submission_id: cgato-l3-thegreenlion-8b_9588_v2
developer_uid: c.gato
alignment_samples: 0
best_of: 16
celo_rating: 1220.9
display_name: cgato-l3-thegreenlion-8b_9588_v2
formatter: {'memory_template': '<|im_start|>system\n{memory}<|im_end|>\n', 'prompt_template': '<|im_start|>user\n{prompt}<|im_end|>\n', 'bot_template': '<|im_start|>assistant\n{message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n', 'truncate_by_message': True}
generation_params: {'temperature': 0.9, 'top_p': 1.0, 'min_p': 0.1, 'top_k': 100, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64, 'reward_max_token_input': 256}
is_internal_developer: False
language_model: cgato/L3-TheGreenLion-8b-SFT-v0.1.2
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: cgato/L3-TheGreenLion-8b
model_name: cgato-l3-thegreenlion-8b_9588_v2
model_num_parameters: 8030294016.0
model_repo: cgato/L3-TheGreenLion-8b-SFT-v0.1.2
model_size: 8B
num_battles: 14865
num_wins: 7878
propriety_score: 0.7266028002947679
propriety_total_count: 1357.0
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': True, 'user_template': '{user_name}: {message}\n'}
reward_repo: Jellywibble/gpt2_xl_pairwise_89m_step_347634
status: torndown
submission_type: basic
timestamp: 2024-07-30T14:13:05+00:00
us_pacific_date: 2024-07-30
win_ratio: 0.5299697275479314
Download Preference Data
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cgato-l3-thegreenlion-8b-9588-v2-mkmlizer
Waiting for job on cgato-l3-thegreenlion-8b-9588-v2-mkmlizer to finish
cgato-l3-thegreenlion-8b-9588-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-l3-thegreenlion-8b-9588-v2-mkmlizer: ║ _____ __ __ ║
cgato-l3-thegreenlion-8b-9588-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cgato-l3-thegreenlion-8b-9588-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cgato-l3-thegreenlion-8b-9588-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cgato-l3-thegreenlion-8b-9588-v2-mkmlizer: ║ /___/ ║
cgato-l3-thegreenlion-8b-9588-v2-mkmlizer: ║ ║
cgato-l3-thegreenlion-8b-9588-v2-mkmlizer: ║ Version: 0.9.7 ║
cgato-l3-thegreenlion-8b-9588-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cgato-l3-thegreenlion-8b-9588-v2-mkmlizer: ║ https://mk1.ai ║
cgato-l3-thegreenlion-8b-9588-v2-mkmlizer: ║ ║
cgato-l3-thegreenlion-8b-9588-v2-mkmlizer: ║ The license key for the current software has been verified as ║
cgato-l3-thegreenlion-8b-9588-v2-mkmlizer: ║ belonging to: ║
cgato-l3-thegreenlion-8b-9588-v2-mkmlizer: ║ ║
cgato-l3-thegreenlion-8b-9588-v2-mkmlizer: ║ Chai Research Corp. ║
cgato-l3-thegreenlion-8b-9588-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cgato-l3-thegreenlion-8b-9588-v2-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
cgato-l3-thegreenlion-8b-9588-v2-mkmlizer: ║ ║
cgato-l3-thegreenlion-8b-9588-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-l3-thegreenlion-8b-9588-v2-mkmlizer: Downloaded to shared memory in 24.466s
cgato-l3-thegreenlion-8b-9588-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpb62gqh2p, device:0
cgato-l3-thegreenlion-8b-9588-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cgato-l3-thegreenlion-8b-9588-v2-mkmlizer: quantized model in 25.990s
cgato-l3-thegreenlion-8b-9588-v2-mkmlizer: Processed model cgato/L3-TheGreenLion-8b-SFT-v0.1.2 in 50.456s
cgato-l3-thegreenlion-8b-9588-v2-mkmlizer: creating bucket guanaco-mkml-models
cgato-l3-thegreenlion-8b-9588-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-l3-thegreenlion-8b-9588-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-l3-thegreenlion-8b-9588-v2
cgato-l3-thegreenlion-8b-9588-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-l3-thegreenlion-8b-9588-v2/config.json
cgato-l3-thegreenlion-8b-9588-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-l3-thegreenlion-8b-9588-v2/special_tokens_map.json
cgato-l3-thegreenlion-8b-9588-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-l3-thegreenlion-8b-9588-v2/tokenizer_config.json
cgato-l3-thegreenlion-8b-9588-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-l3-thegreenlion-8b-9588-v2/tokenizer.json
cgato-l3-thegreenlion-8b-9588-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cgato-l3-thegreenlion-8b-9588-v2/flywheel_model.0.safetensors
cgato-l3-thegreenlion-8b-9588-v2-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
cgato-l3-thegreenlion-8b-9588-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 2%|▏ | 5/291 [00:00<00:07, 36.48it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:04, 58.39it/s] Loading 0: 7%|▋ | 20/291 [00:00<00:04, 54.71it/s] Loading 0: 9%|▉ | 26/291 [00:00<00:04, 53.78it/s] Loading 0: 11%|█ | 32/291 [00:00<00:05, 45.58it/s] Loading 0: 14%|█▎ | 40/291 [00:00<00:04, 54.78it/s] Loading 0: 16%|█▌ | 46/291 [00:00<00:04, 51.06it/s] Loading 0: 18%|█▊ | 52/291 [00:01<00:04, 51.80it/s] Loading 0: 20%|█▉ | 58/291 [00:01<00:04, 53.83it/s] Loading 0: 22%|██▏ | 64/291 [00:01<00:04, 48.51it/s] Loading 0: 24%|██▍ | 70/291 [00:01<00:04, 48.72it/s] Loading 0: 26%|██▌ | 76/291 [00:01<00:04, 51.45it/s] Loading 0: 28%|██▊ | 82/291 [00:01<00:04, 47.10it/s] Loading 0: 30%|██▉ | 87/291 [00:01<00:06, 32.27it/s] Loading 0: 32%|███▏ | 94/291 [00:02<00:05, 38.95it/s] Loading 0: 34%|███▍ | 100/291 [00:02<00:04, 39.75it/s] Loading 0: 36%|███▌ | 105/291 [00:02<00:04, 40.73it/s] Loading 0: 38%|███▊ | 112/291 [00:02<00:03, 46.33it/s] Loading 0: 41%|████ | 118/291 [00:02<00:03, 45.00it/s] Loading 0: 42%|████▏ | 123/291 [00:02<00:03, 45.15it/s] Loading 0: 45%|████▍ | 130/291 [00:02<00:03, 49.69it/s] Loading 0: 47%|████▋ | 136/291 [00:02<00:03, 46.89it/s] Loading 0: 48%|████▊ | 141/291 [00:03<00:03, 45.71it/s] Loading 0: 51%|█████ | 148/291 [00:03<00:02, 49.88it/s] Loading 0: 53%|█████▎ | 154/291 [00:03<00:02, 46.98it/s] Loading 0: 55%|█████▍ | 159/291 [00:03<00:02, 46.33it/s] Loading 0: 57%|█████▋ | 166/291 [00:03<00:02, 51.21it/s] Loading 0: 59%|█████▉ | 172/291 [00:03<00:02, 47.37it/s] Loading 0: 62%|██████▏ | 179/291 [00:03<00:02, 50.64it/s] Loading 0: 64%|██████▎ | 185/291 [00:03<00:02, 51.20it/s] Loading 0: 66%|██████▌ | 191/291 [00:04<00:02, 33.68it/s] Loading 0: 67%|██████▋ | 196/291 [00:04<00:02, 35.22it/s] Loading 0: 69%|██████▉ | 202/291 [00:04<00:02, 40.32it/s] Loading 0: 71%|███████ | 207/291 [00:04<00:01, 42.38it/s] Loading 0: 73%|███████▎ | 212/291 [00:04<00:02, 38.27it/s] Loading 0: 75%|███████▌ | 219/291 [00:04<00:01, 45.30it/s] Loading 0: 77%|███████▋ | 225/291 [00:04<00:01, 48.21it/s] Loading 0: 79%|███████▉ | 231/291 [00:05<00:01, 42.91it/s] Loading 0: 82%|████████▏ | 238/291 [00:05<00:01, 48.38it/s] Loading 0: 84%|████████▍ | 244/291 [00:05<00:01, 46.33it/s] Loading 0: 86%|████████▌ | 249/291 [00:05<00:00, 44.73it/s] Loading 0: 88%|████████▊ | 256/291 [00:05<00:00, 49.66it/s] Loading 0: 90%|█████████ | 262/291 [00:05<00:00, 47.16it/s] Loading 0: 92%|█████████▏| 267/291 [00:05<00:00, 46.42it/s] Loading 0: 94%|█████████▍| 274/291 [00:05<00:00, 50.23it/s] Loading 0: 96%|█████████▌| 280/291 [00:06<00:00, 47.16it/s] Loading 0: 98%|█████████▊| 285/291 [00:06<00:00, 45.99it/s] Loading 0: 100%|█████████▉| 290/291 [00:11<00:00, 3.28it/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.
cgato-l3-thegreenlion-8b-9588-v2-mkmlizer: warnings.warn(
cgato-l3-thegreenlion-8b-9588-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.
cgato-l3-thegreenlion-8b-9588-v2-mkmlizer: warnings.warn(
cgato-l3-thegreenlion-8b-9588-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.
cgato-l3-thegreenlion-8b-9588-v2-mkmlizer: warnings.warn(
cgato-l3-thegreenlion-8b-9588-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cgato-l3-thegreenlion-8b-9588-v2-mkmlizer: Saving duration: 1.480s
cgato-l3-thegreenlion-8b-9588-v2-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 11.197s
cgato-l3-thegreenlion-8b-9588-v2-mkmlizer: creating bucket guanaco-reward-models
cgato-l3-thegreenlion-8b-9588-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cgato-l3-thegreenlion-8b-9588-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cgato-l3-thegreenlion-8b-9588-v2_reward
cgato-l3-thegreenlion-8b-9588-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cgato-l3-thegreenlion-8b-9588-v2_reward/config.json
cgato-l3-thegreenlion-8b-9588-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cgato-l3-thegreenlion-8b-9588-v2_reward/special_tokens_map.json
cgato-l3-thegreenlion-8b-9588-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cgato-l3-thegreenlion-8b-9588-v2_reward/tokenizer_config.json
cgato-l3-thegreenlion-8b-9588-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cgato-l3-thegreenlion-8b-9588-v2_reward/merges.txt
cgato-l3-thegreenlion-8b-9588-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cgato-l3-thegreenlion-8b-9588-v2_reward/vocab.json
cgato-l3-thegreenlion-8b-9588-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cgato-l3-thegreenlion-8b-9588-v2_reward/tokenizer.json
cgato-l3-thegreenlion-8b-9588-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cgato-l3-thegreenlion-8b-9588-v2_reward/reward.tensors
Job cgato-l3-thegreenlion-8b-9588-v2-mkmlizer completed after 94.76s with status: succeeded
Stopping job with name cgato-l3-thegreenlion-8b-9588-v2-mkmlizer
Pipeline stage MKMLizer completed in 95.98s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.23s
Running pipeline stage ISVCDeployer
Creating inference service cgato-l3-thegreenlion-8b-9588-v2
Waiting for inference service cgato-l3-thegreenlion-8b-9588-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
Inference service cgato-l3-thegreenlion-8b-9588-v2 ready after 130.844233751297s
Pipeline stage ISVCDeployer completed in 132.67s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.30837082862854s
Received healthy response to inference request in 1.2292413711547852s
Received healthy response to inference request in 1.3730847835540771s
Received healthy response to inference request in 1.0775811672210693s
Received healthy response to inference request in 1.0873963832855225s
5 requests
0 failed requests
5th percentile: 1.0795442104339599
10th percentile: 1.0815072536468506
20th percentile: 1.085433340072632
30th percentile: 1.115765380859375
40th percentile: 1.17250337600708
50th percentile: 1.2292413711547852
60th percentile: 1.286778736114502
70th percentile: 1.3443161010742186
80th percentile: 1.56014199256897
90th percentile: 1.934256410598755
95th percentile: 2.1213136196136473
99th percentile: 2.2709593868255613
mean time: 1.4151349067687988
Pipeline stage StressChecker completed in 7.83s
cgato-l3-thegreenlion-8b_9588_v2 status is now deployed due to DeploymentManager action
cgato-l3-thegreenlion-8b_9588_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cgato-l3-thegreenlion-8b_9588_v2
Running pipeline stage ISVCDeleter
Checking if service cgato-l3-thegreenlion-8b-9588-v2 is running
Tearing down inference service cgato-l3-thegreenlion-8b-9588-v2
Service cgato-l3-thegreenlion-8b-9588-v2 has been torndown
Pipeline stage ISVCDeleter completed in 5.26s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cgato-l3-thegreenlion-8b-9588-v2/config.json from bucket guanaco-mkml-models
Deleting key cgato-l3-thegreenlion-8b-9588-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cgato-l3-thegreenlion-8b-9588-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cgato-l3-thegreenlion-8b-9588-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key cgato-l3-thegreenlion-8b-9588-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cgato-l3-thegreenlion-8b-9588-v2_reward/config.json from bucket guanaco-reward-models
Deleting key cgato-l3-thegreenlion-8b-9588-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key cgato-l3-thegreenlion-8b-9588-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cgato-l3-thegreenlion-8b-9588-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cgato-l3-thegreenlion-8b-9588-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cgato-l3-thegreenlion-8b-9588-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cgato-l3-thegreenlion-8b-9588-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.52s
cgato-l3-thegreenlion-8b_9588_v2 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics