submission_id: hastagaras-anjay-8b-llam_6940_v1
developer_uid: Hastagaras
status: inactive
model_repo: Hastagaras/Anjay-8B-Llama3-CrestRoot
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.08, 'top_k': 50, '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: 2024-06-03T03:30:40+00:00
model_name: new
model_eval_status: success
model_group: Hastagaras/Anjay-8B-Llam
num_battles: 7572
num_wins: 4089
celo_rating: 1210.35
propriety_score: 0.6905829596412556
propriety_total_count: 223.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: new
ineligible_reason: propriety_total_count < 5000
language_model: Hastagaras/Anjay-8B-Llama3-CrestRoot
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-02
win_ratio: 0.5400158478605388
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-anjay-8b-llam-6940-v1-mkmlizer
Waiting for job on hastagaras-anjay-8b-llam-6940-v1-mkmlizer to finish
hastagaras-anjay-8b-llam-6940-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-anjay-8b-llam-6940-v1-mkmlizer: ║ _____ __ __ ║
hastagaras-anjay-8b-llam-6940-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-anjay-8b-llam-6940-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-anjay-8b-llam-6940-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-anjay-8b-llam-6940-v1-mkmlizer: ║ /___/ ║
hastagaras-anjay-8b-llam-6940-v1-mkmlizer: ║ ║
hastagaras-anjay-8b-llam-6940-v1-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-anjay-8b-llam-6940-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-anjay-8b-llam-6940-v1-mkmlizer: ║ https://mk1.ai ║
hastagaras-anjay-8b-llam-6940-v1-mkmlizer: ║ ║
hastagaras-anjay-8b-llam-6940-v1-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-anjay-8b-llam-6940-v1-mkmlizer: ║ belonging to: ║
hastagaras-anjay-8b-llam-6940-v1-mkmlizer: ║ ║
hastagaras-anjay-8b-llam-6940-v1-mkmlizer: ║ Chai Research Corp. ║
hastagaras-anjay-8b-llam-6940-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-anjay-8b-llam-6940-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-anjay-8b-llam-6940-v1-mkmlizer: ║ ║
hastagaras-anjay-8b-llam-6940-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-anjay-8b-llam-6940-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-anjay-8b-llam-6940-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-anjay-8b-llam-6940-v1-mkmlizer: Downloaded to shared memory in 38.559s
hastagaras-anjay-8b-llam-6940-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-anjay-8b-llam-6940-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-anjay-8b-llam-6940-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<10:50, 2.25s/it] Loading 0: 6%|▌ | 18/291 [00:04<00:51, 5.35it/s] Loading 0: 12%|█▏ | 36/291 [00:04<00:20, 12.67it/s] Loading 0: 18%|█▊ | 53/291 [00:04<00:11, 21.58it/s] Loading 0: 23%|██▎ | 68/291 [00:05<00:08, 26.39it/s] Loading 0: 30%|██▉ | 86/291 [00:05<00:05, 38.87it/s] Loading 0: 36%|███▌ | 104/291 [00:05<00:03, 53.33it/s] Loading 0: 42%|████▏ | 122/291 [00:05<00:02, 69.12it/s] Loading 0: 48%|████▊ | 140/291 [00:05<00:01, 85.22it/s] Loading 0: 54%|█████▍ | 158/291 [00:05<00:01, 100.91it/s] Loading 0: 60%|█████▉ | 174/291 [00:06<00:01, 77.73it/s] Loading 0: 64%|██████▍ | 187/291 [00:06<00:01, 86.33it/s] Loading 0: 70%|███████ | 204/291 [00:06<00:00, 100.51it/s] Loading 0: 76%|███████▋ | 222/291 [00:06<00:00, 114.95it/s] Loading 0: 82%|████████▏ | 240/291 [00:06<00:00, 128.17it/s] Loading 0: 89%|████████▊ | 258/291 [00:06<00:00, 139.59it/s] Loading 0: 94%|█████████▍| 274/291 [00:06<00:00, 94.15it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-anjay-8b-llam-6940-v1-mkmlizer: quantized model in 22.871s
hastagaras-anjay-8b-llam-6940-v1-mkmlizer: Processed model Hastagaras/Anjay-8B-Llama3-CrestRoot in 63.877s
hastagaras-anjay-8b-llam-6940-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-anjay-8b-llam-6940-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-anjay-8b-llam-6940-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-anjay-8b-llam-6940-v1
hastagaras-anjay-8b-llam-6940-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-anjay-8b-llam-6940-v1/config.json
hastagaras-anjay-8b-llam-6940-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-anjay-8b-llam-6940-v1/special_tokens_map.json
hastagaras-anjay-8b-llam-6940-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-anjay-8b-llam-6940-v1/tokenizer.json
hastagaras-anjay-8b-llam-6940-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-anjay-8b-llam-6940-v1/tokenizer_config.json
hastagaras-anjay-8b-llam-6940-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-anjay-8b-llam-6940-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-anjay-8b-llam-6940-v1-mkmlizer: warnings.warn(
hastagaras-anjay-8b-llam-6940-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-anjay-8b-llam-6940-v1-mkmlizer: warnings.warn(
hastagaras-anjay-8b-llam-6940-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-anjay-8b-llam-6940-v1-mkmlizer: warnings.warn(
hastagaras-anjay-8b-llam-6940-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-anjay-8b-llam-6940-v1-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-anjay-8b-llam-6940-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-anjay-8b-llam-6940-v1-mkmlizer: Saving duration: 0.388s
hastagaras-anjay-8b-llam-6940-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.706s
hastagaras-anjay-8b-llam-6940-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-anjay-8b-llam-6940-v1_reward/config.json
hastagaras-anjay-8b-llam-6940-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-anjay-8b-llam-6940-v1_reward/tokenizer_config.json
hastagaras-anjay-8b-llam-6940-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-anjay-8b-llam-6940-v1_reward/vocab.json
hastagaras-anjay-8b-llam-6940-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-anjay-8b-llam-6940-v1_reward/merges.txt
hastagaras-anjay-8b-llam-6940-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-anjay-8b-llam-6940-v1_reward/special_tokens_map.json
hastagaras-anjay-8b-llam-6940-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-anjay-8b-llam-6940-v1_reward/tokenizer.json
hastagaras-anjay-8b-llam-6940-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-anjay-8b-llam-6940-v1_reward/reward.tensors
Job hastagaras-anjay-8b-llam-6940-v1-mkmlizer completed after 93.37s with status: succeeded
Stopping job with name hastagaras-anjay-8b-llam-6940-v1-mkmlizer
Pipeline stage MKMLizer completed in 96.22s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-anjay-8b-llam-6940-v1
Waiting for inference service hastagaras-anjay-8b-llam-6940-v1 to be ready
Inference service hastagaras-anjay-8b-llam-6940-v1 ready after 50.32922315597534s
Pipeline stage ISVCDeployer completed in 57.42s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.092806339263916s
Received healthy response to inference request in 1.4000072479248047s
Received healthy response to inference request in 1.3649663925170898s
Received healthy response to inference request in 1.3372249603271484s
Received healthy response to inference request in 1.276414394378662s
5 requests
0 failed requests
5th percentile: 1.2885765075683593
10th percentile: 1.3007386207580567
20th percentile: 1.3250628471374513
30th percentile: 1.3427732467651368
40th percentile: 1.3538698196411132
50th percentile: 1.3649663925170898
60th percentile: 1.3789827346801757
70th percentile: 1.3929990768432616
80th percentile: 1.538567066192627
90th percentile: 1.8156867027282715
95th percentile: 1.9542465209960938
99th percentile: 2.0650943756103515
mean time: 1.4942838668823242
Pipeline stage StressChecker completed in 8.14s
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-anjay-8b-llam_6940_v1 status is now deployed due to DeploymentManager action
hastagaras-anjay-8b-llam_6940_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics