submission_id: hastagaras-waduh-1-sft-l_7494_v4
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': 1.0, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 100, '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\nRoleplay 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: 2024-05-20T03:16:46+00:00
model_name: test
model_eval_status: success
model_group: Hastagaras/Waduh-1-SFT-l
num_battles: 23374
num_wins: 12948
celo_rating: 1197.47
safety_score: 0.97
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: test
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: 0.5539488320355951
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-waduh-1-sft-l-7494-v4-mkmlizer
Waiting for job on hastagaras-waduh-1-sft-l-7494-v4-mkmlizer to finish
Stopping job with name hastagaras-waduh-1-sft-l-7494-v4-mkmlizer
%s, retrying in %s seconds...
Starting job with name hastagaras-waduh-1-sft-l-7494-v4-mkmlizer
Waiting for job on hastagaras-waduh-1-sft-l-7494-v4-mkmlizer to finish
hastagaras-waduh-1-sft-l-7494-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-waduh-1-sft-l-7494-v4-mkmlizer: ║ _____ __ __ ║
hastagaras-waduh-1-sft-l-7494-v4-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-waduh-1-sft-l-7494-v4-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-waduh-1-sft-l-7494-v4-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-waduh-1-sft-l-7494-v4-mkmlizer: ║ /___/ ║
hastagaras-waduh-1-sft-l-7494-v4-mkmlizer: ║ ║
hastagaras-waduh-1-sft-l-7494-v4-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-waduh-1-sft-l-7494-v4-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-waduh-1-sft-l-7494-v4-mkmlizer: ║ https://mk1.ai ║
hastagaras-waduh-1-sft-l-7494-v4-mkmlizer: ║ ║
hastagaras-waduh-1-sft-l-7494-v4-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-waduh-1-sft-l-7494-v4-mkmlizer: ║ belonging to: ║
hastagaras-waduh-1-sft-l-7494-v4-mkmlizer: ║ ║
hastagaras-waduh-1-sft-l-7494-v4-mkmlizer: ║ Chai Research Corp. ║
hastagaras-waduh-1-sft-l-7494-v4-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-waduh-1-sft-l-7494-v4-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-waduh-1-sft-l-7494-v4-mkmlizer: ║ ║
hastagaras-waduh-1-sft-l-7494-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-waduh-1-sft-l-7494-v4-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-v4-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-waduh-1-sft-l-7494-v4-mkmlizer: Downloaded to shared memory in 17.724s
hastagaras-waduh-1-sft-l-7494-v4-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-waduh-1-sft-l-7494-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-waduh-1-sft-l-7494-v4-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 5%|▍ | 14/291 [00:00<00:01, 138.83it/s] Loading 0: 12%|█▏ | 34/291 [00:00<00:01, 174.56it/s] Loading 0: 19%|█▊ | 54/291 [00:00<00:01, 185.60it/s] Loading 0: 26%|██▌ | 75/291 [00:00<00:01, 190.63it/s] Loading 0: 33%|███▎ | 95/291 [00:00<00:02, 83.45it/s] Loading 0: 41%|████ | 120/291 [00:00<00:01, 111.07it/s] Loading 0: 48%|████▊ | 139/291 [00:01<00:01, 126.45it/s] Loading 0: 54%|█████▍ | 158/291 [00:01<00:00, 140.53it/s] Loading 0: 62%|██████▏ | 180/291 [00:01<00:00, 159.01it/s] Loading 0: 69%|██████▊ | 200/291 [00:01<00:00, 93.75it/s] Loading 0: 76%|███████▌ | 220/291 [00:01<00:00, 109.63it/s] Loading 0: 83%|████████▎ | 242/291 [00:01<00:00, 130.02it/s] Loading 0: 91%|█████████ | 264/291 [00:02<00:00, 148.55it/s] Loading 0: 97%|█████████▋| 283/291 [00:02<00:00, 157.39it/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-v4-mkmlizer: quantized model in 17.666s
hastagaras-waduh-1-sft-l-7494-v4-mkmlizer: Processed model Hastagaras/Waduh-1-SFT-llama3-8b in 36.482s
hastagaras-waduh-1-sft-l-7494-v4-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-waduh-1-sft-l-7494-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-waduh-1-sft-l-7494-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-waduh-1-sft-l-7494-v4
hastagaras-waduh-1-sft-l-7494-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-waduh-1-sft-l-7494-v4/special_tokens_map.json
hastagaras-waduh-1-sft-l-7494-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-waduh-1-sft-l-7494-v4/config.json
hastagaras-waduh-1-sft-l-7494-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-waduh-1-sft-l-7494-v4/tokenizer_config.json
hastagaras-waduh-1-sft-l-7494-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-waduh-1-sft-l-7494-v4/tokenizer.json
hastagaras-waduh-1-sft-l-7494-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-waduh-1-sft-l-7494-v4/flywheel_model.0.safetensors
hastagaras-waduh-1-sft-l-7494-v4-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-waduh-1-sft-l-7494-v4-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-v4-mkmlizer: warnings.warn(
hastagaras-waduh-1-sft-l-7494-v4-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-v4-mkmlizer: warnings.warn(
hastagaras-waduh-1-sft-l-7494-v4-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-v4-mkmlizer: warnings.warn(
hastagaras-waduh-1-sft-l-7494-v4-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-v4-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-waduh-1-sft-l-7494-v4-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-waduh-1-sft-l-7494-v4-mkmlizer: Saving duration: 0.279s
hastagaras-waduh-1-sft-l-7494-v4-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.309s
hastagaras-waduh-1-sft-l-7494-v4-mkmlizer: creating bucket guanaco-reward-models
hastagaras-waduh-1-sft-l-7494-v4-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-waduh-1-sft-l-7494-v4-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-waduh-1-sft-l-7494-v4_reward
hastagaras-waduh-1-sft-l-7494-v4-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-waduh-1-sft-l-7494-v4_reward/special_tokens_map.json
hastagaras-waduh-1-sft-l-7494-v4-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-waduh-1-sft-l-7494-v4_reward/vocab.json
hastagaras-waduh-1-sft-l-7494-v4-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-waduh-1-sft-l-7494-v4_reward/tokenizer_config.json
hastagaras-waduh-1-sft-l-7494-v4-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-waduh-1-sft-l-7494-v4_reward/config.json
hastagaras-waduh-1-sft-l-7494-v4-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-waduh-1-sft-l-7494-v4_reward/merges.txt
hastagaras-waduh-1-sft-l-7494-v4-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-waduh-1-sft-l-7494-v4_reward/tokenizer.json
hastagaras-waduh-1-sft-l-7494-v4-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-waduh-1-sft-l-7494-v4_reward/reward.tensors
Job hastagaras-waduh-1-sft-l-7494-v4-mkmlizer completed after 74.36s with status: succeeded
Stopping job with name hastagaras-waduh-1-sft-l-7494-v4-mkmlizer
Pipeline stage MKMLizer completed in 77.52s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-waduh-1-sft-l-7494-v4
Waiting for inference service hastagaras-waduh-1-sft-l-7494-v4 to be ready
Inference service hastagaras-waduh-1-sft-l-7494-v4 ready after 50.28473520278931s
Pipeline stage ISVCDeployer completed in 57.43s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2102346420288086s
Received healthy response to inference request in 1.3018298149108887s
Received healthy response to inference request in 1.2841336727142334s
Received healthy response to inference request in 1.3612170219421387s
Received healthy response to inference request in 1.2859060764312744s
5 requests
0 failed requests
5th percentile: 1.2844881534576416
10th percentile: 1.2848426342010497
20th percentile: 1.2855515956878663
30th percentile: 1.2890908241271972
40th percentile: 1.295460319519043
50th percentile: 1.3018298149108887
60th percentile: 1.3255846977233887
70th percentile: 1.3493395805358888
80th percentile: 1.5310205459594728
90th percentile: 1.8706275939941408
95th percentile: 2.0404311180114743
99th percentile: 2.176273937225342
mean time: 1.4886642456054688
Pipeline stage StressChecker completed in 8.17s
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 0.04s
M-Eval Dataset for topic stay_in_character is loaded
hastagaras-waduh-1-sft-l_7494_v4 status is now deployed due to DeploymentManager action
hastagaras-waduh-1-sft-l_7494_v4 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics