submission_id: pawankrd-cosmosrp-llama31_v2
developer_uid: PawanOsman
alignment_samples: 0
best_of: 16
celo_rating: 1255.97
display_name: cosmosrp-llama31-test
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}
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, 'reward_max_token_input': 128}
is_internal_developer: False
language_model: PawanKrd/cosmosrp-llama31
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: PawanKrd/cosmosrp-llama3
model_name: cosmosrp-llama31-test
model_num_parameters: 8030261248.0
model_repo: PawanKrd/cosmosrp-llama31
model_size: 8B
num_battles: 13232
num_wins: 7513
propriety_score: 0.7189655172413794
propriety_total_count: 1160.0
ranking_group: single
reward_formatter: {'bot_template': '{bot_name}: {message}\n', 'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'response_template': '{bot_name}:', 'truncate_by_message': False, 'user_template': '{user_name}: {message}\n'}
reward_repo: Jellywibble/gpt2_xl_pairwise_89m_step_347634
status: torndown
submission_type: basic
timestamp: 2024-07-26T12:57:25+00:00
us_pacific_date: 2024-07-26
win_ratio: 0.5677902055622733
Download Preference Data
Resubmit model
Running pipeline stage MKMLizer
Starting job with name pawankrd-cosmosrp-llama31-v2-mkmlizer
Waiting for job on pawankrd-cosmosrp-llama31-v2-mkmlizer to finish
pawankrd-cosmosrp-llama31-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
pawankrd-cosmosrp-llama31-v2-mkmlizer: ║ _____ __ __ ║
pawankrd-cosmosrp-llama31-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
pawankrd-cosmosrp-llama31-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
pawankrd-cosmosrp-llama31-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
pawankrd-cosmosrp-llama31-v2-mkmlizer: ║ /___/ ║
pawankrd-cosmosrp-llama31-v2-mkmlizer: ║ ║
pawankrd-cosmosrp-llama31-v2-mkmlizer: ║ Version: 0.9.7 ║
pawankrd-cosmosrp-llama31-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
pawankrd-cosmosrp-llama31-v2-mkmlizer: ║ https://mk1.ai ║
pawankrd-cosmosrp-llama31-v2-mkmlizer: ║ ║
pawankrd-cosmosrp-llama31-v2-mkmlizer: ║ The license key for the current software has been verified as ║
pawankrd-cosmosrp-llama31-v2-mkmlizer: ║ belonging to: ║
pawankrd-cosmosrp-llama31-v2-mkmlizer: ║ ║
pawankrd-cosmosrp-llama31-v2-mkmlizer: ║ Chai Research Corp. ║
pawankrd-cosmosrp-llama31-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
pawankrd-cosmosrp-llama31-v2-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
pawankrd-cosmosrp-llama31-v2-mkmlizer: ║ ║
pawankrd-cosmosrp-llama31-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
pawankrd-cosmosrp-llama31-v2-mkmlizer: Downloaded to shared memory in 20.591s
pawankrd-cosmosrp-llama31-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp_piav9k7, device:0
pawankrd-cosmosrp-llama31-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
pawankrd-cosmosrp-llama31-v2-mkmlizer: quantized model in 25.627s
pawankrd-cosmosrp-llama31-v2-mkmlizer: Processed model PawanKrd/cosmosrp-llama31 in 46.217s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
pawankrd-cosmosrp-llama31-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
pawankrd-cosmosrp-llama31-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/pawankrd-cosmosrp-llama31-v2
pawankrd-cosmosrp-llama31-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/pawankrd-cosmosrp-llama31-v2/special_tokens_map.json
pawankrd-cosmosrp-llama31-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/pawankrd-cosmosrp-llama31-v2/config.json
pawankrd-cosmosrp-llama31-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/pawankrd-cosmosrp-llama31-v2/tokenizer_config.json
pawankrd-cosmosrp-llama31-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/pawankrd-cosmosrp-llama31-v2/tokenizer.json
pawankrd-cosmosrp-llama31-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/pawankrd-cosmosrp-llama31-v2/flywheel_model.0.safetensors
pawankrd-cosmosrp-llama31-v2-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
pawankrd-cosmosrp-llama31-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<11:34, 2.40s/it] Loading 0: 2%|▏ | 6/291 [00:04<03:04, 1.54it/s] Loading 0: 5%|▍ | 14/291 [00:05<01:00, 4.61it/s] Loading 0: 7%|▋ | 20/291 [00:05<00:36, 7.48it/s] Loading 0: 9%|▉ | 27/291 [00:05<00:22, 11.82it/s] Loading 0: 11%|█▏ | 33/291 [00:05<00:16, 15.55it/s] Loading 0: 14%|█▍ | 42/291 [00:05<00:11, 22.18it/s] Loading 0: 18%|█▊ | 51/291 [00:05<00:08, 28.03it/s] Loading 0: 20%|██ | 59/291 [00:05<00:06, 35.38it/s] Loading 0: 22%|██▏ | 65/291 [00:06<00:07, 28.77it/s] Loading 0: 24%|██▍ | 70/291 [00:06<00:07, 31.35it/s] Loading 0: 27%|██▋ | 78/291 [00:06<00:05, 35.75it/s] Loading 0: 30%|██▉ | 87/291 [00:06<00:04, 41.10it/s] Loading 0: 33%|███▎ | 96/291 [00:06<00:04, 45.78it/s] Loading 0: 36%|███▌ | 104/291 [00:06<00:03, 51.06it/s] Loading 0: 38%|███▊ | 110/291 [00:07<00:03, 48.37it/s] Loading 0: 40%|███▉ | 116/291 [00:07<00:03, 49.73it/s] Loading 0: 42%|████▏ | 123/291 [00:07<00:03, 47.70it/s] Loading 0: 45%|████▌ | 132/291 [00:07<00:03, 50.33it/s] Loading 0: 48%|████▊ | 140/291 [00:07<00:02, 56.85it/s] Loading 0: 51%|█████ | 147/291 [00:07<00:02, 57.22it/s] Loading 0: 53%|█████▎ | 153/291 [00:07<00:02, 55.59it/s] Loading 0: 55%|█████▍ | 159/291 [00:07<00:02, 49.96it/s] Loading 0: 57%|█████▋ | 166/291 [00:08<00:03, 40.29it/s] Loading 0: 59%|█████▉ | 171/291 [00:08<00:02, 41.61it/s] Loading 0: 61%|██████ | 177/291 [00:08<00:02, 40.88it/s] Loading 0: 64%|██████▎ | 185/291 [00:08<00:02, 49.50it/s] Loading 0: 66%|██████▌ | 191/291 [00:08<00:02, 48.61it/s] Loading 0: 68%|██████▊ | 198/291 [00:08<00:01, 53.11it/s] Loading 0: 70%|███████ | 204/291 [00:08<00:01, 49.57it/s] Loading 0: 73%|███████▎ | 212/291 [00:09<00:01, 56.96it/s] Loading 0: 75%|███████▌ | 219/291 [00:09<00:01, 56.33it/s] Loading 0: 77%|███████▋ | 225/291 [00:09<00:01, 55.85it/s] Loading 0: 79%|███████▉ | 231/291 [00:09<00:01, 48.75it/s] Loading 0: 82%|████████▏ | 239/291 [00:09<00:00, 56.32it/s] Loading 0: 84%|████████▍ | 245/291 [00:09<00:00, 53.31it/s] Loading 0: 86%|████████▋ | 251/291 [00:09<00:00, 54.49it/s] Loading 0: 89%|████████▊ | 258/291 [00:09<00:00, 51.11it/s] Loading 0: 91%|█████████▏| 266/291 [00:10<00:00, 41.44it/s] Loading 0: 93%|█████████▎| 272/291 [00:10<00:00, 42.45it/s] Loading 0: 95%|█████████▌| 277/291 [00:10<00:00, 43.52it/s] Loading 0: 98%|█████████▊| 285/291 [00:10<00:00, 45.37it/s] /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:957: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
pawankrd-cosmosrp-llama31-v2-mkmlizer: warnings.warn(
pawankrd-cosmosrp-llama31-v2-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:785: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
pawankrd-cosmosrp-llama31-v2-mkmlizer: warnings.warn(
pawankrd-cosmosrp-llama31-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
pawankrd-cosmosrp-llama31-v2-mkmlizer: Saving duration: 1.386s
pawankrd-cosmosrp-llama31-v2-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 10.906s
pawankrd-cosmosrp-llama31-v2-mkmlizer: creating bucket guanaco-reward-models
pawankrd-cosmosrp-llama31-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
pawankrd-cosmosrp-llama31-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/pawankrd-cosmosrp-llama31-v2_reward
pawankrd-cosmosrp-llama31-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/pawankrd-cosmosrp-llama31-v2_reward/config.json
pawankrd-cosmosrp-llama31-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/pawankrd-cosmosrp-llama31-v2_reward/special_tokens_map.json
pawankrd-cosmosrp-llama31-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/pawankrd-cosmosrp-llama31-v2_reward/vocab.json
pawankrd-cosmosrp-llama31-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/pawankrd-cosmosrp-llama31-v2_reward/tokenizer.json
pawankrd-cosmosrp-llama31-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/pawankrd-cosmosrp-llama31-v2_reward/reward.tensors
Job pawankrd-cosmosrp-llama31-v2-mkmlizer completed after 84.67s with status: succeeded
Stopping job with name pawankrd-cosmosrp-llama31-v2-mkmlizer
Pipeline stage MKMLizer completed in 86.03s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service pawankrd-cosmosrp-llama31-v2
Waiting for inference service pawankrd-cosmosrp-llama31-v2 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service pawankrd-cosmosrp-llama31-v2 ready after 70.49020338058472s
Pipeline stage ISVCDeployer completed in 72.23s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.095306396484375s
Received healthy response to inference request in 1.3743867874145508s
Received healthy response to inference request in 1.3511056900024414s
Received healthy response to inference request in 1.3268203735351562s
Received healthy response to inference request in 1.299994707107544s
5 requests
0 failed requests
5th percentile: 1.3053598403930664
10th percentile: 1.3107249736785889
20th percentile: 1.3214552402496338
30th percentile: 1.3316774368286133
40th percentile: 1.3413915634155273
50th percentile: 1.3511056900024414
60th percentile: 1.3604181289672852
70th percentile: 1.369730567932129
80th percentile: 1.5185707092285157
90th percentile: 1.8069385528564454
95th percentile: 1.9511224746704101
99th percentile: 2.066469612121582
mean time: 1.4895227909088136
Pipeline stage StressChecker completed in 8.14s
pawankrd-cosmosrp-llama31_v2 status is now deployed due to DeploymentManager action
pawankrd-cosmosrp-llama31_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of pawankrd-cosmosrp-llama31_v2
Running pipeline stage ISVCDeleter
Checking if service pawankrd-cosmosrp-llama31-v2 is running
Tearing down inference service pawankrd-cosmosrp-llama31-v2
Service pawankrd-cosmosrp-llama31-v2 has been torndown
Pipeline stage ISVCDeleter completed in 4.04s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key pawankrd-cosmosrp-llama31-v2/config.json from bucket guanaco-mkml-models
Deleting key pawankrd-cosmosrp-llama31-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key pawankrd-cosmosrp-llama31-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key pawankrd-cosmosrp-llama31-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key pawankrd-cosmosrp-llama31-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key pawankrd-cosmosrp-llama31-v2_reward/config.json from bucket guanaco-reward-models
Deleting key pawankrd-cosmosrp-llama31-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key pawankrd-cosmosrp-llama31-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key pawankrd-cosmosrp-llama31-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key pawankrd-cosmosrp-llama31-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key pawankrd-cosmosrp-llama31-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key pawankrd-cosmosrp-llama31-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.54s
pawankrd-cosmosrp-llama31_v2 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics