chaiml-elo-run-3-cp7000

developer_uid: zonemercy
submission_id: chaiml-elo-run-3-cp7000_v6
model_name: chaiml-elo-run-3-cp7000_v6
model_group: ChaiML/elo_run_3_cp7000
status: torndown
timestamp: 2024-07-20T15:49:30+00:00
num_battles: 348678
num_wins: 208478
celo_rating: 1271.6
family_friendly_score: 0.0
submission_type: basic
model_repo: ChaiML/elo_run_3_cp7000
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: chaiml-elo-run-3-cp7000_v6
is_internal_developer: True
language_model: ChaiML/elo_run_3_cp7000
model_size: 8B
ranking_group: single
us_pacific_date: 2024-07-20
win_ratio: 0.5979098193748961
generation_params: {'temperature': 0.95, '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: {'bot_template': '{bot_name}: {message}\n', 'memory_template': "''", 'prompt_template': "''", '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-run-3-cp7000-v6-mkmlizer
Waiting for job on chaiml-elo-run-3-cp7000-v6-mkmlizer to finish
Stopping job with name chaiml-elo-run-3-cp7000-v6-mkmlizer
%s, retrying in %s seconds...
Starting job with name chaiml-elo-run-3-cp7000-v6-mkmlizer
Waiting for job on chaiml-elo-run-3-cp7000-v6-mkmlizer to finish
chaiml-elo-run-3-cp7000-v6-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-elo-run-3-cp7000-v6-mkmlizer: ║     _____            __           __                                ║
chaiml-elo-run-3-cp7000-v6-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-elo-run-3-cp7000-v6-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-elo-run-3-cp7000-v6-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-elo-run-3-cp7000-v6-mkmlizer: ║       /___/                                                         ║
chaiml-elo-run-3-cp7000-v6-mkmlizer: ║                                                                     ║
chaiml-elo-run-3-cp7000-v6-mkmlizer: ║  Version: 0.9.5.post3                                               ║
chaiml-elo-run-3-cp7000-v6-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-elo-run-3-cp7000-v6-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-elo-run-3-cp7000-v6-mkmlizer: ║                                                                     ║
chaiml-elo-run-3-cp7000-v6-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-elo-run-3-cp7000-v6-mkmlizer: ║  belonging to:                                                      ║
chaiml-elo-run-3-cp7000-v6-mkmlizer: ║                                                                     ║
chaiml-elo-run-3-cp7000-v6-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-elo-run-3-cp7000-v6-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-elo-run-3-cp7000-v6-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
chaiml-elo-run-3-cp7000-v6-mkmlizer: ║                                                                     ║
chaiml-elo-run-3-cp7000-v6-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-elo-run-3-cp7000-v6-mkmlizer: Downloaded to shared memory in 41.221s
chaiml-elo-run-3-cp7000-v6-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp674jpmge, device:0
chaiml-elo-run-3-cp7000-v6-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-elo-run-3-cp7000-v6-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:06, 42.99it/s]
Loading 0:   5%|▍         | 14/291 [00:00<00:04, 58.15it/s]
Loading 0:   8%|▊         | 23/291 [00:00<00:04, 62.30it/s]
Loading 0:  11%|█▏        | 33/291 [00:00<00:05, 49.31it/s]
Loading 0:  13%|█▎        | 39/291 [00:00<00:05, 46.91it/s]
Loading 0:  16%|█▋        | 48/291 [00:00<00:04, 53.01it/s]
Loading 0:  20%|█▉        | 57/291 [00:01<00:04, 57.32it/s]
Loading 0:  23%|██▎       | 66/291 [00:01<00:03, 60.40it/s]
Loading 0:  25%|██▌       | 74/291 [00:01<00:03, 60.58it/s]
Loading 0:  28%|██▊       | 81/291 [00:01<00:04, 43.48it/s]
Loading 0:  31%|███       | 90/291 [00:01<00:04, 49.20it/s]
Loading 0:  34%|███▍      | 99/291 [00:01<00:03, 54.23it/s]
Loading 0:  36%|███▋      | 106/291 [00:01<00:03, 57.45it/s]
Loading 0:  39%|███▉      | 113/291 [00:02<00:03, 57.28it/s]
Loading 0:  42%|████▏     | 122/291 [00:02<00:02, 63.19it/s]
Loading 0:  44%|████▍     | 129/291 [00:02<00:02, 62.05it/s]
Loading 0:  47%|████▋     | 136/291 [00:02<00:03, 43.27it/s]
Loading 0:  49%|████▉     | 142/291 [00:02<00:03, 45.94it/s]
Loading 0:  51%|█████     | 148/291 [00:02<00:03, 47.44it/s]
Loading 0:  54%|█████▍    | 157/291 [00:02<00:02, 53.48it/s]
Loading 0:  57%|█████▋    | 166/291 [00:03<00:02, 58.22it/s]
Loading 0:  60%|██████    | 175/291 [00:03<00:01, 61.85it/s]
Loading 0:  64%|██████▍   | 186/291 [00:03<00:01, 52.50it/s]
Loading 0:  66%|██████▌   | 192/291 [00:03<00:01, 50.17it/s]
Loading 0:  69%|██████▉   | 201/291 [00:03<00:01, 55.16it/s]
Loading 0:  72%|███████▏  | 210/291 [00:03<00:01, 59.15it/s]
Loading 0:  75%|███████▌  | 219/291 [00:04<00:01, 62.12it/s]
Loading 0:  78%|███████▊  | 227/291 [00:04<00:01, 62.24it/s]
Loading 0:  80%|████████  | 234/291 [00:04<00:01, 45.32it/s]
Loading 0:  82%|████████▏ | 240/291 [00:04<00:01, 47.50it/s]
Loading 0:  85%|████████▌ | 248/291 [00:04<00:00, 51.28it/s]
Loading 0:  88%|████████▊ | 257/291 [00:04<00:00, 55.58it/s]
Loading 0:  91%|█████████▏| 266/291 [00:04<00:00, 59.62it/s]
Loading 0:  95%|█████████▍| 275/291 [00:05<00:00, 62.69it/s]
Loading 0:  98%|█████████▊| 286/291 [00:10<00:00,  5.15it/s]
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
chaiml-elo-run-3-cp7000-v6-mkmlizer: quantized model in 25.077s
chaiml-elo-run-3-cp7000-v6-mkmlizer: Processed model ChaiML/elo_run_3_cp7000 in 66.297s
chaiml-elo-run-3-cp7000-v6-mkmlizer: creating bucket guanaco-mkml-models
chaiml-elo-run-3-cp7000-v6-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-elo-run-3-cp7000-v6-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-elo-run-3-cp7000-v6
chaiml-elo-run-3-cp7000-v6-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-elo-run-3-cp7000-v6/special_tokens_map.json
chaiml-elo-run-3-cp7000-v6-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-elo-run-3-cp7000-v6/config.json
chaiml-elo-run-3-cp7000-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-elo-run-3-cp7000-v6/tokenizer_config.json
chaiml-elo-run-3-cp7000-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-elo-run-3-cp7000-v6/tokenizer.json
chaiml-elo-run-3-cp7000-v6-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-elo-run-3-cp7000-v6/flywheel_model.0.safetensors
chaiml-elo-run-3-cp7000-v6-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
chaiml-elo-run-3-cp7000-v6-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-run-3-cp7000-v6-mkmlizer:   warnings.warn(
chaiml-elo-run-3-cp7000-v6-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-run-3-cp7000-v6-mkmlizer:   warnings.warn(
chaiml-elo-run-3-cp7000-v6-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-run-3-cp7000-v6-mkmlizer:   warnings.warn(
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
chaiml-elo-run-3-cp7000-v6-mkmlizer: 
Downloading shards:   0%|          | 0/2 [00:00<?, ?it/s]
Downloading shards:  50%|█████     | 1/2 [00:05<00:05,  5.25s/it]
Downloading shards: 100%|██████████| 2/2 [00:08<00:00,  3.81s/it]
Downloading shards: 100%|██████████| 2/2 [00:08<00:00,  4.03s/it]
chaiml-elo-run-3-cp7000-v6-mkmlizer: 
Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/s]
Loading checkpoint shards:  50%|█████     | 1/2 [00:00<00:00,  2.34it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00,  3.89it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00,  3.54it/s]
chaiml-elo-run-3-cp7000-v6-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
chaiml-elo-run-3-cp7000-v6-mkmlizer: Saving duration: 1.498s
chaiml-elo-run-3-cp7000-v6-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 12.964s
chaiml-elo-run-3-cp7000-v6-mkmlizer: creating bucket guanaco-reward-models
chaiml-elo-run-3-cp7000-v6-mkmlizer: Bucket 's3://guanaco-reward-models/' created
chaiml-elo-run-3-cp7000-v6-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/chaiml-elo-run-3-cp7000-v6_reward
chaiml-elo-run-3-cp7000-v6-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/chaiml-elo-run-3-cp7000-v6_reward/config.json
chaiml-elo-run-3-cp7000-v6-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/chaiml-elo-run-3-cp7000-v6_reward/tokenizer_config.json
chaiml-elo-run-3-cp7000-v6-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/chaiml-elo-run-3-cp7000-v6_reward/special_tokens_map.json
chaiml-elo-run-3-cp7000-v6-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/chaiml-elo-run-3-cp7000-v6_reward/merges.txt
chaiml-elo-run-3-cp7000-v6-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/chaiml-elo-run-3-cp7000-v6_reward/vocab.json
chaiml-elo-run-3-cp7000-v6-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/chaiml-elo-run-3-cp7000-v6_reward/tokenizer.json
chaiml-elo-run-3-cp7000-v6-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/chaiml-elo-run-3-cp7000-v6_reward/reward.tensors
Job chaiml-elo-run-3-cp7000-v6-mkmlizer completed after 110.49s with status: succeeded
Stopping job with name chaiml-elo-run-3-cp7000-v6-mkmlizer
Pipeline stage MKMLizer completed in 113.54s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service chaiml-elo-run-3-cp7000-v6
Waiting for inference service chaiml-elo-run-3-cp7000-v6 to be ready
Failed to get response for submission kaoeiri-pantheramix-l3-r_5669_v7: ('http://kaoeiri-pantheramix-l3-r-5669-v7-predictor-default.tenant-chaiml-guanaco.knative.ord1.coreweave.cloud/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Inference service chaiml-elo-run-3-cp7000-v6 ready after 41.198684215545654s
Pipeline stage ISVCDeployer completed in 43.83s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1249876022338867s
Received healthy response to inference request in 1.409592866897583s
Received healthy response to inference request in 1.3035109043121338s
Received healthy response to inference request in 1.3051016330718994s
Received healthy response to inference request in 1.3220303058624268s
5 requests
0 failed requests
5th percentile: 1.303829050064087
10th percentile: 1.30414719581604
20th percentile: 1.3047834873199462
30th percentile: 1.3084873676300048
40th percentile: 1.315258836746216
50th percentile: 1.3220303058624268
60th percentile: 1.3570553302764892
70th percentile: 1.3920803546905518
80th percentile: 1.5526718139648439
90th percentile: 1.8388297080993654
95th percentile: 1.9819086551666258
99th percentile: 2.0963718128204345
mean time: 1.493044662475586
Pipeline stage StressChecker completed in 8.13s
chaiml-elo-run-3-cp7000_v6 status is now deployed due to DeploymentManager action
chaiml-elo-run-3-cp7000_v6 status is now inactive due to auto deactivation removed underperforming models
chaiml-elo-run-3-cp7000_v6 status is now deployed due to admin request
chaiml-elo-run-3-cp7000_v6 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of chaiml-elo-run-3-cp7000_v6
Running pipeline stage ISVCDeleter
Checking if service chaiml-elo-run-3-cp7000-v6 is running
Tearing down inference service chaiml-elo-run-3-cp7000-v6
Service chaiml-elo-run-3-cp7000-v6 has been torndown
Pipeline stage ISVCDeleter completed in 5.77s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key chaiml-elo-run-3-cp7000-v6/config.json from bucket guanaco-mkml-models
Deleting key chaiml-elo-run-3-cp7000-v6/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key chaiml-elo-run-3-cp7000-v6/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key chaiml-elo-run-3-cp7000-v6/tokenizer.json from bucket guanaco-mkml-models
Deleting key chaiml-elo-run-3-cp7000-v6/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key chaiml-elo-run-3-cp7000-v6_reward/config.json from bucket guanaco-reward-models
Deleting key chaiml-elo-run-3-cp7000-v6_reward/merges.txt from bucket guanaco-reward-models
Deleting key chaiml-elo-run-3-cp7000-v6_reward/reward.tensors from bucket guanaco-reward-models
Deleting key chaiml-elo-run-3-cp7000-v6_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key chaiml-elo-run-3-cp7000-v6_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key chaiml-elo-run-3-cp7000-v6_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key chaiml-elo-run-3-cp7000-v6_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.44s
chaiml-elo-run-3-cp7000_v6 status is now torndown due to DeploymentManager action