submission_id: chaiml-elo-alignment-run-3_v6
developer_uid: zonemercy
status: inactive
model_repo: ChaiML/elo_alignment_run_3
reward_repo: ChaiML/gpt2_xl_pairwise_89m_step_347634
generation_params: {'temperature': 1.0, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|eot_id|>'], 'max_input_tokens': 512, 'best_of': 16, '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: {'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}
timestamp: 2024-07-13T05:30:08+00:00
model_name: chaiml-elo-alignment-run-3_v3
model_group: ChaiML/elo_alignment_run
num_battles: 52400
num_wins: 29755
celo_rating: 1269.6
alignment_score: None
alignment_samples: 0
propriety_score: 0.7264264781934149
propriety_total_count: 5801.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: chaiml-elo-alignment-run-3_v3
ineligible_reason: None
language_model: ChaiML/elo_alignment_run_3
model_size: 8B
reward_model: ChaiML/gpt2_xl_pairwise_89m_step_347634
us_pacific_date: 2024-07-12
win_ratio: 0.5678435114503817
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name chaiml-elo-alignment-run-3-v6-mkmlizer
Waiting for job on chaiml-elo-alignment-run-3-v6-mkmlizer to finish
chaiml-elo-alignment-run-3-v6-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-elo-alignment-run-3-v6-mkmlizer: ║ _____ __ __ ║
chaiml-elo-alignment-run-3-v6-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-elo-alignment-run-3-v6-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-elo-alignment-run-3-v6-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-elo-alignment-run-3-v6-mkmlizer: ║ /___/ ║
chaiml-elo-alignment-run-3-v6-mkmlizer: ║ ║
chaiml-elo-alignment-run-3-v6-mkmlizer: ║ Version: 0.8.14 ║
chaiml-elo-alignment-run-3-v6-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-elo-alignment-run-3-v6-mkmlizer: ║ https://mk1.ai ║
chaiml-elo-alignment-run-3-v6-mkmlizer: ║ ║
chaiml-elo-alignment-run-3-v6-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-elo-alignment-run-3-v6-mkmlizer: ║ belonging to: ║
chaiml-elo-alignment-run-3-v6-mkmlizer: ║ ║
chaiml-elo-alignment-run-3-v6-mkmlizer: ║ Chai Research Corp. ║
chaiml-elo-alignment-run-3-v6-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-elo-alignment-run-3-v6-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
chaiml-elo-alignment-run-3-v6-mkmlizer: ║ ║
chaiml-elo-alignment-run-3-v6-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-elo-alignment-run-3-v6-mkmlizer: Downloaded to shared memory in 47.811s
chaiml-elo-alignment-run-3-v6-mkmlizer: quantizing model to /dev/shm/model_cache
chaiml-elo-alignment-run-3-v6-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-elo-alignment-run-3-v6-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 2%|▏ | 5/291 [00:00<00:06, 43.12it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:04, 62.82it/s] Loading 0: 7%|▋ | 21/291 [00:00<00:03, 69.81it/s] Loading 0: 10%|▉ | 29/291 [00:00<00:03, 72.33it/s] Loading 0: 13%|█▎ | 37/291 [00:00<00:08, 29.66it/s] Loading 0: 15%|█▍ | 43/291 [00:01<00:07, 33.83it/s] Loading 0: 17%|█▋ | 50/291 [00:01<00:06, 38.21it/s] Loading 0: 20%|█▉ | 58/291 [00:01<00:05, 46.42it/s] Loading 0: 23%|██▎ | 66/291 [00:01<00:04, 53.42it/s] Loading 0: 25%|██▌ | 73/291 [00:01<00:03, 56.96it/s] Loading 0: 27%|██▋ | 80/291 [00:01<00:06, 30.72it/s] Loading 0: 30%|██▉ | 86/291 [00:02<00:06, 34.10it/s] Loading 0: 32%|███▏ | 92/291 [00:02<00:05, 37.36it/s] Loading 0: 35%|███▍ | 101/291 [00:02<00:04, 44.65it/s] Loading 0: 38%|███▊ | 110/291 [00:02<00:03, 50.51it/s] Loading 0: 42%|████▏ | 122/291 [00:02<00:02, 62.16it/s] Loading 0: 44%|████▍ | 129/291 [00:02<00:02, 61.18it/s] Loading 0: 47%|████▋ | 136/291 [00:03<00:04, 33.87it/s] Loading 0: 49%|████▉ | 142/291 [00:03<00:04, 36.86it/s] Loading 0: 51%|█████ | 149/291 [00:03<00:03, 40.37it/s] Loading 0: 54%|█████▍ | 157/291 [00:03<00:02, 47.78it/s] Loading 0: 57%|█████▋ | 166/291 [00:03<00:02, 52.94it/s] Loading 0: 60%|█████▉ | 174/291 [00:03<00:01, 58.93it/s] Loading 0: 63%|██████▎ | 182/291 [00:03<00:01, 63.99it/s] Loading 0: 65%|██████▌ | 190/291 [00:04<00:02, 33.80it/s] Loading 0: 67%|██████▋ | 196/291 [00:04<00:02, 37.34it/s] Loading 0: 70%|██████▉ | 203/291 [00:04<00:02, 41.03it/s] Loading 0: 73%|███████▎ | 212/291 [00:04<00:01, 47.53it/s] Loading 0: 76%|███████▌ | 221/291 [00:04<00:01, 52.42it/s] Loading 0: 79%|███████▊ | 229/291 [00:05<00:01, 58.17it/s] Loading 0: 81%|████████ | 236/291 [00:05<00:01, 35.52it/s] Loading 0: 83%|████████▎ | 242/291 [00:05<00:01, 37.99it/s] Loading 0: 85%|████████▌ | 248/291 [00:05<00:01, 40.61it/s] Loading 0: 88%|████████▊ | 256/291 [00:05<00:00, 48.51it/s] Loading 0: 91%|█████████ | 264/291 [00:05<00:00, 55.41it/s] Loading 0: 94%|█████████▍| 273/291 [00:05<00:00, 59.16it/s] Loading 0: 97%|█████████▋| 281/291 [00:06<00:00, 59.63it/s] Loading 0: 99%|█████████▉| 288/291 [00:13<00:00, 3.46it/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-v6-mkmlizer: quantized model in 32.154s
chaiml-elo-alignment-run-3-v6-mkmlizer: Processed model ChaiML/elo_alignment_run_3 in 79.965s
chaiml-elo-alignment-run-3-v6-mkmlizer: creating bucket guanaco-mkml-models
chaiml-elo-alignment-run-3-v6-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-elo-alignment-run-3-v6-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v6
chaiml-elo-alignment-run-3-v6-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v6/config.json
chaiml-elo-alignment-run-3-v6-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v6/special_tokens_map.json
chaiml-elo-alignment-run-3-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v6/tokenizer_config.json
chaiml-elo-alignment-run-3-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v6/tokenizer.json
chaiml-elo-alignment-run-3-v6-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v6/flywheel_model.0.safetensors
chaiml-elo-alignment-run-3-v6-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
chaiml-elo-alignment-run-3-v6-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-v6-mkmlizer: warnings.warn(
chaiml-elo-alignment-run-3-v6-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-v6-mkmlizer: warnings.warn(
chaiml-elo-alignment-run-3-v6-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-v6-mkmlizer: warnings.warn(
chaiml-elo-alignment-run-3-v6-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py:468: 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-v6-mkmlizer: warnings.warn(
chaiml-elo-alignment-run-3-v6-mkmlizer: Downloading shards: 0%| | 0/2 [00:00<?, ?it/s] Downloading shards: 50%|█████ | 1/2 [00:06<00:06, 6.74s/it] Downloading shards: 100%|██████████| 2/2 [00:09<00:00, 4.12s/it] Downloading shards: 100%|██████████| 2/2 [00:09<00:00, 4.51s/it]
chaiml-elo-alignment-run-3-v6-mkmlizer: Loading checkpoint shards: 0%| | 0/2 [00:00<?, ?it/s] Loading checkpoint shards: 50%|█████ | 1/2 [00:01<00:01, 1.22s/it] Loading checkpoint shards: 100%|██████████| 2/2 [00:01<00:00, 1.61it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:01<00:00, 1.41it/s]
chaiml-elo-alignment-run-3-v6-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
chaiml-elo-alignment-run-3-v6-mkmlizer: Saving duration: 2.193s
chaiml-elo-alignment-run-3-v6-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 15.201s
chaiml-elo-alignment-run-3-v6-mkmlizer: creating bucket guanaco-reward-models
chaiml-elo-alignment-run-3-v6-mkmlizer: Bucket 's3://guanaco-reward-models/' created
chaiml-elo-alignment-run-3-v6-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/chaiml-elo-alignment-run-3-v6_reward
chaiml-elo-alignment-run-3-v6-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/chaiml-elo-alignment-run-3-v6_reward/config.json
chaiml-elo-alignment-run-3-v6-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/chaiml-elo-alignment-run-3-v6_reward/tokenizer_config.json
chaiml-elo-alignment-run-3-v6-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/chaiml-elo-alignment-run-3-v6_reward/special_tokens_map.json
chaiml-elo-alignment-run-3-v6-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/chaiml-elo-alignment-run-3-v6_reward/vocab.json
chaiml-elo-alignment-run-3-v6-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/chaiml-elo-alignment-run-3-v6_reward/tokenizer.json
chaiml-elo-alignment-run-3-v6-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/chaiml-elo-alignment-run-3-v6_reward/merges.txt
chaiml-elo-alignment-run-3-v6-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/chaiml-elo-alignment-run-3-v6_reward/reward.tensors
Job chaiml-elo-alignment-run-3-v6-mkmlizer completed after 124.6s with status: succeeded
Stopping job with name chaiml-elo-alignment-run-3-v6-mkmlizer
Pipeline stage MKMLizer completed in 125.53s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.08s
Running pipeline stage ISVCDeployer
Creating inference service chaiml-elo-alignment-run-3-v6
Waiting for inference service chaiml-elo-alignment-run-3-v6 to be ready
Inference service chaiml-elo-alignment-run-3-v6 ready after 50.21882367134094s
Pipeline stage ISVCDeployer completed in 57.31s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.532345771789551s
Received healthy response to inference request in 1.4898769855499268s
Received healthy response to inference request in 1.4900388717651367s
Received healthy response to inference request in 3.280768632888794s
Received healthy response to inference request in 1.4889328479766846s
5 requests
0 failed requests
5th percentile: 1.489121675491333
10th percentile: 1.4893105030059814
20th percentile: 1.4896881580352783
30th percentile: 1.4899093627929687
40th percentile: 1.4899741172790528
50th percentile: 1.4900388717651367
60th percentile: 2.2063307762145996
70th percentile: 2.922622680664062
80th percentile: 3.331084060668945
90th percentile: 3.431714916229248
95th percentile: 3.4820303440093996
99th percentile: 3.5222826862335204
mean time: 2.2563926219940185
Pipeline stage StressChecker completed in 11.87s
chaiml-elo-alignment-run-3_v6 status is now deployed due to DeploymentManager action
chaiml-elo-alignment-run-3_v6 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics