submission_id: jellywibble-chateaulafit_7738_v3
developer_uid: Jellywibble
status: inactive
model_repo: Jellywibble/ChateauLafite8BRawQLORA
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 50, '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: 2024-05-22T07:54:57+00:00
model_name: jellywibble-chateaulafit_v2
model_eval_status: success
model_group: Jellywibble/ChateauLafit
num_battles: 11169
num_wins: 6069
celo_rating: 1199.93
safety_score: 0.95
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_v2
ineligible_reason: propriety_total_count < 5000
language_model: Jellywibble/ChateauLafite8BRawQLORA
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-05-22
win_ratio: 0.54337899543379
Resubmit model
Running pipeline stage MKMLizer
Starting job with name jellywibble-chateaulafit-7738-v3-mkmlizer
Waiting for job on jellywibble-chateaulafit-7738-v3-mkmlizer to finish
jellywibble-chateaulafit-7738-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
jellywibble-chateaulafit-7738-v3-mkmlizer: ║ _____ __ __ ║
jellywibble-chateaulafit-7738-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
jellywibble-chateaulafit-7738-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
jellywibble-chateaulafit-7738-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
jellywibble-chateaulafit-7738-v3-mkmlizer: ║ /___/ ║
jellywibble-chateaulafit-7738-v3-mkmlizer: ║ ║
jellywibble-chateaulafit-7738-v3-mkmlizer: ║ Version: 0.8.14 ║
jellywibble-chateaulafit-7738-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
jellywibble-chateaulafit-7738-v3-mkmlizer: ║ https://mk1.ai ║
jellywibble-chateaulafit-7738-v3-mkmlizer: ║ ║
jellywibble-chateaulafit-7738-v3-mkmlizer: ║ The license key for the current software has been verified as ║
jellywibble-chateaulafit-7738-v3-mkmlizer: ║ belonging to: ║
jellywibble-chateaulafit-7738-v3-mkmlizer: ║ ║
jellywibble-chateaulafit-7738-v3-mkmlizer: ║ Chai Research Corp. ║
jellywibble-chateaulafit-7738-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
jellywibble-chateaulafit-7738-v3-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
jellywibble-chateaulafit-7738-v3-mkmlizer: ║ ║
jellywibble-chateaulafit-7738-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
jellywibble-chateaulafit-7738-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.
jellywibble-chateaulafit-7738-v3-mkmlizer: warnings.warn(warning_message, FutureWarning)
jellywibble-chateaulafit-7738-v3-mkmlizer: Downloaded to shared memory in 22.791s
jellywibble-chateaulafit-7738-v3-mkmlizer: quantizing model to /dev/shm/model_cache
jellywibble-chateaulafit-7738-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
jellywibble-chateaulafit-7738-v3-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 12/291 [00:00<00:02, 107.51it/s] Loading 0: 8%|▊ | 23/291 [00:00<00:03, 88.36it/s] Loading 0: 11%|█▏ | 33/291 [00:00<00:05, 45.86it/s] Loading 0: 14%|█▎ | 40/291 [00:00<00:05, 49.87it/s] Loading 0: 17%|█▋ | 50/291 [00:00<00:03, 60.81it/s] Loading 0: 23%|██▎ | 66/291 [00:00<00:02, 81.18it/s] Loading 0: 26%|██▌ | 76/291 [00:01<00:02, 84.57it/s] Loading 0: 30%|██▉ | 86/291 [00:01<00:04, 50.89it/s] Loading 0: 34%|███▍ | 99/291 [00:01<00:03, 62.81it/s] Loading 0: 37%|███▋ | 108/291 [00:01<00:02, 65.86it/s] Loading 0: 40%|████ | 117/291 [00:01<00:02, 60.65it/s] Loading 0: 44%|████▎ | 127/291 [00:01<00:02, 67.39it/s] Loading 0: 46%|████▋ | 135/291 [00:02<00:03, 44.21it/s] Loading 0: 51%|█████ | 147/291 [00:02<00:02, 56.65it/s] Loading 0: 54%|█████▍ | 157/291 [00:02<00:02, 64.41it/s] Loading 0: 57%|█████▋ | 167/291 [00:02<00:01, 71.58it/s] Loading 0: 63%|██████▎ | 183/291 [00:02<00:01, 91.18it/s] Loading 0: 67%|██████▋ | 194/291 [00:03<00:01, 53.73it/s] Loading 0: 72%|███████▏ | 210/291 [00:03<00:01, 69.39it/s] Loading 0: 76%|███████▌ | 220/291 [00:03<00:00, 74.91it/s] Loading 0: 80%|████████ | 233/291 [00:03<00:01, 55.05it/s] Loading 0: 84%|████████▎ | 243/291 [00:03<00:00, 62.04it/s] Loading 0: 88%|████████▊ | 255/291 [00:03<00:00, 72.00it/s] Loading 0: 91%|█████████ | 265/291 [00:04<00:00, 75.12it/s] Loading 0: 95%|█████████▍| 275/291 [00:04<00:00, 80.14it/s] Loading 0: 98%|█████████▊| 286/291 [00:09<00:00, 6.85it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
jellywibble-chateaulafit-7738-v3-mkmlizer: quantized model in 19.366s
jellywibble-chateaulafit-7738-v3-mkmlizer: Processed model Jellywibble/ChateauLafite8BRawQLORA in 44.337s
jellywibble-chateaulafit-7738-v3-mkmlizer: creating bucket guanaco-mkml-models
jellywibble-chateaulafit-7738-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
jellywibble-chateaulafit-7738-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/jellywibble-chateaulafit-7738-v3
jellywibble-chateaulafit-7738-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/jellywibble-chateaulafit-7738-v3/config.json
jellywibble-chateaulafit-7738-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/jellywibble-chateaulafit-7738-v3/special_tokens_map.json
jellywibble-chateaulafit-7738-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/jellywibble-chateaulafit-7738-v3/tokenizer_config.json
jellywibble-chateaulafit-7738-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/jellywibble-chateaulafit-7738-v3/tokenizer.json
jellywibble-chateaulafit-7738-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/jellywibble-chateaulafit-7738-v3/flywheel_model.0.safetensors
jellywibble-chateaulafit-7738-v3-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
jellywibble-chateaulafit-7738-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.
jellywibble-chateaulafit-7738-v3-mkmlizer: warnings.warn(
jellywibble-chateaulafit-7738-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.
jellywibble-chateaulafit-7738-v3-mkmlizer: warnings.warn(
jellywibble-chateaulafit-7738-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.
jellywibble-chateaulafit-7738-v3-mkmlizer: warnings.warn(
jellywibble-chateaulafit-7738-v3-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()
jellywibble-chateaulafit-7738-v3-mkmlizer: return self.fget.__get__(instance, owner)()
jellywibble-chateaulafit-7738-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
jellywibble-chateaulafit-7738-v3-mkmlizer: Saving duration: 0.228s
jellywibble-chateaulafit-7738-v3-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.860s
jellywibble-chateaulafit-7738-v3-mkmlizer: creating bucket guanaco-reward-models
jellywibble-chateaulafit-7738-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
jellywibble-chateaulafit-7738-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/jellywibble-chateaulafit-7738-v3_reward
jellywibble-chateaulafit-7738-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/jellywibble-chateaulafit-7738-v3_reward/special_tokens_map.json
jellywibble-chateaulafit-7738-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/jellywibble-chateaulafit-7738-v3_reward/merges.txt
jellywibble-chateaulafit-7738-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/jellywibble-chateaulafit-7738-v3_reward/vocab.json
jellywibble-chateaulafit-7738-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/jellywibble-chateaulafit-7738-v3_reward/tokenizer.json
jellywibble-chateaulafit-7738-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/jellywibble-chateaulafit-7738-v3_reward/config.json
jellywibble-chateaulafit-7738-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/jellywibble-chateaulafit-7738-v3_reward/tokenizer_config.json
jellywibble-chateaulafit-7738-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/jellywibble-chateaulafit-7738-v3_reward/reward.tensors
Job jellywibble-chateaulafit-7738-v3-mkmlizer completed after 73.17s with status: succeeded
Stopping job with name jellywibble-chateaulafit-7738-v3-mkmlizer
Pipeline stage MKMLizer completed in 76.98s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service jellywibble-chateaulafit-7738-v3
Waiting for inference service jellywibble-chateaulafit-7738-v3 to be ready
Inference service jellywibble-chateaulafit-7738-v3 ready after 30.165165662765503s
Pipeline stage ISVCDeployer completed in 36.96s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.568007707595825s
Received healthy response to inference request in 1.2453258037567139s
Received healthy response to inference request in 1.2588837146759033s
Received healthy response to inference request in 1.2616000175476074s
Received healthy response to inference request in 1.2381706237792969s
5 requests
0 failed requests
5th percentile: 1.2396016597747803
10th percentile: 1.2410326957702638
20th percentile: 1.2438947677612304
30th percentile: 1.2480373859405518
40th percentile: 1.2534605503082275
50th percentile: 1.2588837146759033
60th percentile: 1.259970235824585
70th percentile: 1.2610567569732667
80th percentile: 1.5228815555572512
90th percentile: 2.0454446315765384
95th percentile: 2.3067261695861814
99th percentile: 2.5157513999938965
mean time: 1.5143975734710693
Pipeline stage StressChecker completed in 8.20s
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 0.05s
M-Eval Dataset for topic stay_in_character is loaded
jellywibble-chateaulafit_7738_v3 status is now deployed due to DeploymentManager action
jellywibble-chateaulafit_7738_v3 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics