submission_id: pawankrd-cosmosrp_v53
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: 2024-07-09T18:52:11+00:00
model_name: pawankrd-cosmosrp_v53
model_group: PawanKrd/CosmosRP
num_battles: 30116
num_wins: 14822
celo_rating: 1186.86
alignment_score: None
alignment_samples: 0
propriety_score: 0.7544497607655503
propriety_total_count: 5225.0
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_v53
ineligible_reason: None
language_model: PawanKrd/CosmosRP
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-07-09
win_ratio: 0.4921636339487316
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name pawankrd-cosmosrp-v53-mkmlizer
Waiting for job on pawankrd-cosmosrp-v53-mkmlizer to finish
pawankrd-cosmosrp-v53-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
pawankrd-cosmosrp-v53-mkmlizer: ║ _____ __ __ ║
pawankrd-cosmosrp-v53-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
pawankrd-cosmosrp-v53-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
pawankrd-cosmosrp-v53-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
pawankrd-cosmosrp-v53-mkmlizer: ║ /___/ ║
pawankrd-cosmosrp-v53-mkmlizer: ║ ║
pawankrd-cosmosrp-v53-mkmlizer: ║ Version: 0.8.14 ║
pawankrd-cosmosrp-v53-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
pawankrd-cosmosrp-v53-mkmlizer: ║ https://mk1.ai ║
pawankrd-cosmosrp-v53-mkmlizer: ║ ║
pawankrd-cosmosrp-v53-mkmlizer: ║ The license key for the current software has been verified as ║
pawankrd-cosmosrp-v53-mkmlizer: ║ belonging to: ║
pawankrd-cosmosrp-v53-mkmlizer: ║ ║
pawankrd-cosmosrp-v53-mkmlizer: ║ Chai Research Corp. ║
pawankrd-cosmosrp-v53-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
pawankrd-cosmosrp-v53-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
pawankrd-cosmosrp-v53-mkmlizer: ║ ║
pawankrd-cosmosrp-v53-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
pawankrd-cosmosrp-v53-mkmlizer: Downloaded to shared memory in 26.297s
pawankrd-cosmosrp-v53-mkmlizer: quantizing model to /dev/shm/model_cache
pawankrd-cosmosrp-v53-mkmlizer: Saving flywheel model at /dev/shm/model_cache
pawankrd-cosmosrp-v53-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:02, 119.58it/s] Loading 0: 10%|▉ | 28/291 [00:00<00:01, 136.08it/s] Loading 0: 14%|█▍ | 42/291 [00:00<00:01, 124.87it/s] Loading 0: 20%|█▉ | 57/291 [00:00<00:01, 133.16it/s] Loading 0: 24%|██▍ | 71/291 [00:00<00:01, 130.19it/s] Loading 0: 29%|██▉ | 85/291 [00:01<00:03, 59.55it/s] Loading 0: 34%|███▍ | 99/291 [00:01<00:02, 72.91it/s] Loading 0: 38%|███▊ | 112/291 [00:01<00:02, 82.66it/s] Loading 0: 43%|████▎ | 126/291 [00:01<00:01, 94.90it/s] Loading 0: 48%|████▊ | 139/291 [00:01<00:01, 100.18it/s] Loading 0: 52%|█████▏ | 152/291 [00:01<00:01, 106.79it/s] Loading 0: 57%|█████▋ | 165/291 [00:01<00:01, 112.62it/s] Loading 0: 62%|██████▏ | 179/291 [00:01<00:00, 118.40it/s] Loading 0: 66%|██████▌ | 192/291 [00:02<00:01, 59.31it/s] Loading 0: 70%|██████▉ | 203/291 [00:02<00:01, 66.07it/s] Loading 0: 75%|███████▌ | 219/291 [00:02<00:00, 80.78it/s] Loading 0: 79%|███████▉ | 230/291 [00:02<00:01, 48.59it/s] Loading 0: 85%|████████▍ | 246/291 [00:03<00:00, 63.01it/s] Loading 0: 88%|████████▊ | 257/291 [00:03<00:00, 69.23it/s] Loading 0: 94%|█████████▍| 273/291 [00:03<00:00, 85.42it/s] Loading 0: 98%|█████████▊| 285/291 [00:03<00:00, 92.11it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
pawankrd-cosmosrp-v53-mkmlizer: quantized model in 29.210s
pawankrd-cosmosrp-v53-mkmlizer: Processed model PawanKrd/CosmosRP in 55.508s
pawankrd-cosmosrp-v53-mkmlizer: creating bucket guanaco-mkml-models
pawankrd-cosmosrp-v53-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
pawankrd-cosmosrp-v53-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/pawankrd-cosmosrp-v53
pawankrd-cosmosrp-v53-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v53/config.json
pawankrd-cosmosrp-v53-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v53/special_tokens_map.json
pawankrd-cosmosrp-v53-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v53/tokenizer_config.json
pawankrd-cosmosrp-v53-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v53/tokenizer.json
pawankrd-cosmosrp-v53-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/pawankrd-cosmosrp-v53/flywheel_model.0.safetensors
pawankrd-cosmosrp-v53-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
pawankrd-cosmosrp-v53-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-v53-mkmlizer: warnings.warn(
pawankrd-cosmosrp-v53-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-v53-mkmlizer: warnings.warn(
pawankrd-cosmosrp-v53-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-v53-mkmlizer: warnings.warn(
pawankrd-cosmosrp-v53-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-v53-mkmlizer: warnings.warn(
pawankrd-cosmosrp-v53-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-v53-mkmlizer: return self.fget.__get__(instance, owner)()
pawankrd-cosmosrp-v53-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
pawankrd-cosmosrp-v53-mkmlizer: Saving duration: 1.387s
pawankrd-cosmosrp-v53-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 5.845s
pawankrd-cosmosrp-v53-mkmlizer: creating bucket guanaco-reward-models
pawankrd-cosmosrp-v53-mkmlizer: Bucket 's3://guanaco-reward-models/' created
pawankrd-cosmosrp-v53-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/pawankrd-cosmosrp-v53_reward
pawankrd-cosmosrp-v53-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/pawankrd-cosmosrp-v53_reward/config.json
pawankrd-cosmosrp-v53-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/pawankrd-cosmosrp-v53_reward/tokenizer_config.json
pawankrd-cosmosrp-v53-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/pawankrd-cosmosrp-v53_reward/special_tokens_map.json
pawankrd-cosmosrp-v53-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/pawankrd-cosmosrp-v53_reward/merges.txt
pawankrd-cosmosrp-v53-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/pawankrd-cosmosrp-v53_reward/vocab.json
pawankrd-cosmosrp-v53-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/pawankrd-cosmosrp-v53_reward/tokenizer.json
pawankrd-cosmosrp-v53-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/pawankrd-cosmosrp-v53_reward/reward.tensors
Job pawankrd-cosmosrp-v53-mkmlizer completed after 94.34s with status: succeeded
Stopping job with name pawankrd-cosmosrp-v53-mkmlizer
Pipeline stage MKMLizer completed in 95.20s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service pawankrd-cosmosrp-v53
Waiting for inference service pawankrd-cosmosrp-v53 to be ready
Inference service pawankrd-cosmosrp-v53 ready after 50.3174204826355s
Pipeline stage ISVCDeployer completed in 56.95s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.12618350982666s
Received healthy response to inference request in 1.3701379299163818s
Received healthy response to inference request in 1.3368372917175293s
Received healthy response to inference request in 1.309760332107544s
Received healthy response to inference request in 1.2712657451629639s
5 requests
0 failed requests
5th percentile: 1.2789646625518798
10th percentile: 1.286663579940796
20th percentile: 1.302061414718628
30th percentile: 1.315175724029541
40th percentile: 1.3260065078735352
50th percentile: 1.3368372917175293
60th percentile: 1.3501575469970704
70th percentile: 1.3634778022766114
80th percentile: 1.5213470458984377
90th percentile: 1.8237652778625488
95th percentile: 1.9749743938446043
99th percentile: 2.095941686630249
mean time: 1.4828369617462158
Pipeline stage StressChecker completed in 8.11s
pawankrd-cosmosrp_v53 status is now deployed due to DeploymentManager action
pawankrd-cosmosrp_v53 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics