submission_id: hastagaras-halu-8b-llama_3117_v2
developer_uid: Hastagaras
status: inactive
model_repo: Hastagaras/Halu-8B-Llama3-v0.2
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: 2024-05-24T04:28:30+00:00
model_name: HALUUUU
model_eval_status: success
model_group: Hastagaras/Halu-8B-Llama
num_battles: 7975
num_wins: 4253
celo_rating: 1203.24
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: HALUUUU
ineligible_reason: propriety_total_count < 5000
language_model: Hastagaras/Halu-8B-Llama3-v0.2
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-05-23
win_ratio: 0.5332915360501568
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-halu-8b-llama-3117-v2-mkmlizer
Waiting for job on hastagaras-halu-8b-llama-3117-v2-mkmlizer to finish
hastagaras-halu-8b-llama-3117-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-halu-8b-llama-3117-v2-mkmlizer: ║ _____ __ __ ║
hastagaras-halu-8b-llama-3117-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-halu-8b-llama-3117-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-halu-8b-llama-3117-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-halu-8b-llama-3117-v2-mkmlizer: ║ /___/ ║
hastagaras-halu-8b-llama-3117-v2-mkmlizer: ║ ║
hastagaras-halu-8b-llama-3117-v2-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-halu-8b-llama-3117-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-halu-8b-llama-3117-v2-mkmlizer: ║ https://mk1.ai ║
hastagaras-halu-8b-llama-3117-v2-mkmlizer: ║ ║
hastagaras-halu-8b-llama-3117-v2-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-halu-8b-llama-3117-v2-mkmlizer: ║ belonging to: ║
hastagaras-halu-8b-llama-3117-v2-mkmlizer: ║ ║
hastagaras-halu-8b-llama-3117-v2-mkmlizer: ║ Chai Research Corp. ║
hastagaras-halu-8b-llama-3117-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-halu-8b-llama-3117-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-halu-8b-llama-3117-v2-mkmlizer: ║ ║
hastagaras-halu-8b-llama-3117-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-halu-8b-llama-3117-v2-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-3117-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-halu-8b-llama-3117-v2-mkmlizer: Downloaded to shared memory in 42.353s
hastagaras-halu-8b-llama-3117-v2-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-halu-8b-llama-3117-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-halu-8b-llama-3117-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 12/291 [00:00<00:02, 116.05it/s] Loading 0: 8%|▊ | 24/291 [00:00<00:02, 113.11it/s] Loading 0: 13%|█▎ | 39/291 [00:00<00:02, 124.60it/s] Loading 0: 18%|█▊ | 52/291 [00:00<00:02, 117.10it/s] Loading 0: 23%|██▎ | 67/291 [00:00<00:01, 121.00it/s] Loading 0: 27%|██▋ | 80/291 [00:00<00:01, 121.90it/s] Loading 0: 32%|███▏ | 93/291 [00:01<00:03, 65.74it/s] Loading 0: 35%|███▌ | 103/291 [00:01<00:02, 72.08it/s] Loading 0: 39%|███▉ | 113/291 [00:01<00:02, 77.37it/s] Loading 0: 44%|████▍ | 129/291 [00:01<00:01, 92.95it/s] Loading 0: 48%|████▊ | 140/291 [00:01<00:01, 94.03it/s] Loading 0: 54%|█████▎ | 156/291 [00:01<00:01, 106.85it/s] Loading 0: 58%|█████▊ | 168/291 [00:01<00:01, 106.33it/s] Loading 0: 62%|██████▏ | 181/291 [00:01<00:01, 108.53it/s] Loading 0: 66%|██████▋ | 193/291 [00:02<00:01, 66.75it/s] Loading 0: 71%|███████ | 206/291 [00:02<00:01, 78.37it/s] Loading 0: 75%|███████▌ | 219/291 [00:02<00:00, 88.56it/s] Loading 0: 79%|███████▉ | 230/291 [00:02<00:00, 88.41it/s] Loading 0: 85%|████████▍ | 246/291 [00:02<00:00, 101.29it/s] Loading 0: 89%|████████▊ | 258/291 [00:02<00:00, 104.66it/s] Loading 0: 94%|█████████▍| 273/291 [00:02<00:00, 115.25it/s] Loading 0: 98%|█████████▊| 286/291 [00:02<00:00, 116.48it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-halu-8b-llama-3117-v2-mkmlizer: quantized model in 23.834s
hastagaras-halu-8b-llama-3117-v2-mkmlizer: Processed model Hastagaras/Halu-8B-Llama3-v0.2 in 68.706s
hastagaras-halu-8b-llama-3117-v2-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-halu-8b-llama-3117-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-halu-8b-llama-3117-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-halu-8b-llama-3117-v2
hastagaras-halu-8b-llama-3117-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-3117-v2/config.json
hastagaras-halu-8b-llama-3117-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-3117-v2/special_tokens_map.json
hastagaras-halu-8b-llama-3117-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-3117-v2/tokenizer_config.json
hastagaras-halu-8b-llama-3117-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-3117-v2/tokenizer.json
hastagaras-halu-8b-llama-3117-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-halu-8b-llama-3117-v2/flywheel_model.0.safetensors
hastagaras-halu-8b-llama-3117-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-halu-8b-llama-3117-v2-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-3117-v2-mkmlizer: warnings.warn(
hastagaras-halu-8b-llama-3117-v2-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-3117-v2-mkmlizer: warnings.warn(
hastagaras-halu-8b-llama-3117-v2-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-3117-v2-mkmlizer: warnings.warn(
hastagaras-halu-8b-llama-3117-v2-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-3117-v2-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-halu-8b-llama-3117-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-halu-8b-llama-3117-v2-mkmlizer: Saving duration: 0.517s
hastagaras-halu-8b-llama-3117-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 12.814s
hastagaras-halu-8b-llama-3117-v2-mkmlizer: creating bucket guanaco-reward-models
hastagaras-halu-8b-llama-3117-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-halu-8b-llama-3117-v2_reward/reward.tensors
Job hastagaras-halu-8b-llama-3117-v2-mkmlizer completed after 113.66s with status: succeeded
Stopping job with name hastagaras-halu-8b-llama-3117-v2-mkmlizer
Pipeline stage MKMLizer completed in 118.30s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-halu-8b-llama-3117-v2
Waiting for inference service hastagaras-halu-8b-llama-3117-v2 to be ready
Inference service hastagaras-halu-8b-llama-3117-v2 ready after 110.53965473175049s
Pipeline stage ISVCDeployer completed in 118.16s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1686010360717773s
Received healthy response to inference request in 1.3131635189056396s
Received healthy response to inference request in 1.259124755859375s
Received healthy response to inference request in 1.2814843654632568s
Received healthy response to inference request in 1.2508680820465088s
5 requests
0 failed requests
5th percentile: 1.252519416809082
10th percentile: 1.2541707515716554
20th percentile: 1.2574734210968017
30th percentile: 1.2635966777801513
40th percentile: 1.272540521621704
50th percentile: 1.2814843654632568
60th percentile: 1.29415602684021
70th percentile: 1.306827688217163
80th percentile: 1.4842510223388674
90th percentile: 1.8264260292053223
95th percentile: 1.9975135326385496
99th percentile: 2.134383535385132
mean time: 1.4546483516693116
Pipeline stage StressChecker completed in 7.91s
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-llama_3117_v2 status is now deployed due to DeploymentManager action
hastagaras-halu-8b-llama_3117_v2 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics