submission_id: hastagaras-yaelah-8b-lla_4014_v1
developer_uid: Hastagaras
status: inactive
model_repo: Hastagaras/Yaelah-8B-Llama3-Test
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.05, 'top_p': 1.0, 'min_p': 0.05, '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: 2024-06-02T07:29:07+00:00
model_name: gmn
model_eval_status: success
model_group: Hastagaras/Yaelah-8B-Lla
num_battles: 8260
num_wins: 4495
celo_rating: 1206.15
safety_score: 0.95
propriety_score: 0.6647727272727273
propriety_total_count: 176.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: gmn
ineligible_reason: propriety_total_count < 5000
language_model: Hastagaras/Yaelah-8B-Llama3-Test
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-02
win_ratio: 0.5441888619854721
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-yaelah-8b-lla-4014-v1-mkmlizer
Waiting for job on hastagaras-yaelah-8b-lla-4014-v1-mkmlizer to finish
hastagaras-yaelah-8b-lla-4014-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-yaelah-8b-lla-4014-v1-mkmlizer: ║ _____ __ __ ║
hastagaras-yaelah-8b-lla-4014-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-yaelah-8b-lla-4014-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-yaelah-8b-lla-4014-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-yaelah-8b-lla-4014-v1-mkmlizer: ║ /___/ ║
hastagaras-yaelah-8b-lla-4014-v1-mkmlizer: ║ ║
hastagaras-yaelah-8b-lla-4014-v1-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-yaelah-8b-lla-4014-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-yaelah-8b-lla-4014-v1-mkmlizer: ║ https://mk1.ai ║
hastagaras-yaelah-8b-lla-4014-v1-mkmlizer: ║ ║
hastagaras-yaelah-8b-lla-4014-v1-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-yaelah-8b-lla-4014-v1-mkmlizer: ║ belonging to: ║
hastagaras-yaelah-8b-lla-4014-v1-mkmlizer: ║ ║
hastagaras-yaelah-8b-lla-4014-v1-mkmlizer: ║ Chai Research Corp. ║
hastagaras-yaelah-8b-lla-4014-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-yaelah-8b-lla-4014-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-yaelah-8b-lla-4014-v1-mkmlizer: ║ ║
hastagaras-yaelah-8b-lla-4014-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-yaelah-8b-lla-4014-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-yaelah-8b-lla-4014-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-yaelah-8b-lla-4014-v1-mkmlizer: Downloaded to shared memory in 28.667s
hastagaras-yaelah-8b-lla-4014-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-yaelah-8b-lla-4014-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-yaelah-8b-lla-4014-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:02, 123.86it/s] Loading 0: 11%|█ | 31/291 [00:00<00:01, 149.59it/s] Loading 0: 17%|█▋ | 49/291 [00:00<00:01, 157.41it/s] Loading 0: 23%|██▎ | 67/291 [00:00<00:01, 161.52it/s] Loading 0: 29%|██▉ | 84/291 [00:00<00:02, 87.96it/s] Loading 0: 35%|███▌ | 102/291 [00:00<00:01, 105.44it/s] Loading 0: 41%|████ | 120/291 [00:00<00:01, 120.46it/s] Loading 0: 47%|████▋ | 138/291 [00:01<00:01, 132.22it/s] Loading 0: 54%|█████▎ | 156/291 [00:01<00:00, 140.99it/s] Loading 0: 59%|█████▉ | 173/291 [00:01<00:00, 142.81it/s] Loading 0: 65%|██████▍ | 189/291 [00:01<00:01, 90.44it/s] Loading 0: 71%|███████ | 206/291 [00:01<00:00, 104.76it/s] Loading 0: 76%|███████▌ | 221/291 [00:01<00:00, 114.07it/s] Loading 0: 82%|████████▏ | 239/291 [00:01<00:00, 126.68it/s] Loading 0: 88%|████████▊ | 257/291 [00:02<00:00, 137.68it/s] Loading 0: 95%|█████████▍| 275/291 [00:02<00:00, 144.18it/s] Loading 0: 100%|██████████| 291/291 [00:07<00:00, 9.84it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-yaelah-8b-lla-4014-v1-mkmlizer: quantized model in 23.090s
hastagaras-yaelah-8b-lla-4014-v1-mkmlizer: Processed model Hastagaras/Yaelah-8B-Llama3-Test in 54.229s
hastagaras-yaelah-8b-lla-4014-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-yaelah-8b-lla-4014-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-yaelah-8b-lla-4014-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-yaelah-8b-lla-4014-v1
hastagaras-yaelah-8b-lla-4014-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-yaelah-8b-lla-4014-v1/config.json
hastagaras-yaelah-8b-lla-4014-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-yaelah-8b-lla-4014-v1/tokenizer_config.json
hastagaras-yaelah-8b-lla-4014-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-yaelah-8b-lla-4014-v1/special_tokens_map.json
hastagaras-yaelah-8b-lla-4014-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-yaelah-8b-lla-4014-v1/tokenizer.json
hastagaras-yaelah-8b-lla-4014-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-yaelah-8b-lla-4014-v1/flywheel_model.0.safetensors
hastagaras-yaelah-8b-lla-4014-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-yaelah-8b-lla-4014-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-yaelah-8b-lla-4014-v1-mkmlizer: warnings.warn(
hastagaras-yaelah-8b-lla-4014-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-yaelah-8b-lla-4014-v1-mkmlizer: warnings.warn(
hastagaras-yaelah-8b-lla-4014-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-yaelah-8b-lla-4014-v1-mkmlizer: warnings.warn(
hastagaras-yaelah-8b-lla-4014-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-yaelah-8b-lla-4014-v1-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-yaelah-8b-lla-4014-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-yaelah-8b-lla-4014-v1-mkmlizer: Saving duration: 0.388s
hastagaras-yaelah-8b-lla-4014-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.244s
hastagaras-yaelah-8b-lla-4014-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-yaelah-8b-lla-4014-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-yaelah-8b-lla-4014-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-yaelah-8b-lla-4014-v1_reward
hastagaras-yaelah-8b-lla-4014-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-yaelah-8b-lla-4014-v1_reward/config.json
hastagaras-yaelah-8b-lla-4014-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-yaelah-8b-lla-4014-v1_reward/tokenizer_config.json
hastagaras-yaelah-8b-lla-4014-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-yaelah-8b-lla-4014-v1_reward/special_tokens_map.json
hastagaras-yaelah-8b-lla-4014-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-yaelah-8b-lla-4014-v1_reward/merges.txt
hastagaras-yaelah-8b-lla-4014-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-yaelah-8b-lla-4014-v1_reward/vocab.json
hastagaras-yaelah-8b-lla-4014-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-yaelah-8b-lla-4014-v1_reward/tokenizer.json
hastagaras-yaelah-8b-lla-4014-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-yaelah-8b-lla-4014-v1_reward/reward.tensors
Job hastagaras-yaelah-8b-lla-4014-v1-mkmlizer completed after 83.41s with status: succeeded
Stopping job with name hastagaras-yaelah-8b-lla-4014-v1-mkmlizer
Pipeline stage MKMLizer completed in 88.54s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-yaelah-8b-lla-4014-v1
Waiting for inference service hastagaras-yaelah-8b-lla-4014-v1 to be ready
Inference service hastagaras-yaelah-8b-lla-4014-v1 ready after 40.2452826499939s
Pipeline stage ISVCDeployer completed in 48.27s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2622926235198975s
Received healthy response to inference request in 1.3822760581970215s
Received healthy response to inference request in 1.3497605323791504s
Received healthy response to inference request in 1.3241004943847656s
Received healthy response to inference request in 1.265049695968628s
5 requests
0 failed requests
5th percentile: 1.2768598556518556
10th percentile: 1.288670015335083
20th percentile: 1.312290334701538
30th percentile: 1.3292325019836426
40th percentile: 1.3394965171813964
50th percentile: 1.3497605323791504
60th percentile: 1.3627667427062988
70th percentile: 1.3757729530334473
80th percentile: 1.5582793712615968
90th percentile: 1.9102859973907471
95th percentile: 2.086289310455322
99th percentile: 2.2270919609069826
mean time: 1.5166958808898925
Pipeline stage StressChecker completed in 8.32s
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-yaelah-8b-lla_4014_v1 status is now deployed due to DeploymentManager action
hastagaras-yaelah-8b-lla_4014_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics