chaiml-sao10k-l3-rp-v3-3

developer_uid: robert_irvine

submission_id: chaiml-sao10k-l3-rp-v3-3_v87

model_name: chaiml-sao10k-l3-rp-v3-3_v87

model_group: ChaiML/sao10k-l3-rp-v3-3

status: torndown

timestamp: 2024-08-05T02:00:26+00:00

num_battles: 179692

num_wins: 88487

celo_rating: 1156.43

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: 1

max_input_tokens: 512

max_output_tokens: 64

display_name: chaiml-sao10k-l3-rp-v3-3_v87

is_internal_developer: True

language_model: ChaiML/sao10k-l3-rp-v3-3

model_size: 8B

ranking_group: single

us_pacific_date: 2024-08-04

win_ratio: 0.49243705896756673

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': 512, 'best_of': 1, 'max_output_tokens': 64, 'reward_max_token_input': 256}

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|>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-v87-mkmlizer
Waiting for job on chaiml-sao10k-l3-rp-v3-3-v87-mkmlizer to finish
chaiml-sao10k-l3-rp-v3-3-v87-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-sao10k-l3-rp-v3-3-v87-mkmlizer: ║     _____            __           __                                ║
chaiml-sao10k-l3-rp-v3-3-v87-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-sao10k-l3-rp-v3-3-v87-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-sao10k-l3-rp-v3-3-v87-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-sao10k-l3-rp-v3-3-v87-mkmlizer: ║       /___/                                                         ║
chaiml-sao10k-l3-rp-v3-3-v87-mkmlizer: ║                                                                     ║
chaiml-sao10k-l3-rp-v3-3-v87-mkmlizer: ║  Version: 0.9.9                                                     ║
chaiml-sao10k-l3-rp-v3-3-v87-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-sao10k-l3-rp-v3-3-v87-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-sao10k-l3-rp-v3-3-v87-mkmlizer: ║                                                                     ║
chaiml-sao10k-l3-rp-v3-3-v87-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-sao10k-l3-rp-v3-3-v87-mkmlizer: ║  belonging to:                                                      ║
chaiml-sao10k-l3-rp-v3-3-v87-mkmlizer: ║                                                                     ║
chaiml-sao10k-l3-rp-v3-3-v87-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-sao10k-l3-rp-v3-3-v87-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-sao10k-l3-rp-v3-3-v87-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
chaiml-sao10k-l3-rp-v3-3-v87-mkmlizer: ║                                                                     ║
chaiml-sao10k-l3-rp-v3-3-v87-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-sao10k-l3-rp-v3-3-v87-mkmlizer: Downloaded to shared memory in 25.283s
chaiml-sao10k-l3-rp-v3-3-v87-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpwy4135n9, device:0
chaiml-sao10k-l3-rp-v3-3-v87-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-sao10k-l3-rp-v3-3-v87-mkmlizer: quantized model in 26.858s
chaiml-sao10k-l3-rp-v3-3-v87-mkmlizer: Processed model ChaiML/sao10k-l3-rp-v3-3 in 52.141s
chaiml-sao10k-l3-rp-v3-3-v87-mkmlizer: creating bucket guanaco-mkml-models
chaiml-sao10k-l3-rp-v3-3-v87-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-sao10k-l3-rp-v3-3-v87-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v87
chaiml-sao10k-l3-rp-v3-3-v87-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v87/special_tokens_map.json
chaiml-sao10k-l3-rp-v3-3-v87-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v87/config.json
chaiml-sao10k-l3-rp-v3-3-v87-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v87/tokenizer_config.json
chaiml-sao10k-l3-rp-v3-3-v87-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v87/tokenizer.json
chaiml-sao10k-l3-rp-v3-3-v87-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v87/flywheel_model.0.safetensors
chaiml-sao10k-l3-rp-v3-3-v87-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
chaiml-sao10k-l3-rp-v3-3-v87-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/291 [00:04<11:37,  2.41s/it]
Loading 0:   2%|▏         | 6/291 [00:04<03:05,  1.54it/s]
Loading 0:   4%|▍         | 13/291 [00:05<01:06,  4.20it/s]
Loading 0:   7%|▋         | 19/291 [00:05<00:38,  7.12it/s]
Loading 0:   8%|▊         | 24/291 [00:05<00:27,  9.62it/s]
Loading 0:  11%|█         | 32/291 [00:05<00:16, 15.58it/s]
Loading 0:  13%|█▎        | 38/291 [00:05<00:13, 19.37it/s]
Loading 0:  15%|█▍        | 43/291 [00:05<00:10, 22.88it/s]
Loading 0:  17%|█▋        | 50/291 [00:05<00:08, 29.67it/s]
Loading 0:  19%|█▉        | 56/291 [00:05<00:07, 32.47it/s]
Loading 0:  21%|██        | 61/291 [00:06<00:09, 24.05it/s]
Loading 0:  23%|██▎       | 68/291 [00:06<00:07, 30.38it/s]
Loading 0:  25%|██▌       | 74/291 [00:06<00:06, 32.69it/s]
Loading 0:  27%|██▋       | 79/291 [00:06<00:06, 34.95it/s]
Loading 0:  30%|██▉       | 86/291 [00:06<00:04, 41.13it/s]
Loading 0:  32%|███▏      | 92/291 [00:06<00:04, 40.90it/s]
Loading 0:  33%|███▎      | 97/291 [00:07<00:04, 41.98it/s]
Loading 0:  36%|███▌      | 104/291 [00:07<00:04, 46.60it/s]
Loading 0:  37%|███▋      | 109/291 [00:07<00:03, 47.39it/s]
Loading 0:  39%|███▉      | 114/291 [00:07<00:04, 40.99it/s]
Loading 0:  42%|████▏     | 122/291 [00:07<00:03, 49.57it/s]
Loading 0:  44%|████▍     | 128/291 [00:07<00:03, 46.78it/s]
Loading 0:  46%|████▌     | 133/291 [00:07<00:03, 45.69it/s]
Loading 0:  48%|████▊     | 140/291 [00:07<00:02, 51.02it/s]
Loading 0:  50%|█████     | 146/291 [00:08<00:03, 47.98it/s]
Loading 0:  52%|█████▏    | 151/291 [00:08<00:03, 45.66it/s]
Loading 0:  54%|█████▍    | 158/291 [00:08<00:02, 50.51it/s]
Loading 0:  56%|█████▋    | 164/291 [00:08<00:02, 46.66it/s]
Loading 0:  58%|█████▊    | 169/291 [00:08<00:03, 31.20it/s]
Loading 0:  60%|██████    | 175/291 [00:08<00:03, 36.37it/s]
Loading 0:  62%|██████▏   | 180/291 [00:09<00:02, 38.96it/s]
Loading 0:  64%|██████▍   | 186/291 [00:09<00:02, 37.53it/s]
Loading 0:  66%|██████▋   | 193/291 [00:09<00:02, 44.50it/s]
Loading 0:  68%|██████▊   | 199/291 [00:09<00:01, 47.14it/s]
Loading 0:  70%|███████   | 205/291 [00:09<00:02, 42.21it/s]
Loading 0:  73%|███████▎  | 212/291 [00:09<00:01, 47.02it/s]
Loading 0:  75%|███████▍  | 218/291 [00:09<00:01, 44.68it/s]
Loading 0:  77%|███████▋  | 223/291 [00:09<00:01, 44.34it/s]
Loading 0:  79%|███████▉  | 230/291 [00:10<00:01, 49.41it/s]
Loading 0:  81%|████████  | 236/291 [00:10<00:01, 46.68it/s]
Loading 0:  83%|████████▎ | 241/291 [00:10<00:01, 45.72it/s]
Loading 0:  85%|████████▌ | 248/291 [00:10<00:00, 50.84it/s]
Loading 0:  87%|████████▋ | 254/291 [00:10<00:00, 45.80it/s]
Loading 0:  89%|████████▉ | 259/291 [00:10<00:00, 44.01it/s]
Loading 0:  91%|█████████▏| 266/291 [00:11<00:00, 32.25it/s]
Loading 0:  93%|█████████▎| 270/291 [00:11<00:00, 33.61it/s]
Loading 0:  95%|█████████▍| 275/291 [00:11<00:00, 36.72it/s]
Loading 0:  97%|█████████▋| 281/291 [00:11<00:00, 36.90it/s]
Loading 0:  98%|█████████▊| 286/291 [00:11<00:00, 38.26it/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.
chaiml-sao10k-l3-rp-v3-3-v87-mkmlizer:   warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v87-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.
chaiml-sao10k-l3-rp-v3-3-v87-mkmlizer:   warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v87-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.
chaiml-sao10k-l3-rp-v3-3-v87-mkmlizer:   warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v87-mkmlizer: 
Downloading shards:   0%|          | 0/2 [00:00<?, ?it/s]
Downloading shards:  50%|█████     | 1/2 [00:05<00:05,  5.37s/it]
Downloading shards: 100%|██████████| 2/2 [00:08<00:00,  3.94s/it]
Downloading shards: 100%|██████████| 2/2 [00:08<00:00,  4.15s/it]
chaiml-sao10k-l3-rp-v3-3-v87-mkmlizer: 
Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/s]
Loading checkpoint shards:  50%|█████     | 1/2 [00:00<00:00,  2.33it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00,  3.86it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00,  3.51it/s]
chaiml-sao10k-l3-rp-v3-3-v87-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
chaiml-sao10k-l3-rp-v3-3-v87-mkmlizer: Saving duration: 1.314s
chaiml-sao10k-l3-rp-v3-3-v87-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 13.153s
chaiml-sao10k-l3-rp-v3-3-v87-mkmlizer: creating bucket guanaco-reward-models
chaiml-sao10k-l3-rp-v3-3-v87-mkmlizer: Bucket 's3://guanaco-reward-models/' created
chaiml-sao10k-l3-rp-v3-3-v87-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v87_reward
chaiml-sao10k-l3-rp-v3-3-v87-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v87_reward/special_tokens_map.json
chaiml-sao10k-l3-rp-v3-3-v87-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v87_reward/config.json
chaiml-sao10k-l3-rp-v3-3-v87-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v87_reward/tokenizer_config.json
chaiml-sao10k-l3-rp-v3-3-v87-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v87_reward/merges.txt
chaiml-sao10k-l3-rp-v3-3-v87-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v87_reward/vocab.json
chaiml-sao10k-l3-rp-v3-3-v87-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v87_reward/tokenizer.json
chaiml-sao10k-l3-rp-v3-3-v87-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v87_reward/reward.tensors
Job chaiml-sao10k-l3-rp-v3-3-v87-mkmlizer completed after 94.65s with status: succeeded
Stopping job with name chaiml-sao10k-l3-rp-v3-3-v87-mkmlizer
Pipeline stage MKMLizer completed in 95.61s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service chaiml-sao10k-l3-rp-v3-3-v87
Waiting for inference service chaiml-sao10k-l3-rp-v3-3-v87 to be ready
Inference service chaiml-sao10k-l3-rp-v3-3-v87 ready after 160.98415684700012s
Pipeline stage ISVCDeployer completed in 162.56s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.892756462097168s
Received healthy response to inference request in 0.9054880142211914s
Received healthy response to inference request in 1.050724744796753s
Received healthy response to inference request in 0.5904953479766846s
Received healthy response to inference request in 1.0432937145233154s
5 requests
0 failed requests
5th percentile: 0.6534938812255859
10th percentile: 0.7164924144744873
20th percentile: 0.84248948097229
30th percentile: 0.9330491542816162
40th percentile: 0.9881714344024658
50th percentile: 1.0432937145233154
60th percentile: 1.0462661266326905
70th percentile: 1.0492385387420655
80th percentile: 1.219131088256836
90th percentile: 1.555943775177002
95th percentile: 1.7243501186370849
99th percentile: 1.8590751934051513
mean time: 1.0965516567230225
Pipeline stage StressChecker completed in 6.18s
chaiml-sao10k-l3-rp-v3-3_v87 status is now deployed due to DeploymentManager action
chaiml-sao10k-l3-rp-v3-3_v87 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of chaiml-sao10k-l3-rp-v3-3_v87
Running pipeline stage ISVCDeleter
Checking if service chaiml-sao10k-l3-rp-v3-3-v87 is running
Tearing down inference service chaiml-sao10k-l3-rp-v3-3-v87
Service chaiml-sao10k-l3-rp-v3-3-v87 has been torndown
Pipeline stage ISVCDeleter completed in 11.93s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key chaiml-sao10k-l3-rp-v3-3-v87/config.json from bucket guanaco-mkml-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v87/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v87/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v87/tokenizer.json from bucket guanaco-mkml-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v87/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key chaiml-sao10k-l3-rp-v3-3-v87_reward/config.json from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v87_reward/merges.txt from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v87_reward/reward.tensors from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v87_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v87_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v87_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v87_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.88s
chaiml-sao10k-l3-rp-v3-3_v87 status is now torndown due to DeploymentManager action