developer_uid: helkero
submission_id: kaoeiri-hedone-l3-1-8b-v1_v1
model_name: kaoeiri-hedone-l3-1-8b-v1_v1
model_group: Kaoeiri/Hedone-L3.1-8B-v
status: torndown
timestamp: 2024-08-06T15:18:05+00:00
num_battles: 13668
num_wins: 7441
celo_rating: 1230.35
family_friendly_score: 0.0
submission_type: basic
model_repo: Kaoeiri/Hedone-L3.1-8B-v1
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: kaoeiri-hedone-l3-1-8b-v1_v1
is_internal_developer: False
language_model: Kaoeiri/Hedone-L3.1-8B-v1
model_size: 8B
ranking_group: single
us_pacific_date: 2024-08-06
win_ratio: 0.5444103014340065
generation_params: {'temperature': 1.0, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|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 kaoeiri-hedone-l3-1-8b-v1-v1-mkmlizer
Waiting for job on kaoeiri-hedone-l3-1-8b-v1-v1-mkmlizer to finish
kaoeiri-hedone-l3-1-8b-v1-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
kaoeiri-hedone-l3-1-8b-v1-v1-mkmlizer: ║ _____ __ __ ║
kaoeiri-hedone-l3-1-8b-v1-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
kaoeiri-hedone-l3-1-8b-v1-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
kaoeiri-hedone-l3-1-8b-v1-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
kaoeiri-hedone-l3-1-8b-v1-v1-mkmlizer: ║ /___/ ║
kaoeiri-hedone-l3-1-8b-v1-v1-mkmlizer: ║ ║
kaoeiri-hedone-l3-1-8b-v1-v1-mkmlizer: ║ Version: 0.9.9 ║
kaoeiri-hedone-l3-1-8b-v1-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
kaoeiri-hedone-l3-1-8b-v1-v1-mkmlizer: ║ https://mk1.ai ║
kaoeiri-hedone-l3-1-8b-v1-v1-mkmlizer: ║ ║
kaoeiri-hedone-l3-1-8b-v1-v1-mkmlizer: ║ The license key for the current software has been verified as ║
kaoeiri-hedone-l3-1-8b-v1-v1-mkmlizer: ║ belonging to: ║
kaoeiri-hedone-l3-1-8b-v1-v1-mkmlizer: ║ ║
kaoeiri-hedone-l3-1-8b-v1-v1-mkmlizer: ║ Chai Research Corp. ║
kaoeiri-hedone-l3-1-8b-v1-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
kaoeiri-hedone-l3-1-8b-v1-v1-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
kaoeiri-hedone-l3-1-8b-v1-v1-mkmlizer: ║ ║
kaoeiri-hedone-l3-1-8b-v1-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission turboderp-cat-llama-3-7_8684_v21: ('http://turboderp-cat-llama-3-7-8684-v21-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Failed to get response for submission turboderp-cat-llama-3-7_8684_v21: ('http://turboderp-cat-llama-3-7-8684-v21-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
kaoeiri-hedone-l3-1-8b-v1-v1-mkmlizer: quantized model in 27.966s
kaoeiri-hedone-l3-1-8b-v1-v1-mkmlizer: Processed model Kaoeiri/Hedone-L3.1-8B-v1 in 58.960s
kaoeiri-hedone-l3-1-8b-v1-v1-mkmlizer: creating bucket guanaco-mkml-models
kaoeiri-hedone-l3-1-8b-v1-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
kaoeiri-hedone-l3-1-8b-v1-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/kaoeiri-hedone-l3-1-8b-v1-v1
kaoeiri-hedone-l3-1-8b-v1-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/kaoeiri-hedone-l3-1-8b-v1-v1/config.json
kaoeiri-hedone-l3-1-8b-v1-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/kaoeiri-hedone-l3-1-8b-v1-v1/special_tokens_map.json
kaoeiri-hedone-l3-1-8b-v1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/kaoeiri-hedone-l3-1-8b-v1-v1/tokenizer_config.json
kaoeiri-hedone-l3-1-8b-v1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/kaoeiri-hedone-l3-1-8b-v1-v1/tokenizer.json
kaoeiri-hedone-l3-1-8b-v1-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/kaoeiri-hedone-l3-1-8b-v1-v1/flywheel_model.0.safetensors
kaoeiri-hedone-l3-1-8b-v1-v1-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
kaoeiri-hedone-l3-1-8b-v1-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<11:43, 2.43s/it] Loading 0: 2%|▏ | 6/291 [00:05<03:07, 1.52it/s] Loading 0: 4%|▍ | 11/291 [00:05<01:22, 3.38it/s] Loading 0: 5%|▌ | 15/291 [00:05<00:52, 5.21it/s] Loading 0: 8%|▊ | 22/291 [00:05<00:27, 9.63it/s] Loading 0: 9%|▉ | 27/291 [00:05<00:20, 13.10it/s] Loading 0: 11%|█ | 32/291 [00:05<00:15, 17.10it/s] Loading 0: 13%|█▎ | 38/291 [00:05<00:12, 21.00it/s] Loading 0: 15%|█▍ | 43/291 [00:05<00:10, 24.60it/s] Loading 0: 17%|█▋ | 49/291 [00:05<00:07, 30.57it/s] Loading 0: 19%|█▊ | 54/291 [00:06<00:07, 33.21it/s] Loading 0: 20%|██ | 59/291 [00:06<00:06, 35.96it/s] Loading 0: 22%|██▏ | 65/291 [00:06<00:06, 35.50it/s] Loading 0: 24%|██▍ | 70/291 [00:06<00:06, 36.01it/s] Loading 0: 26%|██▌ | 76/291 [00:06<00:05, 40.78it/s] Loading 0: 28%|██▊ | 81/291 [00:06<00:05, 40.94it/s] Loading 0: 30%|██▉ | 86/291 [00:06<00:05, 40.41it/s] Loading 0: 31%|███▏ | 91/291 [00:06<00:04, 41.60it/s] Loading 0: 33%|███▎ | 96/291 [00:07<00:05, 34.07it/s] Loading 0: 35%|███▌ | 103/291 [00:07<00:04, 41.09it/s] Loading 0: 37%|███▋ | 108/291 [00:07<00:04, 40.72it/s] Loading 0: 39%|███▉ | 113/291 [00:07<00:04, 41.38it/s] Loading 0: 41%|████ | 118/291 [00:07<00:04, 42.90it/s] Loading 0: 42%|████▏ | 123/291 [00:08<00:07, 21.70it/s] Loading 0: 45%|████▍ | 130/291 [00:08<00:05, 28.57it/s] Loading 0: 46%|████▋ | 135/291 [00:08<00:05, 31.08it/s] Loading 0: 48%|████▊ | 140/291 [00:08<00:04, 33.44it/s] Loading 0: 50%|████▉ | 145/291 [00:08<00:04, 36.25it/s] Loading 0: 52%|█████▏ | 150/291 [00:08<00:04, 31.39it/s] Loading 0: 54%|█████▍ | 157/291 [00:08<00:03, 37.92it/s] Loading 0: 56%|█████▌ | 162/291 [00:09<00:03, 38.45it/s] Loading 0: 57%|█████▋ | 167/291 [00:09<00:03, 39.48it/s] Loading 0: 59%|█████▉ | 172/291 [00:09<00:02, 40.92it/s] Loading 0: 61%|██████ | 177/291 [00:09<00:03, 33.68it/s] Loading 0: 63%|██████▎ | 184/291 [00:09<00:02, 40.76it/s] Loading 0: 65%|██████▍ | 189/291 [00:09<00:02, 40.55it/s] Loading 0: 67%|██████▋ | 194/291 [00:09<00:02, 39.71it/s] Loading 0: 68%|██████▊ | 199/291 [00:09<00:02, 41.18it/s] Loading 0: 70%|███████ | 204/291 [00:10<00:02, 34.37it/s] Loading 0: 73%|███████▎ | 211/291 [00:10<00:01, 41.16it/s] Loading 0: 74%|███████▍ | 216/291 [00:10<00:01, 40.65it/s] Loading 0: 76%|███████▌ | 221/291 [00:10<00:01, 40.50it/s] Loading 0: 78%|███████▊ | 226/291 [00:10<00:01, 41.91it/s] Loading 0: 79%|███████▉ | 231/291 [00:10<00:01, 33.86it/s] Loading 0: 82%|████████▏ | 238/291 [00:10<00:01, 40.86it/s] Loading 0: 84%|████████▎ | 243/291 [00:11<00:01, 40.86it/s] Loading 0: 85%|████████▌ | 248/291 [00:11<00:01, 40.81it/s] Loading 0: 87%|████████▋ | 253/291 [00:11<00:00, 41.83it/s] Loading 0: 89%|████████▊ | 258/291 [00:11<00:00, 34.15it/s] Loading 0: 91%|█████████ | 265/291 [00:11<00:00, 41.07it/s] Loading 0: 93%|█████████▎| 270/291 [00:11<00:00, 40.15it/s] Loading 0: 95%|█████████▍| 275/291 [00:11<00:00, 40.74it/s] Loading 0: 96%|█████████▌| 280/291 [00:12<00:00, 41.86it/s] Loading 0: 98%|█████████▊| 285/291 [00:12<00:00, 21.70it/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.
kaoeiri-hedone-l3-1-8b-v1-v1-mkmlizer: warnings.warn(
kaoeiri-hedone-l3-1-8b-v1-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.
kaoeiri-hedone-l3-1-8b-v1-v1-mkmlizer: warnings.warn(
kaoeiri-hedone-l3-1-8b-v1-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
kaoeiri-hedone-l3-1-8b-v1-v1-mkmlizer: Saving duration: 1.464s
kaoeiri-hedone-l3-1-8b-v1-v1-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 12.111s
kaoeiri-hedone-l3-1-8b-v1-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
kaoeiri-hedone-l3-1-8b-v1-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/kaoeiri-hedone-l3-1-8b-v1-v1_reward
kaoeiri-hedone-l3-1-8b-v1-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/kaoeiri-hedone-l3-1-8b-v1-v1_reward/special_tokens_map.json
kaoeiri-hedone-l3-1-8b-v1-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/kaoeiri-hedone-l3-1-8b-v1-v1_reward/config.json
kaoeiri-hedone-l3-1-8b-v1-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/kaoeiri-hedone-l3-1-8b-v1-v1_reward/tokenizer_config.json
kaoeiri-hedone-l3-1-8b-v1-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/kaoeiri-hedone-l3-1-8b-v1-v1_reward/merges.txt
kaoeiri-hedone-l3-1-8b-v1-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/kaoeiri-hedone-l3-1-8b-v1-v1_reward/vocab.json
kaoeiri-hedone-l3-1-8b-v1-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/kaoeiri-hedone-l3-1-8b-v1-v1_reward/tokenizer.json
kaoeiri-hedone-l3-1-8b-v1-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/kaoeiri-hedone-l3-1-8b-v1-v1_reward/reward.tensors
Job kaoeiri-hedone-l3-1-8b-v1-v1-mkmlizer completed after 115.27s with status: succeeded
Stopping job with name kaoeiri-hedone-l3-1-8b-v1-v1-mkmlizer
Pipeline stage MKMLizer completed in 116.41s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service kaoeiri-hedone-l3-1-8b-v1-v1
Waiting for inference service kaoeiri-hedone-l3-1-8b-v1-v1 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
Failed to get response for submission turboderp-cat-llama-3-7_8684_v21: ('http://turboderp-cat-llama-3-7-8684-v21-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Failed to get response for submission turboderp-cat-llama-3-7_8684_v21: ('http://turboderp-cat-llama-3-7-8684-v21-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '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
Connection pool is full, discarding connection: %s. Connection pool size: %s
Failed to get response for submission turboderp-cat-llama-3-7_8684_v21: ('http://turboderp-cat-llama-3-7-8684-v21-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'activator request timeout')
Failed to get response for submission turboderp-cat-llama-3-7_8684_v21: ('http://turboderp-cat-llama-3-7-8684-v21-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Inference service kaoeiri-hedone-l3-1-8b-v1-v1 ready after 181.17526245117188s
Pipeline stage ISVCDeployer completed in 183.78s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3867571353912354s
Received healthy response to inference request in 1.4538798332214355s
Received healthy response to inference request in 1.4282183647155762s
Received healthy response to inference request in 1.412811040878296s
Received healthy response to inference request in 1.4887499809265137s
5 requests
0 failed requests
5th percentile: 1.4158925056457519
10th percentile: 1.418973970413208
20th percentile: 1.4251368999481202
30th percentile: 1.4333506584167481
40th percentile: 1.4436152458190918
50th percentile: 1.4538798332214355
60th percentile: 1.4678278923034669
70th percentile: 1.481775951385498
80th percentile: 1.6683514118194582
90th percentile: 2.0275542736053467
95th percentile: 2.207155704498291
99th percentile: 2.3508368492126466
mean time: 1.6340832710266113
Pipeline stage StressChecker completed in 8.95s
kaoeiri-hedone-l3-1-8b-v1_v1 status is now deployed due to DeploymentManager action
kaoeiri-hedone-l3-1-8b-v1_v1 status is now inactive due to auto deactivation removed underperforming models
kaoeiri-hedone-l3-1-8b-v1_v1 status is now torndown due to DeploymentManager action