hastagaras-cupang-12b-te_2089

developer_uid: Hastagaras
submission_id: hastagaras-cupang-12b-te_2089_v1
model_name: hastagaras-cupang-12b-te_2089_v1
model_group: Hastagaras/Cupang-12B-Te
status: torndown
timestamp: 2024-07-31T10:25:49+00:00
num_battles: 10678
num_wins: 5245
celo_rating: 1198.8
family_friendly_score: 0.0
submission_type: basic
model_repo: Hastagaras/Cupang-12B-Test-3-sharded-norm
model_architecture: MistralForCausalLM
reward_repo: ChaiML/gpt2_xl_pairwise_89m_step_347634
model_num_parameters: 12772070400.0
best_of: 4
max_input_tokens: 1024
max_output_tokens: 64
display_name: hastagaras-cupang-12b-te_2089_v1
is_internal_developer: False
language_model: Hastagaras/Cupang-12B-Test-3-sharded-norm
model_size: 13B
ranking_group: single
us_pacific_date: 2024-07-31
win_ratio: 0.4911968533433227
generation_params: {'temperature': 1.05, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 100, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<'], 'max_input_tokens': 1024, 'best_of': 4, 'max_output_tokens': 64, 'reward_max_token_input': 256}
formatter: {'memory_template': "<s>[INST] Act as {bot_name}\n\n{bot_name}'s Persona: {memory}\n\n", 'prompt_template': '{prompt} [/INST]\n', 'bot_template': '{bot_name}: {message}</s>\n', 'user_template': '[INST] {user_name}: {message} [/INST]\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 hastagaras-cupang-12b-te-2089-v1-mkmlizer
Waiting for job on hastagaras-cupang-12b-te-2089-v1-mkmlizer to finish
hastagaras-cupang-12b-te-2089-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-cupang-12b-te-2089-v1-mkmlizer: ║     _____            __           __                                ║
hastagaras-cupang-12b-te-2089-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
hastagaras-cupang-12b-te-2089-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
hastagaras-cupang-12b-te-2089-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
hastagaras-cupang-12b-te-2089-v1-mkmlizer: ║       /___/                                                         ║
hastagaras-cupang-12b-te-2089-v1-mkmlizer: ║                                                                     ║
hastagaras-cupang-12b-te-2089-v1-mkmlizer: ║  Version: 0.9.7                                                     ║
hastagaras-cupang-12b-te-2089-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
hastagaras-cupang-12b-te-2089-v1-mkmlizer: ║  https://mk1.ai                                                     ║
hastagaras-cupang-12b-te-2089-v1-mkmlizer: ║                                                                     ║
hastagaras-cupang-12b-te-2089-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
hastagaras-cupang-12b-te-2089-v1-mkmlizer: ║  belonging to:                                                      ║
hastagaras-cupang-12b-te-2089-v1-mkmlizer: ║                                                                     ║
hastagaras-cupang-12b-te-2089-v1-mkmlizer: ║  Chai Research Corp.                                                ║
hastagaras-cupang-12b-te-2089-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
hastagaras-cupang-12b-te-2089-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
hastagaras-cupang-12b-te-2089-v1-mkmlizer: ║                                                                     ║
hastagaras-cupang-12b-te-2089-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-cupang-12b-te-2089-v1-mkmlizer: quantized model in 37.459s
hastagaras-cupang-12b-te-2089-v1-mkmlizer: Processed model Hastagaras/Cupang-12B-Test-3-sharded-norm in 82.789s
hastagaras-cupang-12b-te-2089-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-cupang-12b-te-2089-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-cupang-12b-te-2089-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-cupang-12b-te-2089-v1
hastagaras-cupang-12b-te-2089-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-cupang-12b-te-2089-v1/config.json
hastagaras-cupang-12b-te-2089-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-cupang-12b-te-2089-v1/special_tokens_map.json
hastagaras-cupang-12b-te-2089-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-cupang-12b-te-2089-v1/tokenizer_config.json
hastagaras-cupang-12b-te-2089-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-cupang-12b-te-2089-v1/tokenizer.json
hastagaras-cupang-12b-te-2089-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-cupang-12b-te-2089-v1/flywheel_model.0.safetensors
hastagaras-cupang-12b-te-2089-v1-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
hastagaras-cupang-12b-te-2089-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:13, 25.91it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:08, 43.57it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:08, 42.55it/s]
Loading 0:   6%|▌         | 22/363 [00:00<00:08, 42.21it/s]
Loading 0:   7%|▋         | 27/363 [00:00<00:07, 43.04it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:09, 35.97it/s]
Loading 0:  11%|█         | 39/363 [00:00<00:07, 44.03it/s]
Loading 0:  12%|█▏        | 44/363 [00:01<00:07, 41.89it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:07, 41.82it/s]
Loading 0:  15%|█▍        | 54/363 [00:01<00:07, 42.94it/s]
Loading 0:  16%|█▋        | 59/363 [00:01<00:06, 43.69it/s]
Loading 0:  18%|█▊        | 64/363 [00:01<00:12, 23.43it/s]
Loading 0:  20%|█▉        | 71/363 [00:01<00:09, 30.20it/s]
Loading 0:  21%|██        | 76/363 [00:02<00:08, 32.41it/s]
Loading 0:  22%|██▏       | 81/363 [00:02<00:08, 34.53it/s]
Loading 0:  24%|██▎       | 86/363 [00:02<00:07, 36.60it/s]
Loading 0:  25%|██▌       | 91/363 [00:02<00:08, 31.57it/s]
Loading 0:  27%|██▋       | 98/363 [00:02<00:07, 37.60it/s]
Loading 0:  28%|██▊       | 103/363 [00:02<00:07, 37.10it/s]
Loading 0:  30%|██▉       | 108/363 [00:02<00:06, 39.01it/s]
Loading 0:  31%|███       | 113/363 [00:03<00:07, 33.23it/s]
Loading 0:  33%|███▎      | 118/363 [00:03<00:07, 33.31it/s]
Loading 0:  34%|███▍      | 125/363 [00:03<00:05, 40.14it/s]
Loading 0:  36%|███▌      | 130/363 [00:03<00:05, 39.82it/s]
Loading 0:  37%|███▋      | 135/363 [00:03<00:05, 38.32it/s]
Loading 0:  38%|███▊      | 139/363 [00:03<00:05, 38.34it/s]
Loading 0:  39%|███▉      | 143/363 [00:04<00:08, 25.60it/s]
Loading 0:  40%|████      | 147/363 [00:04<00:07, 27.29it/s]
Loading 0:  42%|████▏     | 151/363 [00:04<00:07, 28.32it/s]
Loading 0:  43%|████▎     | 156/363 [00:04<00:06, 31.86it/s]
Loading 0:  44%|████▍     | 160/363 [00:04<00:06, 32.33it/s]
Loading 0:  45%|████▌     | 165/363 [00:04<00:05, 35.75it/s]
Loading 0:  47%|████▋     | 169/363 [00:04<00:05, 34.38it/s]
Loading 0:  48%|████▊     | 174/363 [00:04<00:05, 37.56it/s]
Loading 0:  49%|████▉     | 178/363 [00:05<00:05, 35.92it/s]
Loading 0:  50%|█████     | 183/363 [00:05<00:04, 37.58it/s]
Loading 0:  52%|█████▏    | 187/363 [00:05<00:04, 36.08it/s]
Loading 0:  53%|█████▎    | 192/363 [00:05<00:04, 38.54it/s]
Loading 0:  54%|█████▍    | 196/363 [00:05<00:04, 35.95it/s]
Loading 0:  55%|█████▌    | 201/363 [00:05<00:04, 38.49it/s]
Loading 0:  56%|█████▋    | 205/363 [00:05<00:04, 36.40it/s]
Loading 0:  58%|█████▊    | 210/363 [00:05<00:03, 38.52it/s]
Loading 0:  59%|█████▉    | 214/363 [00:06<00:04, 35.38it/s]
Loading 0:  60%|██████    | 218/363 [00:06<00:04, 34.99it/s]
Loading 0:  61%|██████▏   | 223/363 [00:06<00:05, 26.30it/s]
Loading 0:  63%|██████▎   | 227/363 [00:06<00:04, 27.58it/s]
Loading 0:  64%|██████▎   | 231/363 [00:06<00:04, 27.55it/s]
Loading 0:  65%|██████▌   | 237/363 [00:06<00:03, 34.12it/s]
Loading 0:  66%|██████▋   | 241/363 [00:06<00:03, 34.14it/s]
Loading 0:  68%|██████▊   | 246/363 [00:07<00:03, 37.32it/s]
Loading 0:  69%|██████▉   | 250/363 [00:07<00:03, 36.50it/s]
Loading 0:  70%|███████   | 255/363 [00:07<00:02, 39.43it/s]
Loading 0:  72%|███████▏  | 260/363 [00:07<00:02, 39.80it/s]
Loading 0:  73%|███████▎  | 265/363 [00:07<00:02, 40.89it/s]
Loading 0:  74%|███████▍  | 270/363 [00:07<00:02, 42.91it/s]
Loading 0:  76%|███████▌  | 275/363 [00:07<00:02, 35.84it/s]
Loading 0:  78%|███████▊  | 282/363 [00:07<00:01, 43.80it/s]
Loading 0:  79%|███████▉  | 287/363 [00:07<00:01, 42.82it/s]
Loading 0:  80%|████████  | 292/363 [00:08<00:01, 42.56it/s]
Loading 0:  82%|████████▏ | 297/363 [00:08<00:01, 43.58it/s]
Loading 0:  83%|████████▎ | 302/363 [00:08<00:01, 44.69it/s]
Loading 0:  85%|████████▍ | 307/363 [00:15<00:23,  2.35it/s]
Loading 0:  86%|████████▌ | 312/363 [00:15<00:15,  3.21it/s]
Loading 0:  87%|████████▋ | 317/363 [00:15<00:10,  4.40it/s]
Loading 0:  88%|████████▊ | 321/363 [00:15<00:07,  5.62it/s]
Loading 0:  91%|█████████ | 329/363 [00:15<00:03,  9.14it/s]
Loading 0:  92%|█████████▏| 335/363 [00:16<00:02, 11.97it/s]
Loading 0:  94%|█████████▎| 340/363 [00:16<00:01, 14.72it/s]
Loading 0:  95%|█████████▌| 346/363 [00:16<00:00, 19.32it/s]
Loading 0:  97%|█████████▋| 351/363 [00:16<00:00, 22.55it/s]
Loading 0:  98%|█████████▊| 356/363 [00:16<00:00, 26.21it/s]
Loading 0:  99%|█████████▉| 361/363 [00:16<00:00, 30.04it/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.
hastagaras-cupang-12b-te-2089-v1-mkmlizer:   warnings.warn(
hastagaras-cupang-12b-te-2089-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.
hastagaras-cupang-12b-te-2089-v1-mkmlizer:   warnings.warn(
hastagaras-cupang-12b-te-2089-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.
hastagaras-cupang-12b-te-2089-v1-mkmlizer:   warnings.warn(
hastagaras-cupang-12b-te-2089-v1-mkmlizer: 
Downloading shards:   0%|          | 0/2 [00:00<?, ?it/s]
Downloading shards:  50%|█████     | 1/2 [00:05<00:05,  5.84s/it]
Downloading shards: 100%|██████████| 2/2 [00:08<00:00,  4.11s/it]
Downloading shards: 100%|██████████| 2/2 [00:08<00:00,  4.37s/it]
hastagaras-cupang-12b-te-2089-v1-mkmlizer: 
Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/s]
Loading checkpoint shards:  50%|█████     | 1/2 [00:00<00:00,  2.34it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00,  3.84it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00,  3.50it/s]
hastagaras-cupang-12b-te-2089-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-cupang-12b-te-2089-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-cupang-12b-te-2089-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-cupang-12b-te-2089-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-cupang-12b-te-2089-v1_reward
hastagaras-cupang-12b-te-2089-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-cupang-12b-te-2089-v1_reward/config.json
hastagaras-cupang-12b-te-2089-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-cupang-12b-te-2089-v1_reward/special_tokens_map.json
hastagaras-cupang-12b-te-2089-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-cupang-12b-te-2089-v1_reward/tokenizer_config.json
hastagaras-cupang-12b-te-2089-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-cupang-12b-te-2089-v1_reward/merges.txt
hastagaras-cupang-12b-te-2089-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-cupang-12b-te-2089-v1_reward/vocab.json
hastagaras-cupang-12b-te-2089-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-cupang-12b-te-2089-v1_reward/tokenizer.json
hastagaras-cupang-12b-te-2089-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-cupang-12b-te-2089-v1_reward/reward.tensors
Job hastagaras-cupang-12b-te-2089-v1-mkmlizer completed after 126.02s with status: succeeded
Stopping job with name hastagaras-cupang-12b-te-2089-v1-mkmlizer
Pipeline stage MKMLizer completed in 127.28s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-cupang-12b-te-2089-v1
Waiting for inference service hastagaras-cupang-12b-te-2089-v1 to be ready
Inference service hastagaras-cupang-12b-te-2089-v1 ready after 121.46338963508606s
Pipeline stage ISVCDeployer completed in 123.35s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.4248664379119873s
Received healthy response to inference request in 1.274953842163086s
Received healthy response to inference request in 1.6203653812408447s
Received healthy response to inference request in 1.5971624851226807s
Received healthy response to inference request in 1.122382640838623s
5 requests
0 failed requests
5th percentile: 1.1528968811035156
10th percentile: 1.1834111213684082
20th percentile: 1.2444396018981934
30th percentile: 1.339395570755005
40th percentile: 1.4682790279388427
50th percentile: 1.5971624851226807
60th percentile: 1.6064436435699463
70th percentile: 1.615724802017212
80th percentile: 1.7812655925750733
90th percentile: 2.10306601524353
95th percentile: 2.2639662265777587
99th percentile: 2.3926863956451414
mean time: 1.6079461574554443
Pipeline stage StressChecker completed in 8.75s
hastagaras-cupang-12b-te_2089_v1 status is now deployed due to DeploymentManager action
hastagaras-cupang-12b-te_2089_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-cupang-12b-te_2089_v1
Running pipeline stage ISVCDeleter
Checking if service hastagaras-cupang-12b-te-2089-v1 is running
Tearing down inference service hastagaras-cupang-12b-te-2089-v1
Service hastagaras-cupang-12b-te-2089-v1 has been torndown
Pipeline stage ISVCDeleter completed in 4.63s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-cupang-12b-te-2089-v1/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-cupang-12b-te-2089-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-cupang-12b-te-2089-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-cupang-12b-te-2089-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-cupang-12b-te-2089-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-cupang-12b-te-2089-v1_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-cupang-12b-te-2089-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-cupang-12b-te-2089-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-cupang-12b-te-2089-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-cupang-12b-te-2089-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-cupang-12b-te-2089-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-cupang-12b-te-2089-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.53s
hastagaras-cupang-12b-te_2089_v1 status is now torndown due to DeploymentManager action