submission_id: hastagaras-waduh-1-sft-l_7494_v3
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': 1.05, '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: 2024-05-20T01:11:19+00:00
model_name: hopefully-fixed
model_eval_status: success
model_group: Hastagaras/Waduh-1-SFT-l
num_battles: 26437
num_wins: 14028
celo_rating: 1195.61
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: 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: 0.530619964443772
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-waduh-1-sft-l-7494-v3-mkmlizer
Waiting for job on hastagaras-waduh-1-sft-l-7494-v3-mkmlizer to finish
hastagaras-waduh-1-sft-l-7494-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-waduh-1-sft-l-7494-v3-mkmlizer: ║ _____ __ __ ║
hastagaras-waduh-1-sft-l-7494-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-waduh-1-sft-l-7494-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-waduh-1-sft-l-7494-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-waduh-1-sft-l-7494-v3-mkmlizer: ║ /___/ ║
hastagaras-waduh-1-sft-l-7494-v3-mkmlizer: ║ ║
hastagaras-waduh-1-sft-l-7494-v3-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-waduh-1-sft-l-7494-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-waduh-1-sft-l-7494-v3-mkmlizer: ║ https://mk1.ai ║
hastagaras-waduh-1-sft-l-7494-v3-mkmlizer: ║ ║
hastagaras-waduh-1-sft-l-7494-v3-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-waduh-1-sft-l-7494-v3-mkmlizer: ║ belonging to: ║
hastagaras-waduh-1-sft-l-7494-v3-mkmlizer: ║ ║
hastagaras-waduh-1-sft-l-7494-v3-mkmlizer: ║ Chai Research Corp. ║
hastagaras-waduh-1-sft-l-7494-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-waduh-1-sft-l-7494-v3-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-waduh-1-sft-l-7494-v3-mkmlizer: ║ ║
hastagaras-waduh-1-sft-l-7494-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-waduh-1-sft-l-7494-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.
hastagaras-waduh-1-sft-l-7494-v3-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-waduh-1-sft-l-7494-v3-mkmlizer: Downloaded to shared memory in 17.091s
hastagaras-waduh-1-sft-l-7494-v3-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-waduh-1-sft-l-7494-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-waduh-1-sft-l-7494-v3-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 5%|▍ | 14/291 [00:00<00:01, 138.61it/s] Loading 0: 12%|█▏ | 35/291 [00:00<00:01, 176.98it/s] Loading 0: 20%|█▉ | 57/291 [00:00<00:01, 187.87it/s] Loading 0: 26%|██▌ | 76/291 [00:00<00:01, 183.50it/s] Loading 0: 33%|███▎ | 95/291 [00:00<00:02, 81.87it/s] Loading 0: 40%|████ | 117/291 [00:00<00:01, 106.18it/s] Loading 0: 47%|████▋ | 138/291 [00:01<00:01, 125.91it/s] Loading 0: 54%|█████▍ | 157/291 [00:01<00:00, 139.83it/s] Loading 0: 62%|██████▏ | 180/291 [00:01<00:00, 156.52it/s] Loading 0: 68%|██████▊ | 199/291 [00:01<00:01, 89.74it/s] Loading 0: 76%|███████▌ | 220/291 [00:01<00:00, 107.50it/s] Loading 0: 83%|████████▎ | 242/291 [00:01<00:00, 127.88it/s] Loading 0: 91%|█████████ | 264/291 [00:02<00:00, 146.27it/s] Loading 0: 97%|█████████▋| 283/291 [00:02<00:00, 155.86it/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-v3-mkmlizer: quantized model in 17.655s
hastagaras-waduh-1-sft-l-7494-v3-mkmlizer: Processed model Hastagaras/Waduh-1-SFT-llama3-8b in 35.873s
hastagaras-waduh-1-sft-l-7494-v3-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-waduh-1-sft-l-7494-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-waduh-1-sft-l-7494-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-waduh-1-sft-l-7494-v3
hastagaras-waduh-1-sft-l-7494-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-waduh-1-sft-l-7494-v3/config.json
hastagaras-waduh-1-sft-l-7494-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-waduh-1-sft-l-7494-v3/tokenizer_config.json
hastagaras-waduh-1-sft-l-7494-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-waduh-1-sft-l-7494-v3/tokenizer.json
hastagaras-waduh-1-sft-l-7494-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-waduh-1-sft-l-7494-v3/special_tokens_map.json
hastagaras-waduh-1-sft-l-7494-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-waduh-1-sft-l-7494-v3/flywheel_model.0.safetensors
hastagaras-waduh-1-sft-l-7494-v3-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-waduh-1-sft-l-7494-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.
hastagaras-waduh-1-sft-l-7494-v3-mkmlizer: warnings.warn(
hastagaras-waduh-1-sft-l-7494-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.
hastagaras-waduh-1-sft-l-7494-v3-mkmlizer: warnings.warn(
hastagaras-waduh-1-sft-l-7494-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.
hastagaras-waduh-1-sft-l-7494-v3-mkmlizer: warnings.warn(
hastagaras-waduh-1-sft-l-7494-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()
hastagaras-waduh-1-sft-l-7494-v3-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-waduh-1-sft-l-7494-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-waduh-1-sft-l-7494-v3-mkmlizer: Saving duration: 0.262s
hastagaras-waduh-1-sft-l-7494-v3-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.805s
hastagaras-waduh-1-sft-l-7494-v3-mkmlizer: creating bucket guanaco-reward-models
hastagaras-waduh-1-sft-l-7494-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-waduh-1-sft-l-7494-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-waduh-1-sft-l-7494-v3_reward
hastagaras-waduh-1-sft-l-7494-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-waduh-1-sft-l-7494-v3_reward/config.json
hastagaras-waduh-1-sft-l-7494-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-waduh-1-sft-l-7494-v3_reward/special_tokens_map.json
hastagaras-waduh-1-sft-l-7494-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-waduh-1-sft-l-7494-v3_reward/merges.txt
hastagaras-waduh-1-sft-l-7494-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-waduh-1-sft-l-7494-v3_reward/vocab.json
hastagaras-waduh-1-sft-l-7494-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-waduh-1-sft-l-7494-v3_reward/tokenizer_config.json
hastagaras-waduh-1-sft-l-7494-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-waduh-1-sft-l-7494-v3_reward/tokenizer.json
hastagaras-waduh-1-sft-l-7494-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-waduh-1-sft-l-7494-v3_reward/reward.tensors
Job hastagaras-waduh-1-sft-l-7494-v3-mkmlizer completed after 64.14s with status: succeeded
Stopping job with name hastagaras-waduh-1-sft-l-7494-v3-mkmlizer
Pipeline stage MKMLizer completed in 67.61s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-waduh-1-sft-l-7494-v3
Waiting for inference service hastagaras-waduh-1-sft-l-7494-v3 to be ready
Inference service hastagaras-waduh-1-sft-l-7494-v3 ready after 30.202552556991577s
Pipeline stage ISVCDeployer completed in 36.95s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.230670928955078s
Received healthy response to inference request in 1.2953197956085205s
Received healthy response to inference request in 1.2734436988830566s
Received healthy response to inference request in 1.2684574127197266s
Received healthy response to inference request in 1.3056950569152832s
5 requests
0 failed requests
5th percentile: 1.2694546699523925
10th percentile: 1.2704519271850585
20th percentile: 1.2724464416503907
30th percentile: 1.2778189182281494
40th percentile: 1.286569356918335
50th percentile: 1.2953197956085205
60th percentile: 1.2994699001312255
70th percentile: 1.3036200046539306
80th percentile: 1.4906902313232424
90th percentile: 1.8606805801391602
95th percentile: 2.045675754547119
99th percentile: 2.1936718940734865
mean time: 1.474717378616333
Pipeline stage StressChecker completed in 8.02s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.03s
Running M-Eval for topic stay_in_character
hastagaras-waduh-1-sft-l_7494_v3 status is now deployed due to DeploymentManager action
M-Eval Dataset for topic stay_in_character is loaded
hastagaras-waduh-1-sft-l_7494_v3 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics