submission_id: hastagaras-anjir-8b-l3_v8
developer_uid: Hastagaras
status: inactive
model_repo: Hastagaras/Anjir-8B-L3
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 0.08, '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': "<|begin_of_text|>{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}
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: 2024-06-11T08:07:48+00:00
model_name: tst
model_eval_status: success
model_group: Hastagaras/Anjir-8B-L3
num_battles: 15633
num_wins: 8684
celo_rating: 1210.08
safety_score: 0.89
propriety_score: 0.6671501087744742
propriety_total_count: 5516.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: tst
ineligible_reason: None
language_model: Hastagaras/Anjir-8B-L3
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-11
win_ratio: 0.5554915883067869
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-anjir-8b-l3-v8-mkmlizer
Waiting for job on hastagaras-anjir-8b-l3-v8-mkmlizer to finish
hastagaras-anjir-8b-l3-v8-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-anjir-8b-l3-v8-mkmlizer: ║ _____ __ __ ║
hastagaras-anjir-8b-l3-v8-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-anjir-8b-l3-v8-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-anjir-8b-l3-v8-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-anjir-8b-l3-v8-mkmlizer: ║ /___/ ║
hastagaras-anjir-8b-l3-v8-mkmlizer: ║ ║
hastagaras-anjir-8b-l3-v8-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-anjir-8b-l3-v8-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-anjir-8b-l3-v8-mkmlizer: ║ https://mk1.ai ║
hastagaras-anjir-8b-l3-v8-mkmlizer: ║ ║
hastagaras-anjir-8b-l3-v8-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-anjir-8b-l3-v8-mkmlizer: ║ belonging to: ║
hastagaras-anjir-8b-l3-v8-mkmlizer: ║ ║
hastagaras-anjir-8b-l3-v8-mkmlizer: ║ Chai Research Corp. ║
hastagaras-anjir-8b-l3-v8-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-anjir-8b-l3-v8-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-anjir-8b-l3-v8-mkmlizer: ║ ║
hastagaras-anjir-8b-l3-v8-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-anjir-8b-l3-v8-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-v8-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-anjir-8b-l3-v8-mkmlizer: Downloaded to shared memory in 32.331s
hastagaras-anjir-8b-l3-v8-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-anjir-8b-l3-v8-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-anjir-8b-l3-v8-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:05<13:23, 2.78s/it] Loading 0: 5%|▍ | 14/291 [00:05<01:22, 3.34it/s] Loading 0: 8%|▊ | 24/291 [00:05<00:40, 6.66it/s] Loading 0: 14%|█▎ | 40/291 [00:05<00:18, 13.70it/s] Loading 0: 17%|█▋ | 50/291 [00:06<00:12, 19.04it/s] Loading 0: 21%|██ | 60/291 [00:06<00:12, 19.09it/s] Loading 0: 25%|██▌ | 73/291 [00:06<00:07, 27.88it/s] Loading 0: 30%|██▉ | 86/291 [00:06<00:05, 37.58it/s] Loading 0: 33%|███▎ | 96/291 [00:06<00:04, 45.02it/s] Loading 0: 38%|███▊ | 112/291 [00:06<00:02, 60.76it/s] Loading 0: 42%|████▏ | 123/291 [00:07<00:02, 67.46it/s] Loading 0: 48%|████▊ | 139/291 [00:07<00:01, 82.12it/s] Loading 0: 52%|█████▏ | 151/291 [00:07<00:01, 87.01it/s] Loading 0: 57%|█████▋ | 166/291 [00:07<00:02, 52.41it/s] Loading 0: 60%|██████ | 176/291 [00:07<00:01, 58.75it/s] Loading 0: 64%|██████▍ | 187/291 [00:08<00:01, 67.28it/s] Loading 0: 69%|██████▉ | 202/291 [00:08<00:01, 81.10it/s] Loading 0: 73%|███████▎ | 213/291 [00:08<00:00, 84.22it/s] Loading 0: 79%|███████▊ | 229/291 [00:08<00:00, 98.12it/s] Loading 0: 83%|████████▎ | 241/291 [00:08<00:00, 98.16it/s] Loading 0: 88%|████████▊ | 256/291 [00:08<00:00, 105.58it/s] Loading 0: 92%|█████████▏| 268/291 [00:09<00:00, 55.22it/s] Loading 0: 97%|█████████▋| 283/291 [00:09<00:00, 68.35it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-anjir-8b-l3-v8-mkmlizer: quantized model in 22.830s
hastagaras-anjir-8b-l3-v8-mkmlizer: Processed model Hastagaras/Anjir-8B-L3 in 56.528s
hastagaras-anjir-8b-l3-v8-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-anjir-8b-l3-v8-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-anjir-8b-l3-v8-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-v8
hastagaras-anjir-8b-l3-v8-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-v8/config.json
hastagaras-anjir-8b-l3-v8-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-v8/special_tokens_map.json
hastagaras-anjir-8b-l3-v8-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-v8/tokenizer_config.json
hastagaras-anjir-8b-l3-v8-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-v8/tokenizer.json
hastagaras-anjir-8b-l3-v8-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-v8/flywheel_model.0.safetensors
hastagaras-anjir-8b-l3-v8-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-anjir-8b-l3-v8-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-v8-mkmlizer: warnings.warn(
hastagaras-anjir-8b-l3-v8-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-v8-mkmlizer: warnings.warn(
hastagaras-anjir-8b-l3-v8-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-v8-mkmlizer: warnings.warn(
hastagaras-anjir-8b-l3-v8-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-v8-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-anjir-8b-l3-v8-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-anjir-8b-l3-v8-mkmlizer: Saving duration: 0.313s
hastagaras-anjir-8b-l3-v8-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.558s
hastagaras-anjir-8b-l3-v8-mkmlizer: creating bucket guanaco-reward-models
hastagaras-anjir-8b-l3-v8-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-anjir-8b-l3-v8-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-anjir-8b-l3-v8_reward
hastagaras-anjir-8b-l3-v8-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-v8_reward/tokenizer_config.json
hastagaras-anjir-8b-l3-v8-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-v8_reward/config.json
hastagaras-anjir-8b-l3-v8-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-anjir-8b-l3-v8_reward/merges.txt
hastagaras-anjir-8b-l3-v8-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-v8_reward/vocab.json
hastagaras-anjir-8b-l3-v8-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-v8_reward/special_tokens_map.json
hastagaras-anjir-8b-l3-v8-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-v8_reward/tokenizer.json
hastagaras-anjir-8b-l3-v8-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-anjir-8b-l3-v8_reward/reward.tensors
Job hastagaras-anjir-8b-l3-v8-mkmlizer completed after 83.01s with status: succeeded
Stopping job with name hastagaras-anjir-8b-l3-v8-mkmlizer
Pipeline stage MKMLizer completed in 83.94s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.08s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-anjir-8b-l3-v8
Waiting for inference service hastagaras-anjir-8b-l3-v8 to be ready
Inference service hastagaras-anjir-8b-l3-v8 ready after 40.20376133918762s
Pipeline stage ISVCDeployer completed in 46.15s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0935819149017334s
Received healthy response to inference request in 1.2452392578125s
Received healthy response to inference request in 1.259317398071289s
Received healthy response to inference request in 1.2404544353485107s
Received healthy response to inference request in 1.2737035751342773s
5 requests
0 failed requests
5th percentile: 1.2414113998413085
10th percentile: 1.2423683643341064
20th percentile: 1.2442822933197022
30th percentile: 1.2480548858642577
40th percentile: 1.2536861419677734
50th percentile: 1.259317398071289
60th percentile: 1.2650718688964844
70th percentile: 1.2708263397216797
80th percentile: 1.4376792430877687
90th percentile: 1.765630578994751
95th percentile: 1.929606246948242
99th percentile: 2.060786781311035
mean time: 1.422459316253662
Pipeline stage StressChecker completed in 7.83s
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_v8 status is now deployed due to DeploymentManager action
hastagaras-anjir-8b-l3_v8 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics