submission_id: hastagaras-llama-3-8b-ok_5775_v1
developer_uid: Hastagaras
status: inactive
model_repo: Hastagaras/llama-3-8b-okay-two
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.0, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 200, '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': "<|start_header_id|>system<|end_header_id|>\n\n{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}<|eot_id|>', 'bot_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}: {message}<|eot_id|>', 'user_template': '<|start_header_id|>user<|end_header_id|>\n\n{user_name}: {message}<|eot_id|>', 'response_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}:', 'truncate_by_message': True}
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': True}
timestamp: 2024-05-18T10:48:31+00:00
model_name: okay-2
model_eval_status: success
model_group: Hastagaras/llama-3-8b-ok
num_battles: 12815
num_wins: 6682
celo_rating: 1192.03
safety_score: 0.97
propriety_score: 0.0
propriety_total_count: 0.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: okay-2
ineligible_reason: propriety_total_count < 5000
language_model: Hastagaras/llama-3-8b-okay-two
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-05-18
win_ratio: 0.521420210690597
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-llama-3-8b-ok-5775-v1-mkmlizer
Waiting for job on hastagaras-llama-3-8b-ok-5775-v1-mkmlizer to finish
Stopping job with name hastagaras-llama-3-8b-ok-5775-v1-mkmlizer
%s, retrying in %s seconds...
Starting job with name hastagaras-llama-3-8b-ok-5775-v1-mkmlizer
Waiting for job on hastagaras-llama-3-8b-ok-5775-v1-mkmlizer to finish
hastagaras-llama-3-8b-ok-5775-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-llama-3-8b-ok-5775-v1-mkmlizer: ║ _____ __ __ ║
hastagaras-llama-3-8b-ok-5775-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-llama-3-8b-ok-5775-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-llama-3-8b-ok-5775-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-llama-3-8b-ok-5775-v1-mkmlizer: ║ /___/ ║
hastagaras-llama-3-8b-ok-5775-v1-mkmlizer: ║ ║
hastagaras-llama-3-8b-ok-5775-v1-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-llama-3-8b-ok-5775-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-llama-3-8b-ok-5775-v1-mkmlizer: ║ https://mk1.ai ║
hastagaras-llama-3-8b-ok-5775-v1-mkmlizer: ║ ║
hastagaras-llama-3-8b-ok-5775-v1-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-llama-3-8b-ok-5775-v1-mkmlizer: ║ belonging to: ║
hastagaras-llama-3-8b-ok-5775-v1-mkmlizer: ║ ║
hastagaras-llama-3-8b-ok-5775-v1-mkmlizer: ║ Chai Research Corp. ║
hastagaras-llama-3-8b-ok-5775-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-llama-3-8b-ok-5775-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-llama-3-8b-ok-5775-v1-mkmlizer: ║ ║
hastagaras-llama-3-8b-ok-5775-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-llama-3-8b-ok-5775-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/huggingface_hub/utils/_deprecation.py:131: FutureWarning: 'list_files_info' (from 'huggingface_hub.hf_api') is deprecated and will be removed from version '0.23'. Use `list_repo_tree` and `get_paths_info` instead.
hastagaras-llama-3-8b-ok-5775-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-llama-3-8b-ok-5775-v1-mkmlizer: Downloaded to shared memory in 27.424s
hastagaras-llama-3-8b-ok-5775-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-llama-3-8b-ok-5775-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-llama-3-8b-ok-5775-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 7%|▋ | 21/291 [00:00<00:01, 200.00it/s] Loading 0: 14%|█▍ | 42/291 [00:00<00:01, 194.14it/s] Loading 0: 23%|██▎ | 66/291 [00:00<00:01, 208.95it/s] Loading 0: 30%|██▉ | 87/291 [00:00<00:02, 96.69it/s] Loading 0: 38%|███▊ | 111/291 [00:00<00:01, 124.72it/s] Loading 0: 44%|████▍ | 129/291 [00:00<00:01, 120.08it/s] Loading 0: 51%|█████ | 148/291 [00:01<00:01, 133.04it/s] Loading 0: 58%|█████▊ | 170/291 [00:01<00:00, 152.45it/s] Loading 0: 65%|██████▍ | 188/291 [00:01<00:01, 99.06it/s] Loading 0: 70%|██████▉ | 203/291 [00:01<00:00, 107.76it/s] Loading 0: 78%|███████▊ | 228/291 [00:01<00:00, 135.63it/s] Loading 0: 85%|████████▌ | 248/291 [00:01<00:00, 148.02it/s] Loading 0: 94%|█████████▍| 273/291 [00:01<00:00, 169.38it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-llama-3-8b-ok-5775-v1-mkmlizer: quantized model in 17.680s
hastagaras-llama-3-8b-ok-5775-v1-mkmlizer: Processed model Hastagaras/llama-3-8b-okay-two in 46.076s
hastagaras-llama-3-8b-ok-5775-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-llama-3-8b-ok-5775-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-llama-3-8b-ok-5775-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-llama-3-8b-ok-5775-v1
hastagaras-llama-3-8b-ok-5775-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-ok-5775-v1/config.json
hastagaras-llama-3-8b-ok-5775-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-ok-5775-v1/special_tokens_map.json
hastagaras-llama-3-8b-ok-5775-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-ok-5775-v1/tokenizer_config.json
hastagaras-llama-3-8b-ok-5775-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-ok-5775-v1/tokenizer.json
hastagaras-llama-3-8b-ok-5775-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-llama-3-8b-ok-5775-v1/flywheel_model.0.safetensors
hastagaras-llama-3-8b-ok-5775-v1-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.
hastagaras-llama-3-8b-ok-5775-v1-mkmlizer: warnings.warn(
hastagaras-llama-3-8b-ok-5775-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/torch/_utils.py:831: UserWarning: TypedStorage is deprecated. It will be removed in the future and UntypedStorage will be the only storage class. This should only matter to you if you are using storages directly. To access UntypedStorage directly, use tensor.untyped_storage() instead of tensor.storage()
hastagaras-llama-3-8b-ok-5775-v1-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-llama-3-8b-ok-5775-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-llama-3-8b-ok-5775-v1-mkmlizer: Saving duration: 0.217s
hastagaras-llama-3-8b-ok-5775-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 6.847s
hastagaras-llama-3-8b-ok-5775-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-llama-3-8b-ok-5775-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-llama-3-8b-ok-5775-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-llama-3-8b-ok-5775-v1_reward
hastagaras-llama-3-8b-ok-5775-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-llama-3-8b-ok-5775-v1_reward/config.json
hastagaras-llama-3-8b-ok-5775-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-llama-3-8b-ok-5775-v1_reward/special_tokens_map.json
hastagaras-llama-3-8b-ok-5775-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-llama-3-8b-ok-5775-v1_reward/tokenizer_config.json
hastagaras-llama-3-8b-ok-5775-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-llama-3-8b-ok-5775-v1_reward/vocab.json
hastagaras-llama-3-8b-ok-5775-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-llama-3-8b-ok-5775-v1_reward/merges.txt
hastagaras-llama-3-8b-ok-5775-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-llama-3-8b-ok-5775-v1_reward/tokenizer.json
hastagaras-llama-3-8b-ok-5775-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-llama-3-8b-ok-5775-v1_reward/reward.tensors
Job hastagaras-llama-3-8b-ok-5775-v1-mkmlizer completed after 72.66s with status: succeeded
Stopping job with name hastagaras-llama-3-8b-ok-5775-v1-mkmlizer
Pipeline stage MKMLizer completed in 75.96s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.19s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-llama-3-8b-ok-5775-v1
Waiting for inference service hastagaras-llama-3-8b-ok-5775-v1 to be ready
Inference service hastagaras-llama-3-8b-ok-5775-v1 ready after 30.3284113407135s
Pipeline stage ISVCDeployer completed in 37.07s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1311330795288086s
Received healthy response to inference request in 1.3188896179199219s
Received healthy response to inference request in 1.2290947437286377s
Received healthy response to inference request in 1.2418513298034668s
Received healthy response to inference request in 1.306746006011963s
5 requests
0 failed requests
5th percentile: 1.2316460609436035
10th percentile: 1.2341973781585693
20th percentile: 1.239300012588501
30th percentile: 1.254830265045166
40th percentile: 1.2807881355285644
50th percentile: 1.306746006011963
60th percentile: 1.3116034507751464
70th percentile: 1.3164608955383301
80th percentile: 1.4813383102416995
90th percentile: 1.806235694885254
95th percentile: 1.968684387207031
99th percentile: 2.098643341064453
mean time: 1.4455429553985595
Pipeline stage StressChecker completed in 7.90s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.04s
Running M-Eval for topic stay_in_character
hastagaras-llama-3-8b-ok_5775_v1 status is now deployed due to DeploymentManager action
M-Eval Dataset for topic stay_in_character is loaded
hastagaras-llama-3-8b-ok_5775_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics