submission_id: pawankrd-cosmosrp_v63
developer_uid: PawanOsman
status: inactive
model_repo: PawanKrd/CosmosRP
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.6, '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: 2024-07-12T22:42:10+00:00
model_name: pawankrd-cosmosrp_v63
model_group: PawanKrd/CosmosRP
num_battles: 18946
num_wins: 10463
celo_rating: 1240.45
alignment_score: None
alignment_samples: 0
propriety_score: 0.7257614868353124
propriety_total_count: 9685.0
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_v63
ineligible_reason: None
language_model: PawanKrd/CosmosRP
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-07-12
win_ratio: 0.5522537738836694
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name pawankrd-cosmosrp-v63-mkmlizer
Waiting for job on pawankrd-cosmosrp-v63-mkmlizer to finish
Stopping job with name pawankrd-cosmosrp-v63-mkmlizer
%s, retrying in %s seconds...
Starting job with name pawankrd-cosmosrp-v63-mkmlizer
Waiting for job on pawankrd-cosmosrp-v63-mkmlizer to finish
pawankrd-cosmosrp-v63-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
pawankrd-cosmosrp-v63-mkmlizer: ║ _____ __ __ ║
pawankrd-cosmosrp-v63-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
pawankrd-cosmosrp-v63-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
pawankrd-cosmosrp-v63-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
pawankrd-cosmosrp-v63-mkmlizer: ║ /___/ ║
pawankrd-cosmosrp-v63-mkmlizer: ║ ║
pawankrd-cosmosrp-v63-mkmlizer: ║ Version: 0.8.14 ║
pawankrd-cosmosrp-v63-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
pawankrd-cosmosrp-v63-mkmlizer: ║ https://mk1.ai ║
pawankrd-cosmosrp-v63-mkmlizer: ║ ║
pawankrd-cosmosrp-v63-mkmlizer: ║ The license key for the current software has been verified as ║
pawankrd-cosmosrp-v63-mkmlizer: ║ belonging to: ║
pawankrd-cosmosrp-v63-mkmlizer: ║ ║
pawankrd-cosmosrp-v63-mkmlizer: ║ Chai Research Corp. ║
pawankrd-cosmosrp-v63-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
pawankrd-cosmosrp-v63-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
pawankrd-cosmosrp-v63-mkmlizer: ║ ║
pawankrd-cosmosrp-v63-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
pawankrd-cosmosrp-v63-mkmlizer: Downloaded to shared memory in 23.202s
pawankrd-cosmosrp-v63-mkmlizer: quantizing model to /dev/shm/model_cache
pawankrd-cosmosrp-v63-mkmlizer: Saving flywheel model at /dev/shm/model_cache
pawankrd-cosmosrp-v63-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:05<13:24, 2.79s/it] Loading 0: 5%|▍ | 14/291 [00:05<01:22, 3.34it/s] Loading 0: 10%|▉ | 28/291 [00:05<00:32, 8.04it/s] Loading 0: 14%|█▍ | 41/291 [00:05<00:18, 13.66it/s] Loading 0: 19%|█▉ | 55/291 [00:06<00:10, 21.47it/s] Loading 0: 23%|██▎ | 67/291 [00:06<00:09, 22.63it/s] Loading 0: 27%|██▋ | 78/291 [00:06<00:07, 29.68it/s] Loading 0: 32%|███▏ | 94/291 [00:06<00:04, 43.01it/s] Loading 0: 36%|███▌ | 105/291 [00:06<00:03, 50.88it/s] Loading 0: 42%|████▏ | 121/291 [00:06<00:02, 67.42it/s] Loading 0: 46%|████▌ | 134/291 [00:07<00:02, 77.63it/s] Loading 0: 51%|█████ | 148/291 [00:07<00:01, 89.75it/s] Loading 0: 55%|█████▌ | 161/291 [00:07<00:01, 95.31it/s] Loading 0: 60%|█████▉ | 174/291 [00:07<00:02, 55.43it/s] Loading 0: 63%|██████▎ | 184/291 [00:07<00:01, 60.36it/s] Loading 0: 67%|██████▋ | 195/291 [00:07<00:01, 67.74it/s] Loading 0: 73%|███████▎ | 211/291 [00:08<00:00, 85.64it/s] Loading 0: 77%|███████▋ | 223/291 [00:08<00:00, 92.11it/s] Loading 0: 82%|████████▏ | 238/291 [00:08<00:00, 105.36it/s] Loading 0: 86%|████████▋ | 251/291 [00:08<00:00, 108.53it/s] Loading 0: 91%|█████████ | 265/291 [00:08<00:00, 111.16it/s] Loading 0: 96%|█████████▌| 278/291 [00:08<00:00, 59.77it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
pawankrd-cosmosrp-v63-mkmlizer: quantized model in 30.008s
pawankrd-cosmosrp-v63-mkmlizer: Processed model PawanKrd/CosmosRP in 53.211s
pawankrd-cosmosrp-v63-mkmlizer: creating bucket guanaco-mkml-models
pawankrd-cosmosrp-v63-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
pawankrd-cosmosrp-v63-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/pawankrd-cosmosrp-v63
pawankrd-cosmosrp-v63-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v63/special_tokens_map.json
pawankrd-cosmosrp-v63-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v63/config.json
pawankrd-cosmosrp-v63-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v63/tokenizer_config.json
pawankrd-cosmosrp-v63-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v63/tokenizer.json
pawankrd-cosmosrp-v63-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/pawankrd-cosmosrp-v63/flywheel_model.0.safetensors
pawankrd-cosmosrp-v63-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-v63-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
pawankrd-cosmosrp-v63-mkmlizer: warnings.warn(
pawankrd-cosmosrp-v63-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-v63-mkmlizer: warnings.warn(
pawankrd-cosmosrp-v63-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-v63-mkmlizer: warnings.warn(
pawankrd-cosmosrp-v63-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-v63-mkmlizer: warnings.warn(
pawankrd-cosmosrp-v63-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
pawankrd-cosmosrp-v63-mkmlizer: Saving duration: 0.514s
pawankrd-cosmosrp-v63-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.589s
pawankrd-cosmosrp-v63-mkmlizer: creating bucket guanaco-reward-models
pawankrd-cosmosrp-v63-mkmlizer: Bucket 's3://guanaco-reward-models/' created
pawankrd-cosmosrp-v63-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/pawankrd-cosmosrp-v63_reward
pawankrd-cosmosrp-v63-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/pawankrd-cosmosrp-v63_reward/config.json
pawankrd-cosmosrp-v63-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/pawankrd-cosmosrp-v63_reward/special_tokens_map.json
pawankrd-cosmosrp-v63-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/pawankrd-cosmosrp-v63_reward/merges.txt
pawankrd-cosmosrp-v63-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/pawankrd-cosmosrp-v63_reward/vocab.json
pawankrd-cosmosrp-v63-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/pawankrd-cosmosrp-v63_reward/tokenizer_config.json
pawankrd-cosmosrp-v63-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/pawankrd-cosmosrp-v63_reward/tokenizer.json
pawankrd-cosmosrp-v63-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/pawankrd-cosmosrp-v63_reward/reward.tensors
Job pawankrd-cosmosrp-v63-mkmlizer completed after 126.52s with status: succeeded
Stopping job with name pawankrd-cosmosrp-v63-mkmlizer
Pipeline stage MKMLizer completed in 128.32s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.14s
Running pipeline stage ISVCDeployer
Creating inference service pawankrd-cosmosrp-v63
Waiting for inference service pawankrd-cosmosrp-v63 to be ready
Inference service pawankrd-cosmosrp-v63 ready after 40.20303440093994s
Pipeline stage ISVCDeployer completed in 46.99s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.01544189453125s
Received healthy response to inference request in 1.361102819442749s
Received healthy response to inference request in 1.6187744140625s
Received healthy response to inference request in 1.6167070865631104s
Received healthy response to inference request in 1.9134316444396973s
5 requests
0 failed requests
5th percentile: 1.4122236728668214
10th percentile: 1.4633445262908935
20th percentile: 1.565586233139038
30th percentile: 1.6171205520629883
40th percentile: 1.617947483062744
50th percentile: 1.6187744140625
60th percentile: 1.7366373062133789
70th percentile: 1.8545001983642577
80th percentile: 1.933833694458008
90th percentile: 1.974637794494629
95th percentile: 1.9950398445129394
99th percentile: 2.011361484527588
mean time: 1.7050915718078614
Pipeline stage StressChecker completed in 9.34s
pawankrd-cosmosrp_v63 status is now deployed due to DeploymentManager action
pawankrd-cosmosrp_v63 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics