cycy233-l3-ba-e-v1-c3

submission_id: cycy233-l3-ba-e-v1-c3_v2

developer_uid: shiroe40

best_of: 16

celo_rating: 1129.87

display_name: auto

family_friendly_score: 0.0

formatter: {'memory_template': '<|im_start|>system\n{memory}<|im_end|>\n', 'prompt_template': '<|im_start|>user\n{prompt}<|im_end|>\n', 'bot_template': '<|im_start|>assistant\n{bot_name}: {message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{user_name}: {message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n{bot_name}:', 'truncate_by_message': False}

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'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64, 'reward_max_token_input': 256}

is_internal_developer: False

language_model: cycy233/L3-ba-e-v1-c3

max_input_tokens: 512

max_output_tokens: 64

model_architecture: LlamaForCausalLM

model_group: cycy233/L3-ba-e-v1-c3

model_name: auto

model_num_parameters: 8030261248.0

model_repo: cycy233/L3-ba-e-v1-c3

model_size: 8B

num_battles: 10497

num_wins: 4297

ranking_group: single

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'}

reward_repo: Jellywibble/gpt2_xl_pairwise_89m_step_347634

status: torndown

submission_type: basic

timestamp: 2024-07-26T06:37:54+00:00

us_pacific_date: 2024-07-25

win_ratio: 0.40935505382490234

Download Preference Data

Resubmit model

Running pipeline stage MKMLizer
Starting job with name cycy233-l3-ba-e-v1-c3-v2-mkmlizer
Waiting for job on cycy233-l3-ba-e-v1-c3-v2-mkmlizer to finish
cycy233-l3-ba-e-v1-c3-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-ba-e-v1-c3-v2-mkmlizer: ║     _____            __           __                                ║
cycy233-l3-ba-e-v1-c3-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cycy233-l3-ba-e-v1-c3-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cycy233-l3-ba-e-v1-c3-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cycy233-l3-ba-e-v1-c3-v2-mkmlizer: ║       /___/                                                         ║
cycy233-l3-ba-e-v1-c3-v2-mkmlizer: ║                                                                     ║
cycy233-l3-ba-e-v1-c3-v2-mkmlizer: ║  Version: 0.9.7                                                     ║
cycy233-l3-ba-e-v1-c3-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cycy233-l3-ba-e-v1-c3-v2-mkmlizer: ║  https://mk1.ai                                                     ║
cycy233-l3-ba-e-v1-c3-v2-mkmlizer: ║                                                                     ║
cycy233-l3-ba-e-v1-c3-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
cycy233-l3-ba-e-v1-c3-v2-mkmlizer: ║  belonging to:                                                      ║
cycy233-l3-ba-e-v1-c3-v2-mkmlizer: ║                                                                     ║
cycy233-l3-ba-e-v1-c3-v2-mkmlizer: ║  Chai Research Corp.                                                ║
cycy233-l3-ba-e-v1-c3-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cycy233-l3-ba-e-v1-c3-v2-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
cycy233-l3-ba-e-v1-c3-v2-mkmlizer: ║                                                                     ║
cycy233-l3-ba-e-v1-c3-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-ba-e-v1-c3-v2-mkmlizer: Downloaded to shared memory in 26.757s
cycy233-l3-ba-e-v1-c3-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpp_og5cip, device:0
cycy233-l3-ba-e-v1-c3-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
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
cycy233-l3-ba-e-v1-c3-v2-mkmlizer: quantized model in 26.736s
cycy233-l3-ba-e-v1-c3-v2-mkmlizer: Processed model cycy233/L3-ba-e-v1-c3 in 53.493s
cycy233-l3-ba-e-v1-c3-v2-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-ba-e-v1-c3-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-ba-e-v1-c3-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-ba-e-v1-c3-v2
cycy233-l3-ba-e-v1-c3-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-ba-e-v1-c3-v2/config.json
cycy233-l3-ba-e-v1-c3-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-ba-e-v1-c3-v2/special_tokens_map.json
cycy233-l3-ba-e-v1-c3-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-ba-e-v1-c3-v2/tokenizer_config.json
cycy233-l3-ba-e-v1-c3-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-ba-e-v1-c3-v2/tokenizer.json
cycy233-l3-ba-e-v1-c3-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-ba-e-v1-c3-v2/flywheel_model.0.safetensors
cycy233-l3-ba-e-v1-c3-v2-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
cycy233-l3-ba-e-v1-c3-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:08, 34.04it/s]
Loading 0:   4%|▍         | 13/291 [00:00<00:05, 53.82it/s]
Loading 0:   7%|▋         | 19/291 [00:00<00:05, 46.57it/s]
Loading 0:   8%|▊         | 24/291 [00:00<00:05, 45.07it/s]
Loading 0:  11%|█         | 31/291 [00:00<00:05, 51.48it/s]
Loading 0:  13%|█▎        | 37/291 [00:00<00:05, 46.78it/s]
Loading 0:  14%|█▍        | 42/291 [00:00<00:05, 45.94it/s]
Loading 0:  17%|█▋        | 49/291 [00:01<00:04, 51.77it/s]
Loading 0:  19%|█▉        | 55/291 [00:01<00:05, 46.75it/s]
Loading 0:  21%|██        | 60/291 [00:01<00:05, 44.95it/s]
Loading 0:  23%|██▎       | 67/291 [00:01<00:04, 50.21it/s]
Loading 0:  25%|██▌       | 73/291 [00:01<00:04, 46.88it/s]
Loading 0:  27%|██▋       | 78/291 [00:01<00:04, 45.14it/s]
Loading 0:  29%|██▊       | 83/291 [00:01<00:06, 32.88it/s]
Loading 0:  30%|██▉       | 87/291 [00:02<00:06, 32.37it/s]
Loading 0:  32%|███▏      | 94/291 [00:02<00:04, 39.60it/s]
Loading 0:  34%|███▍      | 99/291 [00:02<00:04, 41.95it/s]
Loading 0:  36%|███▌      | 104/291 [00:02<00:05, 36.22it/s]
Loading 0:  38%|███▊      | 112/291 [00:02<00:04, 44.71it/s]
Loading 0:  40%|████      | 117/291 [00:02<00:03, 45.97it/s]
Loading 0:  42%|████▏     | 122/291 [00:02<00:04, 38.34it/s]
Loading 0:  45%|████▍     | 130/291 [00:02<00:03, 46.28it/s]
Loading 0:  47%|████▋     | 136/291 [00:03<00:03, 43.27it/s]
Loading 0:  48%|████▊     | 141/291 [00:03<00:03, 41.77it/s]
Loading 0:  51%|█████     | 148/291 [00:03<00:03, 46.74it/s]
Loading 0:  53%|█████▎    | 153/291 [00:03<00:02, 47.25it/s]
Loading 0:  54%|█████▍    | 158/291 [00:03<00:03, 38.34it/s]
Loading 0:  57%|█████▋    | 166/291 [00:03<00:02, 46.07it/s]
Loading 0:  59%|█████▉    | 171/291 [00:03<00:02, 46.66it/s]
Loading 0:  61%|██████    | 177/291 [00:04<00:02, 43.42it/s]
Loading 0:  63%|██████▎   | 182/291 [00:04<00:02, 41.86it/s]
Loading 0:  64%|██████▍   | 187/291 [00:04<00:03, 32.24it/s]
Loading 0:  66%|██████▌   | 191/291 [00:04<00:03, 33.14it/s]
Loading 0:  67%|██████▋   | 195/291 [00:04<00:03, 31.92it/s]
Loading 0:  69%|██████▉   | 201/291 [00:04<00:02, 37.53it/s]
Loading 0:  71%|███████   | 206/291 [00:04<00:02, 39.14it/s]
Loading 0:  73%|███████▎  | 211/291 [00:05<00:01, 41.10it/s]
Loading 0:  74%|███████▍  | 216/291 [00:05<00:01, 43.25it/s]
Loading 0:  76%|███████▌  | 221/291 [00:05<00:01, 36.68it/s]
Loading 0:  78%|███████▊  | 228/291 [00:05<00:01, 44.50it/s]
Loading 0:  80%|████████  | 233/291 [00:05<00:01, 44.52it/s]
Loading 0:  82%|████████▏ | 238/291 [00:05<00:01, 45.37it/s]
Loading 0:  84%|████████▎ | 243/291 [00:05<00:01, 46.43it/s]
Loading 0:  85%|████████▌ | 248/291 [00:05<00:01, 37.89it/s]
Loading 0:  88%|████████▊ | 255/291 [00:06<00:00, 45.43it/s]
Loading 0:  89%|████████▉ | 260/291 [00:06<00:00, 45.29it/s]
Loading 0:  91%|█████████ | 265/291 [00:06<00:00, 45.30it/s]
Loading 0:  93%|█████████▎| 270/291 [00:06<00:00, 46.06it/s]
Loading 0:  95%|█████████▍| 275/291 [00:06<00:00, 37.41it/s]
Loading 0:  97%|█████████▋| 281/291 [00:06<00:00, 42.41it/s]
Loading 0:  98%|█████████▊| 286/291 [00:06<00:00, 40.46it/s]
Loading 0: 100%|██████████| 291/291 [00:12<00:00,  3.09it/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-ba-e-v1-c3-v2-mkmlizer:   warnings.warn(
cycy233-l3-ba-e-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-l3-ba-e-v1-c3-v2-mkmlizer:   warnings.warn(
cycy233-l3-ba-e-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-l3-ba-e-v1-c3-v2-mkmlizer:   warnings.warn(
cycy233-l3-ba-e-v1-c3-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-l3-ba-e-v1-c3-v2-mkmlizer: Saving duration: 1.439s
cycy233-l3-ba-e-v1-c3-v2-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 11.631s
cycy233-l3-ba-e-v1-c3-v2-mkmlizer: creating bucket guanaco-reward-models
cycy233-l3-ba-e-v1-c3-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-l3-ba-e-v1-c3-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-l3-ba-e-v1-c3-v2_reward
cycy233-l3-ba-e-v1-c3-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-l3-ba-e-v1-c3-v2_reward/config.json
cycy233-l3-ba-e-v1-c3-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-l3-ba-e-v1-c3-v2_reward/special_tokens_map.json
cycy233-l3-ba-e-v1-c3-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-l3-ba-e-v1-c3-v2_reward/tokenizer_config.json
cycy233-l3-ba-e-v1-c3-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-l3-ba-e-v1-c3-v2_reward/merges.txt
cycy233-l3-ba-e-v1-c3-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-l3-ba-e-v1-c3-v2_reward/vocab.json
cycy233-l3-ba-e-v1-c3-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-l3-ba-e-v1-c3-v2_reward/tokenizer.json
cycy233-l3-ba-e-v1-c3-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-l3-ba-e-v1-c3-v2_reward/reward.tensors
Job cycy233-l3-ba-e-v1-c3-v2-mkmlizer completed after 157.79s with status: succeeded
Stopping job with name cycy233-l3-ba-e-v1-c3-v2-mkmlizer
Pipeline stage MKMLizer completed in 158.68s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.13s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-l3-ba-e-v1-c3-v2
Waiting for inference service cycy233-l3-ba-e-v1-c3-v2 to be ready
Inference service cycy233-l3-ba-e-v1-c3-v2 ready after 80.72910857200623s
Pipeline stage ISVCDeployer completed in 82.15s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3368353843688965s
Received healthy response to inference request in 2.4246773719787598s
Received healthy response to inference request in 1.3904509544372559s
Received healthy response to inference request in 1.3669309616088867s
Received healthy response to inference request in 1.3776865005493164s
5 requests
0 failed requests
5th percentile: 1.3690820693969727
10th percentile: 1.3712331771850585
20th percentile: 1.3755353927612304
30th percentile: 1.3802393913269042
40th percentile: 1.38534517288208
50th percentile: 1.3904509544372559
60th percentile: 1.769004726409912
70th percentile: 2.147558498382568
80th percentile: 2.354403781890869
90th percentile: 2.3895405769348144
95th percentile: 2.4071089744567873
99th percentile: 2.4211636924743654
mean time: 1.779316234588623
Pipeline stage StressChecker completed in 9.63s
cycy233-l3-ba-e-v1-c3_v2 status is now deployed due to DeploymentManager action
cycy233-l3-ba-e-v1-c3_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cycy233-l3-ba-e-v1-c3_v2
Running pipeline stage ISVCDeleter
Checking if service cycy233-l3-ba-e-v1-c3-v2 is running
Tearing down inference service cycy233-l3-ba-e-v1-c3-v2
Service cycy233-l3-ba-e-v1-c3-v2 has been torndown
Pipeline stage ISVCDeleter completed in 4.60s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cycy233-l3-ba-e-v1-c3-v2/config.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-ba-e-v1-c3-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cycy233-l3-ba-e-v1-c3-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-ba-e-v1-c3-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-ba-e-v1-c3-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cycy233-l3-ba-e-v1-c3-v2_reward/config.json from bucket guanaco-reward-models
Deleting key cycy233-l3-ba-e-v1-c3-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key cycy233-l3-ba-e-v1-c3-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cycy233-l3-ba-e-v1-c3-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cycy233-l3-ba-e-v1-c3-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cycy233-l3-ba-e-v1-c3-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cycy233-l3-ba-e-v1-c3-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.38s
cycy233-l3-ba-e-v1-c3_v2 status is now torndown due to DeploymentManager action