developer_uid: chai_backend_admin
submission_id: chaiml-elo-alignment-run-3_v19
model_name: chaiml-elo-alignment-run-3_v19
model_group: ChaiML/elo_alignment_run
status: torndown
timestamp: 2024-07-31T02:01:01+00:00
num_battles: 347670
num_wins: 196965
celo_rating: 1253.24
family_friendly_score: 0.0
submission_type: basic
model_repo: ChaiML/elo_alignment_run_3
model_architecture: LlamaForCausalLM
reward_repo: ChaiML/gpt2_xl_pairwise_89m_step_347634
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: chaiml-elo-alignment-run-3_v19
is_internal_developer: True
language_model: ChaiML/elo_alignment_run_3
model_size: 8B
ranking_group: single
us_pacific_date: 2024-07-30
win_ratio: 0.5665286047113642
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': 16, 'max_output_tokens': 64, 'reward_max_token_input': 256}
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}
reward_formatter: {'bot_template': '{bot_name}: {message}\n', 'memory_template': '', 'prompt_template': '', 'response_template': '{bot_name}:', 'truncate_by_message': False, 'user_template': '{user_name}: {message}\n'}
Resubmit model
Running pipeline stage MKMLizer
Starting job with name chaiml-elo-alignment-run-3-v19-mkmlizer
Waiting for job on chaiml-elo-alignment-run-3-v19-mkmlizer to finish
chaiml-elo-alignment-run-3-v19-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-elo-alignment-run-3-v19-mkmlizer: ║ _____ __ __ ║
chaiml-elo-alignment-run-3-v19-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-elo-alignment-run-3-v19-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-elo-alignment-run-3-v19-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-elo-alignment-run-3-v19-mkmlizer: ║ /___/ ║
chaiml-elo-alignment-run-3-v19-mkmlizer: ║ ║
chaiml-elo-alignment-run-3-v19-mkmlizer: ║ Version: 0.9.7 ║
chaiml-elo-alignment-run-3-v19-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-elo-alignment-run-3-v19-mkmlizer: ║ https://mk1.ai ║
chaiml-elo-alignment-run-3-v19-mkmlizer: ║ ║
chaiml-elo-alignment-run-3-v19-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-elo-alignment-run-3-v19-mkmlizer: ║ belonging to: ║
chaiml-elo-alignment-run-3-v19-mkmlizer: ║ ║
chaiml-elo-alignment-run-3-v19-mkmlizer: ║ Chai Research Corp. ║
chaiml-elo-alignment-run-3-v19-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-elo-alignment-run-3-v19-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
chaiml-elo-alignment-run-3-v19-mkmlizer: ║ ║
chaiml-elo-alignment-run-3-v19-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-elo-alignment-run-3-v19-mkmlizer: Downloaded to shared memory in 48.775s
chaiml-elo-alignment-run-3-v19-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpcdfqdv4e, device:0
chaiml-elo-alignment-run-3-v19-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-elo-alignment-run-3-v19-mkmlizer: quantized model in 28.818s
chaiml-elo-alignment-run-3-v19-mkmlizer: Processed model ChaiML/elo_alignment_run_3 in 77.594s
chaiml-elo-alignment-run-3-v19-mkmlizer: creating bucket guanaco-mkml-models
chaiml-elo-alignment-run-3-v19-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-elo-alignment-run-3-v19-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v19
chaiml-elo-alignment-run-3-v19-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v19/config.json
chaiml-elo-alignment-run-3-v19-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v19/special_tokens_map.json
chaiml-elo-alignment-run-3-v19-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v19/tokenizer_config.json
chaiml-elo-alignment-run-3-v19-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v19/tokenizer.json
chaiml-elo-alignment-run-3-v19-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v19/flywheel_model.0.safetensors
chaiml-elo-alignment-run-3-v19-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
chaiml-elo-alignment-run-3-v19-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 2%|▏ | 5/291 [00:00<00:10, 27.89it/s] Loading 0: 4%|▍ | 12/291 [00:00<00:07, 37.32it/s] Loading 0: 5%|▌ | 16/291 [00:00<00:08, 33.83it/s] Loading 0: 7%|▋ | 21/291 [00:00<00:07, 37.09it/s] Loading 0: 9%|▊ | 25/291 [00:00<00:07, 35.05it/s] Loading 0: 11%|█ | 31/291 [00:00<00:06, 41.63it/s] Loading 0: 12%|█▏ | 36/291 [00:01<00:10, 23.97it/s] Loading 0: 14%|█▍ | 41/291 [00:01<00:09, 25.99it/s] Loading 0: 16%|█▋ | 48/291 [00:01<00:07, 32.74it/s] Loading 0: 18%|█▊ | 52/291 [00:01<00:07, 32.36it/s] Loading 0: 20%|█▉ | 57/291 [00:01<00:06, 35.29it/s] Loading 0: 21%|██ | 61/291 [00:01<00:06, 34.43it/s] Loading 0: 23%|██▎ | 66/291 [00:01<00:06, 36.86it/s] Loading 0: 24%|██▍ | 70/291 [00:02<00:06, 34.80it/s] Loading 0: 25%|██▌ | 74/291 [00:02<00:06, 34.96it/s] Loading 0: 27%|██▋ | 78/291 [00:02<00:06, 35.39it/s] Loading 0: 28%|██▊ | 82/291 [00:02<00:08, 24.67it/s] Loading 0: 30%|██▉ | 86/291 [00:02<00:07, 27.38it/s] Loading 0: 31%|███ | 90/291 [00:02<00:06, 29.45it/s] Loading 0: 32%|███▏ | 94/291 [00:02<00:06, 30.05it/s] Loading 0: 34%|███▍ | 99/291 [00:03<00:05, 33.81it/s] Loading 0: 35%|███▌ | 103/291 [00:03<00:05, 32.71it/s] Loading 0: 37%|███▋ | 108/291 [00:03<00:05, 34.94it/s] Loading 0: 38%|███▊ | 112/291 [00:03<00:05, 34.01it/s] Loading 0: 40%|███▉ | 116/291 [00:03<00:05, 34.44it/s] Loading 0: 42%|████▏ | 122/291 [00:03<00:04, 38.92it/s] Loading 0: 44%|████▎ | 127/291 [00:03<00:04, 36.85it/s] Loading 0: 46%|████▌ | 133/291 [00:04<00:05, 29.91it/s] Loading 0: 47%|████▋ | 137/291 [00:04<00:05, 30.27it/s] Loading 0: 48%|████▊ | 141/291 [00:04<00:05, 29.10it/s] Loading 0: 51%|█████ | 147/291 [00:04<00:04, 34.02it/s] Loading 0: 52%|█████▏ | 151/291 [00:04<00:04, 32.85it/s] Loading 0: 54%|█████▎ | 156/291 [00:04<00:03, 34.72it/s] Loading 0: 55%|█████▍ | 160/291 [00:04<00:03, 33.10it/s] Loading 0: 57%|█████▋ | 165/291 [00:05<00:03, 34.59it/s] Loading 0: 58%|█████▊ | 169/291 [00:05<00:03, 33.41it/s] Loading 0: 60%|█████▉ | 174/291 [00:05<00:03, 36.00it/s] Loading 0: 61%|██████ | 178/291 [00:05<00:03, 34.62it/s] Loading 0: 63%|██████▎ | 183/291 [00:05<00:02, 38.31it/s] Loading 0: 64%|██████▍ | 187/291 [00:05<00:03, 26.67it/s] Loading 0: 66%|██████▌ | 191/291 [00:05<00:03, 28.10it/s] Loading 0: 67%|██████▋ | 195/291 [00:06<00:03, 27.11it/s] Loading 0: 69%|██████▉ | 201/291 [00:06<00:02, 32.58it/s] Loading 0: 70%|███████ | 205/291 [00:06<00:02, 31.58it/s] Loading 0: 72%|███████▏ | 210/291 [00:06<00:02, 34.25it/s] Loading 0: 74%|███████▎ | 214/291 [00:06<00:02, 32.94it/s] Loading 0: 75%|███████▌ | 219/291 [00:06<00:02, 35.47it/s] Loading 0: 77%|███████▋ | 223/291 [00:06<00:01, 34.02it/s] Loading 0: 78%|███████▊ | 227/291 [00:06<00:01, 33.61it/s] Loading 0: 79%|███████▉ | 231/291 [00:07<00:01, 33.65it/s] Loading 0: 81%|████████ | 235/291 [00:07<00:02, 25.01it/s] Loading 0: 82%|████████▏ | 239/291 [00:07<00:02, 25.32it/s] Loading 0: 85%|████████▍ | 246/291 [00:07<00:01, 33.36it/s] Loading 0: 86%|████████▌ | 250/291 [00:07<00:01, 32.72it/s] Loading 0: 88%|████████▊ | 255/291 [00:07<00:01, 35.52it/s] Loading 0: 89%|████████▉ | 259/291 [00:07<00:00, 33.84it/s] Loading 0: 91%|█████████ | 264/291 [00:08<00:00, 36.69it/s] Loading 0: 92%|█████████▏| 268/291 [00:08<00:00, 35.14it/s] Loading 0: 94%|█████████▍| 273/291 [00:08<00:00, 37.88it/s] Loading 0: 95%|█████████▌| 277/291 [00:08<00:00, 35.89it/s] Loading 0: 97%|█████████▋| 281/291 [00:08<00:00, 35.86it/s] Loading 0: 98%|█████████▊| 286/291 [00:14<00:01, 2.59it/s] Loading 0: 99%|█████████▉| 289/291 [00:14<00:00, 3.23it/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-alignment-run-3-v19-mkmlizer: warnings.warn(
chaiml-elo-alignment-run-3-v19-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-alignment-run-3-v19-mkmlizer: warnings.warn(
chaiml-elo-alignment-run-3-v19-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-alignment-run-3-v19-mkmlizer: warnings.warn(
chaiml-elo-alignment-run-3-v19-mkmlizer: Downloading shards: 0%| | 0/2 [00:00<?, ?it/s] Downloading shards: 50%|█████ | 1/2 [00:05<00:05, 5.46s/it] Downloading shards: 100%|██████████| 2/2 [00:08<00:00, 3.98s/it] Downloading shards: 100%|██████████| 2/2 [00:08<00:00, 4.21s/it]
chaiml-elo-alignment-run-3-v19-mkmlizer: Loading checkpoint shards: 0%| | 0/2 [00:00<?, ?it/s] Loading checkpoint shards: 50%|█████ | 1/2 [00:00<00:00, 2.42it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 3.98it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 3.62it/s]
chaiml-elo-alignment-run-3-v19-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
chaiml-elo-alignment-run-3-v19-mkmlizer: Saving duration: 1.284s
chaiml-elo-alignment-run-3-v19-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 13.106s
chaiml-elo-alignment-run-3-v19-mkmlizer: creating bucket guanaco-reward-models
chaiml-elo-alignment-run-3-v19-mkmlizer: Bucket 's3://guanaco-reward-models/' created
chaiml-elo-alignment-run-3-v19-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/chaiml-elo-alignment-run-3-v19_reward
chaiml-elo-alignment-run-3-v19-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/chaiml-elo-alignment-run-3-v19_reward/special_tokens_map.json
chaiml-elo-alignment-run-3-v19-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/chaiml-elo-alignment-run-3-v19_reward/config.json
chaiml-elo-alignment-run-3-v19-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/chaiml-elo-alignment-run-3-v19_reward/tokenizer_config.json
chaiml-elo-alignment-run-3-v19-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/chaiml-elo-alignment-run-3-v19_reward/merges.txt
chaiml-elo-alignment-run-3-v19-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/chaiml-elo-alignment-run-3-v19_reward/vocab.json
chaiml-elo-alignment-run-3-v19-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/chaiml-elo-alignment-run-3-v19_reward/tokenizer.json
chaiml-elo-alignment-run-3-v19-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/chaiml-elo-alignment-run-3-v19_reward/reward.tensors
Job chaiml-elo-alignment-run-3-v19-mkmlizer completed after 124.47s with status: succeeded
HTTP Request: %s %s "%s %d %s"
Stopping job with name chaiml-elo-alignment-run-3-v19-mkmlizer
Pipeline stage MKMLizer completed in 126.41s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.65s
Running pipeline stage ISVCDeployer
Creating inference service chaiml-elo-alignment-run-3-v19
Waiting for inference service chaiml-elo-alignment-run-3-v19 to be ready
Inference service chaiml-elo-alignment-run-3-v19 ready after 112.16107892990112s
Pipeline stage ISVCDeployer completed in 113.77s
Running pipeline stage StressChecker
HTTP Request: %s %s "%s %d %s"
Received healthy response to inference request in 2.581631898880005s
HTTP Request: %s %s "%s %d %s"
Received healthy response to inference request in 1.7074759006500244s
HTTP Request: %s %s "%s %d %s"
Received healthy response to inference request in 1.7137529850006104s
HTTP Request: %s %s "%s %d %s"
Received healthy response to inference request in 1.741602897644043s
HTTP Request: %s %s "%s %d %s"
Received healthy response to inference request in 1.7253742218017578s
5 requests
0 failed requests
5th percentile: 1.7087313175201415
10th percentile: 1.7099867343902588
20th percentile: 1.7124975681304933
30th percentile: 1.7160772323608398
40th percentile: 1.7207257270812988
50th percentile: 1.7253742218017578
60th percentile: 1.731865692138672
70th percentile: 1.738357162475586
80th percentile: 1.9096086978912354
90th percentile: 2.2456202983856204
95th percentile: 2.4136260986328124
99th percentile: 2.5480307388305663
mean time: 1.893967580795288
Pipeline stage StressChecker completed in 12.95s
chaiml-elo-alignment-run-3_v19 status is now deployed due to DeploymentManager action
chaiml-elo-alignment-run-3_v19 status is now inactive due to admin request
chaiml-elo-alignment-run-3_v19 status is now torndown due to DeploymentManager action