submission_id: pawankrd-cosmosrp-llama31-dpo_v1
developer_uid: PawanOsman
alignment_samples: 0
best_of: 16
celo_rating: 1268.14
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': 1.0, '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: 11697
num_wins: 6841
propriety_score: 0.7198515769944341
propriety_total_count: 1078.0
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: 2024-07-26T19:05:40+00:00
us_pacific_date: 2024-07-26
win_ratio: 0.5848508164486621
Download Preference Data
Resubmit model
Running pipeline stage MKMLizer
Starting job with name pawankrd-cosmosrp-llama31-dpo-v1-mkmlizer
Waiting for job on pawankrd-cosmosrp-llama31-dpo-v1-mkmlizer to finish
pawankrd-cosmosrp-llama31-dpo-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
pawankrd-cosmosrp-llama31-dpo-v1-mkmlizer: ║ _____ __ __ ║
pawankrd-cosmosrp-llama31-dpo-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
pawankrd-cosmosrp-llama31-dpo-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
pawankrd-cosmosrp-llama31-dpo-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
pawankrd-cosmosrp-llama31-dpo-v1-mkmlizer: ║ /___/ ║
pawankrd-cosmosrp-llama31-dpo-v1-mkmlizer: ║ ║
pawankrd-cosmosrp-llama31-dpo-v1-mkmlizer: ║ Version: 0.9.7 ║
pawankrd-cosmosrp-llama31-dpo-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
pawankrd-cosmosrp-llama31-dpo-v1-mkmlizer: ║ https://mk1.ai ║
pawankrd-cosmosrp-llama31-dpo-v1-mkmlizer: ║ ║
pawankrd-cosmosrp-llama31-dpo-v1-mkmlizer: ║ The license key for the current software has been verified as ║
pawankrd-cosmosrp-llama31-dpo-v1-mkmlizer: ║ belonging to: ║
pawankrd-cosmosrp-llama31-dpo-v1-mkmlizer: ║ ║
pawankrd-cosmosrp-llama31-dpo-v1-mkmlizer: ║ Chai Research Corp. ║
pawankrd-cosmosrp-llama31-dpo-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
pawankrd-cosmosrp-llama31-dpo-v1-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
pawankrd-cosmosrp-llama31-dpo-v1-mkmlizer: ║ ║
pawankrd-cosmosrp-llama31-dpo-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
pawankrd-cosmosrp-llama31-dpo-v1-mkmlizer: Downloaded to shared memory in 31.895s
pawankrd-cosmosrp-llama31-dpo-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpx_skp1m4, device:0
pawankrd-cosmosrp-llama31-dpo-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
pawankrd-cosmosrp-llama31-dpo-v1-mkmlizer: quantized model in 26.186s
pawankrd-cosmosrp-llama31-dpo-v1-mkmlizer: Processed model PawanKrd/cosmosrp-llama31-dpo in 58.082s
pawankrd-cosmosrp-llama31-dpo-v1-mkmlizer: creating bucket guanaco-mkml-models
pawankrd-cosmosrp-llama31-dpo-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
pawankrd-cosmosrp-llama31-dpo-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/pawankrd-cosmosrp-llama31-dpo-v1
pawankrd-cosmosrp-llama31-dpo-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/pawankrd-cosmosrp-llama31-dpo-v1/config.json
pawankrd-cosmosrp-llama31-dpo-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/pawankrd-cosmosrp-llama31-dpo-v1/special_tokens_map.json
pawankrd-cosmosrp-llama31-dpo-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/pawankrd-cosmosrp-llama31-dpo-v1/tokenizer_config.json
pawankrd-cosmosrp-llama31-dpo-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/pawankrd-cosmosrp-llama31-dpo-v1/tokenizer.json
pawankrd-cosmosrp-llama31-dpo-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/pawankrd-cosmosrp-llama31-dpo-v1/flywheel_model.0.safetensors
pawankrd-cosmosrp-llama31-dpo-v1-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
pawankrd-cosmosrp-llama31-dpo-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 2%|▏ | 5/291 [00:00<00:08, 33.23it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:05, 54.12it/s] Loading 0: 7%|▋ | 19/291 [00:00<00:05, 46.74it/s] Loading 0: 8%|▊ | 24/291 [00:00<00:05, 45.44it/s] Loading 0: 11%|█ | 31/291 [00:00<00:05, 51.82it/s] Loading 0: 13%|█▎ | 37/291 [00:00<00:05, 48.04it/s] Loading 0: 14%|█▍ | 42/291 [00:00<00:05, 47.59it/s] Loading 0: 17%|█▋ | 49/291 [00:00<00:04, 53.78it/s] Loading 0: 19%|█▉ | 55/291 [00:01<00:04, 49.02it/s] Loading 0: 21%|██ | 61/291 [00:01<00:04, 50.12it/s] Loading 0: 23%|██▎ | 67/291 [00:01<00:04, 52.61it/s] Loading 0: 25%|██▌ | 73/291 [00:01<00:04, 47.99it/s] Loading 0: 27%|██▋ | 78/291 [00:01<00:04, 47.36it/s] Loading 0: 29%|██▊ | 83/291 [00:01<00:06, 33.44it/s] Loading 0: 30%|██▉ | 87/291 [00:01<00:06, 33.21it/s] Loading 0: 32%|███▏ | 94/291 [00:02<00:04, 40.85it/s] Loading 0: 34%|███▍ | 100/291 [00:02<00:04, 41.09it/s] Loading 0: 36%|███▌ | 105/291 [00:02<00:04, 42.04it/s] Loading 0: 38%|███▊ | 112/291 [00:02<00:03, 47.90it/s] Loading 0: 41%|████ | 118/291 [00:02<00:03, 45.96it/s] Loading 0: 42%|████▏ | 123/291 [00:02<00:03, 45.56it/s] Loading 0: 45%|████▍ | 130/291 [00:02<00:03, 49.47it/s] Loading 0: 47%|████▋ | 136/291 [00:02<00:03, 47.13it/s] Loading 0: 48%|████▊ | 141/291 [00:03<00:03, 46.90it/s] Loading 0: 51%|█████ | 148/291 [00:03<00:02, 51.75it/s] Loading 0: 53%|█████▎ | 154/291 [00:03<00:02, 48.09it/s] Loading 0: 55%|█████▍ | 159/291 [00:03<00:02, 46.71it/s] Loading 0: 57%|█████▋ | 165/291 [00:03<00:02, 48.17it/s] Loading 0: 58%|█████▊ | 170/291 [00:03<00:02, 48.13it/s] Loading 0: 61%|██████ | 177/291 [00:03<00:02, 46.94it/s] Loading 0: 63%|██████▎ | 182/291 [00:03<00:02, 45.62it/s] Loading 0: 64%|██████▍ | 187/291 [00:04<00:03, 34.30it/s] Loading 0: 66%|██████▌ | 192/291 [00:04<00:02, 36.43it/s] Loading 0: 67%|██████▋ | 196/291 [00:04<00:02, 37.03it/s] Loading 0: 69%|██████▉ | 202/291 [00:04<00:02, 41.44it/s] Loading 0: 71%|███████▏ | 208/291 [00:04<00:01, 41.57it/s] Loading 0: 73%|███████▎ | 213/291 [00:04<00:01, 42.11it/s] Loading 0: 76%|███████▌ | 220/291 [00:04<00:01, 48.23it/s] Loading 0: 78%|███████▊ | 226/291 [00:05<00:01, 45.49it/s] Loading 0: 79%|███████▉ | 231/291 [00:05<00:01, 45.67it/s] Loading 0: 82%|████████▏ | 238/291 [00:05<00:01, 50.63it/s] Loading 0: 84%|████████▍ | 244/291 [00:05<00:00, 47.59it/s] Loading 0: 86%|████████▌ | 249/291 [00:05<00:00, 46.31it/s] Loading 0: 88%|████████▊ | 256/291 [00:05<00:00, 51.57it/s] Loading 0: 90%|█████████ | 262/291 [00:05<00:00, 47.41it/s] Loading 0: 92%|█████████▏| 267/291 [00:05<00:00, 46.47it/s] Loading 0: 94%|█████████▍| 274/291 [00:05<00:00, 51.66it/s] Loading 0: 96%|█████████▌| 280/291 [00:06<00:00, 47.78it/s] Loading 0: 98%|█████████▊| 285/291 [00:06<00:00, 46.66it/s] Loading 0: 100%|█████████▉| 290/291 [00:11<00:00, 3.21it/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-v1-mkmlizer: warnings.warn(
pawankrd-cosmosrp-llama31-dpo-v1-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-v1-mkmlizer: warnings.warn(
pawankrd-cosmosrp-llama31-dpo-v1-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-v1-mkmlizer: warnings.warn(
pawankrd-cosmosrp-llama31-dpo-v1-mkmlizer: Saving duration: 1.391s
pawankrd-cosmosrp-llama31-dpo-v1-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 11.179s
pawankrd-cosmosrp-llama31-dpo-v1-mkmlizer: creating bucket guanaco-reward-models
pawankrd-cosmosrp-llama31-dpo-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
pawankrd-cosmosrp-llama31-dpo-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/pawankrd-cosmosrp-llama31-dpo-v1_reward
pawankrd-cosmosrp-llama31-dpo-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/pawankrd-cosmosrp-llama31-dpo-v1_reward/config.json
pawankrd-cosmosrp-llama31-dpo-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/pawankrd-cosmosrp-llama31-dpo-v1_reward/special_tokens_map.json
pawankrd-cosmosrp-llama31-dpo-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/pawankrd-cosmosrp-llama31-dpo-v1_reward/tokenizer_config.json
pawankrd-cosmosrp-llama31-dpo-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/pawankrd-cosmosrp-llama31-dpo-v1_reward/merges.txt
pawankrd-cosmosrp-llama31-dpo-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/pawankrd-cosmosrp-llama31-dpo-v1_reward/vocab.json
pawankrd-cosmosrp-llama31-dpo-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/pawankrd-cosmosrp-llama31-dpo-v1_reward/tokenizer.json
pawankrd-cosmosrp-llama31-dpo-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/pawankrd-cosmosrp-llama31-dpo-v1_reward/reward.tensors
Connection pool is full, discarding connection: %s. Connection pool size: %s
Job pawankrd-cosmosrp-llama31-dpo-v1-mkmlizer completed after 105.68s with status: succeeded
Stopping job with name pawankrd-cosmosrp-llama31-dpo-v1-mkmlizer
Pipeline stage MKMLizer completed in 106.82s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.13s
Running pipeline stage ISVCDeployer
Creating inference service pawankrd-cosmosrp-llama31-dpo-v1
Waiting for inference service pawankrd-cosmosrp-llama31-dpo-v1 to be ready
Inference service pawankrd-cosmosrp-llama31-dpo-v1 ready after 80.54728150367737s
Pipeline stage ISVCDeployer completed in 82.21s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.10404896736145s
Received healthy response to inference request in 1.398162841796875s
Received healthy response to inference request in 1.364483118057251s
Received healthy response to inference request in 1.343163251876831s
Received healthy response to inference request in 1.285146951675415s
5 requests
0 failed requests
5th percentile: 1.2967502117156982
10th percentile: 1.3083534717559815
20th percentile: 1.331559991836548
30th percentile: 1.3474272251129151
40th percentile: 1.355955171585083
50th percentile: 1.364483118057251
60th percentile: 1.3779550075531006
70th percentile: 1.3914268970489503
80th percentile: 1.53934006690979
90th percentile: 1.8216945171356203
95th percentile: 1.9628717422485351
99th percentile: 2.075813522338867
mean time: 1.4990010261535645
Pipeline stage StressChecker completed in 8.50s
pawankrd-cosmosrp-llama31-dpo_v1 status is now deployed due to DeploymentManager action
pawankrd-cosmosrp-llama31-dpo_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of pawankrd-cosmosrp-llama31-dpo_v1
Running pipeline stage ISVCDeleter
Checking if service pawankrd-cosmosrp-llama31-dpo-v1 is running
Tearing down inference service pawankrd-cosmosrp-llama31-dpo-v1
Service pawankrd-cosmosrp-llama31-dpo-v1 has been torndown
Pipeline stage ISVCDeleter completed in 5.12s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key pawankrd-cosmosrp-llama31-dpo-v1/config.json from bucket guanaco-mkml-models
Deleting key pawankrd-cosmosrp-llama31-dpo-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key pawankrd-cosmosrp-llama31-dpo-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key pawankrd-cosmosrp-llama31-dpo-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key pawankrd-cosmosrp-llama31-dpo-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key pawankrd-cosmosrp-llama31-dpo-v1_reward/config.json from bucket guanaco-reward-models
Deleting key pawankrd-cosmosrp-llama31-dpo-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key pawankrd-cosmosrp-llama31-dpo-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key pawankrd-cosmosrp-llama31-dpo-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key pawankrd-cosmosrp-llama31-dpo-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key pawankrd-cosmosrp-llama31-dpo-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key pawankrd-cosmosrp-llama31-dpo-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.45s
pawankrd-cosmosrp-llama31-dpo_v1 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics