developer_uid: shiroe40
submission_id: cycy233-l3-b-c-v0-c5_v2
model_name: auto
model_group: cycy233/L3-b-c-v0-c5
status: torndown
timestamp: 2024-07-22T04:08:06+00:00
num_battles: 14045
num_wins: 8259
celo_rating: 1253.03
family_friendly_score: 0.0
submission_type: basic
model_repo: cycy233/L3-b-c-v0-c5
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/L3-b-c-v0-c5
model_size: 8B
ranking_group: single
us_pacific_date: 2024-07-21
win_ratio: 0.5880384478462086
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}
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-l3-b-c-v0-c5-v2-mkmlizer
Waiting for job on cycy233-l3-b-c-v0-c5-v2-mkmlizer to finish
cycy233-l3-b-c-v0-c5-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-b-c-v0-c5-v2-mkmlizer: ║ _____ __ __ ║
cycy233-l3-b-c-v0-c5-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-l3-b-c-v0-c5-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-l3-b-c-v0-c5-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-l3-b-c-v0-c5-v2-mkmlizer: ║ /___/ ║
cycy233-l3-b-c-v0-c5-v2-mkmlizer: ║ ║
cycy233-l3-b-c-v0-c5-v2-mkmlizer: ║ Version: 0.9.5.post3 ║
cycy233-l3-b-c-v0-c5-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-l3-b-c-v0-c5-v2-mkmlizer: ║ https://mk1.ai ║
cycy233-l3-b-c-v0-c5-v2-mkmlizer: ║ ║
cycy233-l3-b-c-v0-c5-v2-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-l3-b-c-v0-c5-v2-mkmlizer: ║ belonging to: ║
cycy233-l3-b-c-v0-c5-v2-mkmlizer: ║ ║
cycy233-l3-b-c-v0-c5-v2-mkmlizer: ║ Chai Research Corp. ║
cycy233-l3-b-c-v0-c5-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-l3-b-c-v0-c5-v2-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
cycy233-l3-b-c-v0-c5-v2-mkmlizer: ║ ║
cycy233-l3-b-c-v0-c5-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-b-c-v0-c5-v2-mkmlizer: Downloaded to shared memory in 22.441s
cycy233-l3-b-c-v0-c5-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpyu_ezqi2, device:0
cycy233-l3-b-c-v0-c5-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-b-c-v0-c5-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:02, 116.24it/s] Loading 0: 10%|█ | 30/291 [00:00<00:01, 134.16it/s] Loading 0: 15%|█▌ | 44/291 [00:00<00:01, 131.30it/s] Loading 0: 20%|█▉ | 58/291 [00:00<00:01, 130.77it/s] Loading 0: 25%|██▌ | 73/291 [00:00<00:01, 136.97it/s] Loading 0: 30%|██▉ | 87/291 [00:00<00:02, 74.34it/s] Loading 0: 35%|███▌ | 102/291 [00:01<00:02, 89.31it/s] Loading 0: 39%|███▉ | 114/291 [00:01<00:01, 95.23it/s] Loading 0: 45%|████▍ | 130/291 [00:01<00:01, 106.43it/s] Loading 0: 51%|█████ | 147/291 [00:01<00:01, 117.15it/s] Loading 0: 55%|█████▌ | 161/291 [00:01<00:01, 119.30it/s] Loading 0: 60%|██████ | 176/291 [00:01<00:00, 125.97it/s] Loading 0: 65%|██████▌ | 190/291 [00:01<00:01, 80.66it/s] Loading 0: 69%|██████▉ | 202/291 [00:01<00:01, 88.17it/s] Loading 0: 75%|███████▌ | 219/291 [00:02<00:00, 102.89it/s] Loading 0: 80%|███████▉ | 232/291 [00:02<00:00, 108.70it/s] Loading 0: 85%|████████▍ | 247/291 [00:02<00:00, 115.09it/s] Loading 0: 91%|█████████ | 264/291 [00:02<00:00, 124.65it/s] Loading 0: 96%|█████████▌| 278/291 [00:02<00:00, 126.55it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cycy233-l3-b-c-v0-c5-v2-mkmlizer: quantized model in 22.838s
cycy233-l3-b-c-v0-c5-v2-mkmlizer: Processed model cycy233/L3-b-c-v0-c5 in 45.279s
cycy233-l3-b-c-v0-c5-v2-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-b-c-v0-c5-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-b-c-v0-c5-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-b-c-v0-c5-v2
cycy233-l3-b-c-v0-c5-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-b-c-v0-c5-v2/config.json
cycy233-l3-b-c-v0-c5-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-b-c-v0-c5-v2/special_tokens_map.json
cycy233-l3-b-c-v0-c5-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-b-c-v0-c5-v2/tokenizer_config.json
cycy233-l3-b-c-v0-c5-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-b-c-v0-c5-v2/tokenizer.json
cycy233-l3-b-c-v0-c5-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-b-c-v0-c5-v2/flywheel_model.0.safetensors
cycy233-l3-b-c-v0-c5-v2-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
cycy233-l3-b-c-v0-c5-v2-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:950: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
cycy233-l3-b-c-v0-c5-v2-mkmlizer: warnings.warn(
cycy233-l3-b-c-v0-c5-v2-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:778: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
cycy233-l3-b-c-v0-c5-v2-mkmlizer: warnings.warn(
cycy233-l3-b-c-v0-c5-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-b-c-v0-c5-v2-mkmlizer: warnings.warn(
cycy233-l3-b-c-v0-c5-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-l3-b-c-v0-c5-v2-mkmlizer: Saving duration: 1.379s
cycy233-l3-b-c-v0-c5-v2-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 11.096s
cycy233-l3-b-c-v0-c5-v2-mkmlizer: creating bucket guanaco-reward-models
cycy233-l3-b-c-v0-c5-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-l3-b-c-v0-c5-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-l3-b-c-v0-c5-v2_reward
cycy233-l3-b-c-v0-c5-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-l3-b-c-v0-c5-v2_reward/config.json
cycy233-l3-b-c-v0-c5-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-l3-b-c-v0-c5-v2_reward/special_tokens_map.json
cycy233-l3-b-c-v0-c5-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-l3-b-c-v0-c5-v2_reward/tokenizer_config.json
cycy233-l3-b-c-v0-c5-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-l3-b-c-v0-c5-v2_reward/merges.txt
cycy233-l3-b-c-v0-c5-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-l3-b-c-v0-c5-v2_reward/vocab.json
cycy233-l3-b-c-v0-c5-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-l3-b-c-v0-c5-v2_reward/tokenizer.json
cycy233-l3-b-c-v0-c5-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-l3-b-c-v0-c5-v2_reward/reward.tensors
Job cycy233-l3-b-c-v0-c5-v2-mkmlizer completed after 87.86s with status: succeeded
Stopping job with name cycy233-l3-b-c-v0-c5-v2-mkmlizer
Pipeline stage MKMLizer completed in 89.51s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-l3-b-c-v0-c5-v2
Waiting for inference service cycy233-l3-b-c-v0-c5-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
Inference service cycy233-l3-b-c-v0-c5-v2 ready after 50.976799964904785s
Pipeline stage ISVCDeployer completed in 53.28s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3723907470703125s
Received healthy response to inference request in 1.3735065460205078s
Received healthy response to inference request in 1.4266843795776367s
Received healthy response to inference request in 1.394446611404419s
Received healthy response to inference request in 1.4940619468688965s
5 requests
0 failed requests
5th percentile: 1.37769455909729
10th percentile: 1.3818825721740722
20th percentile: 1.3902585983276368
30th percentile: 1.4008941650390625
40th percentile: 1.4137892723083496
50th percentile: 1.4266843795776367
60th percentile: 1.4536354064941406
70th percentile: 1.4805864334106444
80th percentile: 1.6697277069091798
90th percentile: 2.0210592269897463
95th percentile: 2.196724987030029
99th percentile: 2.3372575950622556
mean time: 1.6122180461883544
Pipeline stage StressChecker completed in 8.69s
cycy233-l3-b-c-v0-c5_v2 status is now deployed due to DeploymentManager action
cycy233-l3-b-c-v0-c5_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cycy233-l3-b-c-v0-c5_v2
Running pipeline stage ISVCDeleter
Checking if service cycy233-l3-b-c-v0-c5-v2 is running
Tearing down inference service cycy233-l3-b-c-v0-c5-v2
Service cycy233-l3-b-c-v0-c5-v2 has been torndown
Pipeline stage ISVCDeleter completed in 5.39s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cycy233-l3-b-c-v0-c5-v2/config.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-b-c-v0-c5-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cycy233-l3-b-c-v0-c5-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-b-c-v0-c5-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-b-c-v0-c5-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cycy233-l3-b-c-v0-c5-v2_reward/config.json from bucket guanaco-reward-models
Deleting key cycy233-l3-b-c-v0-c5-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key cycy233-l3-b-c-v0-c5-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cycy233-l3-b-c-v0-c5-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cycy233-l3-b-c-v0-c5-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cycy233-l3-b-c-v0-c5-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cycy233-l3-b-c-v0-c5-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.42s
cycy233-l3-b-c-v0-c5_v2 status is now torndown due to DeploymentManager action