chaiml-sao10k-l3-rp-v3-3

developer_uid: robert_irvine

submission_id: chaiml-sao10k-l3-rp-v3-3_v90

model_name: chaiml-sao10k-l3-rp-v3-3_v90

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

status: torndown

timestamp: 2024-08-06T23:04:13+00:00

num_battles: 12575

num_wins: 6185

celo_rating: 1214.28

family_friendly_score: 0.0

submission_type: basic

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

model_architecture: LlamaForCausalLM

reward_repo: ChaiML/gpt2_medium_pairwise_60m_step_937500

model_num_parameters: 8030261248.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

display_name: chaiml-sao10k-l3-rp-v3-3_v90

is_internal_developer: True

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

model_size: 8B

ranking_group: single

us_pacific_date: 2024-08-06

win_ratio: 0.4918489065606362

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, '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-v90-mkmlizer
Waiting for job on chaiml-sao10k-l3-rp-v3-3-v90-mkmlizer to finish
chaiml-sao10k-l3-rp-v3-3-v90-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-sao10k-l3-rp-v3-3-v90-mkmlizer: ║     _____            __           __                                ║
chaiml-sao10k-l3-rp-v3-3-v90-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-sao10k-l3-rp-v3-3-v90-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-sao10k-l3-rp-v3-3-v90-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-sao10k-l3-rp-v3-3-v90-mkmlizer: ║       /___/                                                         ║
chaiml-sao10k-l3-rp-v3-3-v90-mkmlizer: ║                                                                     ║
chaiml-sao10k-l3-rp-v3-3-v90-mkmlizer: ║  Version: 0.9.9                                                     ║
chaiml-sao10k-l3-rp-v3-3-v90-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-sao10k-l3-rp-v3-3-v90-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-sao10k-l3-rp-v3-3-v90-mkmlizer: ║                                                                     ║
chaiml-sao10k-l3-rp-v3-3-v90-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-sao10k-l3-rp-v3-3-v90-mkmlizer: ║  belonging to:                                                      ║
chaiml-sao10k-l3-rp-v3-3-v90-mkmlizer: ║                                                                     ║
chaiml-sao10k-l3-rp-v3-3-v90-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-sao10k-l3-rp-v3-3-v90-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-sao10k-l3-rp-v3-3-v90-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
chaiml-sao10k-l3-rp-v3-3-v90-mkmlizer: ║                                                                     ║
chaiml-sao10k-l3-rp-v3-3-v90-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-sao10k-l3-rp-v3-3-v90-mkmlizer: Downloaded to shared memory in 22.669s
chaiml-sao10k-l3-rp-v3-3-v90-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpslynzh1d, device:0
chaiml-sao10k-l3-rp-v3-3-v90-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-sao10k-l3-rp-v3-3-v90-mkmlizer: quantized model in 26.871s
chaiml-sao10k-l3-rp-v3-3-v90-mkmlizer: Processed model ChaiML/sao10k-l3-rp-v3-3 in 49.541s
chaiml-sao10k-l3-rp-v3-3-v90-mkmlizer: creating bucket guanaco-mkml-models
chaiml-sao10k-l3-rp-v3-3-v90-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-sao10k-l3-rp-v3-3-v90-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v90
chaiml-sao10k-l3-rp-v3-3-v90-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v90/config.json
chaiml-sao10k-l3-rp-v3-3-v90-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v90/special_tokens_map.json
chaiml-sao10k-l3-rp-v3-3-v90-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v90/tokenizer_config.json
chaiml-sao10k-l3-rp-v3-3-v90-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v90/tokenizer.json
chaiml-sao10k-l3-rp-v3-3-v90-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v90/flywheel_model.0.safetensors
chaiml-sao10k-l3-rp-v3-3-v90-mkmlizer: loading reward model from ChaiML/gpt2_medium_pairwise_60m_step_937500
chaiml-sao10k-l3-rp-v3-3-v90-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/291 [00:04<11:28,  2.38s/it]
Loading 0:   2%|▏         | 6/291 [00:04<03:03,  1.55it/s]
Loading 0:   4%|▍         | 13/291 [00:05<01:05,  4.25it/s]
Loading 0:   7%|▋         | 20/291 [00:05<00:35,  7.55it/s]
Loading 0:   9%|▊         | 25/291 [00:05<00:25, 10.43it/s]
Loading 0:  11%|█▏        | 33/291 [00:05<00:16, 15.67it/s]
Loading 0:  14%|█▍        | 42/291 [00:05<00:11, 22.05it/s]
Loading 0:  17%|█▋        | 50/291 [00:05<00:08, 29.24it/s]
Loading 0:  19%|█▉        | 56/291 [00:05<00:07, 30.84it/s]
Loading 0:  21%|██▏       | 62/291 [00:06<00:08, 26.34it/s]
Loading 0:  23%|██▎       | 68/291 [00:06<00:07, 30.75it/s]
Loading 0:  25%|██▌       | 73/291 [00:06<00:06, 33.70it/s]
Loading 0:  27%|██▋       | 78/291 [00:06<00:06, 31.75it/s]
Loading 0:  29%|██▉       | 85/291 [00:06<00:05, 38.93it/s]
Loading 0:  31%|███       | 90/291 [00:06<00:04, 40.34it/s]
Loading 0:  33%|███▎      | 95/291 [00:06<00:04, 41.01it/s]
Loading 0:  35%|███▍      | 101/291 [00:07<00:04, 40.02it/s]
Loading 0:  36%|███▋      | 106/291 [00:07<00:04, 40.41it/s]
Loading 0:  39%|███▉      | 113/291 [00:07<00:03, 46.15it/s]
Loading 0:  41%|████      | 118/291 [00:07<00:03, 46.23it/s]
Loading 0:  42%|████▏     | 123/291 [00:07<00:04, 38.62it/s]
Loading 0:  45%|████▌     | 131/291 [00:07<00:03, 46.74it/s]
Loading 0:  47%|████▋     | 137/291 [00:07<00:03, 43.89it/s]
Loading 0:  49%|████▉     | 142/291 [00:07<00:03, 43.65it/s]
Loading 0:  51%|█████     | 149/291 [00:08<00:02, 48.08it/s]
Loading 0:  53%|█████▎    | 155/291 [00:08<00:03, 44.63it/s]
Loading 0:  55%|█████▍    | 160/291 [00:08<00:03, 42.69it/s]
Loading 0:  57%|█████▋    | 166/291 [00:08<00:03, 32.46it/s]
Loading 0:  58%|█████▊    | 170/291 [00:08<00:03, 33.67it/s]
Loading 0:  60%|██████    | 176/291 [00:08<00:03, 38.00it/s]
Loading 0:  63%|██████▎   | 182/291 [00:09<00:02, 38.15it/s]
Loading 0:  64%|██████▍   | 187/291 [00:09<00:02, 38.84it/s]
Loading 0:  66%|██████▋   | 193/291 [00:09<00:02, 43.28it/s]
Loading 0:  68%|██████▊   | 198/291 [00:09<00:02, 43.34it/s]
Loading 0:  70%|██████▉   | 203/291 [00:09<00:02, 43.75it/s]
Loading 0:  72%|███████▏  | 209/291 [00:09<00:01, 41.65it/s]
Loading 0:  74%|███████▎  | 214/291 [00:09<00:01, 41.38it/s]
Loading 0:  76%|███████▌  | 221/291 [00:09<00:01, 46.94it/s]
Loading 0:  78%|███████▊  | 227/291 [00:10<00:01, 43.83it/s]
Loading 0:  80%|███████▉  | 232/291 [00:10<00:01, 42.90it/s]
Loading 0:  82%|████████▏ | 239/291 [00:10<00:01, 48.05it/s]
Loading 0:  84%|████████▍ | 245/291 [00:10<00:01, 43.33it/s]
Loading 0:  86%|████████▌ | 250/291 [00:10<00:00, 42.67it/s]
Loading 0:  88%|████████▊ | 256/291 [00:10<00:00, 45.74it/s]
Loading 0:  90%|████████▉ | 261/291 [00:10<00:00, 45.19it/s]
Loading 0:  91%|█████████▏| 266/291 [00:11<00:00, 31.23it/s]
Loading 0:  93%|█████████▎| 271/291 [00:11<00:00, 34.94it/s]
Loading 0:  95%|█████████▍| 276/291 [00:11<00:00, 32.65it/s]
Loading 0:  97%|█████████▋| 283/291 [00:11<00:00, 39.85it/s]
Loading 0:  99%|█████████▉| 288/291 [00:11<00:00, 41.06it/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-v90-mkmlizer:   warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v90-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-v90-mkmlizer:   warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v90-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-v90-mkmlizer:   warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v90-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
chaiml-sao10k-l3-rp-v3-3-v90-mkmlizer: Saving duration: 0.328s
chaiml-sao10k-l3-rp-v3-3-v90-mkmlizer: Processed model ChaiML/gpt2_medium_pairwise_60m_step_937500 in 6.623s
chaiml-sao10k-l3-rp-v3-3-v90-mkmlizer: creating bucket guanaco-reward-models
chaiml-sao10k-l3-rp-v3-3-v90-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v90_reward/merges.txt
chaiml-sao10k-l3-rp-v3-3-v90-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v90_reward/vocab.json
chaiml-sao10k-l3-rp-v3-3-v90-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v90_reward/tokenizer.json
chaiml-sao10k-l3-rp-v3-3-v90-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v90_reward/reward.tensors
Job chaiml-sao10k-l3-rp-v3-3-v90-mkmlizer completed after 84.18s with status: succeeded
Stopping job with name chaiml-sao10k-l3-rp-v3-3-v90-mkmlizer
Pipeline stage MKMLizer completed in 85.21s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service chaiml-sao10k-l3-rp-v3-3-v90
Waiting for inference service chaiml-sao10k-l3-rp-v3-3-v90 to be ready
Inference service chaiml-sao10k-l3-rp-v3-3-v90 ready after 181.30905675888062s
Pipeline stage ISVCDeployer completed in 183.27s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.044628381729126s
Received healthy response to inference request in 1.1682460308074951s
Received healthy response to inference request in 1.202934980392456s
Received healthy response to inference request in 1.1689088344573975s
Received healthy response to inference request in 1.1640474796295166s
5 requests
0 failed requests
5th percentile: 1.1648871898651123
10th percentile: 1.165726900100708
20th percentile: 1.1674063205718994
30th percentile: 1.1683785915374756
40th percentile: 1.1686437129974365
50th percentile: 1.1689088344573975
60th percentile: 1.182519292831421
70th percentile: 1.1961297512054443
80th percentile: 1.3712736606597902
90th percentile: 1.7079510211944582
95th percentile: 1.8762897014617919
99th percentile: 2.010960645675659
mean time: 1.3497531414031982
Pipeline stage StressChecker completed in 7.40s
chaiml-sao10k-l3-rp-v3-3_v90 status is now deployed due to DeploymentManager action
chaiml-sao10k-l3-rp-v3-3_v90 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of chaiml-sao10k-l3-rp-v3-3_v90
Running pipeline stage ISVCDeleter
Checking if service chaiml-sao10k-l3-rp-v3-3-v90 is running
Tearing down inference service chaiml-sao10k-l3-rp-v3-3-v90
Service chaiml-sao10k-l3-rp-v3-3-v90 has been torndown
Pipeline stage ISVCDeleter completed in 7.48s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key chaiml-sao10k-l3-rp-v3-3-v90/config.json from bucket guanaco-mkml-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v90/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v90/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v90/tokenizer.json from bucket guanaco-mkml-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v90/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key chaiml-sao10k-l3-rp-v3-3-v90_reward/config.json from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v90_reward/merges.txt from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v90_reward/reward.tensors from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v90_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v90_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v90_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v90_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.86s
chaiml-sao10k-l3-rp-v3-3_v90 status is now torndown due to DeploymentManager action