developer_uid: robert_irvine
submission_id: chaiml-sao10k-l3-rp-v3-3_v14
model_name: chaiml-sao10k-l3-rp-v3-3_v14
model_group: ChaiML/sao10k-l3-rp-v3-3
status: torndown
timestamp: 2024-07-11T17:29:50+00:00
num_battles: 38830
num_wins: 19788
celo_rating: 1197.14
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_v14
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: 0.5096059747617822
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 with kindness<|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-v14-mkmlizer
Waiting for job on chaiml-sao10k-l3-rp-v3-3-v14-mkmlizer to finish
chaiml-sao10k-l3-rp-v3-3-v14-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-sao10k-l3-rp-v3-3-v14-mkmlizer: ║     _____            __           __                                ║
chaiml-sao10k-l3-rp-v3-3-v14-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-sao10k-l3-rp-v3-3-v14-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-sao10k-l3-rp-v3-3-v14-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-sao10k-l3-rp-v3-3-v14-mkmlizer: ║       /___/                                                         ║
chaiml-sao10k-l3-rp-v3-3-v14-mkmlizer: ║                                                                     ║
chaiml-sao10k-l3-rp-v3-3-v14-mkmlizer: ║  Version: 0.8.14                                                    ║
chaiml-sao10k-l3-rp-v3-3-v14-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-sao10k-l3-rp-v3-3-v14-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-sao10k-l3-rp-v3-3-v14-mkmlizer: ║                                                                     ║
chaiml-sao10k-l3-rp-v3-3-v14-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-sao10k-l3-rp-v3-3-v14-mkmlizer: ║  belonging to:                                                      ║
chaiml-sao10k-l3-rp-v3-3-v14-mkmlizer: ║                                                                     ║
chaiml-sao10k-l3-rp-v3-3-v14-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-sao10k-l3-rp-v3-3-v14-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-sao10k-l3-rp-v3-3-v14-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
chaiml-sao10k-l3-rp-v3-3-v14-mkmlizer: ║                                                                     ║
chaiml-sao10k-l3-rp-v3-3-v14-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-sao10k-l3-rp-v3-3-v14-mkmlizer: Downloaded to shared memory in 26.825s
chaiml-sao10k-l3-rp-v3-3-v14-mkmlizer: quantizing model to /dev/shm/model_cache
chaiml-sao10k-l3-rp-v3-3-v14-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-sao10k-l3-rp-v3-3-v14-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/291 [00:05<13:12,  2.74s/it]
Loading 0:   5%|▍         | 14/291 [00:05<01:21,  3.39it/s]
Loading 0:  10%|▉         | 29/291 [00:05<00:30,  8.50it/s]
Loading 0:  14%|█▍        | 41/291 [00:05<00:18, 13.77it/s]
Loading 0:  19%|█▉        | 56/291 [00:05<00:10, 22.40it/s]
Loading 0:  24%|██▎       | 69/291 [00:06<00:09, 23.73it/s]
Loading 0:  29%|██▉       | 85/291 [00:06<00:05, 34.74it/s]
Loading 0:  33%|███▎      | 96/291 [00:06<00:04, 42.25it/s]
Loading 0:  38%|███▊      | 112/291 [00:06<00:03, 56.78it/s]
Loading 0:  43%|████▎     | 124/291 [00:06<00:02, 64.39it/s]
Loading 0:  47%|████▋     | 136/291 [00:06<00:02, 71.48it/s]
Loading 0:  51%|█████     | 148/291 [00:07<00:01, 79.28it/s]
Loading 0:  55%|█████▍    | 159/291 [00:07<00:01, 82.72it/s]
Loading 0:  58%|█████▊    | 170/291 [00:07<00:02, 49.41it/s]
Loading 0:  63%|██████▎   | 184/291 [00:07<00:01, 60.27it/s]
Loading 0:  67%|██████▋   | 195/291 [00:07<00:01, 66.36it/s]
Loading 0:  73%|███████▎  | 211/291 [00:08<00:00, 82.29it/s]
Loading 0:  76%|███████▋  | 222/291 [00:08<00:00, 82.56it/s]
Loading 0:  80%|████████  | 234/291 [00:08<00:00, 90.01it/s]
Loading 0:  85%|████████▌ | 248/291 [00:08<00:00, 94.23it/s]
Loading 0:  89%|████████▉ | 259/291 [00:08<00:00, 93.82it/s]
Loading 0:  93%|█████████▎| 270/291 [00:08<00:00, 54.03it/s]
Loading 0:  98%|█████████▊| 284/291 [00:09<00:00, 66.13it/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-v14-mkmlizer: quantized model in 29.044s
chaiml-sao10k-l3-rp-v3-3-v14-mkmlizer: Processed model ChaiML/sao10k-l3-rp-v3-3 in 55.869s
chaiml-sao10k-l3-rp-v3-3-v14-mkmlizer: creating bucket guanaco-mkml-models
chaiml-sao10k-l3-rp-v3-3-v14-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-sao10k-l3-rp-v3-3-v14-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v14
chaiml-sao10k-l3-rp-v3-3-v14-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v14/config.json
chaiml-sao10k-l3-rp-v3-3-v14-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v14/tokenizer_config.json
chaiml-sao10k-l3-rp-v3-3-v14-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v14/special_tokens_map.json
chaiml-sao10k-l3-rp-v3-3-v14-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v14/tokenizer.json
chaiml-sao10k-l3-rp-v3-3-v14-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v14/flywheel_model.0.safetensors
chaiml-sao10k-l3-rp-v3-3-v14-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
chaiml-sao10k-l3-rp-v3-3-v14-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-v14-mkmlizer:   warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v14-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-v14-mkmlizer:   warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v14-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-v14-mkmlizer:   warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v14-mkmlizer: 
Downloading shards:   0%|          | 0/2 [00:00<?, ?it/s]
Downloading shards:  50%|█████     | 1/2 [00:06<00:06,  6.41s/it]
Downloading shards: 100%|██████████| 2/2 [00:11<00:00,  5.73s/it]
Downloading shards: 100%|██████████| 2/2 [00:11<00:00,  5.84s/it]
chaiml-sao10k-l3-rp-v3-3-v14-mkmlizer: 
Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/s]
Loading checkpoint shards:  50%|█████     | 1/2 [00:00<00:00,  1.61it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00,  2.63it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00,  2.40it/s]
chaiml-sao10k-l3-rp-v3-3-v14-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
chaiml-sao10k-l3-rp-v3-3-v14-mkmlizer: Saving duration: 2.170s
chaiml-sao10k-l3-rp-v3-3-v14-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 16.129s
chaiml-sao10k-l3-rp-v3-3-v14-mkmlizer: creating bucket guanaco-reward-models
chaiml-sao10k-l3-rp-v3-3-v14-mkmlizer: Bucket 's3://guanaco-reward-models/' created
chaiml-sao10k-l3-rp-v3-3-v14-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v14_reward
chaiml-sao10k-l3-rp-v3-3-v14-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v14_reward/config.json
chaiml-sao10k-l3-rp-v3-3-v14-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v14_reward/tokenizer_config.json
chaiml-sao10k-l3-rp-v3-3-v14-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v14_reward/special_tokens_map.json
chaiml-sao10k-l3-rp-v3-3-v14-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v14_reward/merges.txt
chaiml-sao10k-l3-rp-v3-3-v14-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v14_reward/vocab.json
chaiml-sao10k-l3-rp-v3-3-v14-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v14_reward/tokenizer.json
chaiml-sao10k-l3-rp-v3-3-v14-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v14_reward/reward.tensors
Job chaiml-sao10k-l3-rp-v3-3-v14-mkmlizer completed after 95.11s with status: succeeded
Stopping job with name chaiml-sao10k-l3-rp-v3-3-v14-mkmlizer
Pipeline stage MKMLizer completed in 96.04s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.13s
Running pipeline stage ISVCDeployer
Creating inference service chaiml-sao10k-l3-rp-v3-3-v14
Waiting for inference service chaiml-sao10k-l3-rp-v3-3-v14 to be ready
Inference service chaiml-sao10k-l3-rp-v3-3-v14 ready after 40.24906277656555s
Pipeline stage ISVCDeployer completed in 47.03s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.965602159500122s
Received healthy response to inference request in 1.2579591274261475s
Received healthy response to inference request in 1.2782056331634521s
Received healthy response to inference request in 1.2454218864440918s
Received healthy response to inference request in 1.2989532947540283s
5 requests
0 failed requests
5th percentile: 1.247929334640503
10th percentile: 1.250436782836914
20th percentile: 1.2554516792297363
30th percentile: 1.2620084285736084
40th percentile: 1.2701070308685303
50th percentile: 1.2782056331634521
60th percentile: 1.2865046977996826
70th percentile: 1.294803762435913
80th percentile: 1.4322830677032472
90th percentile: 1.6989426136016847
95th percentile: 1.8322723865509032
99th percentile: 1.9389362049102783
mean time: 1.4092284202575684
Pipeline stage StressChecker completed in 7.77s
chaiml-sao10k-l3-rp-v3-3_v14 status is now deployed due to DeploymentManager action
chaiml-sao10k-l3-rp-v3-3_v14 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of chaiml-sao10k-l3-rp-v3-3_v14
Running pipeline stage ISVCDeleter
Checking if service chaiml-sao10k-l3-rp-v3-3-v14 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.09s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key chaiml-sao10k-l3-rp-v3-3-v14/config.json from bucket guanaco-mkml-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v14/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v14/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v14/tokenizer.json from bucket guanaco-mkml-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v14/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key chaiml-sao10k-l3-rp-v3-3-v14_reward/config.json from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v14_reward/merges.txt from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v14_reward/reward.tensors from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v14_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v14_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v14_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v14_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.32s
chaiml-sao10k-l3-rp-v3-3_v14 status is now torndown due to DeploymentManager action