submission_id: pawankrd-cosmosrp_v52
developer_uid: PawanOsman
status: inactive
model_repo: PawanKrd/CosmosRP
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.0, '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: 2024-07-09T18:51:34+00:00
model_name: pawankrd-cosmosrp_v52
model_group: PawanKrd/CosmosRP
num_battles: 30399
num_wins: 14928
celo_rating: 1186.29
alignment_score: None
alignment_samples: 0
propriety_score: 0.7539499036608863
propriety_total_count: 5190.0
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_v52
ineligible_reason: None
language_model: PawanKrd/CosmosRP
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-07-09
win_ratio: 0.4910687851574065
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name pawankrd-cosmosrp-v52-mkmlizer
Waiting for job on pawankrd-cosmosrp-v52-mkmlizer to finish
pawankrd-cosmosrp-v52-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
pawankrd-cosmosrp-v52-mkmlizer: ║ _____ __ __ ║
pawankrd-cosmosrp-v52-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
pawankrd-cosmosrp-v52-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
pawankrd-cosmosrp-v52-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
pawankrd-cosmosrp-v52-mkmlizer: ║ /___/ ║
pawankrd-cosmosrp-v52-mkmlizer: ║ ║
pawankrd-cosmosrp-v52-mkmlizer: ║ Version: 0.8.14 ║
pawankrd-cosmosrp-v52-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
pawankrd-cosmosrp-v52-mkmlizer: ║ https://mk1.ai ║
pawankrd-cosmosrp-v52-mkmlizer: ║ ║
pawankrd-cosmosrp-v52-mkmlizer: ║ The license key for the current software has been verified as ║
pawankrd-cosmosrp-v52-mkmlizer: ║ belonging to: ║
pawankrd-cosmosrp-v52-mkmlizer: ║ ║
pawankrd-cosmosrp-v52-mkmlizer: ║ Chai Research Corp. ║
pawankrd-cosmosrp-v52-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
pawankrd-cosmosrp-v52-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
pawankrd-cosmosrp-v52-mkmlizer: ║ ║
pawankrd-cosmosrp-v52-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
pawankrd-cosmosrp-v52-mkmlizer: Downloaded to shared memory in 24.050s
pawankrd-cosmosrp-v52-mkmlizer: quantizing model to /dev/shm/model_cache
pawankrd-cosmosrp-v52-mkmlizer: Saving flywheel model at /dev/shm/model_cache
pawankrd-cosmosrp-v52-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:02, 118.48it/s] Loading 0: 9%|▉ | 27/291 [00:00<00:02, 129.28it/s] Loading 0: 14%|█▎ | 40/291 [00:00<00:01, 125.77it/s] Loading 0: 19%|█▊ | 54/291 [00:00<00:01, 130.91it/s] Loading 0: 23%|██▎ | 68/291 [00:00<00:01, 122.30it/s] Loading 0: 29%|██▊ | 83/291 [00:01<00:03, 61.21it/s] Loading 0: 32%|███▏ | 94/291 [00:01<00:02, 68.65it/s] Loading 0: 37%|███▋ | 108/291 [00:01<00:02, 82.58it/s] Loading 0: 42%|████▏ | 121/291 [00:01<00:01, 90.74it/s] Loading 0: 46%|████▋ | 135/291 [00:01<00:01, 102.13it/s] Loading 0: 51%|█████ | 148/291 [00:01<00:01, 107.12it/s] Loading 0: 56%|█████▌ | 162/291 [00:01<00:01, 114.44it/s] Loading 0: 60%|██████ | 176/291 [00:01<00:00, 120.73it/s] Loading 0: 65%|██████▍ | 189/291 [00:02<00:01, 62.30it/s] Loading 0: 69%|██████▉ | 202/291 [00:02<00:01, 72.83it/s] Loading 0: 74%|███████▍ | 216/291 [00:02<00:00, 85.37it/s] Loading 0: 79%|███████▊ | 229/291 [00:02<00:00, 93.22it/s] Loading 0: 84%|████████▍ | 244/291 [00:02<00:00, 105.92it/s] Loading 0: 88%|████████▊ | 257/291 [00:02<00:00, 105.46it/s] Loading 0: 94%|█████████▍| 273/291 [00:02<00:00, 118.79it/s] Loading 0: 99%|█████████▊| 287/291 [00:09<00:00, 6.69it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
pawankrd-cosmosrp-v52-mkmlizer: quantized model in 28.807s
pawankrd-cosmosrp-v52-mkmlizer: Processed model PawanKrd/CosmosRP in 52.857s
pawankrd-cosmosrp-v52-mkmlizer: creating bucket guanaco-mkml-models
pawankrd-cosmosrp-v52-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
pawankrd-cosmosrp-v52-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/pawankrd-cosmosrp-v52
pawankrd-cosmosrp-v52-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v52/special_tokens_map.json
pawankrd-cosmosrp-v52-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v52/config.json
pawankrd-cosmosrp-v52-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v52/tokenizer_config.json
pawankrd-cosmosrp-v52-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v52/tokenizer.json
pawankrd-cosmosrp-v52-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/pawankrd-cosmosrp-v52/flywheel_model.0.safetensors
pawankrd-cosmosrp-v52-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
pawankrd-cosmosrp-v52-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-v52-mkmlizer: warnings.warn(
pawankrd-cosmosrp-v52-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-v52-mkmlizer: warnings.warn(
pawankrd-cosmosrp-v52-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-v52-mkmlizer: warnings.warn(
pawankrd-cosmosrp-v52-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-v52-mkmlizer: warnings.warn(
pawankrd-cosmosrp-v52-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-v52-mkmlizer: return self.fget.__get__(instance, owner)()
pawankrd-cosmosrp-v52-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
pawankrd-cosmosrp-v52-mkmlizer: Saving duration: 1.951s
pawankrd-cosmosrp-v52-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 5.900s
pawankrd-cosmosrp-v52-mkmlizer: creating bucket guanaco-reward-models
pawankrd-cosmosrp-v52-mkmlizer: Bucket 's3://guanaco-reward-models/' created
pawankrd-cosmosrp-v52-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/pawankrd-cosmosrp-v52_reward
pawankrd-cosmosrp-v52-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/pawankrd-cosmosrp-v52_reward/config.json
pawankrd-cosmosrp-v52-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/pawankrd-cosmosrp-v52_reward/special_tokens_map.json
pawankrd-cosmosrp-v52-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/pawankrd-cosmosrp-v52_reward/merges.txt
pawankrd-cosmosrp-v52-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/pawankrd-cosmosrp-v52_reward/tokenizer_config.json
pawankrd-cosmosrp-v52-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/pawankrd-cosmosrp-v52_reward/vocab.json
pawankrd-cosmosrp-v52-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/pawankrd-cosmosrp-v52_reward/tokenizer.json
pawankrd-cosmosrp-v52-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/pawankrd-cosmosrp-v52_reward/reward.tensors
Job pawankrd-cosmosrp-v52-mkmlizer completed after 115.39s with status: succeeded
Stopping job with name pawankrd-cosmosrp-v52-mkmlizer
Pipeline stage MKMLizer completed in 116.39s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service pawankrd-cosmosrp-v52
Waiting for inference service pawankrd-cosmosrp-v52 to be ready
Inference service pawankrd-cosmosrp-v52 ready after 50.26341009140015s
Pipeline stage ISVCDeployer completed in 57.34s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.091083288192749s
Received healthy response to inference request in 1.4079718589782715s
Received healthy response to inference request in 1.3836119174957275s
Received healthy response to inference request in 1.3874993324279785s
Received healthy response to inference request in 1.319899320602417s
5 requests
0 failed requests
5th percentile: 1.332641839981079
10th percentile: 1.3453843593597412
20th percentile: 1.3708693981170654
30th percentile: 1.3843894004821777
40th percentile: 1.3859443664550781
50th percentile: 1.3874993324279785
60th percentile: 1.3956883430480957
70th percentile: 1.403877353668213
80th percentile: 1.544594144821167
90th percentile: 1.817838716506958
95th percentile: 1.9544610023498534
99th percentile: 2.06375883102417
mean time: 1.5180131435394286
Pipeline stage StressChecker completed in 8.28s
pawankrd-cosmosrp_v52 status is now deployed due to DeploymentManager action
pawankrd-cosmosrp_v52 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics