submission_id: jic062-share-qlora-out_v10
developer_uid: chace9580
alignment_samples: 0
best_of: 16
celo_rating: 1190.79
display_name: jic062-share-qlora-out_v10
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}
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, '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': 1024}
is_internal_developer: False
language_model: jic062/share-qlora-out
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: jic062/share-qlora-out
model_name: jic062-share-qlora-out_v10
model_num_parameters: 8030261248.0
model_repo: jic062/share-qlora-out
model_size: 8B
num_battles: 9881
num_wins: 4820
propriety_score: 0.6982670744138634
propriety_total_count: 981.0
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: ChaiML/reward_gpt2_medium_preference_24m_e2
status: torndown
submission_type: basic
timestamp: 2024-07-27T01:26:00+00:00
us_pacific_date: 2024-07-26
win_ratio: 0.4878048780487805
Download Preference Data
Resubmit model
Running pipeline stage MKMLizer
Starting job with name jic062-share-qlora-out-v10-mkmlizer
Waiting for job on jic062-share-qlora-out-v10-mkmlizer to finish
jic062-share-qlora-out-v10-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
jic062-share-qlora-out-v10-mkmlizer: ║ _____ __ __ ║
jic062-share-qlora-out-v10-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
jic062-share-qlora-out-v10-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
jic062-share-qlora-out-v10-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
jic062-share-qlora-out-v10-mkmlizer: ║ /___/ ║
jic062-share-qlora-out-v10-mkmlizer: ║ ║
jic062-share-qlora-out-v10-mkmlizer: ║ Version: 0.9.7 ║
jic062-share-qlora-out-v10-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
jic062-share-qlora-out-v10-mkmlizer: ║ https://mk1.ai ║
jic062-share-qlora-out-v10-mkmlizer: ║ ║
jic062-share-qlora-out-v10-mkmlizer: ║ The license key for the current software has been verified as ║
jic062-share-qlora-out-v10-mkmlizer: ║ belonging to: ║
jic062-share-qlora-out-v10-mkmlizer: ║ ║
jic062-share-qlora-out-v10-mkmlizer: ║ Chai Research Corp. ║
jic062-share-qlora-out-v10-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
jic062-share-qlora-out-v10-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
jic062-share-qlora-out-v10-mkmlizer: ║ ║
jic062-share-qlora-out-v10-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission shuttleai-shuttle-2-5-1-_5730_v8: ('http://shuttleai-shuttle-2-5-1-5730-v8-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'activator request timeout')
Failed to get response for submission shuttleai-shuttle-2-5-1-_5730_v5: ('http://shuttleai-shuttle-2-5-1-5730-v5-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:54728->127.0.0.1:8080: read: connection reset by peer\n')
jic062-share-qlora-out-v10-mkmlizer: Downloaded to shared memory in 49.429s
jic062-share-qlora-out-v10-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpnkkqm_6s, device:0
jic062-share-qlora-out-v10-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission shuttleai-shuttle-2-5-1-_5730_v8: ('http://shuttleai-shuttle-2-5-1-5730-v8-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Failed to get response for submission shuttleai-shuttle-2-5-1-_5730_v8: ('http://shuttleai-shuttle-2-5-1-5730-v8-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
jic062-share-qlora-out-v10-mkmlizer: quantized model in 25.616s
jic062-share-qlora-out-v10-mkmlizer: Processed model jic062/share-qlora-out in 75.046s
jic062-share-qlora-out-v10-mkmlizer: creating bucket guanaco-mkml-models
jic062-share-qlora-out-v10-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
jic062-share-qlora-out-v10-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/jic062-share-qlora-out-v10
jic062-share-qlora-out-v10-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/jic062-share-qlora-out-v10/config.json
jic062-share-qlora-out-v10-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/jic062-share-qlora-out-v10/special_tokens_map.json
jic062-share-qlora-out-v10-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/jic062-share-qlora-out-v10/tokenizer_config.json
jic062-share-qlora-out-v10-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/jic062-share-qlora-out-v10/tokenizer.json
jic062-share-qlora-out-v10-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/jic062-share-qlora-out-v10/flywheel_model.0.safetensors
jic062-share-qlora-out-v10-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
jic062-share-qlora-out-v10-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 2%|▏ | 7/291 [00:00<00:05, 53.40it/s] Loading 0: 6%|▌ | 17/291 [00:00<00:03, 77.43it/s] Loading 0: 11%|█ | 31/291 [00:00<00:02, 87.25it/s] Loading 0: 14%|█▎ | 40/291 [00:00<00:02, 86.28it/s] Loading 0: 17%|█▋ | 49/291 [00:00<00:02, 86.17it/s] Loading 0: 20%|█▉ | 58/291 [00:00<00:02, 85.84it/s] Loading 0: 23%|██▎ | 67/291 [00:00<00:02, 84.05it/s] Loading 0: 26%|██▌ | 76/291 [00:00<00:02, 82.42it/s] Loading 0: 29%|██▉ | 85/291 [00:02<00:09, 21.40it/s] Loading 0: 32%|███▏ | 94/291 [00:02<00:07, 27.82it/s] Loading 0: 35%|███▌ | 103/291 [00:02<00:05, 34.97it/s] Loading 0: 38%|███▊ | 112/291 [00:02<00:04, 40.97it/s] Loading 0: 42%|████▏ | 121/291 [00:02<00:03, 47.58it/s] Loading 0: 45%|████▍ | 130/291 [00:02<00:03, 52.90it/s] Loading 0: 48%|████▊ | 139/291 [00:02<00:02, 58.81it/s] Loading 0: 51%|█████ | 148/291 [00:02<00:02, 65.44it/s] Loading 0: 55%|█████▍ | 160/291 [00:02<00:01, 70.02it/s] Loading 0: 58%|█████▊ | 169/291 [00:03<00:01, 71.57it/s] Loading 0: 61%|██████ | 178/291 [00:03<00:01, 74.45it/s] Loading 0: 64%|██████▍ | 187/291 [00:04<00:04, 22.69it/s] Loading 0: 68%|██████▊ | 197/291 [00:04<00:03, 29.88it/s] Loading 0: 70%|███████ | 205/291 [00:04<00:02, 35.52it/s] Loading 0: 74%|███████▎ | 214/291 [00:04<00:01, 43.17it/s] Loading 0: 77%|███████▋ | 224/291 [00:04<00:01, 52.66it/s] Loading 0: 82%|████████▏ | 238/291 [00:04<00:00, 64.10it/s] Loading 0: 85%|████████▍ | 247/291 [00:04<00:00, 67.32it/s] Loading 0: 88%|████████▊ | 257/291 [00:05<00:00, 74.43it/s] Loading 0: 92%|█████████▏| 268/291 [00:05<00:00, 73.86it/s] Loading 0: 95%|█████████▌| 277/291 [00:05<00:00, 75.88it/s] Loading 0: 98%|█████████▊| 286/291 [00:05<00:00, 78.66it/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.
jic062-share-qlora-out-v10-mkmlizer: warnings.warn(
jic062-share-qlora-out-v10-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.
jic062-share-qlora-out-v10-mkmlizer: warnings.warn(
jic062-share-qlora-out-v10-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.
jic062-share-qlora-out-v10-mkmlizer: warnings.warn(
Failed to get response for submission shuttleai-shuttle-2-5-1-_5730_v8: ('http://shuttleai-shuttle-2-5-1-5730-v8-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
jic062-share-qlora-out-v10-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
jic062-share-qlora-out-v10-mkmlizer: Saving duration: 0.324s
jic062-share-qlora-out-v10-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 6.422s
jic062-share-qlora-out-v10-mkmlizer: creating bucket guanaco-reward-models
jic062-share-qlora-out-v10-mkmlizer: Bucket 's3://guanaco-reward-models/' created
jic062-share-qlora-out-v10-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/jic062-share-qlora-out-v10_reward
jic062-share-qlora-out-v10-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/jic062-share-qlora-out-v10_reward/tokenizer_config.json
jic062-share-qlora-out-v10-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/jic062-share-qlora-out-v10_reward/config.json
jic062-share-qlora-out-v10-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/jic062-share-qlora-out-v10_reward/special_tokens_map.json
jic062-share-qlora-out-v10-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/jic062-share-qlora-out-v10_reward/merges.txt
jic062-share-qlora-out-v10-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/jic062-share-qlora-out-v10_reward/vocab.json
jic062-share-qlora-out-v10-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/jic062-share-qlora-out-v10_reward/tokenizer.json
jic062-share-qlora-out-v10-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/jic062-share-qlora-out-v10_reward/reward.tensors
Job jic062-share-qlora-out-v10-mkmlizer completed after 116.35s with status: succeeded
Stopping job with name jic062-share-qlora-out-v10-mkmlizer
Pipeline stage MKMLizer completed in 117.20s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service jic062-share-qlora-out-v10
Waiting for inference service jic062-share-qlora-out-v10 to be ready
Failed to get response for submission shuttleai-shuttle-2-5-1-_5730_v8: ('http://shuttleai-shuttle-2-5-1-5730-v8-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Failed to get response for submission shuttleai-shuttle-2-5-1-_5730_v8: ('http://shuttleai-shuttle-2-5-1-5730-v8-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Failed to get response for submission shuttleai-shuttle-2-5-1-_5730_v8: ('http://shuttleai-shuttle-2-5-1-5730-v8-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Failed to get response for submission shuttleai-shuttle-2-5-1-_5730_v8: ('http://shuttleai-shuttle-2-5-1-5730-v8-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Failed to get response for submission shuttleai-shuttle-2-5-1-_5730_v8: ('http://shuttleai-shuttle-2-5-1-5730-v8-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Failed to get response for submission shuttleai-shuttle-2-5-1-_5730_v8: ('http://shuttleai-shuttle-2-5-1-5730-v8-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Failed to get response for submission shuttleai-shuttle-2-5-1-_5730_v8: ('http://shuttleai-shuttle-2-5-1-5730-v8-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Failed to get response for submission shuttleai-shuttle-2-5-1-_5730_v8: ('http://shuttleai-shuttle-2-5-1-5730-v8-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Failed to get response for submission shuttleai-shuttle-2-5-1-_5730_v8: ('http://shuttleai-shuttle-2-5-1-5730-v8-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Failed to get response for submission shuttleai-shuttle-2-5-1-_5730_v8: ('http://shuttleai-shuttle-2-5-1-5730-v8-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'activator request timeout')
Failed to get response for submission shuttleai-shuttle-2-5-1-_5730_v8: ('http://shuttleai-shuttle-2-5-1-5730-v8-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Tearing down inference service jic062-share-qlora-out-v10
%s, retrying in %s seconds...
Creating inference service jic062-share-qlora-out-v10
Waiting for inference service jic062-share-qlora-out-v10 to be ready
Inference service jic062-share-qlora-out-v10 ready after 30.24436354637146s
Pipeline stage ISVCDeployer completed in 637.76s
Running pipeline stage StressChecker
Failed to get response for submission shuttleai-shuttle-2-5-1-_5730_v8: ('http://shuttleai-shuttle-2-5-1-5730-v8-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Received healthy response to inference request in 2.341644525527954s
Received healthy response to inference request in 1.3985159397125244s
Received healthy response to inference request in 1.3735017776489258s
Received healthy response to inference request in 1.3781440258026123s
Failed to get response for submission shuttleai-shuttle-2-5-1-_5730_v8: ('http://shuttleai-shuttle-2-5-1-5730-v8-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Received healthy response to inference request in 1.3365020751953125s
5 requests
0 failed requests
5th percentile: 1.343902015686035
10th percentile: 1.3513019561767579
20th percentile: 1.3661018371582032
30th percentile: 1.3744302272796631
40th percentile: 1.3762871265411376
50th percentile: 1.3781440258026123
60th percentile: 1.3862927913665772
70th percentile: 1.394441556930542
80th percentile: 1.5871416568756105
90th percentile: 1.9643930912017824
95th percentile: 2.153018808364868
99th percentile: 2.3039193820953368
mean time: 1.5656616687774658
Pipeline stage StressChecker completed in 8.55s
jic062-share-qlora-out_v10 status is now deployed due to DeploymentManager action
jic062-share-qlora-out_v10 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of jic062-share-qlora-out_v10
Running pipeline stage ISVCDeleter
Checking if service jic062-share-qlora-out-v10 is running
Tearing down inference service jic062-share-qlora-out-v10
Service jic062-share-qlora-out-v10 has been torndown
Pipeline stage ISVCDeleter completed in 5.42s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key jic062-share-qlora-out-v10/config.json from bucket guanaco-mkml-models
Deleting key jic062-share-qlora-out-v10/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key jic062-share-qlora-out-v10/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key jic062-share-qlora-out-v10/tokenizer.json from bucket guanaco-mkml-models
Deleting key jic062-share-qlora-out-v10/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key jic062-share-qlora-out-v10_reward/config.json from bucket guanaco-reward-models
Deleting key jic062-share-qlora-out-v10_reward/merges.txt from bucket guanaco-reward-models
Deleting key jic062-share-qlora-out-v10_reward/reward.tensors from bucket guanaco-reward-models
Deleting key jic062-share-qlora-out-v10_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key jic062-share-qlora-out-v10_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key jic062-share-qlora-out-v10_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key jic062-share-qlora-out-v10_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.62s
jic062-share-qlora-out_v10 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics