submission_id: chaiml-elo-alignment-run-3_v13
developer_uid: chai_backend_admin
best_of: 1
celo_rating: 1222.6
display_name: chaiml-elo-alignment-run-3_v13
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': ['<|eot_id|>'], 'max_input_tokens': 1500, 'best_of': 1, '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_v13
model_num_parameters: 8030261248.0
model_repo: ChaiML/elo_alignment_run_3
model_size: 8B
num_battles: 7866
num_wins: 4340
ranking_group: single
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
status: torndown
submission_type: basic
timestamp: 2024-07-25T03:34:43+00:00
us_pacific_date: 2024-07-24
win_ratio: 0.5517416730231376
Download Preference Data
Resubmit model
Running pipeline stage MKMLizer
Starting job with name chaiml-elo-alignment-run-3-v13-mkmlizer
Waiting for job on chaiml-elo-alignment-run-3-v13-mkmlizer to finish
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')
chaiml-elo-alignment-run-3-v13-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-elo-alignment-run-3-v13-mkmlizer: ║ _____ __ __ ║
chaiml-elo-alignment-run-3-v13-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-elo-alignment-run-3-v13-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-elo-alignment-run-3-v13-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-elo-alignment-run-3-v13-mkmlizer: ║ /___/ ║
chaiml-elo-alignment-run-3-v13-mkmlizer: ║ ║
chaiml-elo-alignment-run-3-v13-mkmlizer: ║ Version: 0.9.6 ║
chaiml-elo-alignment-run-3-v13-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-elo-alignment-run-3-v13-mkmlizer: ║ https://mk1.ai ║
chaiml-elo-alignment-run-3-v13-mkmlizer: ║ ║
chaiml-elo-alignment-run-3-v13-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-elo-alignment-run-3-v13-mkmlizer: ║ belonging to: ║
chaiml-elo-alignment-run-3-v13-mkmlizer: ║ ║
chaiml-elo-alignment-run-3-v13-mkmlizer: ║ Chai Research Corp. ║
chaiml-elo-alignment-run-3-v13-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-elo-alignment-run-3-v13-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
chaiml-elo-alignment-run-3-v13-mkmlizer: ║ ║
chaiml-elo-alignment-run-3-v13-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
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_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-v13-mkmlizer: Downloaded to shared memory in 46.458s
chaiml-elo-alignment-run-3-v13-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpvwtgs0qt, device:0
chaiml-elo-alignment-run-3-v13-mkmlizer: Saving flywheel model at /dev/shm/model_cache
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')
chaiml-elo-alignment-run-3-v13-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 2%|▏ | 5/291 [00:00<00:10, 26.19it/s] Loading 0: 4%|▍ | 12/291 [00:00<00:07, 35.57it/s] Loading 0: 5%|▌ | 16/291 [00:00<00:08, 33.21it/s] Loading 0: 7%|▋ | 21/291 [00:00<00:07, 34.27it/s] Loading 0: 9%|▊ | 25/291 [00:00<00:08, 32.83it/s] Loading 0: 11%|█ | 31/291 [00:00<00:06, 39.13it/s] Loading 0: 12%|█▏ | 36/291 [00:01<00:10, 23.48it/s] Loading 0: 14%|█▍ | 41/291 [00:01<00:09, 25.40it/s] Loading 0: 16%|█▋ | 48/291 [00:01<00:07, 31.85it/s] Loading 0: 18%|█▊ | 52/291 [00:01<00:07, 31.47it/s] Loading 0: 20%|█▉ | 57/291 [00:01<00:06, 34.03it/s] Loading 0: 21%|██ | 61/291 [00:01<00:07, 32.78it/s] Loading 0: 23%|██▎ | 66/291 [00:02<00:06, 35.23it/s] Loading 0: 24%|██▍ | 70/291 [00:02<00:06, 33.38it/s] Loading 0: 25%|██▌ | 74/291 [00:02<00:06, 33.33it/s] Loading 0: 27%|██▋ | 78/291 [00:02<00:06, 33.52it/s] Loading 0: 28%|██▊ | 82/291 [00:02<00:08, 23.52it/s] Loading 0: 29%|██▉ | 85/291 [00:02<00:08, 24.16it/s] Loading 0: 31%|███ | 90/291 [00:02<00:07, 28.57it/s] Loading 0: 32%|███▏ | 94/291 [00:03<00:06, 29.00it/s] Loading 0: 34%|███▍ | 99/291 [00:03<00:05, 32.28it/s] Loading 0: 35%|███▌ | 103/291 [00:03<00:05, 31.76it/s] Loading 0: 37%|███▋ | 108/291 [00:03<00:05, 34.27it/s] Loading 0: 38%|███▊ | 112/291 [00:03<00:05, 32.61it/s] Loading 0: 40%|███▉ | 116/291 [00:03<00:05, 32.81it/s] Loading 0: 42%|████▏ | 122/291 [00:03<00:04, 37.39it/s] Loading 0: 44%|████▎ | 127/291 [00:04<00:04, 35.35it/s] Loading 0: 46%|████▌ | 133/291 [00:04<00:05, 29.24it/s] Loading 0: 47%|████▋ | 137/291 [00:04<00:05, 29.79it/s] Loading 0: 48%|████▊ | 141/291 [00:04<00:05, 27.74it/s] Loading 0: 51%|█████ | 147/291 [00:04<00:04, 32.80it/s] Loading 0: 52%|█████▏ | 151/291 [00:04<00:04, 32.16it/s] Loading 0: 54%|█████▎ | 156/291 [00:04<00:03, 34.26it/s] Loading 0: 55%|█████▍ | 160/291 [00:05<00:03, 33.17it/s] Loading 0: 57%|█████▋ | 165/291 [00:05<00:03, 35.30it/s] Loading 0: 58%|█████▊ | 169/291 [00:05<00:03, 33.53it/s] Loading 0: 60%|█████▉ | 174/291 [00:05<00:03, 36.07it/s] Loading 0: 61%|██████ | 178/291 [00:05<00:03, 34.41it/s] Loading 0: 63%|██████▎ | 183/291 [00:05<00:02, 38.13it/s] Loading 0: 64%|██████▍ | 187/291 [00:05<00:03, 26.70it/s] Loading 0: 66%|██████▌ | 191/291 [00:06<00:03, 27.88it/s] Loading 0: 67%|██████▋ | 195/291 [00:06<00:03, 26.73it/s] Loading 0: 69%|██████▉ | 201/291 [00:06<00:02, 31.72it/s] Loading 0: 70%|███████ | 205/291 [00:06<00:02, 31.56it/s] Loading 0: 72%|███████▏ | 210/291 [00:06<00:02, 33.76it/s] Loading 0: 74%|███████▎ | 214/291 [00:06<00:02, 32.90it/s] Loading 0: 75%|███████▌ | 219/291 [00:06<00:02, 35.31it/s] Loading 0: 77%|███████▋ | 223/291 [00:07<00:02, 33.94it/s] Loading 0: 78%|███████▊ | 227/291 [00:07<00:01, 33.85it/s] Loading 0: 79%|███████▉ | 231/291 [00:07<00:01, 34.30it/s] Loading 0: 81%|████████ | 235/291 [00:07<00:02, 25.23it/s] Loading 0: 82%|████████▏ | 239/291 [00:07<00:02, 25.26it/s] Loading 0: 85%|████████▍ | 246/291 [00:07<00:01, 33.16it/s] Loading 0: 86%|████████▌ | 250/291 [00:07<00:01, 32.89it/s] Loading 0: 88%|████████▊ | 255/291 [00:08<00:01, 35.36it/s] Loading 0: 89%|████████▉ | 259/291 [00:08<00:00, 34.36it/s] Loading 0: 91%|█████████ | 264/291 [00:08<00:00, 36.61it/s] Loading 0: 92%|█████████▏| 268/291 [00:08<00:00, 34.74it/s] Loading 0: 94%|█████████▍| 273/291 [00:08<00:00, 35.95it/s] Loading 0: 95%|█████████▌| 277/291 [00:08<00:00, 34.20it/s] Loading 0: 97%|█████████▋| 281/291 [00:08<00:00, 34.09it/s] Loading 0: 98%|█████████▊| 286/291 [00:14<00:01, 2.56it/s] Loading 0: 99%|█████████▉| 289/291 [00:14<00:00, 3.18it/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-v13-mkmlizer: quantized model in 28.989s
chaiml-elo-alignment-run-3-v13-mkmlizer: Processed model ChaiML/elo_alignment_run_3 in 75.448s
chaiml-elo-alignment-run-3-v13-mkmlizer: creating bucket guanaco-mkml-models
chaiml-elo-alignment-run-3-v13-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-elo-alignment-run-3-v13-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v13
chaiml-elo-alignment-run-3-v13-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v13/tokenizer_config.json
chaiml-elo-alignment-run-3-v13-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v13/tokenizer.json
chaiml-elo-alignment-run-3-v13-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v13/flywheel_model.0.safetensors
chaiml-elo-alignment-run-3-v13-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
chaiml-elo-alignment-run-3-v13-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-v13-mkmlizer: warnings.warn(
chaiml-elo-alignment-run-3-v13-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-v13-mkmlizer: warnings.warn(
chaiml-elo-alignment-run-3-v13-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-v13-mkmlizer: warnings.warn(
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-v13-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
chaiml-elo-alignment-run-3-v13-mkmlizer: Saving duration: 0.324s
chaiml-elo-alignment-run-3-v13-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 15.630s
chaiml-elo-alignment-run-3-v13-mkmlizer: creating bucket guanaco-reward-models
chaiml-elo-alignment-run-3-v13-mkmlizer: Bucket 's3://guanaco-reward-models/' created
chaiml-elo-alignment-run-3-v13-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/chaiml-elo-alignment-run-3-v13_reward
chaiml-elo-alignment-run-3-v13-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/chaiml-elo-alignment-run-3-v13_reward/config.json
chaiml-elo-alignment-run-3-v13-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/chaiml-elo-alignment-run-3-v13_reward/special_tokens_map.json
chaiml-elo-alignment-run-3-v13-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/chaiml-elo-alignment-run-3-v13_reward/tokenizer_config.json
chaiml-elo-alignment-run-3-v13-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/chaiml-elo-alignment-run-3-v13_reward/merges.txt
chaiml-elo-alignment-run-3-v13-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/chaiml-elo-alignment-run-3-v13_reward/vocab.json
chaiml-elo-alignment-run-3-v13-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/chaiml-elo-alignment-run-3-v13_reward/tokenizer.json
chaiml-elo-alignment-run-3-v13-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/chaiml-elo-alignment-run-3-v13_reward/reward.tensors
Job chaiml-elo-alignment-run-3-v13-mkmlizer completed after 115.94s with status: succeeded
Stopping job with name chaiml-elo-alignment-run-3-v13-mkmlizer
Pipeline stage MKMLizer completed in 116.89s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service chaiml-elo-alignment-run-3-v13
Waiting for inference service chaiml-elo-alignment-run-3-v13 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', 'activator 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', 'activator 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', 'activator request timeout')
Inference service chaiml-elo-alignment-run-3-v13 ready after 60.40783476829529s
Pipeline stage ISVCDeployer completed in 61.80s
Running pipeline stage StressChecker
Received healthy response to inference request in 4.359848737716675s
Received healthy response to inference request in 3.589998960494995s
Received healthy response to inference request in 3.609625816345215s
Received healthy response to inference request in 3.5575807094573975s
Received healthy response to inference request in 3.5626463890075684s
5 requests
0 failed requests
5th percentile: 3.5585938453674317
10th percentile: 3.559606981277466
20th percentile: 3.561633253097534
30th percentile: 3.5681169033050537
40th percentile: 3.5790579319000244
50th percentile: 3.589998960494995
60th percentile: 3.597849702835083
70th percentile: 3.605700445175171
80th percentile: 3.759670400619507
90th percentile: 4.059759569168091
95th percentile: 4.2098041534423825
99th percentile: 4.3298398208618165
mean time: 3.73594012260437
Pipeline stage StressChecker completed in 19.55s
chaiml-elo-alignment-run-3_v13 status is now deployed due to DeploymentManager action
chaiml-elo-alignment-run-3_v13 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of chaiml-elo-alignment-run-3_v13
Running pipeline stage ISVCDeleter
Checking if service chaiml-elo-alignment-run-3-v13 is running
Tearing down inference service chaiml-elo-alignment-run-3-v13
Service chaiml-elo-alignment-run-3-v13 has been torndown
Pipeline stage ISVCDeleter completed in 5.00s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key chaiml-elo-alignment-run-3-v13/config.json from bucket guanaco-mkml-models
Deleting key chaiml-elo-alignment-run-3-v13/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key chaiml-elo-alignment-run-3-v13/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key chaiml-elo-alignment-run-3-v13/tokenizer.json from bucket guanaco-mkml-models
Deleting key chaiml-elo-alignment-run-3-v13/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key chaiml-elo-alignment-run-3-v13_reward/config.json from bucket guanaco-reward-models
Deleting key chaiml-elo-alignment-run-3-v13_reward/merges.txt from bucket guanaco-reward-models
Deleting key chaiml-elo-alignment-run-3-v13_reward/reward.tensors from bucket guanaco-reward-models
Deleting key chaiml-elo-alignment-run-3-v13_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key chaiml-elo-alignment-run-3-v13_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key chaiml-elo-alignment-run-3-v13_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key chaiml-elo-alignment-run-3-v13_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.61s
chaiml-elo-alignment-run-3_v13 status is now torndown due to DeploymentManager action