cycy233-l3-e-v2-c4

developer_uid: shiroe40

submission_id: cycy233-l3-e-v2-c4_v5

model_name: auto

model_group: cycy233/L3-e-v2-c4

status: torndown

timestamp: 2024-07-20T03:53:36+00:00

num_battles: 8548

num_wins: 4889

celo_rating: 1264.21

family_friendly_score: 0.0

submission_type: basic

model_repo: cycy233/L3-e-v2-c4

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-e-v2-c4

model_size: 8B

ranking_group: single

us_pacific_date: 2024-07-19

win_ratio: 0.5719466541881142

generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}

formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{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-e-v2-c4-v5-mkmlizer
Waiting for job on cycy233-l3-e-v2-c4-v5-mkmlizer to finish
cycy233-l3-e-v2-c4-v5-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-e-v2-c4-v5-mkmlizer: ║     _____            __           __                                ║
cycy233-l3-e-v2-c4-v5-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cycy233-l3-e-v2-c4-v5-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cycy233-l3-e-v2-c4-v5-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cycy233-l3-e-v2-c4-v5-mkmlizer: ║       /___/                                                         ║
cycy233-l3-e-v2-c4-v5-mkmlizer: ║                                                                     ║
cycy233-l3-e-v2-c4-v5-mkmlizer: ║  Version: 0.9.5.post3                                               ║
cycy233-l3-e-v2-c4-v5-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cycy233-l3-e-v2-c4-v5-mkmlizer: ║  https://mk1.ai                                                     ║
cycy233-l3-e-v2-c4-v5-mkmlizer: ║                                                                     ║
cycy233-l3-e-v2-c4-v5-mkmlizer: ║  The license key for the current software has been verified as      ║
cycy233-l3-e-v2-c4-v5-mkmlizer: ║  belonging to:                                                      ║
cycy233-l3-e-v2-c4-v5-mkmlizer: ║                                                                     ║
cycy233-l3-e-v2-c4-v5-mkmlizer: ║  Chai Research Corp.                                                ║
cycy233-l3-e-v2-c4-v5-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cycy233-l3-e-v2-c4-v5-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
cycy233-l3-e-v2-c4-v5-mkmlizer: ║                                                                     ║
cycy233-l3-e-v2-c4-v5-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-e-v2-c4-v5-mkmlizer: Downloaded to shared memory in 20.732s
cycy233-l3-e-v2-c4-v5-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpo3ba0fcj, device:0
cycy233-l3-e-v2-c4-v5-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-e-v2-c4-v5-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   4%|▍         | 13/291 [00:00<00:02, 115.69it/s]
Loading 0:  10%|█         | 30/291 [00:00<00:01, 134.60it/s]
Loading 0:  15%|█▌        | 44/291 [00:00<00:01, 132.47it/s]
Loading 0:  20%|█▉        | 58/291 [00:00<00:01, 130.19it/s]
Loading 0:  25%|██▍       | 72/291 [00:00<00:01, 114.03it/s]
Loading 0:  29%|██▉       | 84/291 [00:00<00:02, 74.48it/s] 
Loading 0:  33%|███▎      | 95/291 [00:00<00:02, 80.52it/s]
Loading 0:  38%|███▊      | 112/291 [00:01<00:01, 97.12it/s]
Loading 0:  43%|████▎     | 126/291 [00:01<00:01, 107.23it/s]
Loading 0:  48%|████▊     | 139/291 [00:01<00:01, 111.58it/s]
Loading 0:  53%|█████▎    | 153/291 [00:01<00:01, 118.24it/s]
Loading 0:  57%|█████▋    | 166/291 [00:01<00:01, 119.59it/s]
Loading 0:  62%|██████▏   | 180/291 [00:01<00:00, 124.95it/s]
Loading 0:  66%|██████▋   | 193/291 [00:01<00:01, 81.73it/s] 
Loading 0:  72%|███████▏  | 210/291 [00:02<00:00, 96.64it/s]
Loading 0:  76%|███████▋  | 222/291 [00:02<00:00, 101.09it/s]
Loading 0:  81%|████████▏ | 237/291 [00:02<00:00, 112.56it/s]
Loading 0:  86%|████████▌ | 250/291 [00:02<00:00, 112.14it/s]
Loading 0:  91%|█████████ | 265/291 [00:02<00:00, 118.15it/s]
Loading 0:  97%|█████████▋| 281/291 [00:02<00:00, 124.74it/s]
                                                             
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cycy233-l3-e-v2-c4-v5-mkmlizer: quantized model in 22.409s
cycy233-l3-e-v2-c4-v5-mkmlizer: Processed model cycy233/L3-e-v2-c4 in 43.141s
cycy233-l3-e-v2-c4-v5-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-e-v2-c4-v5-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-e-v2-c4-v5-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-e-v2-c4-v5
cycy233-l3-e-v2-c4-v5-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-e-v2-c4-v5/config.json
cycy233-l3-e-v2-c4-v5-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-e-v2-c4-v5/special_tokens_map.json
cycy233-l3-e-v2-c4-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-e-v2-c4-v5/tokenizer_config.json
cycy233-l3-e-v2-c4-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-e-v2-c4-v5/tokenizer.json
Failed to get response for submission kaoeiri-pantheramix-l3-r_5669_v7: ('http://kaoeiri-pantheramix-l3-r-5669-v7-predictor-default.tenant-chaiml-guanaco.knative.ord1.coreweave.cloud/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
cycy233-l3-e-v2-c4-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-e-v2-c4-v5/flywheel_model.0.safetensors
cycy233-l3-e-v2-c4-v5-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
cycy233-l3-e-v2-c4-v5-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-e-v2-c4-v5-mkmlizer:   warnings.warn(
cycy233-l3-e-v2-c4-v5-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-e-v2-c4-v5-mkmlizer:   warnings.warn(
cycy233-l3-e-v2-c4-v5-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-e-v2-c4-v5-mkmlizer:   warnings.warn(
cycy233-l3-e-v2-c4-v5-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-l3-e-v2-c4-v5-mkmlizer: Saving duration: 1.385s
cycy233-l3-e-v2-c4-v5-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 10.640s
cycy233-l3-e-v2-c4-v5-mkmlizer: creating bucket guanaco-reward-models
cycy233-l3-e-v2-c4-v5-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-l3-e-v2-c4-v5-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-l3-e-v2-c4-v5_reward
cycy233-l3-e-v2-c4-v5-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-l3-e-v2-c4-v5_reward/config.json
cycy233-l3-e-v2-c4-v5-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-l3-e-v2-c4-v5_reward/special_tokens_map.json
cycy233-l3-e-v2-c4-v5-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-l3-e-v2-c4-v5_reward/tokenizer_config.json
cycy233-l3-e-v2-c4-v5-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-l3-e-v2-c4-v5_reward/merges.txt
cycy233-l3-e-v2-c4-v5-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-l3-e-v2-c4-v5_reward/vocab.json
cycy233-l3-e-v2-c4-v5-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-l3-e-v2-c4-v5_reward/tokenizer.json
cycy233-l3-e-v2-c4-v5-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-l3-e-v2-c4-v5_reward/reward.tensors
Job cycy233-l3-e-v2-c4-v5-mkmlizer completed after 89.33s with status: succeeded
Stopping job with name cycy233-l3-e-v2-c4-v5-mkmlizer
Pipeline stage MKMLizer completed in 90.89s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-l3-e-v2-c4-v5
Waiting for inference service cycy233-l3-e-v2-c4-v5 to be ready
Inference service cycy233-l3-e-v2-c4-v5 ready after 41.01194357872009s
Pipeline stage ISVCDeployer completed in 42.86s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2646334171295166s
Received healthy response to inference request in 1.3878681659698486s
Received healthy response to inference request in 1.3831021785736084s
Received healthy response to inference request in 1.3798277378082275s
Received healthy response to inference request in 1.517852783203125s
5 requests
0 failed requests
5th percentile: 1.3804826259613037
10th percentile: 1.3811375141143798
20th percentile: 1.3824472904205323
30th percentile: 1.3840553760528564
40th percentile: 1.3859617710113525
50th percentile: 1.3878681659698486
60th percentile: 1.4398620128631592
70th percentile: 1.4918558597564697
80th percentile: 1.6672089099884035
90th percentile: 1.96592116355896
95th percentile: 2.1152772903442383
99th percentile: 2.234762191772461
mean time: 1.5866568565368653
Pipeline stage StressChecker completed in 8.59s
cycy233-l3-e-v2-c4_v5 status is now deployed due to DeploymentManager action
cycy233-l3-e-v2-c4_v5 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cycy233-l3-e-v2-c4_v5
Running pipeline stage ISVCDeleter
Checking if service cycy233-l3-e-v2-c4-v5 is running
Tearing down inference service cycy233-l3-e-v2-c4-v5
Service cycy233-l3-e-v2-c4-v5 has been torndown
Pipeline stage ISVCDeleter completed in 4.36s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cycy233-l3-e-v2-c4-v5/config.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-e-v2-c4-v5/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cycy233-l3-e-v2-c4-v5/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-e-v2-c4-v5/tokenizer.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-e-v2-c4-v5/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cycy233-l3-e-v2-c4-v5_reward/config.json from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v2-c4-v5_reward/merges.txt from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v2-c4-v5_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v2-c4-v5_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v2-c4-v5_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v2-c4-v5_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v2-c4-v5_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.28s
cycy233-l3-e-v2-c4_v5 status is now torndown due to DeploymentManager action