developer_uid: Jellywibble
submission_id: chaiml-elo-alignment-run-3_v28
model_name: dpo-resubmit
model_group: ChaiML/elo_alignment_run
status: torndown
timestamp: 2024-08-05T23:07:34+00:00
num_battles: 9557
num_wins: 5328
celo_rating: 1248.43
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: dpo-resubmit
is_internal_developer: True
language_model: ChaiML/elo_alignment_run_3
model_size: 8B
ranking_group: single
us_pacific_date: 2024-08-05
win_ratio: 0.55749712252799
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': '', 'prompt_template': "{bot_name}'s Persona: {memory}\n####\n{prompt}\n<START>\n", 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': True}
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-v28-mkmlizer
Waiting for job on chaiml-elo-alignment-run-3-v28-mkmlizer to finish
chaiml-elo-alignment-run-3-v28-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-elo-alignment-run-3-v28-mkmlizer: ║     _____            __           __                                ║
chaiml-elo-alignment-run-3-v28-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-elo-alignment-run-3-v28-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-elo-alignment-run-3-v28-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-elo-alignment-run-3-v28-mkmlizer: ║       /___/                                                         ║
chaiml-elo-alignment-run-3-v28-mkmlizer: ║                                                                     ║
chaiml-elo-alignment-run-3-v28-mkmlizer: ║  Version: 0.9.9                                                     ║
chaiml-elo-alignment-run-3-v28-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-elo-alignment-run-3-v28-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-elo-alignment-run-3-v28-mkmlizer: ║                                                                     ║
chaiml-elo-alignment-run-3-v28-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-elo-alignment-run-3-v28-mkmlizer: ║  belonging to:                                                      ║
chaiml-elo-alignment-run-3-v28-mkmlizer: ║                                                                     ║
chaiml-elo-alignment-run-3-v28-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-elo-alignment-run-3-v28-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-elo-alignment-run-3-v28-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
chaiml-elo-alignment-run-3-v28-mkmlizer: ║                                                                     ║
chaiml-elo-alignment-run-3-v28-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-elo-alignment-run-3-v28-mkmlizer: Downloaded to shared memory in 40.092s
chaiml-elo-alignment-run-3-v28-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpuf4c0_yb, device:0
chaiml-elo-alignment-run-3-v28-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-elo-alignment-run-3-v28-mkmlizer: quantized model in 29.039s
chaiml-elo-alignment-run-3-v28-mkmlizer: Processed model ChaiML/elo_alignment_run_3 in 69.132s
chaiml-elo-alignment-run-3-v28-mkmlizer: creating bucket guanaco-mkml-models
chaiml-elo-alignment-run-3-v28-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-elo-alignment-run-3-v28-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v28
chaiml-elo-alignment-run-3-v28-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v28/config.json
chaiml-elo-alignment-run-3-v28-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v28/special_tokens_map.json
chaiml-elo-alignment-run-3-v28-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v28/tokenizer_config.json
chaiml-elo-alignment-run-3-v28-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v28/tokenizer.json
chaiml-elo-alignment-run-3-v28-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v28/flywheel_model.0.safetensors
chaiml-elo-alignment-run-3-v28-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-v28-mkmlizer:   warnings.warn(
chaiml-elo-alignment-run-3-v28-mkmlizer: 
Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/s]
Loading checkpoint shards:  50%|█████     | 1/2 [00:00<00:00,  2.46it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00,  4.03it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00,  3.68it/s]
chaiml-elo-alignment-run-3-v28-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
chaiml-elo-alignment-run-3-v28-mkmlizer: Saving duration: 1.388s
chaiml-elo-alignment-run-3-v28-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 12.975s
chaiml-elo-alignment-run-3-v28-mkmlizer: creating bucket guanaco-reward-models
chaiml-elo-alignment-run-3-v28-mkmlizer: Bucket 's3://guanaco-reward-models/' created
chaiml-elo-alignment-run-3-v28-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/chaiml-elo-alignment-run-3-v28_reward
chaiml-elo-alignment-run-3-v28-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/chaiml-elo-alignment-run-3-v28_reward/tokenizer_config.json
chaiml-elo-alignment-run-3-v28-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/chaiml-elo-alignment-run-3-v28_reward/config.json
chaiml-elo-alignment-run-3-v28-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/chaiml-elo-alignment-run-3-v28_reward/special_tokens_map.json
chaiml-elo-alignment-run-3-v28-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/chaiml-elo-alignment-run-3-v28_reward/merges.txt
chaiml-elo-alignment-run-3-v28-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/chaiml-elo-alignment-run-3-v28_reward/vocab.json
chaiml-elo-alignment-run-3-v28-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/chaiml-elo-alignment-run-3-v28_reward/tokenizer.json
chaiml-elo-alignment-run-3-v28-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/chaiml-elo-alignment-run-3-v28_reward/reward.tensors
Job chaiml-elo-alignment-run-3-v28-mkmlizer completed after 116.21s with status: succeeded
Stopping job with name chaiml-elo-alignment-run-3-v28-mkmlizer
Pipeline stage MKMLizer completed in 117.06s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.08s
Running pipeline stage ISVCDeployer
Creating inference service chaiml-elo-alignment-run-3-v28
Waiting for inference service chaiml-elo-alignment-run-3-v28 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service chaiml-elo-alignment-run-3-v28 ready after 181.15974020957947s
Pipeline stage ISVCDeployer completed in 182.63s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2972867488861084s
Received healthy response to inference request in 1.3846101760864258s
Received healthy response to inference request in 1.3956232070922852s
Received healthy response to inference request in 1.3921658992767334s
Received healthy response to inference request in 1.4025652408599854s
5 requests
0 failed requests
5th percentile: 1.3861213207244873
10th percentile: 1.387632465362549
20th percentile: 1.3906547546386718
30th percentile: 1.3928573608398438
40th percentile: 1.3942402839660644
50th percentile: 1.3956232070922852
60th percentile: 1.3984000205993652
70th percentile: 1.4011768341064452
80th percentile: 1.5815095424652101
90th percentile: 1.9393981456756593
95th percentile: 2.1183424472808836
99th percentile: 2.2614978885650636
mean time: 1.5744502544403076
Pipeline stage StressChecker completed in 8.53s
chaiml-elo-alignment-run-3_v28 status is now deployed due to DeploymentManager action
chaiml-elo-alignment-run-3_v28 status is now inactive due to auto deactivation removed underperforming models
chaiml-elo-alignment-run-3_v28 status is now torndown due to DeploymentManager action