cognitivecomputations-do_9214

developer_uid: Azazelle
submission_id: cognitivecomputations-do_9214_v1
model_name: dolphin-2_9_3-mistral-nemo-12b
model_group: cognitivecomputations/do
status: torndown
timestamp: 2024-07-28T18:51:09+00:00
num_battles: 13036
num_wins: 4457
celo_rating: 1082.65
family_friendly_score: 0.0
submission_type: basic
model_repo: cognitivecomputations/dolphin-2.9.3-mistral-nemo-12b
model_architecture: MistralForCausalLM
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
model_num_parameters: 12772090880.0
best_of: 4
max_input_tokens: 512
max_output_tokens: 64
display_name: dolphin-2_9_3-mistral-nemo-12b
is_internal_developer: False
language_model: cognitivecomputations/dolphin-2.9.3-mistral-nemo-12b
model_size: 13B
ranking_group: single
us_pacific_date: 2024-07-28
win_ratio: 0.3418993556305615
generation_params: {'temperature': 0.7, 'top_p': 1.0, 'min_p': 0.07, 'top_k': 1024, 'presence_penalty': 0.03, 'frequency_penalty': 0.01, 'stopping_words': ['\n', '<|im_end|>'], 'max_input_tokens': 512, 'best_of': 4, 'max_output_tokens': 64, 'reward_max_token_input': 1024}
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}
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 cognitivecomputations-do-9214-v1-mkmlizer
Waiting for job on cognitivecomputations-do-9214-v1-mkmlizer to finish
Failed to get response for submission sao10k-hydrochoerus-12b-v1-s1_v3: ('http://sao10k-hydrochoerus-12b-v1-s1-v3-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
cognitivecomputations-do-9214-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cognitivecomputations-do-9214-v1-mkmlizer: ║     _____            __           __                                ║
cognitivecomputations-do-9214-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cognitivecomputations-do-9214-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cognitivecomputations-do-9214-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cognitivecomputations-do-9214-v1-mkmlizer: ║       /___/                                                         ║
cognitivecomputations-do-9214-v1-mkmlizer: ║                                                                     ║
cognitivecomputations-do-9214-v1-mkmlizer: ║  Version: 0.9.7                                                     ║
cognitivecomputations-do-9214-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cognitivecomputations-do-9214-v1-mkmlizer: ║  https://mk1.ai                                                     ║
cognitivecomputations-do-9214-v1-mkmlizer: ║                                                                     ║
cognitivecomputations-do-9214-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
cognitivecomputations-do-9214-v1-mkmlizer: ║  belonging to:                                                      ║
cognitivecomputations-do-9214-v1-mkmlizer: ║                                                                     ║
cognitivecomputations-do-9214-v1-mkmlizer: ║  Chai Research Corp.                                                ║
cognitivecomputations-do-9214-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cognitivecomputations-do-9214-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
cognitivecomputations-do-9214-v1-mkmlizer: ║                                                                     ║
cognitivecomputations-do-9214-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission sao10k-hydrochoerus-12b-v1-s1_v3: ('http://sao10k-hydrochoerus-12b-v1-s1-v3-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'activator request timeout')
Connection pool is full, discarding connection: %s. Connection pool size: %s
cognitivecomputations-do-9214-v1-mkmlizer: Downloaded to shared memory in 34.196s
cognitivecomputations-do-9214-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpesoq0cbu, device:0
cognitivecomputations-do-9214-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission sao10k-hydrochoerus-12b-v1-s1_v3: ('http://sao10k-hydrochoerus-12b-v1-s1-v3-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Failed to get response for submission sao10k-hydrochoerus-12b-v1-s1_v3: ('http://sao10k-hydrochoerus-12b-v1-s1-v3-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Failed to get response for submission sao10k-hydrochoerus-12b-v1-s1_v3: ('http://sao10k-hydrochoerus-12b-v1-s1-v3-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
cognitivecomputations-do-9214-v1-mkmlizer: quantized model in 37.518s
cognitivecomputations-do-9214-v1-mkmlizer: Processed model cognitivecomputations/dolphin-2.9.3-mistral-nemo-12b in 71.714s
cognitivecomputations-do-9214-v1-mkmlizer: creating bucket guanaco-mkml-models
cognitivecomputations-do-9214-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cognitivecomputations-do-9214-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cognitivecomputations-do-9214-v1
cognitivecomputations-do-9214-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cognitivecomputations-do-9214-v1/config.json
cognitivecomputations-do-9214-v1-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/cognitivecomputations-do-9214-v1/added_tokens.json
cognitivecomputations-do-9214-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cognitivecomputations-do-9214-v1/special_tokens_map.json
cognitivecomputations-do-9214-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cognitivecomputations-do-9214-v1/tokenizer_config.json
cognitivecomputations-do-9214-v1-mkmlizer: cp /dev/shm/model_cache/vocab.json s3://guanaco-mkml-models/cognitivecomputations-do-9214-v1/vocab.json
cognitivecomputations-do-9214-v1-mkmlizer: cp /dev/shm/model_cache/merges.txt s3://guanaco-mkml-models/cognitivecomputations-do-9214-v1/merges.txt
cognitivecomputations-do-9214-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cognitivecomputations-do-9214-v1/tokenizer.json
cognitivecomputations-do-9214-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cognitivecomputations-do-9214-v1/flywheel_model.0.safetensors
cognitivecomputations-do-9214-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cognitivecomputations-do-9214-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:11, 30.81it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:07, 48.59it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:08, 42.40it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:08, 40.93it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:07, 46.30it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:07, 42.92it/s]
Loading 0:  12%|█▏        | 42/363 [00:00<00:07, 41.28it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:06, 46.09it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:07, 43.27it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:09, 31.42it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:09, 31.26it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:07, 37.57it/s]
Loading 0:  21%|██▏       | 78/363 [00:02<00:07, 36.82it/s]
Loading 0:  23%|██▎       | 82/363 [00:02<00:07, 35.41it/s]
Loading 0:  25%|██▍       | 89/363 [00:02<00:06, 42.45it/s]
Loading 0:  26%|██▌       | 94/363 [00:02<00:06, 42.42it/s]
Loading 0:  27%|██▋       | 99/363 [00:02<00:06, 42.72it/s]
Loading 0:  29%|██▊       | 104/363 [00:02<00:05, 44.24it/s]
Loading 0:  30%|███       | 109/363 [00:02<00:05, 44.96it/s]
Loading 0:  31%|███▏      | 114/363 [00:02<00:06, 38.42it/s]
Loading 0:  33%|███▎      | 119/363 [00:02<00:06, 37.56it/s]
Loading 0:  34%|███▍      | 125/363 [00:03<00:05, 41.14it/s]
Loading 0:  36%|███▌      | 130/363 [00:03<00:05, 41.31it/s]
Loading 0:  37%|███▋      | 135/363 [00:03<00:05, 41.74it/s]
Loading 0:  39%|███▊      | 140/363 [00:03<00:05, 43.41it/s]
Loading 0:  40%|███▉      | 145/363 [00:03<00:08, 25.69it/s]
Loading 0:  41%|████      | 149/363 [00:03<00:08, 26.27it/s]
Loading 0:  43%|████▎     | 156/363 [00:04<00:06, 33.75it/s]
Loading 0:  44%|████▍     | 161/363 [00:04<00:05, 35.47it/s]
Loading 0:  46%|████▌     | 166/363 [00:04<00:05, 37.30it/s]
Loading 0:  47%|████▋     | 172/363 [00:04<00:05, 37.77it/s]
Loading 0:  49%|████▉     | 177/363 [00:04<00:04, 37.91it/s]
Loading 0:  50%|█████     | 183/363 [00:04<00:04, 42.60it/s]
Loading 0:  52%|█████▏    | 188/363 [00:04<00:04, 42.12it/s]
Loading 0:  53%|█████▎    | 193/363 [00:04<00:04, 42.03it/s]
Loading 0:  55%|█████▍    | 198/363 [00:05<00:03, 43.85it/s]
Loading 0:  56%|█████▌    | 203/363 [00:05<00:04, 36.63it/s]
Loading 0:  58%|█████▊    | 210/363 [00:05<00:03, 43.98it/s]
Loading 0:  59%|█████▉    | 215/363 [00:05<00:03, 43.60it/s]
Loading 0:  61%|██████    | 220/363 [00:05<00:03, 44.53it/s]
Loading 0:  62%|██████▏   | 225/363 [00:05<00:05, 26.20it/s]
Loading 0:  63%|██████▎   | 230/363 [00:06<00:04, 28.40it/s]
Loading 0:  65%|██████▌   | 237/363 [00:06<00:03, 35.66it/s]
Loading 0:  67%|██████▋   | 242/363 [00:06<00:03, 37.36it/s]
Loading 0:  68%|██████▊   | 247/363 [00:06<00:03, 38.60it/s]
Loading 0:  70%|██████▉   | 253/363 [00:06<00:02, 37.96it/s]
Loading 0:  71%|███████   | 258/363 [00:06<00:02, 38.00it/s]
Loading 0:  73%|███████▎  | 264/363 [00:06<00:02, 42.29it/s]
Loading 0:  74%|███████▍  | 269/363 [00:06<00:02, 41.49it/s]
Loading 0:  75%|███████▌  | 274/363 [00:07<00:02, 41.57it/s]
Loading 0:  77%|███████▋  | 279/363 [00:07<00:01, 42.79it/s]
Loading 0:  78%|███████▊  | 284/363 [00:07<00:02, 35.30it/s]
Loading 0:  80%|████████  | 291/363 [00:07<00:01, 42.52it/s]
Loading 0:  82%|████████▏ | 296/363 [00:07<00:01, 42.67it/s]
Loading 0:  83%|████████▎ | 302/363 [00:07<00:01, 46.30it/s]
Loading 0:  85%|████████▍ | 307/363 [00:14<00:22,  2.48it/s]
Loading 0:  86%|████████▌ | 312/363 [00:14<00:15,  3.34it/s]
Loading 0:  88%|████████▊ | 320/363 [00:15<00:08,  5.32it/s]
Loading 0:  90%|████████▉ | 326/363 [00:15<00:05,  7.14it/s]
Loading 0:  91%|█████████ | 331/363 [00:15<00:03,  9.08it/s]
Loading 0:  93%|█████████▎| 337/363 [00:15<00:02, 12.30it/s]
Loading 0:  94%|█████████▍| 342/363 [00:15<00:01, 15.24it/s]
Loading 0:  96%|█████████▌| 347/363 [00:15<00:00, 18.71it/s]
Loading 0:  97%|█████████▋| 353/363 [00:15<00:00, 22.35it/s]
Loading 0:  99%|█████████▊| 358/363 [00:15<00:00, 25.06it/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-v1-mkmlizer:   warnings.warn(
cognitivecomputations-do-9214-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.
cognitivecomputations-do-9214-v1-mkmlizer:   warnings.warn(
cognitivecomputations-do-9214-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.
cognitivecomputations-do-9214-v1-mkmlizer:   warnings.warn(
cognitivecomputations-do-9214-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cognitivecomputations-do-9214-v1-mkmlizer: Saving duration: 0.329s
cognitivecomputations-do-9214-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 6.481s
cognitivecomputations-do-9214-v1-mkmlizer: creating bucket guanaco-reward-models
cognitivecomputations-do-9214-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cognitivecomputations-do-9214-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cognitivecomputations-do-9214-v1_reward
cognitivecomputations-do-9214-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cognitivecomputations-do-9214-v1_reward/config.json
cognitivecomputations-do-9214-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cognitivecomputations-do-9214-v1_reward/special_tokens_map.json
cognitivecomputations-do-9214-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cognitivecomputations-do-9214-v1_reward/tokenizer_config.json
cognitivecomputations-do-9214-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cognitivecomputations-do-9214-v1_reward/merges.txt
cognitivecomputations-do-9214-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cognitivecomputations-do-9214-v1_reward/vocab.json
cognitivecomputations-do-9214-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cognitivecomputations-do-9214-v1_reward/tokenizer.json
cognitivecomputations-do-9214-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cognitivecomputations-do-9214-v1_reward/reward.tensors
Job cognitivecomputations-do-9214-v1-mkmlizer completed after 107.19s with status: succeeded
Stopping job with name cognitivecomputations-do-9214-v1-mkmlizer
Pipeline stage MKMLizer completed in 108.15s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service cognitivecomputations-do-9214-v1
Waiting for inference service cognitivecomputations-do-9214-v1 to be ready
Failed to get response for submission sao10k-hydrochoerus-12b-v1-s1_v3: ('http://sao10k-hydrochoerus-12b-v1-s1-v3-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Inference service cognitivecomputations-do-9214-v1 ready after 111.04304695129395s
Pipeline stage ISVCDeployer completed in 112.66s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.3090033531188965s
Received healthy response to inference request in 1.526350498199463s
Failed to get response for submission sao10k-hydrochoerus-12b-v1-s1_v3: ('http://sao10k-hydrochoerus-12b-v1-s1-v3-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Received healthy response to inference request in 1.510263442993164s
Received healthy response to inference request in 0.9264535903930664s
Received healthy response to inference request in 1.532411813735962s
5 requests
0 failed requests
5th percentile: 1.0029635429382324
10th percentile: 1.0794734954833984
20th percentile: 1.2324934005737305
30th percentile: 1.34925537109375
40th percentile: 1.429759407043457
50th percentile: 1.510263442993164
60th percentile: 1.5166982650756835
70th percentile: 1.5231330871582032
80th percentile: 1.5275627613067626
90th percentile: 1.5299872875213623
95th percentile: 1.5311995506286622
99th percentile: 1.532169361114502
mean time: 1.3608965396881103
Pipeline stage StressChecker completed in 7.80s
cognitivecomputations-do_9214_v1 status is now deployed due to DeploymentManager action
cognitivecomputations-do_9214_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cognitivecomputations-do_9214_v1
Running pipeline stage ISVCDeleter
Checking if service cognitivecomputations-do-9214-v1 is running
Tearing down inference service cognitivecomputations-do-9214-v1
Service cognitivecomputations-do-9214-v1 has been torndown
Pipeline stage ISVCDeleter completed in 5.25s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cognitivecomputations-do-9214-v1/added_tokens.json from bucket guanaco-mkml-models
Deleting key cognitivecomputations-do-9214-v1/config.json from bucket guanaco-mkml-models
Deleting key cognitivecomputations-do-9214-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cognitivecomputations-do-9214-v1/merges.txt from bucket guanaco-mkml-models
Deleting key cognitivecomputations-do-9214-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cognitivecomputations-do-9214-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key cognitivecomputations-do-9214-v1/tokenizer_config.json from bucket guanaco-mkml-models
Deleting key cognitivecomputations-do-9214-v1/vocab.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cognitivecomputations-do-9214-v1_reward/config.json from bucket guanaco-reward-models
Deleting key cognitivecomputations-do-9214-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key cognitivecomputations-do-9214-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cognitivecomputations-do-9214-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cognitivecomputations-do-9214-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cognitivecomputations-do-9214-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cognitivecomputations-do-9214-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.81s
cognitivecomputations-do_9214_v1 status is now torndown due to DeploymentManager action