submission_id: hastagaras-halu-8b-llama_6475_v2
developer_uid: Hastagaras
status: inactive
model_repo: Hastagaras/Halu-8B-Llama3-v0.35
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 0.1, 'top_k': 100, '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': 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: 2024-05-31T06:38:40+00:00
model_name: without-anjir-adapter
model_eval_status: success
model_group: Hastagaras/Halu-8B-Llama
num_battles: 10329
num_wins: 5644
celo_rating: 1214.05
safety_score: 0.95
propriety_score: 1.0
propriety_total_count: 1.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: without-anjir-adapter
ineligible_reason: propriety_total_count < 5000
language_model: Hastagaras/Halu-8B-Llama3-v0.35
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-05-30
win_ratio: 0.5464226933875496
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-halu-8b-llama-6475-v2-mkmlizer
Waiting for job on hastagaras-halu-8b-llama-6475-v2-mkmlizer to finish
hastagaras-halu-8b-llama-6475-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-halu-8b-llama-6475-v2-mkmlizer: ║ _____ __ __ ║
hastagaras-halu-8b-llama-6475-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-halu-8b-llama-6475-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-halu-8b-llama-6475-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-halu-8b-llama-6475-v2-mkmlizer: ║ /___/ ║
hastagaras-halu-8b-llama-6475-v2-mkmlizer: ║ ║
hastagaras-halu-8b-llama-6475-v2-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-halu-8b-llama-6475-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-halu-8b-llama-6475-v2-mkmlizer: ║ https://mk1.ai ║
hastagaras-halu-8b-llama-6475-v2-mkmlizer: ║ ║
hastagaras-halu-8b-llama-6475-v2-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-halu-8b-llama-6475-v2-mkmlizer: ║ belonging to: ║
hastagaras-halu-8b-llama-6475-v2-mkmlizer: ║ ║
hastagaras-halu-8b-llama-6475-v2-mkmlizer: ║ Chai Research Corp. ║
hastagaras-halu-8b-llama-6475-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-halu-8b-llama-6475-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-halu-8b-llama-6475-v2-mkmlizer: ║ ║
hastagaras-halu-8b-llama-6475-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-halu-8b-llama-6475-v2-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-halu-8b-llama-6475-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-halu-8b-llama-6475-v2-mkmlizer: Downloaded to shared memory in 18.409s
hastagaras-halu-8b-llama-6475-v2-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-halu-8b-llama-6475-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-halu-8b-llama-6475-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 5%|▍ | 14/291 [00:00<00:02, 124.37it/s] Loading 0: 11%|█ | 32/291 [00:00<00:01, 150.04it/s] Loading 0: 17%|█▋ | 50/291 [00:00<00:01, 157.11it/s] Loading 0: 23%|██▎ | 68/291 [00:00<00:01, 162.50it/s] Loading 0: 29%|██▉ | 85/291 [00:00<00:02, 87.83it/s] Loading 0: 35%|███▌ | 103/291 [00:00<00:01, 105.01it/s] Loading 0: 42%|████▏ | 121/291 [00:01<00:01, 119.84it/s] Loading 0: 48%|████▊ | 139/291 [00:01<00:01, 130.77it/s] Loading 0: 54%|█████▍ | 157/291 [00:01<00:00, 139.13it/s] Loading 0: 60%|█████▉ | 174/291 [00:01<00:00, 147.00it/s] Loading 0: 65%|██████▌ | 190/291 [00:01<00:01, 91.63it/s] Loading 0: 71%|███████ | 206/291 [00:01<00:00, 104.57it/s] Loading 0: 77%|███████▋ | 223/291 [00:01<00:00, 118.39it/s] Loading 0: 82%|████████▏ | 239/291 [00:01<00:00, 126.69it/s] Loading 0: 88%|████████▊ | 257/291 [00:02<00:00, 136.38it/s] Loading 0: 95%|█████████▍| 275/291 [00:02<00:00, 143.97it/s] Loading 0: 100%|██████████| 291/291 [00:07<00:00, 9.62it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-halu-8b-llama-6475-v2-mkmlizer: quantized model in 23.050s
hastagaras-halu-8b-llama-6475-v2-mkmlizer: Processed model Hastagaras/Halu-8B-Llama3-v0.35 in 43.988s
hastagaras-halu-8b-llama-6475-v2-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-halu-8b-llama-6475-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-halu-8b-llama-6475-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-halu-8b-llama-6475-v2
hastagaras-halu-8b-llama-6475-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-6475-v2/special_tokens_map.json
hastagaras-halu-8b-llama-6475-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-6475-v2/config.json
hastagaras-halu-8b-llama-6475-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-6475-v2/tokenizer_config.json
hastagaras-halu-8b-llama-6475-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-6475-v2/tokenizer.json
hastagaras-halu-8b-llama-6475-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-halu-8b-llama-6475-v2/flywheel_model.0.safetensors
hastagaras-halu-8b-llama-6475-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-halu-8b-llama-6475-v2-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:913: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
hastagaras-halu-8b-llama-6475-v2-mkmlizer: warnings.warn(
hastagaras-halu-8b-llama-6475-v2-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:757: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
hastagaras-halu-8b-llama-6475-v2-mkmlizer: warnings.warn(
hastagaras-halu-8b-llama-6475-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.
hastagaras-halu-8b-llama-6475-v2-mkmlizer: warnings.warn(
hastagaras-halu-8b-llama-6475-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-halu-8b-llama-6475-v2-mkmlizer: Saving duration: 0.397s
hastagaras-halu-8b-llama-6475-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.308s
hastagaras-halu-8b-llama-6475-v2-mkmlizer: creating bucket guanaco-reward-models
hastagaras-halu-8b-llama-6475-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-halu-8b-llama-6475-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-halu-8b-llama-6475-v2_reward
hastagaras-halu-8b-llama-6475-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-6475-v2_reward/config.json
hastagaras-halu-8b-llama-6475-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-6475-v2_reward/special_tokens_map.json
hastagaras-halu-8b-llama-6475-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-6475-v2_reward/tokenizer_config.json
hastagaras-halu-8b-llama-6475-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-halu-8b-llama-6475-v2_reward/merges.txt
hastagaras-halu-8b-llama-6475-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-6475-v2_reward/tokenizer.json
hastagaras-halu-8b-llama-6475-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-6475-v2_reward/vocab.json
hastagaras-halu-8b-llama-6475-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-halu-8b-llama-6475-v2_reward/reward.tensors
Job hastagaras-halu-8b-llama-6475-v2-mkmlizer completed after 72.86s with status: succeeded
Stopping job with name hastagaras-halu-8b-llama-6475-v2-mkmlizer
Pipeline stage MKMLizer completed in 73.64s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-halu-8b-llama-6475-v2
Waiting for inference service hastagaras-halu-8b-llama-6475-v2 to be ready
Inference service hastagaras-halu-8b-llama-6475-v2 ready after 211.13518905639648s
Pipeline stage ISVCDeployer completed in 216.89s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1217381954193115s
Received healthy response to inference request in 1.3644580841064453s
Received healthy response to inference request in 1.3191595077514648s
Received healthy response to inference request in 1.2937633991241455s
Received healthy response to inference request in 1.2469799518585205s
5 requests
0 failed requests
5th percentile: 1.2563366413116455
10th percentile: 1.2656933307647704
20th percentile: 1.2844067096710206
30th percentile: 1.2988426208496093
40th percentile: 1.3090010643005372
50th percentile: 1.3191595077514648
60th percentile: 1.3372789382934571
70th percentile: 1.3553983688354492
80th percentile: 1.5159141063690187
90th percentile: 1.8188261508941652
95th percentile: 1.9702821731567381
99th percentile: 2.091446990966797
mean time: 1.4692198276519775
Pipeline stage StressChecker completed in 8.26s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.03s
Running M-Eval for topic stay_in_character
M-Eval Dataset for topic stay_in_character is loaded
hastagaras-halu-8b-llama_6475_v2 status is now deployed due to DeploymentManager action
hastagaras-halu-8b-llama_6475_v2 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics