submission_id: hastagaras-anjir-8b-l3_v5
developer_uid: Hastagaras
status: inactive
model_repo: Hastagaras/Anjir-8B-L3
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.075, '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: 2024-05-30T08:49:11+00:00
model_name: test4
model_eval_status: success
model_group: Hastagaras/Anjir-8B-L3
num_battles: 10294
num_wins: 5867
celo_rating: 1213.02
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: test4
ineligible_reason: propriety_total_count < 5000
language_model: Hastagaras/Anjir-8B-L3
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-05-30
win_ratio: 0.5699436564989314
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-anjir-8b-l3-v5-mkmlizer
Waiting for job on hastagaras-anjir-8b-l3-v5-mkmlizer to finish
hastagaras-anjir-8b-l3-v5-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-anjir-8b-l3-v5-mkmlizer: ║ _____ __ __ ║
hastagaras-anjir-8b-l3-v5-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-anjir-8b-l3-v5-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-anjir-8b-l3-v5-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-anjir-8b-l3-v5-mkmlizer: ║ /___/ ║
hastagaras-anjir-8b-l3-v5-mkmlizer: ║ ║
hastagaras-anjir-8b-l3-v5-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-anjir-8b-l3-v5-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-anjir-8b-l3-v5-mkmlizer: ║ https://mk1.ai ║
hastagaras-anjir-8b-l3-v5-mkmlizer: ║ ║
hastagaras-anjir-8b-l3-v5-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-anjir-8b-l3-v5-mkmlizer: ║ belonging to: ║
hastagaras-anjir-8b-l3-v5-mkmlizer: ║ ║
hastagaras-anjir-8b-l3-v5-mkmlizer: ║ Chai Research Corp. ║
hastagaras-anjir-8b-l3-v5-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-anjir-8b-l3-v5-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-anjir-8b-l3-v5-mkmlizer: ║ ║
hastagaras-anjir-8b-l3-v5-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-anjir-8b-l3-v5-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-v5-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-anjir-8b-l3-v5-mkmlizer: Downloaded to shared memory in 52.910s
hastagaras-anjir-8b-l3-v5-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-anjir-8b-l3-v5-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-anjir-8b-l3-v5-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<11:36, 2.41s/it] Loading 0: 5%|▌ | 15/291 [00:04<01:06, 4.13it/s] Loading 0: 11%|█ | 32/291 [00:05<00:24, 10.59it/s] Loading 0: 17%|█▋ | 49/291 [00:05<00:12, 18.89it/s] Loading 0: 21%|██▏ | 62/291 [00:05<00:10, 22.55it/s] Loading 0: 26%|██▋ | 77/291 [00:05<00:06, 32.13it/s] Loading 0: 32%|███▏ | 94/291 [00:05<00:04, 45.19it/s] Loading 0: 36%|███▋ | 106/291 [00:05<00:03, 54.33it/s] Loading 0: 42%|████▏ | 122/291 [00:05<00:02, 68.08it/s] Loading 0: 46%|████▋ | 135/291 [00:06<00:01, 78.51it/s] Loading 0: 51%|█████ | 148/291 [00:06<00:01, 87.70it/s] Loading 0: 55%|█████▌ | 161/291 [00:06<00:01, 92.31it/s] Loading 0: 59%|█████▉ | 173/291 [00:06<00:01, 65.49it/s] Loading 0: 64%|██████▎ | 185/291 [00:06<00:01, 74.59it/s] Loading 0: 69%|██████▊ | 200/291 [00:06<00:01, 89.65it/s] Loading 0: 73%|███████▎ | 212/291 [00:06<00:00, 96.02it/s] Loading 0: 78%|███████▊ | 228/291 [00:07<00:00, 111.42it/s] Loading 0: 83%|████████▎ | 241/291 [00:07<00:00, 110.14it/s] Loading 0: 88%|████████▊ | 257/291 [00:07<00:00, 118.34it/s] Loading 0: 93%|█████████▎| 270/291 [00:07<00:00, 75.57it/s] Loading 0: 98%|█████████▊| 284/291 [00:07<00:00, 86.32it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-anjir-8b-l3-v5-mkmlizer: quantized model in 24.031s
hastagaras-anjir-8b-l3-v5-mkmlizer: Processed model Hastagaras/Anjir-8B-L3 in 79.476s
hastagaras-anjir-8b-l3-v5-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-anjir-8b-l3-v5-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-anjir-8b-l3-v5-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-v5
hastagaras-anjir-8b-l3-v5-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-v5/config.json
hastagaras-anjir-8b-l3-v5-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-v5/special_tokens_map.json
hastagaras-anjir-8b-l3-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-v5/tokenizer_config.json
hastagaras-anjir-8b-l3-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-v5/tokenizer.json
hastagaras-anjir-8b-l3-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-v5/flywheel_model.0.safetensors
hastagaras-anjir-8b-l3-v5-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-anjir-8b-l3-v5-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-v5-mkmlizer: warnings.warn(
hastagaras-anjir-8b-l3-v5-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-v5-mkmlizer: warnings.warn(
hastagaras-anjir-8b-l3-v5-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-v5-mkmlizer: warnings.warn(
hastagaras-anjir-8b-l3-v5-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-v5-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-anjir-8b-l3-v5-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-anjir-8b-l3-v5-mkmlizer: Saving duration: 0.393s
hastagaras-anjir-8b-l3-v5-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 12.177s
hastagaras-anjir-8b-l3-v5-mkmlizer: creating bucket guanaco-reward-models
hastagaras-anjir-8b-l3-v5-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-anjir-8b-l3-v5-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-anjir-8b-l3-v5_reward
hastagaras-anjir-8b-l3-v5-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-v5_reward/config.json
hastagaras-anjir-8b-l3-v5-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-v5_reward/tokenizer_config.json
hastagaras-anjir-8b-l3-v5-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-v5_reward/special_tokens_map.json
hastagaras-anjir-8b-l3-v5-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-anjir-8b-l3-v5_reward/merges.txt
hastagaras-anjir-8b-l3-v5-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-v5_reward/vocab.json
hastagaras-anjir-8b-l3-v5-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-v5_reward/tokenizer.json
Job hastagaras-anjir-8b-l3-v5-mkmlizer completed after 113.41s with status: succeeded
Stopping job with name hastagaras-anjir-8b-l3-v5-mkmlizer
Pipeline stage MKMLizer completed in 114.89s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-anjir-8b-l3-v5
Waiting for inference service hastagaras-anjir-8b-l3-v5 to be ready
Inference service hastagaras-anjir-8b-l3-v5 ready after 100.47201418876648s
Pipeline stage ISVCDeployer completed in 106.26s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.185214042663574s
Received healthy response to inference request in 1.3296284675598145s
Received healthy response to inference request in 1.336381435394287s
Received healthy response to inference request in 1.308863639831543s
Received healthy response to inference request in 1.2636752128601074s
5 requests
0 failed requests
5th percentile: 1.2727128982543945
10th percentile: 1.2817505836486816
20th percentile: 1.299825954437256
30th percentile: 1.3130166053771972
40th percentile: 1.321322536468506
50th percentile: 1.3296284675598145
60th percentile: 1.3323296546936034
70th percentile: 1.3350308418273926
80th percentile: 1.5061479568481446
90th percentile: 1.8456809997558594
95th percentile: 2.0154475212097167
99th percentile: 2.1512607383728026
mean time: 1.4847525596618651
Pipeline stage StressChecker completed in 8.04s
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_v5 status is now deployed due to DeploymentManager action
hastagaras-anjir-8b-l3_v5 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics