submission_id: pawankrd-cosmosrp_v16
developer_uid: PawanOsman
status: inactive
model_repo: PawanKrd/CosmosRP
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.2, 'top_p': 0.95, 'min_p': 0.08, 'top_k': 40, '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: 2024-06-18T19:05:50+00:00
model_name: pawankrd-cosmosrp_v16
model_group: PawanKrd/CosmosRP
num_battles: 17606
num_wins: 9860
celo_rating: 1220.72
propriety_score: 0.7126672291189586
propriety_total_count: 8297.0
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_v16
ineligible_reason: None
language_model: PawanKrd/CosmosRP
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-18
win_ratio: 0.5600363512438942
Resubmit model
Running pipeline stage MKMLizer
Starting job with name pawankrd-cosmosrp-v16-mkmlizer
Waiting for job on pawankrd-cosmosrp-v16-mkmlizer to finish
pawankrd-cosmosrp-v16-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
pawankrd-cosmosrp-v16-mkmlizer: ║ _____ __ __ ║
pawankrd-cosmosrp-v16-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
pawankrd-cosmosrp-v16-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
pawankrd-cosmosrp-v16-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
pawankrd-cosmosrp-v16-mkmlizer: ║ /___/ ║
pawankrd-cosmosrp-v16-mkmlizer: ║ ║
pawankrd-cosmosrp-v16-mkmlizer: ║ Version: 0.8.14 ║
pawankrd-cosmosrp-v16-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
pawankrd-cosmosrp-v16-mkmlizer: ║ https://mk1.ai ║
pawankrd-cosmosrp-v16-mkmlizer: ║ ║
pawankrd-cosmosrp-v16-mkmlizer: ║ The license key for the current software has been verified as ║
pawankrd-cosmosrp-v16-mkmlizer: ║ belonging to: ║
pawankrd-cosmosrp-v16-mkmlizer: ║ ║
pawankrd-cosmosrp-v16-mkmlizer: ║ Chai Research Corp. ║
pawankrd-cosmosrp-v16-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
pawankrd-cosmosrp-v16-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
pawankrd-cosmosrp-v16-mkmlizer: ║ ║
pawankrd-cosmosrp-v16-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
pawankrd-cosmosrp-v16-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-v16-mkmlizer: warnings.warn(warning_message, FutureWarning)
pawankrd-cosmosrp-v16-mkmlizer: Downloaded to shared memory in 62.128s
pawankrd-cosmosrp-v16-mkmlizer: quantizing model to /dev/shm/model_cache
pawankrd-cosmosrp-v16-mkmlizer: Saving flywheel model at /dev/shm/model_cache
pawankrd-cosmosrp-v16-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<10:44, 2.23s/it] Loading 0: 3%|▎ | 10/291 [00:04<01:44, 2.70it/s] Loading 0: 7%|▋ | 20/291 [00:04<00:41, 6.53it/s] Loading 0: 10%|▉ | 29/291 [00:05<00:23, 10.97it/s] Loading 0: 14%|█▎ | 40/291 [00:05<00:14, 17.66it/s] Loading 0: 17%|█▋ | 50/291 [00:05<00:09, 24.50it/s] Loading 0: 20%|██ | 59/291 [00:05<00:07, 31.82it/s] Loading 0: 23%|██▎ | 68/291 [00:05<00:07, 30.28it/s] Loading 0: 26%|██▋ | 77/291 [00:05<00:05, 37.90it/s] Loading 0: 30%|██▉ | 86/291 [00:05<00:04, 46.00it/s] Loading 0: 33%|███▎ | 95/291 [00:06<00:03, 53.99it/s] Loading 0: 36%|███▌ | 104/291 [00:06<00:03, 61.31it/s] Loading 0: 39%|███▉ | 113/291 [00:06<00:04, 44.38it/s] Loading 0: 42%|████▏ | 123/291 [00:06<00:03, 51.75it/s] Loading 0: 45%|████▌ | 132/291 [00:06<00:02, 58.98it/s] Loading 0: 49%|████▉ | 143/291 [00:06<00:02, 69.92it/s] Loading 0: 52%|█████▏ | 152/291 [00:06<00:01, 74.49it/s] Loading 0: 55%|█████▌ | 161/291 [00:06<00:01, 78.11it/s] Loading 0: 58%|█████▊ | 170/291 [00:07<00:02, 50.00it/s] Loading 0: 62%|██████▏ | 179/291 [00:07<00:01, 57.47it/s] Loading 0: 65%|██████▍ | 189/291 [00:07<00:01, 65.49it/s] Loading 0: 68%|██████▊ | 198/291 [00:07<00:01, 71.01it/s] Loading 0: 71%|███████▏ | 208/291 [00:07<00:01, 76.91it/s] Loading 0: 75%|███████▍ | 217/291 [00:08<00:01, 50.92it/s] Loading 0: 78%|███████▊ | 226/291 [00:08<00:01, 58.17it/s] Loading 0: 81%|████████ | 235/291 [00:08<00:00, 64.53it/s] Loading 0: 84%|████████▍ | 245/291 [00:08<00:00, 72.70it/s] Loading 0: 87%|████████▋ | 254/291 [00:08<00:00, 76.66it/s] Loading 0: 90%|█████████ | 263/291 [00:08<00:00, 79.98it/s] Loading 0: 93%|█████████▎| 272/291 [00:08<00:00, 50.54it/s] Loading 0: 97%|█████████▋| 281/291 [00:08<00:00, 58.03it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
pawankrd-cosmosrp-v16-mkmlizer: quantized model in 25.044s
pawankrd-cosmosrp-v16-mkmlizer: Processed model PawanKrd/CosmosRP in 92.085s
pawankrd-cosmosrp-v16-mkmlizer: creating bucket guanaco-mkml-models
pawankrd-cosmosrp-v16-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
pawankrd-cosmosrp-v16-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/pawankrd-cosmosrp-v16
pawankrd-cosmosrp-v16-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v16/special_tokens_map.json
pawankrd-cosmosrp-v16-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v16/tokenizer_config.json
pawankrd-cosmosrp-v16-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v16/config.json
pawankrd-cosmosrp-v16-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v16/tokenizer.json
pawankrd-cosmosrp-v16-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/pawankrd-cosmosrp-v16/flywheel_model.0.safetensors
pawankrd-cosmosrp-v16-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
pawankrd-cosmosrp-v16-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-v16-mkmlizer: warnings.warn(
pawankrd-cosmosrp-v16-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-v16-mkmlizer: warnings.warn(
pawankrd-cosmosrp-v16-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-v16-mkmlizer: warnings.warn(
pawankrd-cosmosrp-v16-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-v16-mkmlizer: return self.fget.__get__(instance, owner)()
pawankrd-cosmosrp-v16-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
pawankrd-cosmosrp-v16-mkmlizer: Saving duration: 0.404s
pawankrd-cosmosrp-v16-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.692s
pawankrd-cosmosrp-v16-mkmlizer: creating bucket guanaco-reward-models
pawankrd-cosmosrp-v16-mkmlizer: Bucket 's3://guanaco-reward-models/' created
pawankrd-cosmosrp-v16-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/pawankrd-cosmosrp-v16_reward
pawankrd-cosmosrp-v16-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/pawankrd-cosmosrp-v16_reward/config.json
pawankrd-cosmosrp-v16-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/pawankrd-cosmosrp-v16_reward/special_tokens_map.json
pawankrd-cosmosrp-v16-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/pawankrd-cosmosrp-v16_reward/vocab.json
pawankrd-cosmosrp-v16-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/pawankrd-cosmosrp-v16_reward/merges.txt
pawankrd-cosmosrp-v16-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/pawankrd-cosmosrp-v16_reward/tokenizer_config.json
pawankrd-cosmosrp-v16-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/pawankrd-cosmosrp-v16_reward/tokenizer.json
pawankrd-cosmosrp-v16-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/pawankrd-cosmosrp-v16_reward/reward.tensors
Job pawankrd-cosmosrp-v16-mkmlizer completed after 124.69s with status: succeeded
Stopping job with name pawankrd-cosmosrp-v16-mkmlizer
Pipeline stage MKMLizer completed in 128.79s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service pawankrd-cosmosrp-v16
Waiting for inference service pawankrd-cosmosrp-v16 to be ready
Inference service pawankrd-cosmosrp-v16 ready after 110.68077063560486s
Pipeline stage ISVCDeployer completed in 118.11s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.181795120239258s
Received healthy response to inference request in 1.3786709308624268s
Received healthy response to inference request in 1.353363037109375s
Received healthy response to inference request in 1.3356573581695557s
Received healthy response to inference request in 1.267854928970337s
5 requests
0 failed requests
5th percentile: 1.2814154148101806
10th percentile: 1.2949759006500243
20th percentile: 1.322096872329712
30th percentile: 1.3391984939575194
40th percentile: 1.3462807655334472
50th percentile: 1.353363037109375
60th percentile: 1.3634861946105956
70th percentile: 1.3736093521118165
80th percentile: 1.539295768737793
90th percentile: 1.8605454444885254
95th percentile: 2.0211702823638915
99th percentile: 2.1496701526641844
mean time: 1.5034682750701904
Pipeline stage StressChecker completed in 8.81s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.04s
pawankrd-cosmosrp_v16 status is now deployed due to DeploymentManager action
pawankrd-cosmosrp_v16 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics