submission_id: chaiml-sao10k-l3-rp-v3-3_v21
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 emotion<|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: 2024-07-11T17:47:42+00:00
model_name: chaiml-sao10k-l3-rp-v3-3_v21
model_group: ChaiML/sao10k-l3-rp-v3-3
num_battles: 40969
num_wins: 21681
celo_rating: 1213.18
alignment_score: None
alignment_samples: 0
propriety_score: 0.739848455410919
propriety_total_count: 5147.0
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_v21
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: 0.5292050086650882
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name chaiml-sao10k-l3-rp-v3-3-v21-mkmlizer
Waiting for job on chaiml-sao10k-l3-rp-v3-3-v21-mkmlizer to finish
chaiml-sao10k-l3-rp-v3-3-v21-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-sao10k-l3-rp-v3-3-v21-mkmlizer: ║ _____ __ __ ║
chaiml-sao10k-l3-rp-v3-3-v21-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-sao10k-l3-rp-v3-3-v21-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-sao10k-l3-rp-v3-3-v21-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-sao10k-l3-rp-v3-3-v21-mkmlizer: ║ /___/ ║
chaiml-sao10k-l3-rp-v3-3-v21-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v21-mkmlizer: ║ Version: 0.8.14 ║
chaiml-sao10k-l3-rp-v3-3-v21-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-sao10k-l3-rp-v3-3-v21-mkmlizer: ║ https://mk1.ai ║
chaiml-sao10k-l3-rp-v3-3-v21-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v21-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-sao10k-l3-rp-v3-3-v21-mkmlizer: ║ belonging to: ║
chaiml-sao10k-l3-rp-v3-3-v21-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v21-mkmlizer: ║ Chai Research Corp. ║
chaiml-sao10k-l3-rp-v3-3-v21-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-sao10k-l3-rp-v3-3-v21-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
chaiml-sao10k-l3-rp-v3-3-v21-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v21-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-sao10k-l3-rp-v3-3-v21-mkmlizer: Downloaded to shared memory in 23.819s
chaiml-sao10k-l3-rp-v3-3-v21-mkmlizer: quantizing model to /dev/shm/model_cache
chaiml-sao10k-l3-rp-v3-3-v21-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-sao10k-l3-rp-v3-3-v21-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:05<13:14, 2.75s/it] Loading 0: 4%|▍ | 13/291 [00:05<01:28, 3.14it/s] Loading 0: 8%|▊ | 24/291 [00:05<00:39, 6.84it/s] Loading 0: 14%|█▎ | 40/291 [00:05<00:17, 14.00it/s] Loading 0: 18%|█▊ | 51/291 [00:05<00:12, 19.84it/s] Loading 0: 21%|██▏ | 62/291 [00:06<00:10, 21.34it/s] Loading 0: 26%|██▌ | 76/291 [00:06<00:06, 31.27it/s] Loading 0: 30%|██▉ | 87/291 [00:06<00:05, 39.43it/s] Loading 0: 35%|███▌ | 103/291 [00:06<00:03, 55.24it/s] Loading 0: 40%|███▉ | 115/291 [00:06<00:02, 64.37it/s] Loading 0: 45%|████▍ | 130/291 [00:06<00:02, 79.82it/s] Loading 0: 49%|████▉ | 143/291 [00:07<00:01, 87.84it/s] Loading 0: 54%|█████▍ | 157/291 [00:07<00:01, 95.75it/s] Loading 0: 58%|█████▊ | 170/291 [00:07<00:02, 53.04it/s] Loading 0: 63%|██████▎ | 184/291 [00:07<00:01, 65.69it/s] Loading 0: 67%|██████▋ | 195/291 [00:07<00:01, 71.89it/s] Loading 0: 73%|███████▎ | 211/291 [00:07<00:00, 88.93it/s] Loading 0: 77%|███████▋ | 224/291 [00:08<00:00, 91.75it/s] Loading 0: 82%|████████▏ | 238/291 [00:08<00:00, 101.92it/s] Loading 0: 86%|████████▋ | 251/291 [00:08<00:00, 107.26it/s] Loading 0: 91%|█████████ | 265/291 [00:08<00:00, 115.28it/s] Loading 0: 96%|█████████▌| 278/291 [00:08<00:00, 61.52it/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-v21-mkmlizer: quantized model in 28.707s
chaiml-sao10k-l3-rp-v3-3-v21-mkmlizer: Processed model ChaiML/sao10k-l3-rp-v3-3 in 52.527s
chaiml-sao10k-l3-rp-v3-3-v21-mkmlizer: creating bucket guanaco-mkml-models
chaiml-sao10k-l3-rp-v3-3-v21-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-sao10k-l3-rp-v3-3-v21-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v21
chaiml-sao10k-l3-rp-v3-3-v21-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v21/config.json
chaiml-sao10k-l3-rp-v3-3-v21-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v21/special_tokens_map.json
chaiml-sao10k-l3-rp-v3-3-v21-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v21/tokenizer_config.json
chaiml-sao10k-l3-rp-v3-3-v21-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v21/tokenizer.json
chaiml-sao10k-l3-rp-v3-3-v21-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v21/flywheel_model.0.safetensors
chaiml-sao10k-l3-rp-v3-3-v21-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
chaiml-sao10k-l3-rp-v3-3-v21-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-v21-mkmlizer: warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v21-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-v21-mkmlizer: warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v21-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-v21-mkmlizer: warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v21-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-v21-mkmlizer: warnings.warn(
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
chaiml-sao10k-l3-rp-v3-3-v21-mkmlizer: Downloading shards: 0%| | 0/2 [00:00<?, ?it/s] Downloading shards: 50%|█████ | 1/2 [00:07<00:07, 7.02s/it] Downloading shards: 100%|██████████| 2/2 [00:08<00:00, 3.99s/it] Downloading shards: 100%|██████████| 2/2 [00:08<00:00, 4.45s/it]
chaiml-sao10k-l3-rp-v3-3-v21-mkmlizer: Loading checkpoint shards: 0%| | 0/2 [00:00<?, ?it/s] Loading checkpoint shards: 50%|█████ | 1/2 [00:00<00:00, 1.68it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 2.73it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 2.50it/s]
chaiml-sao10k-l3-rp-v3-3-v21-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
chaiml-sao10k-l3-rp-v3-3-v21-mkmlizer: Saving duration: 2.152s
chaiml-sao10k-l3-rp-v3-3-v21-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 14.563s
chaiml-sao10k-l3-rp-v3-3-v21-mkmlizer: creating bucket guanaco-reward-models
chaiml-sao10k-l3-rp-v3-3-v21-mkmlizer: Bucket 's3://guanaco-reward-models/' created
chaiml-sao10k-l3-rp-v3-3-v21-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v21_reward
chaiml-sao10k-l3-rp-v3-3-v21-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v21_reward/config.json
chaiml-sao10k-l3-rp-v3-3-v21-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v21_reward/tokenizer_config.json
chaiml-sao10k-l3-rp-v3-3-v21-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v21_reward/vocab.json
chaiml-sao10k-l3-rp-v3-3-v21-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v21_reward/special_tokens_map.json
chaiml-sao10k-l3-rp-v3-3-v21-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v21_reward/tokenizer.json
chaiml-sao10k-l3-rp-v3-3-v21-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v21_reward/merges.txt
chaiml-sao10k-l3-rp-v3-3-v21-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v21_reward/reward.tensors
Job chaiml-sao10k-l3-rp-v3-3-v21-mkmlizer completed after 94.85s with status: succeeded
Stopping job with name chaiml-sao10k-l3-rp-v3-3-v21-mkmlizer
Pipeline stage MKMLizer completed in 95.69s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service chaiml-sao10k-l3-rp-v3-3-v21
Waiting for inference service chaiml-sao10k-l3-rp-v3-3-v21 to be ready
Failed to get response for submission chaser-cz-sharegpt-qlora-out_v3: ('http://chaser-cz-sharegpt-qlora-out-v3-predictor-default.tenant-chaiml-guanaco.knative.ord1.coreweave.cloud/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:52396->127.0.0.1:8080: read: connection reset by peer\n')
Inference service chaiml-sao10k-l3-rp-v3-3-v21 ready after 40.22960877418518s
Pipeline stage ISVCDeployer completed in 47.06s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9285764694213867s
Received healthy response to inference request in 1.26548171043396s
Received healthy response to inference request in 1.2756659984588623s
Received healthy response to inference request in 1.2426657676696777s
Received healthy response to inference request in 1.268369197845459s
5 requests
0 failed requests
5th percentile: 1.2472289562225343
10th percentile: 1.2517921447753906
20th percentile: 1.2609185218811034
30th percentile: 1.2660592079162598
40th percentile: 1.2672142028808593
50th percentile: 1.268369197845459
60th percentile: 1.2712879180908203
70th percentile: 1.2742066383361816
80th percentile: 1.4062480926513672
90th percentile: 1.667412281036377
95th percentile: 1.7979943752288818
99th percentile: 1.9024600505828857
mean time: 1.3961518287658692
Pipeline stage StressChecker completed in 7.68s
chaiml-sao10k-l3-rp-v3-3_v21 status is now deployed due to DeploymentManager action
chaiml-sao10k-l3-rp-v3-3_v21 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics