submission_id: pawankrd-cosmosrp_v38
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: 2024-07-07T07:43:36+00:00
model_name: pawankrd-cosmosrp_v38
model_group: PawanKrd/CosmosRP
num_battles: 43821
num_wins: 23778
celo_rating: 1216.2
propriety_score: 0.7086004273504274
propriety_total_count: 7488.0
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_v38
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: 0.5426165537071267
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name pawankrd-cosmosrp-v38-mkmlizer
Waiting for job on pawankrd-cosmosrp-v38-mkmlizer to finish
pawankrd-cosmosrp-v38-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
pawankrd-cosmosrp-v38-mkmlizer: ║ _____ __ __ ║
pawankrd-cosmosrp-v38-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
pawankrd-cosmosrp-v38-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
pawankrd-cosmosrp-v38-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
pawankrd-cosmosrp-v38-mkmlizer: ║ /___/ ║
pawankrd-cosmosrp-v38-mkmlizer: ║ ║
pawankrd-cosmosrp-v38-mkmlizer: ║ Version: 0.8.14 ║
pawankrd-cosmosrp-v38-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
pawankrd-cosmosrp-v38-mkmlizer: ║ https://mk1.ai ║
pawankrd-cosmosrp-v38-mkmlizer: ║ ║
pawankrd-cosmosrp-v38-mkmlizer: ║ The license key for the current software has been verified as ║
pawankrd-cosmosrp-v38-mkmlizer: ║ belonging to: ║
pawankrd-cosmosrp-v38-mkmlizer: ║ ║
pawankrd-cosmosrp-v38-mkmlizer: ║ Chai Research Corp. ║
pawankrd-cosmosrp-v38-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
pawankrd-cosmosrp-v38-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
pawankrd-cosmosrp-v38-mkmlizer: ║ ║
pawankrd-cosmosrp-v38-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
pawankrd-cosmosrp-v38-mkmlizer: Downloaded to shared memory in 29.683s
pawankrd-cosmosrp-v38-mkmlizer: quantizing model to /dev/shm/model_cache
pawankrd-cosmosrp-v38-mkmlizer: Saving flywheel model at /dev/shm/model_cache
pawankrd-cosmosrp-v38-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:05<12:03, 2.50s/it] Loading 0: 4%|▍ | 13/291 [00:05<01:20, 3.44it/s] Loading 0: 8%|▊ | 23/291 [00:05<00:37, 7.12it/s] Loading 0: 11%|█▏ | 33/291 [00:05<00:21, 11.91it/s] Loading 0: 17%|█▋ | 49/291 [00:05<00:11, 21.84it/s] Loading 0: 21%|██ | 60/291 [00:05<00:10, 22.88it/s] Loading 0: 25%|██▌ | 74/291 [00:05<00:06, 33.27it/s] Loading 0: 29%|██▉ | 85/291 [00:06<00:04, 41.68it/s] Loading 0: 33%|███▎ | 96/291 [00:06<00:03, 49.39it/s] Loading 0: 38%|███▊ | 112/291 [00:06<00:02, 65.19it/s] Loading 0: 42%|████▏ | 123/291 [00:06<00:02, 70.15it/s] Loading 0: 48%|████▊ | 139/291 [00:06<00:01, 84.71it/s] Loading 0: 52%|█████▏ | 151/291 [00:06<00:01, 87.19it/s] Loading 0: 57%|█████▋ | 166/291 [00:07<00:01, 63.36it/s] Loading 0: 60%|██████ | 176/291 [00:07<00:01, 69.44it/s] Loading 0: 64%|██████▍ | 187/291 [00:07<00:01, 77.09it/s] Loading 0: 69%|██████▊ | 200/291 [00:07<00:01, 88.35it/s] Loading 0: 73%|███████▎ | 211/291 [00:07<00:00, 91.85it/s] Loading 0: 76%|███████▋ | 222/291 [00:07<00:00, 90.54it/s] Loading 0: 82%|████████▏ | 238/291 [00:07<00:00, 102.97it/s] Loading 0: 86%|████████▌ | 250/291 [00:07<00:00, 101.42it/s] Loading 0: 91%|█████████ | 265/291 [00:07<00:00, 109.16it/s] Loading 0: 95%|█████████▌| 277/291 [00:08<00:00, 66.47it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
pawankrd-cosmosrp-v38-mkmlizer: quantized model in 25.237s
pawankrd-cosmosrp-v38-mkmlizer: Processed model PawanKrd/CosmosRP in 54.920s
pawankrd-cosmosrp-v38-mkmlizer: creating bucket guanaco-mkml-models
pawankrd-cosmosrp-v38-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
pawankrd-cosmosrp-v38-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/pawankrd-cosmosrp-v38
pawankrd-cosmosrp-v38-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v38/special_tokens_map.json
pawankrd-cosmosrp-v38-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v38/config.json
pawankrd-cosmosrp-v38-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v38/tokenizer_config.json
pawankrd-cosmosrp-v38-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v38/tokenizer.json
pawankrd-cosmosrp-v38-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/pawankrd-cosmosrp-v38/flywheel_model.0.safetensors
pawankrd-cosmosrp-v38-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
pawankrd-cosmosrp-v38-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-v38-mkmlizer: warnings.warn(
pawankrd-cosmosrp-v38-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-v38-mkmlizer: warnings.warn(
pawankrd-cosmosrp-v38-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-v38-mkmlizer: warnings.warn(
pawankrd-cosmosrp-v38-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-v38-mkmlizer: warnings.warn(
pawankrd-cosmosrp-v38-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-v38-mkmlizer: return self.fget.__get__(instance, owner)()
pawankrd-cosmosrp-v38-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
pawankrd-cosmosrp-v38-mkmlizer: Saving duration: 0.387s
pawankrd-cosmosrp-v38-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 8.180s
pawankrd-cosmosrp-v38-mkmlizer: creating bucket guanaco-reward-models
pawankrd-cosmosrp-v38-mkmlizer: Bucket 's3://guanaco-reward-models/' created
pawankrd-cosmosrp-v38-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/pawankrd-cosmosrp-v38_reward
pawankrd-cosmosrp-v38-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/pawankrd-cosmosrp-v38_reward/config.json
pawankrd-cosmosrp-v38-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/pawankrd-cosmosrp-v38_reward/special_tokens_map.json
pawankrd-cosmosrp-v38-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/pawankrd-cosmosrp-v38_reward/merges.txt
pawankrd-cosmosrp-v38-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/pawankrd-cosmosrp-v38_reward/tokenizer_config.json
pawankrd-cosmosrp-v38-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/pawankrd-cosmosrp-v38_reward/vocab.json
pawankrd-cosmosrp-v38-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/pawankrd-cosmosrp-v38_reward/tokenizer.json
pawankrd-cosmosrp-v38-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/pawankrd-cosmosrp-v38_reward/reward.tensors
Job pawankrd-cosmosrp-v38-mkmlizer completed after 83.39s with status: succeeded
Stopping job with name pawankrd-cosmosrp-v38-mkmlizer
Pipeline stage MKMLizer completed in 84.35s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service pawankrd-cosmosrp-v38
Waiting for inference service pawankrd-cosmosrp-v38 to be ready
Inference service pawankrd-cosmosrp-v38 ready after 80.31861448287964s
Pipeline stage ISVCDeployer completed in 87.17s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0499777793884277s
Received healthy response to inference request in 1.351386547088623s
Received healthy response to inference request in 1.3273634910583496s
Received healthy response to inference request in 1.2911622524261475s
Received healthy response to inference request in 1.2780413627624512s
5 requests
0 failed requests
5th percentile: 1.2806655406951903
10th percentile: 1.2832897186279297
20th percentile: 1.2885380744934083
30th percentile: 1.2984025001525878
40th percentile: 1.3128829956054688
50th percentile: 1.3273634910583496
60th percentile: 1.336972713470459
70th percentile: 1.3465819358825684
80th percentile: 1.4911047935485842
90th percentile: 1.770541286468506
95th percentile: 1.9102595329284666
99th percentile: 2.0220341300964355
mean time: 1.4595862865447997
Pipeline stage StressChecker completed in 7.97s
pawankrd-cosmosrp_v38 status is now deployed due to DeploymentManager action
pawankrd-cosmosrp_v38 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics