submission_id: chaiml-elo-run-3-cp7000_v7
developer_uid: robert_irvine
alignment_samples: 2198
alignment_score: -1.4348813877371585
best_of: 4
celo_rating: 1243.66
display_name: chaiml-elo-run-3-cp7000_v7
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': 4, '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_v7
model_num_parameters: 8030261248.0
model_repo: ChaiML/elo_run_3_cp7000
model_size: 8B
num_battles: 168563
num_wins: 95343
propriety_score: 0.7013832930432446
propriety_total_count: 14892.0
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: 2024-08-05T01:08:41+00:00
us_pacific_date: 2024-08-04
win_ratio: 0.5656223489140558
Download Preference Data
Resubmit model
Running pipeline stage MKMLizer
Starting job with name chaiml-elo-run-3-cp7000-v7-mkmlizer
Waiting for job on chaiml-elo-run-3-cp7000-v7-mkmlizer to finish
Stopping job with name chaiml-elo-run-3-cp7000-v7-mkmlizer
%s, retrying in %s seconds...
Starting job with name chaiml-elo-run-3-cp7000-v7-mkmlizer
Waiting for job on chaiml-elo-run-3-cp7000-v7-mkmlizer to finish
chaiml-elo-run-3-cp7000-v7-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-elo-run-3-cp7000-v7-mkmlizer: ║ _____ __ __ ║
chaiml-elo-run-3-cp7000-v7-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-elo-run-3-cp7000-v7-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-elo-run-3-cp7000-v7-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-elo-run-3-cp7000-v7-mkmlizer: ║ /___/ ║
chaiml-elo-run-3-cp7000-v7-mkmlizer: ║ ║
chaiml-elo-run-3-cp7000-v7-mkmlizer: ║ Version: 0.9.9 ║
chaiml-elo-run-3-cp7000-v7-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-elo-run-3-cp7000-v7-mkmlizer: ║ https://mk1.ai ║
chaiml-elo-run-3-cp7000-v7-mkmlizer: ║ ║
chaiml-elo-run-3-cp7000-v7-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-elo-run-3-cp7000-v7-mkmlizer: ║ belonging to: ║
chaiml-elo-run-3-cp7000-v7-mkmlizer: ║ ║
chaiml-elo-run-3-cp7000-v7-mkmlizer: ║ Chai Research Corp. ║
chaiml-elo-run-3-cp7000-v7-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-elo-run-3-cp7000-v7-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
chaiml-elo-run-3-cp7000-v7-mkmlizer: ║ ║
chaiml-elo-run-3-cp7000-v7-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-elo-run-3-cp7000-v7-mkmlizer: Downloaded to shared memory in 64.989s
chaiml-elo-run-3-cp7000-v7-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpcyd7rlyz, device:0
chaiml-elo-run-3-cp7000-v7-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-elo-run-3-cp7000-v7-mkmlizer: quantized model in 28.676s
chaiml-elo-run-3-cp7000-v7-mkmlizer: Processed model ChaiML/elo_run_3_cp7000 in 93.664s
chaiml-elo-run-3-cp7000-v7-mkmlizer: creating bucket guanaco-mkml-models
chaiml-elo-run-3-cp7000-v7-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-elo-run-3-cp7000-v7-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-elo-run-3-cp7000-v7
chaiml-elo-run-3-cp7000-v7-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-elo-run-3-cp7000-v7/config.json
chaiml-elo-run-3-cp7000-v7-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-elo-run-3-cp7000-v7/special_tokens_map.json
chaiml-elo-run-3-cp7000-v7-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-elo-run-3-cp7000-v7/tokenizer_config.json
chaiml-elo-run-3-cp7000-v7-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-elo-run-3-cp7000-v7/flywheel_model.0.safetensors
chaiml-elo-run-3-cp7000-v7-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
chaiml-elo-run-3-cp7000-v7-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 2%|▏ | 5/291 [00:00<00:10, 26.69it/s] Loading 0: 4%|▍ | 12/291 [00:00<00:07, 36.12it/s] Loading 0: 5%|▌ | 16/291 [00:00<00:08, 33.53it/s] Loading 0: 7%|▋ | 21/291 [00:00<00:07, 36.19it/s] Loading 0: 9%|▊ | 25/291 [00:00<00:07, 34.34it/s] Loading 0: 10%|█ | 30/291 [00:00<00:06, 38.49it/s] Loading 0: 12%|█▏ | 34/291 [00:01<00:09, 26.37it/s] Loading 0: 13%|█▎ | 38/291 [00:01<00:09, 27.77it/s] Loading 0: 14%|█▍ | 42/291 [00:01<00:09, 27.04it/s] Loading 0: 16%|█▋ | 48/291 [00:01<00:07, 32.52it/s] Loading 0: 18%|█▊ | 52/291 [00:01<00:07, 32.14it/s] Loading 0: 20%|█▉ | 57/291 [00:01<00:06, 34.64it/s] Loading 0: 21%|██ | 61/291 [00:01<00:06, 33.22it/s] Loading 0: 23%|██▎ | 66/291 [00:02<00:06, 35.99it/s] Loading 0: 24%|██▍ | 70/291 [00:02<00:06, 34.28it/s] Loading 0: 25%|██▌ | 74/291 [00:02<00:06, 34.33it/s] Loading 0: 27%|██▋ | 78/291 [00:02<00:06, 34.24it/s] Loading 0: 28%|██▊ | 82/291 [00:02<00:08, 24.01it/s] Loading 0: 29%|██▉ | 85/291 [00:02<00:08, 25.13it/s] Loading 0: 31%|███ | 90/291 [00:02<00:06, 29.37it/s] Loading 0: 32%|███▏ | 94/291 [00:03<00:06, 29.59it/s] Loading 0: 34%|███▍ | 99/291 [00:03<00:05, 32.94it/s] Loading 0: 35%|███▌ | 103/291 [00:03<00:05, 31.60it/s] Loading 0: 37%|███▋ | 108/291 [00:03<00:05, 34.62it/s] Loading 0: 38%|███▊ | 112/291 [00:03<00:05, 33.62it/s] Loading 0: 40%|███▉ | 116/291 [00:03<00:05, 34.18it/s] Loading 0: 42%|████▏ | 122/291 [00:03<00:04, 38.35it/s] Loading 0: 44%|████▎ | 127/291 [00:03<00:04, 36.32it/s] Loading 0: 46%|████▌ | 133/291 [00:04<00:05, 31.49it/s] Loading 0: 47%|████▋ | 137/291 [00:04<00:04, 31.11it/s] Loading 0: 48%|████▊ | 141/291 [00:04<00:05, 28.87it/s] Loading 0: 51%|█████ | 147/291 [00:04<00:04, 33.93it/s] Loading 0: 52%|█████▏ | 151/291 [00:04<00:04, 33.00it/s] Loading 0: 54%|█████▎ | 156/291 [00:04<00:03, 35.59it/s] Loading 0: 55%|█████▍ | 160/291 [00:04<00:03, 34.34it/s] Loading 0: 57%|█████▋ | 165/291 [00:05<00:03, 36.96it/s] Loading 0: 58%|█████▊ | 169/291 [00:05<00:03, 35.35it/s] Loading 0: 60%|█████▉ | 174/291 [00:05<00:03, 37.42it/s] Loading 0: 61%|██████ | 178/291 [00:05<00:03, 35.05it/s] Loading 0: 63%|██████▎ | 183/291 [00:05<00:02, 38.70it/s] Loading 0: 64%|██████▍ | 187/291 [00:05<00:03, 27.03it/s] Loading 0: 66%|██████▌ | 191/291 [00:05<00:03, 28.05it/s] Loading 0: 67%|██████▋ | 195/291 [00:06<00:03, 26.78it/s] Loading 0: 69%|██████▉ | 201/291 [00:06<00:02, 32.25it/s] Loading 0: 70%|███████ | 205/291 [00:06<00:02, 31.69it/s] Loading 0: 72%|███████▏ | 210/291 [00:06<00:02, 33.73it/s] Loading 0: 74%|███████▎ | 214/291 [00:06<00:02, 32.18it/s] Loading 0: 75%|███████▌ | 219/291 [00:06<00:02, 34.61it/s] Loading 0: 77%|███████▋ | 223/291 [00:06<00:02, 33.42it/s] Loading 0: 78%|███████▊ | 227/291 [00:07<00:01, 33.16it/s] Loading 0: 79%|███████▉ | 231/291 [00:07<00:01, 33.55it/s] Loading 0: 81%|████████ | 235/291 [00:07<00:02, 25.52it/s] Loading 0: 82%|████████▏ | 239/291 [00:07<00:02, 25.36it/s] Loading 0: 85%|████████▍ | 246/291 [00:07<00:01, 33.26it/s] Loading 0: 86%|████████▌ | 250/291 [00:07<00:01, 32.95it/s] Loading 0: 88%|████████▊ | 255/291 [00:07<00:01, 35.00it/s] Loading 0: 89%|████████▉ | 259/291 [00:08<00:00, 33.68it/s] Loading 0: 91%|█████████ | 264/291 [00:08<00:00, 36.04it/s] Loading 0: 92%|█████████▏| 268/291 [00:08<00:00, 34.73it/s] Loading 0: 94%|█████████▍| 273/291 [00:08<00:00, 37.31it/s] Loading 0: 95%|█████████▌| 277/291 [00:08<00:00, 35.02it/s] Loading 0: 97%|█████████▋| 281/291 [00:08<00:00, 34.98it/s] Loading 0: 98%|█████████▊| 286/291 [00:14<00:01, 2.58it/s] Loading 0: 99%|█████████▉| 289/291 [00:14<00:00, 3.21it/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-v7-mkmlizer: warnings.warn(
chaiml-elo-run-3-cp7000-v7-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-v7-mkmlizer: warnings.warn(
chaiml-elo-run-3-cp7000-v7-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.
chaiml-elo-run-3-cp7000-v7-mkmlizer: warnings.warn(
chaiml-elo-run-3-cp7000-v7-mkmlizer: Downloading shards: 0%| | 0/2 [00:00<?, ?it/s] Downloading shards: 50%|█████ | 1/2 [00:05<00:05, 5.31s/it] Downloading shards: 100%|██████████| 2/2 [00:08<00:00, 3.78s/it] Downloading shards: 100%|██████████| 2/2 [00:08<00:00, 4.01s/it]
chaiml-elo-run-3-cp7000-v7-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, 4.02it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 3.66it/s]
chaiml-elo-run-3-cp7000-v7-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
chaiml-elo-run-3-cp7000-v7-mkmlizer: Saving duration: 1.307s
chaiml-elo-run-3-cp7000-v7-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 12.910s
chaiml-elo-run-3-cp7000-v7-mkmlizer: creating bucket guanaco-reward-models
chaiml-elo-run-3-cp7000-v7-mkmlizer: Bucket 's3://guanaco-reward-models/' created
chaiml-elo-run-3-cp7000-v7-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/chaiml-elo-run-3-cp7000-v7_reward
chaiml-elo-run-3-cp7000-v7-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/chaiml-elo-run-3-cp7000-v7_reward/vocab.json
chaiml-elo-run-3-cp7000-v7-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/chaiml-elo-run-3-cp7000-v7_reward/tokenizer.json
chaiml-elo-run-3-cp7000-v7-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/chaiml-elo-run-3-cp7000-v7_reward/reward.tensors
Job chaiml-elo-run-3-cp7000-v7-mkmlizer completed after 135.83s with status: succeeded
Stopping job with name chaiml-elo-run-3-cp7000-v7-mkmlizer
Pipeline stage MKMLizer completed in 137.81s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service chaiml-elo-run-3-cp7000-v7
Waiting for inference service chaiml-elo-run-3-cp7000-v7 to be ready
Inference service chaiml-elo-run-3-cp7000-v7 ready after 171.18305230140686s
Pipeline stage ISVCDeployer completed in 172.68s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1025869846343994s
Received healthy response to inference request in 1.1456732749938965s
Received healthy response to inference request in 1.1013500690460205s
Received healthy response to inference request in 1.1310083866119385s
Received healthy response to inference request in 1.1282668113708496s
5 requests
0 failed requests
5th percentile: 1.1067334175109864
10th percentile: 1.112116765975952
20th percentile: 1.1228834629058837
30th percentile: 1.1288151264190673
40th percentile: 1.129911756515503
50th percentile: 1.1310083866119385
60th percentile: 1.1368743419647216
70th percentile: 1.142740297317505
80th percentile: 1.3370560169219972
90th percentile: 1.7198215007781983
95th percentile: 1.9112042427062987
99th percentile: 2.064310436248779
mean time: 1.321777105331421
Pipeline stage StressChecker completed in 7.42s
chaiml-elo-run-3-cp7000_v7 status is now deployed due to DeploymentManager action
chaiml-elo-run-3-cp7000_v7 status is now inactive due to auto deactivation removed underperforming models
chaiml-elo-run-3-cp7000_v7 status is now deployed due to admin request
chaiml-elo-run-3-cp7000_v7 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of chaiml-elo-run-3-cp7000_v7
Running pipeline stage ISVCDeleter
Checking if service chaiml-elo-run-3-cp7000-v7 is running
Tearing down inference service chaiml-elo-run-3-cp7000-v7
Service chaiml-elo-run-3-cp7000-v7 has been torndown
Pipeline stage ISVCDeleter completed in 6.09s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key chaiml-elo-run-3-cp7000-v7/config.json from bucket guanaco-mkml-models
Deleting key chaiml-elo-run-3-cp7000-v7/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key chaiml-elo-run-3-cp7000-v7/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key chaiml-elo-run-3-cp7000-v7/tokenizer.json from bucket guanaco-mkml-models
Deleting key chaiml-elo-run-3-cp7000-v7/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key chaiml-elo-run-3-cp7000-v7_reward/config.json from bucket guanaco-reward-models
Deleting key chaiml-elo-run-3-cp7000-v7_reward/merges.txt from bucket guanaco-reward-models
Deleting key chaiml-elo-run-3-cp7000-v7_reward/reward.tensors from bucket guanaco-reward-models
Deleting key chaiml-elo-run-3-cp7000-v7_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key chaiml-elo-run-3-cp7000-v7_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key chaiml-elo-run-3-cp7000-v7_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key chaiml-elo-run-3-cp7000-v7_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.15s
chaiml-elo-run-3-cp7000_v7 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics