developer_uid: robert_irvine
submission_id: chaiml-sao10k-l3-rp-v3-3_v17
model_name: chaiml-sao10k-l3-rp-v3-3_v17
model_group: ChaiML/sao10k-l3-rp-v3-3
status: torndown
timestamp: 2024-07-11T17:35:48+00:00
num_battles: 37784
num_wins: 20366
celo_rating: 1217.11
family_friendly_score: 0.0
submission_type: basic
model_repo: ChaiML/sao10k-l3-rp-v3-3
model_architecture: LlamaForCausalLM
reward_repo: ChaiML/gpt2_xl_pairwise_89m_step_347634
model_num_parameters: 8030261248.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
display_name: chaiml-sao10k-l3-rp-v3-3_v17
is_internal_developer: True
language_model: ChaiML/sao10k-l3-rp-v3-3
model_size: 8B
ranking_group: single
us_pacific_date: 2024-07-11
win_ratio: 0.5390112216811349
generation_params: {'temperature': 0.95, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|end_header_id|>,', '<|eot_id|>,', '\n\n{user_name}'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': "<|begin_of_text|><|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|>system<|end_header_id|>\n\nrespond verbosely<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}:', 'truncate_by_message': False}
reward_formatter: {'bot_template': 'Bot: {message}\n', 'memory_template': '""', 'prompt_template': '""', 'response_template': 'Bot:', 'truncate_by_message': False, 'user_template': 'User: {message}\n'}
Resubmit model
Running pipeline stage MKMLizer
Starting job with name chaiml-sao10k-l3-rp-v3-3-v17-mkmlizer
Waiting for job on chaiml-sao10k-l3-rp-v3-3-v17-mkmlizer to finish
chaiml-sao10k-l3-rp-v3-3-v17-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-sao10k-l3-rp-v3-3-v17-mkmlizer: ║     _____            __           __                                ║
chaiml-sao10k-l3-rp-v3-3-v17-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-sao10k-l3-rp-v3-3-v17-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-sao10k-l3-rp-v3-3-v17-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-sao10k-l3-rp-v3-3-v17-mkmlizer: ║       /___/                                                         ║
chaiml-sao10k-l3-rp-v3-3-v17-mkmlizer: ║                                                                     ║
chaiml-sao10k-l3-rp-v3-3-v17-mkmlizer: ║  Version: 0.8.14                                                    ║
chaiml-sao10k-l3-rp-v3-3-v17-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-sao10k-l3-rp-v3-3-v17-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-sao10k-l3-rp-v3-3-v17-mkmlizer: ║                                                                     ║
chaiml-sao10k-l3-rp-v3-3-v17-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-sao10k-l3-rp-v3-3-v17-mkmlizer: ║  belonging to:                                                      ║
chaiml-sao10k-l3-rp-v3-3-v17-mkmlizer: ║                                                                     ║
chaiml-sao10k-l3-rp-v3-3-v17-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-sao10k-l3-rp-v3-3-v17-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-sao10k-l3-rp-v3-3-v17-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
chaiml-sao10k-l3-rp-v3-3-v17-mkmlizer: ║                                                                     ║
chaiml-sao10k-l3-rp-v3-3-v17-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
chaiml-sao10k-l3-rp-v3-3-v17-mkmlizer: Downloaded to shared memory in 24.869s
chaiml-sao10k-l3-rp-v3-3-v17-mkmlizer: quantizing model to /dev/shm/model_cache
chaiml-sao10k-l3-rp-v3-3-v17-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-sao10k-l3-rp-v3-3-v17-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/291 [00:05<13:19,  2.77s/it]
Loading 0:   5%|▍         | 14/291 [00:05<01:22,  3.36it/s]
Loading 0:   9%|▉         | 27/291 [00:05<00:34,  7.73it/s]
Loading 0:  14%|█▍        | 41/291 [00:05<00:18, 13.85it/s]
Loading 0:  19%|█▉        | 55/291 [00:05<00:10, 21.69it/s]
Loading 0:  23%|██▎       | 67/291 [00:06<00:10, 22.23it/s]
Loading 0:  27%|██▋       | 78/291 [00:06<00:07, 29.04it/s]
Loading 0:  32%|███▏      | 94/291 [00:06<00:04, 41.85it/s]
Loading 0:  36%|███▌      | 105/291 [00:06<00:03, 48.91it/s]
Loading 0:  42%|████▏     | 121/291 [00:06<00:02, 64.17it/s]
Loading 0:  46%|████▌     | 133/291 [00:07<00:02, 72.67it/s]
Loading 0:  51%|█████     | 148/291 [00:07<00:01, 87.00it/s]
Loading 0:  55%|█████▌    | 161/291 [00:07<00:01, 94.22it/s]
Loading 0:  60%|█████▉    | 174/291 [00:07<00:02, 55.29it/s]
Loading 0:  64%|██████▎   | 185/291 [00:07<00:01, 62.72it/s]
Loading 0:  67%|██████▋   | 195/291 [00:07<00:01, 66.79it/s]
Loading 0:  73%|███████▎  | 211/291 [00:08<00:00, 84.01it/s]
Loading 0:  76%|███████▋  | 222/291 [00:08<00:00, 87.88it/s]
Loading 0:  82%|████████▏ | 238/291 [00:08<00:00, 103.30it/s]
Loading 0:  86%|████████▋ | 251/291 [00:08<00:00, 107.01it/s]
Loading 0:  91%|█████████ | 265/291 [00:08<00:00, 113.80it/s]
Loading 0:  96%|█████████▌| 278/291 [00:09<00:00, 57.15it/s] 
Loading 0:  99%|█████████▉| 289/291 [00:09<00:00, 65.06it/s]
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
chaiml-sao10k-l3-rp-v3-3-v17-mkmlizer: quantized model in 29.116s
chaiml-sao10k-l3-rp-v3-3-v17-mkmlizer: Processed model ChaiML/sao10k-l3-rp-v3-3 in 53.986s
chaiml-sao10k-l3-rp-v3-3-v17-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v17/tokenizer.json
chaiml-sao10k-l3-rp-v3-3-v17-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v17/flywheel_model.0.safetensors
chaiml-sao10k-l3-rp-v3-3-v17-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
chaiml-sao10k-l3-rp-v3-3-v17-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.
chaiml-sao10k-l3-rp-v3-3-v17-mkmlizer:   warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v17-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`.
chaiml-sao10k-l3-rp-v3-3-v17-mkmlizer:   warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v17-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.
chaiml-sao10k-l3-rp-v3-3-v17-mkmlizer:   warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v17-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.
chaiml-sao10k-l3-rp-v3-3-v17-mkmlizer:   warnings.warn(
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
chaiml-sao10k-l3-rp-v3-3-v17-mkmlizer: 
Downloading shards:   0%|          | 0/2 [00:00<?, ?it/s]
Downloading shards:  50%|█████     | 1/2 [00:06<00:06,  6.49s/it]
Downloading shards: 100%|██████████| 2/2 [00:11<00:00,  5.80s/it]
Downloading shards: 100%|██████████| 2/2 [00:11<00:00,  5.90s/it]
chaiml-sao10k-l3-rp-v3-3-v17-mkmlizer: 
Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/s]
Loading checkpoint shards:  50%|█████     | 1/2 [00:00<00:00,  1.65it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00,  2.69it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00,  2.45it/s]
chaiml-sao10k-l3-rp-v3-3-v17-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
chaiml-sao10k-l3-rp-v3-3-v17-mkmlizer: Saving duration: 2.148s
chaiml-sao10k-l3-rp-v3-3-v17-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 16.378s
chaiml-sao10k-l3-rp-v3-3-v17-mkmlizer: creating bucket guanaco-reward-models
chaiml-sao10k-l3-rp-v3-3-v17-mkmlizer: Bucket 's3://guanaco-reward-models/' created
chaiml-sao10k-l3-rp-v3-3-v17-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v17_reward
chaiml-sao10k-l3-rp-v3-3-v17-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v17_reward/special_tokens_map.json
chaiml-sao10k-l3-rp-v3-3-v17-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v17_reward/merges.txt
chaiml-sao10k-l3-rp-v3-3-v17-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v17_reward/config.json
chaiml-sao10k-l3-rp-v3-3-v17-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v17_reward/vocab.json
chaiml-sao10k-l3-rp-v3-3-v17-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v17_reward/tokenizer.json
chaiml-sao10k-l3-rp-v3-3-v17-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v17_reward/tokenizer_config.json
chaiml-sao10k-l3-rp-v3-3-v17-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v17_reward/reward.tensors
Job chaiml-sao10k-l3-rp-v3-3-v17-mkmlizer completed after 104.56s with status: succeeded
Stopping job with name chaiml-sao10k-l3-rp-v3-3-v17-mkmlizer
Pipeline stage MKMLizer completed in 105.46s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service chaiml-sao10k-l3-rp-v3-3-v17
Waiting for inference service chaiml-sao10k-l3-rp-v3-3-v17 to be ready
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Inference service chaiml-sao10k-l3-rp-v3-3-v17 ready after 40.259357929229736s
Pipeline stage ISVCDeployer completed in 47.17s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.054561138153076s
Received healthy response to inference request in 1.2898178100585938s
Received healthy response to inference request in 1.298661470413208s
Received healthy response to inference request in 1.281597375869751s
Received healthy response to inference request in 1.2694854736328125s
5 requests
0 failed requests
5th percentile: 1.2719078540802002
10th percentile: 1.274330234527588
20th percentile: 1.2791749954223632
30th percentile: 1.2832414627075195
40th percentile: 1.2865296363830567
50th percentile: 1.2898178100585938
60th percentile: 1.2933552742004395
70th percentile: 1.2968927383422852
80th percentile: 1.4498414039611818
90th percentile: 1.752201271057129
95th percentile: 1.9033812046051024
99th percentile: 2.0243251514434815
mean time: 1.4388246536254883
Pipeline stage StressChecker completed in 7.92s
chaiml-sao10k-l3-rp-v3-3_v17 status is now deployed due to DeploymentManager action
chaiml-sao10k-l3-rp-v3-3_v17 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of chaiml-sao10k-l3-rp-v3-3_v17
Running pipeline stage ISVCDeleter
Checking if service chaiml-sao10k-l3-rp-v3-3-v17 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 5.06s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key chaiml-sao10k-l3-rp-v3-3-v17/config.json from bucket guanaco-mkml-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v17/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v17/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v17/tokenizer.json from bucket guanaco-mkml-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v17/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key chaiml-sao10k-l3-rp-v3-3-v17_reward/config.json from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v17_reward/merges.txt from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v17_reward/reward.tensors from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v17_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v17_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v17_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v17_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.68s
chaiml-sao10k-l3-rp-v3-3_v17 status is now torndown due to DeploymentManager action