developer_uid: sao10k
submission_id: sao10k-l3-8b-tamamo-v1_v1
model_name: RP-v5-Expr2
model_group: Sao10K/L3-8B-Tamamo-v1
status: torndown
timestamp: 2024-07-26T21:08:51+00:00
num_battles: 73833
num_wins: 40116
celo_rating: 1255.32
family_friendly_score: 0.0
submission_type: basic
model_repo: Sao10K/L3-8B-Tamamo-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: RP-v5-Expr2
is_internal_developer: False
language_model: Sao10K/L3-8B-Tamamo-v1
model_size: 8B
ranking_group: single
us_pacific_date: 2024-07-26
win_ratio: 0.5433342814188777
generation_params: {'temperature': 1.4, 'top_p': 1.0, 'min_p': 0.1, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|end_header_id|>,', '<|eot_id|>,', '\n\n{user_name}'], '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 sao10k-l3-8b-tamamo-v1-v1-mkmlizer
Waiting for job on sao10k-l3-8b-tamamo-v1-v1-mkmlizer to finish
sao10k-l3-8b-tamamo-v1-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sao10k-l3-8b-tamamo-v1-v1-mkmlizer: ║ _____ __ __ ║
sao10k-l3-8b-tamamo-v1-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
sao10k-l3-8b-tamamo-v1-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
sao10k-l3-8b-tamamo-v1-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
sao10k-l3-8b-tamamo-v1-v1-mkmlizer: ║ /___/ ║
sao10k-l3-8b-tamamo-v1-v1-mkmlizer: ║ ║
sao10k-l3-8b-tamamo-v1-v1-mkmlizer: ║ Version: 0.9.7 ║
sao10k-l3-8b-tamamo-v1-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
sao10k-l3-8b-tamamo-v1-v1-mkmlizer: ║ https://mk1.ai ║
sao10k-l3-8b-tamamo-v1-v1-mkmlizer: ║ ║
sao10k-l3-8b-tamamo-v1-v1-mkmlizer: ║ The license key for the current software has been verified as ║
sao10k-l3-8b-tamamo-v1-v1-mkmlizer: ║ belonging to: ║
sao10k-l3-8b-tamamo-v1-v1-mkmlizer: ║ ║
sao10k-l3-8b-tamamo-v1-v1-mkmlizer: ║ Chai Research Corp. ║
sao10k-l3-8b-tamamo-v1-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
sao10k-l3-8b-tamamo-v1-v1-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
sao10k-l3-8b-tamamo-v1-v1-mkmlizer: ║ ║
sao10k-l3-8b-tamamo-v1-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
sao10k-l3-8b-tamamo-v1-v1-mkmlizer: Downloaded to shared memory in 32.670s
sao10k-l3-8b-tamamo-v1-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpk8__x_gc, device:0
sao10k-l3-8b-tamamo-v1-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
sao10k-l3-8b-tamamo-v1-v1-mkmlizer: quantized model in 26.284s
sao10k-l3-8b-tamamo-v1-v1-mkmlizer: Processed model Sao10K/L3-8B-Tamamo-v1 in 58.955s
sao10k-l3-8b-tamamo-v1-v1-mkmlizer: creating bucket guanaco-mkml-models
sao10k-l3-8b-tamamo-v1-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sao10k-l3-8b-tamamo-v1-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sao10k-l3-8b-tamamo-v1-v1
sao10k-l3-8b-tamamo-v1-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sao10k-l3-8b-tamamo-v1-v1/config.json
sao10k-l3-8b-tamamo-v1-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sao10k-l3-8b-tamamo-v1-v1/special_tokens_map.json
sao10k-l3-8b-tamamo-v1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sao10k-l3-8b-tamamo-v1-v1/tokenizer_config.json
sao10k-l3-8b-tamamo-v1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sao10k-l3-8b-tamamo-v1-v1/tokenizer.json
sao10k-l3-8b-tamamo-v1-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sao10k-l3-8b-tamamo-v1-v1/flywheel_model.0.safetensors
Failed to get response for submission chaiml-sao10k-l3-rp-v3-3_v37: ('http://chaiml-sao10k-l3-rp-v3-3-v37-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:44080->127.0.0.1:8080: read: connection reset by peer\n')
sao10k-l3-8b-tamamo-v1-v1-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
sao10k-l3-8b-tamamo-v1-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<11:32, 2.40s/it] Loading 0: 2%|▏ | 6/291 [00:04<03:04, 1.54it/s] Loading 0: 4%|▍ | 11/291 [00:05<01:21, 3.44it/s] Loading 0: 5%|▌ | 15/291 [00:05<00:51, 5.32it/s] Loading 0: 8%|▊ | 23/291 [00:05<00:25, 10.40it/s] Loading 0: 10%|▉ | 29/291 [00:05<00:18, 14.04it/s] Loading 0: 12%|█▏ | 34/291 [00:05<00:14, 17.59it/s] Loading 0: 14%|█▍ | 42/291 [00:05<00:10, 23.51it/s] Loading 0: 17%|█▋ | 50/291 [00:05<00:07, 31.59it/s] Loading 0: 19%|█▉ | 56/291 [00:05<00:07, 33.51it/s] Loading 0: 21%|██ | 61/291 [00:06<00:08, 26.49it/s] Loading 0: 23%|██▎ | 68/291 [00:06<00:06, 32.68it/s] Loading 0: 25%|██▌ | 74/291 [00:06<00:06, 34.65it/s] Loading 0: 27%|██▋ | 79/291 [00:06<00:05, 36.36it/s] Loading 0: 30%|██▉ | 86/291 [00:06<00:04, 42.85it/s] Loading 0: 32%|███▏ | 92/291 [00:06<00:04, 41.86it/s] Loading 0: 33%|███▎ | 97/291 [00:07<00:04, 42.17it/s] Loading 0: 36%|███▌ | 104/291 [00:07<00:03, 47.90it/s] Loading 0: 38%|███▊ | 110/291 [00:07<00:03, 45.51it/s] Loading 0: 40%|███▉ | 115/291 [00:07<00:04, 43.64it/s] Loading 0: 42%|████▏ | 121/291 [00:07<00:03, 47.62it/s] Loading 0: 43%|████▎ | 126/291 [00:07<00:03, 47.28it/s] Loading 0: 45%|████▌ | 132/291 [00:07<00:03, 41.32it/s] Loading 0: 48%|████▊ | 139/291 [00:07<00:03, 48.03it/s] Loading 0: 50%|████▉ | 145/291 [00:08<00:02, 50.06it/s] Loading 0: 52%|█████▏ | 151/291 [00:08<00:03, 45.43it/s] Loading 0: 54%|█████▍ | 158/291 [00:08<00:02, 50.83it/s] Loading 0: 56%|█████▋ | 164/291 [00:08<00:02, 47.72it/s] Loading 0: 58%|█████▊ | 170/291 [00:08<00:03, 34.95it/s] Loading 0: 60%|██████ | 176/291 [00:08<00:02, 39.64it/s] Loading 0: 63%|██████▎ | 182/291 [00:08<00:02, 40.14it/s] Loading 0: 64%|██████▍ | 187/291 [00:09<00:02, 41.07it/s] Loading 0: 67%|██████▋ | 194/291 [00:09<00:02, 47.48it/s] Loading 0: 69%|██████▊ | 200/291 [00:09<00:01, 46.27it/s] Loading 0: 70%|███████ | 205/291 [00:09<00:01, 46.96it/s] Loading 0: 73%|███████▎ | 211/291 [00:09<00:01, 50.27it/s] Loading 0: 75%|███████▍ | 217/291 [00:09<00:01, 52.47it/s] Loading 0: 77%|███████▋ | 223/291 [00:09<00:01, 44.81it/s] Loading 0: 79%|███████▉ | 230/291 [00:09<00:01, 50.58it/s] Loading 0: 81%|████████ | 236/291 [00:10<00:01, 46.57it/s] Loading 0: 83%|████████▎ | 241/291 [00:10<00:01, 45.73it/s] Loading 0: 85%|████████▌ | 248/291 [00:10<00:00, 51.55it/s] Loading 0: 87%|████████▋ | 254/291 [00:10<00:00, 48.48it/s] Loading 0: 89%|████████▉ | 260/291 [00:10<00:00, 50.38it/s] Loading 0: 91%|█████████▏| 266/291 [00:10<00:00, 36.57it/s] Loading 0: 93%|█████████▎| 272/291 [00:10<00:00, 37.96it/s] Loading 0: 95%|█████████▌| 277/291 [00:11<00:00, 39.87it/s] Loading 0: 98%|█████████▊| 284/291 [00:11<00:00, 45.49it/s] Loading 0: 100%|█████████▉| 290/291 [00:11<00:00, 45.14it/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.
sao10k-l3-8b-tamamo-v1-v1-mkmlizer: warnings.warn(
sao10k-l3-8b-tamamo-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.
sao10k-l3-8b-tamamo-v1-v1-mkmlizer: warnings.warn(
sao10k-l3-8b-tamamo-v1-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.
sao10k-l3-8b-tamamo-v1-v1-mkmlizer: warnings.warn(
sao10k-l3-8b-tamamo-v1-v1-mkmlizer: Saving duration: 1.383s
sao10k-l3-8b-tamamo-v1-v1-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 10.642s
sao10k-l3-8b-tamamo-v1-v1-mkmlizer: creating bucket guanaco-reward-models
sao10k-l3-8b-tamamo-v1-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
sao10k-l3-8b-tamamo-v1-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/sao10k-l3-8b-tamamo-v1-v1_reward
sao10k-l3-8b-tamamo-v1-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/sao10k-l3-8b-tamamo-v1-v1_reward/config.json
sao10k-l3-8b-tamamo-v1-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/sao10k-l3-8b-tamamo-v1-v1_reward/special_tokens_map.json
sao10k-l3-8b-tamamo-v1-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/sao10k-l3-8b-tamamo-v1-v1_reward/tokenizer_config.json
sao10k-l3-8b-tamamo-v1-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/sao10k-l3-8b-tamamo-v1-v1_reward/merges.txt
sao10k-l3-8b-tamamo-v1-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/sao10k-l3-8b-tamamo-v1-v1_reward/vocab.json
sao10k-l3-8b-tamamo-v1-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/sao10k-l3-8b-tamamo-v1-v1_reward/tokenizer.json
sao10k-l3-8b-tamamo-v1-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/sao10k-l3-8b-tamamo-v1-v1_reward/reward.tensors
Job sao10k-l3-8b-tamamo-v1-v1-mkmlizer completed after 106.16s with status: succeeded
Stopping job with name sao10k-l3-8b-tamamo-v1-v1-mkmlizer
Pipeline stage MKMLizer completed in 107.15s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service sao10k-l3-8b-tamamo-v1-v1
Waiting for inference service sao10k-l3-8b-tamamo-v1-v1 to be ready
Inference service sao10k-l3-8b-tamamo-v1-v1 ready after 90.84777498245239s
Pipeline stage ISVCDeployer completed in 92.56s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1879663467407227s
Received healthy response to inference request in 1.433485507965088s
Received healthy response to inference request in 1.4213862419128418s
Received healthy response to inference request in 1.4097883701324463s
Received healthy response to inference request in 1.4618747234344482s
5 requests
0 failed requests
5th percentile: 1.4121079444885254
10th percentile: 1.4144275188446045
20th percentile: 1.4190666675567627
30th percentile: 1.423806095123291
40th percentile: 1.4286458015441894
50th percentile: 1.433485507965088
60th percentile: 1.444841194152832
70th percentile: 1.4561968803405763
80th percentile: 1.6070930480957033
90th percentile: 1.897529697418213
95th percentile: 2.0427480220794676
99th percentile: 2.1589226818084715
mean time: 1.5829002380371093
Pipeline stage StressChecker completed in 8.60s
sao10k-l3-8b-tamamo-v1_v1 status is now deployed due to DeploymentManager action
sao10k-l3-8b-tamamo-v1_v1 status is now inactive due to auto deactivation removed underperforming models
sao10k-l3-8b-tamamo-v1_v1 status is now deployed due to admin request
sao10k-l3-8b-tamamo-v1_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of sao10k-l3-8b-tamamo-v1_v1
Running pipeline stage ISVCDeleter
Checking if service sao10k-l3-8b-tamamo-v1-v1 is running
Tearing down inference service sao10k-l3-8b-tamamo-v1-v1
Service sao10k-l3-8b-tamamo-v1-v1 has been torndown
Pipeline stage ISVCDeleter completed in 4.89s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key sao10k-l3-8b-tamamo-v1-v1/config.json from bucket guanaco-mkml-models
Deleting key sao10k-l3-8b-tamamo-v1-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key sao10k-l3-8b-tamamo-v1-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key sao10k-l3-8b-tamamo-v1-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key sao10k-l3-8b-tamamo-v1-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key sao10k-l3-8b-tamamo-v1-v1_reward/config.json from bucket guanaco-reward-models
Deleting key sao10k-l3-8b-tamamo-v1-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key sao10k-l3-8b-tamamo-v1-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key sao10k-l3-8b-tamamo-v1-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key sao10k-l3-8b-tamamo-v1-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key sao10k-l3-8b-tamamo-v1-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key sao10k-l3-8b-tamamo-v1-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.40s
sao10k-l3-8b-tamamo-v1_v1 status is now torndown due to DeploymentManager action