chaiml-sao10k-l3-rp-v3-3

developer_uid: robert_irvine

submission_id: chaiml-sao10k-l3-rp-v3-3_v65

model_name: chaiml-sao10k-l3-rp-v3-3_v65

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

status: torndown

timestamp: 2024-08-01T00:49:52+00:00

num_battles: 278659

num_wins: 139771

celo_rating: 1230.24

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_v65

is_internal_developer: True

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

model_size: 8B

ranking_group: single

us_pacific_date: 2024-07-31

win_ratio: 0.5015843737327702

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-v65-mkmlizer
Waiting for job on chaiml-sao10k-l3-rp-v3-3-v65-mkmlizer to finish
chaiml-sao10k-l3-rp-v3-3-v65-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-sao10k-l3-rp-v3-3-v65-mkmlizer: ║     _____            __           __                                ║
chaiml-sao10k-l3-rp-v3-3-v65-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-sao10k-l3-rp-v3-3-v65-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-sao10k-l3-rp-v3-3-v65-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-sao10k-l3-rp-v3-3-v65-mkmlizer: ║       /___/                                                         ║
chaiml-sao10k-l3-rp-v3-3-v65-mkmlizer: ║                                                                     ║
chaiml-sao10k-l3-rp-v3-3-v65-mkmlizer: ║  Version: 0.9.7                                                     ║
chaiml-sao10k-l3-rp-v3-3-v65-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-sao10k-l3-rp-v3-3-v65-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-sao10k-l3-rp-v3-3-v65-mkmlizer: ║                                                                     ║
chaiml-sao10k-l3-rp-v3-3-v65-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-sao10k-l3-rp-v3-3-v65-mkmlizer: ║  belonging to:                                                      ║
chaiml-sao10k-l3-rp-v3-3-v65-mkmlizer: ║                                                                     ║
chaiml-sao10k-l3-rp-v3-3-v65-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-sao10k-l3-rp-v3-3-v65-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-sao10k-l3-rp-v3-3-v65-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
chaiml-sao10k-l3-rp-v3-3-v65-mkmlizer: ║                                                                     ║
chaiml-sao10k-l3-rp-v3-3-v65-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-sao10k-l3-rp-v3-3-v65-mkmlizer: Downloaded to shared memory in 33.458s
chaiml-sao10k-l3-rp-v3-3-v65-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpb3lnw99g, device:0
chaiml-sao10k-l3-rp-v3-3-v65-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-sao10k-l3-rp-v3-3-v65-mkmlizer: quantized model in 25.951s
chaiml-sao10k-l3-rp-v3-3-v65-mkmlizer: Processed model ChaiML/sao10k-l3-rp-v3-3 in 59.410s
chaiml-sao10k-l3-rp-v3-3-v65-mkmlizer: creating bucket guanaco-mkml-models
chaiml-sao10k-l3-rp-v3-3-v65-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-sao10k-l3-rp-v3-3-v65-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v65
chaiml-sao10k-l3-rp-v3-3-v65-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v65/config.json
chaiml-sao10k-l3-rp-v3-3-v65-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v65/special_tokens_map.json
chaiml-sao10k-l3-rp-v3-3-v65-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v65/tokenizer_config.json
chaiml-sao10k-l3-rp-v3-3-v65-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v65/tokenizer.json
chaiml-sao10k-l3-rp-v3-3-v65-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v65/flywheel_model.0.safetensors
chaiml-sao10k-l3-rp-v3-3-v65-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
chaiml-sao10k-l3-rp-v3-3-v65-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:   5%|▍         | 14/291 [00:05<00:59,  4.62it/s]
Loading 0:   7%|▋         | 20/291 [00:05<00:36,  7.45it/s]
Loading 0:   9%|▊         | 25/291 [00:05<00:25, 10.39it/s]
Loading 0:  11%|█         | 32/291 [00:05<00:16, 15.76it/s]
Loading 0:  13%|█▎        | 38/291 [00:05<00:12, 20.03it/s]
Loading 0:  15%|█▌        | 44/291 [00:05<00:09, 25.08it/s]
Loading 0:  18%|█▊        | 51/291 [00:05<00:08, 29.37it/s]
Loading 0:  21%|██        | 60/291 [00:06<00:08, 28.26it/s]
Loading 0:  24%|██▎       | 69/291 [00:06<00:06, 34.14it/s]
Loading 0:  26%|██▋       | 77/291 [00:06<00:05, 41.57it/s]
Loading 0:  29%|██▊       | 83/291 [00:06<00:04, 42.12it/s]
Loading 0:  31%|███       | 89/291 [00:06<00:04, 42.78it/s]
Loading 0:  33%|███▎      | 95/291 [00:06<00:04, 45.25it/s]
Loading 0:  35%|███▍      | 101/291 [00:06<00:04, 44.41it/s]
Loading 0:  36%|███▋      | 106/291 [00:06<00:04, 44.97it/s]
Loading 0:  39%|███▉      | 114/291 [00:07<00:03, 46.40it/s]
Loading 0:  42%|████▏     | 122/291 [00:07<00:03, 54.19it/s]
Loading 0:  44%|████▍     | 128/291 [00:07<00:03, 49.58it/s]
Loading 0:  46%|████▌     | 134/291 [00:07<00:03, 50.73it/s]
Loading 0:  48%|████▊     | 140/291 [00:07<00:02, 52.91it/s]
Loading 0:  50%|█████     | 146/291 [00:07<00:02, 49.93it/s]
Loading 0:  52%|█████▏    | 152/291 [00:07<00:02, 50.33it/s]
Loading 0:  55%|█████▍    | 159/291 [00:08<00:02, 47.00it/s]
Loading 0:  57%|█████▋    | 166/291 [00:08<00:03, 38.38it/s]
Loading 0:  59%|█████▉    | 171/291 [00:08<00:03, 39.92it/s]
Loading 0:  61%|██████    | 177/291 [00:08<00:03, 37.94it/s]
Loading 0:  64%|██████▎   | 185/291 [00:08<00:02, 45.60it/s]
Loading 0:  66%|██████▌   | 191/291 [00:08<00:02, 45.11it/s]
Loading 0:  67%|██████▋   | 196/291 [00:08<00:02, 45.65it/s]
Loading 0:  70%|██████▉   | 203/291 [00:09<00:01, 50.91it/s]
Loading 0:  72%|███████▏  | 209/291 [00:09<00:01, 47.94it/s]
Loading 0:  74%|███████▎  | 214/291 [00:09<00:01, 47.16it/s]
Loading 0:  76%|███████▌  | 221/291 [00:09<00:01, 52.80it/s]
Loading 0:  78%|███████▊  | 227/291 [00:09<00:01, 49.53it/s]
Loading 0:  80%|████████  | 233/291 [00:09<00:01, 50.05it/s]
Loading 0:  82%|████████▏ | 240/291 [00:09<00:01, 46.29it/s]
Loading 0:  85%|████████▌ | 248/291 [00:09<00:00, 53.40it/s]
Loading 0:  87%|████████▋ | 254/291 [00:10<00:00, 46.38it/s]
Loading 0:  89%|████████▉ | 259/291 [00:10<00:00, 44.74it/s]
Loading 0:  91%|█████████ | 265/291 [00:10<00:00, 48.11it/s]
Loading 0:  93%|█████████▎| 271/291 [00:10<00:00, 34.01it/s]
Loading 0:  95%|█████████▍| 276/291 [00:10<00:00, 32.98it/s]
Loading 0:  98%|█████████▊| 284/291 [00:10<00:00, 41.74it/s]
Loading 0: 100%|█████████▉| 290/291 [00:11<00:00, 41.75it/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-v65-mkmlizer:   warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v65-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-v65-mkmlizer:   warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v65-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-v65-mkmlizer:   warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v65-mkmlizer: 
Downloading shards:   0%|          | 0/2 [00:00<?, ?it/s]
Downloading shards:  50%|█████     | 1/2 [00:05<00:05,  5.16s/it]
Downloading shards: 100%|██████████| 2/2 [00:08<00:00,  4.15s/it]
Downloading shards: 100%|██████████| 2/2 [00:08<00:00,  4.30s/it]
chaiml-sao10k-l3-rp-v3-3-v65-mkmlizer: 
Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/s]
Loading checkpoint shards:  50%|█████     | 1/2 [00:00<00:00,  2.42it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00,  3.99it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00,  3.63it/s]
chaiml-sao10k-l3-rp-v3-3-v65-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
chaiml-sao10k-l3-rp-v3-3-v65-mkmlizer: Saving duration: 1.367s
chaiml-sao10k-l3-rp-v3-3-v65-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 13.981s
chaiml-sao10k-l3-rp-v3-3-v65-mkmlizer: creating bucket guanaco-reward-models
chaiml-sao10k-l3-rp-v3-3-v65-mkmlizer: Bucket 's3://guanaco-reward-models/' created
chaiml-sao10k-l3-rp-v3-3-v65-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v65_reward
chaiml-sao10k-l3-rp-v3-3-v65-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v65_reward/tokenizer_config.json
chaiml-sao10k-l3-rp-v3-3-v65-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v65_reward/config.json
chaiml-sao10k-l3-rp-v3-3-v65-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v65_reward/special_tokens_map.json
chaiml-sao10k-l3-rp-v3-3-v65-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v65_reward/vocab.json
chaiml-sao10k-l3-rp-v3-3-v65-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v65_reward/merges.txt
chaiml-sao10k-l3-rp-v3-3-v65-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v65_reward/tokenizer.json
chaiml-sao10k-l3-rp-v3-3-v65-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v65_reward/reward.tensors
Job chaiml-sao10k-l3-rp-v3-3-v65-mkmlizer completed after 105.6s with status: succeeded
Stopping job with name chaiml-sao10k-l3-rp-v3-3-v65-mkmlizer
Pipeline stage MKMLizer completed in 106.63s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service chaiml-sao10k-l3-rp-v3-3-v65
Waiting for inference service chaiml-sao10k-l3-rp-v3-3-v65 to be ready
Inference service chaiml-sao10k-l3-rp-v3-3-v65 ready after 120.90563249588013s
Pipeline stage ISVCDeployer completed in 122.53s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0255041122436523s
Received healthy response to inference request in 1.2090506553649902s
Received healthy response to inference request in 1.2506802082061768s
Received healthy response to inference request in 1.5125668048858643s
Received healthy response to inference request in 1.2135252952575684s
5 requests
0 failed requests
5th percentile: 1.2099455833435058
10th percentile: 1.2108405113220215
20th percentile: 1.2126303672790528
30th percentile: 1.22095627784729
40th percentile: 1.2358182430267335
50th percentile: 1.2506802082061768
60th percentile: 1.3554348468780517
70th percentile: 1.4601894855499267
80th percentile: 1.6151542663574219
90th percentile: 1.820329189300537
95th percentile: 1.9229166507720947
99th percentile: 2.004986619949341
mean time: 1.4422654151916503
Pipeline stage StressChecker completed in 7.93s
chaiml-sao10k-l3-rp-v3-3_v65 status is now deployed due to DeploymentManager action
chaiml-sao10k-l3-rp-v3-3_v65 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of chaiml-sao10k-l3-rp-v3-3_v65
Running pipeline stage ISVCDeleter
Checking if service chaiml-sao10k-l3-rp-v3-3-v65 is running
Tearing down inference service chaiml-sao10k-l3-rp-v3-3-v65
Service chaiml-sao10k-l3-rp-v3-3-v65 has been torndown
Pipeline stage ISVCDeleter completed in 4.92s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key chaiml-sao10k-l3-rp-v3-3-v65/config.json from bucket guanaco-mkml-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v65/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v65/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v65/tokenizer.json from bucket guanaco-mkml-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v65/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key chaiml-sao10k-l3-rp-v3-3-v65_reward/config.json from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v65_reward/merges.txt from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v65_reward/reward.tensors from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v65_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v65_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v65_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v65_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.58s
chaiml-sao10k-l3-rp-v3-3_v65 status is now torndown due to DeploymentManager action