submission_id: hastagaras-halu-8b-llama_2564_v6
developer_uid: Hastagaras
status: inactive
model_repo: Hastagaras/Halu-8B-Llama3-v0.3
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.05, 'top_p': 0.95, 'min_p': 0.1, 'top_k': 105, '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: 2024-05-24T12:47:29+00:00
model_name: terakhir
model_eval_status: success
model_group: Hastagaras/Halu-8B-Llama
num_battles: 7662
num_wins: 4164
celo_rating: 1207.47
safety_score: 0.98
propriety_score: 0.0
propriety_total_count: 0.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: terakhir
ineligible_reason: propriety_total_count < 5000
language_model: Hastagaras/Halu-8B-Llama3-v0.3
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-05-24
win_ratio: 0.543461237274863
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-halu-8b-llama-2564-v6-mkmlizer
Waiting for job on hastagaras-halu-8b-llama-2564-v6-mkmlizer to finish
hastagaras-halu-8b-llama-2564-v6-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-halu-8b-llama-2564-v6-mkmlizer: ║ _____ __ __ ║
hastagaras-halu-8b-llama-2564-v6-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-halu-8b-llama-2564-v6-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-halu-8b-llama-2564-v6-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-halu-8b-llama-2564-v6-mkmlizer: ║ /___/ ║
hastagaras-halu-8b-llama-2564-v6-mkmlizer: ║ ║
hastagaras-halu-8b-llama-2564-v6-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-halu-8b-llama-2564-v6-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-halu-8b-llama-2564-v6-mkmlizer: ║ https://mk1.ai ║
hastagaras-halu-8b-llama-2564-v6-mkmlizer: ║ ║
hastagaras-halu-8b-llama-2564-v6-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-halu-8b-llama-2564-v6-mkmlizer: ║ belonging to: ║
hastagaras-halu-8b-llama-2564-v6-mkmlizer: ║ ║
hastagaras-halu-8b-llama-2564-v6-mkmlizer: ║ Chai Research Corp. ║
hastagaras-halu-8b-llama-2564-v6-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-halu-8b-llama-2564-v6-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-halu-8b-llama-2564-v6-mkmlizer: ║ ║
hastagaras-halu-8b-llama-2564-v6-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-halu-8b-llama-2564-v6-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-v6-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-halu-8b-llama-2564-v6-mkmlizer: Downloaded to shared memory in 18.375s
hastagaras-halu-8b-llama-2564-v6-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-halu-8b-llama-2564-v6-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-halu-8b-llama-2564-v6-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 2%|▏ | 5/291 [00:00<00:05, 49.02it/s] Loading 0: 5%|▍ | 14/291 [00:00<00:03, 70.61it/s] Loading 0: 11%|█ | 31/291 [00:00<00:02, 106.21it/s] Loading 0: 16%|█▋ | 48/291 [00:00<00:01, 122.53it/s] Loading 0: 21%|██ | 61/291 [00:00<00:01, 122.89it/s] Loading 0: 26%|██▌ | 76/291 [00:00<00:01, 125.77it/s] Loading 0: 31%|███ | 89/291 [00:01<00:03, 60.06it/s] Loading 0: 34%|███▍ | 99/291 [00:01<00:02, 66.06it/s] Loading 0: 38%|███▊ | 112/291 [00:01<00:02, 75.94it/s] Loading 0: 44%|████▍ | 129/291 [00:01<00:01, 93.21it/s] Loading 0: 48%|████▊ | 141/291 [00:01<00:01, 98.76it/s] Loading 0: 54%|█████▍ | 157/291 [00:01<00:01, 110.22it/s] Loading 0: 59%|█████▉ | 173/291 [00:01<00:00, 118.54it/s] Loading 0: 64%|██████▍ | 187/291 [00:02<00:01, 68.34it/s] Loading 0: 68%|██████▊ | 197/291 [00:02<00:01, 66.41it/s] Loading 0: 71%|███████ | 207/291 [00:02<00:01, 71.46it/s] Loading 0: 75%|███████▍ | 217/291 [00:02<00:00, 76.92it/s] Loading 0: 78%|███████▊ | 228/291 [00:02<00:00, 79.68it/s] Loading 0: 82%|████████▏ | 238/291 [00:02<00:00, 79.46it/s] Loading 0: 86%|████████▌ | 250/291 [00:02<00:00, 88.85it/s] Loading 0: 91%|█████████ | 264/291 [00:03<00:00, 96.48it/s] Loading 0: 95%|█████████▍| 275/291 [00:03<00:00, 97.73it/s] Loading 0: 99%|█████████▊| 287/291 [00:08<00:00, 6.49it/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-v6-mkmlizer: quantized model in 25.434s
hastagaras-halu-8b-llama-2564-v6-mkmlizer: Processed model Hastagaras/Halu-8B-Llama3-v0.3 in 44.968s
hastagaras-halu-8b-llama-2564-v6-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-halu-8b-llama-2564-v6-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-halu-8b-llama-2564-v6-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-halu-8b-llama-2564-v6
hastagaras-halu-8b-llama-2564-v6-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-2564-v6/config.json
hastagaras-halu-8b-llama-2564-v6-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-2564-v6/special_tokens_map.json
hastagaras-halu-8b-llama-2564-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-2564-v6/tokenizer_config.json
hastagaras-halu-8b-llama-2564-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-2564-v6/tokenizer.json
hastagaras-halu-8b-llama-2564-v6-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-halu-8b-llama-2564-v6/flywheel_model.0.safetensors
hastagaras-halu-8b-llama-2564-v6-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-halu-8b-llama-2564-v6-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-v6-mkmlizer: warnings.warn(
hastagaras-halu-8b-llama-2564-v6-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-v6-mkmlizer: warnings.warn(
hastagaras-halu-8b-llama-2564-v6-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-v6-mkmlizer: warnings.warn(
hastagaras-halu-8b-llama-2564-v6-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-v6-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-halu-8b-llama-2564-v6-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-halu-8b-llama-2564-v6-mkmlizer: creating bucket guanaco-reward-models
hastagaras-halu-8b-llama-2564-v6-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-halu-8b-llama-2564-v6-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-halu-8b-llama-2564-v6_reward
hastagaras-halu-8b-llama-2564-v6-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-2564-v6_reward/tokenizer_config.json
hastagaras-halu-8b-llama-2564-v6-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-2564-v6_reward/special_tokens_map.json
hastagaras-halu-8b-llama-2564-v6-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-2564-v6_reward/config.json
hastagaras-halu-8b-llama-2564-v6-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-2564-v6_reward/vocab.json
hastagaras-halu-8b-llama-2564-v6-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-halu-8b-llama-2564-v6_reward/merges.txt
hastagaras-halu-8b-llama-2564-v6-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-2564-v6_reward/tokenizer.json
hastagaras-halu-8b-llama-2564-v6-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-halu-8b-llama-2564-v6_reward/reward.tensors
Job hastagaras-halu-8b-llama-2564-v6-mkmlizer completed after 72.9s with status: succeeded
Stopping job with name hastagaras-halu-8b-llama-2564-v6-mkmlizer
Pipeline stage MKMLizer completed in 77.07s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-halu-8b-llama-2564-v6
Waiting for inference service hastagaras-halu-8b-llama-2564-v6 to be ready
Inference service hastagaras-halu-8b-llama-2564-v6 ready after 50.31980061531067s
Pipeline stage ISVCDeployer completed in 57.77s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1641452312469482s
Received healthy response to inference request in 1.3770966529846191s
Received healthy response to inference request in 1.3242535591125488s
Received healthy response to inference request in 1.3116869926452637s
Received healthy response to inference request in 1.2438979148864746s
5 requests
0 failed requests
5th percentile: 1.2574557304382323
10th percentile: 1.2710135459899903
20th percentile: 1.298129177093506
30th percentile: 1.3142003059387206
40th percentile: 1.3192269325256347
50th percentile: 1.3242535591125488
60th percentile: 1.345390796661377
70th percentile: 1.366528034210205
80th percentile: 1.534506368637085
90th percentile: 1.8493257999420167
95th percentile: 2.006735515594482
99th percentile: 2.132663288116455
mean time: 1.484216070175171
Pipeline stage StressChecker completed in 8.01s
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 0.05s
M-Eval Dataset for topic stay_in_character is loaded
hastagaras-halu-8b-llama_2564_v6 status is now deployed due to DeploymentManager action
hastagaras-halu-8b-llama_2564_v6 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics