submission_id: pawankrd-cosmosrp_v41
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: 2024-07-07T18:31:29+00:00
model_name: pawankrd-cosmosrp_v41
model_group: PawanKrd/CosmosRP
num_battles: 44781
num_wins: 25067
celo_rating: 1229.61
propriety_score: 0.7085056876938987
propriety_total_count: 7736.0
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_v41
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: 0.5597686518836114
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name pawankrd-cosmosrp-v41-mkmlizer
Waiting for job on pawankrd-cosmosrp-v41-mkmlizer to finish
pawankrd-cosmosrp-v41-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
pawankrd-cosmosrp-v41-mkmlizer: ║ _____ __ __ ║
pawankrd-cosmosrp-v41-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
pawankrd-cosmosrp-v41-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
pawankrd-cosmosrp-v41-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
pawankrd-cosmosrp-v41-mkmlizer: ║ /___/ ║
pawankrd-cosmosrp-v41-mkmlizer: ║ ║
pawankrd-cosmosrp-v41-mkmlizer: ║ Version: 0.8.14 ║
pawankrd-cosmosrp-v41-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
pawankrd-cosmosrp-v41-mkmlizer: ║ https://mk1.ai ║
pawankrd-cosmosrp-v41-mkmlizer: ║ ║
pawankrd-cosmosrp-v41-mkmlizer: ║ The license key for the current software has been verified as ║
pawankrd-cosmosrp-v41-mkmlizer: ║ belonging to: ║
pawankrd-cosmosrp-v41-mkmlizer: ║ ║
pawankrd-cosmosrp-v41-mkmlizer: ║ Chai Research Corp. ║
pawankrd-cosmosrp-v41-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
pawankrd-cosmosrp-v41-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
pawankrd-cosmosrp-v41-mkmlizer: ║ ║
pawankrd-cosmosrp-v41-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
pawankrd-cosmosrp-v41-mkmlizer: Downloaded to shared memory in 36.434s
pawankrd-cosmosrp-v41-mkmlizer: quantizing model to /dev/shm/model_cache
pawankrd-cosmosrp-v41-mkmlizer: Saving flywheel model at /dev/shm/model_cache
pawankrd-cosmosrp-v41-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:02, 113.08it/s] Loading 0: 9%|▉ | 27/291 [00:00<00:02, 126.02it/s] Loading 0: 14%|█▎ | 40/291 [00:00<00:02, 122.72it/s] Loading 0: 19%|█▊ | 54/291 [00:00<00:01, 127.41it/s] Loading 0: 23%|██▎ | 67/291 [00:00<00:01, 123.74it/s] Loading 0: 27%|██▋ | 80/291 [00:00<00:01, 125.40it/s] Loading 0: 32%|███▏ | 93/291 [00:01<00:03, 56.60it/s] Loading 0: 36%|███▌ | 104/291 [00:01<00:02, 63.73it/s] Loading 0: 41%|████ | 120/291 [00:01<00:02, 80.92it/s] Loading 0: 45%|████▌ | 132/291 [00:01<00:01, 87.75it/s] Loading 0: 51%|█████ | 147/291 [00:01<00:01, 99.45it/s] Loading 0: 55%|█████▍ | 159/291 [00:01<00:01, 102.60it/s] Loading 0: 59%|█████▉ | 173/291 [00:01<00:01, 111.39it/s] Loading 0: 64%|██████▍ | 187/291 [00:02<00:01, 63.29it/s] Loading 0: 68%|██████▊ | 197/291 [00:02<00:01, 69.37it/s] Loading 0: 72%|███████▏ | 210/291 [00:02<00:01, 77.76it/s] Loading 0: 76%|███████▌ | 220/291 [00:02<00:00, 82.32it/s] Loading 0: 80%|████████ | 234/291 [00:02<00:00, 95.19it/s] Loading 0: 85%|████████▍ | 247/291 [00:02<00:00, 101.60it/s] Loading 0: 90%|████████▉ | 261/291 [00:02<00:00, 110.03it/s] Loading 0: 94%|█████████▍| 274/291 [00:02<00:00, 110.34it/s] Loading 0: 99%|█████████▊| 287/291 [00:09<00:00, 6.10it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
pawankrd-cosmosrp-v41-mkmlizer: quantized model in 28.776s
pawankrd-cosmosrp-v41-mkmlizer: Processed model PawanKrd/CosmosRP in 65.210s
pawankrd-cosmosrp-v41-mkmlizer: creating bucket guanaco-mkml-models
pawankrd-cosmosrp-v41-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
pawankrd-cosmosrp-v41-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/pawankrd-cosmosrp-v41
pawankrd-cosmosrp-v41-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v41/config.json
pawankrd-cosmosrp-v41-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v41/tokenizer_config.json
pawankrd-cosmosrp-v41-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v41/special_tokens_map.json
pawankrd-cosmosrp-v41-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v41/tokenizer.json
pawankrd-cosmosrp-v41-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/pawankrd-cosmosrp-v41/flywheel_model.0.safetensors
pawankrd-cosmosrp-v41-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
pawankrd-cosmosrp-v41-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-v41-mkmlizer: warnings.warn(
pawankrd-cosmosrp-v41-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-v41-mkmlizer: warnings.warn(
pawankrd-cosmosrp-v41-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-v41-mkmlizer: warnings.warn(
pawankrd-cosmosrp-v41-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-v41-mkmlizer: warnings.warn(
pawankrd-cosmosrp-v41-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-v41-mkmlizer: return self.fget.__get__(instance, owner)()
pawankrd-cosmosrp-v41-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
pawankrd-cosmosrp-v41-mkmlizer: Saving duration: 0.506s
pawankrd-cosmosrp-v41-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 5.249s
pawankrd-cosmosrp-v41-mkmlizer: creating bucket guanaco-reward-models
pawankrd-cosmosrp-v41-mkmlizer: Bucket 's3://guanaco-reward-models/' created
pawankrd-cosmosrp-v41-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/pawankrd-cosmosrp-v41_reward
pawankrd-cosmosrp-v41-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/pawankrd-cosmosrp-v41_reward/config.json
pawankrd-cosmosrp-v41-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/pawankrd-cosmosrp-v41_reward/special_tokens_map.json
pawankrd-cosmosrp-v41-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/pawankrd-cosmosrp-v41_reward/tokenizer_config.json
pawankrd-cosmosrp-v41-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/pawankrd-cosmosrp-v41_reward/merges.txt
pawankrd-cosmosrp-v41-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/pawankrd-cosmosrp-v41_reward/vocab.json
pawankrd-cosmosrp-v41-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/pawankrd-cosmosrp-v41_reward/tokenizer.json
pawankrd-cosmosrp-v41-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/pawankrd-cosmosrp-v41_reward/reward.tensors
Job pawankrd-cosmosrp-v41-mkmlizer completed after 93.86s with status: succeeded
Stopping job with name pawankrd-cosmosrp-v41-mkmlizer
Pipeline stage MKMLizer completed in 94.85s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service pawankrd-cosmosrp-v41
Waiting for inference service pawankrd-cosmosrp-v41 to be ready
Inference service pawankrd-cosmosrp-v41 ready after 40.20407676696777s
Pipeline stage ISVCDeployer completed in 47.31s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1000680923461914s
Received healthy response to inference request in 1.3796041011810303s
Received healthy response to inference request in 1.3318891525268555s
Received healthy response to inference request in 1.3226332664489746s
Received healthy response to inference request in 1.2530388832092285s
5 requests
0 failed requests
5th percentile: 1.2669577598571777
10th percentile: 1.280876636505127
20th percentile: 1.3087143898010254
30th percentile: 1.3244844436645509
40th percentile: 1.3281867980957032
50th percentile: 1.3318891525268555
60th percentile: 1.3509751319885255
70th percentile: 1.3700611114501953
80th percentile: 1.5236968994140627
90th percentile: 1.811882495880127
95th percentile: 1.955975294113159
99th percentile: 2.071249532699585
mean time: 1.477446699142456
Pipeline stage StressChecker completed in 8.20s
pawankrd-cosmosrp_v41 status is now deployed due to DeploymentManager action
pawankrd-cosmosrp_v41 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics