submission_id: pawankrd-cosmosrp_v48
developer_uid: PawanOsman
status: inactive
model_repo: PawanKrd/CosmosRP
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.6, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['<', '>'], '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: 2024-07-09T05:57:32+00:00
model_name: pawankrd-cosmosrp_v48
model_group: PawanKrd/CosmosRP
num_battles: 31361
num_wins: 15000
celo_rating: 1182.67
propriety_score: 0.7611262488646685
propriety_total_count: 5505.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: pawankrd-cosmosrp_v48
ineligible_reason: None
language_model: PawanKrd/CosmosRP
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-07-08
win_ratio: 0.4783010745830809
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name pawankrd-cosmosrp-v48-mkmlizer
Waiting for job on pawankrd-cosmosrp-v48-mkmlizer to finish
pawankrd-cosmosrp-v48-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
pawankrd-cosmosrp-v48-mkmlizer: ║ _____ __ __ ║
pawankrd-cosmosrp-v48-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
pawankrd-cosmosrp-v48-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
pawankrd-cosmosrp-v48-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
pawankrd-cosmosrp-v48-mkmlizer: ║ /___/ ║
pawankrd-cosmosrp-v48-mkmlizer: ║ ║
pawankrd-cosmosrp-v48-mkmlizer: ║ Version: 0.8.14 ║
pawankrd-cosmosrp-v48-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
pawankrd-cosmosrp-v48-mkmlizer: ║ https://mk1.ai ║
pawankrd-cosmosrp-v48-mkmlizer: ║ ║
pawankrd-cosmosrp-v48-mkmlizer: ║ The license key for the current software has been verified as ║
pawankrd-cosmosrp-v48-mkmlizer: ║ belonging to: ║
pawankrd-cosmosrp-v48-mkmlizer: ║ ║
pawankrd-cosmosrp-v48-mkmlizer: ║ Chai Research Corp. ║
pawankrd-cosmosrp-v48-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
pawankrd-cosmosrp-v48-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
pawankrd-cosmosrp-v48-mkmlizer: ║ ║
pawankrd-cosmosrp-v48-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
pawankrd-cosmosrp-v48-mkmlizer: Downloaded to shared memory in 25.865s
pawankrd-cosmosrp-v48-mkmlizer: quantizing model to /dev/shm/model_cache
pawankrd-cosmosrp-v48-mkmlizer: Saving flywheel model at /dev/shm/model_cache
pawankrd-cosmosrp-v48-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:02, 110.53it/s] Loading 0: 9%|▉ | 27/291 [00:00<00:02, 122.77it/s] Loading 0: 14%|█▎ | 40/291 [00:00<00:02, 119.48it/s] Loading 0: 18%|█▊ | 53/291 [00:00<00:01, 121.37it/s] Loading 0: 23%|██▎ | 67/291 [00:00<00:01, 120.28it/s] Loading 0: 28%|██▊ | 81/291 [00:00<00:01, 124.53it/s] Loading 0: 32%|███▏ | 94/291 [00:01<00:03, 53.97it/s] Loading 0: 37%|███▋ | 107/291 [00:01<00:02, 65.39it/s] Loading 0: 41%|████ | 120/291 [00:01<00:02, 77.11it/s] Loading 0: 45%|████▌ | 132/291 [00:01<00:01, 83.81it/s] Loading 0: 51%|█████ | 147/291 [00:01<00:01, 96.44it/s] Loading 0: 55%|█████▍ | 159/291 [00:01<00:01, 98.80it/s] Loading 0: 59%|█████▉ | 173/291 [00:01<00:01, 107.36it/s] Loading 0: 64%|██████▍ | 187/291 [00:02<00:01, 58.73it/s] Loading 0: 68%|██████▊ | 197/291 [00:02<00:01, 64.68it/s] Loading 0: 73%|███████▎ | 211/291 [00:02<00:01, 75.95it/s] Loading 0: 77%|███████▋ | 225/291 [00:02<00:00, 88.15it/s] Loading 0: 82%|████████▏ | 238/291 [00:02<00:00, 95.04it/s] Loading 0: 87%|████████▋ | 252/291 [00:02<00:00, 104.50it/s] Loading 0: 91%|█████████ | 264/291 [00:02<00:00, 108.32it/s] Loading 0: 95%|█████████▍| 276/291 [00:03<00:00, 108.23it/s] Loading 0: 99%|█████████▉| 288/291 [00:09<00:00, 5.82it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
pawankrd-cosmosrp-v48-mkmlizer: quantized model in 29.541s
pawankrd-cosmosrp-v48-mkmlizer: Processed model PawanKrd/CosmosRP in 55.406s
pawankrd-cosmosrp-v48-mkmlizer: creating bucket guanaco-mkml-models
pawankrd-cosmosrp-v48-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
pawankrd-cosmosrp-v48-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/pawankrd-cosmosrp-v48
pawankrd-cosmosrp-v48-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v48/config.json
pawankrd-cosmosrp-v48-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v48/tokenizer_config.json
pawankrd-cosmosrp-v48-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v48/special_tokens_map.json
pawankrd-cosmosrp-v48-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v48/tokenizer.json
pawankrd-cosmosrp-v48-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/pawankrd-cosmosrp-v48/flywheel_model.0.safetensors
pawankrd-cosmosrp-v48-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
pawankrd-cosmosrp-v48-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:919: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
pawankrd-cosmosrp-v48-mkmlizer: warnings.warn(
pawankrd-cosmosrp-v48-mkmlizer: /opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py:1132: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`.
pawankrd-cosmosrp-v48-mkmlizer: warnings.warn(
pawankrd-cosmosrp-v48-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:769: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
pawankrd-cosmosrp-v48-mkmlizer: warnings.warn(
pawankrd-cosmosrp-v48-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.
pawankrd-cosmosrp-v48-mkmlizer: warnings.warn(
pawankrd-cosmosrp-v48-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()
pawankrd-cosmosrp-v48-mkmlizer: return self.fget.__get__(instance, owner)()
pawankrd-cosmosrp-v48-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
pawankrd-cosmosrp-v48-mkmlizer: Saving duration: 0.527s
pawankrd-cosmosrp-v48-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 5.448s
pawankrd-cosmosrp-v48-mkmlizer: creating bucket guanaco-reward-models
pawankrd-cosmosrp-v48-mkmlizer: Bucket 's3://guanaco-reward-models/' created
pawankrd-cosmosrp-v48-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/pawankrd-cosmosrp-v48_reward
pawankrd-cosmosrp-v48-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/pawankrd-cosmosrp-v48_reward/config.json
pawankrd-cosmosrp-v48-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/pawankrd-cosmosrp-v48_reward/tokenizer_config.json
pawankrd-cosmosrp-v48-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/pawankrd-cosmosrp-v48_reward/merges.txt
pawankrd-cosmosrp-v48-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/pawankrd-cosmosrp-v48_reward/special_tokens_map.json
pawankrd-cosmosrp-v48-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/pawankrd-cosmosrp-v48_reward/vocab.json
pawankrd-cosmosrp-v48-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/pawankrd-cosmosrp-v48_reward/tokenizer.json
pawankrd-cosmosrp-v48-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/pawankrd-cosmosrp-v48_reward/reward.tensors
Job pawankrd-cosmosrp-v48-mkmlizer completed after 93.91s with status: succeeded
Stopping job with name pawankrd-cosmosrp-v48-mkmlizer
Pipeline stage MKMLizer completed in 95.08s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service pawankrd-cosmosrp-v48
Waiting for inference service pawankrd-cosmosrp-v48 to be ready
Inference service pawankrd-cosmosrp-v48 ready after 40.16977047920227s
Pipeline stage ISVCDeployer completed in 47.21s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.115466356277466s
Received healthy response to inference request in 1.3591575622558594s
Received healthy response to inference request in 1.3458356857299805s
Received healthy response to inference request in 1.3193516731262207s
Received healthy response to inference request in 1.252425193786621s
5 requests
0 failed requests
5th percentile: 1.265810489654541
10th percentile: 1.279195785522461
20th percentile: 1.3059663772583008
30th percentile: 1.3246484756469727
40th percentile: 1.3352420806884766
50th percentile: 1.3458356857299805
60th percentile: 1.3511644363403321
70th percentile: 1.3564931869506835
80th percentile: 1.5104193210601808
90th percentile: 1.8129428386688233
95th percentile: 1.9642045974731444
99th percentile: 2.0852140045166014
mean time: 1.4784472942352296
Pipeline stage StressChecker completed in 8.11s
pawankrd-cosmosrp_v48 status is now deployed due to DeploymentManager action
pawankrd-cosmosrp_v48 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics