developer_uid: zonemercy
submission_id: cognitivecomputations-do_9214_v2
model_name: cognitivecomputations-do_9214_v2
model_group: cognitivecomputations/do
status: torndown
timestamp: 2024-08-02T23:30:35+00:00
num_battles: 25499
num_wins: 7165
celo_rating: 1059.96
family_friendly_score: 0.0
submission_type: basic
model_repo: cognitivecomputations/dolphin-2.9.3-mistral-nemo-12b
model_architecture: MistralForCausalLM
reward_repo: ChaiML/gpt2_xl_pairwise_89m_step_347634
model_num_parameters: 12772090880.0
best_of: 1
max_input_tokens: 1024
max_output_tokens: 64
display_name: cognitivecomputations-do_9214_v2
is_internal_developer: True
language_model: cognitivecomputations/dolphin-2.9.3-mistral-nemo-12b
model_size: 13B
ranking_group: single
us_pacific_date: 2024-08-02
win_ratio: 0.28099141142789913
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': ['\n', '</s>', '###', 'Bot:', 'User:', 'You:', '<|im_end|>'], 'max_input_tokens': 1024, 'best_of': 1, 'max_output_tokens': 64, 'reward_max_token_input': 256}
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': '', 'prompt_template': '', 'response_template': '{bot_name}:', 'truncate_by_message': False, 'user_template': '{user_name}: {message}\n'}
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cognitivecomputations-do-9214-v2-mkmlizer
Waiting for job on cognitivecomputations-do-9214-v2-mkmlizer to finish
cognitivecomputations-do-9214-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cognitivecomputations-do-9214-v2-mkmlizer: ║     _____            __           __                                ║
cognitivecomputations-do-9214-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cognitivecomputations-do-9214-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cognitivecomputations-do-9214-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cognitivecomputations-do-9214-v2-mkmlizer: ║       /___/                                                         ║
cognitivecomputations-do-9214-v2-mkmlizer: ║                                                                     ║
cognitivecomputations-do-9214-v2-mkmlizer: ║  Version: 0.9.9                                                     ║
cognitivecomputations-do-9214-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cognitivecomputations-do-9214-v2-mkmlizer: ║  https://mk1.ai                                                     ║
cognitivecomputations-do-9214-v2-mkmlizer: ║                                                                     ║
cognitivecomputations-do-9214-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
cognitivecomputations-do-9214-v2-mkmlizer: ║  belonging to:                                                      ║
cognitivecomputations-do-9214-v2-mkmlizer: ║                                                                     ║
cognitivecomputations-do-9214-v2-mkmlizer: ║  Chai Research Corp.                                                ║
cognitivecomputations-do-9214-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cognitivecomputations-do-9214-v2-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
cognitivecomputations-do-9214-v2-mkmlizer: ║                                                                     ║
cognitivecomputations-do-9214-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cognitivecomputations-do-9214-v2-mkmlizer: Downloaded to shared memory in 35.189s
cognitivecomputations-do-9214-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp20diyi19, device:0
cognitivecomputations-do-9214-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cognitivecomputations-do-9214-v2-mkmlizer: quantized model in 37.214s
cognitivecomputations-do-9214-v2-mkmlizer: Processed model cognitivecomputations/dolphin-2.9.3-mistral-nemo-12b in 72.404s
cognitivecomputations-do-9214-v2-mkmlizer: creating bucket guanaco-mkml-models
cognitivecomputations-do-9214-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cognitivecomputations-do-9214-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cognitivecomputations-do-9214-v2
cognitivecomputations-do-9214-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cognitivecomputations-do-9214-v2/config.json
cognitivecomputations-do-9214-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cognitivecomputations-do-9214-v2/special_tokens_map.json
cognitivecomputations-do-9214-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cognitivecomputations-do-9214-v2/tokenizer.json
cognitivecomputations-do-9214-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cognitivecomputations-do-9214-v2/flywheel_model.0.safetensors
cognitivecomputations-do-9214-v2-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
cognitivecomputations-do-9214-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:12, 29.25it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:07, 46.05it/s]
Loading 0:   5%|▍         | 18/363 [00:00<00:07, 46.58it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:09, 34.40it/s]
Loading 0:   8%|▊         | 30/363 [00:00<00:07, 42.63it/s]
Loading 0:  10%|▉         | 35/363 [00:00<00:07, 41.84it/s]
Loading 0:  11%|█         | 40/363 [00:00<00:07, 41.23it/s]
Loading 0:  12%|█▏        | 45/363 [00:01<00:07, 42.96it/s]
Loading 0:  14%|█▍        | 50/363 [00:01<00:09, 34.44it/s]
Loading 0:  15%|█▌        | 56/363 [00:01<00:07, 39.38it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:11, 27.38it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:10, 27.29it/s]
Loading 0:  20%|█▉        | 71/363 [00:01<00:08, 33.11it/s]
Loading 0:  21%|██        | 75/363 [00:02<00:08, 33.40it/s]
Loading 0:  22%|██▏       | 80/363 [00:02<00:07, 36.96it/s]
Loading 0:  23%|██▎       | 85/363 [00:02<00:07, 37.69it/s]
Loading 0:  25%|██▍       | 90/363 [00:02<00:07, 38.37it/s]
Loading 0:  26%|██▌       | 95/363 [00:02<00:06, 39.59it/s]
Loading 0:  28%|██▊       | 100/363 [00:02<00:08, 32.70it/s]
Loading 0:  29%|██▉       | 106/363 [00:02<00:06, 37.87it/s]
Loading 0:  31%|███       | 112/363 [00:03<00:06, 41.74it/s]
Loading 0:  32%|███▏      | 117/363 [00:03<00:06, 39.88it/s]
Loading 0:  34%|███▎      | 122/363 [00:03<00:05, 41.10it/s]
Loading 0:  35%|███▍      | 127/363 [00:03<00:07, 33.13it/s]
Loading 0:  37%|███▋      | 134/363 [00:03<00:05, 40.08it/s]
Loading 0:  38%|███▊      | 139/363 [00:03<00:05, 40.09it/s]
Loading 0:  40%|███▉      | 144/363 [00:04<00:08, 24.37it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:08, 26.24it/s]
Loading 0:  43%|████▎     | 156/363 [00:04<00:06, 33.06it/s]
Loading 0:  44%|████▍     | 161/363 [00:04<00:05, 34.48it/s]
Loading 0:  46%|████▌     | 166/363 [00:04<00:05, 35.42it/s]
Loading 0:  47%|████▋     | 171/363 [00:04<00:05, 37.69it/s]
Loading 0:  48%|████▊     | 176/363 [00:04<00:05, 32.33it/s]
Loading 0:  50%|█████     | 183/363 [00:05<00:04, 39.04it/s]
Loading 0:  52%|█████▏    | 188/363 [00:05<00:04, 38.58it/s]
Loading 0:  53%|█████▎    | 193/363 [00:05<00:04, 39.94it/s]
Loading 0:  55%|█████▍    | 198/363 [00:05<00:03, 41.68it/s]
Loading 0:  56%|█████▌    | 203/363 [00:05<00:04, 33.99it/s]
Loading 0:  58%|█████▊    | 210/363 [00:05<00:03, 40.68it/s]
Loading 0:  59%|█████▉    | 215/363 [00:05<00:03, 40.64it/s]
Loading 0:  61%|██████    | 220/363 [00:06<00:03, 41.92it/s]
Loading 0:  62%|██████▏   | 225/363 [00:06<00:05, 25.23it/s]
Loading 0:  63%|██████▎   | 230/363 [00:06<00:04, 27.64it/s]
Loading 0:  65%|██████▌   | 237/363 [00:06<00:03, 34.48it/s]
Loading 0:  67%|██████▋   | 242/363 [00:06<00:03, 36.05it/s]
Loading 0:  68%|██████▊   | 247/363 [00:06<00:03, 36.52it/s]
Loading 0:  69%|██████▉   | 252/363 [00:07<00:02, 38.62it/s]
Loading 0:  71%|███████   | 257/363 [00:07<00:03, 32.67it/s]
Loading 0:  73%|███████▎  | 264/363 [00:07<00:02, 39.44it/s]
Loading 0:  74%|███████▍  | 269/363 [00:07<00:02, 39.74it/s]
Loading 0:  75%|███████▌  | 274/363 [00:07<00:02, 40.01it/s]
Loading 0:  77%|███████▋  | 279/363 [00:07<00:02, 41.26it/s]
Loading 0:  78%|███████▊  | 284/363 [00:07<00:02, 34.55it/s]
Loading 0:  80%|████████  | 291/363 [00:08<00:01, 41.62it/s]
Loading 0:  82%|████████▏ | 296/363 [00:08<00:01, 41.65it/s]
Loading 0:  83%|████████▎ | 301/363 [00:08<00:01, 42.75it/s]
Loading 0:  84%|████████▍ | 306/363 [00:15<00:23,  2.47it/s]
Loading 0:  85%|████████▌ | 310/363 [00:15<00:16,  3.16it/s]
Loading 0:  86%|████████▌ | 313/363 [00:15<00:12,  3.87it/s]
Loading 0:  88%|████████▊ | 319/363 [00:15<00:07,  5.94it/s]
Loading 0:  89%|████████▉ | 323/363 [00:15<00:05,  7.59it/s]
Loading 0:  90%|█████████ | 328/363 [00:15<00:03, 10.37it/s]
Loading 0:  91%|█████████▏| 332/363 [00:15<00:02, 12.79it/s]
Loading 0:  93%|█████████▎| 338/363 [00:15<00:01, 17.55it/s]
Loading 0:  94%|█████████▍| 343/363 [00:15<00:00, 21.81it/s]
Loading 0:  96%|█████████▌| 348/363 [00:16<00:00, 22.83it/s]
Loading 0:  98%|█████████▊| 355/363 [00:16<00:00, 30.11it/s]
Loading 0:  99%|█████████▉| 360/363 [00:16<00:00, 32.48it/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.
cognitivecomputations-do-9214-v2-mkmlizer:   warnings.warn(
cognitivecomputations-do-9214-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.
cognitivecomputations-do-9214-v2-mkmlizer:   warnings.warn(
cognitivecomputations-do-9214-v2-mkmlizer: 
Downloading shards:   0%|          | 0/2 [00:00<?, ?it/s]
Downloading shards:  50%|█████     | 1/2 [00:05<00:05,  5.52s/it]
Downloading shards: 100%|██████████| 2/2 [00:08<00:00,  4.02s/it]
Downloading shards: 100%|██████████| 2/2 [00:08<00:00,  4.25s/it]
cognitivecomputations-do-9214-v2-mkmlizer: 
Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/s]
Loading checkpoint shards:  50%|█████     | 1/2 [00:00<00:00,  2.20it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00,  3.65it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00,  3.32it/s]
cognitivecomputations-do-9214-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cognitivecomputations-do-9214-v2-mkmlizer: Saving duration: 1.373s
cognitivecomputations-do-9214-v2-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 13.542s
cognitivecomputations-do-9214-v2-mkmlizer: creating bucket guanaco-reward-models
cognitivecomputations-do-9214-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cognitivecomputations-do-9214-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cognitivecomputations-do-9214-v2_reward
cognitivecomputations-do-9214-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cognitivecomputations-do-9214-v2_reward/config.json
cognitivecomputations-do-9214-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cognitivecomputations-do-9214-v2_reward/special_tokens_map.json
cognitivecomputations-do-9214-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cognitivecomputations-do-9214-v2_reward/tokenizer_config.json
cognitivecomputations-do-9214-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cognitivecomputations-do-9214-v2_reward/merges.txt
cognitivecomputations-do-9214-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cognitivecomputations-do-9214-v2_reward/vocab.json
cognitivecomputations-do-9214-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cognitivecomputations-do-9214-v2_reward/tokenizer.json
cognitivecomputations-do-9214-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cognitivecomputations-do-9214-v2_reward/reward.tensors
Job cognitivecomputations-do-9214-v2-mkmlizer completed after 116.31s with status: succeeded
Stopping job with name cognitivecomputations-do-9214-v2-mkmlizer
Pipeline stage MKMLizer completed in 117.50s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service cognitivecomputations-do-9214-v2
Waiting for inference service cognitivecomputations-do-9214-v2 to be ready
Inference service cognitivecomputations-do-9214-v2 ready after 141.04443836212158s
Pipeline stage ISVCDeployer completed in 142.67s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.457453727722168s
Received healthy response to inference request in 0.3501114845275879s
Received healthy response to inference request in 0.3755481243133545s
Received healthy response to inference request in 0.3750734329223633s
Received healthy response to inference request in 0.3733198642730713s
5 requests
0 failed requests
5th percentile: 0.3547531604766846
10th percentile: 0.35939483642578124
20th percentile: 0.3686781883239746
30th percentile: 0.3736705780029297
40th percentile: 0.3743720054626465
50th percentile: 0.3750734329223633
60th percentile: 0.37526330947875974
70th percentile: 0.37545318603515626
80th percentile: 0.7919292449951176
90th percentile: 1.6246914863586428
95th percentile: 2.041072607040405
99th percentile: 2.3741775035858153
mean time: 0.7863013267517089
Pipeline stage StressChecker completed in 4.60s
cognitivecomputations-do_9214_v2 status is now deployed due to DeploymentManager action
cognitivecomputations-do_9214_v2 status is now inactive due to admin request
admin requested tearing down of cognitivecomputations-do_9214_v2
Running pipeline stage ISVCDeleter
Checking if service cognitivecomputations-do-9214-v2 is running
Tearing down inference service cognitivecomputations-do-9214-v2
Service cognitivecomputations-do-9214-v2 has been torndown
Pipeline stage ISVCDeleter completed in 5.14s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cognitivecomputations-do-9214-v2/added_tokens.json from bucket guanaco-mkml-models
Deleting key cognitivecomputations-do-9214-v2/config.json from bucket guanaco-mkml-models
Deleting key cognitivecomputations-do-9214-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cognitivecomputations-do-9214-v2/merges.txt from bucket guanaco-mkml-models
Deleting key cognitivecomputations-do-9214-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cognitivecomputations-do-9214-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key cognitivecomputations-do-9214-v2/tokenizer_config.json from bucket guanaco-mkml-models
Deleting key cognitivecomputations-do-9214-v2/vocab.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cognitivecomputations-do-9214-v2_reward/config.json from bucket guanaco-reward-models
Deleting key cognitivecomputations-do-9214-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key cognitivecomputations-do-9214-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cognitivecomputations-do-9214-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cognitivecomputations-do-9214-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cognitivecomputations-do-9214-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cognitivecomputations-do-9214-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 7.49s
cognitivecomputations-do_9214_v2 status is now torndown due to DeploymentManager action