submission_id: chaiml-sao10k-l3-rp-v3-3_v73
developer_uid: robert_irvine
alignment_samples: 0
best_of: 8
celo_rating: 1233.78
display_name: chaiml-sao10k-l3-rp-v3-3_v73
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}
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, 'reward_max_token_input': 256}
is_internal_developer: True
language_model: ChaiML/sao10k-l3-rp-v3-3
max_input_tokens: 1024
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: ChaiML/sao10k-l3-rp-v3-3
model_name: chaiml-sao10k-l3-rp-v3-3_v73
model_num_parameters: 8030261248.0
model_repo: ChaiML/sao10k-l3-rp-v3-3
model_size: 8B
num_battles: 32106
num_wins: 16490
propriety_score: 0.720954356846473
propriety_total_count: 2892.0
ranking_group: single
reward_formatter: {'bot_template': 'Bot: {message}\n', 'memory_template': '', 'prompt_template': '', 'response_template': 'Bot:', 'truncate_by_message': False, 'user_template': 'User: {message}\n'}
reward_repo: rirv938/retune_gpt2_xl_on_chaiml_sao10k_step_585
status: torndown
submission_type: basic
timestamp: 2024-08-01T18:57:11+00:00
us_pacific_date: 2024-08-01
win_ratio: 0.513611163022488
Download Preference Data
Resubmit model
Running pipeline stage MKMLizer
Starting job with name chaiml-sao10k-l3-rp-v3-3-v73-mkmlizer
Waiting for job on chaiml-sao10k-l3-rp-v3-3-v73-mkmlizer to finish
Failed to get response for submission blend_sugom_2024-08-01: 'BlendChatApi' object has no attribute 'tags'
chaiml-sao10k-l3-rp-v3-3-v73-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-sao10k-l3-rp-v3-3-v73-mkmlizer: ║ _____ __ __ ║
chaiml-sao10k-l3-rp-v3-3-v73-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-sao10k-l3-rp-v3-3-v73-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-sao10k-l3-rp-v3-3-v73-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-sao10k-l3-rp-v3-3-v73-mkmlizer: ║ /___/ ║
chaiml-sao10k-l3-rp-v3-3-v73-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v73-mkmlizer: ║ Version: 0.9.7 ║
chaiml-sao10k-l3-rp-v3-3-v73-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-sao10k-l3-rp-v3-3-v73-mkmlizer: ║ https://mk1.ai ║
chaiml-sao10k-l3-rp-v3-3-v73-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v73-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-sao10k-l3-rp-v3-3-v73-mkmlizer: ║ belonging to: ║
chaiml-sao10k-l3-rp-v3-3-v73-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v73-mkmlizer: ║ Chai Research Corp. ║
chaiml-sao10k-l3-rp-v3-3-v73-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-sao10k-l3-rp-v3-3-v73-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
chaiml-sao10k-l3-rp-v3-3-v73-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v73-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-sao10k-l3-rp-v3-3-v73-mkmlizer: Downloaded to shared memory in 22.328s
chaiml-sao10k-l3-rp-v3-3-v73-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp31bj4_0n, device:0
chaiml-sao10k-l3-rp-v3-3-v73-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission blend_sugom_2024-08-01: 'BlendChatApi' object has no attribute 'tags'
chaiml-sao10k-l3-rp-v3-3-v73-mkmlizer: quantized model in 26.031s
chaiml-sao10k-l3-rp-v3-3-v73-mkmlizer: Processed model ChaiML/sao10k-l3-rp-v3-3 in 48.359s
chaiml-sao10k-l3-rp-v3-3-v73-mkmlizer: creating bucket guanaco-mkml-models
chaiml-sao10k-l3-rp-v3-3-v73-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-sao10k-l3-rp-v3-3-v73-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v73
chaiml-sao10k-l3-rp-v3-3-v73-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v73/config.json
chaiml-sao10k-l3-rp-v3-3-v73-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v73/special_tokens_map.json
chaiml-sao10k-l3-rp-v3-3-v73-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v73/tokenizer_config.json
chaiml-sao10k-l3-rp-v3-3-v73-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v73/tokenizer.json
chaiml-sao10k-l3-rp-v3-3-v73-mkmlizer: loading reward model from rirv938/retune_gpt2_xl_on_chaiml_sao10k_step_585
chaiml-sao10k-l3-rp-v3-3-v73-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<11:24, 2.37s/it] Loading 0: 2%|▏ | 6/291 [00:04<03:02, 1.56it/s] Loading 0: 4%|▍ | 13/291 [00:04<01:04, 4.28it/s] Loading 0: 7%|▋ | 20/291 [00:05<00:35, 7.60it/s] Loading 0: 9%|▊ | 25/291 [00:05<00:25, 10.50it/s] Loading 0: 11%|█▏ | 33/291 [00:05<00:16, 15.77it/s] Loading 0: 14%|█▍ | 42/291 [00:05<00:11, 22.19it/s] Loading 0: 17%|█▋ | 50/291 [00:05<00:08, 29.31it/s] Loading 0: 19%|█▉ | 56/291 [00:05<00:07, 31.67it/s] Loading 0: 21%|██▏ | 62/291 [00:06<00:08, 27.28it/s] Loading 0: 24%|██▎ | 69/291 [00:06<00:07, 30.53it/s] Loading 0: 26%|██▋ | 77/291 [00:06<00:05, 38.06it/s] Loading 0: 29%|██▊ | 83/291 [00:06<00:05, 39.14it/s] Loading 0: 30%|███ | 88/291 [00:06<00:04, 40.71it/s] Loading 0: 33%|███▎ | 95/291 [00:06<00:04, 46.88it/s] Loading 0: 35%|███▍ | 101/291 [00:06<00:04, 44.58it/s] Loading 0: 36%|███▋ | 106/291 [00:07<00:04, 45.03it/s] Loading 0: 39%|███▉ | 113/291 [00:07<00:03, 50.31it/s] Loading 0: 41%|████ | 119/291 [00:07<00:03, 46.58it/s] Loading 0: 43%|████▎ | 124/291 [00:07<00:03, 44.88it/s] Loading 0: 45%|████▌ | 131/291 [00:07<00:03, 49.39it/s] Loading 0: 47%|████▋ | 137/291 [00:07<00:03, 45.36it/s] Loading 0: 49%|████▉ | 142/291 [00:07<00:03, 44.73it/s] Loading 0: 51%|█████ | 149/291 [00:07<00:02, 50.16it/s] Loading 0: 53%|█████▎ | 155/291 [00:08<00:02, 46.60it/s] Loading 0: 55%|█████▍ | 160/291 [00:08<00:02, 46.32it/s] Loading 0: 57%|█████▋ | 166/291 [00:08<00:03, 34.57it/s] Loading 0: 59%|█████▉ | 171/291 [00:08<00:03, 37.33it/s] Loading 0: 60%|██████ | 176/291 [00:08<00:02, 39.77it/s] Loading 0: 63%|██████▎ | 182/291 [00:08<00:02, 40.87it/s] Loading 0: 64%|██████▍ | 187/291 [00:08<00:02, 42.47it/s] Loading 0: 67%|██████▋ | 194/291 [00:08<00:01, 48.72it/s] Loading 0: 69%|██████▊ | 200/291 [00:09<00:02, 45.45it/s] Loading 0: 70%|███████ | 205/291 [00:09<00:01, 45.87it/s] Loading 0: 73%|███████▎ | 212/291 [00:09<00:01, 51.73it/s] Loading 0: 75%|███████▍ | 218/291 [00:09<00:01, 48.82it/s] Loading 0: 77%|███████▋ | 224/291 [00:09<00:01, 49.39it/s] Loading 0: 79%|███████▉ | 230/291 [00:09<00:01, 51.77it/s] Loading 0: 81%|████████ | 236/291 [00:09<00:01, 45.70it/s] Loading 0: 83%|████████▎ | 241/291 [00:09<00:01, 44.11it/s] Loading 0: 85%|████████▌ | 248/291 [00:10<00:00, 49.08it/s] Loading 0: 87%|████████▋ | 254/291 [00:10<00:00, 46.74it/s] Loading 0: 89%|████████▉ | 259/291 [00:10<00:00, 46.97it/s] Loading 0: 91%|█████████▏| 266/291 [00:10<00:00, 35.43it/s] Loading 0: 93%|█████████▎| 272/291 [00:10<00:00, 36.57it/s] Loading 0: 95%|█████████▌| 277/291 [00:10<00:00, 37.99it/s] Loading 0: 98%|█████████▊| 284/291 [00:11<00:00, 43.85it/s] Loading 0: 100%|█████████▉| 290/291 [00:11<00:00, 42.41it/s] /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:957: 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-v73-mkmlizer: warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v73-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:785: 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-v73-mkmlizer: warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v73-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py:469: 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-v73-mkmlizer: warnings.warn(
Failed to get response for submission blend_sugom_2024-08-01: 'BlendChatApi' object has no attribute 'tags'
Failed to get response for submission blend_sugom_2024-08-01: 'BlendChatApi' object has no attribute 'tags'
chaiml-sao10k-l3-rp-v3-3-v73-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
chaiml-sao10k-l3-rp-v3-3-v73-mkmlizer: Saving duration: 1.439s
chaiml-sao10k-l3-rp-v3-3-v73-mkmlizer: Processed model rirv938/retune_gpt2_xl_on_chaiml_sao10k_step_585 in 10.603s
chaiml-sao10k-l3-rp-v3-3-v73-mkmlizer: creating bucket guanaco-reward-models
chaiml-sao10k-l3-rp-v3-3-v73-mkmlizer: Bucket 's3://guanaco-reward-models/' created
chaiml-sao10k-l3-rp-v3-3-v73-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v73_reward
chaiml-sao10k-l3-rp-v3-3-v73-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v73_reward/config.json
chaiml-sao10k-l3-rp-v3-3-v73-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v73_reward/special_tokens_map.json
chaiml-sao10k-l3-rp-v3-3-v73-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v73_reward/tokenizer_config.json
chaiml-sao10k-l3-rp-v3-3-v73-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v73_reward/merges.txt
chaiml-sao10k-l3-rp-v3-3-v73-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v73_reward/vocab.json
chaiml-sao10k-l3-rp-v3-3-v73-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v73_reward/tokenizer.json
chaiml-sao10k-l3-rp-v3-3-v73-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v73_reward/reward.tensors
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Job chaiml-sao10k-l3-rp-v3-3-v73-mkmlizer completed after 94.78s with status: succeeded
Stopping job with name chaiml-sao10k-l3-rp-v3-3-v73-mkmlizer
Pipeline stage MKMLizer completed in 95.82s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service chaiml-sao10k-l3-rp-v3-3-v73
Waiting for inference service chaiml-sao10k-l3-rp-v3-3-v73 to be ready
Failed to get response for submission blend_sugom_2024-08-01: 'BlendChatApi' object has no attribute 'tags'
Inference service chaiml-sao10k-l3-rp-v3-3-v73 ready after 141.35133457183838s
Pipeline stage ISVCDeployer completed in 143.13s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9903943538665771s
Received healthy response to inference request in 1.1870181560516357s
Received healthy response to inference request in 1.5115995407104492s
Received healthy response to inference request in 1.2439303398132324s
Received healthy response to inference request in 1.231255054473877s
5 requests
0 failed requests
5th percentile: 1.195865535736084
10th percentile: 1.2047129154205323
20th percentile: 1.2224076747894288
30th percentile: 1.233790111541748
40th percentile: 1.2388602256774903
50th percentile: 1.2439303398132324
60th percentile: 1.3509980201721192
70th percentile: 1.4580657005310058
80th percentile: 1.6073585033416748
90th percentile: 1.798876428604126
95th percentile: 1.8946353912353515
99th percentile: 1.971242561340332
mean time: 1.4328394889831544
Pipeline stage StressChecker completed in 7.91s
chaiml-sao10k-l3-rp-v3-3_v73 status is now deployed due to DeploymentManager action
chaiml-sao10k-l3-rp-v3-3_v73 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of chaiml-sao10k-l3-rp-v3-3_v73
Running pipeline stage ISVCDeleter
Checking if service chaiml-sao10k-l3-rp-v3-3-v73 is running
Tearing down inference service chaiml-sao10k-l3-rp-v3-3-v73
Service chaiml-sao10k-l3-rp-v3-3-v73 has been torndown
Pipeline stage ISVCDeleter completed in 4.75s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key chaiml-sao10k-l3-rp-v3-3-v73/config.json from bucket guanaco-mkml-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v73/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v73/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v73/tokenizer.json from bucket guanaco-mkml-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v73/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key chaiml-sao10k-l3-rp-v3-3-v73_reward/config.json from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v73_reward/merges.txt from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v73_reward/reward.tensors from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v73_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v73_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v73_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v73_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.65s
chaiml-sao10k-l3-rp-v3-3_v73 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics