submission_id: chaiml-sao10k-l3-rp-v3-3_v15
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 tension<|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: 2024-07-11T17:32:26+00:00
model_name: chaiml-sao10k-l3-rp-v3-3_v15
model_group: ChaiML/sao10k-l3-rp-v3-3
num_battles: 38335
num_wins: 20398
celo_rating: 1214.52
alignment_score: None
alignment_samples: 0
propriety_score: 0.7254520707758118
propriety_total_count: 5143.0
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_v15
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: 0.532098604408504
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name chaiml-sao10k-l3-rp-v3-3-v15-mkmlizer
Waiting for job on chaiml-sao10k-l3-rp-v3-3-v15-mkmlizer to finish
chaiml-sao10k-l3-rp-v3-3-v15-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-sao10k-l3-rp-v3-3-v15-mkmlizer: ║ _____ __ __ ║
chaiml-sao10k-l3-rp-v3-3-v15-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-sao10k-l3-rp-v3-3-v15-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-sao10k-l3-rp-v3-3-v15-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-sao10k-l3-rp-v3-3-v15-mkmlizer: ║ /___/ ║
chaiml-sao10k-l3-rp-v3-3-v15-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v15-mkmlizer: ║ Version: 0.8.14 ║
chaiml-sao10k-l3-rp-v3-3-v15-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-sao10k-l3-rp-v3-3-v15-mkmlizer: ║ https://mk1.ai ║
chaiml-sao10k-l3-rp-v3-3-v15-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v15-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-sao10k-l3-rp-v3-3-v15-mkmlizer: ║ belonging to: ║
chaiml-sao10k-l3-rp-v3-3-v15-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v15-mkmlizer: ║ Chai Research Corp. ║
chaiml-sao10k-l3-rp-v3-3-v15-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-sao10k-l3-rp-v3-3-v15-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
chaiml-sao10k-l3-rp-v3-3-v15-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v15-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-sao10k-l3-rp-v3-3-v15-mkmlizer: Downloaded to shared memory in 22.877s
chaiml-sao10k-l3-rp-v3-3-v15-mkmlizer: quantizing model to /dev/shm/model_cache
chaiml-sao10k-l3-rp-v3-3-v15-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
chaiml-sao10k-l3-rp-v3-3-v15-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:05<13:16, 2.75s/it] Loading 0: 5%|▍ | 14/291 [00:05<01:21, 3.38it/s] Loading 0: 10%|▉ | 28/291 [00:05<00:32, 8.13it/s] Loading 0: 14%|█▍ | 41/291 [00:05<00:18, 13.86it/s] Loading 0: 19%|█▉ | 56/291 [00:05<00:10, 22.44it/s] Loading 0: 24%|██▎ | 69/291 [00:06<00:09, 23.58it/s] Loading 0: 29%|██▉ | 85/291 [00:06<00:05, 34.65it/s] Loading 0: 33%|███▎ | 97/291 [00:06<00:04, 42.83it/s] Loading 0: 38%|███▊ | 112/291 [00:06<00:03, 56.06it/s] Loading 0: 43%|████▎ | 124/291 [00:06<00:02, 65.32it/s] Loading 0: 48%|████▊ | 139/291 [00:06<00:01, 80.30it/s] Loading 0: 52%|█████▏ | 152/291 [00:07<00:01, 89.01it/s] Loading 0: 57%|█████▋ | 166/291 [00:07<00:02, 56.42it/s] Loading 0: 61%|██████ | 177/291 [00:07<00:01, 63.43it/s] Loading 0: 66%|██████▋ | 193/291 [00:07<00:01, 79.59it/s] Loading 0: 70%|███████ | 205/291 [00:07<00:00, 86.72it/s] Loading 0: 76%|███████▌ | 220/291 [00:07<00:00, 100.11it/s] Loading 0: 80%|████████ | 233/291 [00:08<00:00, 105.53it/s] Loading 0: 85%|████████▍ | 247/291 [00:08<00:00, 107.68it/s] Loading 0: 89%|████████▉ | 260/291 [00:08<00:00, 106.62it/s] Loading 0: 93%|█████████▎| 272/291 [00:08<00:00, 59.92it/s] Loading 0: 98%|█████████▊| 284/291 [00:08<00:00, 68.61it/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-v15-mkmlizer: quantized model in 28.987s
chaiml-sao10k-l3-rp-v3-3-v15-mkmlizer: Processed model ChaiML/sao10k-l3-rp-v3-3 in 51.864s
chaiml-sao10k-l3-rp-v3-3-v15-mkmlizer: creating bucket guanaco-mkml-models
chaiml-sao10k-l3-rp-v3-3-v15-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-sao10k-l3-rp-v3-3-v15-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v15
chaiml-sao10k-l3-rp-v3-3-v15-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v15/special_tokens_map.json
chaiml-sao10k-l3-rp-v3-3-v15-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v15/config.json
chaiml-sao10k-l3-rp-v3-3-v15-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v15/tokenizer_config.json
chaiml-sao10k-l3-rp-v3-3-v15-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v15/tokenizer.json
chaiml-sao10k-l3-rp-v3-3-v15-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v15/flywheel_model.0.safetensors
chaiml-sao10k-l3-rp-v3-3-v15-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-v15-mkmlizer: warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v15-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-v15-mkmlizer: warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v15-mkmlizer: Downloading shards: 0%| | 0/2 [00:00<?, ?it/s] Downloading shards: 50%|█████ | 1/2 [00:06<00:06, 6.23s/it] Downloading shards: 100%|██████████| 2/2 [00:08<00:00, 3.98s/it] Downloading shards: 100%|██████████| 2/2 [00:08<00:00, 4.32s/it]
chaiml-sao10k-l3-rp-v3-3-v15-mkmlizer: Loading checkpoint shards: 0%| | 0/2 [00:00<?, ?it/s] Loading checkpoint shards: 50%|█████ | 1/2 [00:00<00:00, 1.66it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 2.70it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 2.47it/s]
chaiml-sao10k-l3-rp-v3-3-v15-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
chaiml-sao10k-l3-rp-v3-3-v15-mkmlizer: Saving duration: 2.164s
chaiml-sao10k-l3-rp-v3-3-v15-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 13.015s
chaiml-sao10k-l3-rp-v3-3-v15-mkmlizer: creating bucket guanaco-reward-models
chaiml-sao10k-l3-rp-v3-3-v15-mkmlizer: Bucket 's3://guanaco-reward-models/' created
chaiml-sao10k-l3-rp-v3-3-v15-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v15_reward
chaiml-sao10k-l3-rp-v3-3-v15-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v15_reward/config.json
chaiml-sao10k-l3-rp-v3-3-v15-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v15_reward/special_tokens_map.json
chaiml-sao10k-l3-rp-v3-3-v15-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v15_reward/tokenizer_config.json
chaiml-sao10k-l3-rp-v3-3-v15-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v15_reward/merges.txt
chaiml-sao10k-l3-rp-v3-3-v15-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v15_reward/vocab.json
chaiml-sao10k-l3-rp-v3-3-v15-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v15_reward/tokenizer.json
chaiml-sao10k-l3-rp-v3-3-v15-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v15_reward/reward.tensors
Job chaiml-sao10k-l3-rp-v3-3-v15-mkmlizer completed after 104.22s with status: succeeded
Stopping job with name chaiml-sao10k-l3-rp-v3-3-v15-mkmlizer
Pipeline stage MKMLizer completed in 105.24s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service chaiml-sao10k-l3-rp-v3-3-v15
Waiting for inference service chaiml-sao10k-l3-rp-v3-3-v15 to be ready
Inference service chaiml-sao10k-l3-rp-v3-3-v15 ready after 40.223461866378784s
Pipeline stage ISVCDeployer completed in 47.04s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9088780879974365s
Received healthy response to inference request in 1.2410953044891357s
Received healthy response to inference request in 1.2833232879638672s
Received healthy response to inference request in 1.240516185760498s
Received healthy response to inference request in 1.3367414474487305s
5 requests
0 failed requests
5th percentile: 1.2406320095062255
10th percentile: 1.240747833251953
20th percentile: 1.2409794807434082
30th percentile: 1.2495409011840821
40th percentile: 1.2664320945739747
50th percentile: 1.2833232879638672
60th percentile: 1.3046905517578125
70th percentile: 1.3260578155517577
80th percentile: 1.4511687755584717
90th percentile: 1.680023431777954
95th percentile: 1.7944507598876953
99th percentile: 1.8859926223754884
mean time: 1.4021108627319336
Pipeline stage StressChecker completed in 7.86s
chaiml-sao10k-l3-rp-v3-3_v15 status is now deployed due to DeploymentManager action
chaiml-sao10k-l3-rp-v3-3_v15 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics