submission_id: hastagaras-halu-8b-llama_4766_v3
developer_uid: Hastagaras
status: inactive
model_repo: Hastagaras/HALU-8B-LLAMA3-BRSLURP
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.95, 'top_p': 0.95, 'min_p': 0.08, '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: 2024-06-01T03:10:55+00:00
model_name: renamed-from-exp2-3
model_eval_status: success
model_group: Hastagaras/HALU-8B-LLAMA
num_battles: 8728
num_wins: 4778
celo_rating: 1217.0
propriety_score: 1.0
propriety_total_count: 6.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: renamed-from-exp2-3
ineligible_reason: propriety_total_count < 5000
language_model: Hastagaras/HALU-8B-LLAMA3-BRSLURP
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-05-31
win_ratio: 0.5474335472043996
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-halu-8b-llama-4766-v3-mkmlizer
Waiting for job on hastagaras-halu-8b-llama-4766-v3-mkmlizer to finish
hastagaras-halu-8b-llama-4766-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-halu-8b-llama-4766-v3-mkmlizer: ║ _____ __ __ ║
hastagaras-halu-8b-llama-4766-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-halu-8b-llama-4766-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-halu-8b-llama-4766-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-halu-8b-llama-4766-v3-mkmlizer: ║ /___/ ║
hastagaras-halu-8b-llama-4766-v3-mkmlizer: ║ ║
hastagaras-halu-8b-llama-4766-v3-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-halu-8b-llama-4766-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-halu-8b-llama-4766-v3-mkmlizer: ║ https://mk1.ai ║
hastagaras-halu-8b-llama-4766-v3-mkmlizer: ║ ║
hastagaras-halu-8b-llama-4766-v3-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-halu-8b-llama-4766-v3-mkmlizer: ║ belonging to: ║
hastagaras-halu-8b-llama-4766-v3-mkmlizer: ║ ║
hastagaras-halu-8b-llama-4766-v3-mkmlizer: ║ Chai Research Corp. ║
hastagaras-halu-8b-llama-4766-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-halu-8b-llama-4766-v3-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-halu-8b-llama-4766-v3-mkmlizer: ║ ║
hastagaras-halu-8b-llama-4766-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-halu-8b-llama-4766-v3-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-4766-v3-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-halu-8b-llama-4766-v3-mkmlizer: Downloaded to shared memory in 29.699s
hastagaras-halu-8b-llama-4766-v3-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-halu-8b-llama-4766-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-halu-8b-llama-4766-v3-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<10:46, 2.24s/it] Loading 0: 6%|▌ | 17/291 [00:04<00:53, 5.08it/s] Loading 0: 11%|█▏ | 33/291 [00:04<00:22, 11.60it/s] Loading 0: 18%|█▊ | 51/291 [00:04<00:11, 21.08it/s] Loading 0: 22%|██▏ | 65/291 [00:05<00:08, 25.38it/s] Loading 0: 28%|██▊ | 81/291 [00:05<00:05, 36.55it/s] Loading 0: 33%|███▎ | 97/291 [00:05<00:03, 49.58it/s] Loading 0: 39%|███▉ | 114/291 [00:05<00:02, 65.01it/s] Loading 0: 45%|████▌ | 132/291 [00:05<00:01, 81.91it/s] Loading 0: 52%|█████▏ | 150/291 [00:05<00:01, 98.76it/s] Loading 0: 57%|█████▋ | 166/291 [00:05<00:01, 76.50it/s] Loading 0: 63%|██████▎ | 184/291 [00:06<00:01, 92.96it/s] Loading 0: 69%|██████▉ | 202/291 [00:06<00:00, 108.17it/s] Loading 0: 75%|███████▍ | 217/291 [00:06<00:00, 110.69it/s] Loading 0: 80%|████████ | 234/291 [00:06<00:00, 123.44it/s] Loading 0: 86%|████████▌ | 249/291 [00:06<00:00, 129.83it/s] Loading 0: 91%|█████████▏| 266/291 [00:06<00:00, 88.74it/s] Loading 0: 98%|█████████▊| 284/291 [00:06<00:00, 104.94it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-halu-8b-llama-4766-v3-mkmlizer: quantized model in 22.827s
hastagaras-halu-8b-llama-4766-v3-mkmlizer: Processed model Hastagaras/HALU-8B-LLAMA3-BRSLURP in 55.063s
hastagaras-halu-8b-llama-4766-v3-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-halu-8b-llama-4766-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-halu-8b-llama-4766-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-halu-8b-llama-4766-v3
hastagaras-halu-8b-llama-4766-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-4766-v3/tokenizer_config.json
hastagaras-halu-8b-llama-4766-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-4766-v3/special_tokens_map.json
hastagaras-halu-8b-llama-4766-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-4766-v3/config.json
hastagaras-halu-8b-llama-4766-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-4766-v3/tokenizer.json
hastagaras-halu-8b-llama-4766-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-halu-8b-llama-4766-v3/flywheel_model.0.safetensors
hastagaras-halu-8b-llama-4766-v3-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-halu-8b-llama-4766-v3-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-4766-v3-mkmlizer: warnings.warn(
hastagaras-halu-8b-llama-4766-v3-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-4766-v3-mkmlizer: warnings.warn(
hastagaras-halu-8b-llama-4766-v3-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-4766-v3-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-halu-8b-llama-4766-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-halu-8b-llama-4766-v3-mkmlizer: Saving duration: 0.391s
hastagaras-halu-8b-llama-4766-v3-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.001s
hastagaras-halu-8b-llama-4766-v3-mkmlizer: creating bucket guanaco-reward-models
hastagaras-halu-8b-llama-4766-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-halu-8b-llama-4766-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-halu-8b-llama-4766-v3_reward
hastagaras-halu-8b-llama-4766-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-4766-v3_reward/special_tokens_map.json
hastagaras-halu-8b-llama-4766-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-4766-v3_reward/tokenizer_config.json
hastagaras-halu-8b-llama-4766-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-halu-8b-llama-4766-v3_reward/merges.txt
hastagaras-halu-8b-llama-4766-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-4766-v3_reward/config.json
hastagaras-halu-8b-llama-4766-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-4766-v3_reward/vocab.json
hastagaras-halu-8b-llama-4766-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-4766-v3_reward/tokenizer.json
hastagaras-halu-8b-llama-4766-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-halu-8b-llama-4766-v3_reward/reward.tensors
Job hastagaras-halu-8b-llama-4766-v3-mkmlizer completed after 83.34s with status: succeeded
Stopping job with name hastagaras-halu-8b-llama-4766-v3-mkmlizer
Pipeline stage MKMLizer completed in 84.19s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-halu-8b-llama-4766-v3
Waiting for inference service hastagaras-halu-8b-llama-4766-v3 to be ready
Inference service hastagaras-halu-8b-llama-4766-v3 ready after 50.50803232192993s
Pipeline stage ISVCDeployer completed in 56.39s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1566708087921143s
Received healthy response to inference request in 1.329690933227539s
Received healthy response to inference request in 1.3108627796173096s
Received healthy response to inference request in 1.3023557662963867s
Received healthy response to inference request in 1.2430744171142578s
5 requests
0 failed requests
5th percentile: 1.2549306869506835
10th percentile: 1.2667869567871093
20th percentile: 1.290499496459961
30th percentile: 1.3040571689605713
40th percentile: 1.3074599742889403
50th percentile: 1.3108627796173096
60th percentile: 1.3183940410614015
70th percentile: 1.3259253025054931
80th percentile: 1.4950869083404543
90th percentile: 1.8258788585662842
95th percentile: 1.991274833679199
99th percentile: 2.1235916137695314
mean time: 1.4685309410095215
Pipeline stage StressChecker completed in 7.94s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.04s
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_4766_v3 status is now deployed due to DeploymentManager action
hastagaras-halu-8b-llama_4766_v3 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics