developer_uid: shiroe40
submission_id: cycy233-l-ba-v1-c3_v2
model_name: auto
model_group: cycy233/L-ba-v1-c3
status: torndown
timestamp: 2024-08-03T01:08:56+00:00
num_battles: 24798
num_wins: 12484
celo_rating: 1227.51
family_friendly_score: 0.0
submission_type: basic
model_repo: cycy233/L-ba-v1-c3
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/L-ba-v1-c3
model_size: 8B
ranking_group: single
us_pacific_date: 2024-08-02
win_ratio: 0.5034276957819179
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': ['\n', '<|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-l-ba-v1-c3-v2-mkmlizer
Waiting for job on cycy233-l-ba-v1-c3-v2-mkmlizer to finish
cycy233-l-ba-v1-c3-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l-ba-v1-c3-v2-mkmlizer: ║ _____ __ __ ║
cycy233-l-ba-v1-c3-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-l-ba-v1-c3-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-l-ba-v1-c3-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-l-ba-v1-c3-v2-mkmlizer: ║ /___/ ║
cycy233-l-ba-v1-c3-v2-mkmlizer: ║ ║
cycy233-l-ba-v1-c3-v2-mkmlizer: ║ Version: 0.9.9 ║
cycy233-l-ba-v1-c3-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-l-ba-v1-c3-v2-mkmlizer: ║ https://mk1.ai ║
cycy233-l-ba-v1-c3-v2-mkmlizer: ║ ║
cycy233-l-ba-v1-c3-v2-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-l-ba-v1-c3-v2-mkmlizer: ║ belonging to: ║
cycy233-l-ba-v1-c3-v2-mkmlizer: ║ ║
cycy233-l-ba-v1-c3-v2-mkmlizer: ║ Chai Research Corp. ║
cycy233-l-ba-v1-c3-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-l-ba-v1-c3-v2-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
cycy233-l-ba-v1-c3-v2-mkmlizer: ║ ║
cycy233-l-ba-v1-c3-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l-ba-v1-c3-v2-mkmlizer: Downloaded to shared memory in 21.799s
cycy233-l-ba-v1-c3-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpk9kynvgb, device:0
cycy233-l-ba-v1-c3-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l-ba-v1-c3-v2-mkmlizer: quantized model in 25.796s
cycy233-l-ba-v1-c3-v2-mkmlizer: Processed model cycy233/L-ba-v1-c3 in 47.595s
cycy233-l-ba-v1-c3-v2-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l-ba-v1-c3-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l-ba-v1-c3-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l-ba-v1-c3-v2
cycy233-l-ba-v1-c3-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l-ba-v1-c3-v2/config.json
cycy233-l-ba-v1-c3-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l-ba-v1-c3-v2/special_tokens_map.json
cycy233-l-ba-v1-c3-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l-ba-v1-c3-v2/tokenizer_config.json
cycy233-l-ba-v1-c3-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l-ba-v1-c3-v2/tokenizer.json
cycy233-l-ba-v1-c3-v2-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
cycy233-l-ba-v1-c3-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%|▏ | 4/291 [00:00<00:07, 37.77it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:04, 63.30it/s] Loading 0: 9%|▊ | 25/291 [00:00<00:03, 74.85it/s] Loading 0: 12%|█▏ | 34/291 [00:00<00:03, 76.58it/s] Loading 0: 15%|█▍ | 43/291 [00:00<00:03, 78.22it/s] Loading 0: 18%|█▊ | 52/291 [00:00<00:02, 80.07it/s] Loading 0: 21%|██ | 61/291 [00:00<00:02, 82.68it/s] Loading 0: 24%|██▍ | 70/291 [00:00<00:02, 84.83it/s] Loading 0: 27%|██▋ | 79/291 [00:00<00:02, 85.47it/s] Loading 0: 30%|███ | 88/291 [00:02<00:09, 21.51it/s] Loading 0: 33%|███▎ | 97/291 [00:02<00:07, 27.55it/s] Loading 0: 37%|███▋ | 107/291 [00:02<00:05, 36.08it/s] Loading 0: 42%|████▏ | 121/291 [00:02<00:03, 47.58it/s] Loading 0: 46%|████▌ | 133/291 [00:02<00:02, 55.65it/s] Loading 0: 51%|█████ | 148/291 [00:02<00:02, 66.83it/s] Loading 0: 55%|█████▍ | 159/291 [00:02<00:01, 74.69it/s] Loading 0: 58%|█████▊ | 169/291 [00:03<00:01, 65.71it/s] Loading 0: 61%|██████ | 178/291 [00:03<00:01, 68.77it/s] Loading 0: 64%|██████▍ | 187/291 [00:04<00:04, 23.10it/s] Loading 0: 67%|██████▋ | 196/291 [00:04<00:03, 29.03it/s] Loading 0: 70%|███████ | 205/291 [00:04<00:02, 35.64it/s] Loading 0: 74%|███████▎ | 214/291 [00:04<00:01, 42.17it/s] Loading 0: 77%|███████▋ | 223/291 [00:04<00:01, 48.89it/s] Loading 0: 80%|███████▉ | 232/291 [00:04<00:01, 55.71it/s] Loading 0: 85%|████████▍ | 247/291 [00:04<00:00, 68.05it/s] Loading 0: 88%|████████▊ | 256/291 [00:05<00:00, 72.62it/s] Loading 0: 91%|█████████ | 265/291 [00:05<00:00, 75.84it/s] Loading 0: 94%|█████████▍| 274/291 [00:05<00:00, 78.53it/s] Loading 0: 97%|█████████▋| 283/291 [00:05<00:00, 79.34it/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-l-ba-v1-c3-v2-mkmlizer: warnings.warn(
cycy233-l-ba-v1-c3-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-l-ba-v1-c3-v2-mkmlizer: warnings.warn(
cycy233-l-ba-v1-c3-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-l-ba-v1-c3-v2-mkmlizer: warnings.warn(
cycy233-l-ba-v1-c3-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-l-ba-v1-c3-v2-mkmlizer: Saving duration: 1.393s
cycy233-l-ba-v1-c3-v2-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 10.354s
cycy233-l-ba-v1-c3-v2-mkmlizer: creating bucket guanaco-reward-models
cycy233-l-ba-v1-c3-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-l-ba-v1-c3-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-l-ba-v1-c3-v2_reward
cycy233-l-ba-v1-c3-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-l-ba-v1-c3-v2_reward/config.json
cycy233-l-ba-v1-c3-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-l-ba-v1-c3-v2_reward/special_tokens_map.json
cycy233-l-ba-v1-c3-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-l-ba-v1-c3-v2_reward/tokenizer_config.json
cycy233-l-ba-v1-c3-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-l-ba-v1-c3-v2_reward/merges.txt
cycy233-l-ba-v1-c3-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-l-ba-v1-c3-v2_reward/vocab.json
cycy233-l-ba-v1-c3-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-l-ba-v1-c3-v2_reward/tokenizer.json
cycy233-l-ba-v1-c3-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-l-ba-v1-c3-v2_reward/reward.tensors
Job cycy233-l-ba-v1-c3-v2-mkmlizer completed after 96.23s with status: succeeded
Stopping job with name cycy233-l-ba-v1-c3-v2-mkmlizer
Pipeline stage MKMLizer completed in 97.48s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-l-ba-v1-c3-v2
Waiting for inference service cycy233-l-ba-v1-c3-v2 to be ready
Inference service cycy233-l-ba-v1-c3-v2 ready after 141.17415380477905s
Pipeline stage ISVCDeployer completed in 142.69s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1966538429260254s
Received healthy response to inference request in 1.4602069854736328s
Received healthy response to inference request in 1.4444544315338135s
Received healthy response to inference request in 1.3997573852539062s
Received healthy response to inference request in 1.458186388015747s
5 requests
0 failed requests
5th percentile: 1.4086967945098876
10th percentile: 1.4176362037658692
20th percentile: 1.4355150222778321
30th percentile: 1.4472008228302002
40th percentile: 1.4526936054229735
50th percentile: 1.458186388015747
60th percentile: 1.4589946269989014
70th percentile: 1.4598028659820557
80th percentile: 1.6074963569641114
90th percentile: 1.9020750999450684
95th percentile: 2.049364471435547
99th percentile: 2.16719596862793
mean time: 1.591851806640625
Pipeline stage StressChecker completed in 8.70s
cycy233-l-ba-v1-c3_v2 status is now deployed due to DeploymentManager action
cycy233-l-ba-v1-c3_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cycy233-l-ba-v1-c3_v2
Running pipeline stage ISVCDeleter
Checking if service cycy233-l-ba-v1-c3-v2 is running
Tearing down inference service cycy233-l-ba-v1-c3-v2
Service cycy233-l-ba-v1-c3-v2 has been torndown
Pipeline stage ISVCDeleter completed in 5.46s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cycy233-l-ba-v1-c3-v2/config.json from bucket guanaco-mkml-models
Deleting key cycy233-l-ba-v1-c3-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cycy233-l-ba-v1-c3-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cycy233-l-ba-v1-c3-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key cycy233-l-ba-v1-c3-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cycy233-l-ba-v1-c3-v2_reward/config.json from bucket guanaco-reward-models
Deleting key cycy233-l-ba-v1-c3-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key cycy233-l-ba-v1-c3-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cycy233-l-ba-v1-c3-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cycy233-l-ba-v1-c3-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cycy233-l-ba-v1-c3-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cycy233-l-ba-v1-c3-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 27.30s
cycy233-l-ba-v1-c3_v2 status is now torndown due to DeploymentManager action