submission_id: hastagaras-esekembrew-0-3_v7
developer_uid: Hastagaras
status: inactive
model_repo: Hastagaras/Esekembrew-0.3
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.98, 'top_p': 0.95, 'min_p': 0.04, 'top_k': 200, '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: 2024-05-19T00:26:46+00:00
model_name: debug
model_eval_status: success
model_group: Hastagaras/Esekembrew-0.
num_battles: 25067
num_wins: 13992
celo_rating: 1210.24
safety_score: 0.96
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: debug
ineligible_reason: propriety_total_count < 5000
language_model: Hastagaras/Esekembrew-0.3
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-05-18
win_ratio: 0.5581840667012407
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-esekembrew-0-3-v7-mkmlizer
Waiting for job on hastagaras-esekembrew-0-3-v7-mkmlizer to finish
hastagaras-esekembrew-0-3-v7-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-esekembrew-0-3-v7-mkmlizer: ║ _____ __ __ ║
hastagaras-esekembrew-0-3-v7-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-esekembrew-0-3-v7-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-esekembrew-0-3-v7-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-esekembrew-0-3-v7-mkmlizer: ║ /___/ ║
hastagaras-esekembrew-0-3-v7-mkmlizer: ║ ║
hastagaras-esekembrew-0-3-v7-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-esekembrew-0-3-v7-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-esekembrew-0-3-v7-mkmlizer: ║ https://mk1.ai ║
hastagaras-esekembrew-0-3-v7-mkmlizer: ║ ║
hastagaras-esekembrew-0-3-v7-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-esekembrew-0-3-v7-mkmlizer: ║ belonging to: ║
hastagaras-esekembrew-0-3-v7-mkmlizer: ║ ║
hastagaras-esekembrew-0-3-v7-mkmlizer: ║ Chai Research Corp. ║
hastagaras-esekembrew-0-3-v7-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-esekembrew-0-3-v7-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-esekembrew-0-3-v7-mkmlizer: ║ ║
hastagaras-esekembrew-0-3-v7-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-esekembrew-0-3-v7-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-esekembrew-0-3-v7-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-esekembrew-0-3-v7-mkmlizer: Downloaded to shared memory in 14.571s
hastagaras-esekembrew-0-3-v7-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-esekembrew-0-3-v7-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-esekembrew-0-3-v7-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 7%|▋ | 21/291 [00:00<00:01, 195.53it/s] Loading 0: 14%|█▍ | 41/291 [00:00<00:01, 180.53it/s] Loading 0: 22%|██▏ | 64/291 [00:00<00:01, 201.02it/s] Loading 0: 29%|██▉ | 85/291 [00:00<00:02, 88.53it/s] Loading 0: 36%|███▌ | 104/291 [00:00<00:01, 106.85it/s] Loading 0: 44%|████▎ | 127/291 [00:00<00:01, 132.67it/s] Loading 0: 50%|█████ | 146/291 [00:01<00:00, 145.49it/s] Loading 0: 57%|█████▋ | 165/291 [00:01<00:00, 154.84it/s] Loading 0: 64%|██████▍ | 186/291 [00:01<00:00, 168.85it/s] Loading 0: 71%|███████ | 206/291 [00:01<00:00, 96.13it/s] Loading 0: 78%|███████▊ | 228/291 [00:01<00:00, 116.61it/s] Loading 0: 85%|████████▍ | 247/291 [00:01<00:00, 130.78it/s] Loading 0: 91%|█████████▏| 266/291 [00:02<00:00, 141.69it/s] Loading 0: 99%|█████████▊| 287/291 [00:07<00:00, 12.44it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-esekembrew-0-3-v7-mkmlizer: quantized model in 17.910s
hastagaras-esekembrew-0-3-v7-mkmlizer: Processed model Hastagaras/Esekembrew-0.3 in 33.588s
hastagaras-esekembrew-0-3-v7-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-esekembrew-0-3-v7-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-esekembrew-0-3-v7/config.json
hastagaras-esekembrew-0-3-v7-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-esekembrew-0-3-v7/tokenizer.json
hastagaras-esekembrew-0-3-v7-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-esekembrew-0-3-v7/flywheel_model.0.safetensors
hastagaras-esekembrew-0-3-v7-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-esekembrew-0-3-v7-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-esekembrew-0-3-v7-mkmlizer: warnings.warn(
hastagaras-esekembrew-0-3-v7-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-esekembrew-0-3-v7-mkmlizer: warnings.warn(
hastagaras-esekembrew-0-3-v7-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-esekembrew-0-3-v7-mkmlizer: warnings.warn(
hastagaras-esekembrew-0-3-v7-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()
hastagaras-esekembrew-0-3-v7-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-esekembrew-0-3-v7-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-esekembrew-0-3-v7-mkmlizer: Saving duration: 0.251s
hastagaras-esekembrew-0-3-v7-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.390s
hastagaras-esekembrew-0-3-v7-mkmlizer: creating bucket guanaco-reward-models
hastagaras-esekembrew-0-3-v7-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-esekembrew-0-3-v7-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-esekembrew-0-3-v7_reward
hastagaras-esekembrew-0-3-v7-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-esekembrew-0-3-v7_reward/config.json
hastagaras-esekembrew-0-3-v7-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-esekembrew-0-3-v7_reward/special_tokens_map.json
hastagaras-esekembrew-0-3-v7-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-esekembrew-0-3-v7_reward/tokenizer_config.json
hastagaras-esekembrew-0-3-v7-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-esekembrew-0-3-v7_reward/merges.txt
hastagaras-esekembrew-0-3-v7-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-esekembrew-0-3-v7_reward/vocab.json
hastagaras-esekembrew-0-3-v7-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-esekembrew-0-3-v7_reward/tokenizer.json
hastagaras-esekembrew-0-3-v7-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-esekembrew-0-3-v7_reward/reward.tensors
Job hastagaras-esekembrew-0-3-v7-mkmlizer completed after 62.85s with status: succeeded
Stopping job with name hastagaras-esekembrew-0-3-v7-mkmlizer
Pipeline stage MKMLizer completed in 66.10s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-esekembrew-0-3-v7
Waiting for inference service hastagaras-esekembrew-0-3-v7 to be ready
Inference service hastagaras-esekembrew-0-3-v7 ready after 40.22425699234009s
Pipeline stage ISVCDeployer completed in 47.41s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1421773433685303s
Received healthy response to inference request in 1.374558687210083s
Received healthy response to inference request in 1.3454627990722656s
Received healthy response to inference request in 1.286346673965454s
Received healthy response to inference request in 1.3586087226867676s
5 requests
0 failed requests
5th percentile: 1.2981698989868165
10th percentile: 1.3099931240081788
20th percentile: 1.3336395740509033
30th percentile: 1.348091983795166
40th percentile: 1.3533503532409668
50th percentile: 1.3586087226867676
60th percentile: 1.3649887084960937
70th percentile: 1.37136869430542
80th percentile: 1.5280824184417725
90th percentile: 1.8351298809051515
95th percentile: 1.9886536121368408
99th percentile: 2.111472597122192
mean time: 1.5014308452606202
Pipeline stage StressChecker completed in 8.15s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.04s
Running M-Eval for topic stay_in_character
hastagaras-esekembrew-0-3_v7 status is now deployed due to DeploymentManager action
M-Eval Dataset for topic stay_in_character is loaded
hastagaras-esekembrew-0-3_v7 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics