submission_id: hastagaras-halu-8b-llam_2564_v14
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: 2024-06-03T22:31:00+00:00
model_name: HWEHWHEHW
model_eval_status: success
model_group: Hastagaras/Halu-8B-Llama
num_battles: 6938
num_wins: 3691
celo_rating: 1199.96
safety_score: 0.97
propriety_score: 0.6699507389162561
propriety_total_count: 203.0
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: 0.531997693859902
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-halu-8b-llam-2564-v14-mkmlizer
Waiting for job on hastagaras-halu-8b-llam-2564-v14-mkmlizer to finish
hastagaras-halu-8b-llam-2564-v14-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-halu-8b-llam-2564-v14-mkmlizer: ║ _____ __ __ ║
hastagaras-halu-8b-llam-2564-v14-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-halu-8b-llam-2564-v14-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-halu-8b-llam-2564-v14-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-halu-8b-llam-2564-v14-mkmlizer: ║ /___/ ║
hastagaras-halu-8b-llam-2564-v14-mkmlizer: ║ ║
hastagaras-halu-8b-llam-2564-v14-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-halu-8b-llam-2564-v14-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-halu-8b-llam-2564-v14-mkmlizer: ║ https://mk1.ai ║
hastagaras-halu-8b-llam-2564-v14-mkmlizer: ║ ║
hastagaras-halu-8b-llam-2564-v14-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-halu-8b-llam-2564-v14-mkmlizer: ║ belonging to: ║
hastagaras-halu-8b-llam-2564-v14-mkmlizer: ║ ║
hastagaras-halu-8b-llam-2564-v14-mkmlizer: ║ Chai Research Corp. ║
hastagaras-halu-8b-llam-2564-v14-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-halu-8b-llam-2564-v14-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-halu-8b-llam-2564-v14-mkmlizer: ║ ║
hastagaras-halu-8b-llam-2564-v14-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-halu-8b-llam-2564-v14-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-v14-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-halu-8b-llam-2564-v14-mkmlizer: Downloaded to shared memory in 15.647s
hastagaras-halu-8b-llam-2564-v14-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-halu-8b-llam-2564-v14-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-halu-8b-llam-2564-v14-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 5%|▌ | 15/291 [00:00<00:01, 149.36it/s] Loading 0: 12%|█▏ | 36/291 [00:00<00:01, 182.21it/s] Loading 0: 20%|█▉ | 57/291 [00:00<00:01, 189.69it/s] Loading 0: 26%|██▌ | 76/291 [00:00<00:01, 186.45it/s] Loading 0: 33%|███▎ | 95/291 [00:00<00:02, 85.81it/s] Loading 0: 41%|████ | 118/291 [00:00<00:01, 112.58it/s] Loading 0: 47%|████▋ | 138/291 [00:01<00:01, 130.91it/s] Loading 0: 54%|█████▍ | 157/291 [00:01<00:00, 144.52it/s] Loading 0: 62%|██████▏ | 180/291 [00:01<00:00, 162.83it/s] Loading 0: 69%|██████▊ | 200/291 [00:01<00:00, 99.86it/s] Loading 0: 75%|███████▌ | 219/291 [00:01<00:00, 115.71it/s] Loading 0: 82%|████████▏ | 238/291 [00:01<00:00, 130.40it/s] Loading 0: 89%|████████▉ | 260/291 [00:01<00:00, 149.67it/s] Loading 0: 97%|█████████▋| 281/291 [00:02<00:00, 164.16it/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-v14-mkmlizer: quantized model in 17.329s
hastagaras-halu-8b-llam-2564-v14-mkmlizer: Processed model Hastagaras/Halu-8B-Llama3-v0.3 in 34.034s
hastagaras-halu-8b-llam-2564-v14-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-halu-8b-llam-2564-v14-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-halu-8b-llam-2564-v14-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-halu-8b-llam-2564-v14
hastagaras-halu-8b-llam-2564-v14-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-halu-8b-llam-2564-v14/special_tokens_map.json
hastagaras-halu-8b-llam-2564-v14-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-halu-8b-llam-2564-v14/tokenizer_config.json
hastagaras-halu-8b-llam-2564-v14-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-halu-8b-llam-2564-v14/config.json
hastagaras-halu-8b-llam-2564-v14-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-halu-8b-llam-2564-v14/tokenizer.json
hastagaras-halu-8b-llam-2564-v14-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-halu-8b-llam-2564-v14/flywheel_model.0.safetensors
hastagaras-halu-8b-llam-2564-v14-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-halu-8b-llam-2564-v14-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-v14-mkmlizer: warnings.warn(
hastagaras-halu-8b-llam-2564-v14-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-v14-mkmlizer: warnings.warn(
hastagaras-halu-8b-llam-2564-v14-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-v14-mkmlizer: warnings.warn(
hastagaras-halu-8b-llam-2564-v14-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-v14-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-halu-8b-llam-2564-v14-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-halu-8b-llam-2564-v14-mkmlizer: Saving duration: 0.265s
hastagaras-halu-8b-llam-2564-v14-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.570s
hastagaras-halu-8b-llam-2564-v14-mkmlizer: creating bucket guanaco-reward-models
hastagaras-halu-8b-llam-2564-v14-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-halu-8b-llam-2564-v14-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-halu-8b-llam-2564-v14_reward
hastagaras-halu-8b-llam-2564-v14-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-halu-8b-llam-2564-v14_reward/config.json
hastagaras-halu-8b-llam-2564-v14-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-halu-8b-llam-2564-v14_reward/tokenizer_config.json
hastagaras-halu-8b-llam-2564-v14-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-halu-8b-llam-2564-v14_reward/special_tokens_map.json
hastagaras-halu-8b-llam-2564-v14-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-halu-8b-llam-2564-v14_reward/vocab.json
hastagaras-halu-8b-llam-2564-v14-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-halu-8b-llam-2564-v14_reward/merges.txt
hastagaras-halu-8b-llam-2564-v14-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-halu-8b-llam-2564-v14_reward/tokenizer.json
hastagaras-halu-8b-llam-2564-v14-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-halu-8b-llam-2564-v14_reward/reward.tensors
Job hastagaras-halu-8b-llam-2564-v14-mkmlizer completed after 52.5s with status: succeeded
Stopping job with name hastagaras-halu-8b-llam-2564-v14-mkmlizer
Pipeline stage MKMLizer completed in 57.78s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-halu-8b-llam-2564-v14
Waiting for inference service hastagaras-halu-8b-llam-2564-v14 to be ready
Inference service hastagaras-halu-8b-llam-2564-v14 ready after 30.21272563934326s
Pipeline stage ISVCDeployer completed in 38.25s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1540513038635254s
Received healthy response to inference request in 1.343327522277832s
Received healthy response to inference request in 1.3494858741760254s
Received healthy response to inference request in 1.3000304698944092s
Received healthy response to inference request in 1.2383344173431396s
5 requests
0 failed requests
5th percentile: 1.2506736278533936
10th percentile: 1.2630128383636474
20th percentile: 1.2876912593841552
30th percentile: 1.3086898803710938
40th percentile: 1.3260087013244628
50th percentile: 1.343327522277832
60th percentile: 1.3457908630371094
70th percentile: 1.3482542037963867
80th percentile: 1.5103989601135255
90th percentile: 1.8322251319885254
95th percentile: 1.9931382179260253
99th percentile: 2.1218686866760255
mean time: 1.4770459175109862
Pipeline stage StressChecker completed in 8.03s
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-halu-8b-llam_2564_v14 status is now deployed due to DeploymentManager action
hastagaras-halu-8b-llam_2564_v14 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics