submission_id: jic062-share-qlora-out_v11
developer_uid: chace9580
alignment_samples: 0
best_of: 16
celo_rating: 1193.23
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', '<|end_of_text|>'], '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: 10841
num_wins: 5386
propriety_score: 0.7142857142857143
propriety_total_count: 1064.0
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: 2024-07-27T01:26:47+00:00
us_pacific_date: 2024-07-26
win_ratio: 0.49681763674937734
Download Preference Data
Resubmit model
Running pipeline stage MKMLizer
Starting job with name jic062-share-qlora-out-v11-mkmlizer
Waiting for job on jic062-share-qlora-out-v11-mkmlizer to finish
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')
jic062-share-qlora-out-v11-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
jic062-share-qlora-out-v11-mkmlizer: ║ _____ __ __ ║
jic062-share-qlora-out-v11-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
jic062-share-qlora-out-v11-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
jic062-share-qlora-out-v11-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
jic062-share-qlora-out-v11-mkmlizer: ║ /___/ ║
jic062-share-qlora-out-v11-mkmlizer: ║ ║
jic062-share-qlora-out-v11-mkmlizer: ║ Version: 0.9.7 ║
jic062-share-qlora-out-v11-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
jic062-share-qlora-out-v11-mkmlizer: ║ https://mk1.ai ║
jic062-share-qlora-out-v11-mkmlizer: ║ ║
jic062-share-qlora-out-v11-mkmlizer: ║ The license key for the current software has been verified as ║
jic062-share-qlora-out-v11-mkmlizer: ║ belonging to: ║
jic062-share-qlora-out-v11-mkmlizer: ║ ║
jic062-share-qlora-out-v11-mkmlizer: ║ Chai Research Corp. ║
jic062-share-qlora-out-v11-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
jic062-share-qlora-out-v11-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
jic062-share-qlora-out-v11-mkmlizer: ║ ║
jic062-share-qlora-out-v11-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', '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-v11-mkmlizer: Downloaded to shared memory in 39.415s
jic062-share-qlora-out-v11-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp19xo81u6, device:0
jic062-share-qlora-out-v11-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')
jic062-share-qlora-out-v11-mkmlizer: quantized model in 26.115s
jic062-share-qlora-out-v11-mkmlizer: Processed model jic062/share-qlora-out in 65.531s
jic062-share-qlora-out-v11-mkmlizer: creating bucket guanaco-mkml-models
jic062-share-qlora-out-v11-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
jic062-share-qlora-out-v11-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/jic062-share-qlora-out-v11
jic062-share-qlora-out-v11-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/jic062-share-qlora-out-v11/config.json
jic062-share-qlora-out-v11-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/jic062-share-qlora-out-v11/special_tokens_map.json
jic062-share-qlora-out-v11-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/jic062-share-qlora-out-v11/tokenizer_config.json
jic062-share-qlora-out-v11-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/jic062-share-qlora-out-v11/tokenizer.json
jic062-share-qlora-out-v11-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/jic062-share-qlora-out-v11/flywheel_model.0.safetensors
jic062-share-qlora-out-v11-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
jic062-share-qlora-out-v11-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 2%|▏ | 7/291 [00:00<00:05, 51.89it/s] Loading 0: 5%|▌ | 16/291 [00:00<00:03, 70.31it/s] Loading 0: 11%|█ | 31/291 [00:00<00:03, 86.30it/s] Loading 0: 14%|█▎ | 40/291 [00:00<00:02, 86.10it/s] Loading 0: 17%|█▋ | 49/291 [00:00<00:02, 83.33it/s] Loading 0: 20%|█▉ | 58/291 [00:00<00:02, 83.16it/s] Loading 0: 23%|██▎ | 67/291 [00:00<00:02, 84.51it/s] Loading 0: 26%|██▌ | 76/291 [00:00<00:02, 85.55it/s] Loading 0: 29%|██▉ | 85/291 [00:02<00:09, 20.70it/s] Loading 0: 33%|███▎ | 96/291 [00:02<00:06, 28.83it/s] Loading 0: 36%|███▌ | 104/291 [00:02<00:05, 34.27it/s] Loading 0: 38%|███▊ | 112/291 [00:02<00:04, 40.38it/s] Loading 0: 42%|████▏ | 121/291 [00:02<00:03, 46.88it/s] Loading 0: 45%|████▍ | 130/291 [00:02<00:02, 54.26it/s] Loading 0: 48%|████▊ | 139/291 [00:02<00:02, 60.05it/s] Loading 0: 51%|█████ | 148/291 [00:02<00:02, 63.36it/s] Loading 0: 54%|█████▍ | 157/291 [00:02<00:01, 68.24it/s] Loading 0: 58%|█████▊ | 168/291 [00:03<00:01, 78.41it/s] Loading 0: 61%|██████ | 178/291 [00:03<00:01, 75.20it/s] Loading 0: 64%|██████▍ | 187/291 [00:04<00:04, 21.69it/s] Loading 0: 69%|██████▉ | 202/291 [00:04<00:02, 31.85it/s] Loading 0: 73%|███████▎ | 211/291 [00:04<00:02, 37.92it/s] Loading 0: 76%|███████▌ | 220/291 [00:04<00:01, 44.51it/s] Loading 0: 79%|███████▉ | 231/291 [00:04<00:01, 54.85it/s] Loading 0: 83%|████████▎ | 241/291 [00:05<00:00, 57.81it/s] Loading 0: 86%|████████▌ | 250/291 [00:05<00:00, 60.89it/s] Loading 0: 89%|████████▉ | 259/291 [00:05<00:00, 65.90it/s] Loading 0: 92%|█████████▏| 268/291 [00:05<00:00, 69.99it/s] Loading 0: 95%|█████████▌| 277/291 [00:05<00:00, 73.92it/s] Loading 0: 99%|█████████▊| 287/291 [00:05<00:00, 42.77it/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-v11-mkmlizer: warnings.warn(
jic062-share-qlora-out-v11-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-v11-mkmlizer: warnings.warn(
jic062-share-qlora-out-v11-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
jic062-share-qlora-out-v11-mkmlizer: Saving duration: 0.311s
jic062-share-qlora-out-v11-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 5.989s
jic062-share-qlora-out-v11-mkmlizer: creating bucket guanaco-reward-models
jic062-share-qlora-out-v11-mkmlizer: Bucket 's3://guanaco-reward-models/' created
jic062-share-qlora-out-v11-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/jic062-share-qlora-out-v11_reward
jic062-share-qlora-out-v11-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/jic062-share-qlora-out-v11_reward/config.json
jic062-share-qlora-out-v11-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/jic062-share-qlora-out-v11_reward/tokenizer_config.json
jic062-share-qlora-out-v11-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/jic062-share-qlora-out-v11_reward/special_tokens_map.json
jic062-share-qlora-out-v11-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/jic062-share-qlora-out-v11_reward/merges.txt
jic062-share-qlora-out-v11-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/jic062-share-qlora-out-v11_reward/vocab.json
jic062-share-qlora-out-v11-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/jic062-share-qlora-out-v11_reward/tokenizer.json
jic062-share-qlora-out-v11-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/jic062-share-qlora-out-v11_reward/reward.tensors
Job jic062-share-qlora-out-v11-mkmlizer completed after 94.83s with status: succeeded
Stopping job with name jic062-share-qlora-out-v11-mkmlizer
Pipeline stage MKMLizer completed in 95.79s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service jic062-share-qlora-out-v11
Waiting for inference service jic062-share-qlora-out-v11 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')
Inference service jic062-share-qlora-out-v11 ready after 80.76107954978943s
Pipeline stage ISVCDeployer completed in 82.55s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2430343627929688s
Received healthy response to inference request in 1.3629732131958008s
Received healthy response to inference request in 1.357363224029541s
Received healthy response to inference request in 1.3637900352478027s
Received healthy response to inference request in 1.3625333309173584s
5 requests
0 failed requests
5th percentile: 1.3583972454071045
10th percentile: 1.359431266784668
20th percentile: 1.361499309539795
30th percentile: 1.3626213073730469
40th percentile: 1.3627972602844238
50th percentile: 1.3629732131958008
60th percentile: 1.3632999420166017
70th percentile: 1.3636266708374023
80th percentile: 1.539638900756836
90th percentile: 1.8913366317749025
95th percentile: 2.067185497283935
99th percentile: 2.207864589691162
mean time: 1.5379388332366943
Pipeline stage StressChecker completed in 8.29s
jic062-share-qlora-out_v11 status is now deployed due to DeploymentManager action
jic062-share-qlora-out_v11 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of jic062-share-qlora-out_v11
Running pipeline stage ISVCDeleter
Checking if service jic062-share-qlora-out-v11 is running
Tearing down inference service jic062-share-qlora-out-v11
Service jic062-share-qlora-out-v11 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 jic062-share-qlora-out-v11/config.json from bucket guanaco-mkml-models
Deleting key jic062-share-qlora-out-v11/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key jic062-share-qlora-out-v11/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key jic062-share-qlora-out-v11/tokenizer.json from bucket guanaco-mkml-models
Deleting key jic062-share-qlora-out-v11/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key jic062-share-qlora-out-v11_reward/config.json from bucket guanaco-reward-models
Deleting key jic062-share-qlora-out-v11_reward/merges.txt from bucket guanaco-reward-models
Deleting key jic062-share-qlora-out-v11_reward/reward.tensors from bucket guanaco-reward-models
Deleting key jic062-share-qlora-out-v11_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key jic062-share-qlora-out-v11_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key jic062-share-qlora-out-v11_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key jic062-share-qlora-out-v11_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.38s
jic062-share-qlora-out_v11 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics