submission_id: hastagaras-waduh-1-sft-l_7494_v2
developer_uid: Hastagaras
status: inactive
model_repo: Hastagaras/Waduh-1-SFT-llama3-8b
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.8, 'top_p': 0.95, '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': "<|start_header_id|>system<|end_header_id|>\n\nAct as {bot_name}\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': True}
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': True}
timestamp: 2024-05-20T01:04:17+00:00
model_name: hopefully-fixed
model_eval_status: success
model_group: Hastagaras/Waduh-1-SFT-l
num_battles: 28749
num_wins: 15278
celo_rating: 1195.99
safety_score: 0.94
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: hopefully-fixed
ineligible_reason: propriety_total_count < 5000
language_model: Hastagaras/Waduh-1-SFT-llama3-8b
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-05-19
win_ratio: 0.5314271800758287
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-waduh-1-sft-l-7494-v2-mkmlizer
Waiting for job on hastagaras-waduh-1-sft-l-7494-v2-mkmlizer to finish
hastagaras-waduh-1-sft-l-7494-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-waduh-1-sft-l-7494-v2-mkmlizer: ║ _____ __ __ ║
hastagaras-waduh-1-sft-l-7494-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-waduh-1-sft-l-7494-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-waduh-1-sft-l-7494-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-waduh-1-sft-l-7494-v2-mkmlizer: ║ /___/ ║
hastagaras-waduh-1-sft-l-7494-v2-mkmlizer: ║ ║
hastagaras-waduh-1-sft-l-7494-v2-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-waduh-1-sft-l-7494-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-waduh-1-sft-l-7494-v2-mkmlizer: ║ https://mk1.ai ║
hastagaras-waduh-1-sft-l-7494-v2-mkmlizer: ║ ║
hastagaras-waduh-1-sft-l-7494-v2-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-waduh-1-sft-l-7494-v2-mkmlizer: ║ belonging to: ║
hastagaras-waduh-1-sft-l-7494-v2-mkmlizer: ║ ║
hastagaras-waduh-1-sft-l-7494-v2-mkmlizer: ║ Chai Research Corp. ║
hastagaras-waduh-1-sft-l-7494-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-waduh-1-sft-l-7494-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-waduh-1-sft-l-7494-v2-mkmlizer: ║ ║
hastagaras-waduh-1-sft-l-7494-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-waduh-1-sft-l-7494-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.
hastagaras-waduh-1-sft-l-7494-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-waduh-1-sft-l-7494-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 7%|▋ | 21/291 [00:00<00:01, 189.77it/s] Loading 0: 14%|█▍ | 41/291 [00:00<00:01, 186.29it/s] Loading 0: 23%|██▎ | 66/291 [00:00<00:01, 211.24it/s] Loading 0: 30%|███ | 88/291 [00:00<00:01, 102.60it/s] Loading 0: 38%|███▊ | 111/291 [00:00<00:01, 128.31it/s] Loading 0: 45%|████▌ | 131/291 [00:00<00:01, 143.06it/s] Loading 0: 54%|█████▎ | 156/291 [00:01<00:00, 167.54it/s] Loading 0: 62%|██████▏ | 179/291 [00:01<00:00, 180.11it/s] Loading 0: 69%|██████▊ | 200/291 [00:01<00:00, 108.85it/s] Loading 0: 76%|███████▌ | 220/291 [00:01<00:00, 123.78it/s] Loading 0: 84%|████████▎ | 243/291 [00:01<00:00, 145.21it/s] Loading 0: 91%|█████████ | 265/291 [00:01<00:00, 159.62it/s] Loading 0: 99%|█████████▊| 287/291 [00:06<00:00, 14.11it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-waduh-1-sft-l-7494-v2-mkmlizer: quantized model in 16.832s
hastagaras-waduh-1-sft-l-7494-v2-mkmlizer: Processed model Hastagaras/Waduh-1-SFT-llama3-8b in 35.272s
hastagaras-waduh-1-sft-l-7494-v2-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-waduh-1-sft-l-7494-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-waduh-1-sft-l-7494-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-waduh-1-sft-l-7494-v2
hastagaras-waduh-1-sft-l-7494-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-waduh-1-sft-l-7494-v2/config.json
hastagaras-waduh-1-sft-l-7494-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-waduh-1-sft-l-7494-v2/special_tokens_map.json
hastagaras-waduh-1-sft-l-7494-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-waduh-1-sft-l-7494-v2/tokenizer_config.json
hastagaras-waduh-1-sft-l-7494-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-waduh-1-sft-l-7494-v2/tokenizer.json
hastagaras-waduh-1-sft-l-7494-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-waduh-1-sft-l-7494-v2/flywheel_model.0.safetensors
hastagaras-waduh-1-sft-l-7494-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-waduh-1-sft-l-7494-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.
hastagaras-waduh-1-sft-l-7494-v2-mkmlizer: warnings.warn(
hastagaras-waduh-1-sft-l-7494-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.
hastagaras-waduh-1-sft-l-7494-v2-mkmlizer: warnings.warn(
hastagaras-waduh-1-sft-l-7494-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.
hastagaras-waduh-1-sft-l-7494-v2-mkmlizer: warnings.warn(
hastagaras-waduh-1-sft-l-7494-v2-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-waduh-1-sft-l-7494-v2-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-waduh-1-sft-l-7494-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-waduh-1-sft-l-7494-v2-mkmlizer: Saving duration: 0.230s
hastagaras-waduh-1-sft-l-7494-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.617s
hastagaras-waduh-1-sft-l-7494-v2-mkmlizer: creating bucket guanaco-reward-models
Job hastagaras-waduh-1-sft-l-7494-v2-mkmlizer completed after 62.65s with status: succeeded
Stopping job with name hastagaras-waduh-1-sft-l-7494-v2-mkmlizer
Pipeline stage MKMLizer completed in 66.22s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-waduh-1-sft-l-7494-v2
Waiting for inference service hastagaras-waduh-1-sft-l-7494-v2 to be ready
Inference service hastagaras-waduh-1-sft-l-7494-v2 ready after 30.172658920288086s
Pipeline stage ISVCDeployer completed in 37.69s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.247934103012085s
Received healthy response to inference request in 1.3137850761413574s
Received healthy response to inference request in 1.291642665863037s
Received healthy response to inference request in 1.261518955230713s
Received healthy response to inference request in 1.3336544036865234s
5 requests
0 failed requests
5th percentile: 1.2675436973571776
10th percentile: 1.2735684394836426
20th percentile: 1.2856179237365724
30th percentile: 1.2960711479187013
40th percentile: 1.3049281120300293
50th percentile: 1.3137850761413574
60th percentile: 1.3217328071594239
70th percentile: 1.3296805381774903
80th percentile: 1.5165103435516358
90th percentile: 1.8822222232818604
95th percentile: 2.0650781631469726
99th percentile: 2.2113629150390626
mean time: 1.4897070407867432
Pipeline stage StressChecker completed in 8.06s
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
hastagaras-waduh-1-sft-l_7494_v2 status is now deployed due to DeploymentManager action
hastagaras-waduh-1-sft-l_7494_v2 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics