submission_id: pawankrd-cosmosrp_v39
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: 2024-07-07T09:13:15+00:00
model_name: pawankrd-cosmosrp_v39
model_group: PawanKrd/CosmosRP
num_battles: 32395
num_wins: 17223
celo_rating: 1209.53
propriety_score: 0.7169335972647112
propriety_total_count: 5557.0
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_v39
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: 0.5316561197715697
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name pawankrd-cosmosrp-v39-mkmlizer
Waiting for job on pawankrd-cosmosrp-v39-mkmlizer to finish
Stopping job with name pawankrd-cosmosrp-v39-mkmlizer
%s, retrying in %s seconds...
Starting job with name pawankrd-cosmosrp-v39-mkmlizer
Waiting for job on pawankrd-cosmosrp-v39-mkmlizer to finish
pawankrd-cosmosrp-v39-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
pawankrd-cosmosrp-v39-mkmlizer: ║ _____ __ __ ║
pawankrd-cosmosrp-v39-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
pawankrd-cosmosrp-v39-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
pawankrd-cosmosrp-v39-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
pawankrd-cosmosrp-v39-mkmlizer: ║ /___/ ║
pawankrd-cosmosrp-v39-mkmlizer: ║ ║
pawankrd-cosmosrp-v39-mkmlizer: ║ Version: 0.8.14 ║
pawankrd-cosmosrp-v39-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
pawankrd-cosmosrp-v39-mkmlizer: ║ https://mk1.ai ║
pawankrd-cosmosrp-v39-mkmlizer: ║ ║
pawankrd-cosmosrp-v39-mkmlizer: ║ The license key for the current software has been verified as ║
pawankrd-cosmosrp-v39-mkmlizer: ║ belonging to: ║
pawankrd-cosmosrp-v39-mkmlizer: ║ ║
pawankrd-cosmosrp-v39-mkmlizer: ║ Chai Research Corp. ║
pawankrd-cosmosrp-v39-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
pawankrd-cosmosrp-v39-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
pawankrd-cosmosrp-v39-mkmlizer: ║ ║
pawankrd-cosmosrp-v39-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Job pawankrd-cosmosrp-v39-mkmlizer completed after 23.49s with status: failed
Stopping job with name pawankrd-cosmosrp-v39-mkmlizer
%s, retrying in %s seconds...
Starting job with name pawankrd-cosmosrp-v39-mkmlizer
Waiting for job on pawankrd-cosmosrp-v39-mkmlizer to finish
pawankrd-cosmosrp-v39-mkmlizer: Downloaded to shared memory in 28.694s
pawankrd-cosmosrp-v39-mkmlizer: quantizing model to /dev/shm/model_cache
pawankrd-cosmosrp-v39-mkmlizer: Saving flywheel model at /dev/shm/model_cache
pawankrd-cosmosrp-v39-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:02, 112.94it/s] Loading 0: 9%|▉ | 26/291 [00:00<00:02, 119.66it/s] Loading 0: 13%|█▎ | 39/291 [00:00<00:02, 121.09it/s] Loading 0: 18%|█▊ | 52/291 [00:00<00:02, 116.79it/s] Loading 0: 23%|██▎ | 66/291 [00:00<00:01, 120.90it/s] Loading 0: 27%|██▋ | 79/291 [00:00<00:01, 117.28it/s] Loading 0: 31%|███▏ | 91/291 [00:01<00:02, 66.84it/s] Loading 0: 35%|███▌ | 103/291 [00:01<00:02, 75.50it/s] Loading 0: 40%|███▉ | 116/291 [00:01<00:02, 86.67it/s] Loading 0: 44%|████▍ | 129/291 [00:01<00:01, 95.90it/s] Loading 0: 48%|████▊ | 141/291 [00:01<00:01, 97.16it/s] Loading 0: 54%|█████▎ | 156/291 [00:01<00:01, 107.47it/s] Loading 0: 58%|█████▊ | 168/291 [00:01<00:01, 104.80it/s] Loading 0: 62%|██████▏ | 181/291 [00:01<00:01, 107.82it/s] Loading 0: 66%|██████▋ | 193/291 [00:02<00:01, 67.22it/s] Loading 0: 70%|███████ | 205/291 [00:02<00:01, 76.94it/s] Loading 0: 75%|███████▌ | 219/291 [00:02<00:00, 88.16it/s] Loading 0: 79%|███████▉ | 230/291 [00:02<00:00, 89.70it/s] Loading 0: 85%|████████▍ | 246/291 [00:02<00:00, 103.27it/s] Loading 0: 89%|████████▊ | 258/291 [00:02<00:00, 102.79it/s] Loading 0: 94%|█████████▍| 273/291 [00:02<00:00, 111.44it/s] Loading 0: 98%|█████████▊| 285/291 [00:02<00:00, 110.60it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
pawankrd-cosmosrp-v39-mkmlizer: quantized model in 25.064s
pawankrd-cosmosrp-v39-mkmlizer: Processed model PawanKrd/CosmosRP in 53.758s
pawankrd-cosmosrp-v39-mkmlizer: creating bucket guanaco-mkml-models
pawankrd-cosmosrp-v39-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
pawankrd-cosmosrp-v39-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/pawankrd-cosmosrp-v39
pawankrd-cosmosrp-v39-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v39/config.json
pawankrd-cosmosrp-v39-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v39/special_tokens_map.json
pawankrd-cosmosrp-v39-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v39/tokenizer_config.json
pawankrd-cosmosrp-v39-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v39/tokenizer.json
pawankrd-cosmosrp-v39-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/pawankrd-cosmosrp-v39/flywheel_model.0.safetensors
pawankrd-cosmosrp-v39-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
pawankrd-cosmosrp-v39-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-v39-mkmlizer: warnings.warn(
pawankrd-cosmosrp-v39-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-v39-mkmlizer: warnings.warn(
pawankrd-cosmosrp-v39-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-v39-mkmlizer: warnings.warn(
pawankrd-cosmosrp-v39-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-v39-mkmlizer: warnings.warn(
pawankrd-cosmosrp-v39-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-v39-mkmlizer: return self.fget.__get__(instance, owner)()
pawankrd-cosmosrp-v39-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
pawankrd-cosmosrp-v39-mkmlizer: Saving duration: 0.407s
pawankrd-cosmosrp-v39-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.285s
pawankrd-cosmosrp-v39-mkmlizer: creating bucket guanaco-reward-models
pawankrd-cosmosrp-v39-mkmlizer: Bucket 's3://guanaco-reward-models/' created
pawankrd-cosmosrp-v39-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/pawankrd-cosmosrp-v39_reward
pawankrd-cosmosrp-v39-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/pawankrd-cosmosrp-v39_reward/special_tokens_map.json
pawankrd-cosmosrp-v39-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/pawankrd-cosmosrp-v39_reward/config.json
pawankrd-cosmosrp-v39-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/pawankrd-cosmosrp-v39_reward/tokenizer_config.json
pawankrd-cosmosrp-v39-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/pawankrd-cosmosrp-v39_reward/merges.txt
pawankrd-cosmosrp-v39-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/pawankrd-cosmosrp-v39_reward/vocab.json
pawankrd-cosmosrp-v39-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/pawankrd-cosmosrp-v39_reward/tokenizer.json
pawankrd-cosmosrp-v39-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/pawankrd-cosmosrp-v39_reward/reward.tensors
Job pawankrd-cosmosrp-v39-mkmlizer completed after 85.36s with status: succeeded
Stopping job with name pawankrd-cosmosrp-v39-mkmlizer
Pipeline stage MKMLizer completed in 111.19s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service pawankrd-cosmosrp-v39
Waiting for inference service pawankrd-cosmosrp-v39 to be ready
Inference service pawankrd-cosmosrp-v39 ready after 40.18594455718994s
Pipeline stage ISVCDeployer completed in 47.20s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9729228019714355s
Received healthy response to inference request in 1.3243064880371094s
Received healthy response to inference request in 1.3071305751800537s
Received healthy response to inference request in 1.2730042934417725s
Received healthy response to inference request in 1.2458291053771973s
5 requests
0 failed requests
5th percentile: 1.2512641429901123
10th percentile: 1.2566991806030274
20th percentile: 1.2675692558288574
30th percentile: 1.2798295497894288
40th percentile: 1.2934800624847411
50th percentile: 1.3071305751800537
60th percentile: 1.314000940322876
70th percentile: 1.3208713054656982
80th percentile: 1.4540297508239748
90th percentile: 1.7134762763977052
95th percentile: 1.8431995391845701
99th percentile: 1.9469781494140626
mean time: 1.4246386528015136
Pipeline stage StressChecker completed in 7.88s
pawankrd-cosmosrp_v39 status is now deployed due to DeploymentManager action
pawankrd-cosmosrp_v39 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics