submission_id: pawankrd-cosmosrp_v20
developer_uid: PawanOsman
status: inactive
model_repo: PawanKrd/CosmosRP
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.2, 'top_p': 0.95, 'min_p': 0.08, 'top_k': 40, '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: 2024-06-20T07:46:15+00:00
model_name: pawankrd-cosmosrp_v20
model_group: PawanKrd/CosmosRP
num_battles: 33128
num_wins: 18463
celo_rating: 1224.46
propriety_score: 0.6911462349010538
propriety_total_count: 15564.0
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_v20
ineligible_reason: None
language_model: PawanKrd/CosmosRP
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-20
win_ratio: 0.5573231103598165
Resubmit model
Running pipeline stage MKMLizer
Starting job with name pawankrd-cosmosrp-v20-mkmlizer
Waiting for job on pawankrd-cosmosrp-v20-mkmlizer to finish
pawankrd-cosmosrp-v20-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
pawankrd-cosmosrp-v20-mkmlizer: ║ _____ __ __ ║
pawankrd-cosmosrp-v20-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
pawankrd-cosmosrp-v20-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
pawankrd-cosmosrp-v20-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
pawankrd-cosmosrp-v20-mkmlizer: ║ /___/ ║
pawankrd-cosmosrp-v20-mkmlizer: ║ ║
pawankrd-cosmosrp-v20-mkmlizer: ║ Version: 0.8.14 ║
pawankrd-cosmosrp-v20-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
pawankrd-cosmosrp-v20-mkmlizer: ║ https://mk1.ai ║
pawankrd-cosmosrp-v20-mkmlizer: ║ ║
pawankrd-cosmosrp-v20-mkmlizer: ║ The license key for the current software has been verified as ║
pawankrd-cosmosrp-v20-mkmlizer: ║ belonging to: ║
pawankrd-cosmosrp-v20-mkmlizer: ║ ║
pawankrd-cosmosrp-v20-mkmlizer: ║ Chai Research Corp. ║
pawankrd-cosmosrp-v20-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
pawankrd-cosmosrp-v20-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
pawankrd-cosmosrp-v20-mkmlizer: ║ ║
pawankrd-cosmosrp-v20-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
pawankrd-cosmosrp-v20-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.
pawankrd-cosmosrp-v20-mkmlizer: warnings.warn(warning_message, FutureWarning)
pawankrd-cosmosrp-v20-mkmlizer: Downloaded to shared memory in 28.283s
pawankrd-cosmosrp-v20-mkmlizer: quantizing model to /dev/shm/model_cache
pawankrd-cosmosrp-v20-mkmlizer: Saving flywheel model at /dev/shm/model_cache
pawankrd-cosmosrp-v20-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<10:52, 2.26s/it] Loading 0: 5%|▌ | 15/291 [00:04<01:02, 4.41it/s] Loading 0: 11%|█▏ | 33/291 [00:04<00:21, 11.73it/s] Loading 0: 17%|█▋ | 50/291 [00:04<00:11, 20.65it/s] Loading 0: 22%|██▏ | 64/291 [00:05<00:09, 24.82it/s] Loading 0: 27%|██▋ | 78/291 [00:05<00:06, 34.12it/s] Loading 0: 33%|███▎ | 96/291 [00:05<00:03, 48.92it/s] Loading 0: 39%|███▉ | 114/291 [00:05<00:02, 64.95it/s] Loading 0: 45%|████▌ | 132/291 [00:05<00:01, 81.21it/s] Loading 0: 52%|█████▏ | 150/291 [00:05<00:01, 97.45it/s] Loading 0: 57%|█████▋ | 166/291 [00:06<00:01, 73.58it/s] Loading 0: 63%|██████▎ | 184/291 [00:06<00:01, 89.29it/s] Loading 0: 69%|██████▉ | 202/291 [00:06<00:00, 103.49it/s] Loading 0: 76%|███████▌ | 220/291 [00:06<00:00, 117.24it/s] Loading 0: 82%|████████▏ | 238/291 [00:06<00:00, 130.38it/s] Loading 0: 88%|████████▊ | 256/291 [00:06<00:00, 140.82it/s] Loading 0: 94%|█████████▍| 273/291 [00:06<00:00, 93.35it/s] Loading 0: 99%|█████████▊| 287/291 [00:07<00:00, 101.80it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
pawankrd-cosmosrp-v20-mkmlizer: quantized model in 23.164s
pawankrd-cosmosrp-v20-mkmlizer: Processed model PawanKrd/CosmosRP in 53.967s
pawankrd-cosmosrp-v20-mkmlizer: creating bucket guanaco-mkml-models
pawankrd-cosmosrp-v20-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
pawankrd-cosmosrp-v20-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/pawankrd-cosmosrp-v20
pawankrd-cosmosrp-v20-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v20/config.json
pawankrd-cosmosrp-v20-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v20/tokenizer_config.json
pawankrd-cosmosrp-v20-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v20/tokenizer.json
pawankrd-cosmosrp-v20-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v20/special_tokens_map.json
pawankrd-cosmosrp-v20-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/pawankrd-cosmosrp-v20/flywheel_model.0.safetensors
pawankrd-cosmosrp-v20-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
pawankrd-cosmosrp-v20-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.
pawankrd-cosmosrp-v20-mkmlizer: warnings.warn(
pawankrd-cosmosrp-v20-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.
pawankrd-cosmosrp-v20-mkmlizer: warnings.warn(
pawankrd-cosmosrp-v20-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-v20-mkmlizer: warnings.warn(
pawankrd-cosmosrp-v20-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-v20-mkmlizer: return self.fget.__get__(instance, owner)()
pawankrd-cosmosrp-v20-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
pawankrd-cosmosrp-v20-mkmlizer: Saving duration: 0.404s
pawankrd-cosmosrp-v20-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.615s
pawankrd-cosmosrp-v20-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/pawankrd-cosmosrp-v20_reward/reward.tensors
Job pawankrd-cosmosrp-v20-mkmlizer completed after 82.73s with status: succeeded
Stopping job with name pawankrd-cosmosrp-v20-mkmlizer
Pipeline stage MKMLizer completed in 85.36s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service pawankrd-cosmosrp-v20
Waiting for inference service pawankrd-cosmosrp-v20 to be ready
Inference service pawankrd-cosmosrp-v20 ready after 130.62897419929504s
Pipeline stage ISVCDeployer completed in 137.29s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1759026050567627s
Received healthy response to inference request in 1.3422815799713135s
Received healthy response to inference request in 1.3258936405181885s
Received healthy response to inference request in 1.302626132965088s
Received healthy response to inference request in 1.2661173343658447s
5 requests
0 failed requests
5th percentile: 1.2734190940856933
10th percentile: 1.280720853805542
20th percentile: 1.2953243732452393
30th percentile: 1.307279634475708
40th percentile: 1.3165866374969482
50th percentile: 1.3258936405181885
60th percentile: 1.3324488162994386
70th percentile: 1.3390039920806884
80th percentile: 1.5090057849884035
90th percentile: 1.842454195022583
95th percentile: 2.009178400039673
99th percentile: 2.1425577640533446
mean time: 1.4825642585754395
Pipeline stage StressChecker completed in 8.02s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.03s
pawankrd-cosmosrp_v20 status is now deployed due to DeploymentManager action
pawankrd-cosmosrp_v20 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics