submission_id: hastagaras-sychomet-8b-l3-rp_v2
developer_uid: Hastagaras
status: inactive
model_repo: Hastagaras/Sychomet-8B-L3-RP
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 0.1, 'top_k': 45, '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': "<|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}
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: 2024-06-18T01:34:26+00:00
model_name: sm
model_group: Hastagaras/Sychomet-8B-L
num_battles: 14404
num_wins: 8059
celo_rating: 1217.12
propriety_score: 0.6797937849062008
propriety_total_count: 6983.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: sm
ineligible_reason: None
language_model: Hastagaras/Sychomet-8B-L3-RP
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-17
win_ratio: 0.5594973618439323
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-sychomet-8b-l3-rp-v2-mkmlizer
Waiting for job on hastagaras-sychomet-8b-l3-rp-v2-mkmlizer to finish
hastagaras-sychomet-8b-l3-rp-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-sychomet-8b-l3-rp-v2-mkmlizer: ║ _____ __ __ ║
hastagaras-sychomet-8b-l3-rp-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-sychomet-8b-l3-rp-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-sychomet-8b-l3-rp-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-sychomet-8b-l3-rp-v2-mkmlizer: ║ /___/ ║
hastagaras-sychomet-8b-l3-rp-v2-mkmlizer: ║ ║
hastagaras-sychomet-8b-l3-rp-v2-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-sychomet-8b-l3-rp-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-sychomet-8b-l3-rp-v2-mkmlizer: ║ https://mk1.ai ║
hastagaras-sychomet-8b-l3-rp-v2-mkmlizer: ║ ║
hastagaras-sychomet-8b-l3-rp-v2-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-sychomet-8b-l3-rp-v2-mkmlizer: ║ belonging to: ║
hastagaras-sychomet-8b-l3-rp-v2-mkmlizer: ║ ║
hastagaras-sychomet-8b-l3-rp-v2-mkmlizer: ║ Chai Research Corp. ║
hastagaras-sychomet-8b-l3-rp-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-sychomet-8b-l3-rp-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-sychomet-8b-l3-rp-v2-mkmlizer: ║ ║
hastagaras-sychomet-8b-l3-rp-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-sychomet-8b-l3-rp-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-sychomet-8b-l3-rp-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-sychomet-8b-l3-rp-v2-mkmlizer: Downloaded to shared memory in 33.749s
hastagaras-sychomet-8b-l3-rp-v2-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-sychomet-8b-l3-rp-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-sychomet-8b-l3-rp-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:02, 125.69it/s] Loading 0: 11%|█ | 31/291 [00:00<00:01, 147.08it/s] Loading 0: 16%|█▋ | 48/291 [00:00<00:01, 156.66it/s] Loading 0: 23%|██▎ | 66/291 [00:00<00:01, 158.58it/s] Loading 0: 29%|██▊ | 83/291 [00:00<00:02, 80.18it/s] Loading 0: 33%|███▎ | 95/291 [00:00<00:02, 84.35it/s] Loading 0: 38%|███▊ | 112/291 [00:01<00:01, 101.98it/s] Loading 0: 45%|████▍ | 130/291 [00:01<00:01, 117.06it/s] Loading 0: 51%|█████ | 148/291 [00:01<00:01, 128.36it/s] Loading 0: 57%|█████▋ | 166/291 [00:01<00:00, 137.25it/s] Loading 0: 63%|██████▎ | 184/291 [00:01<00:00, 147.24it/s] Loading 0: 69%|██████▊ | 200/291 [00:01<00:01, 88.73it/s] Loading 0: 74%|███████▎ | 214/291 [00:01<00:00, 98.02it/s] Loading 0: 79%|███████▉ | 230/291 [00:02<00:00, 109.16it/s] Loading 0: 85%|████████▍ | 247/291 [00:02<00:00, 117.21it/s] Loading 0: 91%|█████████ | 265/291 [00:02<00:00, 128.61it/s] Loading 0: 97%|█████████▋| 282/291 [00:02<00:00, 126.97it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-sychomet-8b-l3-rp-v2-mkmlizer: quantized model in 31.135s
hastagaras-sychomet-8b-l3-rp-v2-mkmlizer: Processed model Hastagaras/Sychomet-8B-L3-RP in 67.474s
hastagaras-sychomet-8b-l3-rp-v2-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-sychomet-8b-l3-rp-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-sychomet-8b-l3-rp-v2/flywheel_model.0.safetensors
hastagaras-sychomet-8b-l3-rp-v2-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-sychomet-8b-l3-rp-v2-mkmlizer: warnings.warn(
hastagaras-sychomet-8b-l3-rp-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-sychomet-8b-l3-rp-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-sychomet-8b-l3-rp-v2-mkmlizer: warnings.warn(
hastagaras-sychomet-8b-l3-rp-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-sychomet-8b-l3-rp-v2-mkmlizer: warnings.warn(
hastagaras-sychomet-8b-l3-rp-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-sychomet-8b-l3-rp-v2-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-sychomet-8b-l3-rp-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-sychomet-8b-l3-rp-v2-mkmlizer: Saving duration: 0.420s
hastagaras-sychomet-8b-l3-rp-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.183s
hastagaras-sychomet-8b-l3-rp-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-sychomet-8b-l3-rp-v2_reward/reward.tensors
Job hastagaras-sychomet-8b-l3-rp-v2-mkmlizer completed after 93.01s with status: succeeded
Stopping job with name hastagaras-sychomet-8b-l3-rp-v2-mkmlizer
Pipeline stage MKMLizer completed in 97.00s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-sychomet-8b-l3-rp-v2
Waiting for inference service hastagaras-sychomet-8b-l3-rp-v2 to be ready
Inference service hastagaras-sychomet-8b-l3-rp-v2 ready after 30.18953251838684s
Pipeline stage ISVCDeployer completed in 37.72s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0762031078338623s
Received healthy response to inference request in 1.343613862991333s
Received healthy response to inference request in 1.313413143157959s
Retrying (%r) after connection broken by '%r': %s
Received healthy response to inference request in 1.2739202976226807s
Received healthy response to inference request in 1.3356733322143555s
5 requests
0 failed requests
5th percentile: 1.2818188667297363
10th percentile: 1.289717435836792
20th percentile: 1.3055145740509033
30th percentile: 1.3178651809692383
40th percentile: 1.3267692565917968
50th percentile: 1.3356733322143555
60th percentile: 1.3388495445251465
70th percentile: 1.3420257568359375
80th percentile: 1.490131711959839
90th percentile: 1.7831674098968506
95th percentile: 1.9296852588653564
99th percentile: 2.046899538040161
mean time: 1.468564748764038
Pipeline stage StressChecker completed in 8.03s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.03s
hastagaras-sychomet-8b-l3-rp_v2 status is now deployed due to DeploymentManager action
hastagaras-sychomet-8b-l3-rp_v2 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics