submission_id: pawankrd-cosmosrp_v42
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': ['\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\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: 2024-07-07T20:40:32+00:00
model_name: pawankrd-cosmosrp_v42
model_group: PawanKrd/CosmosRP
num_battles: 36211
num_wins: 20017
celo_rating: 1225.38
propriety_score: 0.7028171307604625
propriety_total_count: 6141.0
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_v42
ineligible_reason: None
language_model: PawanKrd/CosmosRP
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-07-07
win_ratio: 0.5527878269034271
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name pawankrd-cosmosrp-v42-mkmlizer
Waiting for job on pawankrd-cosmosrp-v42-mkmlizer to finish
pawankrd-cosmosrp-v42-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
pawankrd-cosmosrp-v42-mkmlizer: ║ _____ __ __ ║
pawankrd-cosmosrp-v42-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
pawankrd-cosmosrp-v42-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
pawankrd-cosmosrp-v42-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
pawankrd-cosmosrp-v42-mkmlizer: ║ /___/ ║
pawankrd-cosmosrp-v42-mkmlizer: ║ ║
pawankrd-cosmosrp-v42-mkmlizer: ║ Version: 0.8.14 ║
pawankrd-cosmosrp-v42-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
pawankrd-cosmosrp-v42-mkmlizer: ║ https://mk1.ai ║
pawankrd-cosmosrp-v42-mkmlizer: ║ ║
pawankrd-cosmosrp-v42-mkmlizer: ║ The license key for the current software has been verified as ║
pawankrd-cosmosrp-v42-mkmlizer: ║ belonging to: ║
pawankrd-cosmosrp-v42-mkmlizer: ║ ║
pawankrd-cosmosrp-v42-mkmlizer: ║ Chai Research Corp. ║
pawankrd-cosmosrp-v42-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
pawankrd-cosmosrp-v42-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
pawankrd-cosmosrp-v42-mkmlizer: ║ ║
pawankrd-cosmosrp-v42-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
pawankrd-cosmosrp-v42-mkmlizer: Downloaded to shared memory in 31.645s
pawankrd-cosmosrp-v42-mkmlizer: quantizing model to /dev/shm/model_cache
pawankrd-cosmosrp-v42-mkmlizer: Saving flywheel model at /dev/shm/model_cache
pawankrd-cosmosrp-v42-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:02, 114.38it/s] Loading 0: 9%|▉ | 27/291 [00:00<00:02, 125.48it/s] Loading 0: 14%|█▎ | 40/291 [00:00<00:02, 121.80it/s] Loading 0: 18%|█▊ | 53/291 [00:00<00:01, 122.41it/s] Loading 0: 23%|██▎ | 67/291 [00:00<00:01, 121.20it/s] Loading 0: 28%|██▊ | 81/291 [00:00<00:01, 125.04it/s] Loading 0: 32%|███▏ | 94/291 [00:01<00:03, 55.63it/s] Loading 0: 37%|███▋ | 108/291 [00:01<00:02, 68.86it/s] Loading 0: 41%|████ | 119/291 [00:01<00:02, 75.39it/s] Loading 0: 45%|████▍ | 130/291 [00:01<00:02, 76.81it/s] Loading 0: 49%|████▉ | 143/291 [00:01<00:01, 87.73it/s] Loading 0: 54%|█████▍ | 157/291 [00:01<00:01, 96.25it/s] Loading 0: 59%|█████▉ | 171/291 [00:01<00:01, 105.87it/s] Loading 0: 64%|██████▎ | 185/291 [00:01<00:00, 113.30it/s] Loading 0: 68%|██████▊ | 198/291 [00:02<00:01, 58.75it/s] Loading 0: 73%|███████▎ | 211/291 [00:02<00:01, 68.50it/s] Loading 0: 77%|███████▋ | 225/291 [00:02<00:00, 81.07it/s] Loading 0: 82%|████████▏ | 238/291 [00:02<00:00, 89.60it/s] Loading 0: 87%|████████▋ | 252/291 [00:02<00:00, 100.03it/s] Loading 0: 91%|█████████ | 264/291 [00:02<00:00, 104.37it/s] Loading 0: 95%|█████████▍| 276/291 [00:03<00:00, 102.41it/s] Loading 0: 99%|█████████▉| 288/291 [00:09<00:00, 5.88it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
pawankrd-cosmosrp-v42-mkmlizer: quantized model in 29.313s
pawankrd-cosmosrp-v42-mkmlizer: Processed model PawanKrd/CosmosRP in 60.958s
pawankrd-cosmosrp-v42-mkmlizer: creating bucket guanaco-mkml-models
pawankrd-cosmosrp-v42-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
pawankrd-cosmosrp-v42-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/pawankrd-cosmosrp-v42
pawankrd-cosmosrp-v42-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v42/config.json
pawankrd-cosmosrp-v42-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v42/special_tokens_map.json
pawankrd-cosmosrp-v42-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v42/tokenizer_config.json
pawankrd-cosmosrp-v42-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v42/tokenizer.json
pawankrd-cosmosrp-v42-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/pawankrd-cosmosrp-v42/flywheel_model.0.safetensors
pawankrd-cosmosrp-v42-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
pawankrd-cosmosrp-v42-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-v42-mkmlizer: warnings.warn(
pawankrd-cosmosrp-v42-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-v42-mkmlizer: warnings.warn(
pawankrd-cosmosrp-v42-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-v42-mkmlizer: warnings.warn(
pawankrd-cosmosrp-v42-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-v42-mkmlizer: warnings.warn(
pawankrd-cosmosrp-v42-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-v42-mkmlizer: return self.fget.__get__(instance, owner)()
pawankrd-cosmosrp-v42-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
pawankrd-cosmosrp-v42-mkmlizer: Saving duration: 0.525s
pawankrd-cosmosrp-v42-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.694s
pawankrd-cosmosrp-v42-mkmlizer: creating bucket guanaco-reward-models
pawankrd-cosmosrp-v42-mkmlizer: Bucket 's3://guanaco-reward-models/' created
pawankrd-cosmosrp-v42-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/pawankrd-cosmosrp-v42_reward
pawankrd-cosmosrp-v42-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/pawankrd-cosmosrp-v42_reward/config.json
pawankrd-cosmosrp-v42-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/pawankrd-cosmosrp-v42_reward/special_tokens_map.json
pawankrd-cosmosrp-v42-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/pawankrd-cosmosrp-v42_reward/tokenizer_config.json
pawankrd-cosmosrp-v42-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/pawankrd-cosmosrp-v42_reward/vocab.json
pawankrd-cosmosrp-v42-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/pawankrd-cosmosrp-v42_reward/merges.txt
pawankrd-cosmosrp-v42-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/pawankrd-cosmosrp-v42_reward/tokenizer.json
pawankrd-cosmosrp-v42-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/pawankrd-cosmosrp-v42_reward/reward.tensors
Job pawankrd-cosmosrp-v42-mkmlizer completed after 94.53s with status: succeeded
Stopping job with name pawankrd-cosmosrp-v42-mkmlizer
Pipeline stage MKMLizer completed in 95.50s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.16s
Running pipeline stage ISVCDeployer
Creating inference service pawankrd-cosmosrp-v42
Waiting for inference service pawankrd-cosmosrp-v42 to be ready
Inference service pawankrd-cosmosrp-v42 ready after 160.82722854614258s
Pipeline stage ISVCDeployer completed in 167.94s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0890603065490723s
Received healthy response to inference request in 1.3803424835205078s
Received healthy response to inference request in 1.3520803451538086s
Received healthy response to inference request in 1.3179967403411865s
Received healthy response to inference request in 1.4289462566375732s
5 requests
0 failed requests
5th percentile: 1.324813461303711
10th percentile: 1.3316301822662353
20th percentile: 1.345263624191284
30th percentile: 1.3577327728271484
40th percentile: 1.3690376281738281
50th percentile: 1.3803424835205078
60th percentile: 1.399783992767334
70th percentile: 1.4192255020141602
80th percentile: 1.5609690666198732
90th percentile: 1.8250146865844727
95th percentile: 1.9570374965667723
99th percentile: 2.0626557445526124
mean time: 1.5136852264404297
Pipeline stage StressChecker completed in 8.37s
pawankrd-cosmosrp_v42 status is now deployed due to DeploymentManager action
pawankrd-cosmosrp_v42 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics