submission_id: pawankrd-cosmosrp-16k_v2
developer_uid: PawanOsman
status: inactive
model_repo: PawanKrd/CosmosRP-16k
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.9, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 80, '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\nNo matter what, your responses should be family-friendly.\n\n", 'prompt_template': '{prompt}\nNo matter what, your responses should be family-friendly.<|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: 2024-06-27T13:51:47+00:00
model_name: pawankrd-cosmosrp-16k_v2
model_group: PawanKrd/CosmosRP-16k
num_battles: 27988
num_wins: 15047
celo_rating: 1209.65
propriety_score: 0.7188023769617553
propriety_total_count: 13126.0
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-16k_v2
ineligible_reason: None
language_model: PawanKrd/CosmosRP-16k
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-27
win_ratio: 0.5376232671144776
Resubmit model
Running pipeline stage MKMLizer
Starting job with name pawankrd-cosmosrp-16k-v2-mkmlizer
Waiting for job on pawankrd-cosmosrp-16k-v2-mkmlizer to finish
pawankrd-cosmosrp-16k-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
pawankrd-cosmosrp-16k-v2-mkmlizer: ║ _____ __ __ ║
pawankrd-cosmosrp-16k-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
pawankrd-cosmosrp-16k-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
pawankrd-cosmosrp-16k-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
pawankrd-cosmosrp-16k-v2-mkmlizer: ║ /___/ ║
pawankrd-cosmosrp-16k-v2-mkmlizer: ║ ║
pawankrd-cosmosrp-16k-v2-mkmlizer: ║ Version: 0.8.14 ║
pawankrd-cosmosrp-16k-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
pawankrd-cosmosrp-16k-v2-mkmlizer: ║ https://mk1.ai ║
pawankrd-cosmosrp-16k-v2-mkmlizer: ║ ║
pawankrd-cosmosrp-16k-v2-mkmlizer: ║ The license key for the current software has been verified as ║
pawankrd-cosmosrp-16k-v2-mkmlizer: ║ belonging to: ║
pawankrd-cosmosrp-16k-v2-mkmlizer: ║ ║
pawankrd-cosmosrp-16k-v2-mkmlizer: ║ Chai Research Corp. ║
pawankrd-cosmosrp-16k-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
pawankrd-cosmosrp-16k-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
pawankrd-cosmosrp-16k-v2-mkmlizer: ║ ║
pawankrd-cosmosrp-16k-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
pawankrd-cosmosrp-16k-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.
pawankrd-cosmosrp-16k-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
pawankrd-cosmosrp-16k-v2-mkmlizer: Downloaded to shared memory in 40.763s
pawankrd-cosmosrp-16k-v2-mkmlizer: quantizing model to /dev/shm/model_cache
pawankrd-cosmosrp-16k-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
pawankrd-cosmosrp-16k-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<11:47, 2.45s/it] Loading 0: 5%|▌ | 15/291 [00:05<01:07, 4.06it/s] Loading 0: 11%|█ | 32/291 [00:05<00:24, 10.45it/s] Loading 0: 15%|█▍ | 43/291 [00:05<00:15, 15.65it/s] Loading 0: 20%|██ | 59/291 [00:05<00:09, 25.49it/s] Loading 0: 25%|██▍ | 72/291 [00:05<00:07, 28.31it/s] Loading 0: 30%|██▉ | 86/291 [00:05<00:05, 38.78it/s] Loading 0: 35%|███▌ | 103/291 [00:05<00:03, 53.68it/s] Loading 0: 40%|████ | 117/291 [00:06<00:02, 65.95it/s] Loading 0: 45%|████▌ | 131/291 [00:06<00:02, 78.35it/s] Loading 0: 50%|████▉ | 145/291 [00:06<00:01, 88.09it/s] Loading 0: 55%|█████▍ | 159/291 [00:06<00:01, 96.23it/s] Loading 0: 59%|█████▉ | 172/291 [00:06<00:01, 69.27it/s] Loading 0: 64%|██████▍ | 186/291 [00:06<00:01, 79.76it/s] Loading 0: 69%|██████▊ | 200/291 [00:06<00:00, 91.50it/s] Loading 0: 73%|███████▎ | 213/291 [00:06<00:00, 97.18it/s] Loading 0: 79%|███████▉ | 230/291 [00:07<00:00, 112.55it/s] Loading 0: 84%|████████▎ | 243/291 [00:07<00:00, 112.24it/s] Loading 0: 88%|████████▊ | 257/291 [00:07<00:00, 117.94it/s] Loading 0: 93%|█████████▎| 270/291 [00:07<00:00, 74.80it/s] Loading 0: 98%|█████████▊| 284/291 [00:07<00:00, 85.90it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
pawankrd-cosmosrp-16k-v2-mkmlizer: quantized model in 25.578s
pawankrd-cosmosrp-16k-v2-mkmlizer: Processed model PawanKrd/CosmosRP-16k in 68.905s
pawankrd-cosmosrp-16k-v2-mkmlizer: creating bucket guanaco-mkml-models
pawankrd-cosmosrp-16k-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
pawankrd-cosmosrp-16k-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/pawankrd-cosmosrp-16k-v2
pawankrd-cosmosrp-16k-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/pawankrd-cosmosrp-16k-v2/config.json
pawankrd-cosmosrp-16k-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/pawankrd-cosmosrp-16k-v2/special_tokens_map.json
pawankrd-cosmosrp-16k-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/pawankrd-cosmosrp-16k-v2/tokenizer_config.json
pawankrd-cosmosrp-16k-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/pawankrd-cosmosrp-16k-v2/tokenizer.json
pawankrd-cosmosrp-16k-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/pawankrd-cosmosrp-16k-v2/flywheel_model.0.safetensors
pawankrd-cosmosrp-16k-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
pawankrd-cosmosrp-16k-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.
pawankrd-cosmosrp-16k-v2-mkmlizer: warnings.warn(
pawankrd-cosmosrp-16k-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.
pawankrd-cosmosrp-16k-v2-mkmlizer: warnings.warn(
pawankrd-cosmosrp-16k-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.
pawankrd-cosmosrp-16k-v2-mkmlizer: warnings.warn(
pawankrd-cosmosrp-16k-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()
pawankrd-cosmosrp-16k-v2-mkmlizer: return self.fget.__get__(instance, owner)()
pawankrd-cosmosrp-16k-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
pawankrd-cosmosrp-16k-v2-mkmlizer: Saving duration: 0.412s
pawankrd-cosmosrp-16k-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 12.392s
Job pawankrd-cosmosrp-16k-v2-mkmlizer completed after 105.76s with status: succeeded
Stopping job with name pawankrd-cosmosrp-16k-v2-mkmlizer
Pipeline stage MKMLizer completed in 106.82s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.13s
Running pipeline stage ISVCDeployer
Creating inference service pawankrd-cosmosrp-16k-v2
Waiting for inference service pawankrd-cosmosrp-16k-v2 to be ready
Inference service pawankrd-cosmosrp-16k-v2 ready after 40.21971321105957s
Pipeline stage ISVCDeployer completed in 48.17s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.379483938217163s
Received healthy response to inference request in 1.3089497089385986s
Received healthy response to inference request in 1.3138611316680908s
Received healthy response to inference request in 1.2889719009399414s
Received healthy response to inference request in 1.3645341396331787s
5 requests
0 failed requests
5th percentile: 1.2929674625396728
10th percentile: 1.2969630241394043
20th percentile: 1.3049541473388673
30th percentile: 1.309931993484497
40th percentile: 1.311896562576294
50th percentile: 1.3138611316680908
60th percentile: 1.334130334854126
70th percentile: 1.3543995380401612
80th percentile: 1.5675240993499757
90th percentile: 1.9735040187835695
95th percentile: 2.176493978500366
99th percentile: 2.3388859462738036
mean time: 1.5311601638793946
Pipeline stage StressChecker completed in 8.44s
pawankrd-cosmosrp-16k_v2 status is now deployed due to DeploymentManager action
pawankrd-cosmosrp-16k_v2 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics