submission_id: chaiml-sao10k-l3-rp-v3-3_v77
developer_uid: robert_irvine
alignment_samples: 0
best_of: 8
celo_rating: 1231.98
display_name: chaiml-sao10k-l3-rp-v3-3_v77
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}
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}
is_internal_developer: True
language_model: ChaiML/sao10k-l3-rp-v3-3
max_input_tokens: 1024
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: ChaiML/sao10k-l3-rp-v3-3
model_name: chaiml-sao10k-l3-rp-v3-3_v77
model_num_parameters: 8030261248.0
model_repo: ChaiML/sao10k-l3-rp-v3-3
model_size: 8B
num_battles: 22301
num_wins: 11428
propriety_score: 0.7275362318840579
propriety_total_count: 2070.0
ranking_group: single
reward_formatter: {'bot_template': 'Bot: {message}\n', 'memory_template': '', 'prompt_template': '', 'response_template': 'Bot:', 'truncate_by_message': False, 'user_template': 'User: {message}\n'}
reward_repo: rirv938/retune_gpt2_xl_on_chaiml_sao10k_step_585
status: torndown
submission_type: basic
timestamp: 2024-08-01T19:15:31+00:00
us_pacific_date: 2024-08-01
win_ratio: 0.5124433881888705
Download Preference Data
Resubmit model
Running pipeline stage MKMLizer
Starting job with name chaiml-sao10k-l3-rp-v3-3-v77-mkmlizer
Waiting for job on chaiml-sao10k-l3-rp-v3-3-v77-mkmlizer to finish
chaiml-sao10k-l3-rp-v3-3-v77-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-sao10k-l3-rp-v3-3-v77-mkmlizer: ║ _____ __ __ ║
chaiml-sao10k-l3-rp-v3-3-v77-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-sao10k-l3-rp-v3-3-v77-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-sao10k-l3-rp-v3-3-v77-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-sao10k-l3-rp-v3-3-v77-mkmlizer: ║ /___/ ║
chaiml-sao10k-l3-rp-v3-3-v77-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v77-mkmlizer: ║ Version: 0.9.7 ║
chaiml-sao10k-l3-rp-v3-3-v77-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-sao10k-l3-rp-v3-3-v77-mkmlizer: ║ https://mk1.ai ║
chaiml-sao10k-l3-rp-v3-3-v77-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v77-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-sao10k-l3-rp-v3-3-v77-mkmlizer: ║ belonging to: ║
chaiml-sao10k-l3-rp-v3-3-v77-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v77-mkmlizer: ║ Chai Research Corp. ║
chaiml-sao10k-l3-rp-v3-3-v77-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-sao10k-l3-rp-v3-3-v77-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
chaiml-sao10k-l3-rp-v3-3-v77-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v77-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission blend_sugom_2024-08-01: 'BlendChatApi' object has no attribute 'tags'
chaiml-sao10k-l3-rp-v3-3-v77-mkmlizer: Downloaded to shared memory in 22.783s
chaiml-sao10k-l3-rp-v3-3-v77-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpksmqaq2z, device:0
chaiml-sao10k-l3-rp-v3-3-v77-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-sao10k-l3-rp-v3-3-v77-mkmlizer: quantized model in 25.502s
chaiml-sao10k-l3-rp-v3-3-v77-mkmlizer: Processed model ChaiML/sao10k-l3-rp-v3-3 in 48.285s
chaiml-sao10k-l3-rp-v3-3-v77-mkmlizer: creating bucket guanaco-mkml-models
chaiml-sao10k-l3-rp-v3-3-v77-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-sao10k-l3-rp-v3-3-v77-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v77
chaiml-sao10k-l3-rp-v3-3-v77-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v77/config.json
chaiml-sao10k-l3-rp-v3-3-v77-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v77/special_tokens_map.json
chaiml-sao10k-l3-rp-v3-3-v77-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v77/tokenizer_config.json
chaiml-sao10k-l3-rp-v3-3-v77-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v77/tokenizer.json
chaiml-sao10k-l3-rp-v3-3-v77-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v77/flywheel_model.0.safetensors
chaiml-sao10k-l3-rp-v3-3-v77-mkmlizer: loading reward model from rirv938/retune_gpt2_xl_on_chaiml_sao10k_step_585
chaiml-sao10k-l3-rp-v3-3-v77-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<11:23, 2.36s/it] Loading 0: 2%|▏ | 6/291 [00:04<03:01, 1.57it/s] Loading 0: 4%|▍ | 13/291 [00:04<01:04, 4.29it/s] Loading 0: 7%|▋ | 20/291 [00:05<00:35, 7.62it/s] Loading 0: 9%|▊ | 25/291 [00:05<00:25, 10.52it/s] Loading 0: 11%|█▏ | 33/291 [00:05<00:16, 15.77it/s] Loading 0: 14%|█▍ | 42/291 [00:05<00:11, 22.14it/s] Loading 0: 17%|█▋ | 50/291 [00:05<00:08, 29.34it/s] Loading 0: 19%|█▉ | 56/291 [00:05<00:07, 32.09it/s] Loading 0: 21%|██▏ | 62/291 [00:06<00:08, 26.53it/s] Loading 0: 24%|██▎ | 69/291 [00:06<00:07, 29.89it/s] Loading 0: 26%|██▋ | 77/291 [00:06<00:05, 37.66it/s] Loading 0: 29%|██▊ | 83/291 [00:06<00:05, 39.09it/s] Loading 0: 30%|███ | 88/291 [00:06<00:04, 41.06it/s] Loading 0: 33%|███▎ | 95/291 [00:06<00:04, 46.98it/s] Loading 0: 35%|███▍ | 101/291 [00:06<00:04, 45.84it/s] Loading 0: 37%|███▋ | 107/291 [00:06<00:03, 48.26it/s] Loading 0: 39%|███▉ | 113/291 [00:07<00:03, 51.03it/s] Loading 0: 41%|████ | 119/291 [00:07<00:03, 47.64it/s] Loading 0: 43%|████▎ | 125/291 [00:07<00:03, 49.11it/s] Loading 0: 45%|████▌ | 132/291 [00:07<00:03, 46.26it/s] Loading 0: 48%|████▊ | 140/291 [00:07<00:02, 52.95it/s] Loading 0: 50%|█████ | 146/291 [00:07<00:03, 48.31it/s] Loading 0: 52%|█████▏ | 152/291 [00:07<00:02, 50.12it/s] Loading 0: 55%|█████▍ | 159/291 [00:08<00:02, 47.25it/s] Loading 0: 57%|█████▋ | 166/291 [00:08<00:03, 37.68it/s] Loading 0: 59%|█████▉ | 172/291 [00:08<00:02, 41.63it/s] Loading 0: 61%|██████ | 177/291 [00:08<00:02, 38.41it/s] Loading 0: 64%|██████▎ | 185/291 [00:08<00:02, 47.14it/s] Loading 0: 66%|██████▌ | 191/291 [00:08<00:02, 46.18it/s] Loading 0: 68%|██████▊ | 197/291 [00:08<00:01, 48.03it/s] Loading 0: 70%|███████ | 204/291 [00:09<00:01, 46.02it/s] Loading 0: 73%|███████▎ | 212/291 [00:09<00:01, 53.76it/s] Loading 0: 75%|███████▍ | 218/291 [00:09<00:01, 50.33it/s] Loading 0: 77%|███████▋ | 224/291 [00:09<00:01, 51.14it/s] Loading 0: 79%|███████▉ | 231/291 [00:09<00:01, 47.98it/s] Loading 0: 82%|████████▏ | 239/291 [00:09<00:00, 55.50it/s] Loading 0: 84%|████████▍ | 245/291 [00:09<00:00, 51.78it/s] Loading 0: 86%|████████▋ | 251/291 [00:09<00:00, 52.50it/s] Loading 0: 89%|████████▊ | 258/291 [00:10<00:00, 48.93it/s] Loading 0: 91%|█████████▏| 266/291 [00:10<00:00, 38.55it/s] Loading 0: 93%|█████████▎| 272/291 [00:10<00:00, 38.94it/s] Loading 0: 95%|█████████▌| 277/291 [00:10<00:00, 40.93it/s] Loading 0: 98%|█████████▊| 284/291 [00:10<00:00, 46.40it/s] Loading 0: 100%|█████████▉| 290/291 [00:10<00:00, 45.79it/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-v77-mkmlizer: warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v77-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-v77-mkmlizer: warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v77-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-v77-mkmlizer: warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v77-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
chaiml-sao10k-l3-rp-v3-3-v77-mkmlizer: Saving duration: 1.404s
chaiml-sao10k-l3-rp-v3-3-v77-mkmlizer: Processed model rirv938/retune_gpt2_xl_on_chaiml_sao10k_step_585 in 8.584s
chaiml-sao10k-l3-rp-v3-3-v77-mkmlizer: creating bucket guanaco-reward-models
Failed to get response for submission blend_sugom_2024-08-01: 'BlendChatApi' object has no attribute 'tags'
chaiml-sao10k-l3-rp-v3-3-v77-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v77_reward/tokenizer_config.json
chaiml-sao10k-l3-rp-v3-3-v77-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v77_reward/config.json
chaiml-sao10k-l3-rp-v3-3-v77-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v77_reward/special_tokens_map.json
chaiml-sao10k-l3-rp-v3-3-v77-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v77_reward/merges.txt
chaiml-sao10k-l3-rp-v3-3-v77-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v77_reward/vocab.json
chaiml-sao10k-l3-rp-v3-3-v77-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v77_reward/tokenizer.json
chaiml-sao10k-l3-rp-v3-3-v77-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v77_reward/reward.tensors
Job chaiml-sao10k-l3-rp-v3-3-v77-mkmlizer completed after 84.74s with status: succeeded
Stopping job with name chaiml-sao10k-l3-rp-v3-3-v77-mkmlizer
Pipeline stage MKMLizer completed in 85.81s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Failed to get response for submission blend_sugom_2024-08-01: 'BlendChatApi' object has no attribute 'tags'
Creating inference service chaiml-sao10k-l3-rp-v3-3-v77
Waiting for inference service chaiml-sao10k-l3-rp-v3-3-v77 to be ready
Failed to get response for submission blend_sugom_2024-08-01: 'BlendChatApi' object has no attribute 'tags'
Failed to get response for submission blend_sugom_2024-08-01: 'BlendChatApi' object has no attribute 'tags'
Failed to get response for submission blend_sugom_2024-08-01: 'BlendChatApi' object has no attribute 'tags'
Failed to get response for submission blend_megit_2024-08-01: ('http://jellywibble-vampirekingb-5114-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:54898->127.0.0.1:8080: read: connection reset by peer\n')
Inference service chaiml-sao10k-l3-rp-v3-3-v77 ready after 131.08593821525574s
Pipeline stage ISVCDeployer completed in 132.73s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.032277822494507s
Received healthy response to inference request in 1.2021372318267822s
Received healthy response to inference request in 1.2544310092926025s
Failed to get response for submission blend_sugom_2024-08-01: 'BlendChatApi' object has no attribute 'tags'
Received healthy response to inference request in 1.2569334506988525s
Received healthy response to inference request in 1.2427866458892822s
5 requests
0 failed requests
5th percentile: 1.2102671146392823
10th percentile: 1.2183969974517823
20th percentile: 1.2346567630767822
30th percentile: 1.2451155185699463
40th percentile: 1.2497732639312744
50th percentile: 1.2544310092926025
60th percentile: 1.2554319858551026
70th percentile: 1.2564329624176025
80th percentile: 1.4120023250579836
90th percentile: 1.7221400737762451
95th percentile: 1.8772089481353758
99th percentile: 2.001264047622681
mean time: 1.3977132320404053
Pipeline stage StressChecker completed in 7.67s
chaiml-sao10k-l3-rp-v3-3_v77 status is now deployed due to DeploymentManager action
chaiml-sao10k-l3-rp-v3-3_v77 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of chaiml-sao10k-l3-rp-v3-3_v77
Running pipeline stage ISVCDeleter
Checking if service chaiml-sao10k-l3-rp-v3-3-v77 is running
Tearing down inference service chaiml-sao10k-l3-rp-v3-3-v77
Service chaiml-sao10k-l3-rp-v3-3-v77 has been torndown
Pipeline stage ISVCDeleter completed in 5.34s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key chaiml-sao10k-l3-rp-v3-3-v77/config.json from bucket guanaco-mkml-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v77/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v77/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v77/tokenizer.json from bucket guanaco-mkml-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v77/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key chaiml-sao10k-l3-rp-v3-3-v77_reward/config.json from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v77_reward/merges.txt from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v77_reward/reward.tensors from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v77_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v77_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v77_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v77_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.66s
chaiml-sao10k-l3-rp-v3-3_v77 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics