submission_id: chaiml-sao10k-l3-rp-v3-3_v22
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 advice<|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: 2024-07-11T18:10:34+00:00
model_name: chaiml-sao10k-l3-rp-v3-3_v22
model_group: ChaiML/sao10k-l3-rp-v3-3
num_battles: 42791
num_wins: 22557
celo_rating: 1212.33
propriety_score: 0.7156312262271327
propriety_total_count: 5521.0
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_v22
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: 0.5271435582248604
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name chaiml-sao10k-l3-rp-v3-3-v22-mkmlizer
Waiting for job on chaiml-sao10k-l3-rp-v3-3-v22-mkmlizer to finish
Stopping job with name chaiml-sao10k-l3-rp-v3-3-v22-mkmlizer
%s, retrying in %s seconds...
Starting job with name chaiml-sao10k-l3-rp-v3-3-v22-mkmlizer
Waiting for job on chaiml-sao10k-l3-rp-v3-3-v22-mkmlizer to finish
chaiml-sao10k-l3-rp-v3-3-v22-mkmlizer: Downloaded to shared memory in 21.103s
chaiml-sao10k-l3-rp-v3-3-v22-mkmlizer: quantizing model to /dev/shm/model_cache
chaiml-sao10k-l3-rp-v3-3-v22-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-sao10k-l3-rp-v3-3-v22-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<10:47, 2.24s/it] Loading 0: 5%|▌ | 15/291 [00:04<01:02, 4.45it/s] Loading 0: 11%|█ | 32/291 [00:04<00:22, 11.37it/s] Loading 0: 17%|█▋ | 50/291 [00:04<00:11, 20.81it/s] Loading 0: 22%|██▏ | 64/291 [00:05<00:09, 25.11it/s] Loading 0: 27%|██▋ | 80/291 [00:05<00:05, 36.22it/s] Loading 0: 33%|███▎ | 96/291 [00:05<00:03, 48.87it/s] Loading 0: 39%|███▉ | 114/291 [00:05<00:02, 64.67it/s] Loading 0: 45%|████▌ | 132/291 [00:05<00:01, 80.89it/s] Loading 0: 52%|█████▏ | 150/291 [00:05<00:01, 96.99it/s] Loading 0: 57%|█████▋ | 166/291 [00:06<00:01, 75.50it/s] Loading 0: 62%|██████▏ | 181/291 [00:06<00:01, 87.58it/s] Loading 0: 68%|██████▊ | 198/291 [00:06<00:00, 102.53it/s] Loading 0: 73%|███████▎ | 213/291 [00:06<00:00, 112.46it/s] Loading 0: 79%|███████▉ | 231/291 [00:06<00:00, 125.44it/s] Loading 0: 86%|████████▌ | 249/291 [00:06<00:00, 134.80it/s] Loading 0: 91%|█████████▏| 266/291 [00:06<00:00, 88.90it/s] Loading 0: 98%|█████████▊| 284/291 [00:06<00:00, 104.12it/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-v22-mkmlizer: quantized model in 23.196s
chaiml-sao10k-l3-rp-v3-3-v22-mkmlizer: Processed model ChaiML/sao10k-l3-rp-v3-3 in 44.299s
chaiml-sao10k-l3-rp-v3-3-v22-mkmlizer: creating bucket guanaco-mkml-models
chaiml-sao10k-l3-rp-v3-3-v22-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-sao10k-l3-rp-v3-3-v22-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v22
chaiml-sao10k-l3-rp-v3-3-v22-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v22/config.json
chaiml-sao10k-l3-rp-v3-3-v22-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v22/tokenizer_config.json
chaiml-sao10k-l3-rp-v3-3-v22-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v22/special_tokens_map.json
chaiml-sao10k-l3-rp-v3-3-v22-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v22/tokenizer.json
chaiml-sao10k-l3-rp-v3-3-v22-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v22/flywheel_model.0.safetensors
chaiml-sao10k-l3-rp-v3-3-v22-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
chaiml-sao10k-l3-rp-v3-3-v22-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-v22-mkmlizer: warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v22-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-v22-mkmlizer: warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v22-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-v22-mkmlizer: warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v22-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-v22-mkmlizer: warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v22-mkmlizer: Downloading shards: 0%| | 0/2 [00:00<?, ?it/s] Downloading shards: 50%|█████ | 1/2 [00:05<00:05, 5.66s/it] Downloading shards: 100%|██████████| 2/2 [00:07<00:00, 3.53s/it] Downloading shards: 100%|██████████| 2/2 [00:07<00:00, 3.85s/it]
chaiml-sao10k-l3-rp-v3-3-v22-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
chaiml-sao10k-l3-rp-v3-3-v22-mkmlizer: Saving duration: 3.197s
chaiml-sao10k-l3-rp-v3-3-v22-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 13.482s
chaiml-sao10k-l3-rp-v3-3-v22-mkmlizer: creating bucket guanaco-reward-models
chaiml-sao10k-l3-rp-v3-3-v22-mkmlizer: Bucket 's3://guanaco-reward-models/' created
chaiml-sao10k-l3-rp-v3-3-v22-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v22_reward
chaiml-sao10k-l3-rp-v3-3-v22-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v22_reward/special_tokens_map.json
chaiml-sao10k-l3-rp-v3-3-v22-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v22_reward/config.json
chaiml-sao10k-l3-rp-v3-3-v22-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v22_reward/tokenizer_config.json
chaiml-sao10k-l3-rp-v3-3-v22-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v22_reward/merges.txt
chaiml-sao10k-l3-rp-v3-3-v22-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v22_reward/tokenizer.json
chaiml-sao10k-l3-rp-v3-3-v22-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v22_reward/vocab.json
chaiml-sao10k-l3-rp-v3-3-v22-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v22_reward/reward.tensors
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
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Job chaiml-sao10k-l3-rp-v3-3-v22-mkmlizer completed after 219.14s with status: succeeded
Stopping job with name chaiml-sao10k-l3-rp-v3-3-v22-mkmlizer
Pipeline stage MKMLizer completed in 220.88s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service chaiml-sao10k-l3-rp-v3-3-v22
Waiting for inference service chaiml-sao10k-l3-rp-v3-3-v22 to be ready
Inference service chaiml-sao10k-l3-rp-v3-3-v22 ready after 50.31493544578552s
Pipeline stage ISVCDeployer completed in 57.42s
Running pipeline stage StressChecker
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
Connection pool is full, discarding connection: %s
Received healthy response to inference request in 2.0157339572906494s
Received healthy response to inference request in 1.240220069885254s
Received healthy response to inference request in 1.3034839630126953s
Received healthy response to inference request in 1.2542273998260498s
Received healthy response to inference request in 1.3281829357147217s
5 requests
0 failed requests
5th percentile: 1.2430215358734131
10th percentile: 1.2458230018615724
20th percentile: 1.2514259338378906
30th percentile: 1.264078712463379
40th percentile: 1.2837813377380372
50th percentile: 1.3034839630126953
60th percentile: 1.3133635520935059
70th percentile: 1.3232431411743164
80th percentile: 1.4656931400299074
90th percentile: 1.7407135486602785
95th percentile: 1.8782237529754637
99th percentile: 1.9882319164276123
mean time: 1.428369665145874
Pipeline stage StressChecker completed in 7.90s
chaiml-sao10k-l3-rp-v3-3_v22 status is now deployed due to DeploymentManager action
chaiml-sao10k-l3-rp-v3-3_v22 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics