submission_id: hastagaras-anjir-8b-l3-mk-ii_v2
developer_uid: Hastagaras
status: inactive
model_repo: Hastagaras/Anjir-8B-L3-MK.II
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 0.0, '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: 2024-06-08T02:51:16+00:00
model_name: hastagaras-anjir-8b-l3-mk-ii_v2
model_eval_status: success
model_group: Hastagaras/Anjir-8B-L3-M
num_battles: 9049
num_wins: 4896
celo_rating: 1209.62
propriety_score: 0.6375739644970414
propriety_total_count: 676.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: hastagaras-anjir-8b-l3-mk-ii_v2
ineligible_reason: propriety_total_count < 5000
language_model: Hastagaras/Anjir-8B-L3-MK.II
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-07
win_ratio: 0.541054260139242
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-anjir-8b-l3-mk-ii-v2-mkmlizer
Waiting for job on hastagaras-anjir-8b-l3-mk-ii-v2-mkmlizer to finish
hastagaras-anjir-8b-l3-mk-ii-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-anjir-8b-l3-mk-ii-v2-mkmlizer: ║ _____ __ __ ║
hastagaras-anjir-8b-l3-mk-ii-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-anjir-8b-l3-mk-ii-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-anjir-8b-l3-mk-ii-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-anjir-8b-l3-mk-ii-v2-mkmlizer: ║ /___/ ║
hastagaras-anjir-8b-l3-mk-ii-v2-mkmlizer: ║ ║
hastagaras-anjir-8b-l3-mk-ii-v2-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-anjir-8b-l3-mk-ii-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-anjir-8b-l3-mk-ii-v2-mkmlizer: ║ https://mk1.ai ║
hastagaras-anjir-8b-l3-mk-ii-v2-mkmlizer: ║ ║
hastagaras-anjir-8b-l3-mk-ii-v2-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-anjir-8b-l3-mk-ii-v2-mkmlizer: ║ belonging to: ║
hastagaras-anjir-8b-l3-mk-ii-v2-mkmlizer: ║ ║
hastagaras-anjir-8b-l3-mk-ii-v2-mkmlizer: ║ Chai Research Corp. ║
hastagaras-anjir-8b-l3-mk-ii-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-anjir-8b-l3-mk-ii-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-anjir-8b-l3-mk-ii-v2-mkmlizer: ║ ║
hastagaras-anjir-8b-l3-mk-ii-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-anjir-8b-l3-mk-ii-v2-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-mk-ii-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-anjir-8b-l3-mk-ii-v2-mkmlizer: Downloaded to shared memory in 22.772s
hastagaras-anjir-8b-l3-mk-ii-v2-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-anjir-8b-l3-mk-ii-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-anjir-8b-l3-mk-ii-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:02, 127.42it/s] Loading 0: 11%|█ | 31/291 [00:00<00:01, 150.08it/s] Loading 0: 17%|█▋ | 49/291 [00:00<00:01, 157.57it/s] Loading 0: 23%|██▎ | 67/291 [00:00<00:01, 160.97it/s] Loading 0: 29%|██▉ | 84/291 [00:00<00:02, 82.50it/s] Loading 0: 35%|███▌ | 102/291 [00:00<00:01, 99.85it/s] Loading 0: 41%|████ | 120/291 [00:01<00:01, 115.17it/s] Loading 0: 47%|████▋ | 138/291 [00:01<00:01, 128.58it/s] Loading 0: 54%|█████▎ | 156/291 [00:01<00:00, 139.00it/s] Loading 0: 59%|█████▉ | 173/291 [00:01<00:00, 144.33it/s] Loading 0: 65%|██████▍ | 189/291 [00:01<00:01, 89.73it/s] Loading 0: 71%|███████ | 206/291 [00:01<00:00, 104.58it/s] Loading 0: 76%|███████▌ | 221/291 [00:01<00:00, 113.30it/s] Loading 0: 82%|████████▏ | 239/291 [00:02<00:00, 127.06it/s] Loading 0: 88%|████████▊ | 257/291 [00:02<00:00, 137.83it/s] Loading 0: 95%|█████████▍| 275/291 [00:02<00:00, 146.89it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-anjir-8b-l3-mk-ii-v2-mkmlizer: quantized model in 22.739s
hastagaras-anjir-8b-l3-mk-ii-v2-mkmlizer: Processed model Hastagaras/Anjir-8B-L3-MK.II in 48.078s
hastagaras-anjir-8b-l3-mk-ii-v2-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-anjir-8b-l3-mk-ii-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-anjir-8b-l3-mk-ii-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-mk-ii-v2
hastagaras-anjir-8b-l3-mk-ii-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-mk-ii-v2/tokenizer_config.json
hastagaras-anjir-8b-l3-mk-ii-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-mk-ii-v2/config.json
hastagaras-anjir-8b-l3-mk-ii-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-mk-ii-v2/special_tokens_map.json
hastagaras-anjir-8b-l3-mk-ii-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-mk-ii-v2/tokenizer.json
hastagaras-anjir-8b-l3-mk-ii-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-mk-ii-v2/flywheel_model.0.safetensors
hastagaras-anjir-8b-l3-mk-ii-v2-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-mk-ii-v2-mkmlizer: warnings.warn(
hastagaras-anjir-8b-l3-mk-ii-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-anjir-8b-l3-mk-ii-v2-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-mk-ii-v2-mkmlizer: warnings.warn(
hastagaras-anjir-8b-l3-mk-ii-v2-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-mk-ii-v2-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-anjir-8b-l3-mk-ii-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-anjir-8b-l3-mk-ii-v2-mkmlizer: Saving duration: 0.403s
hastagaras-anjir-8b-l3-mk-ii-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.378s
hastagaras-anjir-8b-l3-mk-ii-v2-mkmlizer: creating bucket guanaco-reward-models
hastagaras-anjir-8b-l3-mk-ii-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-anjir-8b-l3-mk-ii-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-anjir-8b-l3-mk-ii-v2_reward
hastagaras-anjir-8b-l3-mk-ii-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-mk-ii-v2_reward/tokenizer_config.json
hastagaras-anjir-8b-l3-mk-ii-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-anjir-8b-l3-mk-ii-v2_reward/merges.txt
hastagaras-anjir-8b-l3-mk-ii-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-mk-ii-v2_reward/config.json
hastagaras-anjir-8b-l3-mk-ii-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-mk-ii-v2_reward/special_tokens_map.json
hastagaras-anjir-8b-l3-mk-ii-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-mk-ii-v2_reward/vocab.json
hastagaras-anjir-8b-l3-mk-ii-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-mk-ii-v2_reward/tokenizer.json
hastagaras-anjir-8b-l3-mk-ii-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-anjir-8b-l3-mk-ii-v2_reward/reward.tensors
Job hastagaras-anjir-8b-l3-mk-ii-v2-mkmlizer completed after 72.94s with status: succeeded
Stopping job with name hastagaras-anjir-8b-l3-mk-ii-v2-mkmlizer
Pipeline stage MKMLizer completed in 73.31s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-anjir-8b-l3-mk-ii-v2
Waiting for inference service hastagaras-anjir-8b-l3-mk-ii-v2 to be ready
Inference service hastagaras-anjir-8b-l3-mk-ii-v2 ready after 40.238462924957275s
Pipeline stage ISVCDeployer completed in 45.81s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0791547298431396s
Received healthy response to inference request in 1.364912509918213s
Received healthy response to inference request in 1.3349964618682861s
Received healthy response to inference request in 1.3012192249298096s
Received healthy response to inference request in 1.2795026302337646s
5 requests
0 failed requests
5th percentile: 1.2838459491729737
10th percentile: 1.2881892681121827
20th percentile: 1.2968759059906005
30th percentile: 1.307974672317505
40th percentile: 1.3214855670928956
50th percentile: 1.3349964618682861
60th percentile: 1.3469628810882568
70th percentile: 1.3589293003082275
80th percentile: 1.5077609539031984
90th percentile: 1.793457841873169
95th percentile: 1.9363062858581541
99th percentile: 2.0505850410461424
mean time: 1.4719571113586425
Pipeline stage StressChecker completed in 8.00s
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-mk-ii_v2 status is now deployed due to DeploymentManager action
hastagaras-anjir-8b-l3-mk-ii_v2 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics