submission_id: cycy233-l3-ss-v0-c1_v2
developer_uid: shiroe40
alignment_samples: 9736
alignment_score: -0.27845630804170907
best_of: 4
celo_rating: 1152.4
display_name: auto
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': 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': 4, 'max_output_tokens': 64, 'reward_max_token_input': 256}
is_internal_developer: False
language_model: cycy233/L3-ss-v0-c1
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: cycy233/L3-ss-v0-c1
model_name: auto
model_num_parameters: 8030261248.0
model_repo: cycy233/L3-ss-v0-c1
model_size: 8B
num_battles: 9736
num_wins: 3889
propriety_score: 0.6959910913140311
propriety_total_count: 898.0
ranking_group: single
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'}
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
status: torndown
submission_type: basic
timestamp: 2024-08-13T04:13:47+00:00
us_pacific_date: 2024-08-12
win_ratio: 0.3994453574363188
Download Preference Data
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cycy233-l3-ss-v0-c1-v2-mkmlizer
Waiting for job on cycy233-l3-ss-v0-c1-v2-mkmlizer to finish
Stopping job with name cycy233-l3-ss-v0-c1-v2-mkmlizer
%s, retrying in %s seconds...
Starting job with name cycy233-l3-ss-v0-c1-v2-mkmlizer
Waiting for job on cycy233-l3-ss-v0-c1-v2-mkmlizer to finish
Stopping job with name cycy233-l3-ss-v0-c1-v2-mkmlizer
%s, retrying in %s seconds...
Starting job with name cycy233-l3-ss-v0-c1-v2-mkmlizer
Waiting for job on cycy233-l3-ss-v0-c1-v2-mkmlizer to finish
cycy233-l3-ss-v0-c1-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-ss-v0-c1-v2-mkmlizer: ║ _____ __ __ ║
cycy233-l3-ss-v0-c1-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-l3-ss-v0-c1-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-l3-ss-v0-c1-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-l3-ss-v0-c1-v2-mkmlizer: ║ /___/ ║
cycy233-l3-ss-v0-c1-v2-mkmlizer: ║ ║
cycy233-l3-ss-v0-c1-v2-mkmlizer: ║ Version: 0.9.9 ║
cycy233-l3-ss-v0-c1-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-l3-ss-v0-c1-v2-mkmlizer: ║ https://mk1.ai ║
cycy233-l3-ss-v0-c1-v2-mkmlizer: ║ ║
cycy233-l3-ss-v0-c1-v2-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-l3-ss-v0-c1-v2-mkmlizer: ║ belonging to: ║
cycy233-l3-ss-v0-c1-v2-mkmlizer: ║ ║
cycy233-l3-ss-v0-c1-v2-mkmlizer: ║ Chai Research Corp. ║
cycy233-l3-ss-v0-c1-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-l3-ss-v0-c1-v2-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
cycy233-l3-ss-v0-c1-v2-mkmlizer: ║ ║
cycy233-l3-ss-v0-c1-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-ss-v0-c1-v2-mkmlizer: Downloaded to shared memory in 22.680s
cycy233-l3-ss-v0-c1-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp5vw_edix, device:0
cycy233-l3-ss-v0-c1-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-ss-v0-c1-v2-mkmlizer: quantized model in 26.951s
cycy233-l3-ss-v0-c1-v2-mkmlizer: Processed model cycy233/L3-ss-v0-c1 in 49.631s
cycy233-l3-ss-v0-c1-v2-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-ss-v0-c1-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-ss-v0-c1-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-ss-v0-c1-v2
cycy233-l3-ss-v0-c1-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-ss-v0-c1-v2/config.json
cycy233-l3-ss-v0-c1-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-ss-v0-c1-v2/special_tokens_map.json
cycy233-l3-ss-v0-c1-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-ss-v0-c1-v2/tokenizer_config.json
cycy233-l3-ss-v0-c1-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-ss-v0-c1-v2/tokenizer.json
cycy233-l3-ss-v0-c1-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-ss-v0-c1-v2/flywheel_model.0.safetensors
cycy233-l3-ss-v0-c1-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-l3-ss-v0-c1-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%|▏ | 4/291 [00:00<00:08, 35.49it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:04, 61.03it/s] Loading 0: 8%|▊ | 22/291 [00:00<00:03, 67.35it/s] Loading 0: 11%|█ | 31/291 [00:00<00:03, 73.26it/s] Loading 0: 14%|█▎ | 40/291 [00:00<00:03, 78.00it/s] Loading 0: 18%|█▊ | 52/291 [00:00<00:02, 79.90it/s] Loading 0: 23%|██▎ | 67/291 [00:00<00:02, 86.97it/s] Loading 0: 26%|██▌ | 76/291 [00:00<00:02, 85.82it/s] Loading 0: 29%|██▉ | 85/291 [00:02<00:09, 20.76it/s] Loading 0: 32%|███▏ | 94/291 [00:02<00:07, 26.27it/s] Loading 0: 35%|███▌ | 103/291 [00:02<00:05, 31.36it/s] Loading 0: 38%|███▊ | 112/291 [00:02<00:04, 38.24it/s] Loading 0: 42%|████▏ | 121/291 [00:02<00:03, 45.74it/s] Loading 0: 45%|████▍ | 130/291 [00:02<00:03, 52.69it/s] Loading 0: 48%|████▊ | 139/291 [00:02<00:02, 58.62it/s] Loading 0: 51%|█████ | 148/291 [00:03<00:02, 65.22it/s] Loading 0: 55%|█████▍ | 160/291 [00:03<00:01, 70.87it/s] Loading 0: 58%|█████▊ | 170/291 [00:03<00:01, 76.64it/s] Loading 0: 62%|██████▏ | 179/291 [00:03<00:01, 78.98it/s] Loading 0: 65%|██████▍ | 188/291 [00:04<00:04, 21.26it/s] Loading 0: 68%|██████▊ | 197/291 [00:04<00:03, 27.26it/s] Loading 0: 73%|███████▎ | 211/291 [00:04<00:02, 37.90it/s] Loading 0: 76%|███████▋ | 222/291 [00:04<00:01, 47.27it/s] Loading 0: 79%|███████▉ | 231/291 [00:05<00:01, 52.50it/s] Loading 0: 82%|████████▏ | 240/291 [00:05<00:00, 58.01it/s] Loading 0: 86%|████████▌ | 249/291 [00:05<00:00, 64.29it/s] Loading 0: 89%|████████▉ | 259/291 [00:05<00:00, 66.01it/s] Loading 0: 92%|█████████▏| 268/291 [00:05<00:00, 71.11it/s] Loading 0: 95%|█████████▌| 277/291 [00:05<00:00, 72.63it/s] Loading 0: 98%|█████████▊| 286/291 [00:05<00:00, 76.85it/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-v0-c1-v2-mkmlizer: warnings.warn(
cycy233-l3-ss-v0-c1-v2-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-v0-c1-v2-mkmlizer: warnings.warn(
cycy233-l3-ss-v0-c1-v2-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-v0-c1-v2-mkmlizer: warnings.warn(
cycy233-l3-ss-v0-c1-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-l3-ss-v0-c1-v2-mkmlizer: Saving duration: 0.329s
cycy233-l3-ss-v0-c1-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.996s
cycy233-l3-ss-v0-c1-v2-mkmlizer: creating bucket guanaco-reward-models
cycy233-l3-ss-v0-c1-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-l3-ss-v0-c1-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-l3-ss-v0-c1-v2_reward
cycy233-l3-ss-v0-c1-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-l3-ss-v0-c1-v2_reward/config.json
cycy233-l3-ss-v0-c1-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-l3-ss-v0-c1-v2_reward/special_tokens_map.json
cycy233-l3-ss-v0-c1-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-l3-ss-v0-c1-v2_reward/tokenizer_config.json
cycy233-l3-ss-v0-c1-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-l3-ss-v0-c1-v2_reward/merges.txt
cycy233-l3-ss-v0-c1-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-l3-ss-v0-c1-v2_reward/vocab.json
cycy233-l3-ss-v0-c1-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-l3-ss-v0-c1-v2_reward/tokenizer.json
cycy233-l3-ss-v0-c1-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-l3-ss-v0-c1-v2_reward/reward.tensors
Job cycy233-l3-ss-v0-c1-v2-mkmlizer completed after 84.82s with status: succeeded
Stopping job with name cycy233-l3-ss-v0-c1-v2-mkmlizer
Pipeline stage MKMLizer completed in 97.11s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-l3-ss-v0-c1-v2
Waiting for inference service cycy233-l3-ss-v0-c1-v2 to be ready
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
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
Inference service cycy233-l3-ss-v0-c1-v2 ready after 211.43490505218506s
Pipeline stage ISVCDeployer completed in 213.71s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0188968181610107s
Received healthy response to inference request in 1.1568706035614014s
Received healthy response to inference request in 1.184264898300171s
Received healthy response to inference request in 1.1858892440795898s
Received healthy response to inference request in 1.15446138381958s
5 requests
0 failed requests
5th percentile: 1.1549432277679443
10th percentile: 1.1554250717163086
20th percentile: 1.156388759613037
30th percentile: 1.1623494625091553
40th percentile: 1.173307180404663
50th percentile: 1.184264898300171
60th percentile: 1.1849146366119385
70th percentile: 1.1855643749237061
80th percentile: 1.3524907588958741
90th percentile: 1.6856937885284424
95th percentile: 1.8522953033447265
99th percentile: 1.9855765151977538
mean time: 1.3400765895843505
Pipeline stage StressChecker completed in 7.44s
cycy233-l3-ss-v0-c1_v2 status is now deployed due to DeploymentManager action
cycy233-l3-ss-v0-c1_v2 status is now inactive due to auto deactivation removed underperforming models
cycy233-l3-ss-v0-c1_v2 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics