submission_id: hastagaras-anjir-8b-l3-m_8084_v1
developer_uid: Hastagaras
status: inactive
model_repo: Hastagaras/Anjir-8B-L3-MK.V-BJ2
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.05, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 80, '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: 2024-06-11T17:58:24+00:00
model_name: bj2
model_eval_status: success
model_group: Hastagaras/Anjir-8B-L3-M
num_battles: 9039
num_wins: 4952
celo_rating: 1215.05
propriety_score: 0.6893793103448276
propriety_total_count: 3625.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: bj2
ineligible_reason: propriety_total_count < 5000
language_model: Hastagaras/Anjir-8B-L3-MK.V-BJ2
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-11
win_ratio: 0.5478482132979312
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-anjir-8b-l3-m-8084-v1-mkmlizer
Waiting for job on hastagaras-anjir-8b-l3-m-8084-v1-mkmlizer to finish
hastagaras-anjir-8b-l3-m-8084-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-anjir-8b-l3-m-8084-v1-mkmlizer: ║ _____ __ __ ║
hastagaras-anjir-8b-l3-m-8084-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-anjir-8b-l3-m-8084-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-anjir-8b-l3-m-8084-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-anjir-8b-l3-m-8084-v1-mkmlizer: ║ /___/ ║
hastagaras-anjir-8b-l3-m-8084-v1-mkmlizer: ║ ║
hastagaras-anjir-8b-l3-m-8084-v1-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-anjir-8b-l3-m-8084-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-anjir-8b-l3-m-8084-v1-mkmlizer: ║ https://mk1.ai ║
hastagaras-anjir-8b-l3-m-8084-v1-mkmlizer: ║ ║
hastagaras-anjir-8b-l3-m-8084-v1-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-anjir-8b-l3-m-8084-v1-mkmlizer: ║ belonging to: ║
hastagaras-anjir-8b-l3-m-8084-v1-mkmlizer: ║ ║
hastagaras-anjir-8b-l3-m-8084-v1-mkmlizer: ║ Chai Research Corp. ║
hastagaras-anjir-8b-l3-m-8084-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-anjir-8b-l3-m-8084-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-anjir-8b-l3-m-8084-v1-mkmlizer: ║ ║
hastagaras-anjir-8b-l3-m-8084-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-anjir-8b-l3-m-8084-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-m-8084-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-anjir-8b-l3-m-8084-v1-mkmlizer: Downloaded to shared memory in 44.873s
hastagaras-anjir-8b-l3-m-8084-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-anjir-8b-l3-m-8084-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-anjir-8b-l3-m-8084-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:02, 126.81it/s] Loading 0: 10%|█ | 30/291 [00:00<00:01, 145.10it/s] Loading 0: 15%|█▌ | 45/291 [00:00<00:01, 144.41it/s] Loading 0: 21%|██ | 60/291 [00:00<00:01, 139.29it/s] Loading 0: 26%|██▌ | 76/291 [00:00<00:01, 142.43it/s] Loading 0: 31%|███▏ | 91/291 [00:01<00:03, 65.78it/s] Loading 0: 36%|███▌ | 104/291 [00:01<00:02, 75.42it/s] Loading 0: 42%|████▏ | 121/291 [00:01<00:01, 92.06it/s] Loading 0: 47%|████▋ | 138/291 [00:01<00:01, 107.24it/s] Loading 0: 53%|█████▎ | 153/291 [00:01<00:01, 116.81it/s] Loading 0: 57%|█████▋ | 167/291 [00:01<00:01, 119.97it/s] Loading 0: 64%|██████▎ | 185/291 [00:01<00:00, 134.54it/s] Loading 0: 69%|██████▊ | 200/291 [00:02<00:01, 73.00it/s] Loading 0: 73%|███████▎ | 212/291 [00:02<00:00, 80.07it/s] Loading 0: 79%|███████▊ | 229/291 [00:02<00:00, 96.76it/s] Loading 0: 85%|████████▍ | 247/291 [00:02<00:00, 111.26it/s] Loading 0: 91%|█████████ | 264/291 [00:02<00:00, 124.21it/s] Loading 0: 96%|█████████▌| 279/291 [00:02<00:00, 129.92it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-anjir-8b-l3-m-8084-v1-mkmlizer: quantized model in 19.917s
hastagaras-anjir-8b-l3-m-8084-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-anjir-8b-l3-m-8084-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-anjir-8b-l3-m-8084-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-m-8084-v1
hastagaras-anjir-8b-l3-m-8084-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-m-8084-v1/config.json
hastagaras-anjir-8b-l3-m-8084-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-m-8084-v1/special_tokens_map.json
hastagaras-anjir-8b-l3-m-8084-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-m-8084-v1/tokenizer_config.json
hastagaras-anjir-8b-l3-m-8084-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-m-8084-v1/tokenizer.json
hastagaras-anjir-8b-l3-m-8084-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-m-8084-v1/flywheel_model.0.safetensors
hastagaras-anjir-8b-l3-m-8084-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-anjir-8b-l3-m-8084-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-m-8084-v1-mkmlizer: warnings.warn(
hastagaras-anjir-8b-l3-m-8084-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-m-8084-v1-mkmlizer: warnings.warn(
hastagaras-anjir-8b-l3-m-8084-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-m-8084-v1-mkmlizer: warnings.warn(
hastagaras-anjir-8b-l3-m-8084-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-anjir-8b-l3-m-8084-v1_reward/merges.txt
hastagaras-anjir-8b-l3-m-8084-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-m-8084-v1_reward/vocab.json
hastagaras-anjir-8b-l3-m-8084-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-m-8084-v1_reward/tokenizer.json
hastagaras-anjir-8b-l3-m-8084-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-anjir-8b-l3-m-8084-v1_reward/reward.tensors
Job hastagaras-anjir-8b-l3-m-8084-v1-mkmlizer completed after 118.62s with status: succeeded
Stopping job with name hastagaras-anjir-8b-l3-m-8084-v1-mkmlizer
Pipeline stage MKMLizer completed in 119.60s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-anjir-8b-l3-m-8084-v1
Waiting for inference service hastagaras-anjir-8b-l3-m-8084-v1 to be ready
Inference service hastagaras-anjir-8b-l3-m-8084-v1 ready after 40.23246765136719s
Pipeline stage ISVCDeployer completed in 46.14s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.174509048461914s
Received healthy response to inference request in 1.3406529426574707s
Received healthy response to inference request in 1.354222297668457s
Received healthy response to inference request in 1.314070701599121s
Received healthy response to inference request in 1.2602789402008057s
5 requests
0 failed requests
5th percentile: 1.2710372924804687
10th percentile: 1.2817956447601317
20th percentile: 1.303312349319458
30th percentile: 1.319387149810791
40th percentile: 1.330020046234131
50th percentile: 1.3406529426574707
60th percentile: 1.3460806846618651
70th percentile: 1.3515084266662598
80th percentile: 1.5182796478271485
90th percentile: 1.8463943481445313
95th percentile: 2.0104516983032226
99th percentile: 2.141697578430176
mean time: 1.4887467861175536
Pipeline stage StressChecker completed in 8.02s
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-anjir-8b-l3-m_8084_v1 status is now deployed due to DeploymentManager action
hastagaras-anjir-8b-l3-m_8084_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics