submission_id: hastagaras-llama-3-8b-no_7499_v1
developer_uid: Hastagaras
status: torndown
model_repo: Hastagaras/llama-3-8b-not-okay
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, '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\nYou're {bot_name} in this roleplay chat between {user_name} and {bot_name}. Always write your response as {bot_name} based on the following persona.\n\n{bot_name}'s Persona: {memory}\n", 'prompt_template': 'Previously: {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", 'prompt_template': '{prompt}\n', 'bot_template': 'Bot: {message}\n', 'user_template': 'User: {message}\n', 'response_template': 'Bot:', 'truncate_by_message': False}
timestamp: 2024-05-15T05:09:13+00:00
model_name: badbadbad
model_eval_status: success
model_group: Hastagaras/llama-3-8b-no
num_battles: 25435
num_wins: 13642
celo_rating: 1193.89
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: badbadbad
ineligible_reason: propriety_total_count < 800
language_model: Hastagaras/llama-3-8b-not-okay
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-05-14
win_ratio: 0.5363475525850206
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-llama-3-8b-no-7499-v1-mkmlizer
Waiting for job on hastagaras-llama-3-8b-no-7499-v1-mkmlizer to finish
hastagaras-llama-3-8b-no-7499-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-llama-3-8b-no-7499-v1-mkmlizer: ║ _____ __ __ ║
hastagaras-llama-3-8b-no-7499-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-llama-3-8b-no-7499-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-llama-3-8b-no-7499-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-llama-3-8b-no-7499-v1-mkmlizer: ║ /___/ ║
hastagaras-llama-3-8b-no-7499-v1-mkmlizer: ║ ║
hastagaras-llama-3-8b-no-7499-v1-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-llama-3-8b-no-7499-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-llama-3-8b-no-7499-v1-mkmlizer: ║ https://mk1.ai ║
hastagaras-llama-3-8b-no-7499-v1-mkmlizer: ║ ║
hastagaras-llama-3-8b-no-7499-v1-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-llama-3-8b-no-7499-v1-mkmlizer: ║ belonging to: ║
hastagaras-llama-3-8b-no-7499-v1-mkmlizer: ║ ║
hastagaras-llama-3-8b-no-7499-v1-mkmlizer: ║ Chai Research Corp. ║
hastagaras-llama-3-8b-no-7499-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-llama-3-8b-no-7499-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-llama-3-8b-no-7499-v1-mkmlizer: ║ ║
hastagaras-llama-3-8b-no-7499-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-llama-3-8b-no-7499-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-llama-3-8b-no-7499-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-llama-3-8b-no-7499-v1-mkmlizer: Downloaded to shared memory in 31.692s
hastagaras-llama-3-8b-no-7499-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-llama-3-8b-no-7499-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-llama-3-8b-no-7499-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 8%|▊ | 22/291 [00:00<00:01, 202.58it/s] Loading 0: 15%|█▌ | 44/291 [00:00<00:01, 209.67it/s] Loading 0: 22%|██▏ | 65/291 [00:00<00:01, 208.35it/s] Loading 0: 30%|██▉ | 86/291 [00:00<00:02, 95.10it/s] Loading 0: 38%|███▊ | 111/291 [00:00<00:01, 123.89it/s] Loading 0: 45%|████▌ | 131/291 [00:00<00:01, 138.01it/s] Loading 0: 54%|█████▎ | 156/291 [00:01<00:00, 163.27it/s] Loading 0: 60%|██████ | 176/291 [00:01<00:00, 172.14it/s] Loading 0: 67%|██████▋ | 196/291 [00:01<00:00, 107.26it/s] Loading 0: 74%|███████▍ | 216/291 [00:01<00:00, 123.92it/s] Loading 0: 80%|████████ | 233/291 [00:01<00:00, 130.63it/s] Loading 0: 86%|████████▌ | 250/291 [00:01<00:00, 130.84it/s] Loading 0: 93%|█████████▎| 270/291 [00:01<00:00, 146.03it/s] Loading 0: 99%|█████████▊| 287/291 [00:06<00:00, 11.93it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-llama-3-8b-no-7499-v1-mkmlizer: quantized model in 17.227s
hastagaras-llama-3-8b-no-7499-v1-mkmlizer: Processed model Hastagaras/llama-3-8b-not-okay in 49.842s
hastagaras-llama-3-8b-no-7499-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-llama-3-8b-no-7499-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-llama-3-8b-no-7499-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-llama-3-8b-no-7499-v1
hastagaras-llama-3-8b-no-7499-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-no-7499-v1/special_tokens_map.json
hastagaras-llama-3-8b-no-7499-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-no-7499-v1/config.json
hastagaras-llama-3-8b-no-7499-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-no-7499-v1/tokenizer_config.json
hastagaras-llama-3-8b-no-7499-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-no-7499-v1/tokenizer.json
hastagaras-llama-3-8b-no-7499-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-llama-3-8b-no-7499-v1/flywheel_model.0.safetensors
hastagaras-llama-3-8b-no-7499-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-llama-3-8b-no-7499-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-llama-3-8b-no-7499-v1-mkmlizer: warnings.warn(
hastagaras-llama-3-8b-no-7499-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-llama-3-8b-no-7499-v1-mkmlizer: warnings.warn(
hastagaras-llama-3-8b-no-7499-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-llama-3-8b-no-7499-v1-mkmlizer: warnings.warn(
hastagaras-llama-3-8b-no-7499-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-llama-3-8b-no-7499-v1-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-llama-3-8b-no-7499-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-llama-3-8b-no-7499-v1-mkmlizer: Saving duration: 0.215s
hastagaras-llama-3-8b-no-7499-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 6.024s
hastagaras-llama-3-8b-no-7499-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-llama-3-8b-no-7499-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-llama-3-8b-no-7499-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-llama-3-8b-no-7499-v1_reward
hastagaras-llama-3-8b-no-7499-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-llama-3-8b-no-7499-v1_reward/special_tokens_map.json
hastagaras-llama-3-8b-no-7499-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-llama-3-8b-no-7499-v1_reward/tokenizer_config.json
hastagaras-llama-3-8b-no-7499-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-llama-3-8b-no-7499-v1_reward/config.json
hastagaras-llama-3-8b-no-7499-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-llama-3-8b-no-7499-v1_reward/merges.txt
hastagaras-llama-3-8b-no-7499-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-llama-3-8b-no-7499-v1_reward/vocab.json
hastagaras-llama-3-8b-no-7499-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-llama-3-8b-no-7499-v1_reward/tokenizer.json
hastagaras-llama-3-8b-no-7499-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-llama-3-8b-no-7499-v1_reward/reward.tensors
Job hastagaras-llama-3-8b-no-7499-v1-mkmlizer completed after 83.45s with status: succeeded
Stopping job with name hastagaras-llama-3-8b-no-7499-v1-mkmlizer
Pipeline stage MKMLizer completed in 88.90s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-llama-3-8b-no-7499-v1
Waiting for inference service hastagaras-llama-3-8b-no-7499-v1 to be ready
Inference service hastagaras-llama-3-8b-no-7499-v1 ready after 40.217079162597656s
Pipeline stage ISVCDeployer completed in 47.38s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.264190435409546s
Received healthy response to inference request in 1.293400764465332s
Received healthy response to inference request in 1.268754005432129s
Received healthy response to inference request in 1.325505018234253s
Received healthy response to inference request in 1.3009870052337646s
5 requests
0 failed requests
5th percentile: 1.2736833572387696
10th percentile: 1.2786127090454102
20th percentile: 1.2884714126586914
30th percentile: 1.2949180126190185
40th percentile: 1.2979525089263917
50th percentile: 1.3009870052337646
60th percentile: 1.31079421043396
70th percentile: 1.3206014156341552
80th percentile: 1.5132421016693116
90th percentile: 1.8887162685394288
95th percentile: 2.076453351974487
99th percentile: 2.2266430187225343
mean time: 1.4905674457550049
Pipeline stage StressChecker completed in 8.09s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.06s
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-llama-3-8b-no_7499_v1 status is now deployed due to DeploymentManager action
hastagaras-llama-3-8b-no_7499_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-llama-3-8b-no_7499_v1
Running pipeline stage ISVCDeleter
Checking if service hastagaras-llama-3-8b-no-7499-v1 is running
Tearing down inference service hastagaras-llama-3-8b-no-7499-v1
Toredown service hastagaras-llama-3-8b-no-7499-v1
Pipeline stage ISVCDeleter completed in 4.30s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-llama-3-8b-no-7499-v1/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-no-7499-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-no-7499-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-no-7499-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-no-7499-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-llama-3-8b-no-7499-v1_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-no-7499-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-no-7499-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-no-7499-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-no-7499-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-no-7499-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-no-7499-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.22s
hastagaras-llama-3-8b-no_7499_v1 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics