submission_id: hastagaras-halu-8b-llama_2564_v7
developer_uid: Hastagaras
status: inactive
model_repo: Hastagaras/Halu-8B-Llama3-v0.3
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.0, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 200, '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: 2024-05-26T04:17:38+00:00
model_name: morebattleplease
model_eval_status: success
model_group: Hastagaras/Halu-8B-Llama
num_battles: 10913
num_wins: 5998
celo_rating: 1209.54
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: morebattleplease
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: 2024-05-25
win_ratio: 0.5496197196004765
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-halu-8b-llama-2564-v7-mkmlizer
Waiting for job on hastagaras-halu-8b-llama-2564-v7-mkmlizer to finish
hastagaras-halu-8b-llama-2564-v7-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-halu-8b-llama-2564-v7-mkmlizer: ║ _____ __ __ ║
hastagaras-halu-8b-llama-2564-v7-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-halu-8b-llama-2564-v7-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-halu-8b-llama-2564-v7-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-halu-8b-llama-2564-v7-mkmlizer: ║ /___/ ║
hastagaras-halu-8b-llama-2564-v7-mkmlizer: ║ ║
hastagaras-halu-8b-llama-2564-v7-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-halu-8b-llama-2564-v7-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-halu-8b-llama-2564-v7-mkmlizer: ║ https://mk1.ai ║
hastagaras-halu-8b-llama-2564-v7-mkmlizer: ║ ║
hastagaras-halu-8b-llama-2564-v7-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-halu-8b-llama-2564-v7-mkmlizer: ║ belonging to: ║
hastagaras-halu-8b-llama-2564-v7-mkmlizer: ║ ║
hastagaras-halu-8b-llama-2564-v7-mkmlizer: ║ Chai Research Corp. ║
hastagaras-halu-8b-llama-2564-v7-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-halu-8b-llama-2564-v7-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-halu-8b-llama-2564-v7-mkmlizer: ║ ║
hastagaras-halu-8b-llama-2564-v7-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-halu-8b-llama-2564-v7-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-2564-v7-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-halu-8b-llama-2564-v7-mkmlizer: Downloaded to shared memory in 16.413s
hastagaras-halu-8b-llama-2564-v7-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-halu-8b-llama-2564-v7-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-halu-8b-llama-2564-v7-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:02, 123.78it/s] Loading 0: 10%|█ | 30/291 [00:00<00:01, 147.88it/s] Loading 0: 16%|█▋ | 48/291 [00:00<00:01, 154.15it/s] Loading 0: 23%|██▎ | 66/291 [00:00<00:01, 155.90it/s] Loading 0: 28%|██▊ | 82/291 [00:00<00:01, 156.33it/s] Loading 0: 34%|███▎ | 98/291 [00:00<00:02, 80.05it/s] Loading 0: 39%|███▉ | 113/291 [00:01<00:01, 91.87it/s] Loading 0: 45%|████▌ | 131/291 [00:01<00:01, 108.85it/s] Loading 0: 51%|█████ | 149/291 [00:01<00:01, 121.75it/s] Loading 0: 57%|█████▋ | 167/291 [00:01<00:00, 131.31it/s] Loading 0: 64%|██████▍ | 187/291 [00:01<00:01, 91.09it/s] Loading 0: 69%|██████▉ | 201/291 [00:01<00:00, 99.76it/s] Loading 0: 75%|███████▌ | 219/291 [00:01<00:00, 113.23it/s] Loading 0: 81%|████████▏ | 237/291 [00:02<00:00, 124.96it/s] Loading 0: 88%|████████▊ | 255/291 [00:02<00:00, 134.01it/s] Loading 0: 94%|█████████▍| 273/291 [00:02<00:00, 141.42it/s] Loading 0: 99%|█████████▉| 289/291 [00:07<00:00, 10.10it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-halu-8b-llama-2564-v7-mkmlizer: quantized model in 22.740s
hastagaras-halu-8b-llama-2564-v7-mkmlizer: Processed model Hastagaras/Halu-8B-Llama3-v0.3 in 41.727s
hastagaras-halu-8b-llama-2564-v7-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-halu-8b-llama-2564-v7-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-halu-8b-llama-2564-v7-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-halu-8b-llama-2564-v7
hastagaras-halu-8b-llama-2564-v7-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-2564-v7/special_tokens_map.json
hastagaras-halu-8b-llama-2564-v7-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-2564-v7/config.json
hastagaras-halu-8b-llama-2564-v7-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-2564-v7/tokenizer.json
hastagaras-halu-8b-llama-2564-v7-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-2564-v7/tokenizer_config.json
hastagaras-halu-8b-llama-2564-v7-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-halu-8b-llama-2564-v7/flywheel_model.0.safetensors
hastagaras-halu-8b-llama-2564-v7-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-halu-8b-llama-2564-v7-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-2564-v7-mkmlizer: warnings.warn(
hastagaras-halu-8b-llama-2564-v7-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-2564-v7-mkmlizer: warnings.warn(
hastagaras-halu-8b-llama-2564-v7-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-2564-v7-mkmlizer: warnings.warn(
hastagaras-halu-8b-llama-2564-v7-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-2564-v7-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-halu-8b-llama-2564-v7-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-halu-8b-llama-2564-v7-mkmlizer: Saving duration: 0.410s
hastagaras-halu-8b-llama-2564-v7-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 6.587s
hastagaras-halu-8b-llama-2564-v7-mkmlizer: creating bucket guanaco-reward-models
hastagaras-halu-8b-llama-2564-v7-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-halu-8b-llama-2564-v7-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-halu-8b-llama-2564-v7_reward
hastagaras-halu-8b-llama-2564-v7-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-2564-v7_reward/config.json
hastagaras-halu-8b-llama-2564-v7-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-2564-v7_reward/tokenizer_config.json
hastagaras-halu-8b-llama-2564-v7-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-2564-v7_reward/special_tokens_map.json
hastagaras-halu-8b-llama-2564-v7-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-halu-8b-llama-2564-v7_reward/merges.txt
hastagaras-halu-8b-llama-2564-v7-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-2564-v7_reward/vocab.json
hastagaras-halu-8b-llama-2564-v7-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-2564-v7_reward/tokenizer.json
hastagaras-halu-8b-llama-2564-v7-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-halu-8b-llama-2564-v7_reward/reward.tensors
Job hastagaras-halu-8b-llama-2564-v7-mkmlizer completed after 72.89s with status: succeeded
Stopping job with name hastagaras-halu-8b-llama-2564-v7-mkmlizer
Pipeline stage MKMLizer completed in 77.81s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-halu-8b-llama-2564-v7
Waiting for inference service hastagaras-halu-8b-llama-2564-v7 to be ready
Inference service hastagaras-halu-8b-llama-2564-v7 ready after 30.164358139038086s
Pipeline stage ISVCDeployer completed in 37.98s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1017043590545654s
Received healthy response to inference request in 1.3982830047607422s
Received healthy response to inference request in 1.3365569114685059s
Received healthy response to inference request in 1.320894479751587s
Received healthy response to inference request in 1.275641679763794s
5 requests
0 failed requests
5th percentile: 1.2846922397613525
10th percentile: 1.293742799758911
20th percentile: 1.3118439197540284
30th percentile: 1.3240269660949706
40th percentile: 1.3302919387817382
50th percentile: 1.3365569114685059
60th percentile: 1.3612473487854004
70th percentile: 1.385937786102295
80th percentile: 1.538967275619507
90th percentile: 1.8203358173370363
95th percentile: 1.9610200881958006
99th percentile: 2.0735675048828126
mean time: 1.4866160869598388
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 0.03s
M-Eval Dataset for topic stay_in_character is loaded
hastagaras-halu-8b-llama_2564_v7 status is now deployed due to DeploymentManager action
hastagaras-halu-8b-llama_2564_v7 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics