chaiml-elo-alignment-run-3

submission_id: chaiml-elo-alignment-run-3_v15
developer_uid: chai_backend_admin
best_of: 2
celo_rating: 1256.54
display_name: chaiml-elo-alignment-run-3_v15
family_friendly_score: 0.0
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': True}
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': ['<|im_end|>', '<|im_start|>', '<START>', '<|eot_id|>', '<END>', '#', '####'], 'max_input_tokens': 1500, 'best_of': 2, 'max_output_tokens': 256, 'reward_max_token_input': 256}
ineligible_reason: max_output_tokens!=64
is_internal_developer: True
language_model: ChaiML/elo_alignment_run_3
max_input_tokens: 1500
max_output_tokens: 256
model_architecture: LlamaForCausalLM
model_group: ChaiML/elo_alignment_run
model_name: chaiml-elo-alignment-run-3_v15
model_num_parameters: 8030261248.0
model_repo: ChaiML/elo_alignment_run_3
model_size: 8B
num_battles: 9302
num_wins: 5552
ranking_group: single
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
status: torndown
submission_type: basic
timestamp: 2024-07-25T03:53:44+00:00
us_pacific_date: 2024-07-24
win_ratio: 0.5968608901311546
Download Preference Data
Resubmit model
Running pipeline stage MKMLizer
Starting job with name chaiml-elo-alignment-run-3-v15-mkmlizer
Waiting for job on chaiml-elo-alignment-run-3-v15-mkmlizer to finish
chaiml-elo-alignment-run-3-v15-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-elo-alignment-run-3-v15-mkmlizer: ║     _____            __           __                                ║
chaiml-elo-alignment-run-3-v15-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-elo-alignment-run-3-v15-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-elo-alignment-run-3-v15-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-elo-alignment-run-3-v15-mkmlizer: ║       /___/                                                         ║
chaiml-elo-alignment-run-3-v15-mkmlizer: ║                                                                     ║
chaiml-elo-alignment-run-3-v15-mkmlizer: ║  Version: 0.9.6                                                     ║
chaiml-elo-alignment-run-3-v15-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-elo-alignment-run-3-v15-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-elo-alignment-run-3-v15-mkmlizer: ║                                                                     ║
chaiml-elo-alignment-run-3-v15-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-elo-alignment-run-3-v15-mkmlizer: ║  belonging to:                                                      ║
chaiml-elo-alignment-run-3-v15-mkmlizer: ║                                                                     ║
chaiml-elo-alignment-run-3-v15-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-elo-alignment-run-3-v15-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-elo-alignment-run-3-v15-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
chaiml-elo-alignment-run-3-v15-mkmlizer: ║                                                                     ║
chaiml-elo-alignment-run-3-v15-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission neversleep-lumimaid-mist_1884_v1: ('http://neversleep-lumimaid-mist-1884-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Failed to get response for submission neversleep-lumimaid-mist_7954_v1: ('http://neversleep-lumimaid-mist-7954-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Failed to get response for submission neversleep-lumimaid-mist_1884_v1: ('http://neversleep-lumimaid-mist-1884-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
chaiml-elo-alignment-run-3-v15-mkmlizer: Downloaded to shared memory in 38.405s
chaiml-elo-alignment-run-3-v15-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp7fb8msu_, device:0
chaiml-elo-alignment-run-3-v15-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission blend_dunet_2024-07-19: ('http://undi95-meta-llama-3-70b-6209-v18-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '{"error":"TypeError : SamplingParameters.__init__() got an unexpected keyword argument \'reward_max_tokens\'"}')
chaiml-elo-alignment-run-3-v15-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:11, 24.57it/s]
Loading 0:   4%|▍         | 12/291 [00:00<00:08, 33.61it/s]
Loading 0:   5%|▌         | 16/291 [00:00<00:08, 31.32it/s]
Loading 0:   7%|▋         | 21/291 [00:00<00:07, 34.55it/s]
Loading 0:   9%|▊         | 25/291 [00:00<00:08, 32.16it/s]
Loading 0:  11%|█         | 31/291 [00:00<00:06, 38.44it/s]
Loading 0:  12%|█▏        | 36/291 [00:01<00:11, 21.41it/s]
Loading 0:  14%|█▍        | 41/291 [00:01<00:10, 23.28it/s]
Loading 0:  16%|█▋        | 48/291 [00:01<00:08, 29.86it/s]
Loading 0:  18%|█▊        | 52/291 [00:01<00:08, 29.55it/s]
Loading 0:  20%|█▉        | 57/291 [00:01<00:07, 32.47it/s]
Loading 0:  21%|██        | 61/291 [00:02<00:07, 31.41it/s]
Loading 0:  23%|██▎       | 66/291 [00:02<00:06, 33.37it/s]
Loading 0:  24%|██▍       | 70/291 [00:02<00:06, 32.24it/s]
Loading 0:  25%|██▌       | 74/291 [00:02<00:06, 32.76it/s]
Loading 0:  27%|██▋       | 78/291 [00:02<00:06, 32.39it/s]
Loading 0:  28%|██▊       | 82/291 [00:02<00:09, 22.00it/s]
Loading 0:  29%|██▉       | 85/291 [00:02<00:08, 23.04it/s]
Loading 0:  31%|███       | 90/291 [00:03<00:07, 27.12it/s]
Loading 0:  32%|███▏      | 94/291 [00:03<00:07, 27.83it/s]
Loading 0:  34%|███▍      | 99/291 [00:03<00:06, 31.74it/s]
Loading 0:  35%|███▌      | 103/291 [00:03<00:06, 31.01it/s]
Loading 0:  37%|███▋      | 108/291 [00:03<00:05, 34.02it/s]
Loading 0:  38%|███▊      | 112/291 [00:03<00:05, 32.05it/s]
Loading 0:  40%|███▉      | 116/291 [00:03<00:05, 31.33it/s]
Loading 0:  42%|████▏     | 122/291 [00:04<00:04, 36.00it/s]
Loading 0:  44%|████▎     | 127/291 [00:04<00:04, 34.02it/s]
Loading 0:  46%|████▌     | 133/291 [00:04<00:05, 28.82it/s]
Loading 0:  47%|████▋     | 137/291 [00:04<00:05, 28.84it/s]
Loading 0:  48%|████▊     | 141/291 [00:04<00:05, 27.20it/s]
Loading 0:  51%|█████     | 147/291 [00:04<00:04, 32.16it/s]
Loading 0:  52%|█████▏    | 151/291 [00:05<00:04, 30.85it/s]
Loading 0:  54%|█████▎    | 156/291 [00:05<00:04, 33.22it/s]
Loading 0:  55%|█████▍    | 160/291 [00:05<00:04, 32.15it/s]
Loading 0:  57%|█████▋    | 165/291 [00:05<00:03, 34.73it/s]
Loading 0:  58%|█████▊    | 169/291 [00:05<00:03, 31.95it/s]
Loading 0:  60%|█████▉    | 174/291 [00:05<00:03, 33.82it/s]
Loading 0:  61%|██████    | 178/291 [00:05<00:03, 32.51it/s]
Loading 0:  63%|██████▎   | 184/291 [00:05<00:02, 39.02it/s]
Loading 0:  65%|██████▍   | 189/291 [00:06<00:04, 23.44it/s]
Loading 0:  67%|██████▋   | 194/291 [00:06<00:03, 24.86it/s]
Loading 0:  69%|██████▉   | 201/291 [00:06<00:02, 31.66it/s]
Loading 0:  70%|███████   | 205/291 [00:06<00:02, 31.39it/s]
Loading 0:  72%|███████▏  | 210/291 [00:06<00:02, 34.32it/s]
Loading 0:  74%|███████▎  | 214/291 [00:07<00:02, 32.82it/s]
Loading 0:  75%|███████▌  | 219/291 [00:07<00:02, 35.30it/s]
Loading 0:  77%|███████▋  | 223/291 [00:07<00:02, 33.50it/s]
Loading 0:  78%|███████▊  | 227/291 [00:07<00:01, 33.52it/s]
Loading 0:  79%|███████▉  | 231/291 [00:07<00:01, 33.41it/s]
Loading 0:  81%|████████  | 235/291 [00:07<00:02, 24.49it/s]
Loading 0:  82%|████████▏ | 239/291 [00:07<00:02, 23.97it/s]
Loading 0:  85%|████████▍ | 246/291 [00:08<00:01, 31.01it/s]
Loading 0:  86%|████████▌ | 250/291 [00:08<00:01, 29.45it/s]
Loading 0:  88%|████████▊ | 255/291 [00:08<00:01, 30.93it/s]
Loading 0:  89%|████████▉ | 259/291 [00:08<00:01, 29.62it/s]
Loading 0:  91%|█████████ | 264/291 [00:08<00:00, 31.53it/s]
Loading 0:  92%|█████████▏| 268/291 [00:08<00:00, 30.80it/s]
Loading 0:  94%|█████████▍| 273/291 [00:08<00:00, 33.51it/s]
Loading 0:  95%|█████████▌| 277/291 [00:09<00:00, 32.29it/s]
Loading 0:  97%|█████████▋| 281/291 [00:09<00:00, 32.59it/s]
Loading 0:  98%|█████████▊| 286/291 [00:14<00:01,  2.50it/s]
Loading 0:  99%|█████████▉| 289/291 [00:15<00:00,  3.11it/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-v15-mkmlizer: quantized model in 29.968s
chaiml-elo-alignment-run-3-v15-mkmlizer: Processed model ChaiML/elo_alignment_run_3 in 68.373s
chaiml-elo-alignment-run-3-v15-mkmlizer: creating bucket guanaco-mkml-models
chaiml-elo-alignment-run-3-v15-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-elo-alignment-run-3-v15-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v15
chaiml-elo-alignment-run-3-v15-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v15/special_tokens_map.json
chaiml-elo-alignment-run-3-v15-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v15/config.json
chaiml-elo-alignment-run-3-v15-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v15/tokenizer_config.json
chaiml-elo-alignment-run-3-v15-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v15/tokenizer.json
chaiml-elo-alignment-run-3-v15-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v15/flywheel_model.0.safetensors
chaiml-elo-alignment-run-3-v15-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
chaiml-elo-alignment-run-3-v15-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:950: 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-v15-mkmlizer:   warnings.warn(
chaiml-elo-alignment-run-3-v15-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:778: 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-v15-mkmlizer:   warnings.warn(
chaiml-elo-alignment-run-3-v15-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-v15-mkmlizer:   warnings.warn(
chaiml-elo-alignment-run-3-v15-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
chaiml-elo-alignment-run-3-v15-mkmlizer: Saving duration: 0.327s
chaiml-elo-alignment-run-3-v15-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 5.573s
chaiml-elo-alignment-run-3-v15-mkmlizer: creating bucket guanaco-reward-models
chaiml-elo-alignment-run-3-v15-mkmlizer: Bucket 's3://guanaco-reward-models/' created
chaiml-elo-alignment-run-3-v15-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/chaiml-elo-alignment-run-3-v15_reward
chaiml-elo-alignment-run-3-v15-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/chaiml-elo-alignment-run-3-v15_reward/config.json
chaiml-elo-alignment-run-3-v15-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/chaiml-elo-alignment-run-3-v15_reward/special_tokens_map.json
chaiml-elo-alignment-run-3-v15-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/chaiml-elo-alignment-run-3-v15_reward/tokenizer_config.json
chaiml-elo-alignment-run-3-v15-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/chaiml-elo-alignment-run-3-v15_reward/merges.txt
chaiml-elo-alignment-run-3-v15-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/chaiml-elo-alignment-run-3-v15_reward/vocab.json
chaiml-elo-alignment-run-3-v15-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/chaiml-elo-alignment-run-3-v15_reward/tokenizer.json
chaiml-elo-alignment-run-3-v15-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/chaiml-elo-alignment-run-3-v15_reward/reward.tensors
Job chaiml-elo-alignment-run-3-v15-mkmlizer completed after 105.35s with status: succeeded
Stopping job with name chaiml-elo-alignment-run-3-v15-mkmlizer
Pipeline stage MKMLizer completed in 106.48s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service chaiml-elo-alignment-run-3-v15
Waiting for inference service chaiml-elo-alignment-run-3-v15 to be ready
Failed to get response for submission neversleep-lumimaid-mist_1893_v1: ('http://neversleep-lumimaid-mist-1893-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Failed to get response for submission neversleep-lumimaid-mist_1884_v1: ('http://neversleep-lumimaid-mist-1884-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Failed to get response for submission neversleep-lumimaid-mist_1884_v1: ('http://neversleep-lumimaid-mist-1884-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Failed to get response for submission neversleep-lumimaid-mist_1884_v1: ('http://neversleep-lumimaid-mist-1884-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Failed to get response for submission neversleep-lumimaid-mist_1893_v1: ('http://neversleep-lumimaid-mist-1893-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Failed to get response for submission neversleep-lumimaid-mist_1884_v1: ('http://neversleep-lumimaid-mist-1884-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Failed to get response for submission neversleep-lumimaid-mist_1893_v1: ('http://neversleep-lumimaid-mist-1893-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Inference service chaiml-elo-alignment-run-3-v15 ready after 60.412537813186646s
Pipeline stage ISVCDeployer completed in 61.67s
Running pipeline stage StressChecker
Received healthy response to inference request in 4.594767808914185s
Received healthy response to inference request in 3.741985321044922s
Received healthy response to inference request in 3.607902765274048s
Received healthy response to inference request in 3.7401773929595947s
Received healthy response to inference request in 3.638179302215576s
5 requests
0 failed requests
5th percentile: 3.6139580726623537
10th percentile: 3.620013380050659
20th percentile: 3.6321239948272703
30th percentile: 3.6585789203643797
40th percentile: 3.699378156661987
50th percentile: 3.7401773929595947
60th percentile: 3.7409005641937254
70th percentile: 3.7416237354278565
80th percentile: 3.9125418186187746
90th percentile: 4.253654813766479
95th percentile: 4.424211311340332
99th percentile: 4.560656509399414
mean time: 3.864602518081665
Pipeline stage StressChecker completed in 19.96s
chaiml-elo-alignment-run-3_v15 status is now deployed due to DeploymentManager action
chaiml-elo-alignment-run-3_v15 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of chaiml-elo-alignment-run-3_v15
Running pipeline stage ISVCDeleter
Checking if service chaiml-elo-alignment-run-3-v15 is running
Tearing down inference service chaiml-elo-alignment-run-3-v15
Service chaiml-elo-alignment-run-3-v15 has been torndown
Pipeline stage ISVCDeleter completed in 5.03s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key chaiml-elo-alignment-run-3-v15/config.json from bucket guanaco-mkml-models
Deleting key chaiml-elo-alignment-run-3-v15/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key chaiml-elo-alignment-run-3-v15/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key chaiml-elo-alignment-run-3-v15/tokenizer.json from bucket guanaco-mkml-models
Deleting key chaiml-elo-alignment-run-3-v15/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key chaiml-elo-alignment-run-3-v15_reward/config.json from bucket guanaco-reward-models
Deleting key chaiml-elo-alignment-run-3-v15_reward/merges.txt from bucket guanaco-reward-models
Deleting key chaiml-elo-alignment-run-3-v15_reward/reward.tensors from bucket guanaco-reward-models
Deleting key chaiml-elo-alignment-run-3-v15_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key chaiml-elo-alignment-run-3-v15_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key chaiml-elo-alignment-run-3-v15_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key chaiml-elo-alignment-run-3-v15_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.50s
chaiml-elo-alignment-run-3_v15 status is now torndown due to DeploymentManager action