submission_id: hastagaras-halu-8b-llam_2564_v13
developer_uid: Jellywibble
status: inactive
model_repo: Hastagaras/Halu-8B-Llama3-v0.3
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.05, 'top_p': 0.95, 'min_p': 0.1, '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\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: 2024-06-03T22:18:32+00:00
model_name: HWEHWHEHW
model_eval_status: success
model_group: Hastagaras/Halu-8B-Llama
num_battles: 8809
num_wins: 4795
celo_rating: 1206.41
safety_score: 0.96
propriety_score: 0.625
propriety_total_count: 232.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: HWEHWHEHW
ineligible_reason: propriety_total_count < 5000
language_model: Hastagaras/Halu-8B-Llama3-v0.3
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-03
win_ratio: 0.5443296628448178
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-halu-8b-llam-2564-v13-mkmlizer
Waiting for job on hastagaras-halu-8b-llam-2564-v13-mkmlizer to finish
hastagaras-halu-8b-llam-2564-v13-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-halu-8b-llam-2564-v13-mkmlizer: ║ _____ __ __ ║
hastagaras-halu-8b-llam-2564-v13-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-halu-8b-llam-2564-v13-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-halu-8b-llam-2564-v13-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-halu-8b-llam-2564-v13-mkmlizer: ║ /___/ ║
hastagaras-halu-8b-llam-2564-v13-mkmlizer: ║ ║
hastagaras-halu-8b-llam-2564-v13-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-halu-8b-llam-2564-v13-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-halu-8b-llam-2564-v13-mkmlizer: ║ https://mk1.ai ║
hastagaras-halu-8b-llam-2564-v13-mkmlizer: ║ ║
hastagaras-halu-8b-llam-2564-v13-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-halu-8b-llam-2564-v13-mkmlizer: ║ belonging to: ║
hastagaras-halu-8b-llam-2564-v13-mkmlizer: ║ ║
hastagaras-halu-8b-llam-2564-v13-mkmlizer: ║ Chai Research Corp. ║
hastagaras-halu-8b-llam-2564-v13-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-halu-8b-llam-2564-v13-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-halu-8b-llam-2564-v13-mkmlizer: ║ ║
hastagaras-halu-8b-llam-2564-v13-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-halu-8b-llam-2564-v13-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-halu-8b-llam-2564-v13-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-halu-8b-llam-2564-v13-mkmlizer: Downloaded to shared memory in 18.173s
hastagaras-halu-8b-llam-2564-v13-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-halu-8b-llam-2564-v13-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-halu-8b-llam-2564-v13-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:02, 126.55it/s] Loading 0: 11%|█ | 31/291 [00:00<00:01, 147.22it/s] Loading 0: 17%|█▋ | 49/291 [00:00<00:01, 149.81it/s] Loading 0: 23%|██▎ | 66/291 [00:00<00:01, 156.40it/s] Loading 0: 29%|██▊ | 83/291 [00:00<00:02, 83.30it/s] Loading 0: 33%|███▎ | 97/291 [00:00<00:02, 94.66it/s] Loading 0: 39%|███▉ | 113/291 [00:01<00:01, 107.31it/s] Loading 0: 45%|████▌ | 131/291 [00:01<00:01, 121.77it/s] Loading 0: 51%|█████ | 149/291 [00:01<00:01, 133.13it/s] Loading 0: 57%|█████▋ | 167/291 [00:01<00:00, 142.19it/s] Loading 0: 64%|██████▍ | 187/291 [00:01<00:01, 96.98it/s] Loading 0: 69%|██████▉ | 202/291 [00:01<00:00, 104.09it/s] Loading 0: 76%|███████▌ | 220/291 [00:01<00:00, 116.95it/s] Loading 0: 82%|████████▏ | 238/291 [00:02<00:00, 128.63it/s] Loading 0: 88%|████████▊ | 256/291 [00:02<00:00, 138.18it/s] Loading 0: 94%|█████████▍| 274/291 [00:02<00:00, 145.47it/s] Loading 0: 100%|█████████▉| 290/291 [00:07<00:00, 10.01it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-halu-8b-llam-2564-v13-mkmlizer: quantized model in 22.873s
hastagaras-halu-8b-llam-2564-v13-mkmlizer: Processed model Hastagaras/Halu-8B-Llama3-v0.3 in 43.568s
hastagaras-halu-8b-llam-2564-v13-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-halu-8b-llam-2564-v13-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-halu-8b-llam-2564-v13-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-halu-8b-llam-2564-v13
hastagaras-halu-8b-llam-2564-v13-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-halu-8b-llam-2564-v13/tokenizer_config.json
hastagaras-halu-8b-llam-2564-v13-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-halu-8b-llam-2564-v13/config.json
hastagaras-halu-8b-llam-2564-v13-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-halu-8b-llam-2564-v13/special_tokens_map.json
hastagaras-halu-8b-llam-2564-v13-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-halu-8b-llam-2564-v13/tokenizer.json
hastagaras-halu-8b-llam-2564-v13-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-halu-8b-llam-2564-v13/flywheel_model.0.safetensors
hastagaras-halu-8b-llam-2564-v13-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-halu-8b-llam-2564-v13-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-halu-8b-llam-2564-v13-mkmlizer: warnings.warn(
hastagaras-halu-8b-llam-2564-v13-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-halu-8b-llam-2564-v13-mkmlizer: warnings.warn(
hastagaras-halu-8b-llam-2564-v13-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-halu-8b-llam-2564-v13-mkmlizer: warnings.warn(
hastagaras-halu-8b-llam-2564-v13-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-halu-8b-llam-2564-v13-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-halu-8b-llam-2564-v13-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-halu-8b-llam-2564-v13-mkmlizer: Saving duration: 0.412s
hastagaras-halu-8b-llam-2564-v13-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 5.765s
hastagaras-halu-8b-llam-2564-v13-mkmlizer: creating bucket guanaco-reward-models
hastagaras-halu-8b-llam-2564-v13-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-halu-8b-llam-2564-v13-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-halu-8b-llam-2564-v13_reward
hastagaras-halu-8b-llam-2564-v13-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-halu-8b-llam-2564-v13_reward/special_tokens_map.json
hastagaras-halu-8b-llam-2564-v13-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-halu-8b-llam-2564-v13_reward/tokenizer_config.json
hastagaras-halu-8b-llam-2564-v13-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-halu-8b-llam-2564-v13_reward/config.json
hastagaras-halu-8b-llam-2564-v13-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-halu-8b-llam-2564-v13_reward/vocab.json
hastagaras-halu-8b-llam-2564-v13-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-halu-8b-llam-2564-v13_reward/merges.txt
hastagaras-halu-8b-llam-2564-v13-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-halu-8b-llam-2564-v13_reward/tokenizer.json
hastagaras-halu-8b-llam-2564-v13-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-halu-8b-llam-2564-v13_reward/reward.tensors
Job hastagaras-halu-8b-llam-2564-v13-mkmlizer completed after 73.73s with status: succeeded
Stopping job with name hastagaras-halu-8b-llam-2564-v13-mkmlizer
Pipeline stage MKMLizer completed in 78.31s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-halu-8b-llam-2564-v13
Waiting for inference service hastagaras-halu-8b-llam-2564-v13 to be ready
Inference service hastagaras-halu-8b-llam-2564-v13 ready after 40.26809072494507s
Pipeline stage ISVCDeployer completed in 48.35s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0863449573516846s
Received healthy response to inference request in 1.3613183498382568s
Received healthy response to inference request in 1.3375751972198486s
Received healthy response to inference request in 1.3061621189117432s
Received healthy response to inference request in 1.2511365413665771s
5 requests
0 failed requests
5th percentile: 1.2621416568756103
10th percentile: 1.2731467723846435
20th percentile: 1.29515700340271
30th percentile: 1.3124447345733643
40th percentile: 1.3250099658966064
50th percentile: 1.3375751972198486
60th percentile: 1.347072458267212
70th percentile: 1.3565697193145752
80th percentile: 1.5063236713409425
90th percentile: 1.7963343143463135
95th percentile: 1.941339635848999
99th percentile: 2.0573438930511476
mean time: 1.468507432937622
Pipeline stage StressChecker completed in 8.05s
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-halu-8b-llam_2564_v13 status is now deployed due to DeploymentManager action
M-Eval Dataset for topic stay_in_character is loaded
hastagaras-halu-8b-llam_2564_v13 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics