submission_id: chaiml-sao10k-l3-rp-v3-3_v7
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|>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: 2024-07-10T17:59:24+00:00
model_name: chaiml-sao10k-l3-rp-v3-3_v7
model_group: ChaiML/sao10k-l3-rp-v3-3
num_battles: 30502
num_wins: 17798
celo_rating: 1229.98
propriety_score: 0.7232727953566748
propriety_total_count: 5341.0
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_v7
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: 2024-07-10
win_ratio: 0.5835027211330405
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name chaiml-sao10k-l3-rp-v3-3-v7-mkmlizer
Waiting for job on chaiml-sao10k-l3-rp-v3-3-v7-mkmlizer to finish
chaiml-sao10k-l3-rp-v3-3-v7-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-sao10k-l3-rp-v3-3-v7-mkmlizer: ║ _____ __ __ ║
chaiml-sao10k-l3-rp-v3-3-v7-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-sao10k-l3-rp-v3-3-v7-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-sao10k-l3-rp-v3-3-v7-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-sao10k-l3-rp-v3-3-v7-mkmlizer: ║ /___/ ║
chaiml-sao10k-l3-rp-v3-3-v7-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v7-mkmlizer: ║ Version: 0.8.14 ║
chaiml-sao10k-l3-rp-v3-3-v7-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-sao10k-l3-rp-v3-3-v7-mkmlizer: ║ https://mk1.ai ║
chaiml-sao10k-l3-rp-v3-3-v7-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v7-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-sao10k-l3-rp-v3-3-v7-mkmlizer: ║ belonging to: ║
chaiml-sao10k-l3-rp-v3-3-v7-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v7-mkmlizer: ║ Chai Research Corp. ║
chaiml-sao10k-l3-rp-v3-3-v7-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-sao10k-l3-rp-v3-3-v7-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
chaiml-sao10k-l3-rp-v3-3-v7-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v7-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission blend_pefis_2024-07-04: ('http://mistralai-mixtral-8x7b-3473-v33-predictor-default.tenant-chaiml-guanaco.knative.ord1.coreweave.cloud/v1/models/GPT-J-6B-lit-v2:predict', '{"error":"TypeError : SamplingParameters.__init__() got an unexpected keyword argument \'min_p\'"}')
chaiml-sao10k-l3-rp-v3-3-v7-mkmlizer: Downloaded to shared memory in 40.415s
chaiml-sao10k-l3-rp-v3-3-v7-mkmlizer: quantizing model to /dev/shm/model_cache
chaiml-sao10k-l3-rp-v3-3-v7-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-sao10k-l3-rp-v3-3-v7-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:05<13:37, 2.83s/it] Loading 0: 5%|▍ | 14/291 [00:05<01:24, 3.29it/s] Loading 0: 10%|▉ | 28/291 [00:05<00:33, 7.90it/s] Loading 0: 14%|█▍ | 41/291 [00:05<00:18, 13.47it/s] Loading 0: 19%|█▉ | 55/291 [00:06<00:11, 21.21it/s] Loading 0: 23%|██▎ | 67/291 [00:06<00:10, 22.03it/s] Loading 0: 27%|██▋ | 78/291 [00:06<00:07, 28.78it/s] Loading 0: 32%|███▏ | 94/291 [00:06<00:04, 41.53it/s] Loading 0: 36%|███▌ | 105/291 [00:06<00:03, 48.96it/s] Loading 0: 41%|████ | 118/291 [00:07<00:02, 60.64it/s] Loading 0: 45%|████▍ | 130/291 [00:07<00:02, 70.94it/s] Loading 0: 49%|████▉ | 142/291 [00:07<00:02, 68.96it/s] Loading 0: 52%|█████▏ | 152/291 [00:07<00:02, 66.13it/s] Loading 0: 57%|█████▋ | 166/291 [00:08<00:02, 43.44it/s] Loading 0: 60%|██████ | 176/291 [00:08<00:02, 50.41it/s] Loading 0: 64%|██████▍ | 186/291 [00:08<00:01, 57.80it/s] Loading 0: 68%|██████▊ | 199/291 [00:08<00:01, 70.41it/s] Loading 0: 73%|███████▎ | 211/291 [00:08<00:01, 79.62it/s] Loading 0: 76%|███████▋ | 222/291 [00:08<00:00, 80.32it/s] Loading 0: 80%|████████ | 234/291 [00:08<00:00, 89.39it/s] Loading 0: 85%|████████▍ | 247/291 [00:08<00:00, 97.80it/s] Loading 0: 89%|████████▊ | 258/291 [00:08<00:00, 93.42it/s] Loading 0: 92%|█████████▏| 269/291 [00:09<00:00, 51.49it/s] Loading 0: 97%|█████████▋| 283/291 [00:09<00:00, 63.83it/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-v7-mkmlizer: quantized model in 29.949s
chaiml-sao10k-l3-rp-v3-3-v7-mkmlizer: Processed model ChaiML/sao10k-l3-rp-v3-3 in 70.364s
chaiml-sao10k-l3-rp-v3-3-v7-mkmlizer: creating bucket guanaco-mkml-models
chaiml-sao10k-l3-rp-v3-3-v7-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-sao10k-l3-rp-v3-3-v7-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v7
chaiml-sao10k-l3-rp-v3-3-v7-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v7/special_tokens_map.json
chaiml-sao10k-l3-rp-v3-3-v7-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v7/tokenizer_config.json
chaiml-sao10k-l3-rp-v3-3-v7-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v7/config.json
chaiml-sao10k-l3-rp-v3-3-v7-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v7/tokenizer.json
chaiml-sao10k-l3-rp-v3-3-v7-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v7/flywheel_model.0.safetensors
chaiml-sao10k-l3-rp-v3-3-v7-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
chaiml-sao10k-l3-rp-v3-3-v7-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-v7-mkmlizer: warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v7-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-v7-mkmlizer: warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v7-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-v7-mkmlizer: warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v7-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-v7-mkmlizer: warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v7-mkmlizer: Downloading shards: 0%| | 0/2 [00:00<?, ?it/s] Downloading shards: 50%|█████ | 1/2 [00:07<00:07, 7.04s/it] Downloading shards: 100%|██████████| 2/2 [00:09<00:00, 4.20s/it] Downloading shards: 100%|██████████| 2/2 [00:09<00:00, 4.62s/it]
chaiml-sao10k-l3-rp-v3-3-v7-mkmlizer: Loading checkpoint shards: 0%| | 0/2 [00:00<?, ?it/s] Loading checkpoint shards: 50%|█████ | 1/2 [00:00<00:00, 1.60it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 2.64it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 2.40it/s]
chaiml-sao10k-l3-rp-v3-3-v7-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
chaiml-sao10k-l3-rp-v3-3-v7-mkmlizer: Saving duration: 2.196s
chaiml-sao10k-l3-rp-v3-3-v7-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 13.890s
chaiml-sao10k-l3-rp-v3-3-v7-mkmlizer: creating bucket guanaco-reward-models
chaiml-sao10k-l3-rp-v3-3-v7-mkmlizer: Bucket 's3://guanaco-reward-models/' created
chaiml-sao10k-l3-rp-v3-3-v7-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v7_reward
chaiml-sao10k-l3-rp-v3-3-v7-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v7_reward/config.json
chaiml-sao10k-l3-rp-v3-3-v7-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v7_reward/merges.txt
chaiml-sao10k-l3-rp-v3-3-v7-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v7_reward/special_tokens_map.json
chaiml-sao10k-l3-rp-v3-3-v7-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v7_reward/tokenizer_config.json
chaiml-sao10k-l3-rp-v3-3-v7-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v7_reward/vocab.json
chaiml-sao10k-l3-rp-v3-3-v7-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v7_reward/tokenizer.json
chaiml-sao10k-l3-rp-v3-3-v7-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v7_reward/reward.tensors
Job chaiml-sao10k-l3-rp-v3-3-v7-mkmlizer completed after 114.78s with status: succeeded
Stopping job with name chaiml-sao10k-l3-rp-v3-3-v7-mkmlizer
Pipeline stage MKMLizer completed in 115.67s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service chaiml-sao10k-l3-rp-v3-3-v7
Waiting for inference service chaiml-sao10k-l3-rp-v3-3-v7 to be ready
Inference service chaiml-sao10k-l3-rp-v3-3-v7 ready after 50.317514419555664s
Pipeline stage ISVCDeployer completed in 57.23s
Running pipeline stage StressChecker
%s, retrying in %s seconds...
Received healthy response to inference request in 1.9694583415985107s
Received healthy response to inference request in 1.2472755908966064s
Received healthy response to inference request in 1.2848107814788818s
Received healthy response to inference request in 1.282945156097412s
Received healthy response to inference request in 1.2466156482696533s
5 requests
0 failed requests
5th percentile: 1.2467476367950439
10th percentile: 1.2468796253204346
20th percentile: 1.247143602371216
30th percentile: 1.2544095039367675
40th percentile: 1.26867733001709
50th percentile: 1.282945156097412
60th percentile: 1.28369140625
70th percentile: 1.284437656402588
80th percentile: 1.4217402935028076
90th percentile: 1.6955993175506592
95th percentile: 1.832528829574585
99th percentile: 1.9420724391937256
mean time: 1.4062211036682128
Pipeline stage StressChecker completed in 13.18s
chaiml-sao10k-l3-rp-v3-3_v7 status is now deployed due to DeploymentManager action
chaiml-sao10k-l3-rp-v3-3_v7 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics