developer_uid: shiroe40
submission_id: cycy233-l3-ss-v1-c2_v1
model_name: auto
model_group: cycy233/L3-ss-v1-c2
status: torndown
timestamp: 2024-08-13T15:33:22+00:00
num_battles: 7976
num_wins: 4019
celo_rating: 1211.97
family_friendly_score: 0.0
submission_type: basic
model_repo: cycy233/L3-ss-v1-c2
model_architecture: LlamaForCausalLM
reward_repo: Jellywibble/gpt2_xl_pairwise_89m_step_347634
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: auto
is_internal_developer: False
language_model: cycy233/L3-ss-v1-c2
model_size: 8B
ranking_group: single
us_pacific_date: 2024-08-13
win_ratio: 0.5038866599799399
generation_params: {'temperature': 1.0, 'top_p': 0.9, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['<|end_header_id|>', '<|eot_id|>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64, 'reward_max_token_input': 256}
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}
reward_formatter: {'bot_template': '{bot_name}: {message}\n', 'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'response_template': '{bot_name}:', 'truncate_by_message': False, 'user_template': '{user_name}: {message}\n'}
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cycy233-l3-ss-v1-c2-v1-mkmlizer
Waiting for job on cycy233-l3-ss-v1-c2-v1-mkmlizer to finish
cycy233-l3-ss-v1-c2-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-ss-v1-c2-v1-mkmlizer: ║ _____ __ __ ║
cycy233-l3-ss-v1-c2-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-l3-ss-v1-c2-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-l3-ss-v1-c2-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-l3-ss-v1-c2-v1-mkmlizer: ║ /___/ ║
cycy233-l3-ss-v1-c2-v1-mkmlizer: ║ ║
cycy233-l3-ss-v1-c2-v1-mkmlizer: ║ Version: 0.9.9 ║
cycy233-l3-ss-v1-c2-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-l3-ss-v1-c2-v1-mkmlizer: ║ https://mk1.ai ║
cycy233-l3-ss-v1-c2-v1-mkmlizer: ║ ║
cycy233-l3-ss-v1-c2-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-l3-ss-v1-c2-v1-mkmlizer: ║ belonging to: ║
cycy233-l3-ss-v1-c2-v1-mkmlizer: ║ ║
cycy233-l3-ss-v1-c2-v1-mkmlizer: ║ Chai Research Corp. ║
cycy233-l3-ss-v1-c2-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-l3-ss-v1-c2-v1-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
cycy233-l3-ss-v1-c2-v1-mkmlizer: ║ ║
cycy233-l3-ss-v1-c2-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-ss-v1-c2-v1-mkmlizer: Downloaded to shared memory in 64.279s
cycy233-l3-ss-v1-c2-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpl6zjwu7z, device:0
cycy233-l3-ss-v1-c2-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-ss-v1-c2-v1-mkmlizer: quantized model in 25.629s
cycy233-l3-ss-v1-c2-v1-mkmlizer: Processed model cycy233/L3-ss-v1-c2 in 89.909s
cycy233-l3-ss-v1-c2-v1-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-ss-v1-c2-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-ss-v1-c2-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-ss-v1-c2-v1
cycy233-l3-ss-v1-c2-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-ss-v1-c2-v1/config.json
cycy233-l3-ss-v1-c2-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-ss-v1-c2-v1/special_tokens_map.json
cycy233-l3-ss-v1-c2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-ss-v1-c2-v1/tokenizer_config.json
cycy233-l3-ss-v1-c2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-ss-v1-c2-v1/tokenizer.json
cycy233-l3-ss-v1-c2-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-ss-v1-c2-v1/flywheel_model.0.safetensors
cycy233-l3-ss-v1-c2-v1-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
cycy233-l3-ss-v1-c2-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%|▏ | 4/291 [00:00<00:07, 37.19it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:04, 60.04it/s] Loading 0: 8%|▊ | 22/291 [00:00<00:03, 67.63it/s] Loading 0: 11%|█ | 31/291 [00:00<00:03, 72.30it/s] Loading 0: 14%|█▎ | 40/291 [00:00<00:03, 76.93it/s] Loading 0: 17%|█▋ | 49/291 [00:00<00:03, 80.53it/s] Loading 0: 20%|█▉ | 58/291 [00:00<00:02, 79.82it/s] Loading 0: 23%|██▎ | 67/291 [00:00<00:02, 80.78it/s] Loading 0: 26%|██▌ | 76/291 [00:01<00:02, 80.36it/s] Loading 0: 29%|██▉ | 85/291 [00:02<00:10, 19.95it/s] Loading 0: 32%|███▏ | 94/291 [00:02<00:07, 26.18it/s] Loading 0: 36%|███▋ | 106/291 [00:02<00:05, 35.32it/s] Loading 0: 42%|████▏ | 121/291 [00:02<00:03, 47.87it/s] Loading 0: 45%|████▍ | 130/291 [00:02<00:03, 53.64it/s] Loading 0: 49%|████▉ | 142/291 [00:02<00:02, 60.80it/s] Loading 0: 52%|█████▏ | 151/291 [00:02<00:02, 66.20it/s] Loading 0: 57%|█████▋ | 166/291 [00:03<00:01, 77.05it/s] Loading 0: 61%|██████ | 178/291 [00:03<00:01, 79.20it/s] Loading 0: 64%|██████▍ | 187/291 [00:04<00:04, 25.57it/s] Loading 0: 67%|██████▋ | 196/291 [00:04<00:03, 31.33it/s] Loading 0: 71%|███████ | 206/291 [00:04<00:02, 39.15it/s] Loading 0: 76%|███████▌ | 220/291 [00:04<00:01, 50.52it/s] Loading 0: 79%|███████▉ | 230/291 [00:04<00:01, 58.23it/s] Loading 0: 83%|████████▎ | 241/291 [00:04<00:00, 62.85it/s] Loading 0: 88%|████████▊ | 256/291 [00:05<00:00, 73.31it/s] Loading 0: 91%|█████████▏| 266/291 [00:05<00:00, 78.37it/s] Loading 0: 95%|█████████▍| 276/291 [00:05<00:00, 81.52it/s] Loading 0: 98%|█████████▊| 286/291 [00:05<00:00, 75.70it/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.
cycy233-l3-ss-v1-c2-v1-mkmlizer: warnings.warn(
cycy233-l3-ss-v1-c2-v1-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.
cycy233-l3-ss-v1-c2-v1-mkmlizer: warnings.warn(
cycy233-l3-ss-v1-c2-v1-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.
cycy233-l3-ss-v1-c2-v1-mkmlizer: warnings.warn(
cycy233-l3-ss-v1-c2-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-l3-ss-v1-c2-v1-mkmlizer: Saving duration: 1.516s
cycy233-l3-ss-v1-c2-v1-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 11.258s
cycy233-l3-ss-v1-c2-v1-mkmlizer: creating bucket guanaco-reward-models
cycy233-l3-ss-v1-c2-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-l3-ss-v1-c2-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-l3-ss-v1-c2-v1_reward
cycy233-l3-ss-v1-c2-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-l3-ss-v1-c2-v1_reward/special_tokens_map.json
cycy233-l3-ss-v1-c2-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-l3-ss-v1-c2-v1_reward/config.json
cycy233-l3-ss-v1-c2-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-l3-ss-v1-c2-v1_reward/tokenizer_config.json
cycy233-l3-ss-v1-c2-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-l3-ss-v1-c2-v1_reward/merges.txt
cycy233-l3-ss-v1-c2-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-l3-ss-v1-c2-v1_reward/vocab.json
cycy233-l3-ss-v1-c2-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-l3-ss-v1-c2-v1_reward/tokenizer.json
cycy233-l3-ss-v1-c2-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-l3-ss-v1-c2-v1_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
Job cycy233-l3-ss-v1-c2-v1-mkmlizer completed after 135.54s with status: succeeded
Stopping job with name cycy233-l3-ss-v1-c2-v1-mkmlizer
Pipeline stage MKMLizer completed in 136.44s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-l3-ss-v1-c2-v1
Waiting for inference service cycy233-l3-ss-v1-c2-v1 to be ready
Failed to get response for submission mistralai-mistral-nemo-_9330_v42: ('http://mistralai-mistral-nemo-9330-v42-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'activator request timeout')
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
Failed to get response for submission mistralai-mistral-nemo-_9330_v42: ('http://mistralai-mistral-nemo-9330-v42-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'activator request timeout')
Failed to get response for submission mistralai-mistral-nemo-_9330_v42: ('http://mistralai-mistral-nemo-9330-v42-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'activator request timeout')
Failed to get response for submission mistralai-mistral-nemo-_9330_v42: ('http://mistralai-mistral-nemo-9330-v42-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'activator request timeout')
Failed to get response for submission mistralai-mistral-nemo-_9330_v42: ('http://mistralai-mistral-nemo-9330-v42-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'activator request timeout')
Failed to get response for submission mistralai-mistral-nemo-_9330_v42: ('http://mistralai-mistral-nemo-9330-v42-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'activator request timeout')
Failed to get response for submission mistralai-mistral-nemo-_9330_v42: ('http://mistralai-mistral-nemo-9330-v42-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'activator request timeout')
Failed to get response for submission mistralai-mistral-nemo-_9330_v42: ('http://mistralai-mistral-nemo-9330-v42-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'activator request timeout')
Failed to get response for submission mistralai-mistral-nemo-_9330_v42: ('http://mistralai-mistral-nemo-9330-v42-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'activator request timeout')
Failed to get response for submission mistralai-mistral-nemo-_9330_v42: ('http://mistralai-mistral-nemo-9330-v42-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'activator request timeout')
Failed to get response for submission mistralai-mistral-nemo-_9330_v42: ('http://mistralai-mistral-nemo-9330-v42-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'activator request timeout')
Failed to get response for submission mistralai-mistral-nemo-_9330_v42: ('http://mistralai-mistral-nemo-9330-v42-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'activator request timeout')
Failed to get response for submission mistralai-mistral-nemo-_9330_v42: ('http://mistralai-mistral-nemo-9330-v42-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'activator request timeout')
Inference service cycy233-l3-ss-v1-c2-v1 ready after 211.2715938091278s
Pipeline stage ISVCDeployer completed in 212.75s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.258814573287964s
Received healthy response to inference request in 1.5085277557373047s
Received healthy response to inference request in 1.4811341762542725s
Received healthy response to inference request in 1.456216812133789s
Received healthy response to inference request in 1.5326409339904785s
5 requests
0 failed requests
5th percentile: 1.4612002849578858
10th percentile: 1.4661837577819825
20th percentile: 1.4761507034301757
30th percentile: 1.486612892150879
40th percentile: 1.4975703239440918
50th percentile: 1.5085277557373047
60th percentile: 1.5181730270385743
70th percentile: 1.5278182983398438
80th percentile: 1.6778756618499757
90th percentile: 1.96834511756897
95th percentile: 2.1135798454284664
99th percentile: 2.2297676277160643
mean time: 1.6474668502807617
Pipeline stage StressChecker completed in 9.23s
cycy233-l3-ss-v1-c2_v1 status is now deployed due to DeploymentManager action
cycy233-l3-ss-v1-c2_v1 status is now inactive due to auto deactivation removed underperforming models
cycy233-l3-ss-v1-c2_v1 status is now torndown due to DeploymentManager action