submission_id: jellywibble-chateaulafit_5121_v2
developer_uid: Jellywibble
status: inactive
model_repo: Jellywibble/ChateauLafite8BUnquantQLORA
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.95, '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': "<|begin_of_text|>{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: 2024-05-24T04:57:29+00:00
model_name: jellywibble-chateaulafit_v1
model_eval_status: success
model_group: Jellywibble/ChateauLafit
num_battles: 15509
num_wins: 8186
celo_rating: 1196.93
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: jellywibble-chateaulafit_v1
ineligible_reason: propriety_total_count < 5000
language_model: Jellywibble/ChateauLafite8BUnquantQLORA
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-05-23
win_ratio: 0.5278225546456896
Resubmit model
Running pipeline stage MKMLizer
Starting job with name jellywibble-chateaulafit-5121-v2-mkmlizer
Waiting for job on jellywibble-chateaulafit-5121-v2-mkmlizer to finish
jellywibble-chateaulafit-5121-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
jellywibble-chateaulafit-5121-v2-mkmlizer: ║ _____ __ __ ║
jellywibble-chateaulafit-5121-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
jellywibble-chateaulafit-5121-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
jellywibble-chateaulafit-5121-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
jellywibble-chateaulafit-5121-v2-mkmlizer: ║ /___/ ║
jellywibble-chateaulafit-5121-v2-mkmlizer: ║ ║
jellywibble-chateaulafit-5121-v2-mkmlizer: ║ Version: 0.8.14 ║
jellywibble-chateaulafit-5121-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
jellywibble-chateaulafit-5121-v2-mkmlizer: ║ https://mk1.ai ║
jellywibble-chateaulafit-5121-v2-mkmlizer: ║ ║
jellywibble-chateaulafit-5121-v2-mkmlizer: ║ The license key for the current software has been verified as ║
jellywibble-chateaulafit-5121-v2-mkmlizer: ║ belonging to: ║
jellywibble-chateaulafit-5121-v2-mkmlizer: ║ ║
jellywibble-chateaulafit-5121-v2-mkmlizer: ║ Chai Research Corp. ║
jellywibble-chateaulafit-5121-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
jellywibble-chateaulafit-5121-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
jellywibble-chateaulafit-5121-v2-mkmlizer: ║ ║
jellywibble-chateaulafit-5121-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
jellywibble-chateaulafit-5121-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.
jellywibble-chateaulafit-5121-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
jellywibble-chateaulafit-5121-v2-mkmlizer: Downloaded to shared memory in 23.661s
jellywibble-chateaulafit-5121-v2-mkmlizer: quantizing model to /dev/shm/model_cache
jellywibble-chateaulafit-5121-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
jellywibble-chateaulafit-5121-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:02, 129.81it/s] Loading 0: 10%|█ | 30/291 [00:00<00:01, 144.16it/s] Loading 0: 15%|█▌ | 45/291 [00:00<00:01, 140.75it/s] Loading 0: 21%|██ | 60/291 [00:00<00:01, 135.94it/s] Loading 0: 26%|██▌ | 76/291 [00:00<00:01, 139.32it/s] Loading 0: 31%|███ | 90/291 [00:00<00:02, 67.46it/s] Loading 0: 36%|███▌ | 104/291 [00:01<00:02, 79.58it/s] Loading 0: 42%|████▏ | 122/291 [00:01<00:01, 97.74it/s] Loading 0: 48%|████▊ | 140/291 [00:01<00:01, 112.97it/s] Loading 0: 54%|█████▍ | 158/291 [00:01<00:01, 125.39it/s] Loading 0: 62%|██████▏ | 179/291 [00:01<00:00, 143.70it/s] Loading 0: 67%|██████▋ | 196/291 [00:01<00:01, 77.86it/s] Loading 0: 73%|███████▎ | 211/291 [00:02<00:00, 88.53it/s] Loading 0: 78%|███████▊ | 228/291 [00:02<00:00, 102.21it/s] Loading 0: 83%|████████▎ | 242/291 [00:02<00:00, 109.90it/s] Loading 0: 88%|████████▊ | 257/291 [00:02<00:00, 115.33it/s] Loading 0: 94%|█████████▍| 274/291 [00:02<00:00, 126.96it/s] Loading 0: 99%|█████████▉| 289/291 [00:07<00:00, 9.67it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
jellywibble-chateaulafit-5121-v2-mkmlizer: quantized model in 19.205s
jellywibble-chateaulafit-5121-v2-mkmlizer: Processed model Jellywibble/ChateauLafite8BUnquantQLORA in 43.957s
jellywibble-chateaulafit-5121-v2-mkmlizer: creating bucket guanaco-mkml-models
jellywibble-chateaulafit-5121-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
jellywibble-chateaulafit-5121-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/jellywibble-chateaulafit-5121-v2
jellywibble-chateaulafit-5121-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/jellywibble-chateaulafit-5121-v2/config.json
jellywibble-chateaulafit-5121-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/jellywibble-chateaulafit-5121-v2/special_tokens_map.json
jellywibble-chateaulafit-5121-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/jellywibble-chateaulafit-5121-v2/tokenizer_config.json
jellywibble-chateaulafit-5121-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/jellywibble-chateaulafit-5121-v2/tokenizer.json
jellywibble-chateaulafit-5121-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/jellywibble-chateaulafit-5121-v2/flywheel_model.0.safetensors
jellywibble-chateaulafit-5121-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
jellywibble-chateaulafit-5121-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.
jellywibble-chateaulafit-5121-v2-mkmlizer: warnings.warn(
jellywibble-chateaulafit-5121-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.
jellywibble-chateaulafit-5121-v2-mkmlizer: warnings.warn(
jellywibble-chateaulafit-5121-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.
jellywibble-chateaulafit-5121-v2-mkmlizer: warnings.warn(
jellywibble-chateaulafit-5121-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
jellywibble-chateaulafit-5121-v2-mkmlizer: Saving duration: 0.309s
jellywibble-chateaulafit-5121-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 6.958s
jellywibble-chateaulafit-5121-v2-mkmlizer: creating bucket guanaco-reward-models
jellywibble-chateaulafit-5121-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
jellywibble-chateaulafit-5121-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/jellywibble-chateaulafit-5121-v2_reward
jellywibble-chateaulafit-5121-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/jellywibble-chateaulafit-5121-v2_reward/config.json
jellywibble-chateaulafit-5121-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/jellywibble-chateaulafit-5121-v2_reward/tokenizer_config.json
jellywibble-chateaulafit-5121-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/jellywibble-chateaulafit-5121-v2_reward/special_tokens_map.json
jellywibble-chateaulafit-5121-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/jellywibble-chateaulafit-5121-v2_reward/merges.txt
jellywibble-chateaulafit-5121-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/jellywibble-chateaulafit-5121-v2_reward/vocab.json
jellywibble-chateaulafit-5121-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/jellywibble-chateaulafit-5121-v2_reward/tokenizer.json
jellywibble-chateaulafit-5121-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/jellywibble-chateaulafit-5121-v2_reward/reward.tensors
Job jellywibble-chateaulafit-5121-v2-mkmlizer completed after 73.73s with status: succeeded
Stopping job with name jellywibble-chateaulafit-5121-v2-mkmlizer
Pipeline stage MKMLizer completed in 76.92s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service jellywibble-chateaulafit-5121-v2
Waiting for inference service jellywibble-chateaulafit-5121-v2 to be ready
Inference service jellywibble-chateaulafit-5121-v2 ready after 40.20194220542908s
Pipeline stage ISVCDeployer completed in 47.04s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2700586318969727s
Received healthy response to inference request in 1.2740015983581543s
Received healthy response to inference request in 1.287142038345337s
Received healthy response to inference request in 1.2734127044677734s
Received healthy response to inference request in 1.2690606117248535s
5 requests
0 failed requests
5th percentile: 1.2699310302734375
10th percentile: 1.2708014488220214
20th percentile: 1.2725422859191895
30th percentile: 1.2735304832458496
40th percentile: 1.273766040802002
50th percentile: 1.2740015983581543
60th percentile: 1.2792577743530273
70th percentile: 1.2845139503479004
80th percentile: 1.4837253570556643
90th percentile: 1.8768919944763185
95th percentile: 2.0734753131866452
99th percentile: 2.230741968154907
mean time: 1.4747351169586183
Pipeline stage StressChecker completed in 7.97s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running pipeline stage DaemonicSafetyScorer
Running M-Eval for topic stay_in_character
Pipeline stage DaemonicSafetyScorer completed in 0.03s
M-Eval Dataset for topic stay_in_character is loaded
jellywibble-chateaulafit_5121_v2 status is now deployed due to DeploymentManager action
jellywibble-chateaulafit_5121_v2 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics