jellywibble-vampirekingn_2830

submission_id: jellywibble-vampirekingn_2830_v1
developer_uid: chai_backend_admin
best_of: 2
celo_rating: 1204.74
display_name: jellywibble-vampirekingn_2830_v1
family_friendly_score: 0.0
formatter: {'memory_template': '### Instruction:\n{memory}\n', 'prompt_template': '### Input:\n{prompt}\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '### Response:\n{bot_name}:', 'truncate_by_message': True}
generation_params: {'temperature': 0.9, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['</s>', '###'], 'max_input_tokens': 1500, 'best_of': 2, 'max_output_tokens': 128, 'reward_max_token_input': 256}
ineligible_reason: max_output_tokens!=64
is_internal_developer: True
language_model: Jellywibble/VampireKingNoDedupEP2
max_input_tokens: 1500
max_output_tokens: 128
model_architecture: MistralForCausalLM
model_group: Jellywibble/VampireKingN
model_name: jellywibble-vampirekingn_2830_v1
model_num_parameters: 12772070400.0
model_repo: Jellywibble/VampireKingNoDedupEP2
model_size: 13B
num_battles: 10689
num_wins: 5065
ranking_group: single
reward_repo: ChaiML/gpt2_xl_pairwise_89m_step_347634
status: torndown
submission_type: basic
timestamp: 2024-08-08T01:08:58+00:00
us_pacific_date: 2024-08-07
win_ratio: 0.47385162316400037
Download Preference Data
Resubmit model
Running pipeline stage MKMLizer
Starting job with name jellywibble-vampirekingn-2830-v1-mkmlizer
Waiting for job on jellywibble-vampirekingn-2830-v1-mkmlizer to finish
jellywibble-vampirekingn-2830-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
jellywibble-vampirekingn-2830-v1-mkmlizer: ║     _____            __           __                                ║
jellywibble-vampirekingn-2830-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
jellywibble-vampirekingn-2830-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
jellywibble-vampirekingn-2830-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
jellywibble-vampirekingn-2830-v1-mkmlizer: ║       /___/                                                         ║
jellywibble-vampirekingn-2830-v1-mkmlizer: ║                                                                     ║
jellywibble-vampirekingn-2830-v1-mkmlizer: ║  Version: 0.9.9                                                     ║
jellywibble-vampirekingn-2830-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
jellywibble-vampirekingn-2830-v1-mkmlizer: ║  https://mk1.ai                                                     ║
jellywibble-vampirekingn-2830-v1-mkmlizer: ║                                                                     ║
jellywibble-vampirekingn-2830-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
jellywibble-vampirekingn-2830-v1-mkmlizer: ║  belonging to:                                                      ║
jellywibble-vampirekingn-2830-v1-mkmlizer: ║                                                                     ║
jellywibble-vampirekingn-2830-v1-mkmlizer: ║  Chai Research Corp.                                                ║
jellywibble-vampirekingn-2830-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
jellywibble-vampirekingn-2830-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
jellywibble-vampirekingn-2830-v1-mkmlizer: ║                                                                     ║
jellywibble-vampirekingn-2830-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
jellywibble-vampirekingn-2830-v1-mkmlizer: Downloaded to shared memory in 49.080s
jellywibble-vampirekingn-2830-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpdxn3vwyv, device:0
jellywibble-vampirekingn-2830-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
jellywibble-vampirekingn-2830-v1-mkmlizer: quantized model in 37.003s
jellywibble-vampirekingn-2830-v1-mkmlizer: Processed model Jellywibble/VampireKingNoDedupEP2 in 86.083s
jellywibble-vampirekingn-2830-v1-mkmlizer: creating bucket guanaco-mkml-models
jellywibble-vampirekingn-2830-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
jellywibble-vampirekingn-2830-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/jellywibble-vampirekingn-2830-v1
jellywibble-vampirekingn-2830-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/jellywibble-vampirekingn-2830-v1/config.json
jellywibble-vampirekingn-2830-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/jellywibble-vampirekingn-2830-v1/special_tokens_map.json
jellywibble-vampirekingn-2830-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/jellywibble-vampirekingn-2830-v1/tokenizer_config.json
jellywibble-vampirekingn-2830-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/jellywibble-vampirekingn-2830-v1/tokenizer.json
jellywibble-vampirekingn-2830-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/jellywibble-vampirekingn-2830-v1/flywheel_model.0.safetensors
jellywibble-vampirekingn-2830-v1-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
jellywibble-vampirekingn-2830-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:13, 27.41it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:07, 45.25it/s]
Loading 0:   5%|▍         | 18/363 [00:00<00:07, 45.64it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:09, 35.80it/s]
Loading 0:   8%|▊         | 30/363 [00:00<00:07, 44.39it/s]
Loading 0:  10%|▉         | 35/363 [00:00<00:07, 43.91it/s]
Loading 0:  11%|█         | 40/363 [00:00<00:07, 43.73it/s]
Loading 0:  13%|█▎        | 46/363 [00:01<00:07, 41.07it/s]
Loading 0:  14%|█▍        | 51/363 [00:01<00:07, 39.79it/s]
Loading 0:  15%|█▌        | 56/363 [00:01<00:07, 40.92it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:11, 27.32it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:10, 27.66it/s]
Loading 0:  20%|█▉        | 71/363 [00:01<00:08, 33.63it/s]
Loading 0:  21%|██        | 75/363 [00:02<00:08, 34.20it/s]
Loading 0:  22%|██▏       | 80/363 [00:02<00:07, 37.70it/s]
Loading 0:  23%|██▎       | 85/363 [00:02<00:07, 39.28it/s]
Loading 0:  25%|██▍       | 90/363 [00:02<00:06, 40.69it/s]
Loading 0:  26%|██▌       | 95/363 [00:02<00:06, 41.95it/s]
Loading 0:  28%|██▊       | 100/363 [00:02<00:07, 35.46it/s]
Loading 0:  29%|██▉       | 107/363 [00:02<00:05, 43.46it/s]
Loading 0:  31%|███       | 113/363 [00:02<00:06, 40.06it/s]
Loading 0:  33%|███▎      | 118/363 [00:03<00:06, 39.80it/s]
Loading 0:  34%|███▍      | 125/363 [00:03<00:05, 46.86it/s]
Loading 0:  36%|███▌      | 131/363 [00:03<00:04, 47.88it/s]
Loading 0:  38%|███▊      | 137/363 [00:03<00:05, 42.24it/s]
Loading 0:  39%|███▉      | 142/363 [00:03<00:07, 31.46it/s]
Loading 0:  40%|████      | 146/363 [00:03<00:06, 32.93it/s]
Loading 0:  41%|████▏     | 150/363 [00:03<00:06, 32.26it/s]
Loading 0:  43%|████▎     | 157/363 [00:04<00:05, 39.03it/s]
Loading 0:  45%|████▍     | 163/363 [00:04<00:05, 38.80it/s]
Loading 0:  46%|████▋     | 168/363 [00:04<00:04, 39.39it/s]
Loading 0:  48%|████▊     | 175/363 [00:04<00:04, 44.40it/s]
Loading 0:  50%|████▉     | 181/363 [00:04<00:04, 43.22it/s]
Loading 0:  51%|█████     | 186/363 [00:04<00:04, 42.41it/s]
Loading 0:  53%|█████▎    | 193/363 [00:04<00:03, 47.11it/s]
Loading 0:  55%|█████▍    | 199/363 [00:05<00:03, 43.91it/s]
Loading 0:  56%|█████▌    | 204/363 [00:05<00:03, 42.75it/s]
Loading 0:  58%|█████▊    | 211/363 [00:05<00:03, 47.80it/s]
Loading 0:  60%|█████▉    | 217/363 [00:05<00:03, 45.18it/s]
Loading 0:  61%|██████▏   | 223/363 [00:05<00:04, 33.76it/s]
Loading 0:  63%|██████▎   | 227/363 [00:05<00:03, 34.96it/s]
Loading 0:  64%|██████▎   | 231/363 [00:05<00:03, 33.27it/s]
Loading 0:  65%|██████▌   | 237/363 [00:06<00:03, 39.06it/s]
Loading 0:  67%|██████▋   | 242/363 [00:06<00:02, 40.41it/s]
Loading 0:  68%|██████▊   | 247/363 [00:06<00:02, 41.86it/s]
Loading 0:  70%|██████▉   | 253/363 [00:06<00:02, 40.72it/s]
Loading 0:  71%|███████   | 258/363 [00:06<00:02, 40.49it/s]
Loading 0:  73%|███████▎  | 265/363 [00:06<00:02, 45.67it/s]
Loading 0:  75%|███████▍  | 271/363 [00:06<00:02, 43.54it/s]
Loading 0:  76%|███████▌  | 276/363 [00:06<00:02, 42.23it/s]
Loading 0:  78%|███████▊  | 283/363 [00:07<00:01, 46.81it/s]
Loading 0:  79%|███████▉  | 288/363 [00:07<00:01, 47.47it/s]
Loading 0:  81%|████████  | 293/363 [00:07<00:01, 38.72it/s]
Loading 0:  82%|████████▏ | 299/363 [00:07<00:01, 43.23it/s]
Loading 0:  84%|████████▎ | 304/363 [00:14<00:23,  2.53it/s]
Loading 0:  85%|████████▍ | 308/363 [00:14<00:16,  3.26it/s]
Loading 0:  86%|████████▌ | 312/363 [00:14<00:12,  4.23it/s]
Loading 0:  88%|████████▊ | 320/363 [00:14<00:06,  7.00it/s]
Loading 0:  90%|████████▉ | 326/363 [00:14<00:03,  9.40it/s]
Loading 0:  91%|█████████ | 331/363 [00:14<00:02, 11.91it/s]
Loading 0:  93%|█████████▎| 338/363 [00:15<00:01, 16.64it/s]
Loading 0:  95%|█████████▍| 344/363 [00:15<00:00, 20.10it/s]
Loading 0:  96%|█████████▌| 349/363 [00:15<00:00, 23.30it/s]
Loading 0:  98%|█████████▊| 356/363 [00:15<00:00, 29.68it/s]
Loading 0: 100%|█████████▉| 362/363 [00:15<00:00, 31.76it/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.
jellywibble-vampirekingn-2830-v1-mkmlizer:   warnings.warn(
jellywibble-vampirekingn-2830-v1-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.
jellywibble-vampirekingn-2830-v1-mkmlizer:   warnings.warn(
jellywibble-vampirekingn-2830-v1-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.
jellywibble-vampirekingn-2830-v1-mkmlizer:   warnings.warn(
jellywibble-vampirekingn-2830-v1-mkmlizer: 
Downloading shards:   0%|          | 0/2 [00:00<?, ?it/s]
Downloading shards:  50%|█████     | 1/2 [00:05<00:05,  5.54s/it]
Downloading shards: 100%|██████████| 2/2 [00:08<00:00,  3.99s/it]
Downloading shards: 100%|██████████| 2/2 [00:08<00:00,  4.23s/it]
jellywibble-vampirekingn-2830-v1-mkmlizer: 
Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/s]
Loading checkpoint shards:  50%|█████     | 1/2 [00:00<00:00,  2.29it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00,  3.74it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00,  3.42it/s]
jellywibble-vampirekingn-2830-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
jellywibble-vampirekingn-2830-v1-mkmlizer: Saving duration: 1.451s
jellywibble-vampirekingn-2830-v1-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 13.486s
jellywibble-vampirekingn-2830-v1-mkmlizer: creating bucket guanaco-reward-models
jellywibble-vampirekingn-2830-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
jellywibble-vampirekingn-2830-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/jellywibble-vampirekingn-2830-v1_reward
jellywibble-vampirekingn-2830-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/jellywibble-vampirekingn-2830-v1_reward/special_tokens_map.json
jellywibble-vampirekingn-2830-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/jellywibble-vampirekingn-2830-v1_reward/config.json
jellywibble-vampirekingn-2830-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/jellywibble-vampirekingn-2830-v1_reward/tokenizer_config.json
jellywibble-vampirekingn-2830-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/jellywibble-vampirekingn-2830-v1_reward/merges.txt
jellywibble-vampirekingn-2830-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/jellywibble-vampirekingn-2830-v1_reward/vocab.json
jellywibble-vampirekingn-2830-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/jellywibble-vampirekingn-2830-v1_reward/tokenizer.json
Job jellywibble-vampirekingn-2830-v1-mkmlizer completed after 146.87s with status: succeeded
Stopping job with name jellywibble-vampirekingn-2830-v1-mkmlizer
Pipeline stage MKMLizer completed in 147.87s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service jellywibble-vampirekingn-2830-v1
Waiting for inference service jellywibble-vampirekingn-2830-v1 to be ready
Inference service jellywibble-vampirekingn-2830-v1 ready after 181.07264614105225s
Pipeline stage ISVCDeployer completed in 183.18s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.879236936569214s
Received healthy response to inference request in 1.7638144493103027s
Received healthy response to inference request in 1.9618635177612305s
Received healthy response to inference request in 2.679175615310669s
Received healthy response to inference request in 2.7166101932525635s
5 requests
0 failed requests
5th percentile: 1.8034242630004882
10th percentile: 1.8430340766906739
20th percentile: 1.922253704071045
30th percentile: 2.105325937271118
40th percentile: 2.3922507762908936
50th percentile: 2.679175615310669
60th percentile: 2.694149446487427
70th percentile: 2.7091232776641845
80th percentile: 2.7491355419158934
90th percentile: 2.8141862392425536
95th percentile: 2.846711587905884
99th percentile: 2.872731866836548
mean time: 2.400140142440796
Pipeline stage StressChecker completed in 12.76s
jellywibble-vampirekingn_2830_v1 status is now deployed due to DeploymentManager action
jellywibble-vampirekingn_2830_v1 status is now inactive due to auto deactivation removed underperforming models
jellywibble-vampirekingn_2830_v1 status is now torndown due to DeploymentManager action
admin requested tearing down of jellywibble-vampirekingn_2830_v1
Running pipeline stage ISVCDeleter
Pipeline stage %s skipped, reason=%s
Pipeline stage ISVCDeleter completed in 1.24s
Running pipeline stage MKMLModelDeleter
Pipeline stage %s skipped, reason=%s
Pipeline stage MKMLModelDeleter completed in 0.36s
jellywibble-vampirekingn_2830_v1 status is now torndown due to DeploymentManager action