submission_id: hastagaras-halu-8b-llama_6475_v1
developer_uid: Hastagaras
status: inactive
model_repo: Hastagaras/Halu-8B-Llama3-v0.35
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.95, '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\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: 2024-05-31T04:38:14+00:00
model_name: newhalu
model_eval_status: success
model_group: Hastagaras/Halu-8B-Llama
num_battles: 10900
num_wins: 5818
celo_rating: 1206.25
safety_score: 0.96
propriety_score: 0.2
propriety_total_count: 5.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: newhalu
ineligible_reason: propriety_total_count < 5000
language_model: Hastagaras/Halu-8B-Llama3-v0.35
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-05-30
win_ratio: 0.5337614678899083
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-halu-8b-llama-6475-v1-mkmlizer
Waiting for job on hastagaras-halu-8b-llama-6475-v1-mkmlizer to finish
hastagaras-halu-8b-llama-6475-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-halu-8b-llama-6475-v1-mkmlizer: ║ _____ __ __ ║
hastagaras-halu-8b-llama-6475-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-halu-8b-llama-6475-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-halu-8b-llama-6475-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-halu-8b-llama-6475-v1-mkmlizer: ║ /___/ ║
hastagaras-halu-8b-llama-6475-v1-mkmlizer: ║ ║
hastagaras-halu-8b-llama-6475-v1-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-halu-8b-llama-6475-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-halu-8b-llama-6475-v1-mkmlizer: ║ https://mk1.ai ║
hastagaras-halu-8b-llama-6475-v1-mkmlizer: ║ ║
hastagaras-halu-8b-llama-6475-v1-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-halu-8b-llama-6475-v1-mkmlizer: ║ belonging to: ║
hastagaras-halu-8b-llama-6475-v1-mkmlizer: ║ ║
hastagaras-halu-8b-llama-6475-v1-mkmlizer: ║ Chai Research Corp. ║
hastagaras-halu-8b-llama-6475-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-halu-8b-llama-6475-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-halu-8b-llama-6475-v1-mkmlizer: ║ ║
hastagaras-halu-8b-llama-6475-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-halu-8b-llama-6475-v1-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-llama-6475-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-halu-8b-llama-6475-v1-mkmlizer: Downloaded to shared memory in 34.244s
hastagaras-halu-8b-llama-6475-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-halu-8b-llama-6475-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-halu-8b-llama-6475-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:02, 128.13it/s] Loading 0: 11%|█ | 31/291 [00:00<00:01, 150.64it/s] Loading 0: 17%|█▋ | 49/291 [00:00<00:01, 159.20it/s] Loading 0: 23%|██▎ | 67/291 [00:00<00:01, 162.68it/s] Loading 0: 29%|██▉ | 84/291 [00:00<00:02, 86.52it/s] Loading 0: 35%|███▌ | 102/291 [00:00<00:01, 102.98it/s] Loading 0: 41%|████ | 120/291 [00:01<00:01, 118.80it/s] Loading 0: 47%|████▋ | 138/291 [00:01<00:01, 131.42it/s] Loading 0: 54%|█████▎ | 156/291 [00:01<00:00, 141.35it/s] Loading 0: 59%|█████▉ | 173/291 [00:01<00:00, 145.00it/s] Loading 0: 65%|██████▍ | 189/291 [00:01<00:01, 91.12it/s] Loading 0: 71%|███████ | 206/291 [00:01<00:00, 105.45it/s] Loading 0: 76%|███████▌ | 221/291 [00:01<00:00, 113.64it/s] Loading 0: 82%|████████▏ | 239/291 [00:01<00:00, 127.26it/s] Loading 0: 88%|████████▊ | 257/291 [00:02<00:00, 137.27it/s] Loading 0: 95%|█████████▍| 275/291 [00:02<00:00, 146.09it/s] Loading 0: 100%|██████████| 291/291 [00:07<00:00, 10.02it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-halu-8b-llama-6475-v1-mkmlizer: quantized model in 22.615s
hastagaras-halu-8b-llama-6475-v1-mkmlizer: Processed model Hastagaras/Halu-8B-Llama3-v0.35 in 59.401s
hastagaras-halu-8b-llama-6475-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-halu-8b-llama-6475-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-halu-8b-llama-6475-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-halu-8b-llama-6475-v1
hastagaras-halu-8b-llama-6475-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-6475-v1/tokenizer_config.json
hastagaras-halu-8b-llama-6475-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-6475-v1/config.json
hastagaras-halu-8b-llama-6475-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-6475-v1/special_tokens_map.json
hastagaras-halu-8b-llama-6475-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-6475-v1/tokenizer.json
hastagaras-halu-8b-llama-6475-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-halu-8b-llama-6475-v1/flywheel_model.0.safetensors
hastagaras-halu-8b-llama-6475-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-halu-8b-llama-6475-v1-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-llama-6475-v1-mkmlizer: warnings.warn(
hastagaras-halu-8b-llama-6475-v1-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-llama-6475-v1-mkmlizer: warnings.warn(
hastagaras-halu-8b-llama-6475-v1-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-llama-6475-v1-mkmlizer: warnings.warn(
hastagaras-halu-8b-llama-6475-v1-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-llama-6475-v1-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-halu-8b-llama-6475-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-halu-8b-llama-6475-v1-mkmlizer: Saving duration: 0.393s
hastagaras-halu-8b-llama-6475-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.260s
hastagaras-halu-8b-llama-6475-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-halu-8b-llama-6475-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-halu-8b-llama-6475-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-halu-8b-llama-6475-v1_reward
hastagaras-halu-8b-llama-6475-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-6475-v1_reward/special_tokens_map.json
hastagaras-halu-8b-llama-6475-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-6475-v1_reward/tokenizer_config.json
hastagaras-halu-8b-llama-6475-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-6475-v1_reward/config.json
hastagaras-halu-8b-llama-6475-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-halu-8b-llama-6475-v1_reward/merges.txt
hastagaras-halu-8b-llama-6475-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-6475-v1_reward/vocab.json
hastagaras-halu-8b-llama-6475-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-6475-v1_reward/tokenizer.json
hastagaras-halu-8b-llama-6475-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-halu-8b-llama-6475-v1_reward/reward.tensors
Job hastagaras-halu-8b-llama-6475-v1-mkmlizer completed after 93.32s with status: succeeded
Stopping job with name hastagaras-halu-8b-llama-6475-v1-mkmlizer
Pipeline stage MKMLizer completed in 94.04s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-halu-8b-llama-6475-v1
Waiting for inference service hastagaras-halu-8b-llama-6475-v1 to be ready
Inference service hastagaras-halu-8b-llama-6475-v1 ready after 40.25817012786865s
Pipeline stage ISVCDeployer completed in 46.24s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.169161319732666s
Received healthy response to inference request in 1.3336384296417236s
Received healthy response to inference request in 1.3176355361938477s
Received healthy response to inference request in 1.3025424480438232s
Received healthy response to inference request in 1.264343500137329s
5 requests
0 failed requests
5th percentile: 1.2719832897186278
10th percentile: 1.2796230792999268
20th percentile: 1.2949026584625245
30th percentile: 1.3055610656738281
40th percentile: 1.311598300933838
50th percentile: 1.3176355361938477
60th percentile: 1.3240366935729981
70th percentile: 1.3304378509521484
80th percentile: 1.5007430076599122
90th percentile: 1.834952163696289
95th percentile: 2.0020567417144775
99th percentile: 2.135740404129028
mean time: 1.477464246749878
Pipeline stage StressChecker completed in 8.04s
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 0.05s
M-Eval Dataset for topic stay_in_character is loaded
hastagaras-halu-8b-llama_6475_v1 status is now deployed due to DeploymentManager action
hastagaras-halu-8b-llama_6475_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics