submission_id: hastagaras-halu-8b-llama_4167_v1
developer_uid: Hastagaras
best_of: 16
display_name: test
family_friendly_score: 0.0
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}
generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 0.08, '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}
ineligible_reason: model is not deployable
is_internal_developer: False
language_model: Hastagaras/Halu-8B-Llama3-CR-v0.45
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_eval_status: error
model_group: Hastagaras/Halu-8B-Llama
model_name: test
model_num_parameters: 8030261248.0
model_repo: Hastagaras/Halu-8B-Llama3-CR-v0.45
model_size: 8B
num_battles: 298
num_wins: 158
ranking_group: single
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'}
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
status: rejected
submission_type: basic
timestamp: 2024-06-03T08:19:13+00:00
us_pacific_date: 2024-06-03
win_ratio: 0.5302013422818792
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-halu-8b-llama-4167-v1-mkmlizer
Waiting for job on hastagaras-halu-8b-llama-4167-v1-mkmlizer to finish
hastagaras-halu-8b-llama-4167-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-halu-8b-llama-4167-v1-mkmlizer: ║     _____            __           __                                ║
hastagaras-halu-8b-llama-4167-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
hastagaras-halu-8b-llama-4167-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
hastagaras-halu-8b-llama-4167-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
hastagaras-halu-8b-llama-4167-v1-mkmlizer: ║       /___/                                                         ║
hastagaras-halu-8b-llama-4167-v1-mkmlizer: ║                                                                     ║
hastagaras-halu-8b-llama-4167-v1-mkmlizer: ║  Version: 0.8.14                                                    ║
hastagaras-halu-8b-llama-4167-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
hastagaras-halu-8b-llama-4167-v1-mkmlizer: ║  https://mk1.ai                                                     ║
hastagaras-halu-8b-llama-4167-v1-mkmlizer: ║                                                                     ║
hastagaras-halu-8b-llama-4167-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
hastagaras-halu-8b-llama-4167-v1-mkmlizer: ║  belonging to:                                                      ║
hastagaras-halu-8b-llama-4167-v1-mkmlizer: ║                                                                     ║
hastagaras-halu-8b-llama-4167-v1-mkmlizer: ║  Chai Research Corp.                                                ║
hastagaras-halu-8b-llama-4167-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
hastagaras-halu-8b-llama-4167-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
hastagaras-halu-8b-llama-4167-v1-mkmlizer: ║                                                                     ║
hastagaras-halu-8b-llama-4167-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-halu-8b-llama-4167-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-halu-8b-llama-4167-v1-mkmlizer:   warnings.warn(warning_message, FutureWarning)
hastagaras-halu-8b-llama-4167-v1-mkmlizer: Downloaded to shared memory in 30.790s
hastagaras-halu-8b-llama-4167-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-halu-8b-llama-4167-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-halu-8b-llama-4167-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   5%|▍         | 14/291 [00:00<00:02, 124.87it/s]
Loading 0:  11%|█         | 32/291 [00:00<00:01, 149.53it/s]
Loading 0:  17%|█▋        | 50/291 [00:00<00:01, 159.23it/s]
Loading 0:  23%|██▎       | 68/291 [00:00<00:01, 164.78it/s]
Loading 0:  29%|██▉       | 85/291 [00:00<00:02, 90.56it/s] 
Loading 0:  35%|███▌      | 103/291 [00:00<00:01, 107.98it/s]
Loading 0:  42%|████▏     | 121/291 [00:00<00:01, 123.21it/s]
Loading 0:  48%|████▊     | 139/291 [00:01<00:01, 135.20it/s]
Loading 0:  54%|█████▍    | 157/291 [00:01<00:00, 145.15it/s]
Loading 0:  61%|██████    | 177/291 [00:01<00:00, 159.60it/s]
Loading 0:  67%|██████▋   | 195/291 [00:01<00:00, 97.12it/s] 
Loading 0:  73%|███████▎  | 212/291 [00:01<00:00, 109.17it/s]
Loading 0:  79%|███████▉  | 230/291 [00:01<00:00, 120.63it/s]
Loading 0:  85%|████████▌ | 248/291 [00:01<00:00, 131.03it/s]
Loading 0:  91%|█████████▏| 266/291 [00:02<00:00, 141.47it/s]
Loading 0:  98%|█████████▊| 286/291 [00:02<00:00, 156.11it/s]
                                                             
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-halu-8b-llama-4167-v1-mkmlizer: quantized model in 22.734s
hastagaras-halu-8b-llama-4167-v1-mkmlizer: Processed model Hastagaras/Halu-8B-Llama3-CR-v0.45 in 55.970s
hastagaras-halu-8b-llama-4167-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-halu-8b-llama-4167-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-halu-8b-llama-4167-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-halu-8b-llama-4167-v1
hastagaras-halu-8b-llama-4167-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-4167-v1/config.json
hastagaras-halu-8b-llama-4167-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-4167-v1/special_tokens_map.json
hastagaras-halu-8b-llama-4167-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-4167-v1/tokenizer_config.json
hastagaras-halu-8b-llama-4167-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-4167-v1/tokenizer.json
hastagaras-halu-8b-llama-4167-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-halu-8b-llama-4167-v1/flywheel_model.0.safetensors
hastagaras-halu-8b-llama-4167-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-halu-8b-llama-4167-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-halu-8b-llama-4167-v1-mkmlizer:   warnings.warn(
hastagaras-halu-8b-llama-4167-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-halu-8b-llama-4167-v1-mkmlizer:   warnings.warn(
hastagaras-halu-8b-llama-4167-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-halu-8b-llama-4167-v1-mkmlizer:   warnings.warn(
hastagaras-halu-8b-llama-4167-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-halu-8b-llama-4167-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
hastagaras-halu-8b-llama-4167-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-halu-8b-llama-4167-v1-mkmlizer: Saving duration: 0.378s
hastagaras-halu-8b-llama-4167-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.081s
hastagaras-halu-8b-llama-4167-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-halu-8b-llama-4167-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-halu-8b-llama-4167-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-halu-8b-llama-4167-v1_reward
hastagaras-halu-8b-llama-4167-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-4167-v1_reward/config.json
hastagaras-halu-8b-llama-4167-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-4167-v1_reward/tokenizer_config.json
hastagaras-halu-8b-llama-4167-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-4167-v1_reward/special_tokens_map.json
hastagaras-halu-8b-llama-4167-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-halu-8b-llama-4167-v1_reward/merges.txt
hastagaras-halu-8b-llama-4167-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-4167-v1_reward/vocab.json
hastagaras-halu-8b-llama-4167-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-4167-v1_reward/tokenizer.json
hastagaras-halu-8b-llama-4167-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-halu-8b-llama-4167-v1_reward/reward.tensors
Job hastagaras-halu-8b-llama-4167-v1-mkmlizer completed after 83.07s with status: succeeded
Stopping job with name hastagaras-halu-8b-llama-4167-v1-mkmlizer
Pipeline stage MKMLizer completed in 87.06s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-halu-8b-llama-4167-v1
Waiting for inference service hastagaras-halu-8b-llama-4167-v1 to be ready
Inference service hastagaras-halu-8b-llama-4167-v1 ready after 40.20963644981384s
Pipeline stage ISVCDeployer completed in 47.79s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.103869676589966s
Received healthy response to inference request in 1.3711903095245361s
Received healthy response to inference request in 1.3056280612945557s
%s, retrying in %s seconds...
Received healthy response to inference request in 1.2422032356262207s
Received healthy response to inference request in 1.3605952262878418s
Received healthy response to inference request in 1.3476340770721436s
Received healthy response to inference request in 1.3118414878845215s
Received healthy response to inference request in 1.2497012615203857s
5 requests
0 failed requests
5th percentile: 1.2437028408050537
10th percentile: 1.2452024459838866
20th percentile: 1.2482016563415528
30th percentile: 1.262129306793213
40th percentile: 1.2869853973388672
50th percentile: 1.3118414878845215
60th percentile: 1.3261585235595703
70th percentile: 1.3404755592346191
80th percentile: 1.3502263069152831
90th percentile: 1.3554107666015625
95th percentile: 1.3580029964447022
99th percentile: 1.360076780319214
mean time: 1.3023950576782226
Pipeline stage StressChecker completed in 17.10s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.03s
hastagaras-halu-8b-llama_4167_v1 status is now deployed due to DeploymentManager action
Running M-Eval for topic stay_in_character
M-Eval Dataset for topic stay_in_character is loaded
hastagaras-halu-8b-llama_4167_v1 status is now rejected due to a failure to get M-Eval score. Please try again in five minutes.