submission_id: chaiml-elo-run-3-cp7000_v8
developer_uid: robert_irvine
alignment_samples: 0
best_of: 1
celo_rating: 1205.33
display_name: chaiml-elo-run-3-cp7000_v8
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': 0.95, 'top_p': 1.0, 'min_p': 0.08, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|eot_id|>'], 'max_input_tokens': 512, 'best_of': 1, 'max_output_tokens': 64, 'reward_max_token_input': 256}
is_internal_developer: True
language_model: ChaiML/elo_run_3_cp7000
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: ChaiML/elo_run_3_cp7000
model_name: chaiml-elo-run-3-cp7000_v8
model_num_parameters: 8030261248.0
model_repo: ChaiML/elo_run_3_cp7000
model_size: 8B
num_battles: 179147
num_wins: 102449
propriety_score: 0.7101566889318934
propriety_total_count: 16019.0
ranking_group: single
reward_formatter: {'bot_template': 'Bot: {message}\n', 'memory_template': '', 'prompt_template': '', 'response_template': 'Bot:', 'truncate_by_message': False, 'user_template': 'User: {message}\n'}
reward_repo: ChaiML/gpt2_xl_pairwise_89m_step_347634
status: torndown
submission_type: basic
timestamp: 2024-08-05T01:55:08+00:00
us_pacific_date: 2024-08-04
win_ratio: 0.5718711449256756
Download Preference Data
Resubmit model
Running pipeline stage MKMLizer
Starting job with name chaiml-elo-run-3-cp7000-v8-mkmlizer
Waiting for job on chaiml-elo-run-3-cp7000-v8-mkmlizer to finish
chaiml-elo-run-3-cp7000-v8-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-elo-run-3-cp7000-v8-mkmlizer: ║ _____ __ __ ║
chaiml-elo-run-3-cp7000-v8-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-elo-run-3-cp7000-v8-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-elo-run-3-cp7000-v8-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-elo-run-3-cp7000-v8-mkmlizer: ║ /___/ ║
chaiml-elo-run-3-cp7000-v8-mkmlizer: ║ ║
chaiml-elo-run-3-cp7000-v8-mkmlizer: ║ Version: 0.9.9 ║
chaiml-elo-run-3-cp7000-v8-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-elo-run-3-cp7000-v8-mkmlizer: ║ https://mk1.ai ║
chaiml-elo-run-3-cp7000-v8-mkmlizer: ║ ║
chaiml-elo-run-3-cp7000-v8-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-elo-run-3-cp7000-v8-mkmlizer: ║ belonging to: ║
chaiml-elo-run-3-cp7000-v8-mkmlizer: ║ ║
chaiml-elo-run-3-cp7000-v8-mkmlizer: ║ Chai Research Corp. ║
chaiml-elo-run-3-cp7000-v8-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-elo-run-3-cp7000-v8-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
chaiml-elo-run-3-cp7000-v8-mkmlizer: ║ ║
chaiml-elo-run-3-cp7000-v8-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-elo-run-3-cp7000-v8-mkmlizer: Downloaded to shared memory in 44.134s
chaiml-elo-run-3-cp7000-v8-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpw4xsocdn, device:0
chaiml-elo-run-3-cp7000-v8-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-elo-run-3-cp7000-v8-mkmlizer: quantized model in 28.690s
chaiml-elo-run-3-cp7000-v8-mkmlizer: Processed model ChaiML/elo_run_3_cp7000 in 72.825s
chaiml-elo-run-3-cp7000-v8-mkmlizer: creating bucket guanaco-mkml-models
chaiml-elo-run-3-cp7000-v8-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-elo-run-3-cp7000-v8-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-elo-run-3-cp7000-v8
chaiml-elo-run-3-cp7000-v8-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-elo-run-3-cp7000-v8/config.json
chaiml-elo-run-3-cp7000-v8-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-elo-run-3-cp7000-v8/special_tokens_map.json
chaiml-elo-run-3-cp7000-v8-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-elo-run-3-cp7000-v8/tokenizer_config.json
chaiml-elo-run-3-cp7000-v8-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-elo-run-3-cp7000-v8/tokenizer.json
chaiml-elo-run-3-cp7000-v8-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-elo-run-3-cp7000-v8/flywheel_model.0.safetensors
chaiml-elo-run-3-cp7000-v8-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
chaiml-elo-run-3-cp7000-v8-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 2%|▏ | 5/291 [00:00<00:10, 27.49it/s] Loading 0: 4%|▍ | 12/291 [00:00<00:07, 36.81it/s] Loading 0: 5%|▌ | 16/291 [00:00<00:08, 33.79it/s] Loading 0: 7%|▋ | 21/291 [00:00<00:07, 36.32it/s] Loading 0: 9%|▊ | 25/291 [00:00<00:07, 34.21it/s] Loading 0: 11%|█ | 31/291 [00:00<00:06, 40.38it/s] Loading 0: 12%|█▏ | 36/291 [00:01<00:10, 23.82it/s] Loading 0: 14%|█▍ | 41/291 [00:01<00:09, 25.53it/s] Loading 0: 16%|█▋ | 48/291 [00:01<00:07, 32.26it/s] Loading 0: 18%|█▊ | 52/291 [00:01<00:07, 31.95it/s] Loading 0: 20%|█▉ | 57/291 [00:01<00:06, 34.76it/s] Loading 0: 21%|██ | 61/291 [00:01<00:06, 33.43it/s] Loading 0: 23%|██▎ | 66/291 [00:02<00:06, 36.25it/s] Loading 0: 24%|██▍ | 70/291 [00:02<00:06, 34.76it/s] Loading 0: 25%|██▌ | 74/291 [00:02<00:06, 34.54it/s] Loading 0: 27%|██▋ | 78/291 [00:02<00:06, 33.93it/s] Loading 0: 28%|██▊ | 82/291 [00:02<00:08, 24.20it/s] Loading 0: 30%|██▉ | 86/291 [00:02<00:07, 26.84it/s] Loading 0: 31%|███ | 90/291 [00:02<00:06, 29.20it/s] Loading 0: 32%|███▏ | 94/291 [00:03<00:06, 29.06it/s] Loading 0: 34%|███▍ | 99/291 [00:03<00:05, 32.38it/s] Loading 0: 35%|███▌ | 103/291 [00:03<00:05, 31.76it/s] Loading 0: 37%|███▋ | 108/291 [00:03<00:05, 33.18it/s] Loading 0: 38%|███▊ | 112/291 [00:03<00:05, 32.71it/s] Loading 0: 40%|███▉ | 116/291 [00:03<00:05, 33.22it/s] Loading 0: 42%|████▏ | 122/291 [00:03<00:04, 37.80it/s] Loading 0: 44%|████▎ | 127/291 [00:03<00:04, 35.65it/s] Loading 0: 46%|████▌ | 133/291 [00:04<00:05, 30.79it/s] Loading 0: 47%|████▋ | 137/291 [00:04<00:04, 31.00it/s] Loading 0: 48%|████▊ | 141/291 [00:04<00:05, 28.16it/s] Loading 0: 51%|█████ | 147/291 [00:04<00:04, 33.12it/s] Loading 0: 52%|█████▏ | 151/291 [00:04<00:04, 32.67it/s] Loading 0: 54%|█████▎ | 156/291 [00:04<00:03, 35.40it/s] Loading 0: 55%|█████▍ | 160/291 [00:04<00:03, 34.20it/s] Loading 0: 57%|█████▋ | 165/291 [00:05<00:03, 36.77it/s] Loading 0: 58%|█████▊ | 169/291 [00:05<00:03, 35.32it/s] Loading 0: 60%|█████▉ | 174/291 [00:05<00:03, 37.44it/s] Loading 0: 61%|██████ | 178/291 [00:05<00:03, 35.31it/s] Loading 0: 63%|██████▎ | 183/291 [00:05<00:02, 38.05it/s] Loading 0: 64%|██████▍ | 187/291 [00:05<00:04, 25.79it/s] Loading 0: 66%|██████▌ | 191/291 [00:05<00:03, 26.75it/s] Loading 0: 67%|██████▋ | 195/291 [00:06<00:03, 26.09it/s] Loading 0: 69%|██████▉ | 201/291 [00:06<00:02, 31.14it/s] Loading 0: 70%|███████ | 205/291 [00:06<00:02, 30.81it/s] Loading 0: 72%|███████▏ | 210/291 [00:06<00:02, 33.77it/s] Loading 0: 74%|███████▎ | 214/291 [00:06<00:02, 32.51it/s] Loading 0: 75%|███████▌ | 219/291 [00:06<00:02, 35.02it/s] Loading 0: 77%|███████▋ | 223/291 [00:06<00:02, 33.76it/s] Loading 0: 78%|███████▊ | 227/291 [00:07<00:01, 33.60it/s] Loading 0: 79%|███████▉ | 231/291 [00:07<00:01, 33.67it/s] Loading 0: 81%|████████ | 235/291 [00:07<00:02, 24.97it/s] Loading 0: 82%|████████▏ | 239/291 [00:07<00:02, 24.67it/s] Loading 0: 85%|████████▍ | 246/291 [00:07<00:01, 32.41it/s] Loading 0: 86%|████████▌ | 250/291 [00:07<00:01, 32.06it/s] Loading 0: 88%|████████▊ | 255/291 [00:07<00:01, 34.70it/s] Loading 0: 89%|████████▉ | 259/291 [00:08<00:00, 33.29it/s] Loading 0: 91%|█████████ | 264/291 [00:08<00:00, 36.04it/s] Loading 0: 92%|█████████▏| 268/291 [00:08<00:00, 34.49it/s] Loading 0: 94%|█████████▍| 273/291 [00:08<00:00, 36.20it/s] Loading 0: 95%|█████████▌| 277/291 [00:08<00:00, 34.44it/s] Loading 0: 97%|█████████▋| 281/291 [00:08<00:00, 34.39it/s] Loading 0: 98%|█████████▊| 286/291 [00:14<00:01, 2.58it/s] Loading 0: 99%|█████████▉| 289/291 [00:14<00:00, 3.22it/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.
chaiml-elo-run-3-cp7000-v8-mkmlizer: warnings.warn(
chaiml-elo-run-3-cp7000-v8-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.
chaiml-elo-run-3-cp7000-v8-mkmlizer: warnings.warn(
chaiml-elo-run-3-cp7000-v8-mkmlizer: Downloading shards: 0%| | 0/2 [00:00<?, ?it/s] Downloading shards: 50%|█████ | 1/2 [00:05<00:05, 5.78s/it] Downloading shards: 100%|██████████| 2/2 [00:09<00:00, 4.47s/it] Downloading shards: 100%|██████████| 2/2 [00:09<00:00, 4.66s/it]
chaiml-elo-run-3-cp7000-v8-mkmlizer: Loading checkpoint shards: 0%| | 0/2 [00:00<?, ?it/s] Loading checkpoint shards: 50%|█████ | 1/2 [00:00<00:00, 2.44it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 4.04it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 3.68it/s]
chaiml-elo-run-3-cp7000-v8-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
chaiml-elo-run-3-cp7000-v8-mkmlizer: Saving duration: 1.290s
chaiml-elo-run-3-cp7000-v8-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 14.250s
chaiml-elo-run-3-cp7000-v8-mkmlizer: creating bucket guanaco-reward-models
chaiml-elo-run-3-cp7000-v8-mkmlizer: Bucket 's3://guanaco-reward-models/' created
chaiml-elo-run-3-cp7000-v8-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/chaiml-elo-run-3-cp7000-v8_reward
chaiml-elo-run-3-cp7000-v8-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/chaiml-elo-run-3-cp7000-v8_reward/config.json
chaiml-elo-run-3-cp7000-v8-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/chaiml-elo-run-3-cp7000-v8_reward/special_tokens_map.json
chaiml-elo-run-3-cp7000-v8-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/chaiml-elo-run-3-cp7000-v8_reward/tokenizer_config.json
chaiml-elo-run-3-cp7000-v8-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/chaiml-elo-run-3-cp7000-v8_reward/merges.txt
chaiml-elo-run-3-cp7000-v8-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/chaiml-elo-run-3-cp7000-v8_reward/vocab.json
chaiml-elo-run-3-cp7000-v8-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/chaiml-elo-run-3-cp7000-v8_reward/tokenizer.json
chaiml-elo-run-3-cp7000-v8-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/chaiml-elo-run-3-cp7000-v8_reward/reward.tensors
Job chaiml-elo-run-3-cp7000-v8-mkmlizer completed after 125.28s with status: succeeded
Stopping job with name chaiml-elo-run-3-cp7000-v8-mkmlizer
Pipeline stage MKMLizer completed in 126.29s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.08s
Running pipeline stage ISVCDeployer
Creating inference service chaiml-elo-run-3-cp7000-v8
Waiting for inference service chaiml-elo-run-3-cp7000-v8 to be ready
Inference service chaiml-elo-run-3-cp7000-v8 ready after 160.9710955619812s
Pipeline stage ISVCDeployer completed in 162.50s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.4967570304870605s
Received healthy response to inference request in 1.055450201034546s
Received healthy response to inference request in 0.6145598888397217s
Received healthy response to inference request in 1.043257713317871s
Received healthy response to inference request in 1.0550565719604492s
5 requests
0 failed requests
5th percentile: 0.7002994537353515
10th percentile: 0.7860390186309815
20th percentile: 0.9575181484222413
30th percentile: 1.0456174850463866
40th percentile: 1.050337028503418
50th percentile: 1.0550565719604492
60th percentile: 1.055214023590088
70th percentile: 1.0553714752197265
80th percentile: 1.1437115669250488
90th percentile: 1.3202342987060547
95th percentile: 1.4084956645965576
99th percentile: 1.47910475730896
mean time: 1.0530162811279298
Pipeline stage StressChecker completed in 5.94s
chaiml-elo-run-3-cp7000_v8 status is now deployed due to DeploymentManager action
chaiml-elo-run-3-cp7000_v8 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of chaiml-elo-run-3-cp7000_v8
Running pipeline stage ISVCDeleter
Checking if service chaiml-elo-run-3-cp7000-v8 is running
Tearing down inference service chaiml-elo-run-3-cp7000-v8
Service chaiml-elo-run-3-cp7000-v8 has been torndown
Pipeline stage ISVCDeleter completed in 5.24s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key chaiml-elo-run-3-cp7000-v8/config.json from bucket guanaco-mkml-models
Deleting key chaiml-elo-run-3-cp7000-v8/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key chaiml-elo-run-3-cp7000-v8/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key chaiml-elo-run-3-cp7000-v8/tokenizer.json from bucket guanaco-mkml-models
Deleting key chaiml-elo-run-3-cp7000-v8/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key chaiml-elo-run-3-cp7000-v8_reward/config.json from bucket guanaco-reward-models
Deleting key chaiml-elo-run-3-cp7000-v8_reward/merges.txt from bucket guanaco-reward-models
Deleting key chaiml-elo-run-3-cp7000-v8_reward/reward.tensors from bucket guanaco-reward-models
Deleting key chaiml-elo-run-3-cp7000-v8_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key chaiml-elo-run-3-cp7000-v8_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key chaiml-elo-run-3-cp7000-v8_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key chaiml-elo-run-3-cp7000-v8_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.78s
chaiml-elo-run-3-cp7000_v8 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics