developer_uid: zonemercy
submission_id: chaiml-elo-alignment-run-3_v7
model_name: chaiml-elo-alignment-run-3_v3
model_group: ChaiML/elo_alignment_run
status: torndown
timestamp: 2024-07-13T17:49:16+00:00
num_battles: 57438
num_wins: 33465
celo_rating: 1244.99
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: 4
max_input_tokens: 512
max_output_tokens: 64
display_name: chaiml-elo-alignment-run-3_v3
is_internal_developer: True
language_model: ChaiML/elo_alignment_run_3
model_size: 8B
ranking_group: single
us_pacific_date: 2024-07-13
win_ratio: 0.5826282252167555
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}
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': "{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'}
Resubmit model
Running pipeline stage MKMLizer
Starting job with name chaiml-elo-alignment-run-3-v7-mkmlizer
Waiting for job on chaiml-elo-alignment-run-3-v7-mkmlizer to finish
chaiml-elo-alignment-run-3-v7-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-elo-alignment-run-3-v7-mkmlizer: ║     _____            __           __                                ║
chaiml-elo-alignment-run-3-v7-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-elo-alignment-run-3-v7-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-elo-alignment-run-3-v7-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-elo-alignment-run-3-v7-mkmlizer: ║       /___/                                                         ║
chaiml-elo-alignment-run-3-v7-mkmlizer: ║                                                                     ║
chaiml-elo-alignment-run-3-v7-mkmlizer: ║  Version: 0.8.14                                                    ║
chaiml-elo-alignment-run-3-v7-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-elo-alignment-run-3-v7-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-elo-alignment-run-3-v7-mkmlizer: ║                                                                     ║
chaiml-elo-alignment-run-3-v7-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-elo-alignment-run-3-v7-mkmlizer: ║  belonging to:                                                      ║
chaiml-elo-alignment-run-3-v7-mkmlizer: ║                                                                     ║
chaiml-elo-alignment-run-3-v7-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-elo-alignment-run-3-v7-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-elo-alignment-run-3-v7-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
chaiml-elo-alignment-run-3-v7-mkmlizer: ║                                                                     ║
chaiml-elo-alignment-run-3-v7-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-elo-alignment-run-3-v7-mkmlizer: Downloaded to shared memory in 42.263s
chaiml-elo-alignment-run-3-v7-mkmlizer: quantizing model to /dev/shm/model_cache
chaiml-elo-alignment-run-3-v7-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-elo-alignment-run-3-v7-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   3%|▎         | 8/291 [00:00<00:03, 73.60it/s]
Loading 0:   6%|▌         | 17/291 [00:00<00:03, 79.29it/s]
Loading 0:   9%|▊         | 25/291 [00:00<00:03, 79.25it/s]
Loading 0:  11%|█▏        | 33/291 [00:00<00:05, 43.09it/s]
Loading 0:  13%|█▎        | 39/291 [00:00<00:05, 44.95it/s]
Loading 0:  16%|█▋        | 48/291 [00:00<00:04, 54.20it/s]
Loading 0:  20%|█▉        | 57/291 [00:00<00:03, 62.13it/s]
Loading 0:  23%|██▎       | 66/291 [00:01<00:03, 67.76it/s]
Loading 0:  25%|██▌       | 74/291 [00:01<00:03, 69.76it/s]
Loading 0:  28%|██▊       | 82/291 [00:01<00:04, 42.89it/s]
Loading 0:  31%|███▏      | 91/291 [00:01<00:03, 51.22it/s]
Loading 0:  34%|███▍      | 100/291 [00:01<00:03, 58.94it/s]
Loading 0:  37%|███▋      | 109/291 [00:01<00:02, 64.24it/s]
Loading 0:  42%|████▏     | 122/291 [00:01<00:02, 75.72it/s]
Loading 0:  45%|████▌     | 131/291 [00:02<00:02, 75.78it/s]
Loading 0:  48%|████▊     | 140/291 [00:02<00:03, 44.16it/s]
Loading 0:  51%|█████     | 149/291 [00:02<00:02, 51.75it/s]
Loading 0:  54%|█████▍    | 158/291 [00:02<00:02, 58.53it/s]
Loading 0:  57%|█████▋    | 167/291 [00:02<00:01, 64.78it/s]
Loading 0:  60%|██████    | 176/291 [00:02<00:01, 70.32it/s]
Loading 0:  64%|██████▍   | 186/291 [00:03<00:01, 53.57it/s]
Loading 0:  66%|██████▋   | 193/291 [00:03<00:01, 51.51it/s]
Loading 0:  69%|██████▉   | 202/291 [00:03<00:01, 59.23it/s]
Loading 0:  73%|███████▎  | 211/291 [00:03<00:01, 65.90it/s]
Loading 0:  76%|███████▌  | 220/291 [00:03<00:00, 71.39it/s]
Loading 0:  78%|███████▊  | 228/291 [00:03<00:00, 72.17it/s]
Loading 0:  81%|████████  | 236/291 [00:04<00:01, 49.79it/s]
Loading 0:  84%|████████▎ | 243/291 [00:04<00:00, 53.85it/s]
Loading 0:  87%|████████▋ | 252/291 [00:04<00:00, 61.26it/s]
Loading 0:  90%|████████▉ | 261/291 [00:04<00:00, 67.09it/s]
Loading 0:  93%|█████████▎| 270/291 [00:04<00:00, 72.36it/s]
Loading 0:  96%|█████████▌| 279/291 [00:04<00:00, 76.41it/s]
Loading 0:  99%|█████████▉| 288/291 [00:10<00:00,  5.06it/s]
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
chaiml-elo-alignment-run-3-v7-mkmlizer: quantized model in 33.011s
chaiml-elo-alignment-run-3-v7-mkmlizer: Processed model ChaiML/elo_alignment_run_3 in 75.274s
chaiml-elo-alignment-run-3-v7-mkmlizer: creating bucket guanaco-mkml-models
chaiml-elo-alignment-run-3-v7-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-elo-alignment-run-3-v7-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v7
chaiml-elo-alignment-run-3-v7-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v7/special_tokens_map.json
chaiml-elo-alignment-run-3-v7-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v7/tokenizer_config.json
chaiml-elo-alignment-run-3-v7-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v7/config.json
chaiml-elo-alignment-run-3-v7-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v7/tokenizer.json
chaiml-elo-alignment-run-3-v7-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v7/flywheel_model.0.safetensors
chaiml-elo-alignment-run-3-v7-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
chaiml-elo-alignment-run-3-v7-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:919: 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-v7-mkmlizer:   warnings.warn(
chaiml-elo-alignment-run-3-v7-mkmlizer: /opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py:1132: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`.
chaiml-elo-alignment-run-3-v7-mkmlizer:   warnings.warn(
chaiml-elo-alignment-run-3-v7-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:769: 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-v7-mkmlizer:   warnings.warn(
chaiml-elo-alignment-run-3-v7-mkmlizer: 
Downloading shards:   0%|          | 0/2 [00:00<?, ?it/s]
Downloading shards:  50%|█████     | 1/2 [00:05<00:05,  5.56s/it]
Downloading shards: 100%|██████████| 2/2 [00:07<00:00,  3.37s/it]
Downloading shards: 100%|██████████| 2/2 [00:07<00:00,  3.70s/it]
chaiml-elo-alignment-run-3-v7-mkmlizer: 
Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/s]
Loading checkpoint shards:  50%|█████     | 1/2 [00:00<00:00,  2.06it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00,  3.42it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00,  3.11it/s]
chaiml-elo-alignment-run-3-v7-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
chaiml-elo-alignment-run-3-v7-mkmlizer: Saving duration: 8.135s
chaiml-elo-alignment-run-3-v7-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 18.109s
chaiml-elo-alignment-run-3-v7-mkmlizer: creating bucket guanaco-reward-models
chaiml-elo-alignment-run-3-v7-mkmlizer: Bucket 's3://guanaco-reward-models/' created
chaiml-elo-alignment-run-3-v7-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/chaiml-elo-alignment-run-3-v7_reward
chaiml-elo-alignment-run-3-v7-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/chaiml-elo-alignment-run-3-v7_reward/config.json
chaiml-elo-alignment-run-3-v7-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/chaiml-elo-alignment-run-3-v7_reward/merges.txt
chaiml-elo-alignment-run-3-v7-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/chaiml-elo-alignment-run-3-v7_reward/tokenizer_config.json
chaiml-elo-alignment-run-3-v7-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/chaiml-elo-alignment-run-3-v7_reward/vocab.json
chaiml-elo-alignment-run-3-v7-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/chaiml-elo-alignment-run-3-v7_reward/special_tokens_map.json
chaiml-elo-alignment-run-3-v7-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/chaiml-elo-alignment-run-3-v7_reward/tokenizer.json
chaiml-elo-alignment-run-3-v7-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/chaiml-elo-alignment-run-3-v7_reward/reward.tensors
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Job chaiml-elo-alignment-run-3-v7-mkmlizer completed after 280.0s with status: succeeded
Stopping job with name chaiml-elo-alignment-run-3-v7-mkmlizer
Pipeline stage MKMLizer completed in 280.94s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.08s
Running pipeline stage ISVCDeployer
Creating inference service chaiml-elo-alignment-run-3-v7
Waiting for inference service chaiml-elo-alignment-run-3-v7 to be ready
Inference service chaiml-elo-alignment-run-3-v7 ready after 51.27644085884094s
Pipeline stage ISVCDeployer completed in 58.02s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9634020328521729s
Received healthy response to inference request in 1.1761279106140137s
Received healthy response to inference request in 1.4793527126312256s
Received healthy response to inference request in 1.645812749862671s
Received healthy response to inference request in 3.2582154273986816s
5 requests
0 failed requests
5th percentile: 1.2367728710174561
10th percentile: 1.2974178314208984
20th percentile: 1.4187077522277831
30th percentile: 1.5126447200775146
40th percentile: 1.5792287349700929
50th percentile: 1.645812749862671
60th percentile: 1.7728484630584718
70th percentile: 1.8998841762542724
80th percentile: 2.222364711761475
90th percentile: 2.7402900695800785
95th percentile: 2.9992527484893796
99th percentile: 3.206422891616821
mean time: 1.9045821666717528
Pipeline stage StressChecker completed in 10.13s
chaiml-elo-alignment-run-3_v7 status is now deployed due to DeploymentManager action
chaiml-elo-alignment-run-3_v7 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of chaiml-elo-alignment-run-3_v7
Running pipeline stage ISVCDeleter
Checking if service chaiml-elo-alignment-run-3-v7 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 8.60s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key chaiml-elo-alignment-run-3-v7/config.json from bucket guanaco-mkml-models
Deleting key chaiml-elo-alignment-run-3-v7/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key chaiml-elo-alignment-run-3-v7/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key chaiml-elo-alignment-run-3-v7/tokenizer.json from bucket guanaco-mkml-models
Deleting key chaiml-elo-alignment-run-3-v7/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key chaiml-elo-alignment-run-3-v7_reward/config.json from bucket guanaco-reward-models
Deleting key chaiml-elo-alignment-run-3-v7_reward/merges.txt from bucket guanaco-reward-models
Deleting key chaiml-elo-alignment-run-3-v7_reward/reward.tensors from bucket guanaco-reward-models
Deleting key chaiml-elo-alignment-run-3-v7_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key chaiml-elo-alignment-run-3-v7_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key chaiml-elo-alignment-run-3-v7_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key chaiml-elo-alignment-run-3-v7_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.97s
chaiml-elo-alignment-run-3_v7 status is now torndown due to DeploymentManager action