submission_id: jic062-share-qlora-out_v6
developer_uid: chace9580
alignment_samples: 0
best_of: 16
celo_rating: 1163.66
display_name: jic062-share-qlora-out_v6
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_v6
model_num_parameters: 8030261248.0
model_repo: jic062/share-qlora-out
model_size: 8B
num_battles: 11256
num_wins: 5175
propriety_score: 0.685427135678392
propriety_total_count: 995.0
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: 2024-07-26T06:19:00+00:00
us_pacific_date: 2024-07-25
win_ratio: 0.4597547974413646
Download Preference Data
Resubmit model
Running pipeline stage MKMLizer
Starting job with name jic062-share-qlora-out-v6-mkmlizer
Waiting for job on jic062-share-qlora-out-v6-mkmlizer to finish
jic062-share-qlora-out-v6-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
jic062-share-qlora-out-v6-mkmlizer: ║ _____ __ __ ║
jic062-share-qlora-out-v6-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
jic062-share-qlora-out-v6-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
jic062-share-qlora-out-v6-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
jic062-share-qlora-out-v6-mkmlizer: ║ /___/ ║
jic062-share-qlora-out-v6-mkmlizer: ║ ║
jic062-share-qlora-out-v6-mkmlizer: ║ Version: 0.9.7 ║
jic062-share-qlora-out-v6-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
jic062-share-qlora-out-v6-mkmlizer: ║ https://mk1.ai ║
jic062-share-qlora-out-v6-mkmlizer: ║ ║
jic062-share-qlora-out-v6-mkmlizer: ║ The license key for the current software has been verified as ║
jic062-share-qlora-out-v6-mkmlizer: ║ belonging to: ║
jic062-share-qlora-out-v6-mkmlizer: ║ ║
jic062-share-qlora-out-v6-mkmlizer: ║ Chai Research Corp. ║
jic062-share-qlora-out-v6-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
jic062-share-qlora-out-v6-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
jic062-share-qlora-out-v6-mkmlizer: ║ ║
jic062-share-qlora-out-v6-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
jic062-share-qlora-out-v6-mkmlizer: Downloaded to shared memory in 24.625s
jic062-share-qlora-out-v6-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp2mo08zqv, device:0
jic062-share-qlora-out-v6-mkmlizer: Saving flywheel model at /dev/shm/model_cache
jic062-share-qlora-out-v6-mkmlizer: quantized model in 25.706s
jic062-share-qlora-out-v6-mkmlizer: Processed model jic062/share-qlora-out in 50.332s
jic062-share-qlora-out-v6-mkmlizer: creating bucket guanaco-mkml-models
jic062-share-qlora-out-v6-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
jic062-share-qlora-out-v6-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/jic062-share-qlora-out-v6
jic062-share-qlora-out-v6-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/jic062-share-qlora-out-v6/config.json
jic062-share-qlora-out-v6-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/jic062-share-qlora-out-v6/special_tokens_map.json
jic062-share-qlora-out-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/jic062-share-qlora-out-v6/tokenizer_config.json
jic062-share-qlora-out-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/jic062-share-qlora-out-v6/tokenizer.json
jic062-share-qlora-out-v6-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/jic062-share-qlora-out-v6/flywheel_model.0.safetensors
jic062-share-qlora-out-v6-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
jic062-share-qlora-out-v6-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 2%|▏ | 7/291 [00:00<00:05, 55.53it/s] Loading 0: 6%|▌ | 17/291 [00:00<00:03, 79.00it/s] Loading 0: 10%|█ | 30/291 [00:00<00:02, 100.97it/s] Loading 0: 14%|█▍ | 41/291 [00:00<00:02, 89.48it/s] Loading 0: 18%|█▊ | 51/291 [00:00<00:02, 91.92it/s] Loading 0: 21%|██ | 61/291 [00:00<00:02, 79.96it/s] Loading 0: 24%|██▍ | 70/291 [00:00<00:02, 80.67it/s] Loading 0: 27%|██▋ | 79/291 [00:00<00:02, 81.33it/s] Loading 0: 30%|███ | 88/291 [00:02<00:09, 21.48it/s] Loading 0: 33%|███▎ | 97/291 [00:02<00:06, 27.72it/s] Loading 0: 36%|███▋ | 106/291 [00:02<00:05, 34.72it/s] Loading 0: 40%|███▉ | 115/291 [00:02<00:04, 41.24it/s] Loading 0: 43%|████▎ | 124/291 [00:02<00:03, 47.57it/s] Loading 0: 46%|████▌ | 133/291 [00:02<00:02, 55.38it/s] Loading 0: 49%|████▉ | 142/291 [00:02<00:02, 62.59it/s] Loading 0: 52%|█████▏ | 152/291 [00:02<00:01, 71.02it/s] Loading 0: 55%|█████▌ | 161/291 [00:02<00:01, 74.71it/s] Loading 0: 58%|█████▊ | 170/291 [00:03<00:01, 76.94it/s] Loading 0: 62%|██████▏ | 179/291 [00:03<00:01, 79.45it/s] Loading 0: 65%|██████▍ | 188/291 [00:04<00:04, 21.76it/s] Loading 0: 69%|██████▉ | 202/291 [00:04<00:02, 31.60it/s] Loading 0: 73%|███████▎ | 213/291 [00:04<00:01, 40.51it/s] Loading 0: 77%|███████▋ | 223/291 [00:04<00:01, 46.11it/s] Loading 0: 80%|███████▉ | 232/291 [00:04<00:01, 52.82it/s] Loading 0: 85%|████████▍ | 247/291 [00:04<00:00, 64.57it/s] Loading 0: 88%|████████▊ | 256/291 [00:05<00:00, 67.74it/s] Loading 0: 92%|█████████▏| 267/291 [00:05<00:00, 76.36it/s] Loading 0: 95%|█████████▌| 277/291 [00:05<00:00, 74.14it/s] Loading 0: 99%|█████████▊| 287/291 [00:05<00:00, 45.71it/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-v6-mkmlizer: warnings.warn(
jic062-share-qlora-out-v6-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-v6-mkmlizer: warnings.warn(
jic062-share-qlora-out-v6-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-v6-mkmlizer: warnings.warn(
jic062-share-qlora-out-v6-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
jic062-share-qlora-out-v6-mkmlizer: Saving duration: 0.332s
jic062-share-qlora-out-v6-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 6.493s
jic062-share-qlora-out-v6-mkmlizer: creating bucket guanaco-reward-models
jic062-share-qlora-out-v6-mkmlizer: Bucket 's3://guanaco-reward-models/' created
jic062-share-qlora-out-v6-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/jic062-share-qlora-out-v6_reward
jic062-share-qlora-out-v6-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/jic062-share-qlora-out-v6_reward/config.json
jic062-share-qlora-out-v6-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/jic062-share-qlora-out-v6_reward/special_tokens_map.json
jic062-share-qlora-out-v6-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/jic062-share-qlora-out-v6_reward/tokenizer_config.json
jic062-share-qlora-out-v6-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/jic062-share-qlora-out-v6_reward/merges.txt
jic062-share-qlora-out-v6-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/jic062-share-qlora-out-v6_reward/vocab.json
jic062-share-qlora-out-v6-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/jic062-share-qlora-out-v6_reward/tokenizer.json
jic062-share-qlora-out-v6-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/jic062-share-qlora-out-v6_reward/reward.tensors
Job jic062-share-qlora-out-v6-mkmlizer completed after 84.37s with status: succeeded
Stopping job with name jic062-share-qlora-out-v6-mkmlizer
Pipeline stage MKMLizer completed in 85.46s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.07s
Running pipeline stage ISVCDeployer
Creating inference service jic062-share-qlora-out-v6
Waiting for inference service jic062-share-qlora-out-v6 to be ready
Inference service jic062-share-qlora-out-v6 ready after 60.67989373207092s
Pipeline stage ISVCDeployer completed in 63.04s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1683404445648193s
Received healthy response to inference request in 1.3147332668304443s
Received healthy response to inference request in 1.3346457481384277s
Received healthy response to inference request in 2.4508166313171387s
Received healthy response to inference request in 1.2247624397277832s
5 requests
0 failed requests
5th percentile: 1.2427566051483154
10th percentile: 1.2607507705688477
20th percentile: 1.296739101409912
30th percentile: 1.318715763092041
40th percentile: 1.3266807556152345
50th percentile: 1.3346457481384277
60th percentile: 1.6681236267089843
70th percentile: 2.001601505279541
80th percentile: 2.2248356819152835
90th percentile: 2.337826156616211
95th percentile: 2.3943213939666745
99th percentile: 2.4395175838470458
mean time: 1.6986597061157227
Pipeline stage StressChecker completed in 9.20s
jic062-share-qlora-out_v6 status is now deployed due to DeploymentManager action
jic062-share-qlora-out_v6 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of jic062-share-qlora-out_v6
Running pipeline stage ISVCDeleter
Checking if service jic062-share-qlora-out-v6 is running
Tearing down inference service jic062-share-qlora-out-v6
Service jic062-share-qlora-out-v6 has been torndown
Pipeline stage ISVCDeleter completed in 4.25s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key jic062-share-qlora-out-v6/config.json from bucket guanaco-mkml-models
Deleting key jic062-share-qlora-out-v6/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key jic062-share-qlora-out-v6/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key jic062-share-qlora-out-v6/tokenizer.json from bucket guanaco-mkml-models
Deleting key jic062-share-qlora-out-v6/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key jic062-share-qlora-out-v6_reward/config.json from bucket guanaco-reward-models
Deleting key jic062-share-qlora-out-v6_reward/merges.txt from bucket guanaco-reward-models
Deleting key jic062-share-qlora-out-v6_reward/reward.tensors from bucket guanaco-reward-models
Deleting key jic062-share-qlora-out-v6_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key jic062-share-qlora-out-v6_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key jic062-share-qlora-out-v6_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key jic062-share-qlora-out-v6_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.34s
jic062-share-qlora-out_v6 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics