submission_id: jellywibble-chateaulafit_5121_v1
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': 4, '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: 2024-05-22T06:47:20+00:00
model_name: jellywibble-chateaulafit_v1
model_eval_status: success
model_group: Jellywibble/ChateauLafit
num_battles: 5607
num_wins: 2813
celo_rating: 1174.61
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: 4
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: 2024-05-21
win_ratio: 0.5016943106830747
Resubmit model
Running pipeline stage MKMLizer
Starting job with name jellywibble-chateaulafit-5121-v1-mkmlizer
Waiting for job on jellywibble-chateaulafit-5121-v1-mkmlizer to finish
jellywibble-chateaulafit-5121-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
jellywibble-chateaulafit-5121-v1-mkmlizer: ║ _____ __ __ ║
jellywibble-chateaulafit-5121-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
jellywibble-chateaulafit-5121-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
jellywibble-chateaulafit-5121-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
jellywibble-chateaulafit-5121-v1-mkmlizer: ║ /___/ ║
jellywibble-chateaulafit-5121-v1-mkmlizer: ║ ║
jellywibble-chateaulafit-5121-v1-mkmlizer: ║ Version: 0.8.14 ║
jellywibble-chateaulafit-5121-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
jellywibble-chateaulafit-5121-v1-mkmlizer: ║ https://mk1.ai ║
jellywibble-chateaulafit-5121-v1-mkmlizer: ║ ║
jellywibble-chateaulafit-5121-v1-mkmlizer: ║ The license key for the current software has been verified as ║
jellywibble-chateaulafit-5121-v1-mkmlizer: ║ belonging to: ║
jellywibble-chateaulafit-5121-v1-mkmlizer: ║ ║
jellywibble-chateaulafit-5121-v1-mkmlizer: ║ Chai Research Corp. ║
jellywibble-chateaulafit-5121-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
jellywibble-chateaulafit-5121-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
jellywibble-chateaulafit-5121-v1-mkmlizer: ║ ║
jellywibble-chateaulafit-5121-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
jellywibble-chateaulafit-5121-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.
jellywibble-chateaulafit-5121-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
jellywibble-chateaulafit-5121-v1-mkmlizer: Downloaded to shared memory in 28.040s
jellywibble-chateaulafit-5121-v1-mkmlizer: quantizing model to /dev/shm/model_cache
jellywibble-chateaulafit-5121-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
jellywibble-chateaulafit-5121-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:02, 113.09it/s] Loading 0: 10%|█ | 30/291 [00:00<00:01, 135.20it/s] Loading 0: 15%|█▌ | 44/291 [00:00<00:01, 132.78it/s] Loading 0: 20%|█▉ | 58/291 [00:00<00:01, 123.70it/s] Loading 0: 26%|██▌ | 75/291 [00:00<00:01, 132.29it/s] Loading 0: 31%|███ | 89/291 [00:01<00:03, 65.29it/s] Loading 0: 35%|███▌ | 103/291 [00:01<00:02, 75.88it/s] Loading 0: 41%|████ | 120/291 [00:01<00:01, 92.43it/s] Loading 0: 46%|████▌ | 133/291 [00:01<00:01, 98.59it/s] Loading 0: 51%|█████ | 148/291 [00:01<00:01, 108.18it/s] Loading 0: 57%|█████▋ | 165/291 [00:01<00:01, 118.90it/s] Loading 0: 62%|██████▏ | 179/291 [00:01<00:00, 122.65it/s] Loading 0: 66%|██████▋ | 193/291 [00:02<00:01, 67.56it/s] Loading 0: 70%|███████ | 204/291 [00:02<00:01, 74.26it/s] Loading 0: 76%|███████▌ | 220/291 [00:02<00:00, 87.91it/s] Loading 0: 80%|███████▉ | 232/291 [00:02<00:00, 94.61it/s] Loading 0: 85%|████████▍ | 246/291 [00:02<00:00, 104.52it/s] Loading 0: 89%|████████▉ | 259/291 [00:02<00:00, 105.99it/s] Loading 0: 94%|█████████▍| 273/291 [00:02<00:00, 112.48it/s] Loading 0: 99%|█████████▊| 287/291 [00:08<00:00, 8.02it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
jellywibble-chateaulafit-5121-v1-mkmlizer: Processed model Jellywibble/ChateauLafite8BUnquantQLORA in 49.042s
jellywibble-chateaulafit-5121-v1-mkmlizer: creating bucket guanaco-mkml-models
jellywibble-chateaulafit-5121-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
jellywibble-chateaulafit-5121-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/jellywibble-chateaulafit-5121-v1
jellywibble-chateaulafit-5121-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/jellywibble-chateaulafit-5121-v1/config.json
jellywibble-chateaulafit-5121-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/jellywibble-chateaulafit-5121-v1/tokenizer_config.json
jellywibble-chateaulafit-5121-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/jellywibble-chateaulafit-5121-v1/special_tokens_map.json
jellywibble-chateaulafit-5121-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/jellywibble-chateaulafit-5121-v1/tokenizer.json
jellywibble-chateaulafit-5121-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/jellywibble-chateaulafit-5121-v1/flywheel_model.0.safetensors
jellywibble-chateaulafit-5121-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
jellywibble-chateaulafit-5121-v1-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-v1-mkmlizer: warnings.warn(
jellywibble-chateaulafit-5121-v1-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-v1-mkmlizer: warnings.warn(
jellywibble-chateaulafit-5121-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.
jellywibble-chateaulafit-5121-v1-mkmlizer: warnings.warn(
jellywibble-chateaulafit-5121-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()
jellywibble-chateaulafit-5121-v1-mkmlizer: return self.fget.__get__(instance, owner)()
jellywibble-chateaulafit-5121-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
jellywibble-chateaulafit-5121-v1-mkmlizer: Saving duration: 0.284s
jellywibble-chateaulafit-5121-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.459s
jellywibble-chateaulafit-5121-v1-mkmlizer: creating bucket guanaco-reward-models
jellywibble-chateaulafit-5121-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
jellywibble-chateaulafit-5121-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/jellywibble-chateaulafit-5121-v1_reward
jellywibble-chateaulafit-5121-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/jellywibble-chateaulafit-5121-v1_reward/config.json
jellywibble-chateaulafit-5121-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/jellywibble-chateaulafit-5121-v1_reward/tokenizer_config.json
jellywibble-chateaulafit-5121-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/jellywibble-chateaulafit-5121-v1_reward/special_tokens_map.json
jellywibble-chateaulafit-5121-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/jellywibble-chateaulafit-5121-v1_reward/merges.txt
jellywibble-chateaulafit-5121-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/jellywibble-chateaulafit-5121-v1_reward/vocab.json
jellywibble-chateaulafit-5121-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/jellywibble-chateaulafit-5121-v1_reward/tokenizer.json
jellywibble-chateaulafit-5121-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/jellywibble-chateaulafit-5121-v1_reward/reward.tensors
Job jellywibble-chateaulafit-5121-v1-mkmlizer completed after 73.33s with status: succeeded
Stopping job with name jellywibble-chateaulafit-5121-v1-mkmlizer
Pipeline stage MKMLizer completed in 77.58s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service jellywibble-chateaulafit-5121-v1
Waiting for inference service jellywibble-chateaulafit-5121-v1 to be ready
Inference service jellywibble-chateaulafit-5121-v1 ready after 40.225770473480225s
Pipeline stage ISVCDeployer completed in 47.61s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.151212215423584s
Received healthy response to inference request in 1.1262428760528564s
Received healthy response to inference request in 1.112025499343872s
Received healthy response to inference request in 1.1117405891418457s
Received healthy response to inference request in 1.1156682968139648s
5 requests
0 failed requests
5th percentile: 1.111797571182251
10th percentile: 1.1118545532226562
20th percentile: 1.1119685173034668
30th percentile: 1.1127540588378906
40th percentile: 1.1142111778259278
50th percentile: 1.1156682968139648
60th percentile: 1.1198981285095215
70th percentile: 1.1241279602050782
80th percentile: 1.331236743927002
90th percentile: 1.7412244796752931
95th percentile: 1.9462183475494383
99th percentile: 2.110213441848755
mean time: 1.3233778953552247
Pipeline stage StressChecker completed in 7.27s
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_v1 status is now deployed due to DeploymentManager action
jellywibble-chateaulafit_5121_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics