submission_id: hastagaras-jamet-8b-l3-m_3129_v1
developer_uid: Hastagaras
status: inactive
model_repo: Hastagaras/Jamet-8B-L3-MK.III-EX
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.0, 'top_p': 0.95, 'min_p': 0.1, '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: 2024-06-05T22:11:16+00:00
model_name: dt-flip
model_eval_status: success
model_group: Hastagaras/Jamet-8B-L3-M
num_battles: 27584
num_wins: 15387
celo_rating: 1214.4
safety_score: 0.96
propriety_score: 0.6518796992481203
propriety_total_count: 1330.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: dt-flip
ineligible_reason: propriety_total_count < 5000
language_model: Hastagaras/Jamet-8B-L3-MK.III-EX
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-05
win_ratio: 0.5578233758700696
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-jamet-8b-l3-m-3129-v1-mkmlizer
Waiting for job on hastagaras-jamet-8b-l3-m-3129-v1-mkmlizer to finish
hastagaras-jamet-8b-l3-m-3129-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-jamet-8b-l3-m-3129-v1-mkmlizer: ║ _____ __ __ ║
hastagaras-jamet-8b-l3-m-3129-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-jamet-8b-l3-m-3129-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-jamet-8b-l3-m-3129-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-jamet-8b-l3-m-3129-v1-mkmlizer: ║ /___/ ║
hastagaras-jamet-8b-l3-m-3129-v1-mkmlizer: ║ ║
hastagaras-jamet-8b-l3-m-3129-v1-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-jamet-8b-l3-m-3129-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-jamet-8b-l3-m-3129-v1-mkmlizer: ║ https://mk1.ai ║
hastagaras-jamet-8b-l3-m-3129-v1-mkmlizer: ║ ║
hastagaras-jamet-8b-l3-m-3129-v1-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-jamet-8b-l3-m-3129-v1-mkmlizer: ║ belonging to: ║
hastagaras-jamet-8b-l3-m-3129-v1-mkmlizer: ║ ║
hastagaras-jamet-8b-l3-m-3129-v1-mkmlizer: ║ Chai Research Corp. ║
hastagaras-jamet-8b-l3-m-3129-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-jamet-8b-l3-m-3129-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-jamet-8b-l3-m-3129-v1-mkmlizer: ║ ║
hastagaras-jamet-8b-l3-m-3129-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-jamet-8b-l3-m-3129-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-jamet-8b-l3-m-3129-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-jamet-8b-l3-m-3129-v1-mkmlizer: Downloaded to shared memory in 40.861s
hastagaras-jamet-8b-l3-m-3129-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-jamet-8b-l3-m-3129-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-jamet-8b-l3-m-3129-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 5%|▍ | 14/291 [00:00<00:02, 125.98it/s] Loading 0: 11%|█ | 31/291 [00:00<00:01, 144.03it/s] Loading 0: 16%|█▋ | 48/291 [00:00<00:01, 152.93it/s] Loading 0: 22%|██▏ | 64/291 [00:00<00:01, 155.56it/s] Loading 0: 27%|██▋ | 80/291 [00:00<00:01, 149.45it/s] Loading 0: 33%|███▎ | 96/291 [00:01<00:02, 68.63it/s] Loading 0: 38%|███▊ | 112/291 [00:01<00:02, 83.30it/s] Loading 0: 45%|████▍ | 130/291 [00:01<00:01, 99.50it/s] Loading 0: 51%|█████ | 147/291 [00:01<00:01, 114.55it/s] Loading 0: 56%|█████▌ | 163/291 [00:01<00:01, 125.15it/s] Loading 0: 62%|██████▏ | 180/291 [00:01<00:00, 131.45it/s] Loading 0: 67%|██████▋ | 195/291 [00:01<00:01, 74.28it/s] Loading 0: 72%|███████▏ | 210/291 [00:02<00:00, 86.43it/s] Loading 0: 77%|███████▋ | 224/291 [00:02<00:00, 96.32it/s] Loading 0: 82%|████████▏ | 239/291 [00:02<00:00, 104.39it/s] Loading 0: 88%|████████▊ | 256/291 [00:02<00:00, 117.81it/s] Loading 0: 94%|█████████▍| 273/291 [00:02<00:00, 128.76it/s] Loading 0: 99%|█████████▉| 288/291 [00:07<00:00, 9.57it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-jamet-8b-l3-m-3129-v1-mkmlizer: quantized model in 19.877s
hastagaras-jamet-8b-l3-m-3129-v1-mkmlizer: Processed model Hastagaras/Jamet-8B-L3-MK.III-EX in 61.779s
hastagaras-jamet-8b-l3-m-3129-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-jamet-8b-l3-m-3129-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-m-3129-v1
hastagaras-jamet-8b-l3-m-3129-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-m-3129-v1/config.json
hastagaras-jamet-8b-l3-m-3129-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-m-3129-v1/special_tokens_map.json
hastagaras-jamet-8b-l3-m-3129-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-m-3129-v1/tokenizer_config.json
hastagaras-jamet-8b-l3-m-3129-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-m-3129-v1/tokenizer.json
hastagaras-jamet-8b-l3-m-3129-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-m-3129-v1/flywheel_model.0.safetensors
hastagaras-jamet-8b-l3-m-3129-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-jamet-8b-l3-m-3129-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-jamet-8b-l3-m-3129-v1-mkmlizer: warnings.warn(
hastagaras-jamet-8b-l3-m-3129-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-jamet-8b-l3-m-3129-v1-mkmlizer: warnings.warn(
hastagaras-jamet-8b-l3-m-3129-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-jamet-8b-l3-m-3129-v1-mkmlizer: warnings.warn(
hastagaras-jamet-8b-l3-m-3129-v1-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-jamet-8b-l3-m-3129-v1-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-jamet-8b-l3-m-3129-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-jamet-8b-l3-m-3129-v1-mkmlizer: Saving duration: 0.309s
hastagaras-jamet-8b-l3-m-3129-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 6.689s
hastagaras-jamet-8b-l3-m-3129-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-jamet-8b-l3-m-3129-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-jamet-8b-l3-m-3129-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-3129-v1_reward
hastagaras-jamet-8b-l3-m-3129-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-3129-v1_reward/config.json
hastagaras-jamet-8b-l3-m-3129-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-3129-v1_reward/special_tokens_map.json
hastagaras-jamet-8b-l3-m-3129-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-3129-v1_reward/tokenizer_config.json
hastagaras-jamet-8b-l3-m-3129-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-3129-v1_reward/merges.txt
hastagaras-jamet-8b-l3-m-3129-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-3129-v1_reward/vocab.json
hastagaras-jamet-8b-l3-m-3129-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-3129-v1_reward/tokenizer.json
hastagaras-jamet-8b-l3-m-3129-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-3129-v1_reward/reward.tensors
Job hastagaras-jamet-8b-l3-m-3129-v1-mkmlizer completed after 126.87s with status: succeeded
Stopping job with name hastagaras-jamet-8b-l3-m-3129-v1-mkmlizer
Pipeline stage MKMLizer completed in 127.77s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.08s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-jamet-8b-l3-m-3129-v1
Waiting for inference service hastagaras-jamet-8b-l3-m-3129-v1 to be ready
Inference service hastagaras-jamet-8b-l3-m-3129-v1 ready after 50.279683113098145s
Pipeline stage ISVCDeployer completed in 58.53s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1600146293640137s
Received healthy response to inference request in 1.353893756866455s
Received healthy response to inference request in 1.350414752960205s
Received healthy response to inference request in 1.3054871559143066s
Received healthy response to inference request in 1.2418968677520752s
5 requests
0 failed requests
5th percentile: 1.2546149253845216
10th percentile: 1.2673329830169677
20th percentile: 1.2927690982818603
30th percentile: 1.3144726753234863
40th percentile: 1.3324437141418457
50th percentile: 1.350414752960205
60th percentile: 1.351806354522705
70th percentile: 1.353197956085205
80th percentile: 1.515117931365967
90th percentile: 1.8375662803649904
95th percentile: 1.9987904548645017
99th percentile: 2.127769794464111
mean time: 1.482341432571411
Pipeline stage StressChecker completed in 7.99s
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-jamet-8b-l3-m_3129_v1 status is now deployed due to DeploymentManager action
hastagaras-jamet-8b-l3-m_3129_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics