hastagaras-halu-8b-llama_2564

developer_uid: Hastagaras

submission_id: hastagaras-halu-8b-llama_2564_v3

model_name: HWEHWHEHW

model_group: Hastagaras/Halu-8B-Llama

status: rejected

timestamp: 2024-05-24T08:39:44+00:00

num_battles: 1240

num_wins: 710

celo_rating: 1218.79

family_friendly_score: 0.0

submission_type: basic

model_repo: Hastagaras/Halu-8B-Llama3-v0.3

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: HWEHWHEHW

ineligible_reason: model is not deployable

is_internal_developer: False

language_model: Hastagaras/Halu-8B-Llama3-v0.3

model_size: 8B

ranking_group: single

us_pacific_date: 2024-05-24

win_ratio: 0.5725806451612904

generation_params: {'temperature': 1.05, 'top_p': 0.95, 'min_p': 0.1, 'top_k': 200, '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}

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-halu-8b-llama-2564-v3-mkmlizer
Waiting for job on hastagaras-halu-8b-llama-2564-v3-mkmlizer to finish
hastagaras-halu-8b-llama-2564-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-halu-8b-llama-2564-v3-mkmlizer: ║     _____            __           __                                ║
hastagaras-halu-8b-llama-2564-v3-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
hastagaras-halu-8b-llama-2564-v3-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
hastagaras-halu-8b-llama-2564-v3-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
hastagaras-halu-8b-llama-2564-v3-mkmlizer: ║       /___/                                                         ║
hastagaras-halu-8b-llama-2564-v3-mkmlizer: ║                                                                     ║
hastagaras-halu-8b-llama-2564-v3-mkmlizer: ║  Version: 0.8.14                                                    ║
hastagaras-halu-8b-llama-2564-v3-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
hastagaras-halu-8b-llama-2564-v3-mkmlizer: ║  https://mk1.ai                                                     ║
hastagaras-halu-8b-llama-2564-v3-mkmlizer: ║                                                                     ║
hastagaras-halu-8b-llama-2564-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
hastagaras-halu-8b-llama-2564-v3-mkmlizer: ║  belonging to:                                                      ║
hastagaras-halu-8b-llama-2564-v3-mkmlizer: ║                                                                     ║
hastagaras-halu-8b-llama-2564-v3-mkmlizer: ║  Chai Research Corp.                                                ║
hastagaras-halu-8b-llama-2564-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
hastagaras-halu-8b-llama-2564-v3-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
hastagaras-halu-8b-llama-2564-v3-mkmlizer: ║                                                                     ║
hastagaras-halu-8b-llama-2564-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-halu-8b-llama-2564-v3-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-2564-v3-mkmlizer:   warnings.warn(warning_message, FutureWarning)
hastagaras-halu-8b-llama-2564-v3-mkmlizer: Downloaded to shared memory in 18.002s
hastagaras-halu-8b-llama-2564-v3-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-halu-8b-llama-2564-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-halu-8b-llama-2564-v3-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   4%|▍         | 13/291 [00:00<00:02, 126.64it/s]
Loading 0:  11%|█         | 31/291 [00:00<00:01, 148.44it/s]
Loading 0:  17%|█▋        | 49/291 [00:00<00:01, 154.78it/s]
Loading 0:  23%|██▎       | 67/291 [00:00<00:01, 157.40it/s]
Loading 0:  29%|██▊       | 83/291 [00:00<00:02, 83.09it/s] 
Loading 0:  33%|███▎      | 96/291 [00:00<00:02, 92.60it/s]
Loading 0:  39%|███▉      | 113/291 [00:01<00:01, 108.24it/s]
Loading 0:  45%|████▌     | 131/291 [00:01<00:01, 123.40it/s]
Loading 0:  51%|█████     | 148/291 [00:01<00:01, 134.87it/s]
Loading 0:  57%|█████▋    | 166/291 [00:01<00:00, 144.24it/s]
Loading 0:  64%|██████▎   | 185/291 [00:01<00:00, 155.79it/s]
Loading 0:  69%|██████▉   | 202/291 [00:01<00:00, 92.76it/s] 
Loading 0:  76%|███████▌  | 220/291 [00:01<00:00, 107.83it/s]
Loading 0:  82%|████████▏ | 238/291 [00:02<00:00, 121.08it/s]
Loading 0:  88%|████████▊ | 256/291 [00:02<00:00, 132.35it/s]
Loading 0:  94%|█████████▍| 274/291 [00:02<00:00, 141.87it/s]
Loading 0: 100%|█████████▉| 290/291 [00:07<00:00, 10.25it/s] 
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-halu-8b-llama-2564-v3-mkmlizer: quantized model in 22.801s
hastagaras-halu-8b-llama-2564-v3-mkmlizer: Processed model Hastagaras/Halu-8B-Llama3-v0.3 in 43.396s
hastagaras-halu-8b-llama-2564-v3-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-halu-8b-llama-2564-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-halu-8b-llama-2564-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-halu-8b-llama-2564-v3
hastagaras-halu-8b-llama-2564-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-2564-v3/config.json
hastagaras-halu-8b-llama-2564-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-2564-v3/tokenizer_config.json
hastagaras-halu-8b-llama-2564-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-2564-v3/tokenizer.json
hastagaras-halu-8b-llama-2564-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-2564-v3/special_tokens_map.json
hastagaras-halu-8b-llama-2564-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-halu-8b-llama-2564-v3/flywheel_model.0.safetensors
hastagaras-halu-8b-llama-2564-v3-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-halu-8b-llama-2564-v3-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-2564-v3-mkmlizer:   warnings.warn(
hastagaras-halu-8b-llama-2564-v3-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-2564-v3-mkmlizer:   warnings.warn(
hastagaras-halu-8b-llama-2564-v3-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-2564-v3-mkmlizer:   warnings.warn(
hastagaras-halu-8b-llama-2564-v3-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-2564-v3-mkmlizer:   return self.fget.__get__(instance, owner)()
hastagaras-halu-8b-llama-2564-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-halu-8b-llama-2564-v3-mkmlizer: Saving duration: 0.404s
hastagaras-halu-8b-llama-2564-v3-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.384s
hastagaras-halu-8b-llama-2564-v3-mkmlizer: creating bucket guanaco-reward-models
hastagaras-halu-8b-llama-2564-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-halu-8b-llama-2564-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-halu-8b-llama-2564-v3_reward
hastagaras-halu-8b-llama-2564-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-2564-v3_reward/special_tokens_map.json
hastagaras-halu-8b-llama-2564-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-2564-v3_reward/tokenizer_config.json
hastagaras-halu-8b-llama-2564-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-2564-v3_reward/config.json
hastagaras-halu-8b-llama-2564-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-halu-8b-llama-2564-v3_reward/merges.txt
hastagaras-halu-8b-llama-2564-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-2564-v3_reward/vocab.json
hastagaras-halu-8b-llama-2564-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-2564-v3_reward/tokenizer.json
hastagaras-halu-8b-llama-2564-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-halu-8b-llama-2564-v3_reward/reward.tensors
Job hastagaras-halu-8b-llama-2564-v3-mkmlizer completed after 74.83s with status: succeeded
Stopping job with name hastagaras-halu-8b-llama-2564-v3-mkmlizer
Pipeline stage MKMLizer completed in 79.64s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-halu-8b-llama-2564-v3
Waiting for inference service hastagaras-halu-8b-llama-2564-v3 to be ready
Inference service hastagaras-halu-8b-llama-2564-v3 ready after 50.24599266052246s
Pipeline stage ISVCDeployer completed in 57.99s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.141435384750366s
Received healthy response to inference request in 1.3750684261322021s
Received healthy response to inference request in 1.3233675956726074s
Received healthy response to inference request in 1.2836153507232666s
Received healthy response to inference request in 1.2551178932189941s
5 requests
0 failed requests
5th percentile: 1.2608173847198487
10th percentile: 1.266516876220703
20th percentile: 1.277915859222412
30th percentile: 1.2915657997131347
40th percentile: 1.307466697692871
50th percentile: 1.3233675956726074
60th percentile: 1.3440479278564452
70th percentile: 1.3647282600402832
80th percentile: 1.528341817855835
90th percentile: 1.8348886013031007
95th percentile: 1.9881619930267334
99th percentile: 2.1107807064056394
mean time: 1.4757209300994873
Pipeline stage StressChecker completed in 8.39s
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-halu-8b-llama_2564_v3 status is now deployed due to DeploymentManager action
hastagaras-halu-8b-llama_2564_v3 status is now rejected due to a failure to get M-Eval score. Please try again in five minutes.