submission_id: chaiml-sao10k-l3-rp-v3-3_v50
developer_uid: robert_irvine
alignment_samples: 0
best_of: 4
celo_rating: 1175.12
display_name: chaiml-sao10k-l3-rp-v3-3_v50
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': 4, 'max_output_tokens': 64, 'reward_max_token_input': 512}
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_v50
model_num_parameters: 8030261248.0
model_repo: ChaiML/sao10k-l3-rp-v3-3
model_size: 8B
num_battles: 11702
num_wins: 5619
propriety_score: 0.7058823529411765
propriety_total_count: 1224.0
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/gpt2_improves_the_story_512
status: torndown
submission_type: basic
timestamp: 2024-07-24T00:07:55+00:00
us_pacific_date: 2024-07-23
win_ratio: 0.4801743291745001
Download Preference Data
Resubmit model
Running pipeline stage MKMLizer
Starting job with name chaiml-sao10k-l3-rp-v3-3-v50-mkmlizer
Waiting for job on chaiml-sao10k-l3-rp-v3-3-v50-mkmlizer to finish
chaiml-sao10k-l3-rp-v3-3-v50-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-sao10k-l3-rp-v3-3-v50-mkmlizer: ║ _____ __ __ ║
chaiml-sao10k-l3-rp-v3-3-v50-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-sao10k-l3-rp-v3-3-v50-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-sao10k-l3-rp-v3-3-v50-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-sao10k-l3-rp-v3-3-v50-mkmlizer: ║ /___/ ║
chaiml-sao10k-l3-rp-v3-3-v50-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v50-mkmlizer: ║ Version: 0.9.5.post3 ║
chaiml-sao10k-l3-rp-v3-3-v50-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-sao10k-l3-rp-v3-3-v50-mkmlizer: ║ https://mk1.ai ║
chaiml-sao10k-l3-rp-v3-3-v50-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v50-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-sao10k-l3-rp-v3-3-v50-mkmlizer: ║ belonging to: ║
chaiml-sao10k-l3-rp-v3-3-v50-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v50-mkmlizer: ║ Chai Research Corp. ║
chaiml-sao10k-l3-rp-v3-3-v50-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-sao10k-l3-rp-v3-3-v50-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
chaiml-sao10k-l3-rp-v3-3-v50-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v50-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-sao10k-l3-rp-v3-3-v50-mkmlizer: Downloaded to shared memory in 23.498s
chaiml-sao10k-l3-rp-v3-3-v50-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpu7lkw75m, device:0
chaiml-sao10k-l3-rp-v3-3-v50-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-sao10k-l3-rp-v3-3-v50-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<11:29, 2.39s/it] Loading 0: 5%|▍ | 14/291 [00:04<01:11, 3.89it/s] Loading 0: 11%|█ | 31/291 [00:04<00:24, 10.48it/s] Loading 0: 15%|█▌ | 45/291 [00:05<00:14, 17.42it/s] Loading 0: 20%|██ | 59/291 [00:05<00:08, 26.11it/s] Loading 0: 25%|██▍ | 72/291 [00:05<00:07, 30.47it/s] Loading 0: 30%|██▉ | 86/291 [00:05<00:04, 41.50it/s] Loading 0: 35%|███▌ | 103/291 [00:05<00:03, 56.98it/s] Loading 0: 40%|████ | 117/291 [00:05<00:02, 69.13it/s] Loading 0: 45%|████▌ | 131/291 [00:05<00:01, 81.32it/s] Loading 0: 51%|█████ | 148/291 [00:05<00:01, 97.55it/s] Loading 0: 56%|█████▌ | 162/291 [00:06<00:01, 106.09it/s] Loading 0: 60%|██████ | 176/291 [00:06<00:01, 79.43it/s] Loading 0: 66%|██████▋ | 193/291 [00:06<00:01, 94.98it/s] Loading 0: 71%|███████ | 207/291 [00:06<00:00, 103.95it/s] Loading 0: 76%|███████▌ | 221/291 [00:06<00:00, 109.47it/s] Loading 0: 82%|████████▏ | 238/291 [00:06<00:00, 121.25it/s] Loading 0: 87%|████████▋ | 252/291 [00:06<00:00, 124.66it/s] Loading 0: 91%|█████████▏| 266/291 [00:07<00:00, 84.98it/s] Loading 0: 97%|█████████▋| 283/291 [00:07<00:00, 100.22it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
chaiml-sao10k-l3-rp-v3-3-v50-mkmlizer: quantized model in 22.020s
chaiml-sao10k-l3-rp-v3-3-v50-mkmlizer: Processed model ChaiML/sao10k-l3-rp-v3-3 in 45.517s
chaiml-sao10k-l3-rp-v3-3-v50-mkmlizer: creating bucket guanaco-mkml-models
chaiml-sao10k-l3-rp-v3-3-v50-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-sao10k-l3-rp-v3-3-v50-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v50
chaiml-sao10k-l3-rp-v3-3-v50-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v50/tokenizer.json
chaiml-sao10k-l3-rp-v3-3-v50-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v50/flywheel_model.0.safetensors
chaiml-sao10k-l3-rp-v3-3-v50-mkmlizer: loading reward model from rirv938/gpt2_improves_the_story_512
chaiml-sao10k-l3-rp-v3-3-v50-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:950: 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-v50-mkmlizer: warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v50-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:778: 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-v50-mkmlizer: warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v50-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-v50-mkmlizer: warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v50-mkmlizer: Downloading shards: 0%| | 0/2 [00:00<?, ?it/s] Downloading shards: 50%|█████ | 1/2 [00:06<00:06, 6.73s/it] Downloading shards: 100%|██████████| 2/2 [00:09<00:00, 4.55s/it] Downloading shards: 100%|██████████| 2/2 [00:09<00:00, 4.87s/it]
chaiml-sao10k-l3-rp-v3-3-v50-mkmlizer: Loading checkpoint shards: 0%| | 0/2 [00:00<?, ?it/s] Loading checkpoint shards: 50%|█████ | 1/2 [00:00<00:00, 2.48it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 4.08it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 3.72it/s]
chaiml-sao10k-l3-rp-v3-3-v50-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
chaiml-sao10k-l3-rp-v3-3-v50-mkmlizer: Saving duration: 1.368s
chaiml-sao10k-l3-rp-v3-3-v50-mkmlizer: Processed model rirv938/gpt2_improves_the_story_512 in 15.301s
chaiml-sao10k-l3-rp-v3-3-v50-mkmlizer: creating bucket guanaco-reward-models
chaiml-sao10k-l3-rp-v3-3-v50-mkmlizer: Bucket 's3://guanaco-reward-models/' created
chaiml-sao10k-l3-rp-v3-3-v50-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v50_reward
chaiml-sao10k-l3-rp-v3-3-v50-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v50_reward/special_tokens_map.json
chaiml-sao10k-l3-rp-v3-3-v50-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v50_reward/config.json
chaiml-sao10k-l3-rp-v3-3-v50-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v50_reward/tokenizer_config.json
chaiml-sao10k-l3-rp-v3-3-v50-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v50_reward/merges.txt
chaiml-sao10k-l3-rp-v3-3-v50-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v50_reward/vocab.json
chaiml-sao10k-l3-rp-v3-3-v50-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v50_reward/tokenizer.json
chaiml-sao10k-l3-rp-v3-3-v50-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v50_reward/reward.tensors
Job chaiml-sao10k-l3-rp-v3-3-v50-mkmlizer completed after 95.37s with status: succeeded
Stopping job with name chaiml-sao10k-l3-rp-v3-3-v50-mkmlizer
Pipeline stage MKMLizer completed in 96.45s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service chaiml-sao10k-l3-rp-v3-3-v50
Waiting for inference service chaiml-sao10k-l3-rp-v3-3-v50 to be ready
Inference service chaiml-sao10k-l3-rp-v3-3-v50 ready after 50.541502475738525s
Pipeline stage ISVCDeployer completed in 52.20s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0081491470336914s
Received healthy response to inference request in 1.1802146434783936s
Received healthy response to inference request in 1.1549692153930664s
Received healthy response to inference request in 1.1705830097198486s
Received healthy response to inference request in 1.1792981624603271s
5 requests
0 failed requests
5th percentile: 1.1580919742584228
10th percentile: 1.1612147331237792
20th percentile: 1.1674602508544922
30th percentile: 1.1723260402679443
40th percentile: 1.1758121013641358
50th percentile: 1.1792981624603271
60th percentile: 1.1796647548675536
70th percentile: 1.1800313472747803
80th percentile: 1.3458015441894533
90th percentile: 1.6769753456115724
95th percentile: 1.8425622463226317
99th percentile: 1.9750317668914794
mean time: 1.3386428356170654
Pipeline stage StressChecker completed in 7.42s
chaiml-sao10k-l3-rp-v3-3_v50 status is now deployed due to DeploymentManager action
chaiml-sao10k-l3-rp-v3-3_v50 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of chaiml-sao10k-l3-rp-v3-3_v50
Running pipeline stage ISVCDeleter
Checking if service chaiml-sao10k-l3-rp-v3-3-v50 is running
Tearing down inference service chaiml-sao10k-l3-rp-v3-3-v50
Service chaiml-sao10k-l3-rp-v3-3-v50 has been torndown
Pipeline stage ISVCDeleter completed in 5.18s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key chaiml-sao10k-l3-rp-v3-3-v50/config.json from bucket guanaco-mkml-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v50/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v50/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v50/tokenizer.json from bucket guanaco-mkml-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v50/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key chaiml-sao10k-l3-rp-v3-3-v50_reward/config.json from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v50_reward/merges.txt from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v50_reward/reward.tensors from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v50_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v50_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v50_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v50_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.54s
chaiml-sao10k-l3-rp-v3-3_v50 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics