submission_id: chaiml-sao10k-l3-rp-v3-3_v19
developer_uid: robert_irvine
status: inactive
model_repo: ChaiML/sao10k-l3-rp-v3-3
reward_repo: ChaiML/gpt2_xl_pairwise_89m_step_347634
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}
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|>system<|end_header_id|>\n\nrespond intelligently<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}:', 'truncate_by_message': False}
reward_formatter: {'memory_template': '""', 'prompt_template': '""', 'bot_template': 'Bot: {message}\n', 'user_template': 'User: {message}\n', 'response_template': 'Bot:', 'truncate_by_message': False}
timestamp: 2024-07-11T17:39:32+00:00
model_name: chaiml-sao10k-l3-rp-v3-3_v19
model_group: ChaiML/sao10k-l3-rp-v3-3
num_battles: 39392
num_wins: 21434
celo_rating: 1223.1
propriety_score: 0.7221157531621311
propriety_total_count: 5218.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
display_name: chaiml-sao10k-l3-rp-v3-3_v19
ineligible_reason: None
language_model: ChaiML/sao10k-l3-rp-v3-3
model_size: 8B
reward_model: ChaiML/gpt2_xl_pairwise_89m_step_347634
us_pacific_date: 2024-07-11
win_ratio: 0.5441206336311941
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name chaiml-sao10k-l3-rp-v3-3-v19-mkmlizer
Waiting for job on chaiml-sao10k-l3-rp-v3-3-v19-mkmlizer to finish
Stopping job with name chaiml-sao10k-l3-rp-v3-3-v19-mkmlizer
%s, retrying in %s seconds...
Starting job with name chaiml-sao10k-l3-rp-v3-3-v19-mkmlizer
Waiting for job on chaiml-sao10k-l3-rp-v3-3-v19-mkmlizer to finish
chaiml-sao10k-l3-rp-v3-3-v19-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-sao10k-l3-rp-v3-3-v19-mkmlizer: ║ _____ __ __ ║
chaiml-sao10k-l3-rp-v3-3-v19-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-sao10k-l3-rp-v3-3-v19-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-sao10k-l3-rp-v3-3-v19-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-sao10k-l3-rp-v3-3-v19-mkmlizer: ║ /___/ ║
chaiml-sao10k-l3-rp-v3-3-v19-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v19-mkmlizer: ║ Version: 0.8.14 ║
chaiml-sao10k-l3-rp-v3-3-v19-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-sao10k-l3-rp-v3-3-v19-mkmlizer: ║ https://mk1.ai ║
chaiml-sao10k-l3-rp-v3-3-v19-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v19-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-sao10k-l3-rp-v3-3-v19-mkmlizer: ║ belonging to: ║
chaiml-sao10k-l3-rp-v3-3-v19-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v19-mkmlizer: ║ Chai Research Corp. ║
chaiml-sao10k-l3-rp-v3-3-v19-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-sao10k-l3-rp-v3-3-v19-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
chaiml-sao10k-l3-rp-v3-3-v19-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v19-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-sao10k-l3-rp-v3-3-v19-mkmlizer: Downloaded to shared memory in 27.489s
chaiml-sao10k-l3-rp-v3-3-v19-mkmlizer: quantizing model to /dev/shm/model_cache
chaiml-sao10k-l3-rp-v3-3-v19-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-sao10k-l3-rp-v3-3-v19-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:05<13:35, 2.82s/it] Loading 0: 5%|▍ | 14/291 [00:05<01:24, 3.30it/s] Loading 0: 10%|▉ | 28/291 [00:05<00:33, 7.93it/s] Loading 0: 14%|█▍ | 41/291 [00:05<00:18, 13.53it/s] Loading 0: 19%|█▉ | 55/291 [00:06<00:11, 21.32it/s] Loading 0: 23%|██▎ | 67/291 [00:06<00:10, 22.26it/s] Loading 0: 27%|██▋ | 78/291 [00:06<00:07, 28.95it/s] Loading 0: 32%|███▏ | 94/291 [00:06<00:04, 41.73it/s] Loading 0: 36%|███▌ | 105/291 [00:06<00:03, 49.40it/s] Loading 0: 42%|████▏ | 121/291 [00:07<00:02, 65.37it/s] Loading 0: 46%|████▌ | 133/291 [00:07<00:02, 72.99it/s] Loading 0: 51%|█████ | 148/291 [00:07<00:01, 85.62it/s] Loading 0: 55%|█████▍ | 160/291 [00:07<00:01, 91.26it/s] Loading 0: 59%|█████▉ | 172/291 [00:07<00:02, 54.03it/s] Loading 0: 64%|██████▎ | 185/291 [00:07<00:01, 64.93it/s] Loading 0: 68%|██████▊ | 199/291 [00:08<00:01, 78.18it/s] Loading 0: 73%|███████▎ | 212/291 [00:08<00:00, 86.92it/s] Loading 0: 77%|███████▋ | 225/291 [00:08<00:00, 95.61it/s] Loading 0: 82%|████████▏ | 239/291 [00:08<00:00, 102.68it/s] Loading 0: 87%|████████▋ | 253/291 [00:08<00:00, 111.54it/s] Loading 0: 91%|█████████▏| 266/291 [00:08<00:00, 60.14it/s] Loading 0: 96%|█████████▌| 279/291 [00:09<00:00, 71.28it/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-v19-mkmlizer: quantized model in 29.682s
chaiml-sao10k-l3-rp-v3-3-v19-mkmlizer: Processed model ChaiML/sao10k-l3-rp-v3-3 in 57.172s
chaiml-sao10k-l3-rp-v3-3-v19-mkmlizer: creating bucket guanaco-mkml-models
chaiml-sao10k-l3-rp-v3-3-v19-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-sao10k-l3-rp-v3-3-v19-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v19
chaiml-sao10k-l3-rp-v3-3-v19-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v19/config.json
chaiml-sao10k-l3-rp-v3-3-v19-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v19/special_tokens_map.json
chaiml-sao10k-l3-rp-v3-3-v19-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v19/tokenizer_config.json
chaiml-sao10k-l3-rp-v3-3-v19-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v19/tokenizer.json
chaiml-sao10k-l3-rp-v3-3-v19-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v19/flywheel_model.0.safetensors
chaiml-sao10k-l3-rp-v3-3-v19-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
chaiml-sao10k-l3-rp-v3-3-v19-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:919: 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-v19-mkmlizer: warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v19-mkmlizer: /opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py:1132: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`.
chaiml-sao10k-l3-rp-v3-3-v19-mkmlizer: warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v19-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:769: 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-v19-mkmlizer: warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v19-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py:468: 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-v19-mkmlizer: warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v19-mkmlizer: Downloading shards: 0%| | 0/2 [00:00<?, ?it/s] Downloading shards: 50%|█████ | 1/2 [00:07<00:07, 7.27s/it] Downloading shards: 100%|██████████| 2/2 [00:12<00:00, 6.05s/it] Downloading shards: 100%|██████████| 2/2 [00:12<00:00, 6.24s/it]
chaiml-sao10k-l3-rp-v3-3-v19-mkmlizer: Loading checkpoint shards: 0%| | 0/2 [00:00<?, ?it/s] Loading checkpoint shards: 50%|█████ | 1/2 [00:00<00:00, 1.62it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 2.67it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 2.43it/s]
chaiml-sao10k-l3-rp-v3-3-v19-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
chaiml-sao10k-l3-rp-v3-3-v19-mkmlizer: Saving duration: 2.208s
chaiml-sao10k-l3-rp-v3-3-v19-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 17.739s
chaiml-sao10k-l3-rp-v3-3-v19-mkmlizer: creating bucket guanaco-reward-models
chaiml-sao10k-l3-rp-v3-3-v19-mkmlizer: Bucket 's3://guanaco-reward-models/' created
chaiml-sao10k-l3-rp-v3-3-v19-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v19_reward
chaiml-sao10k-l3-rp-v3-3-v19-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v19_reward/config.json
chaiml-sao10k-l3-rp-v3-3-v19-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v19_reward/special_tokens_map.json
chaiml-sao10k-l3-rp-v3-3-v19-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v19_reward/tokenizer_config.json
chaiml-sao10k-l3-rp-v3-3-v19-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v19_reward/merges.txt
chaiml-sao10k-l3-rp-v3-3-v19-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v19_reward/vocab.json
chaiml-sao10k-l3-rp-v3-3-v19-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v19_reward/tokenizer.json
chaiml-sao10k-l3-rp-v3-3-v19-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v19_reward/reward.tensors
Job chaiml-sao10k-l3-rp-v3-3-v19-mkmlizer completed after 104.4s with status: succeeded
Stopping job with name chaiml-sao10k-l3-rp-v3-3-v19-mkmlizer
Pipeline stage MKMLizer completed in 106.08s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service chaiml-sao10k-l3-rp-v3-3-v19
Waiting for inference service chaiml-sao10k-l3-rp-v3-3-v19 to be ready
Inference service chaiml-sao10k-l3-rp-v3-3-v19 ready after 60.35262322425842s
Pipeline stage ISVCDeployer completed in 69.41s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1079020500183105s
Received healthy response to inference request in 1.3205866813659668s
Received healthy response to inference request in 1.3489820957183838s
Received healthy response to inference request in 1.290245532989502s
Received healthy response to inference request in 1.323296070098877s
5 requests
0 failed requests
5th percentile: 1.296313762664795
10th percentile: 1.302381992340088
20th percentile: 1.3145184516906738
30th percentile: 1.3211285591125488
40th percentile: 1.322212314605713
50th percentile: 1.323296070098877
60th percentile: 1.3335704803466797
70th percentile: 1.3438448905944824
80th percentile: 1.5007660865783692
90th percentile: 1.80433406829834
95th percentile: 1.9561180591583252
99th percentile: 2.0775452518463133
mean time: 1.478202486038208
Pipeline stage StressChecker completed in 8.05s
chaiml-sao10k-l3-rp-v3-3_v19 status is now deployed due to DeploymentManager action
chaiml-sao10k-l3-rp-v3-3_v19 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics