submission_id: pawankrd-cosmosrp-experi_5136_v2
developer_uid: PawanOsman
status: inactive
model_repo: PawanKrd/CosmosRP-experimental
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<', '>'], 'max_input_tokens': 1024, 'best_of': 8, '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: 2024-07-02T12:10:25+00:00
model_name: pawankrd-cosmosrp-exp_v2
model_group: PawanKrd/CosmosRP-experi
num_battles: 12255
num_wins: 6512
celo_rating: 1195.4
propriety_score: 0.7079646017699115
propriety_total_count: 5763.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
display_name: pawankrd-cosmosrp-exp_v2
ineligible_reason: None
language_model: PawanKrd/CosmosRP-experimental
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-07-02
win_ratio: 0.531374949000408
Resubmit model
Running pipeline stage MKMLizer
Starting job with name pawankrd-cosmosrp-experi-5136-v2-mkmlizer
Waiting for job on pawankrd-cosmosrp-experi-5136-v2-mkmlizer to finish
pawankrd-cosmosrp-experi-5136-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
pawankrd-cosmosrp-experi-5136-v2-mkmlizer: ║ _____ __ __ ║
pawankrd-cosmosrp-experi-5136-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
pawankrd-cosmosrp-experi-5136-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
pawankrd-cosmosrp-experi-5136-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
pawankrd-cosmosrp-experi-5136-v2-mkmlizer: ║ /___/ ║
pawankrd-cosmosrp-experi-5136-v2-mkmlizer: ║ ║
pawankrd-cosmosrp-experi-5136-v2-mkmlizer: ║ Version: 0.8.14 ║
pawankrd-cosmosrp-experi-5136-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
pawankrd-cosmosrp-experi-5136-v2-mkmlizer: ║ https://mk1.ai ║
pawankrd-cosmosrp-experi-5136-v2-mkmlizer: ║ ║
pawankrd-cosmosrp-experi-5136-v2-mkmlizer: ║ The license key for the current software has been verified as ║
pawankrd-cosmosrp-experi-5136-v2-mkmlizer: ║ belonging to: ║
pawankrd-cosmosrp-experi-5136-v2-mkmlizer: ║ ║
pawankrd-cosmosrp-experi-5136-v2-mkmlizer: ║ Chai Research Corp. ║
pawankrd-cosmosrp-experi-5136-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
pawankrd-cosmosrp-experi-5136-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
pawankrd-cosmosrp-experi-5136-v2-mkmlizer: ║ ║
pawankrd-cosmosrp-experi-5136-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
pawankrd-cosmosrp-experi-5136-v2-mkmlizer: Downloaded to shared memory in 34.836s
pawankrd-cosmosrp-experi-5136-v2-mkmlizer: quantizing model to /dev/shm/model_cache
pawankrd-cosmosrp-experi-5136-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission neversleep-noromaid-v0-_8068_v105: no entry with id "neversleep-noromaid-v0-_8068_v105" found on database!
pawankrd-cosmosrp-experi-5136-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:02, 111.53it/s] Loading 0: 9%|▉ | 27/291 [00:00<00:02, 124.90it/s] Loading 0: 14%|█▎ | 40/291 [00:00<00:02, 121.35it/s] Loading 0: 19%|█▊ | 54/291 [00:00<00:01, 127.27it/s] Loading 0: 23%|██▎ | 67/291 [00:00<00:01, 122.91it/s] Loading 0: 27%|██▋ | 80/291 [00:00<00:01, 124.84it/s] Loading 0: 32%|███▏ | 93/291 [00:01<00:02, 67.13it/s] Loading 0: 36%|███▌ | 104/291 [00:01<00:02, 73.38it/s] Loading 0: 41%|████ | 120/291 [00:01<00:01, 90.14it/s] Loading 0: 45%|████▌ | 132/291 [00:01<00:01, 94.06it/s] Loading 0: 51%|█████ | 147/291 [00:01<00:01, 105.64it/s] Loading 0: 55%|█████▍ | 159/291 [00:01<00:01, 105.53it/s] Loading 0: 59%|█████▉ | 173/291 [00:01<00:01, 112.42it/s] Loading 0: 64%|██████▍ | 187/291 [00:02<00:01, 71.69it/s] Loading 0: 68%|██████▊ | 197/291 [00:02<00:01, 75.98it/s] Loading 0: 73%|███████▎ | 211/291 [00:02<00:00, 85.79it/s] Loading 0: 77%|███████▋ | 225/291 [00:02<00:00, 96.63it/s] Loading 0: 82%|████████▏ | 238/291 [00:02<00:00, 101.39it/s] Loading 0: 86%|████████▋ | 251/291 [00:02<00:00, 108.19it/s] Loading 0: 91%|█████████ | 265/291 [00:02<00:00, 110.75it/s] Loading 0: 96%|█████████▌| 278/291 [00:02<00:00, 114.89it/s] Loading 0: 100%|█████████▉| 290/291 [00:08<00:00, 7.27it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
pawankrd-cosmosrp-experi-5136-v2-mkmlizer: quantized model in 23.966s
pawankrd-cosmosrp-experi-5136-v2-mkmlizer: Processed model PawanKrd/CosmosRP-experimental in 58.802s
pawankrd-cosmosrp-experi-5136-v2-mkmlizer: creating bucket guanaco-mkml-models
pawankrd-cosmosrp-experi-5136-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
pawankrd-cosmosrp-experi-5136-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/pawankrd-cosmosrp-experi-5136-v2
pawankrd-cosmosrp-experi-5136-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/pawankrd-cosmosrp-experi-5136-v2/config.json
pawankrd-cosmosrp-experi-5136-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/pawankrd-cosmosrp-experi-5136-v2/special_tokens_map.json
pawankrd-cosmosrp-experi-5136-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/pawankrd-cosmosrp-experi-5136-v2/tokenizer_config.json
pawankrd-cosmosrp-experi-5136-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/pawankrd-cosmosrp-experi-5136-v2/tokenizer.json
pawankrd-cosmosrp-experi-5136-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/pawankrd-cosmosrp-experi-5136-v2/flywheel_model.0.safetensors
pawankrd-cosmosrp-experi-5136-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
pawankrd-cosmosrp-experi-5136-v2-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-experi-5136-v2-mkmlizer: warnings.warn(
pawankrd-cosmosrp-experi-5136-v2-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-experi-5136-v2-mkmlizer: warnings.warn(
pawankrd-cosmosrp-experi-5136-v2-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-experi-5136-v2-mkmlizer: warnings.warn(
pawankrd-cosmosrp-experi-5136-v2-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-experi-5136-v2-mkmlizer: warnings.warn(
pawankrd-cosmosrp-experi-5136-v2-mkmlizer: Saving duration: 0.383s
pawankrd-cosmosrp-experi-5136-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.448s
pawankrd-cosmosrp-experi-5136-v2-mkmlizer: creating bucket guanaco-reward-models
pawankrd-cosmosrp-experi-5136-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
pawankrd-cosmosrp-experi-5136-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/pawankrd-cosmosrp-experi-5136-v2_reward
pawankrd-cosmosrp-experi-5136-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/pawankrd-cosmosrp-experi-5136-v2_reward/config.json
pawankrd-cosmosrp-experi-5136-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/pawankrd-cosmosrp-experi-5136-v2_reward/tokenizer_config.json
pawankrd-cosmosrp-experi-5136-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/pawankrd-cosmosrp-experi-5136-v2_reward/special_tokens_map.json
pawankrd-cosmosrp-experi-5136-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/pawankrd-cosmosrp-experi-5136-v2_reward/merges.txt
pawankrd-cosmosrp-experi-5136-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/pawankrd-cosmosrp-experi-5136-v2_reward/vocab.json
pawankrd-cosmosrp-experi-5136-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/pawankrd-cosmosrp-experi-5136-v2_reward/tokenizer.json
pawankrd-cosmosrp-experi-5136-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/pawankrd-cosmosrp-experi-5136-v2_reward/reward.tensors
Job pawankrd-cosmosrp-experi-5136-v2-mkmlizer completed after 83.64s with status: succeeded
Stopping job with name pawankrd-cosmosrp-experi-5136-v2-mkmlizer
Pipeline stage MKMLizer completed in 84.60s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service pawankrd-cosmosrp-experi-5136-v2
Waiting for inference service pawankrd-cosmosrp-experi-5136-v2 to be ready
Inference service pawankrd-cosmosrp-experi-5136-v2 ready after 40.23612332344055s
Pipeline stage ISVCDeployer completed in 47.25s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.027553081512451s
Received healthy response to inference request in 1.2227146625518799s
Received healthy response to inference request in 1.242537021636963s
Received healthy response to inference request in 1.2784128189086914s
Received healthy response to inference request in 1.217219591140747s
5 requests
0 failed requests
5th percentile: 1.2183186054229735
10th percentile: 1.2194176197052002
20th percentile: 1.2216156482696534
30th percentile: 1.2266791343688965
40th percentile: 1.2346080780029296
50th percentile: 1.242537021636963
60th percentile: 1.2568873405456542
70th percentile: 1.2712376594543457
80th percentile: 1.4282408714294434
90th percentile: 1.7278969764709473
95th percentile: 1.8777250289916991
99th percentile: 1.9975874710083008
mean time: 1.3976874351501465
Pipeline stage StressChecker completed in 7.81s
pawankrd-cosmosrp-experi_5136_v2 status is now deployed due to DeploymentManager action
pawankrd-cosmosrp-experi_5136_v2 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics