submission_id: chaiml-elo-alignment-run-3_v3
developer_uid: zonemercy
status: inactive
model_repo: ChaiML/elo_alignment_run_3
reward_repo: ChaiML/gpt2_xl_pairwise_89m_step_347634
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}
formatter: {'memory_template': "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\n{bot_name}'s Persona: {memory}\n\n", 'prompt_template': '{prompt}<|eot_id|>', 'bot_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}: {message}<|eot_id|>', 'user_template': '<|start_header_id|>user<|end_header_id|>\n\n{user_name}: {message}<|eot_id|>', 'response_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{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: 2024-07-12T16:11:11+00:00
model_name: chaiml-elo-alignment-run-3_v3
model_group: ChaiML/elo_alignment_run
num_battles: 11314
num_wins: 7069
celo_rating: 1265.75
alignment_score: None
alignment_samples: 0
propriety_score: 0.7334633800319206
propriety_total_count: 5639.0
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: 0.6248011313417006
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name chaiml-elo-alignment-run-3-v3-mkmlizer
Waiting for job on chaiml-elo-alignment-run-3-v3-mkmlizer to finish
chaiml-elo-alignment-run-3-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-elo-alignment-run-3-v3-mkmlizer: ║ _____ __ __ ║
chaiml-elo-alignment-run-3-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-elo-alignment-run-3-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-elo-alignment-run-3-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-elo-alignment-run-3-v3-mkmlizer: ║ /___/ ║
chaiml-elo-alignment-run-3-v3-mkmlizer: ║ ║
chaiml-elo-alignment-run-3-v3-mkmlizer: ║ Version: 0.8.14 ║
chaiml-elo-alignment-run-3-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-elo-alignment-run-3-v3-mkmlizer: ║ https://mk1.ai ║
chaiml-elo-alignment-run-3-v3-mkmlizer: ║ ║
chaiml-elo-alignment-run-3-v3-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-elo-alignment-run-3-v3-mkmlizer: ║ belonging to: ║
chaiml-elo-alignment-run-3-v3-mkmlizer: ║ ║
chaiml-elo-alignment-run-3-v3-mkmlizer: ║ Chai Research Corp. ║
chaiml-elo-alignment-run-3-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-elo-alignment-run-3-v3-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
chaiml-elo-alignment-run-3-v3-mkmlizer: ║ ║
chaiml-elo-alignment-run-3-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-elo-alignment-run-3-v3-mkmlizer: Downloaded to shared memory in 46.577s
chaiml-elo-alignment-run-3-v3-mkmlizer: quantizing model to /dev/shm/model_cache
chaiml-elo-alignment-run-3-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-elo-alignment-run-3-v3-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 2%|▏ | 5/291 [00:00<00:06, 44.52it/s] Loading 0: 5%|▍ | 14/291 [00:00<00:04, 58.50it/s] Loading 0: 8%|▊ | 22/291 [00:00<00:04, 65.16it/s] Loading 0: 11%|█▏ | 33/291 [00:00<00:07, 34.94it/s] Loading 0: 13%|█▎ | 38/291 [00:00<00:06, 37.13it/s] Loading 0: 15%|█▍ | 43/291 [00:01<00:06, 38.93it/s] Loading 0: 17%|█▋ | 50/291 [00:01<00:05, 42.93it/s] Loading 0: 20%|██ | 59/291 [00:01<00:04, 49.63it/s] Loading 0: 23%|██▎ | 68/291 [00:01<00:04, 54.52it/s] Loading 0: 26%|██▌ | 76/291 [00:01<00:03, 60.13it/s] Loading 0: 29%|██▊ | 83/291 [00:02<00:06, 32.11it/s] Loading 0: 32%|███▏ | 92/291 [00:02<00:05, 39.12it/s] Loading 0: 35%|███▍ | 101/291 [00:02<00:04, 45.09it/s] Loading 0: 37%|███▋ | 109/291 [00:02<00:03, 51.68it/s] Loading 0: 40%|████ | 117/291 [00:02<00:03, 57.52it/s] Loading 0: 43%|████▎ | 126/291 [00:02<00:02, 60.20it/s] Loading 0: 46%|████▌ | 133/291 [00:03<00:04, 35.33it/s] Loading 0: 48%|████▊ | 139/291 [00:03<00:04, 36.39it/s] Loading 0: 51%|█████ | 148/291 [00:03<00:03, 43.17it/s] Loading 0: 54%|█████▎ | 156/291 [00:03<00:02, 49.30it/s] Loading 0: 56%|█████▌ | 163/291 [00:03<00:02, 52.71it/s] Loading 0: 58%|█████▊ | 170/291 [00:03<00:02, 52.25it/s] Loading 0: 60%|██████ | 176/291 [00:03<00:02, 49.83it/s] Loading 0: 64%|██████▍ | 186/291 [00:04<00:03, 34.13it/s] Loading 0: 66%|██████▌ | 191/291 [00:04<00:02, 36.09it/s] Loading 0: 67%|██████▋ | 196/291 [00:04<00:02, 37.91it/s] Loading 0: 70%|██████▉ | 203/291 [00:04<00:02, 41.73it/s] Loading 0: 73%|███████▎ | 211/291 [00:04<00:01, 49.75it/s] Loading 0: 76%|███████▌ | 220/291 [00:04<00:01, 54.94it/s] Loading 0: 78%|███████▊ | 228/291 [00:04<00:01, 56.36it/s] Loading 0: 81%|████████ | 235/291 [00:05<00:01, 34.44it/s] Loading 0: 82%|████████▏ | 240/291 [00:05<00:01, 36.60it/s] Loading 0: 85%|████████▌ | 248/291 [00:05<00:01, 42.20it/s] Loading 0: 88%|████████▊ | 256/291 [00:05<00:00, 49.79it/s] Loading 0: 91%|█████████ | 265/291 [00:05<00:00, 54.57it/s] Loading 0: 94%|█████████▍| 274/291 [00:06<00:00, 58.02it/s] Loading 0: 97%|█████████▋| 282/291 [00:06<00:00, 62.87it/s] Loading 0: 99%|█████████▉| 289/291 [00:13<00:00, 3.57it/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-v3-mkmlizer: quantized model in 31.569s
chaiml-elo-alignment-run-3-v3-mkmlizer: Processed model ChaiML/elo_alignment_run_3 in 78.146s
chaiml-elo-alignment-run-3-v3-mkmlizer: creating bucket guanaco-mkml-models
chaiml-elo-alignment-run-3-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-elo-alignment-run-3-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v3
chaiml-elo-alignment-run-3-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v3/tokenizer_config.json
chaiml-elo-alignment-run-3-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v3/config.json
chaiml-elo-alignment-run-3-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v3/special_tokens_map.json
chaiml-elo-alignment-run-3-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v3/tokenizer.json
chaiml-elo-alignment-run-3-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v3/flywheel_model.0.safetensors
chaiml-elo-alignment-run-3-v3-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
chaiml-elo-alignment-run-3-v3-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-v3-mkmlizer: warnings.warn(
chaiml-elo-alignment-run-3-v3-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-v3-mkmlizer: warnings.warn(
chaiml-elo-alignment-run-3-v3-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-v3-mkmlizer: warnings.warn(
chaiml-elo-alignment-run-3-v3-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-v3-mkmlizer: warnings.warn(
chaiml-elo-alignment-run-3-v3-mkmlizer: Downloading shards: 0%| | 0/2 [00:00<?, ?it/s] Downloading shards: 50%|█████ | 1/2 [00:09<00:09, 9.60s/it] Downloading shards: 100%|██████████| 2/2 [00:13<00:00, 6.50s/it] Downloading shards: 100%|██████████| 2/2 [00:13<00:00, 6.97s/it]
chaiml-elo-alignment-run-3-v3-mkmlizer: Loading checkpoint shards: 0%| | 0/2 [00:00<?, ?it/s] Loading checkpoint shards: 50%|█████ | 1/2 [00:00<00:00, 1.65it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 2.69it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 2.46it/s]
chaiml-elo-alignment-run-3-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
chaiml-elo-alignment-run-3-v3-mkmlizer: Saving duration: 2.201s
chaiml-elo-alignment-run-3-v3-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 18.519s
chaiml-elo-alignment-run-3-v3-mkmlizer: creating bucket guanaco-reward-models
chaiml-elo-alignment-run-3-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/chaiml-elo-alignment-run-3-v3_reward/reward.tensors
Job chaiml-elo-alignment-run-3-v3-mkmlizer completed after 134.7s with status: succeeded
Stopping job with name chaiml-elo-alignment-run-3-v3-mkmlizer
Pipeline stage MKMLizer completed in 135.73s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service chaiml-elo-alignment-run-3-v3
Waiting for inference service chaiml-elo-alignment-run-3-v3 to be ready
Inference service chaiml-elo-alignment-run-3-v3 ready after 50.27395677566528s
Pipeline stage ISVCDeployer completed in 56.90s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.31113862991333s
Received healthy response to inference request in 1.562394142150879s
Received healthy response to inference request in 1.5441372394561768s
Received healthy response to inference request in 1.5141808986663818s
Received healthy response to inference request in 1.5823614597320557s
5 requests
0 failed requests
5th percentile: 1.5201721668243409
10th percentile: 1.5261634349823
20th percentile: 1.5381459712982177
30th percentile: 1.5477886199951172
40th percentile: 1.555091381072998
50th percentile: 1.562394142150879
60th percentile: 1.5703810691833495
70th percentile: 1.5783679962158204
80th percentile: 1.7281168937683107
90th percentile: 2.0196277618408205
95th percentile: 2.165383195877075
99th percentile: 2.281987543106079
mean time: 1.7028424739837646
Pipeline stage StressChecker completed in 9.20s
chaiml-elo-alignment-run-3_v3 status is now deployed due to DeploymentManager action
chaiml-elo-alignment-run-3_v3 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics