chaiml-sao10k-l3-rp-v3-3

developer_uid: robert_irvine

submission_id: chaiml-sao10k-l3-rp-v3-3_v86

model_name: chaiml-sao10k-l3-rp-v3-3_v86

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

status: torndown

timestamp: 2024-08-05T00:55:19+00:00

num_battles: 165845

num_wins: 81087

celo_rating: 1195.45

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: 4

max_input_tokens: 512

max_output_tokens: 64

display_name: chaiml-sao10k-l3-rp-v3-3_v86

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: 0.48893243691398597

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': 4, '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-v86-mkmlizer
Waiting for job on chaiml-sao10k-l3-rp-v3-3-v86-mkmlizer to finish
chaiml-sao10k-l3-rp-v3-3-v86-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-sao10k-l3-rp-v3-3-v86-mkmlizer: ║     _____            __           __                                ║
chaiml-sao10k-l3-rp-v3-3-v86-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-sao10k-l3-rp-v3-3-v86-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-sao10k-l3-rp-v3-3-v86-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-sao10k-l3-rp-v3-3-v86-mkmlizer: ║       /___/                                                         ║
chaiml-sao10k-l3-rp-v3-3-v86-mkmlizer: ║                                                                     ║
chaiml-sao10k-l3-rp-v3-3-v86-mkmlizer: ║  Version: 0.9.9                                                     ║
chaiml-sao10k-l3-rp-v3-3-v86-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-sao10k-l3-rp-v3-3-v86-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-sao10k-l3-rp-v3-3-v86-mkmlizer: ║                                                                     ║
chaiml-sao10k-l3-rp-v3-3-v86-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-sao10k-l3-rp-v3-3-v86-mkmlizer: ║  belonging to:                                                      ║
chaiml-sao10k-l3-rp-v3-3-v86-mkmlizer: ║                                                                     ║
chaiml-sao10k-l3-rp-v3-3-v86-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-sao10k-l3-rp-v3-3-v86-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-sao10k-l3-rp-v3-3-v86-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
chaiml-sao10k-l3-rp-v3-3-v86-mkmlizer: ║                                                                     ║
chaiml-sao10k-l3-rp-v3-3-v86-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-sao10k-l3-rp-v3-3-v86-mkmlizer: Downloaded to shared memory in 35.049s
chaiml-sao10k-l3-rp-v3-3-v86-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp9srf0lz5, device:0
chaiml-sao10k-l3-rp-v3-3-v86-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-sao10k-l3-rp-v3-3-v86-mkmlizer: quantized model in 25.783s
chaiml-sao10k-l3-rp-v3-3-v86-mkmlizer: Processed model ChaiML/sao10k-l3-rp-v3-3 in 60.831s
chaiml-sao10k-l3-rp-v3-3-v86-mkmlizer: creating bucket guanaco-mkml-models
chaiml-sao10k-l3-rp-v3-3-v86-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-sao10k-l3-rp-v3-3-v86-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v86
chaiml-sao10k-l3-rp-v3-3-v86-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v86/config.json
chaiml-sao10k-l3-rp-v3-3-v86-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v86/special_tokens_map.json
chaiml-sao10k-l3-rp-v3-3-v86-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v86/tokenizer_config.json
chaiml-sao10k-l3-rp-v3-3-v86-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v86/tokenizer.json
chaiml-sao10k-l3-rp-v3-3-v86-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v86/flywheel_model.0.safetensors
chaiml-sao10k-l3-rp-v3-3-v86-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
chaiml-sao10k-l3-rp-v3-3-v86-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/291 [00:04<11:22,  2.36s/it]
Loading 0:   2%|▏         | 6/291 [00:04<03:01,  1.57it/s]
Loading 0:   4%|▍         | 13/291 [00:04<01:04,  4.30it/s]
Loading 0:   7%|▋         | 19/291 [00:05<00:37,  7.29it/s]
Loading 0:   8%|▊         | 24/291 [00:05<00:27,  9.84it/s]
Loading 0:  11%|█▏        | 33/291 [00:05<00:16, 15.96it/s]
Loading 0:  14%|█▍        | 42/291 [00:05<00:11, 22.07it/s]
Loading 0:  17%|█▋        | 50/291 [00:05<00:08, 28.61it/s]
Loading 0:  19%|█▉        | 56/291 [00:05<00:07, 30.64it/s]
Loading 0:  21%|██        | 61/291 [00:06<00:08, 25.98it/s]
Loading 0:  23%|██▎       | 68/291 [00:06<00:06, 32.29it/s]
Loading 0:  25%|██▌       | 74/291 [00:06<00:06, 34.58it/s]
Loading 0:  27%|██▋       | 79/291 [00:06<00:05, 37.02it/s]
Loading 0:  30%|██▉       | 86/291 [00:06<00:04, 43.08it/s]
Loading 0:  32%|███▏      | 92/291 [00:06<00:04, 42.15it/s]
Loading 0:  33%|███▎      | 97/291 [00:06<00:04, 43.48it/s]
Loading 0:  36%|███▌      | 104/291 [00:06<00:03, 49.79it/s]
Loading 0:  38%|███▊      | 110/291 [00:07<00:03, 47.08it/s]
Loading 0:  40%|███▉      | 116/291 [00:07<00:03, 48.78it/s]
Loading 0:  42%|████▏     | 122/291 [00:07<00:03, 51.63it/s]
Loading 0:  44%|████▍     | 128/291 [00:07<00:03, 47.51it/s]
Loading 0:  46%|████▌     | 133/291 [00:07<00:03, 45.93it/s]
Loading 0:  48%|████▊     | 140/291 [00:07<00:02, 51.30it/s]
Loading 0:  50%|█████     | 146/291 [00:07<00:03, 47.65it/s]
Loading 0:  52%|█████▏    | 151/291 [00:07<00:02, 47.45it/s]
Loading 0:  54%|█████▍    | 158/291 [00:08<00:02, 51.38it/s]
Loading 0:  56%|█████▋    | 164/291 [00:08<00:02, 46.33it/s]
Loading 0:  58%|█████▊    | 169/291 [00:08<00:03, 33.17it/s]
Loading 0:  60%|██████    | 176/291 [00:08<00:02, 39.84it/s]
Loading 0:  63%|██████▎   | 182/291 [00:08<00:02, 40.32it/s]
Loading 0:  64%|██████▍   | 187/291 [00:08<00:02, 41.90it/s]
Loading 0:  67%|██████▋   | 194/291 [00:08<00:02, 46.33it/s]
Loading 0:  69%|██████▊   | 200/291 [00:09<00:02, 44.81it/s]
Loading 0:  70%|███████   | 205/291 [00:09<00:01, 45.09it/s]
Loading 0:  73%|███████▎  | 212/291 [00:09<00:01, 50.61it/s]
Loading 0:  75%|███████▍  | 218/291 [00:09<00:01, 47.42it/s]
Loading 0:  77%|███████▋  | 223/291 [00:09<00:01, 46.17it/s]
Loading 0:  79%|███████▉  | 230/291 [00:09<00:01, 50.68it/s]
Loading 0:  81%|████████  | 236/291 [00:09<00:01, 46.65it/s]
Loading 0:  83%|████████▎ | 241/291 [00:09<00:01, 45.62it/s]
Loading 0:  85%|████████▌ | 248/291 [00:10<00:00, 50.62it/s]
Loading 0:  87%|████████▋ | 254/291 [00:10<00:00, 47.55it/s]
Loading 0:  89%|████████▉ | 259/291 [00:10<00:00, 47.13it/s]
Loading 0:  91%|█████████ | 265/291 [00:10<00:00, 49.42it/s]
Loading 0:  93%|█████████▎| 271/291 [00:10<00:00, 34.74it/s]
Loading 0:  95%|█████████▍| 276/291 [00:10<00:00, 33.18it/s]
Loading 0:  98%|█████████▊| 284/291 [00:11<00:00, 42.09it/s]
Loading 0: 100%|█████████▉| 290/291 [00:11<00:00, 41.69it/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-v86-mkmlizer:   warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v86-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-v86-mkmlizer:   warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v86-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-v86-mkmlizer:   warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v86-mkmlizer: 
Downloading shards:   0%|          | 0/2 [00:00<?, ?it/s]
Downloading shards:  50%|█████     | 1/2 [00:04<00:04,  4.84s/it]
Downloading shards: 100%|██████████| 2/2 [00:07<00:00,  3.44s/it]
Downloading shards: 100%|██████████| 2/2 [00:07<00:00,  3.65s/it]
chaiml-sao10k-l3-rp-v3-3-v86-mkmlizer: 
Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/s]
Loading checkpoint shards:  50%|█████     | 1/2 [00:00<00:00,  2.45it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00,  4.01it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00,  3.66it/s]
chaiml-sao10k-l3-rp-v3-3-v86-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
chaiml-sao10k-l3-rp-v3-3-v86-mkmlizer: Saving duration: 1.386s
chaiml-sao10k-l3-rp-v3-3-v86-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 12.196s
chaiml-sao10k-l3-rp-v3-3-v86-mkmlizer: creating bucket guanaco-reward-models
chaiml-sao10k-l3-rp-v3-3-v86-mkmlizer: Bucket 's3://guanaco-reward-models/' created
chaiml-sao10k-l3-rp-v3-3-v86-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v86_reward
chaiml-sao10k-l3-rp-v3-3-v86-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v86_reward/config.json
chaiml-sao10k-l3-rp-v3-3-v86-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v86_reward/special_tokens_map.json
chaiml-sao10k-l3-rp-v3-3-v86-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v86_reward/tokenizer_config.json
chaiml-sao10k-l3-rp-v3-3-v86-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v86_reward/merges.txt
chaiml-sao10k-l3-rp-v3-3-v86-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v86_reward/vocab.json
chaiml-sao10k-l3-rp-v3-3-v86-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v86_reward/tokenizer.json
chaiml-sao10k-l3-rp-v3-3-v86-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v86_reward/reward.tensors
Job chaiml-sao10k-l3-rp-v3-3-v86-mkmlizer completed after 104.6s with status: succeeded
Stopping job with name chaiml-sao10k-l3-rp-v3-3-v86-mkmlizer
Pipeline stage MKMLizer completed in 105.51s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service chaiml-sao10k-l3-rp-v3-3-v86
Waiting for inference service chaiml-sao10k-l3-rp-v3-3-v86 to be ready
Inference service chaiml-sao10k-l3-rp-v3-3-v86 ready after 160.9745750427246s
Pipeline stage ISVCDeployer completed in 162.58s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9121878147125244s
Received healthy response to inference request in 1.12567138671875s
Received healthy response to inference request in 1.040623426437378s
Received healthy response to inference request in 1.0923538208007812s
Received healthy response to inference request in 1.104792833328247s
5 requests
0 failed requests
5th percentile: 1.0509695053100585
10th percentile: 1.0613155841827393
20th percentile: 1.0820077419281007
30th percentile: 1.0948416233062743
40th percentile: 1.0998172283172607
50th percentile: 1.104792833328247
60th percentile: 1.1131442546844483
70th percentile: 1.1214956760406494
80th percentile: 1.282974672317505
90th percentile: 1.5975812435150147
95th percentile: 1.7548845291137694
99th percentile: 1.8807271575927733
mean time: 1.2551258563995362
Pipeline stage StressChecker completed in 7.11s
chaiml-sao10k-l3-rp-v3-3_v86 status is now deployed due to DeploymentManager action
chaiml-sao10k-l3-rp-v3-3_v86 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of chaiml-sao10k-l3-rp-v3-3_v86
Running pipeline stage ISVCDeleter
Checking if service chaiml-sao10k-l3-rp-v3-3-v86 is running
Tearing down inference service chaiml-sao10k-l3-rp-v3-3-v86
Service chaiml-sao10k-l3-rp-v3-3-v86 has been torndown
Pipeline stage ISVCDeleter completed in 6.55s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key chaiml-sao10k-l3-rp-v3-3-v86/config.json from bucket guanaco-mkml-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v86/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v86/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v86/tokenizer.json from bucket guanaco-mkml-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v86/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key chaiml-sao10k-l3-rp-v3-3-v86_reward/config.json from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v86_reward/merges.txt from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v86_reward/reward.tensors from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v86_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v86_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v86_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v86_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 8.04s
chaiml-sao10k-l3-rp-v3-3_v86 status is now torndown due to DeploymentManager action