submission_id: pawankrd-cosmosrp-2x8b_v1
developer_uid: PawanOsman
status: inactive
model_repo: PawanKrd/CosmosRP-2x8b
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.9, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['<', '>'], 'max_input_tokens': 512, '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': True}
reward_formatter: {'memory_template': '<|im_start|>system\n{memory}<|im_end|>\n', 'prompt_template': '<|im_start|>user\n{prompt}<|im_end|>\n', 'bot_template': '<|im_start|>assistant\n{bot_name}: {message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{user_name}: {message}<|im_end|>\n', 'response_template': '{bot_name}:', 'truncate_by_message': False}
timestamp: 2024-06-13T17:56:29+00:00
model_name: pawankrd-cosmosrp-2x8b_v1
model_eval_status: success
model_group: PawanKrd/CosmosRP-2x8b
num_battles: 31701
num_wins: 17083
celo_rating: 1207.89
propriety_score: 0.7013422818791947
propriety_total_count: 14006.0
submission_type: basic
model_architecture: MixtralForCausalLM
model_num_parameters: 13667667968.0
best_of: 8
max_input_tokens: 512
max_output_tokens: 64
display_name: pawankrd-cosmosrp-2x8b_v1
ineligible_reason: None
language_model: PawanKrd/CosmosRP-2x8b
model_size: 14B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-13
win_ratio: 0.5388788997192517
Resubmit model
Running pipeline stage MKMLizer
Starting job with name pawankrd-cosmosrp-2x8b-v1-mkmlizer
Waiting for job on pawankrd-cosmosrp-2x8b-v1-mkmlizer to finish
pawankrd-cosmosrp-2x8b-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
pawankrd-cosmosrp-2x8b-v1-mkmlizer: ║ _____ __ __ ║
pawankrd-cosmosrp-2x8b-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
pawankrd-cosmosrp-2x8b-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
pawankrd-cosmosrp-2x8b-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
pawankrd-cosmosrp-2x8b-v1-mkmlizer: ║ /___/ ║
pawankrd-cosmosrp-2x8b-v1-mkmlizer: ║ ║
pawankrd-cosmosrp-2x8b-v1-mkmlizer: ║ Version: 0.8.14 ║
pawankrd-cosmosrp-2x8b-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
pawankrd-cosmosrp-2x8b-v1-mkmlizer: ║ https://mk1.ai ║
pawankrd-cosmosrp-2x8b-v1-mkmlizer: ║ ║
pawankrd-cosmosrp-2x8b-v1-mkmlizer: ║ The license key for the current software has been verified as ║
pawankrd-cosmosrp-2x8b-v1-mkmlizer: ║ belonging to: ║
pawankrd-cosmosrp-2x8b-v1-mkmlizer: ║ ║
pawankrd-cosmosrp-2x8b-v1-mkmlizer: ║ Chai Research Corp. ║
pawankrd-cosmosrp-2x8b-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
pawankrd-cosmosrp-2x8b-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
pawankrd-cosmosrp-2x8b-v1-mkmlizer: ║ ║
pawankrd-cosmosrp-2x8b-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
pawankrd-cosmosrp-2x8b-v1-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-2x8b-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
pawankrd-cosmosrp-2x8b-v1-mkmlizer: Downloaded to shared memory in 56.822s
pawankrd-cosmosrp-2x8b-v1-mkmlizer: quantizing model to /dev/shm/model_cache
pawankrd-cosmosrp-2x8b-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
pawankrd-cosmosrp-2x8b-v1-mkmlizer: Loading 0: 0%| | 0/419 [00:00<?, ?it/s] Loading 0: 3%|▎ | 14/419 [00:00<00:03, 127.44it/s] Loading 0: 6%|▋ | 27/419 [00:00<00:03, 124.11it/s] Loading 0: 10%|▉ | 40/419 [00:00<00:03, 119.37it/s] Loading 0: 13%|█▎ | 53/419 [00:00<00:03, 117.37it/s] Loading 0: 16%|█▌ | 65/419 [00:00<00:05, 65.47it/s] Loading 0: 20%|█▉ | 83/419 [00:00<00:03, 88.93it/s] Loading 0: 23%|██▎ | 95/419 [00:00<00:03, 93.65it/s] Loading 0: 26%|██▌ | 108/419 [00:01<00:03, 100.27it/s] Loading 0: 29%|██▉ | 121/419 [00:01<00:02, 105.41it/s] Loading 0: 32%|███▏ | 134/419 [00:01<00:02, 108.51it/s] Loading 0: 35%|███▍ | 146/419 [00:01<00:03, 69.48it/s] Loading 0: 38%|███▊ | 159/419 [00:01<00:03, 79.18it/s] Loading 0: 41%|████ | 172/419 [00:01<00:02, 88.69it/s] Loading 0: 44%|████▍ | 185/419 [00:01<00:02, 96.38it/s] Loading 0: 47%|████▋ | 198/419 [00:02<00:02, 102.38it/s] Loading 0: 51%|█████▏ | 215/419 [00:02<00:02, 75.58it/s] Loading 0: 54%|█████▎ | 225/419 [00:02<00:02, 77.61it/s] Loading 0: 57%|█████▋ | 239/419 [00:02<00:02, 89.70it/s] Loading 0: 60%|█████▉ | 251/419 [00:02<00:01, 96.00it/s] Loading 0: 63%|██████▎ | 263/419 [00:02<00:01, 101.68it/s] Loading 0: 66%|██████▌ | 275/419 [00:02<00:01, 106.03it/s] Loading 0: 69%|██████▉ | 289/419 [00:03<00:01, 69.17it/s] Loading 0: 72%|███████▏ | 302/419 [00:03<00:01, 79.76it/s] Loading 0: 75%|███████▌ | 315/419 [00:03<00:01, 89.29it/s] Loading 0: 78%|███████▊ | 328/419 [00:03<00:00, 97.16it/s] Loading 0: 81%|████████▏ | 341/419 [00:03<00:00, 103.22it/s] Loading 0: 84%|████████▍ | 354/419 [00:03<00:00, 108.01it/s] Loading 0: 88%|████████▊ | 367/419 [00:24<00:00, 108.01it/s] Loading 0: 88%|████████▊ | 368/419 [00:24<00:24, 2.12it/s] Loading 0: 95%|█████████▍| 396/419 [00:24<00:05, 4.01it/s] Loading 0: 99%|█████████▊| 413/419 [00:24<00:01, 5.60it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
pawankrd-cosmosrp-2x8b-v1-mkmlizer: quantized model in 31.458s
pawankrd-cosmosrp-2x8b-v1-mkmlizer: Processed model PawanKrd/CosmosRP-2x8b in 92.403s
pawankrd-cosmosrp-2x8b-v1-mkmlizer: creating bucket guanaco-mkml-models
pawankrd-cosmosrp-2x8b-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
pawankrd-cosmosrp-2x8b-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/pawankrd-cosmosrp-2x8b-v1
pawankrd-cosmosrp-2x8b-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/pawankrd-cosmosrp-2x8b-v1/special_tokens_map.json
pawankrd-cosmosrp-2x8b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/pawankrd-cosmosrp-2x8b-v1/tokenizer_config.json
pawankrd-cosmosrp-2x8b-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/pawankrd-cosmosrp-2x8b-v1/config.json
pawankrd-cosmosrp-2x8b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/pawankrd-cosmosrp-2x8b-v1/tokenizer.json
pawankrd-cosmosrp-2x8b-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/pawankrd-cosmosrp-2x8b-v1/flywheel_model.1.safetensors
pawankrd-cosmosrp-2x8b-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/pawankrd-cosmosrp-2x8b-v1/flywheel_model.0.safetensors
pawankrd-cosmosrp-2x8b-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
pawankrd-cosmosrp-2x8b-v1-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-2x8b-v1-mkmlizer: warnings.warn(
pawankrd-cosmosrp-2x8b-v1-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-2x8b-v1-mkmlizer: warnings.warn(
pawankrd-cosmosrp-2x8b-v1-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-2x8b-v1-mkmlizer: warnings.warn(
pawankrd-cosmosrp-2x8b-v1-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-2x8b-v1-mkmlizer: return self.fget.__get__(instance, owner)()
pawankrd-cosmosrp-2x8b-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
pawankrd-cosmosrp-2x8b-v1-mkmlizer: Saving duration: 0.385s
pawankrd-cosmosrp-2x8b-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 6.461s
pawankrd-cosmosrp-2x8b-v1-mkmlizer: creating bucket guanaco-reward-models
pawankrd-cosmosrp-2x8b-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
pawankrd-cosmosrp-2x8b-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/pawankrd-cosmosrp-2x8b-v1_reward
pawankrd-cosmosrp-2x8b-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/pawankrd-cosmosrp-2x8b-v1_reward/config.json
pawankrd-cosmosrp-2x8b-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/pawankrd-cosmosrp-2x8b-v1_reward/special_tokens_map.json
pawankrd-cosmosrp-2x8b-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/pawankrd-cosmosrp-2x8b-v1_reward/tokenizer_config.json
pawankrd-cosmosrp-2x8b-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/pawankrd-cosmosrp-2x8b-v1_reward/merges.txt
pawankrd-cosmosrp-2x8b-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/pawankrd-cosmosrp-2x8b-v1_reward/vocab.json
pawankrd-cosmosrp-2x8b-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/pawankrd-cosmosrp-2x8b-v1_reward/tokenizer.json
pawankrd-cosmosrp-2x8b-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/pawankrd-cosmosrp-2x8b-v1_reward/reward.tensors
Job pawankrd-cosmosrp-2x8b-v1-mkmlizer completed after 175.45s with status: succeeded
Stopping job with name pawankrd-cosmosrp-2x8b-v1-mkmlizer
Pipeline stage MKMLizer completed in 179.21s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service pawankrd-cosmosrp-2x8b-v1
Waiting for inference service pawankrd-cosmosrp-2x8b-v1 to be ready
Inference service pawankrd-cosmosrp-2x8b-v1 ready after 30.182353973388672s
Pipeline stage ISVCDeployer completed in 37.34s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.947110414505005s
Received healthy response to inference request in 2.1637094020843506s
Received healthy response to inference request in 2.1231517791748047s
Received healthy response to inference request in 2.053389310836792s
Received healthy response to inference request in 2.177424192428589s
5 requests
0 failed requests
5th percentile: 2.0673418045043945
10th percentile: 2.081294298171997
20th percentile: 2.109199285507202
30th percentile: 2.1312633037567137
40th percentile: 2.147486352920532
50th percentile: 2.1637094020843506
60th percentile: 2.169195318222046
70th percentile: 2.174681234359741
80th percentile: 2.3313614368438724
90th percentile: 2.6392359256744387
95th percentile: 2.7931731700897213
99th percentile: 2.9163229656219483
mean time: 2.2929570198059084
Pipeline stage StressChecker completed in 12.11s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.03s
Running M-Eval for topic stay_in_character
pawankrd-cosmosrp-2x8b_v1 status is now deployed due to DeploymentManager action
M-Eval Dataset for topic stay_in_character is loaded
pawankrd-cosmosrp-2x8b_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics