submission_id: pawankrd-cosmosrp-llama31-dpo_v3
developer_uid: PawanOsman
alignment_samples: 0
best_of: 16
celo_rating: 1262.52
display_name: cosmosrp-llama31-dpo
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-dpo
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: PawanKrd/cosmosrp-llama3
model_name: cosmosrp-llama31-dpo
model_num_parameters: 8030261248.0
model_repo: PawanKrd/cosmosrp-llama31-dpo
model_size: 8B
num_battles: 11383
num_wins: 6556
propriety_score: 0.7205731832139202
propriety_total_count: 977.0
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: 2024-07-26T19:06:22+00:00
us_pacific_date: 2024-07-26
win_ratio: 0.5759465870157252
Download Preference Data
Resubmit model
Running pipeline stage MKMLizer
Starting job with name pawankrd-cosmosrp-llama31-dpo-v3-mkmlizer
Waiting for job on pawankrd-cosmosrp-llama31-dpo-v3-mkmlizer to finish
pawankrd-cosmosrp-llama31-dpo-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
pawankrd-cosmosrp-llama31-dpo-v3-mkmlizer: ║ _____ __ __ ║
pawankrd-cosmosrp-llama31-dpo-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
pawankrd-cosmosrp-llama31-dpo-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
pawankrd-cosmosrp-llama31-dpo-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
pawankrd-cosmosrp-llama31-dpo-v3-mkmlizer: ║ /___/ ║
pawankrd-cosmosrp-llama31-dpo-v3-mkmlizer: ║ ║
pawankrd-cosmosrp-llama31-dpo-v3-mkmlizer: ║ Version: 0.9.7 ║
pawankrd-cosmosrp-llama31-dpo-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
pawankrd-cosmosrp-llama31-dpo-v3-mkmlizer: ║ https://mk1.ai ║
pawankrd-cosmosrp-llama31-dpo-v3-mkmlizer: ║ ║
pawankrd-cosmosrp-llama31-dpo-v3-mkmlizer: ║ The license key for the current software has been verified as ║
pawankrd-cosmosrp-llama31-dpo-v3-mkmlizer: ║ belonging to: ║
pawankrd-cosmosrp-llama31-dpo-v3-mkmlizer: ║ ║
pawankrd-cosmosrp-llama31-dpo-v3-mkmlizer: ║ Chai Research Corp. ║
pawankrd-cosmosrp-llama31-dpo-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
pawankrd-cosmosrp-llama31-dpo-v3-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
pawankrd-cosmosrp-llama31-dpo-v3-mkmlizer: ║ ║
pawankrd-cosmosrp-llama31-dpo-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
pawankrd-cosmosrp-llama31-dpo-v3-mkmlizer: Downloaded to shared memory in 21.047s
pawankrd-cosmosrp-llama31-dpo-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpu1j4w59j, device:0
pawankrd-cosmosrp-llama31-dpo-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
pawankrd-cosmosrp-llama31-dpo-v3-mkmlizer: quantized model in 25.914s
pawankrd-cosmosrp-llama31-dpo-v3-mkmlizer: Processed model PawanKrd/cosmosrp-llama31-dpo in 46.961s
pawankrd-cosmosrp-llama31-dpo-v3-mkmlizer: creating bucket guanaco-mkml-models
pawankrd-cosmosrp-llama31-dpo-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
pawankrd-cosmosrp-llama31-dpo-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/pawankrd-cosmosrp-llama31-dpo-v3
pawankrd-cosmosrp-llama31-dpo-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/pawankrd-cosmosrp-llama31-dpo-v3/config.json
pawankrd-cosmosrp-llama31-dpo-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/pawankrd-cosmosrp-llama31-dpo-v3/special_tokens_map.json
pawankrd-cosmosrp-llama31-dpo-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/pawankrd-cosmosrp-llama31-dpo-v3/tokenizer_config.json
pawankrd-cosmosrp-llama31-dpo-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/pawankrd-cosmosrp-llama31-dpo-v3/tokenizer.json
pawankrd-cosmosrp-llama31-dpo-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/pawankrd-cosmosrp-llama31-dpo-v3/flywheel_model.0.safetensors
pawankrd-cosmosrp-llama31-dpo-v3-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
pawankrd-cosmosrp-llama31-dpo-v3-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 2%|▏ | 5/291 [00:00<00:07, 36.55it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:04, 57.44it/s] Loading 0: 7%|▋ | 20/291 [00:00<00:04, 55.55it/s] Loading 0: 9%|▉ | 26/291 [00:00<00:04, 54.05it/s] Loading 0: 11%|█ | 32/291 [00:00<00:05, 45.59it/s] Loading 0: 14%|█▎ | 40/291 [00:00<00:04, 54.88it/s] Loading 0: 16%|█▌ | 46/291 [00:00<00:04, 50.81it/s] Loading 0: 18%|█▊ | 52/291 [00:01<00:04, 51.71it/s] Loading 0: 20%|██ | 59/291 [00:01<00:04, 46.61it/s] Loading 0: 23%|██▎ | 67/291 [00:01<00:04, 54.31it/s] Loading 0: 25%|██▌ | 73/291 [00:01<00:04, 50.55it/s] Loading 0: 27%|██▋ | 79/291 [00:01<00:04, 50.74it/s] Loading 0: 29%|██▉ | 85/291 [00:01<00:05, 36.76it/s] Loading 0: 31%|███ | 90/291 [00:01<00:05, 38.40it/s] Loading 0: 33%|███▎ | 95/291 [00:02<00:05, 35.16it/s] Loading 0: 35%|███▌ | 103/291 [00:02<00:04, 43.30it/s] Loading 0: 37%|███▋ | 109/291 [00:02<00:04, 43.55it/s] Loading 0: 39%|███▉ | 114/291 [00:02<00:04, 44.04it/s] Loading 0: 42%|████▏ | 121/291 [00:02<00:03, 48.85it/s] Loading 0: 44%|████▎ | 127/291 [00:02<00:03, 45.44it/s] Loading 0: 45%|████▌ | 132/291 [00:02<00:03, 45.12it/s] Loading 0: 48%|████▊ | 139/291 [00:02<00:03, 49.75it/s] Loading 0: 50%|████▉ | 145/291 [00:03<00:03, 45.34it/s] Loading 0: 52%|█████▏ | 150/291 [00:03<00:03, 45.71it/s] Loading 0: 54%|█████▍ | 157/291 [00:03<00:02, 51.52it/s] Loading 0: 56%|█████▌ | 163/291 [00:03<00:02, 48.90it/s] Loading 0: 58%|█████▊ | 169/291 [00:03<00:02, 48.82it/s] Loading 0: 60%|██████ | 176/291 [00:03<00:02, 54.11it/s] Loading 0: 63%|██████▎ | 182/291 [00:03<00:02, 45.37it/s] Loading 0: 64%|██████▍ | 187/291 [00:04<00:02, 34.70it/s] Loading 0: 66%|██████▌ | 192/291 [00:04<00:02, 36.25it/s] Loading 0: 68%|██████▊ | 197/291 [00:04<00:02, 38.42it/s] Loading 0: 70%|██████▉ | 203/291 [00:04<00:02, 37.00it/s] Loading 0: 73%|███████▎ | 211/291 [00:04<00:01, 45.43it/s] Loading 0: 75%|███████▍ | 217/291 [00:04<00:01, 44.50it/s] Loading 0: 76%|███████▋ | 222/291 [00:04<00:01, 44.65it/s] Loading 0: 79%|███████▊ | 229/291 [00:05<00:01, 49.82it/s] Loading 0: 81%|████████ | 235/291 [00:05<00:01, 45.51it/s] Loading 0: 82%|████████▏ | 240/291 [00:05<00:01, 45.32it/s] Loading 0: 85%|████████▍ | 247/291 [00:05<00:00, 50.81it/s] Loading 0: 87%|████████▋ | 253/291 [00:05<00:00, 45.15it/s] Loading 0: 89%|████████▊ | 258/291 [00:05<00:00, 44.59it/s] Loading 0: 91%|█████████ | 265/291 [00:05<00:00, 49.88it/s] Loading 0: 93%|█████████▎| 271/291 [00:05<00:00, 47.93it/s] Loading 0: 95%|█████████▍| 276/291 [00:06<00:00, 46.00it/s] Loading 0: 97%|█████████▋| 282/291 [00:06<00:00, 42.86it/s] Loading 0: 99%|█████████▊| 287/291 [00:11<00:01, 3.26it/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-dpo-v3-mkmlizer: warnings.warn(
pawankrd-cosmosrp-llama31-dpo-v3-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-dpo-v3-mkmlizer: warnings.warn(
pawankrd-cosmosrp-llama31-dpo-v3-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py:469: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
pawankrd-cosmosrp-llama31-dpo-v3-mkmlizer: warnings.warn(
pawankrd-cosmosrp-llama31-dpo-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
pawankrd-cosmosrp-llama31-dpo-v3-mkmlizer: Saving duration: 1.375s
pawankrd-cosmosrp-llama31-dpo-v3-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 11.447s
pawankrd-cosmosrp-llama31-dpo-v3-mkmlizer: creating bucket guanaco-reward-models
pawankrd-cosmosrp-llama31-dpo-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
pawankrd-cosmosrp-llama31-dpo-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/pawankrd-cosmosrp-llama31-dpo-v3_reward
pawankrd-cosmosrp-llama31-dpo-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/pawankrd-cosmosrp-llama31-dpo-v3_reward/config.json
pawankrd-cosmosrp-llama31-dpo-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/pawankrd-cosmosrp-llama31-dpo-v3_reward/special_tokens_map.json
pawankrd-cosmosrp-llama31-dpo-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/pawankrd-cosmosrp-llama31-dpo-v3_reward/tokenizer_config.json
pawankrd-cosmosrp-llama31-dpo-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/pawankrd-cosmosrp-llama31-dpo-v3_reward/merges.txt
pawankrd-cosmosrp-llama31-dpo-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/pawankrd-cosmosrp-llama31-dpo-v3_reward/vocab.json
pawankrd-cosmosrp-llama31-dpo-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/pawankrd-cosmosrp-llama31-dpo-v3_reward/tokenizer.json
pawankrd-cosmosrp-llama31-dpo-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/pawankrd-cosmosrp-llama31-dpo-v3_reward/reward.tensors
Job pawankrd-cosmosrp-llama31-dpo-v3-mkmlizer completed after 95.37s with status: succeeded
Stopping job with name pawankrd-cosmosrp-llama31-dpo-v3-mkmlizer
Pipeline stage MKMLizer completed in 96.49s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service pawankrd-cosmosrp-llama31-dpo-v3
Waiting for inference service pawankrd-cosmosrp-llama31-dpo-v3 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service pawankrd-cosmosrp-llama31-dpo-v3 ready after 171.08928084373474s
Pipeline stage ISVCDeployer completed in 172.54s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3101279735565186s
Received healthy response to inference request in 1.627934455871582s
Received healthy response to inference request in 1.3658874034881592s
Received healthy response to inference request in 1.3392670154571533s
Received healthy response to inference request in 1.2907099723815918s
5 requests
0 failed requests
5th percentile: 1.300421380996704
10th percentile: 1.3101327896118165
20th percentile: 1.329555606842041
30th percentile: 1.3445910930633544
40th percentile: 1.355239248275757
50th percentile: 1.3658874034881592
60th percentile: 1.4707062244415283
70th percentile: 1.5755250453948975
80th percentile: 1.7643731594085694
90th percentile: 2.0372505664825438
95th percentile: 2.173689270019531
99th percentile: 2.282840232849121
mean time: 1.586785364151001
Pipeline stage StressChecker completed in 8.60s
pawankrd-cosmosrp-llama31-dpo_v3 status is now deployed due to DeploymentManager action
pawankrd-cosmosrp-llama31-dpo_v3 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of pawankrd-cosmosrp-llama31-dpo_v3
Running pipeline stage ISVCDeleter
Checking if service pawankrd-cosmosrp-llama31-dpo-v3 is running
Tearing down inference service pawankrd-cosmosrp-llama31-dpo-v3
Service pawankrd-cosmosrp-llama31-dpo-v3 has been torndown
Pipeline stage ISVCDeleter completed in 4.38s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key pawankrd-cosmosrp-llama31-dpo-v3/config.json from bucket guanaco-mkml-models
Deleting key pawankrd-cosmosrp-llama31-dpo-v3/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key pawankrd-cosmosrp-llama31-dpo-v3/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key pawankrd-cosmosrp-llama31-dpo-v3/tokenizer.json from bucket guanaco-mkml-models
Deleting key pawankrd-cosmosrp-llama31-dpo-v3/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key pawankrd-cosmosrp-llama31-dpo-v3_reward/config.json from bucket guanaco-reward-models
Deleting key pawankrd-cosmosrp-llama31-dpo-v3_reward/merges.txt from bucket guanaco-reward-models
Deleting key pawankrd-cosmosrp-llama31-dpo-v3_reward/reward.tensors from bucket guanaco-reward-models
Deleting key pawankrd-cosmosrp-llama31-dpo-v3_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key pawankrd-cosmosrp-llama31-dpo-v3_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key pawankrd-cosmosrp-llama31-dpo-v3_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key pawankrd-cosmosrp-llama31-dpo-v3_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.46s
pawankrd-cosmosrp-llama31-dpo_v3 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics