submission_id: hastagaras-anjir-8b-l3-m_8084_v2
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': "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n{bot_name}'s Persona: {memory}\n\n", 'prompt_template': '{prompt}<|eot_id|>', 'bot_template': '<|start_header_id|>assistant<|end_header_id|>\n{bot_name}: {message}<|eot_id|>', 'user_template': '<|start_header_id|>user<|end_header_id|>\n{user_name}: {message}<|eot_id|>', 'response_template': '<|start_header_id|>assistant<|end_header_id|>\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: 2024-06-11T18:02:18+00:00
model_name: itrtv
model_eval_status: success
model_group: Hastagaras/Anjir-8B-L3-M
num_battles: 44587
num_wins: 25277
celo_rating: 1216.78
safety_score: 0.92
propriety_score: 0.6832589673755577
propriety_total_count: 17257.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: itrtv
ineligible_reason: None
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: 0.5669141229506358
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-anjir-8b-l3-m-8084-v2-mkmlizer
Waiting for job on hastagaras-anjir-8b-l3-m-8084-v2-mkmlizer to finish
hastagaras-anjir-8b-l3-m-8084-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-anjir-8b-l3-m-8084-v2-mkmlizer: ║ _____ __ __ ║
hastagaras-anjir-8b-l3-m-8084-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-anjir-8b-l3-m-8084-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-anjir-8b-l3-m-8084-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-anjir-8b-l3-m-8084-v2-mkmlizer: ║ /___/ ║
hastagaras-anjir-8b-l3-m-8084-v2-mkmlizer: ║ ║
hastagaras-anjir-8b-l3-m-8084-v2-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-anjir-8b-l3-m-8084-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-anjir-8b-l3-m-8084-v2-mkmlizer: ║ https://mk1.ai ║
hastagaras-anjir-8b-l3-m-8084-v2-mkmlizer: ║ ║
hastagaras-anjir-8b-l3-m-8084-v2-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-anjir-8b-l3-m-8084-v2-mkmlizer: ║ belonging to: ║
hastagaras-anjir-8b-l3-m-8084-v2-mkmlizer: ║ ║
hastagaras-anjir-8b-l3-m-8084-v2-mkmlizer: ║ Chai Research Corp. ║
hastagaras-anjir-8b-l3-m-8084-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-anjir-8b-l3-m-8084-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-anjir-8b-l3-m-8084-v2-mkmlizer: ║ ║
hastagaras-anjir-8b-l3-m-8084-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-anjir-8b-l3-m-8084-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-m-8084-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-anjir-8b-l3-m-8084-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:02, 124.64it/s] Loading 0: 10%|█ | 30/291 [00:00<00:01, 147.29it/s] Loading 0: 15%|█▌ | 45/291 [00:00<00:01, 146.79it/s] Loading 0: 21%|██ | 60/291 [00:00<00:01, 143.14it/s] Loading 0: 26%|██▌ | 76/291 [00:00<00:01, 145.97it/s] Loading 0: 31%|███▏ | 91/291 [00:00<00:02, 71.88it/s] Loading 0: 36%|███▌ | 104/291 [00:01<00:02, 81.86it/s] Loading 0: 42%|████▏ | 121/291 [00:01<00:01, 99.02it/s] Loading 0: 47%|████▋ | 138/291 [00:01<00:01, 113.93it/s] Loading 0: 52%|█████▏ | 152/291 [00:01<00:01, 119.91it/s] Loading 0: 57%|█████▋ | 167/291 [00:01<00:00, 124.04it/s] Loading 0: 64%|██████▎ | 185/291 [00:01<00:00, 138.45it/s] Loading 0: 69%|██████▉ | 201/291 [00:01<00:01, 79.14it/s] Loading 0: 74%|███████▍ | 215/291 [00:02<00:00, 89.20it/s] Loading 0: 79%|███████▉ | 230/291 [00:02<00:00, 98.91it/s] Loading 0: 85%|████████▍ | 247/291 [00:02<00:00, 114.34it/s] Loading 0: 91%|█████████ | 265/291 [00:02<00:00, 125.64it/s] Loading 0: 97%|█████████▋| 282/291 [00:02<00:00, 132.20it/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-v2-mkmlizer: quantized model in 19.883s
hastagaras-anjir-8b-l3-m-8084-v2-mkmlizer: Processed model Hastagaras/Anjir-8B-L3-MK.V-BJ2 in 47.891s
hastagaras-anjir-8b-l3-m-8084-v2-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-anjir-8b-l3-m-8084-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-anjir-8b-l3-m-8084-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-m-8084-v2
hastagaras-anjir-8b-l3-m-8084-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-m-8084-v2/config.json
hastagaras-anjir-8b-l3-m-8084-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-m-8084-v2/special_tokens_map.json
hastagaras-anjir-8b-l3-m-8084-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-m-8084-v2/tokenizer_config.json
hastagaras-anjir-8b-l3-m-8084-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-m-8084-v2/tokenizer.json
hastagaras-anjir-8b-l3-m-8084-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-m-8084-v2/flywheel_model.0.safetensors
hastagaras-anjir-8b-l3-m-8084-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-anjir-8b-l3-m-8084-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-m-8084-v2-mkmlizer: warnings.warn(
hastagaras-anjir-8b-l3-m-8084-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-m-8084-v2-mkmlizer: warnings.warn(
hastagaras-anjir-8b-l3-m-8084-v2-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-v2-mkmlizer: warnings.warn(
hastagaras-anjir-8b-l3-m-8084-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-m-8084-v2-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-anjir-8b-l3-m-8084-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-anjir-8b-l3-m-8084-v2-mkmlizer: Saving duration: 0.327s
hastagaras-anjir-8b-l3-m-8084-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 6.108s
hastagaras-anjir-8b-l3-m-8084-v2-mkmlizer: creating bucket guanaco-reward-models
hastagaras-anjir-8b-l3-m-8084-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-anjir-8b-l3-m-8084-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-anjir-8b-l3-m-8084-v2_reward
hastagaras-anjir-8b-l3-m-8084-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-m-8084-v2_reward/config.json
hastagaras-anjir-8b-l3-m-8084-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-m-8084-v2_reward/special_tokens_map.json
hastagaras-anjir-8b-l3-m-8084-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-m-8084-v2_reward/tokenizer_config.json
hastagaras-anjir-8b-l3-m-8084-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-anjir-8b-l3-m-8084-v2_reward/merges.txt
hastagaras-anjir-8b-l3-m-8084-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-m-8084-v2_reward/vocab.json
hastagaras-anjir-8b-l3-m-8084-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-m-8084-v2_reward/tokenizer.json
hastagaras-anjir-8b-l3-m-8084-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-anjir-8b-l3-m-8084-v2_reward/reward.tensors
Job hastagaras-anjir-8b-l3-m-8084-v2-mkmlizer completed after 74.17s with status: succeeded
Stopping job with name hastagaras-anjir-8b-l3-m-8084-v2-mkmlizer
Pipeline stage MKMLizer completed in 79.20s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-anjir-8b-l3-m-8084-v2
Waiting for inference service hastagaras-anjir-8b-l3-m-8084-v2 to be ready
Inference service hastagaras-anjir-8b-l3-m-8084-v2 ready after 40.39064383506775s
Pipeline stage ISVCDeployer completed in 48.29s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1559693813323975s
Received healthy response to inference request in 1.3420419692993164s
Received healthy response to inference request in 1.3127655982971191s
Received healthy response to inference request in 1.2873191833496094s
Received healthy response to inference request in 1.3861148357391357s
5 requests
0 failed requests
5th percentile: 1.2924084663391113
10th percentile: 1.2974977493286133
20th percentile: 1.3076763153076172
30th percentile: 1.3186208724975585
40th percentile: 1.3303314208984376
50th percentile: 1.3420419692993164
60th percentile: 1.3596711158752441
70th percentile: 1.3773002624511719
80th percentile: 1.5400857448577883
90th percentile: 1.8480275630950929
95th percentile: 2.001998472213745
99th percentile: 2.125175199508667
mean time: 1.4968421936035157
Pipeline stage StressChecker completed in 8.06s
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-m_8084_v2 status is now deployed due to DeploymentManager action
hastagaras-anjir-8b-l3-m_8084_v2 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics