submission_id: hastagaras-anjir-8b-l3-test_v1
developer_uid: Hastagaras
status: inactive
model_repo: Hastagaras/Anjir-8B-L3-TEST
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.0, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 100, '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: 2024-06-01T07:50:56+00:00
model_name: healing-test
model_eval_status: success
model_group: Hastagaras/Anjir-8B-L3-T
num_battles: 12477
num_wins: 6797
celo_rating: 1210.44
safety_score: 0.93
propriety_score: 0.75
propriety_total_count: 4.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: healing-test
ineligible_reason: propriety_total_count < 5000
language_model: Hastagaras/Anjir-8B-L3-TEST
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-01
win_ratio: 0.5447623627474553
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-anjir-8b-l3-test-v1-mkmlizer
Waiting for job on hastagaras-anjir-8b-l3-test-v1-mkmlizer to finish
hastagaras-anjir-8b-l3-test-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-anjir-8b-l3-test-v1-mkmlizer: ║ _____ __ __ ║
hastagaras-anjir-8b-l3-test-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-anjir-8b-l3-test-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-anjir-8b-l3-test-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-anjir-8b-l3-test-v1-mkmlizer: ║ /___/ ║
hastagaras-anjir-8b-l3-test-v1-mkmlizer: ║ ║
hastagaras-anjir-8b-l3-test-v1-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-anjir-8b-l3-test-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-anjir-8b-l3-test-v1-mkmlizer: ║ https://mk1.ai ║
hastagaras-anjir-8b-l3-test-v1-mkmlizer: ║ ║
hastagaras-anjir-8b-l3-test-v1-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-anjir-8b-l3-test-v1-mkmlizer: ║ belonging to: ║
hastagaras-anjir-8b-l3-test-v1-mkmlizer: ║ ║
hastagaras-anjir-8b-l3-test-v1-mkmlizer: ║ Chai Research Corp. ║
hastagaras-anjir-8b-l3-test-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-anjir-8b-l3-test-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-anjir-8b-l3-test-v1-mkmlizer: ║ ║
hastagaras-anjir-8b-l3-test-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-anjir-8b-l3-test-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-anjir-8b-l3-test-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-anjir-8b-l3-test-v1-mkmlizer: Downloaded to shared memory in 30.094s
hastagaras-anjir-8b-l3-test-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-anjir-8b-l3-test-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-anjir-8b-l3-test-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:02, 120.44it/s] Loading 0: 10%|█ | 30/291 [00:00<00:01, 146.40it/s] Loading 0: 16%|█▌ | 46/291 [00:00<00:01, 151.82it/s] Loading 0: 21%|██▏ | 62/291 [00:00<00:01, 150.39it/s] Loading 0: 27%|██▋ | 78/291 [00:00<00:01, 147.46it/s] Loading 0: 32%|███▏ | 93/291 [00:00<00:02, 75.24it/s] Loading 0: 38%|███▊ | 111/291 [00:01<00:01, 92.95it/s] Loading 0: 44%|████▍ | 129/291 [00:01<00:01, 108.58it/s] Loading 0: 51%|█████ | 147/291 [00:01<00:01, 121.27it/s] Loading 0: 56%|█████▌ | 163/291 [00:01<00:00, 130.24it/s] Loading 0: 62%|██████▏ | 180/291 [00:01<00:00, 137.15it/s] Loading 0: 67%|██████▋ | 196/291 [00:01<00:01, 81.95it/s] Loading 0: 73%|███████▎ | 212/291 [00:01<00:00, 94.48it/s] Loading 0: 79%|███████▉ | 230/291 [00:02<00:00, 109.74it/s] Loading 0: 85%|████████▌ | 248/291 [00:02<00:00, 122.71it/s] Loading 0: 91%|█████████▏| 266/291 [00:02<00:00, 133.52it/s] Loading 0: 98%|█████████▊| 285/291 [00:02<00:00, 146.30it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-anjir-8b-l3-test-v1-mkmlizer: quantized model in 23.054s
hastagaras-anjir-8b-l3-test-v1-mkmlizer: Processed model Hastagaras/Anjir-8B-L3-TEST in 55.799s
hastagaras-anjir-8b-l3-test-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-anjir-8b-l3-test-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-anjir-8b-l3-test-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-test-v1
hastagaras-anjir-8b-l3-test-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-test-v1/tokenizer_config.json
hastagaras-anjir-8b-l3-test-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-test-v1/tokenizer.json
hastagaras-anjir-8b-l3-test-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-test-v1/config.json
hastagaras-anjir-8b-l3-test-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-test-v1/special_tokens_map.json
hastagaras-anjir-8b-l3-test-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-test-v1/flywheel_model.0.safetensors
hastagaras-anjir-8b-l3-test-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-anjir-8b-l3-test-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-anjir-8b-l3-test-v1-mkmlizer: warnings.warn(
hastagaras-anjir-8b-l3-test-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-anjir-8b-l3-test-v1-mkmlizer: warnings.warn(
hastagaras-anjir-8b-l3-test-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-anjir-8b-l3-test-v1-mkmlizer: warnings.warn(
hastagaras-anjir-8b-l3-test-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-anjir-8b-l3-test-v1-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-anjir-8b-l3-test-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-anjir-8b-l3-test-v1-mkmlizer: Saving duration: 0.461s
hastagaras-anjir-8b-l3-test-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.491s
hastagaras-anjir-8b-l3-test-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-anjir-8b-l3-test-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-anjir-8b-l3-test-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-anjir-8b-l3-test-v1_reward
hastagaras-anjir-8b-l3-test-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-test-v1_reward/config.json
hastagaras-anjir-8b-l3-test-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-test-v1_reward/special_tokens_map.json
hastagaras-anjir-8b-l3-test-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-test-v1_reward/tokenizer_config.json
hastagaras-anjir-8b-l3-test-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-anjir-8b-l3-test-v1_reward/merges.txt
hastagaras-anjir-8b-l3-test-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-test-v1_reward/vocab.json
hastagaras-anjir-8b-l3-test-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-test-v1_reward/tokenizer.json
hastagaras-anjir-8b-l3-test-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-anjir-8b-l3-test-v1_reward/reward.tensors
Job hastagaras-anjir-8b-l3-test-v1-mkmlizer completed after 82.9s with status: succeeded
Stopping job with name hastagaras-anjir-8b-l3-test-v1-mkmlizer
Pipeline stage MKMLizer completed in 83.23s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.08s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-anjir-8b-l3-test-v1
Waiting for inference service hastagaras-anjir-8b-l3-test-v1 to be ready
Inference service hastagaras-anjir-8b-l3-test-v1 ready after 40.20845818519592s
Pipeline stage ISVCDeployer completed in 45.77s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1376352310180664s
Received healthy response to inference request in 1.3636014461517334s
Received healthy response to inference request in 1.3196704387664795s
Received healthy response to inference request in 1.2756965160369873s
Received healthy response to inference request in 1.2564756870269775s
5 requests
0 failed requests
5th percentile: 1.2603198528289794
10th percentile: 1.2641640186309815
20th percentile: 1.2718523502349854
30th percentile: 1.2844913005828857
40th percentile: 1.3020808696746826
50th percentile: 1.3196704387664795
60th percentile: 1.337242841720581
70th percentile: 1.3548152446746826
80th percentile: 1.5184082031250001
90th percentile: 1.8280217170715334
95th percentile: 1.9828284740447997
99th percentile: 2.106673879623413
mean time: 1.4706158638000488
Pipeline stage StressChecker completed in 7.98s
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-anjir-8b-l3-test_v1 status is now deployed due to DeploymentManager action
hastagaras-anjir-8b-l3-test_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics