submission_id: chaiml-sao10k-l3-rp-v3-3_v91
developer_uid: robert_irvine
alignment_samples: 0
best_of: 8
celo_rating: 1222.71
display_name: chaiml-sao10k-l3-rp-v3-3_v91
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_v91
model_num_parameters: 8030261248.0
model_repo: ChaiML/sao10k-l3-rp-v3-3
model_size: 8B
num_battles: 12477
num_wins: 6300
propriety_score: 0.7297056199821588
propriety_total_count: 1121.0
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: ChaiML/gpt2_xl_pairwise_89m_step_347634
status: torndown
submission_type: basic
timestamp: 2024-08-06T23:04:59+00:00
us_pacific_date: 2024-08-06
win_ratio: 0.5049290694878577
Download Preference Data
Resubmit model
Running pipeline stage MKMLizer
Starting job with name chaiml-sao10k-l3-rp-v3-3-v91-mkmlizer
Waiting for job on chaiml-sao10k-l3-rp-v3-3-v91-mkmlizer to finish
Stopping job with name chaiml-sao10k-l3-rp-v3-3-v91-mkmlizer
%s, retrying in %s seconds...
Starting job with name chaiml-sao10k-l3-rp-v3-3-v91-mkmlizer
Waiting for job on chaiml-sao10k-l3-rp-v3-3-v91-mkmlizer to finish
chaiml-sao10k-l3-rp-v3-3-v91-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-sao10k-l3-rp-v3-3-v91-mkmlizer: ║ _____ __ __ ║
chaiml-sao10k-l3-rp-v3-3-v91-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-sao10k-l3-rp-v3-3-v91-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-sao10k-l3-rp-v3-3-v91-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-sao10k-l3-rp-v3-3-v91-mkmlizer: ║ /___/ ║
chaiml-sao10k-l3-rp-v3-3-v91-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v91-mkmlizer: ║ Version: 0.9.9 ║
chaiml-sao10k-l3-rp-v3-3-v91-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-sao10k-l3-rp-v3-3-v91-mkmlizer: ║ https://mk1.ai ║
chaiml-sao10k-l3-rp-v3-3-v91-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v91-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-sao10k-l3-rp-v3-3-v91-mkmlizer: ║ belonging to: ║
chaiml-sao10k-l3-rp-v3-3-v91-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v91-mkmlizer: ║ Chai Research Corp. ║
chaiml-sao10k-l3-rp-v3-3-v91-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-sao10k-l3-rp-v3-3-v91-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
chaiml-sao10k-l3-rp-v3-3-v91-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v91-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-sao10k-l3-rp-v3-3-v91-mkmlizer: Downloaded to shared memory in 21.817s
chaiml-sao10k-l3-rp-v3-3-v91-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpm6bol4oi, device:0
chaiml-sao10k-l3-rp-v3-3-v91-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-sao10k-l3-rp-v3-3-v91-mkmlizer: quantized model in 26.369s
chaiml-sao10k-l3-rp-v3-3-v91-mkmlizer: Processed model ChaiML/sao10k-l3-rp-v3-3 in 48.186s
chaiml-sao10k-l3-rp-v3-3-v91-mkmlizer: creating bucket guanaco-mkml-models
chaiml-sao10k-l3-rp-v3-3-v91-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-sao10k-l3-rp-v3-3-v91-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v91
chaiml-sao10k-l3-rp-v3-3-v91-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v91/config.json
chaiml-sao10k-l3-rp-v3-3-v91-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v91/special_tokens_map.json
chaiml-sao10k-l3-rp-v3-3-v91-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v91/tokenizer_config.json
chaiml-sao10k-l3-rp-v3-3-v91-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v91/tokenizer.json
chaiml-sao10k-l3-rp-v3-3-v91-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
chaiml-sao10k-l3-rp-v3-3-v91-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<11:26, 2.38s/it] Loading 0: 2%|▏ | 6/291 [00:04<03:02, 1.56it/s] Loading 0: 5%|▍ | 14/291 [00:05<00:59, 4.63it/s] Loading 0: 7%|▋ | 20/291 [00:05<00:36, 7.41it/s] Loading 0: 9%|▊ | 25/291 [00:05<00:25, 10.34it/s] Loading 0: 11%|█▏ | 33/291 [00:05<00:16, 15.67it/s] Loading 0: 14%|█▍ | 42/291 [00:05<00:11, 21.92it/s] Loading 0: 18%|█▊ | 51/291 [00:05<00:08, 27.95it/s] Loading 0: 20%|██ | 59/291 [00:05<00:06, 35.23it/s] Loading 0: 22%|██▏ | 65/291 [00:06<00:07, 28.31it/s] Loading 0: 24%|██▍ | 70/291 [00:06<00:07, 30.68it/s] Loading 0: 26%|██▋ | 77/291 [00:06<00:05, 37.06it/s] Loading 0: 29%|██▊ | 83/291 [00:06<00:05, 38.45it/s] Loading 0: 30%|███ | 88/291 [00:06<00:05, 39.84it/s] Loading 0: 33%|███▎ | 95/291 [00:06<00:04, 45.65it/s] Loading 0: 35%|███▍ | 101/291 [00:06<00:04, 42.49it/s] Loading 0: 36%|███▋ | 106/291 [00:07<00:04, 40.81it/s] Loading 0: 39%|███▉ | 113/291 [00:07<00:03, 46.67it/s] Loading 0: 41%|████ | 119/291 [00:07<00:03, 44.96it/s] Loading 0: 43%|████▎ | 124/291 [00:07<00:03, 44.75it/s] Loading 0: 45%|████▌ | 131/291 [00:07<00:03, 49.78it/s] Loading 0: 47%|████▋ | 137/291 [00:07<00:03, 46.73it/s] Loading 0: 49%|████▉ | 142/291 [00:07<00:03, 45.39it/s] Loading 0: 51%|█████ | 149/291 [00:07<00:02, 50.56it/s] Loading 0: 53%|█████▎ | 155/291 [00:08<00:02, 47.13it/s] Loading 0: 55%|█████▍ | 160/291 [00:08<00:02, 45.13it/s] Loading 0: 57%|█████▋ | 166/291 [00:08<00:03, 34.50it/s] Loading 0: 58%|█████▊ | 170/291 [00:08<00:03, 35.07it/s] Loading 0: 60%|██████ | 176/291 [00:08<00:02, 40.27it/s] Loading 0: 62%|██████▏ | 181/291 [00:08<00:02, 42.36it/s] Loading 0: 64%|██████▍ | 186/291 [00:08<00:02, 36.58it/s] Loading 0: 66%|██████▋ | 193/291 [00:09<00:02, 44.13it/s] Loading 0: 68%|██████▊ | 198/291 [00:09<00:02, 43.26it/s] Loading 0: 70%|██████▉ | 203/291 [00:09<00:01, 44.16it/s] Loading 0: 72%|███████▏ | 209/291 [00:09<00:01, 41.71it/s] Loading 0: 74%|███████▎ | 214/291 [00:09<00:01, 41.43it/s] Loading 0: 76%|███████▌ | 220/291 [00:09<00:01, 44.86it/s] Loading 0: 77%|███████▋ | 225/291 [00:09<00:01, 44.77it/s] Loading 0: 79%|███████▉ | 230/291 [00:09<00:01, 45.46it/s] Loading 0: 81%|████████ | 236/291 [00:10<00:01, 43.03it/s] Loading 0: 83%|████████▎ | 241/291 [00:10<00:01, 42.70it/s] Loading 0: 85%|████████▌ | 248/291 [00:10<00:00, 47.94it/s] Loading 0: 87%|████████▋ | 254/291 [00:10<00:00, 44.27it/s] Loading 0: 89%|████████▉ | 259/291 [00:10<00:00, 43.84it/s] Loading 0: 91%|█████████▏| 266/291 [00:10<00:00, 33.47it/s] Loading 0: 93%|█████████▎| 272/291 [00:11<00:00, 34.49it/s] Loading 0: 95%|█████████▍| 276/291 [00:11<00:00, 34.22it/s] Loading 0: 98%|█████████▊| 284/291 [00:11<00:00, 42.43it/s] Loading 0: 100%|█████████▉| 290/291 [00:11<00:00, 40.25it/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-v91-mkmlizer: warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v91-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-v91-mkmlizer: warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v91-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-v91-mkmlizer: warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v91-mkmlizer: Downloading shards: 0%| | 0/2 [00:00<?, ?it/s] Downloading shards: 50%|█████ | 1/2 [00:05<00:05, 5.44s/it] Downloading shards: 100%|██████████| 2/2 [00:08<00:00, 4.09s/it] Downloading shards: 100%|██████████| 2/2 [00:08<00:00, 4.29s/it]
chaiml-sao10k-l3-rp-v3-3-v91-mkmlizer: Loading checkpoint shards: 0%| | 0/2 [00:00<?, ?it/s] Loading checkpoint shards: 50%|█████ | 1/2 [00:00<00:00, 2.31it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 3.81it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 3.47it/s]
chaiml-sao10k-l3-rp-v3-3-v91-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
chaiml-sao10k-l3-rp-v3-3-v91-mkmlizer: Saving duration: 1.360s
chaiml-sao10k-l3-rp-v3-3-v91-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 13.679s
chaiml-sao10k-l3-rp-v3-3-v91-mkmlizer: creating bucket guanaco-reward-models
chaiml-sao10k-l3-rp-v3-3-v91-mkmlizer: Bucket 's3://guanaco-reward-models/' created
chaiml-sao10k-l3-rp-v3-3-v91-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v91_reward
chaiml-sao10k-l3-rp-v3-3-v91-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v91_reward/tokenizer_config.json
chaiml-sao10k-l3-rp-v3-3-v91-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v91_reward/config.json
chaiml-sao10k-l3-rp-v3-3-v91-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v91_reward/special_tokens_map.json
chaiml-sao10k-l3-rp-v3-3-v91-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v91_reward/merges.txt
chaiml-sao10k-l3-rp-v3-3-v91-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v91_reward/vocab.json
chaiml-sao10k-l3-rp-v3-3-v91-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v91_reward/tokenizer.json
Job chaiml-sao10k-l3-rp-v3-3-v91-mkmlizer completed after 94.86s with status: succeeded
Stopping job with name chaiml-sao10k-l3-rp-v3-3-v91-mkmlizer
Pipeline stage MKMLizer completed in 96.30s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service chaiml-sao10k-l3-rp-v3-3-v91
Waiting for inference service chaiml-sao10k-l3-rp-v3-3-v91 to be ready
Failed to get response for submission zonemercy-lexical-nemov5_8701_v1: ('http://zonemercy-lexical-nemov5-8701-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:34040->127.0.0.1:8080: read: connection reset by peer\n')
Inference service chaiml-sao10k-l3-rp-v3-3-v91 ready after 171.0929515361786s
Pipeline stage ISVCDeployer completed in 172.88s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.050792694091797s
Received healthy response to inference request in 1.2148675918579102s
Received healthy response to inference request in 1.2429659366607666s
Received healthy response to inference request in 1.2291512489318848s
Received healthy response to inference request in 1.2240054607391357s
5 requests
0 failed requests
5th percentile: 1.2166951656341554
10th percentile: 1.2185227394104003
20th percentile: 1.2221778869628905
30th percentile: 1.2250346183776855
40th percentile: 1.2270929336547851
50th percentile: 1.2291512489318848
60th percentile: 1.2346771240234375
70th percentile: 1.2402029991149903
80th percentile: 1.404531288146973
90th percentile: 1.727661991119385
95th percentile: 1.8892273426055906
99th percentile: 2.0184796237945557
mean time: 1.3923565864562988
Pipeline stage StressChecker completed in 7.95s
chaiml-sao10k-l3-rp-v3-3_v91 status is now deployed due to DeploymentManager action
chaiml-sao10k-l3-rp-v3-3_v91 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of chaiml-sao10k-l3-rp-v3-3_v91
Running pipeline stage ISVCDeleter
Checking if service chaiml-sao10k-l3-rp-v3-3-v91 is running
Tearing down inference service chaiml-sao10k-l3-rp-v3-3-v91
Service chaiml-sao10k-l3-rp-v3-3-v91 has been torndown
Pipeline stage ISVCDeleter completed in 5.81s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key chaiml-sao10k-l3-rp-v3-3-v91/config.json from bucket guanaco-mkml-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v91/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v91/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v91/tokenizer.json from bucket guanaco-mkml-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v91/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key chaiml-sao10k-l3-rp-v3-3-v91_reward/config.json from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v91_reward/merges.txt from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v91_reward/reward.tensors from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v91_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v91_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v91_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v91_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.78s
chaiml-sao10k-l3-rp-v3-3_v91 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics