submission_id: pawankrd-cosmosrp_v56
developer_uid: PawanOsman
status: inactive
model_repo: PawanKrd/CosmosRP
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': ['<', '>'], '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: 2024-07-10T07:49:43+00:00
model_name: pawankrd-cosmosrp_v56
model_group: PawanKrd/CosmosRP
num_battles: 37148
num_wins: 18192
celo_rating: 1183.04
alignment_score: None
alignment_samples: 0
propriety_score: 0.7489314548044959
propriety_total_count: 6317.0
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_v56
ineligible_reason: None
language_model: PawanKrd/CosmosRP
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-07-10
win_ratio: 0.48971680844190807
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name pawankrd-cosmosrp-v56-mkmlizer
Waiting for job on pawankrd-cosmosrp-v56-mkmlizer to finish
pawankrd-cosmosrp-v56-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
pawankrd-cosmosrp-v56-mkmlizer: ║ _____ __ __ ║
pawankrd-cosmosrp-v56-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
pawankrd-cosmosrp-v56-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
pawankrd-cosmosrp-v56-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
pawankrd-cosmosrp-v56-mkmlizer: ║ /___/ ║
pawankrd-cosmosrp-v56-mkmlizer: ║ ║
pawankrd-cosmosrp-v56-mkmlizer: ║ Version: 0.8.14 ║
pawankrd-cosmosrp-v56-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
pawankrd-cosmosrp-v56-mkmlizer: ║ https://mk1.ai ║
pawankrd-cosmosrp-v56-mkmlizer: ║ ║
pawankrd-cosmosrp-v56-mkmlizer: ║ The license key for the current software has been verified as ║
pawankrd-cosmosrp-v56-mkmlizer: ║ belonging to: ║
pawankrd-cosmosrp-v56-mkmlizer: ║ ║
pawankrd-cosmosrp-v56-mkmlizer: ║ Chai Research Corp. ║
pawankrd-cosmosrp-v56-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
pawankrd-cosmosrp-v56-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
pawankrd-cosmosrp-v56-mkmlizer: ║ ║
pawankrd-cosmosrp-v56-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
pawankrd-cosmosrp-v56-mkmlizer: Downloaded to shared memory in 22.989s
pawankrd-cosmosrp-v56-mkmlizer: quantizing model to /dev/shm/model_cache
pawankrd-cosmosrp-v56-mkmlizer: Saving flywheel model at /dev/shm/model_cache
pawankrd-cosmosrp-v56-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:02, 113.42it/s] Loading 0: 9%|▉ | 27/291 [00:00<00:02, 126.63it/s] Loading 0: 14%|█▎ | 40/291 [00:00<00:02, 124.01it/s] Loading 0: 19%|█▊ | 54/291 [00:00<00:01, 129.31it/s] Loading 0: 23%|██▎ | 67/291 [00:00<00:01, 124.90it/s] Loading 0: 28%|██▊ | 81/291 [00:00<00:01, 127.68it/s] Loading 0: 32%|███▏ | 94/291 [00:01<00:03, 58.12it/s] Loading 0: 37%|███▋ | 108/291 [00:01<00:02, 71.25it/s] Loading 0: 42%|████▏ | 121/291 [00:01<00:02, 80.58it/s] Loading 0: 46%|████▌ | 134/291 [00:01<00:01, 90.99it/s] Loading 0: 51%|█████ | 148/291 [00:01<00:01, 98.42it/s] Loading 0: 56%|█████▌ | 162/291 [00:01<00:01, 107.46it/s] Loading 0: 60%|██████ | 176/291 [00:01<00:00, 115.20it/s] Loading 0: 65%|██████▍ | 189/291 [00:02<00:01, 60.71it/s] Loading 0: 69%|██████▉ | 202/291 [00:02<00:01, 70.86it/s] Loading 0: 73%|███████▎ | 213/291 [00:02<00:01, 76.50it/s] Loading 0: 78%|███████▊ | 228/291 [00:02<00:00, 90.75it/s] Loading 0: 82%|████████▏ | 240/291 [00:02<00:00, 95.94it/s] Loading 0: 88%|████████▊ | 255/291 [00:02<00:00, 108.88it/s] Loading 0: 92%|█████████▏| 268/291 [00:02<00:00, 111.90it/s] Loading 0: 97%|█████████▋| 281/291 [00:02<00:00, 114.08it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
pawankrd-cosmosrp-v56-mkmlizer: quantized model in 29.250s
pawankrd-cosmosrp-v56-mkmlizer: Processed model PawanKrd/CosmosRP in 52.239s
pawankrd-cosmosrp-v56-mkmlizer: creating bucket guanaco-mkml-models
pawankrd-cosmosrp-v56-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
pawankrd-cosmosrp-v56-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/pawankrd-cosmosrp-v56
pawankrd-cosmosrp-v56-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v56/config.json
pawankrd-cosmosrp-v56-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v56/special_tokens_map.json
pawankrd-cosmosrp-v56-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v56/tokenizer_config.json
pawankrd-cosmosrp-v56-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v56/tokenizer.json
pawankrd-cosmosrp-v56-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/pawankrd-cosmosrp-v56/flywheel_model.0.safetensors
pawankrd-cosmosrp-v56-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
pawankrd-cosmosrp-v56-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-v56-mkmlizer: warnings.warn(
pawankrd-cosmosrp-v56-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-v56-mkmlizer: warnings.warn(
pawankrd-cosmosrp-v56-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-v56-mkmlizer: warnings.warn(
pawankrd-cosmosrp-v56-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-v56-mkmlizer: warnings.warn(
pawankrd-cosmosrp-v56-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-v56-mkmlizer: return self.fget.__get__(instance, owner)()
pawankrd-cosmosrp-v56-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
pawankrd-cosmosrp-v56-mkmlizer: Saving duration: 0.523s
pawankrd-cosmosrp-v56-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 5.606s
pawankrd-cosmosrp-v56-mkmlizer: creating bucket guanaco-reward-models
pawankrd-cosmosrp-v56-mkmlizer: Bucket 's3://guanaco-reward-models/' created
pawankrd-cosmosrp-v56-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/pawankrd-cosmosrp-v56_reward
pawankrd-cosmosrp-v56-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/pawankrd-cosmosrp-v56_reward/special_tokens_map.json
pawankrd-cosmosrp-v56-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/pawankrd-cosmosrp-v56_reward/tokenizer_config.json
pawankrd-cosmosrp-v56-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/pawankrd-cosmosrp-v56_reward/tokenizer.json
pawankrd-cosmosrp-v56-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/pawankrd-cosmosrp-v56_reward/merges.txt
pawankrd-cosmosrp-v56-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/pawankrd-cosmosrp-v56_reward/config.json
pawankrd-cosmosrp-v56-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/pawankrd-cosmosrp-v56_reward/vocab.json
pawankrd-cosmosrp-v56-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/pawankrd-cosmosrp-v56_reward/reward.tensors
Job pawankrd-cosmosrp-v56-mkmlizer completed after 83.69s with status: succeeded
Stopping job with name pawankrd-cosmosrp-v56-mkmlizer
Pipeline stage MKMLizer completed in 84.57s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.27s
Running pipeline stage ISVCDeployer
Creating inference service pawankrd-cosmosrp-v56
Waiting for inference service pawankrd-cosmosrp-v56 to be ready
Inference service pawankrd-cosmosrp-v56 ready after 40.168736934661865s
Pipeline stage ISVCDeployer completed in 47.22s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9619150161743164s
Received healthy response to inference request in 1.3630790710449219s
Received healthy response to inference request in 1.336207389831543s
Received healthy response to inference request in 1.3110003471374512s
Received healthy response to inference request in 1.262467384338379s
5 requests
0 failed requests
5th percentile: 1.2721739768981934
10th percentile: 1.2818805694580078
20th percentile: 1.3012937545776366
30th percentile: 1.3160417556762696
40th percentile: 1.3261245727539062
50th percentile: 1.336207389831543
60th percentile: 1.3469560623168946
70th percentile: 1.3577047348022462
80th percentile: 1.4828462600708008
90th percentile: 1.7223806381225586
95th percentile: 1.8421478271484375
99th percentile: 1.9379615783691406
mean time: 1.4469338417053224
Pipeline stage StressChecker completed in 7.98s
pawankrd-cosmosrp_v56 status is now deployed due to DeploymentManager action
pawankrd-cosmosrp_v56 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics