submission_id: chaiml-sao10k-l3-rp-v3-3_v16
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 with aggression<|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: 2024-07-11T17:33:47+00:00
model_name: chaiml-sao10k-l3-rp-v3-3_v16
model_group: ChaiML/sao10k-l3-rp-v3-3
num_battles: 40262
num_wins: 20196
celo_rating: 1193.7
propriety_score: 0.6971614883007288
propriety_total_count: 5214.0
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_v16
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: 0.5016144255128906
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name chaiml-sao10k-l3-rp-v3-3-v16-mkmlizer
Waiting for job on chaiml-sao10k-l3-rp-v3-3-v16-mkmlizer to finish
chaiml-sao10k-l3-rp-v3-3-v16-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-sao10k-l3-rp-v3-3-v16-mkmlizer: ║ _____ __ __ ║
chaiml-sao10k-l3-rp-v3-3-v16-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-sao10k-l3-rp-v3-3-v16-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-sao10k-l3-rp-v3-3-v16-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-sao10k-l3-rp-v3-3-v16-mkmlizer: ║ /___/ ║
chaiml-sao10k-l3-rp-v3-3-v16-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v16-mkmlizer: ║ Version: 0.8.14 ║
chaiml-sao10k-l3-rp-v3-3-v16-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-sao10k-l3-rp-v3-3-v16-mkmlizer: ║ https://mk1.ai ║
chaiml-sao10k-l3-rp-v3-3-v16-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v16-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-sao10k-l3-rp-v3-3-v16-mkmlizer: ║ belonging to: ║
chaiml-sao10k-l3-rp-v3-3-v16-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v16-mkmlizer: ║ Chai Research Corp. ║
chaiml-sao10k-l3-rp-v3-3-v16-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-sao10k-l3-rp-v3-3-v16-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
chaiml-sao10k-l3-rp-v3-3-v16-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v16-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-sao10k-l3-rp-v3-3-v16-mkmlizer: Downloaded to shared memory in 24.127s
chaiml-sao10k-l3-rp-v3-3-v16-mkmlizer: quantizing model to /dev/shm/model_cache
chaiml-sao10k-l3-rp-v3-3-v16-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-sao10k-l3-rp-v3-3-v16-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:05<13:17, 2.76s/it] Loading 0: 5%|▍ | 14/291 [00:05<01:22, 3.37it/s] Loading 0: 10%|▉ | 28/291 [00:05<00:32, 8.12it/s] Loading 0: 14%|█▍ | 41/291 [00:05<00:18, 13.83it/s] Loading 0: 19%|█▉ | 55/291 [00:05<00:10, 21.75it/s] Loading 0: 23%|██▎ | 67/291 [00:06<00:09, 23.13it/s] Loading 0: 27%|██▋ | 78/291 [00:06<00:07, 30.23it/s] Loading 0: 32%|███▏ | 94/291 [00:06<00:04, 43.96it/s] Loading 0: 36%|███▋ | 106/291 [00:06<00:03, 53.60it/s] Loading 0: 42%|████▏ | 121/291 [00:06<00:02, 68.65it/s] Loading 0: 46%|████▌ | 134/291 [00:06<00:02, 78.32it/s] Loading 0: 51%|█████ | 148/291 [00:07<00:01, 89.85it/s] Loading 0: 55%|█████▌ | 161/291 [00:07<00:01, 97.30it/s] Loading 0: 60%|█████▉ | 174/291 [00:07<00:02, 53.97it/s] Loading 0: 63%|██████▎ | 184/291 [00:07<00:01, 57.87it/s] Loading 0: 67%|██████▋ | 194/291 [00:07<00:01, 64.72it/s] Loading 0: 71%|███████▏ | 208/291 [00:07<00:01, 79.29it/s] Loading 0: 76%|███████▌ | 221/291 [00:08<00:00, 87.57it/s] Loading 0: 81%|████████ | 235/291 [00:08<00:00, 99.14it/s] Loading 0: 85%|████████▌ | 248/291 [00:08<00:00, 105.13it/s] Loading 0: 90%|█████████ | 263/291 [00:08<00:00, 116.26it/s] Loading 0: 95%|█████████▍| 276/291 [00:08<00:00, 60.97it/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-v16-mkmlizer: creating bucket guanaco-mkml-models
chaiml-sao10k-l3-rp-v3-3-v16-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-sao10k-l3-rp-v3-3-v16-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v16
chaiml-sao10k-l3-rp-v3-3-v16-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v16/special_tokens_map.json
chaiml-sao10k-l3-rp-v3-3-v16-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v16/tokenizer_config.json
chaiml-sao10k-l3-rp-v3-3-v16-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v16/config.json
chaiml-sao10k-l3-rp-v3-3-v16-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v16/tokenizer.json
chaiml-sao10k-l3-rp-v3-3-v16-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v16/flywheel_model.0.safetensors
chaiml-sao10k-l3-rp-v3-3-v16-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
chaiml-sao10k-l3-rp-v3-3-v16-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-v16-mkmlizer: warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v16-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-v16-mkmlizer: warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v16-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-v16-mkmlizer: warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v16-mkmlizer: Downloading shards: 0%| | 0/2 [00:00<?, ?it/s] Downloading shards: 50%|█████ | 1/2 [00:06<00:06, 6.76s/it] Downloading shards: 100%|██████████| 2/2 [00:08<00:00, 3.97s/it] Downloading shards: 100%|██████████| 2/2 [00:08<00:00, 4.39s/it]
chaiml-sao10k-l3-rp-v3-3-v16-mkmlizer: Loading checkpoint shards: 0%| | 0/2 [00:00<?, ?it/s] Loading checkpoint shards: 50%|█████ | 1/2 [00:00<00:00, 1.61it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 2.63it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 2.40it/s]
chaiml-sao10k-l3-rp-v3-3-v16-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
Connection pool is full, discarding connection: %s
chaiml-sao10k-l3-rp-v3-3-v16-mkmlizer: Saving duration: 2.175s
chaiml-sao10k-l3-rp-v3-3-v16-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 13.318s
chaiml-sao10k-l3-rp-v3-3-v16-mkmlizer: creating bucket guanaco-reward-models
chaiml-sao10k-l3-rp-v3-3-v16-mkmlizer: Bucket 's3://guanaco-reward-models/' created
chaiml-sao10k-l3-rp-v3-3-v16-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v16_reward
chaiml-sao10k-l3-rp-v3-3-v16-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v16_reward/special_tokens_map.json
chaiml-sao10k-l3-rp-v3-3-v16-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v16_reward/config.json
chaiml-sao10k-l3-rp-v3-3-v16-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v16_reward/tokenizer_config.json
chaiml-sao10k-l3-rp-v3-3-v16-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v16_reward/vocab.json
chaiml-sao10k-l3-rp-v3-3-v16-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v16_reward/merges.txt
chaiml-sao10k-l3-rp-v3-3-v16-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v16_reward/tokenizer.json
chaiml-sao10k-l3-rp-v3-3-v16-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v16_reward/reward.tensors
Job chaiml-sao10k-l3-rp-v3-3-v16-mkmlizer completed after 104.22s with status: succeeded
Stopping job with name chaiml-sao10k-l3-rp-v3-3-v16-mkmlizer
Pipeline stage MKMLizer completed in 105.09s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service chaiml-sao10k-l3-rp-v3-3-v16
Waiting for inference service chaiml-sao10k-l3-rp-v3-3-v16 to be ready
Inference service chaiml-sao10k-l3-rp-v3-3-v16 ready after 60.329782485961914s
Pipeline stage ISVCDeployer completed in 66.83s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.977473497390747s
Received healthy response to inference request in 1.290095329284668s
Received healthy response to inference request in 1.3164234161376953s
Received healthy response to inference request in 1.2889952659606934s
Received healthy response to inference request in 1.3176331520080566s
5 requests
0 failed requests
5th percentile: 1.2892152786254882
10th percentile: 1.2894352912902831
20th percentile: 1.289875316619873
30th percentile: 1.2953609466552733
40th percentile: 1.3058921813964843
50th percentile: 1.3164234161376953
60th percentile: 1.3169073104858398
70th percentile: 1.3173912048339844
80th percentile: 1.4496012210845948
90th percentile: 1.713537359237671
95th percentile: 1.845505428314209
99th percentile: 1.9510798835754395
mean time: 1.438124132156372
Pipeline stage StressChecker completed in 7.94s
chaiml-sao10k-l3-rp-v3-3_v16 status is now deployed due to DeploymentManager action
chaiml-sao10k-l3-rp-v3-3_v16 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics