developer_uid: Hastagaras
submission_id: hastagaras-sciemet-8b-l3_1113_v2
model_name: test
model_group: Hastagaras/Sciemet-8B-L3
status: rejected
timestamp: 2024-06-16T08:41:36+00:00
num_battles: 111
num_wins: 58
family_friendly_score: 0.0
submission_type: basic
model_repo: Hastagaras/Sciemet-8B-L3-MK.I-Alpha
model_architecture: LlamaForCausalLM
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: test
ineligible_reason: model is not deployable
is_internal_developer: False
language_model: Hastagaras/Sciemet-8B-L3-MK.I-Alpha
model_size: 8B
ranking_group: single
us_pacific_date: 2024-06-16
win_ratio: 0.5225225225225225
generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 45, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|eot_id|>'], '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\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}
model_eval_status: error
reward_formatter: {'bot_template': '{bot_name}: {message}\n', 'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'response_template': '{bot_name}:', 'truncate_by_message': False, 'user_template': '{user_name}: {message}\n'}
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-sciemet-8b-l3-1113-v2-mkmlizer
Waiting for job on hastagaras-sciemet-8b-l3-1113-v2-mkmlizer to finish
hastagaras-sciemet-8b-l3-1113-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-sciemet-8b-l3-1113-v2-mkmlizer: ║     _____            __           __                                ║
hastagaras-sciemet-8b-l3-1113-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
hastagaras-sciemet-8b-l3-1113-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
hastagaras-sciemet-8b-l3-1113-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
hastagaras-sciemet-8b-l3-1113-v2-mkmlizer: ║       /___/                                                         ║
hastagaras-sciemet-8b-l3-1113-v2-mkmlizer: ║                                                                     ║
hastagaras-sciemet-8b-l3-1113-v2-mkmlizer: ║  Version: 0.8.14                                                    ║
hastagaras-sciemet-8b-l3-1113-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
hastagaras-sciemet-8b-l3-1113-v2-mkmlizer: ║  https://mk1.ai                                                     ║
hastagaras-sciemet-8b-l3-1113-v2-mkmlizer: ║                                                                     ║
hastagaras-sciemet-8b-l3-1113-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
hastagaras-sciemet-8b-l3-1113-v2-mkmlizer: ║  belonging to:                                                      ║
hastagaras-sciemet-8b-l3-1113-v2-mkmlizer: ║                                                                     ║
hastagaras-sciemet-8b-l3-1113-v2-mkmlizer: ║  Chai Research Corp.                                                ║
hastagaras-sciemet-8b-l3-1113-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
hastagaras-sciemet-8b-l3-1113-v2-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
hastagaras-sciemet-8b-l3-1113-v2-mkmlizer: ║                                                                     ║
hastagaras-sciemet-8b-l3-1113-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-sciemet-8b-l3-1113-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-sciemet-8b-l3-1113-v2-mkmlizer:   warnings.warn(warning_message, FutureWarning)
hastagaras-sciemet-8b-l3-1113-v2-mkmlizer: Downloaded to shared memory in 43.406s
hastagaras-sciemet-8b-l3-1113-v2-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-sciemet-8b-l3-1113-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-sciemet-8b-l3-1113-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   4%|▍         | 12/291 [00:00<00:02, 111.60it/s]
Loading 0:   8%|▊         | 24/291 [00:00<00:02, 109.91it/s]
Loading 0:  13%|█▎        | 39/291 [00:00<00:02, 124.85it/s]
Loading 0:  18%|█▊        | 52/291 [00:00<00:01, 121.67it/s]
Loading 0:  23%|██▎       | 66/291 [00:00<00:01, 127.41it/s]
Loading 0:  27%|██▋       | 79/291 [00:00<00:01, 123.45it/s]
Loading 0:  32%|███▏      | 92/291 [00:01<00:02, 69.00it/s] 
Loading 0:  35%|███▌      | 103/291 [00:01<00:02, 75.86it/s]
Loading 0:  40%|████      | 117/291 [00:01<00:01, 89.09it/s]
Loading 0:  45%|████▍     | 130/291 [00:01<00:01, 96.29it/s]
Loading 0:  49%|████▉     | 144/291 [00:01<00:01, 106.43it/s]
Loading 0:  54%|█████▍    | 157/291 [00:01<00:01, 109.45it/s]
Loading 0:  58%|█████▊    | 170/291 [00:01<00:01, 114.26it/s]
Loading 0:  63%|██████▎   | 183/291 [00:01<00:00, 118.17it/s]
Loading 0:  67%|██████▋   | 196/291 [00:02<00:01, 70.21it/s] 
Loading 0:  72%|███████▏  | 210/291 [00:02<00:00, 81.53it/s]
Loading 0:  76%|███████▌  | 221/291 [00:02<00:00, 83.93it/s]
Loading 0:  81%|████████▏ | 237/291 [00:02<00:00, 99.15it/s]
Loading 0:  86%|████████▌ | 249/291 [00:02<00:00, 100.67it/s]
Loading 0:  91%|█████████ | 264/291 [00:02<00:00, 109.72it/s]
Loading 0:  95%|█████████▍| 276/291 [00:02<00:00, 107.75it/s]
Loading 0:  99%|█████████▉| 288/291 [00:08<00:00,  7.19it/s] 
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-sciemet-8b-l3-1113-v2-mkmlizer: quantized model in 24.183s
hastagaras-sciemet-8b-l3-1113-v2-mkmlizer: Processed model Hastagaras/Sciemet-8B-L3-MK.I-Alpha in 70.177s
hastagaras-sciemet-8b-l3-1113-v2-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-sciemet-8b-l3-1113-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-sciemet-8b-l3-1113-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-sciemet-8b-l3-1113-v2
hastagaras-sciemet-8b-l3-1113-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-sciemet-8b-l3-1113-v2/tokenizer_config.json
hastagaras-sciemet-8b-l3-1113-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-sciemet-8b-l3-1113-v2/config.json
hastagaras-sciemet-8b-l3-1113-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-sciemet-8b-l3-1113-v2/special_tokens_map.json
hastagaras-sciemet-8b-l3-1113-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-sciemet-8b-l3-1113-v2/tokenizer.json
hastagaras-sciemet-8b-l3-1113-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-sciemet-8b-l3-1113-v2/flywheel_model.0.safetensors
hastagaras-sciemet-8b-l3-1113-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-sciemet-8b-l3-1113-v2-mkmlizer:   warnings.warn(
hastagaras-sciemet-8b-l3-1113-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-sciemet-8b-l3-1113-v2-mkmlizer:   warnings.warn(
hastagaras-sciemet-8b-l3-1113-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-sciemet-8b-l3-1113-v2-mkmlizer:   return self.fget.__get__(instance, owner)()
hastagaras-sciemet-8b-l3-1113-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-sciemet-8b-l3-1113-v2-mkmlizer: Saving duration: 0.414s
hastagaras-sciemet-8b-l3-1113-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 22.850s
hastagaras-sciemet-8b-l3-1113-v2-mkmlizer: creating bucket guanaco-reward-models
hastagaras-sciemet-8b-l3-1113-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-sciemet-8b-l3-1113-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-sciemet-8b-l3-1113-v2_reward
hastagaras-sciemet-8b-l3-1113-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-sciemet-8b-l3-1113-v2_reward/config.json
hastagaras-sciemet-8b-l3-1113-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-sciemet-8b-l3-1113-v2_reward/special_tokens_map.json
hastagaras-sciemet-8b-l3-1113-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-sciemet-8b-l3-1113-v2_reward/merges.txt
hastagaras-sciemet-8b-l3-1113-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-sciemet-8b-l3-1113-v2_reward/tokenizer_config.json
hastagaras-sciemet-8b-l3-1113-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-sciemet-8b-l3-1113-v2_reward/vocab.json
hastagaras-sciemet-8b-l3-1113-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-sciemet-8b-l3-1113-v2_reward/tokenizer.json
hastagaras-sciemet-8b-l3-1113-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-sciemet-8b-l3-1113-v2_reward/reward.tensors
Job hastagaras-sciemet-8b-l3-1113-v2-mkmlizer completed after 113.71s with status: succeeded
Stopping job with name hastagaras-sciemet-8b-l3-1113-v2-mkmlizer
Pipeline stage MKMLizer completed in 117.55s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-sciemet-8b-l3-1113-v2
Waiting for inference service hastagaras-sciemet-8b-l3-1113-v2 to be ready
Inference service hastagaras-sciemet-8b-l3-1113-v2 ready after 60.36375141143799s
Pipeline stage ISVCDeployer completed in 67.93s
Running pipeline stage StressChecker
%s, retrying in %s seconds...
Received healthy response to inference request in 2.2338972091674805s
Received healthy response to inference request in 1.359095573425293s
Received healthy response to inference request in 1.3502721786499023s
Received healthy response to inference request in 1.2985966205596924s
Received healthy response to inference request in 1.3639891147613525s
5 requests
0 failed requests
5th percentile: 1.3089317321777343
10th percentile: 1.3192668437957764
20th percentile: 1.3399370670318604
30th percentile: 1.3520368576049804
40th percentile: 1.3555662155151367
50th percentile: 1.359095573425293
60th percentile: 1.3610529899597168
70th percentile: 1.3630104064941406
80th percentile: 1.5379707336425783
90th percentile: 1.8859339714050294
95th percentile: 2.0599155902862547
99th percentile: 2.1991008853912355
mean time: 1.5211701393127441
Pipeline stage StressChecker completed in 28.37s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.03s
Running M-Eval for topic stay_in_character
hastagaras-sciemet-8b-l3_1113_v2 status is now deployed due to DeploymentManager action
M-Eval Dataset for topic stay_in_character is loaded
hastagaras-sciemet-8b-l3_1113_v2 status is now rejected due to a failure to get M-Eval score. Please try again in five minutes.