submission_id: hastagaras-model-for-ada_2573_v1
developer_uid: Hastagaras
status: inactive
model_repo: Hastagaras/model-for-adapter-extraction
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.05, '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}
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: 2024-06-02T05:42:33+00:00
model_name: debug
model_eval_status: success
model_group: Hastagaras/model-for-ada
num_battles: 9934
num_wins: 5291
celo_rating: 1215.82
safety_score: 0.97
propriety_score: 0.6707317073170732
propriety_total_count: 246.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: debug
ineligible_reason: propriety_total_count < 5000
language_model: Hastagaras/model-for-adapter-extraction
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-01
win_ratio: 0.532615260720757
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-model-for-ada-2573-v1-mkmlizer
Waiting for job on hastagaras-model-for-ada-2573-v1-mkmlizer to finish
hastagaras-model-for-ada-2573-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-model-for-ada-2573-v1-mkmlizer: ║ _____ __ __ ║
hastagaras-model-for-ada-2573-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-model-for-ada-2573-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-model-for-ada-2573-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-model-for-ada-2573-v1-mkmlizer: ║ /___/ ║
hastagaras-model-for-ada-2573-v1-mkmlizer: ║ ║
hastagaras-model-for-ada-2573-v1-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-model-for-ada-2573-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-model-for-ada-2573-v1-mkmlizer: ║ https://mk1.ai ║
hastagaras-model-for-ada-2573-v1-mkmlizer: ║ ║
hastagaras-model-for-ada-2573-v1-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-model-for-ada-2573-v1-mkmlizer: ║ belonging to: ║
hastagaras-model-for-ada-2573-v1-mkmlizer: ║ ║
hastagaras-model-for-ada-2573-v1-mkmlizer: ║ Chai Research Corp. ║
hastagaras-model-for-ada-2573-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-model-for-ada-2573-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-model-for-ada-2573-v1-mkmlizer: ║ ║
hastagaras-model-for-ada-2573-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-model-for-ada-2573-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-model-for-ada-2573-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-model-for-ada-2573-v1-mkmlizer: Downloaded to shared memory in 29.795s
hastagaras-model-for-ada-2573-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-model-for-ada-2573-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-model-for-ada-2573-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 5%|▍ | 14/291 [00:00<00:02, 125.14it/s] Loading 0: 11%|█ | 31/291 [00:00<00:01, 147.46it/s] Loading 0: 17%|█▋ | 49/291 [00:00<00:01, 152.17it/s] Loading 0: 23%|██▎ | 67/291 [00:00<00:01, 153.40it/s] Loading 0: 29%|██▊ | 83/291 [00:00<00:02, 78.08it/s] Loading 0: 33%|███▎ | 95/291 [00:00<00:02, 84.50it/s] Loading 0: 39%|███▉ | 113/291 [00:01<00:01, 101.81it/s] Loading 0: 45%|████▌ | 131/291 [00:01<00:01, 116.03it/s] Loading 0: 51%|█████ | 148/291 [00:01<00:01, 128.75it/s] Loading 0: 57%|█████▋ | 165/291 [00:01<00:00, 137.19it/s] Loading 0: 62%|██████▏ | 181/291 [00:01<00:00, 137.66it/s] Loading 0: 67%|██████▋ | 196/291 [00:01<00:01, 83.29it/s] Loading 0: 72%|███████▏ | 210/291 [00:02<00:00, 87.51it/s] Loading 0: 78%|███████▊ | 228/291 [00:02<00:00, 103.62it/s] Loading 0: 85%|████████▍ | 246/291 [00:02<00:00, 117.44it/s] Loading 0: 91%|█████████ | 264/291 [00:02<00:00, 127.90it/s] Loading 0: 96%|█████████▌| 280/291 [00:02<00:00, 135.37it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-model-for-ada-2573-v1-mkmlizer: quantized model in 23.011s
hastagaras-model-for-ada-2573-v1-mkmlizer: Processed model Hastagaras/model-for-adapter-extraction in 55.460s
hastagaras-model-for-ada-2573-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-model-for-ada-2573-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-model-for-ada-2573-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-model-for-ada-2573-v1
hastagaras-model-for-ada-2573-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-model-for-ada-2573-v1/tokenizer_config.json
hastagaras-model-for-ada-2573-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-model-for-ada-2573-v1/tokenizer.json
hastagaras-model-for-ada-2573-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-model-for-ada-2573-v1/config.json
hastagaras-model-for-ada-2573-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-model-for-ada-2573-v1/special_tokens_map.json
hastagaras-model-for-ada-2573-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-model-for-ada-2573-v1/flywheel_model.0.safetensors
hastagaras-model-for-ada-2573-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-model-for-ada-2573-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-model-for-ada-2573-v1-mkmlizer: warnings.warn(
hastagaras-model-for-ada-2573-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-model-for-ada-2573-v1-mkmlizer: warnings.warn(
hastagaras-model-for-ada-2573-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-model-for-ada-2573-v1-mkmlizer: warnings.warn(
hastagaras-model-for-ada-2573-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-model-for-ada-2573-v1-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-model-for-ada-2573-v1-mkmlizer: Saving duration: 0.461s
hastagaras-model-for-ada-2573-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.433s
hastagaras-model-for-ada-2573-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-model-for-ada-2573-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-model-for-ada-2573-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-model-for-ada-2573-v1_reward
hastagaras-model-for-ada-2573-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-model-for-ada-2573-v1_reward/config.json
hastagaras-model-for-ada-2573-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-model-for-ada-2573-v1_reward/vocab.json
hastagaras-model-for-ada-2573-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-model-for-ada-2573-v1_reward/special_tokens_map.json
hastagaras-model-for-ada-2573-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-model-for-ada-2573-v1_reward/tokenizer_config.json
hastagaras-model-for-ada-2573-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-model-for-ada-2573-v1_reward/merges.txt
hastagaras-model-for-ada-2573-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-model-for-ada-2573-v1_reward/tokenizer.json
hastagaras-model-for-ada-2573-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-model-for-ada-2573-v1_reward/reward.tensors
Job hastagaras-model-for-ada-2573-v1-mkmlizer completed after 83.34s with status: succeeded
Stopping job with name hastagaras-model-for-ada-2573-v1-mkmlizer
Pipeline stage MKMLizer completed in 84.02s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-model-for-ada-2573-v1
Waiting for inference service hastagaras-model-for-ada-2573-v1 to be ready
Inference service hastagaras-model-for-ada-2573-v1 ready after 40.208197832107544s
Pipeline stage ISVCDeployer completed in 46.01s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1291661262512207s
Received healthy response to inference request in 1.3778302669525146s
Received healthy response to inference request in 1.368701457977295s
Received healthy response to inference request in 1.3369271755218506s
Received healthy response to inference request in 1.3229796886444092s
5 requests
0 failed requests
5th percentile: 1.3257691860198975
10th percentile: 1.3285586833953857
20th percentile: 1.3341376781463623
30th percentile: 1.3432820320129395
40th percentile: 1.355991744995117
50th percentile: 1.368701457977295
60th percentile: 1.3723529815673827
70th percentile: 1.3760045051574707
80th percentile: 1.528097438812256
90th percentile: 1.8286317825317384
95th percentile: 1.9788989543914794
99th percentile: 2.0991126918792724
mean time: 1.507120943069458
Pipeline stage StressChecker completed in 8.16s
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-model-for-ada_2573_v1 status is now deployed due to DeploymentManager action
hastagaras-model-for-ada_2573_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics