submission_id: hastagaras-markites-llama3-8b_v3
developer_uid: Hastagaras
status: inactive
model_repo: Hastagaras/Markites-llama3-8b
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.15, 'top_p': 0.95, 'min_p': 0.1, 'top_k': 200, 'presence_penalty': 0.0, 'frequency_penalty': 1.05, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
formatter: {'memory_template': '[[content]]\nText transcript of a never-ending roleplay\n\n[[description]]\nBot name: {bot_name}\n{memory}\n\n', 'prompt_template': '{prompt}\n\n[[conversation]]\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: 2024-05-16T15:11:35+00:00
model_name: mari-kita-tes
model_eval_status: success
model_group: Hastagaras/Markites-llam
num_battles: 26009
num_wins: 13758
celo_rating: 1186.5
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: mari-kita-tes
ineligible_reason: propriety_total_count < 5000
language_model: Hastagaras/Markites-llama3-8b
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-05-16
win_ratio: 0.5289707408973817
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-markites-llama3-8b-v3-mkmlizer
Waiting for job on hastagaras-markites-llama3-8b-v3-mkmlizer to finish
hastagaras-markites-llama3-8b-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-markites-llama3-8b-v3-mkmlizer: ║ _____ __ __ ║
hastagaras-markites-llama3-8b-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-markites-llama3-8b-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-markites-llama3-8b-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-markites-llama3-8b-v3-mkmlizer: ║ /___/ ║
hastagaras-markites-llama3-8b-v3-mkmlizer: ║ ║
hastagaras-markites-llama3-8b-v3-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-markites-llama3-8b-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-markites-llama3-8b-v3-mkmlizer: ║ https://mk1.ai ║
hastagaras-markites-llama3-8b-v3-mkmlizer: ║ ║
hastagaras-markites-llama3-8b-v3-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-markites-llama3-8b-v3-mkmlizer: ║ belonging to: ║
hastagaras-markites-llama3-8b-v3-mkmlizer: ║ ║
hastagaras-markites-llama3-8b-v3-mkmlizer: ║ Chai Research Corp. ║
hastagaras-markites-llama3-8b-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-markites-llama3-8b-v3-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-markites-llama3-8b-v3-mkmlizer: ║ ║
hastagaras-markites-llama3-8b-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-markites-llama3-8b-v3-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-markites-llama3-8b-v3-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-markites-llama3-8b-v3-mkmlizer: Downloaded to shared memory in 23.572s
hastagaras-markites-llama3-8b-v3-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-markites-llama3-8b-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-markites-llama3-8b-v3-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 8%|▊ | 22/291 [00:00<00:01, 198.07it/s] Loading 0: 15%|█▍ | 43/291 [00:00<00:01, 204.75it/s] Loading 0: 23%|██▎ | 66/291 [00:00<00:01, 208.96it/s] Loading 0: 30%|██▉ | 87/291 [00:00<00:02, 95.91it/s] Loading 0: 37%|███▋ | 108/291 [00:00<00:01, 118.67it/s] Loading 0: 44%|████▍ | 129/291 [00:00<00:01, 135.19it/s] Loading 0: 51%|█████ | 148/291 [00:01<00:00, 145.56it/s] Loading 0: 58%|█████▊ | 168/291 [00:01<00:00, 158.86it/s] Loading 0: 64%|██████▍ | 187/291 [00:01<00:01, 102.92it/s] Loading 0: 70%|██████▉ | 203/291 [00:01<00:00, 112.31it/s] Loading 0: 78%|███████▊ | 226/291 [00:01<00:00, 136.72it/s] Loading 0: 85%|████████▍ | 246/291 [00:01<00:00, 150.06it/s] Loading 0: 91%|█████████▏| 266/291 [00:01<00:00, 158.60it/s] Loading 0: 99%|█████████▊| 287/291 [00:06<00:00, 12.92it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-markites-llama3-8b-v3-mkmlizer: quantized model in 17.416s
hastagaras-markites-llama3-8b-v3-mkmlizer: Processed model Hastagaras/Markites-llama3-8b in 41.967s
hastagaras-markites-llama3-8b-v3-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-markites-llama3-8b-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-markites-llama3-8b-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-markites-llama3-8b-v3
hastagaras-markites-llama3-8b-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-markites-llama3-8b-v3/config.json
hastagaras-markites-llama3-8b-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-markites-llama3-8b-v3/tokenizer_config.json
hastagaras-markites-llama3-8b-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-markites-llama3-8b-v3/tokenizer.json
hastagaras-markites-llama3-8b-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-markites-llama3-8b-v3/special_tokens_map.json
hastagaras-markites-llama3-8b-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-markites-llama3-8b-v3/flywheel_model.0.safetensors
hastagaras-markites-llama3-8b-v3-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-markites-llama3-8b-v3-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-markites-llama3-8b-v3-mkmlizer: warnings.warn(
hastagaras-markites-llama3-8b-v3-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-markites-llama3-8b-v3-mkmlizer: warnings.warn(
hastagaras-markites-llama3-8b-v3-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-markites-llama3-8b-v3-mkmlizer: warnings.warn(
hastagaras-markites-llama3-8b-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-markites-llama3-8b-v3-mkmlizer: Saving duration: 0.215s
hastagaras-markites-llama3-8b-v3-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.211s
hastagaras-markites-llama3-8b-v3-mkmlizer: creating bucket guanaco-reward-models
hastagaras-markites-llama3-8b-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-markites-llama3-8b-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-markites-llama3-8b-v3_reward
hastagaras-markites-llama3-8b-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-markites-llama3-8b-v3_reward/config.json
hastagaras-markites-llama3-8b-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-markites-llama3-8b-v3_reward/special_tokens_map.json
hastagaras-markites-llama3-8b-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-markites-llama3-8b-v3_reward/tokenizer_config.json
hastagaras-markites-llama3-8b-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-markites-llama3-8b-v3_reward/merges.txt
hastagaras-markites-llama3-8b-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-markites-llama3-8b-v3_reward/vocab.json
hastagaras-markites-llama3-8b-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-markites-llama3-8b-v3_reward/tokenizer.json
hastagaras-markites-llama3-8b-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-markites-llama3-8b-v3_reward/reward.tensors
Job hastagaras-markites-llama3-8b-v3-mkmlizer completed after 64.29s with status: succeeded
Stopping job with name hastagaras-markites-llama3-8b-v3-mkmlizer
Pipeline stage MKMLizer completed in 69.74s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-markites-llama3-8b-v3
Waiting for inference service hastagaras-markites-llama3-8b-v3 to be ready
Inference service hastagaras-markites-llama3-8b-v3 ready after 40.273385524749756s
Pipeline stage ISVCDeployer completed in 49.13s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9601519107818604s
Received healthy response to inference request in 1.2760920524597168s
Received healthy response to inference request in 1.2734768390655518s
Received healthy response to inference request in 1.2003304958343506s
Received healthy response to inference request in 1.2497901916503906s
5 requests
0 failed requests
5th percentile: 1.2102224349975585
10th percentile: 1.2201143741607665
20th percentile: 1.2398982524871827
30th percentile: 1.2545275211334228
40th percentile: 1.2640021800994874
50th percentile: 1.2734768390655518
60th percentile: 1.2745229244232177
70th percentile: 1.2755690097808838
80th percentile: 1.4129040241241455
90th percentile: 1.686527967453003
95th percentile: 1.8233399391174316
99th percentile: 1.9327895164489746
mean time: 1.391968297958374
Pipeline stage StressChecker completed in 7.61s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running M-Eval for topic stay_in_character
Running pipeline stage DaemonicSafetyScorer
M-Eval Dataset for topic stay_in_character is loaded
Pipeline stage DaemonicSafetyScorer completed in 0.08s
hastagaras-markites-llama3-8b_v3 status is now deployed due to DeploymentManager action
hastagaras-markites-llama3-8b_v3 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics