42%|████▏ | 122/291 [00:01<00:01, 114.32it/s] Loading 0: 48%|████▊ | 140/291 [00:01<00:01, 128.16it/s] Loading 0: 54%|█████▍ | 158/291 [00:01<00:00, 139.80it/s] Loading 0: 62%|██████▏ | 179/291 [00:01<00:00, 157.59it/s] Loading 0: 67%|██████▋ | 196/291 [00:01<00:00, 105.57it/s] Loading 0: 73%|███████▎ | 212/291 [00:01<00:00, 115.23it/s] Loading 0: 79%|███████▉ | 230/291 [00:01<00:00, 129.10it/s] Loading 0: 85%|████████▌ | 248/291 [00:01<00:00, 140.69it/s] Loading 0: 91%|█████████▏| 266/291 [00:02<00:00, 149.32it/s] Loading 0: 98%|█████████▊| 285/291 [00:02<00:00, 159.40it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
frank2030-hathor-stable-7646-v2-mkmlizer: quantized model in 19.757s
frank2030-hathor-stable-7646-v2-mkmlizer: Processed model frank2030/Hathor_Stable-v0.2-L3-8B in 37.421s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
frank2030-hathor-stable-7646-v2-mkmlizer: creating bucket guanaco-mkml-models
frank2030-hathor-stable-7646-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
frank2030-hathor-stable-7646-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/frank2030-hathor-stable-7646-v2
frank2030-hathor-stable-7646-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/frank2030-hathor-stable-7646-v2/special_tokens_map.json
frank2030-hathor-stable-7646-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/frank2030-hathor-stable-7646-v2/tokenizer_config.json
frank2030-hathor-stable-7646-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/frank2030-hathor-stable-7646-v2/tokenizer.json
frank2030-hathor-stable-7646-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/frank2030-hathor-stable-7646-v2/config.json
frank2030-hathor-stable-7646-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/frank2030-hathor-stable-7646-v2/flywheel_model.0.safetensors
frank2030-hathor-stable-7646-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
frank2030-hathor-stable-7646-v2-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:919: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
frank2030-hathor-stable-7646-v2-mkmlizer: warnings.warn(
frank2030-hathor-stable-7646-v2-mkmlizer: /opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py:1132: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`.
frank2030-hathor-stable-7646-v2-mkmlizer: warnings.warn(
frank2030-hathor-stable-7646-v2-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:769: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
frank2030-hathor-stable-7646-v2-mkmlizer: warnings.warn(
frank2030-hathor-stable-7646-v2-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py:468: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
frank2030-hathor-stable-7646-v2-mkmlizer: warnings.warn(
Job frank2030-hathor-stable-7646-v2-mkmlizer completed after 77.52s with status: succeeded
Stopping job with name frank2030-hathor-stable-7646-v2-mkmlizer
Pipeline stage MKMLizer completed in 78.24s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service frank2030-hathor-stable-7646-v2
Waiting for inference service frank2030-hathor-stable-7646-v2 to be ready
Inference service frank2030-hathor-stable-7646-v2 ready after 40.27659225463867s
Pipeline stage ISVCDeployer completed in 46.66s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9867401123046875s
Received healthy response to inference request in 1.251450777053833s
Received healthy response to inference request in 1.2683603763580322s
Received healthy response to inference request in 1.2423758506774902s
Received healthy response to inference request in 1.287593126296997s
5 requests
0 failed requests
5th percentile: 1.2441908359527587
10th percentile: 1.2460058212280274
20th percentile: 1.2496357917785645
30th percentile: 1.2548326969146728
40th percentile: 1.2615965366363526
50th percentile: 1.2683603763580322
60th percentile: 1.2760534763336182
70th percentile: 1.2837465763092042
80th percentile: 1.4274225234985352
90th percentile: 1.7070813179016113
95th percentile: 1.8469107151031494
99th percentile: 1.9587742328643798
mean time: 1.407304048538208
Pipeline stage StressChecker completed in 7.72s
frank2030-hathor-stable-_7646_v2 status is now deployed due to DeploymentManager action
frank2030-hathor-stable-_7646_v2 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics