cycy233-l3-e-v2-c1

developer_uid: shiroe40

submission_id: cycy233-l3-e-v2-c1_v22

model_name: auto

model_group: cycy233/L3-e-v2-c1

status: torndown

timestamp: 2024-07-26T08:52:39+00:00

num_battles: 11609

num_wins: 6411

celo_rating: 1240.44

family_friendly_score: 0.0

submission_type: basic

model_repo: cycy233/L3-e-v2-c1

model_architecture: LlamaForCausalLM

reward_repo: Jellywibble/gpt2_xl_pairwise_89m_step_347634

model_num_parameters: 8030261248.0

best_of: 4

max_input_tokens: 512

max_output_tokens: 64

display_name: auto

is_internal_developer: False

language_model: cycy233/L3-e-v2-c1

model_size: 8B

ranking_group: single

us_pacific_date: 2024-07-26

win_ratio: 0.552243948660522

generation_params: {'temperature': 1.0, 'top_p': 0.9, 'min_p': 0.05, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|end_header_id|>', '<|eot_id|>'], 'max_input_tokens': 512, 'best_of': 4, '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-l3-e-v2-c1-v22-mkmlizer
Waiting for job on cycy233-l3-e-v2-c1-v22-mkmlizer to finish
cycy233-l3-e-v2-c1-v22-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-e-v2-c1-v22-mkmlizer: ║     _____            __           __                                ║
cycy233-l3-e-v2-c1-v22-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cycy233-l3-e-v2-c1-v22-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cycy233-l3-e-v2-c1-v22-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cycy233-l3-e-v2-c1-v22-mkmlizer: ║       /___/                                                         ║
cycy233-l3-e-v2-c1-v22-mkmlizer: ║                                                                     ║
cycy233-l3-e-v2-c1-v22-mkmlizer: ║  Version: 0.9.7                                                     ║
cycy233-l3-e-v2-c1-v22-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cycy233-l3-e-v2-c1-v22-mkmlizer: ║  https://mk1.ai                                                     ║
cycy233-l3-e-v2-c1-v22-mkmlizer: ║                                                                     ║
cycy233-l3-e-v2-c1-v22-mkmlizer: ║  The license key for the current software has been verified as      ║
cycy233-l3-e-v2-c1-v22-mkmlizer: ║  belonging to:                                                      ║
cycy233-l3-e-v2-c1-v22-mkmlizer: ║                                                                     ║
cycy233-l3-e-v2-c1-v22-mkmlizer: ║  Chai Research Corp.                                                ║
cycy233-l3-e-v2-c1-v22-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cycy233-l3-e-v2-c1-v22-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
cycy233-l3-e-v2-c1-v22-mkmlizer: ║                                                                     ║
cycy233-l3-e-v2-c1-v22-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-e-v2-c1-v22-mkmlizer: Downloaded to shared memory in 22.340s
cycy233-l3-e-v2-c1-v22-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpgxksuc0o, device:0
cycy233-l3-e-v2-c1-v22-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission jic062-share-qlora-out_v7: ('http://jic062-share-qlora-out-v7-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
Failed to get response for submission jic062-share-qlora-out_v7: ('http://jic062-share-qlora-out-v7-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
cycy233-l3-e-v2-c1-v22-mkmlizer: quantized model in 25.892s
cycy233-l3-e-v2-c1-v22-mkmlizer: Processed model cycy233/L3-e-v2-c1 in 48.233s
cycy233-l3-e-v2-c1-v22-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-e-v2-c1-v22-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-e-v2-c1-v22-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-e-v2-c1-v22
cycy233-l3-e-v2-c1-v22-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-e-v2-c1-v22/config.json
cycy233-l3-e-v2-c1-v22-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-e-v2-c1-v22/special_tokens_map.json
cycy233-l3-e-v2-c1-v22-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-e-v2-c1-v22/tokenizer_config.json
cycy233-l3-e-v2-c1-v22-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-e-v2-c1-v22/tokenizer.json
cycy233-l3-e-v2-c1-v22-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-e-v2-c1-v22/flywheel_model.0.safetensors
cycy233-l3-e-v2-c1-v22-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
cycy233-l3-e-v2-c1-v22-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:07, 37.49it/s]
Loading 0:   5%|▍         | 14/291 [00:00<00:05, 48.71it/s]
Loading 0:   8%|▊         | 22/291 [00:00<00:04, 58.92it/s]
Loading 0:  10%|▉         | 29/291 [00:00<00:04, 52.94it/s]
Loading 0:  12%|█▏        | 35/291 [00:00<00:04, 52.24it/s]
Loading 0:  14%|█▍        | 41/291 [00:00<00:05, 45.90it/s]
Loading 0:  17%|█▋        | 50/291 [00:01<00:04, 48.48it/s]
Loading 0:  20%|█▉        | 58/291 [00:01<00:04, 55.88it/s]
Loading 0:  22%|██▏       | 64/291 [00:01<00:04, 51.80it/s]
Loading 0:  24%|██▍       | 70/291 [00:01<00:04, 51.58it/s]
Loading 0:  26%|██▌       | 76/291 [00:01<00:04, 52.78it/s]
Loading 0:  28%|██▊       | 82/291 [00:01<00:04, 47.97it/s]
Loading 0:  30%|██▉       | 87/291 [00:01<00:06, 33.44it/s]
Loading 0:  32%|███▏      | 94/291 [00:02<00:04, 40.25it/s]
Loading 0:  34%|███▍      | 100/291 [00:02<00:04, 39.64it/s]
Loading 0:  36%|███▌      | 105/291 [00:02<00:04, 39.71it/s]
Loading 0:  38%|███▊      | 111/291 [00:02<00:04, 42.80it/s]
Loading 0:  40%|███▉      | 116/291 [00:02<00:04, 42.29it/s]
Loading 0:  42%|████▏     | 121/291 [00:02<00:03, 42.64it/s]
Loading 0:  43%|████▎     | 126/291 [00:02<00:03, 44.14it/s]
Loading 0:  45%|████▌     | 131/291 [00:02<00:04, 38.24it/s]
Loading 0:  48%|████▊     | 139/291 [00:03<00:03, 47.44it/s]
Loading 0:  50%|████▉     | 145/291 [00:03<00:03, 44.90it/s]
Loading 0:  52%|█████▏    | 150/291 [00:03<00:03, 43.53it/s]
Loading 0:  54%|█████▍    | 157/291 [00:03<00:02, 48.69it/s]
Loading 0:  56%|█████▌    | 163/291 [00:03<00:02, 46.79it/s]
Loading 0:  58%|█████▊    | 168/291 [00:03<00:02, 46.03it/s]
Loading 0:  59%|█████▉    | 173/291 [00:03<00:02, 46.90it/s]
Loading 0:  62%|██████▏   | 179/291 [00:03<00:02, 50.28it/s]
Loading 0:  64%|██████▎   | 185/291 [00:03<00:02, 51.07it/s]
Loading 0:  66%|██████▌   | 191/291 [00:04<00:03, 32.96it/s]
Loading 0:  67%|██████▋   | 196/291 [00:04<00:02, 34.59it/s]
Loading 0:  70%|██████▉   | 203/291 [00:04<00:02, 36.64it/s]
Loading 0:  73%|███████▎  | 211/291 [00:04<00:01, 44.94it/s]
Loading 0:  75%|███████▍  | 217/291 [00:04<00:01, 44.65it/s]
Loading 0:  76%|███████▋  | 222/291 [00:04<00:01, 44.99it/s]
Loading 0:  79%|███████▊  | 229/291 [00:05<00:01, 49.40it/s]
Loading 0:  81%|████████  | 235/291 [00:05<00:01, 46.77it/s]
Loading 0:  82%|████████▏ | 240/291 [00:05<00:01, 45.47it/s]
Loading 0:  85%|████████▍ | 247/291 [00:05<00:00, 49.69it/s]
Loading 0:  87%|████████▋ | 253/291 [00:05<00:00, 47.42it/s]
Loading 0:  89%|████████▊ | 258/291 [00:05<00:00, 47.04it/s]
Loading 0:  91%|█████████ | 265/291 [00:05<00:00, 52.32it/s]
Loading 0:  93%|█████████▎| 271/291 [00:05<00:00, 49.43it/s]
Loading 0:  95%|█████████▌| 277/291 [00:06<00:00, 49.37it/s]
Loading 0:  97%|█████████▋| 283/291 [00:06<00:00, 45.14it/s]
Loading 0:  99%|█████████▉| 288/291 [00:11<00:00,  3.39it/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-l3-e-v2-c1-v22-mkmlizer:   warnings.warn(
cycy233-l3-e-v2-c1-v22-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-l3-e-v2-c1-v22-mkmlizer:   warnings.warn(
cycy233-l3-e-v2-c1-v22-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-c1-v22-mkmlizer:   warnings.warn(
cycy233-l3-e-v2-c1-v22-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-l3-e-v2-c1-v22-mkmlizer: Saving duration: 1.401s
cycy233-l3-e-v2-c1-v22-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 10.968s
cycy233-l3-e-v2-c1-v22-mkmlizer: creating bucket guanaco-reward-models
cycy233-l3-e-v2-c1-v22-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-l3-e-v2-c1-v22-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-l3-e-v2-c1-v22_reward
cycy233-l3-e-v2-c1-v22-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-l3-e-v2-c1-v22_reward/config.json
cycy233-l3-e-v2-c1-v22-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-l3-e-v2-c1-v22_reward/special_tokens_map.json
cycy233-l3-e-v2-c1-v22-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-l3-e-v2-c1-v22_reward/tokenizer_config.json
cycy233-l3-e-v2-c1-v22-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-l3-e-v2-c1-v22_reward/merges.txt
cycy233-l3-e-v2-c1-v22-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-l3-e-v2-c1-v22_reward/vocab.json
cycy233-l3-e-v2-c1-v22-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-l3-e-v2-c1-v22_reward/tokenizer.json
cycy233-l3-e-v2-c1-v22-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-l3-e-v2-c1-v22_reward/reward.tensors
Job cycy233-l3-e-v2-c1-v22-mkmlizer completed after 95.75s with status: succeeded
Stopping job with name cycy233-l3-e-v2-c1-v22-mkmlizer
Pipeline stage MKMLizer completed in 96.51s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-l3-e-v2-c1-v22
Waiting for inference service cycy233-l3-e-v2-c1-v22 to be ready
Inference service cycy233-l3-e-v2-c1-v22 ready after 71.02748012542725s
Pipeline stage ISVCDeployer completed in 72.08s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0339009761810303s
Received healthy response to inference request in 1.1445515155792236s
Received healthy response to inference request in 1.1516218185424805s
Received healthy response to inference request in 1.0474305152893066s
Received healthy response to inference request in 1.1559948921203613s
5 requests
0 failed requests
5th percentile: 1.06685471534729
10th percentile: 1.0862789154052734
20th percentile: 1.1251273155212402
30th percentile: 1.145965576171875
40th percentile: 1.1487936973571777
50th percentile: 1.1516218185424805
60th percentile: 1.1533710479736328
70th percentile: 1.155120277404785
80th percentile: 1.3315761089324953
90th percentile: 1.6827385425567627
95th percentile: 1.8583197593688963
99th percentile: 1.9987847328186035
mean time: 1.3066999435424804
Pipeline stage StressChecker completed in 7.13s
cycy233-l3-e-v2-c1_v22 status is now deployed due to DeploymentManager action
cycy233-l3-e-v2-c1_v22 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cycy233-l3-e-v2-c1_v22
Running pipeline stage ISVCDeleter
Checking if service cycy233-l3-e-v2-c1-v22 is running
Tearing down inference service cycy233-l3-e-v2-c1-v22
Service cycy233-l3-e-v2-c1-v22 has been torndown
Pipeline stage ISVCDeleter completed in 4.43s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cycy233-l3-e-v2-c1-v22/config.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-e-v2-c1-v22/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cycy233-l3-e-v2-c1-v22/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-e-v2-c1-v22/tokenizer.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-e-v2-c1-v22/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cycy233-l3-e-v2-c1-v22_reward/config.json from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v2-c1-v22_reward/merges.txt from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v2-c1-v22_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v2-c1-v22_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v2-c1-v22_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v2-c1-v22_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v2-c1-v22_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.62s
cycy233-l3-e-v2-c1_v22 status is now torndown due to DeploymentManager action