chaiml-elo-run-3-cp7000

developer_uid: zonemercy

submission_id: chaiml-elo-run-3-cp7000_v4

model_name: nitral-ai-hathor-l3-8b-v-01_v1

model_group: ChaiML/elo_run_3_cp7000

status: torndown

timestamp: 2024-07-13T14:20:02+00:00

num_battles: 60274

num_wins: 38832

celo_rating: 1281.66

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: nitral-ai-hathor-l3-8b-v-01_v1

is_internal_developer: True

language_model: ChaiML/elo_run_3_cp7000

model_size: 8B

ranking_group: single

us_pacific_date: 2024-07-13

win_ratio: 0.6442578889736869

generation_params: {'temperature': 1.12358, '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': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', '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-v4-mkmlizer
Waiting for job on chaiml-elo-run-3-cp7000-v4-mkmlizer to finish
chaiml-elo-run-3-cp7000-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-elo-run-3-cp7000-v4-mkmlizer: ║     _____            __           __                                ║
chaiml-elo-run-3-cp7000-v4-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-elo-run-3-cp7000-v4-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-elo-run-3-cp7000-v4-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-elo-run-3-cp7000-v4-mkmlizer: ║       /___/                                                         ║
chaiml-elo-run-3-cp7000-v4-mkmlizer: ║                                                                     ║
chaiml-elo-run-3-cp7000-v4-mkmlizer: ║  Version: 0.8.14                                                    ║
chaiml-elo-run-3-cp7000-v4-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-elo-run-3-cp7000-v4-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-elo-run-3-cp7000-v4-mkmlizer: ║                                                                     ║
chaiml-elo-run-3-cp7000-v4-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-elo-run-3-cp7000-v4-mkmlizer: ║  belonging to:                                                      ║
chaiml-elo-run-3-cp7000-v4-mkmlizer: ║                                                                     ║
chaiml-elo-run-3-cp7000-v4-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-elo-run-3-cp7000-v4-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-elo-run-3-cp7000-v4-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
chaiml-elo-run-3-cp7000-v4-mkmlizer: ║                                                                     ║
chaiml-elo-run-3-cp7000-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-elo-run-3-cp7000-v4-mkmlizer: Downloaded to shared memory in 48.360s
chaiml-elo-run-3-cp7000-v4-mkmlizer: quantizing model to /dev/shm/model_cache
chaiml-elo-run-3-cp7000-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-elo-run-3-cp7000-v4-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:06, 43.25it/s]
Loading 0:   4%|▍         | 13/291 [00:00<00:04, 62.86it/s]
Loading 0:   7%|▋         | 21/291 [00:00<00:03, 69.71it/s]
Loading 0:  10%|▉         | 29/291 [00:00<00:03, 72.12it/s]
Loading 0:  13%|█▎        | 37/291 [00:00<00:08, 29.87it/s]
Loading 0:  15%|█▍        | 43/291 [00:01<00:07, 34.16it/s]
Loading 0:  17%|█▋        | 50/291 [00:01<00:06, 38.54it/s]
Loading 0:  20%|█▉        | 58/291 [00:01<00:04, 46.87it/s]
Loading 0:  23%|██▎       | 66/291 [00:01<00:04, 54.20it/s]
Loading 0:  25%|██▌       | 73/291 [00:01<00:03, 57.93it/s]
Loading 0:  27%|██▋       | 80/291 [00:01<00:06, 31.55it/s]
Loading 0:  30%|██▉       | 86/291 [00:02<00:05, 34.79it/s]
Loading 0:  32%|███▏      | 92/291 [00:02<00:05, 37.78it/s]
Loading 0:  34%|███▍      | 100/291 [00:02<00:04, 45.54it/s]
Loading 0:  37%|███▋      | 108/291 [00:02<00:03, 52.40it/s]
Loading 0:  40%|███▉      | 115/291 [00:02<00:03, 55.40it/s]
Loading 0:  42%|████▏     | 122/291 [00:02<00:02, 57.71it/s]
Loading 0:  44%|████▍     | 129/291 [00:02<00:02, 58.81it/s]
Loading 0:  47%|████▋     | 136/291 [00:03<00:04, 31.12it/s]
Loading 0:  48%|████▊     | 141/291 [00:03<00:04, 33.23it/s]
Loading 0:  51%|█████     | 148/291 [00:03<00:03, 38.23it/s]
Loading 0:  54%|█████▎    | 156/291 [00:03<00:03, 44.44it/s]
Loading 0:  56%|█████▌    | 162/291 [00:03<00:02, 46.45it/s]
Loading 0:  58%|█████▊    | 168/291 [00:03<00:02, 48.21it/s]
Loading 0:  60%|██████    | 175/291 [00:03<00:02, 53.09it/s]
Loading 0:  64%|██████▍   | 186/291 [00:04<00:02, 35.32it/s]
Loading 0:  66%|██████▌   | 191/291 [00:04<00:02, 37.13it/s]
Loading 0:  67%|██████▋   | 196/291 [00:04<00:02, 38.36it/s]
Loading 0:  70%|██████▉   | 203/291 [00:04<00:02, 41.94it/s]
Loading 0:  73%|███████▎  | 212/291 [00:04<00:01, 48.79it/s]
Loading 0:  76%|███████▌  | 221/291 [00:05<00:01, 53.96it/s]
Loading 0:  78%|███████▊  | 228/291 [00:05<00:01, 57.57it/s]
Loading 0:  81%|████████  | 235/291 [00:05<00:01, 34.64it/s]
Loading 0:  82%|████████▏ | 240/291 [00:05<00:01, 35.82it/s]
Loading 0:  85%|████████▌ | 248/291 [00:05<00:01, 41.56it/s]
Loading 0:  88%|████████▊ | 256/291 [00:05<00:00, 48.54it/s]
Loading 0:  91%|█████████ | 264/291 [00:05<00:00, 54.35it/s]
Loading 0:  93%|█████████▎| 271/291 [00:06<00:00, 57.86it/s]
Loading 0:  96%|█████████▌| 278/291 [00:06<00:00, 55.96it/s]
Loading 0:  98%|█████████▊| 286/291 [00:13<00:01,  3.41it/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-v4-mkmlizer: quantized model in 32.059s
chaiml-elo-run-3-cp7000-v4-mkmlizer: Processed model ChaiML/elo_run_3_cp7000 in 80.420s
chaiml-elo-run-3-cp7000-v4-mkmlizer: creating bucket guanaco-mkml-models
chaiml-elo-run-3-cp7000-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-elo-run-3-cp7000-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-elo-run-3-cp7000-v4
chaiml-elo-run-3-cp7000-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-elo-run-3-cp7000-v4/config.json
chaiml-elo-run-3-cp7000-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-elo-run-3-cp7000-v4/tokenizer_config.json
chaiml-elo-run-3-cp7000-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-elo-run-3-cp7000-v4/special_tokens_map.json
chaiml-elo-run-3-cp7000-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-elo-run-3-cp7000-v4/tokenizer.json
chaiml-elo-run-3-cp7000-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-elo-run-3-cp7000-v4/flywheel_model.0.safetensors
chaiml-elo-run-3-cp7000-v4-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-run-3-cp7000-v4-mkmlizer:   warnings.warn(
chaiml-elo-run-3-cp7000-v4-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-run-3-cp7000-v4-mkmlizer:   warnings.warn(
chaiml-elo-run-3-cp7000-v4-mkmlizer: 
Downloading shards:   0%|          | 0/2 [00:00<?, ?it/s]
Downloading shards:  50%|█████     | 1/2 [00:06<00:06,  6.98s/it]
Downloading shards: 100%|██████████| 2/2 [00:11<00:00,  5.35s/it]
Downloading shards: 100%|██████████| 2/2 [00:11<00:00,  5.59s/it]
chaiml-elo-run-3-cp7000-v4-mkmlizer: 
Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/s]
Loading checkpoint shards:  50%|█████     | 1/2 [00:00<00:00,  1.42it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00,  2.43it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00,  2.19it/s]
chaiml-elo-run-3-cp7000-v4-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
chaiml-elo-run-3-cp7000-v4-mkmlizer: Saving duration: 2.250s
chaiml-elo-run-3-cp7000-v4-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 16.982s
chaiml-elo-run-3-cp7000-v4-mkmlizer: creating bucket guanaco-reward-models
chaiml-elo-run-3-cp7000-v4-mkmlizer: Bucket 's3://guanaco-reward-models/' created
chaiml-elo-run-3-cp7000-v4-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/chaiml-elo-run-3-cp7000-v4_reward
chaiml-elo-run-3-cp7000-v4-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/chaiml-elo-run-3-cp7000-v4_reward/config.json
chaiml-elo-run-3-cp7000-v4-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/chaiml-elo-run-3-cp7000-v4_reward/tokenizer_config.json
chaiml-elo-run-3-cp7000-v4-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/chaiml-elo-run-3-cp7000-v4_reward/special_tokens_map.json
chaiml-elo-run-3-cp7000-v4-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/chaiml-elo-run-3-cp7000-v4_reward/merges.txt
chaiml-elo-run-3-cp7000-v4-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/chaiml-elo-run-3-cp7000-v4_reward/vocab.json
chaiml-elo-run-3-cp7000-v4-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/chaiml-elo-run-3-cp7000-v4_reward/tokenizer.json
chaiml-elo-run-3-cp7000-v4-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/chaiml-elo-run-3-cp7000-v4_reward/reward.tensors
Job chaiml-elo-run-3-cp7000-v4-mkmlizer completed after 124.4s with status: succeeded
Stopping job with name chaiml-elo-run-3-cp7000-v4-mkmlizer
Pipeline stage MKMLizer completed in 125.26s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service chaiml-elo-run-3-cp7000-v4
Waiting for inference service chaiml-elo-run-3-cp7000-v4 to be ready
Inference service chaiml-elo-run-3-cp7000-v4 ready after 40.20185327529907s
Pipeline stage ISVCDeployer completed in 47.09s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1926889419555664s
Received healthy response to inference request in 1.4753575325012207s
Received healthy response to inference request in 4.409171104431152s
Received healthy response to inference request in 1.5013909339904785s
Received healthy response to inference request in 1.4863195419311523s
5 requests
0 failed requests
5th percentile: 1.477549934387207
10th percentile: 1.4797423362731934
20th percentile: 1.484127140045166
30th percentile: 1.4893338203430175
40th percentile: 1.4953623771667481
50th percentile: 1.5013909339904785
60th percentile: 1.7779101371765136
70th percentile: 2.0544293403625487
80th percentile: 2.635985374450684
90th percentile: 3.522578239440918
95th percentile: 3.9658746719360347
99th percentile: 4.320511817932129
mean time: 2.212985610961914
Pipeline stage StressChecker completed in 11.75s
chaiml-elo-run-3-cp7000_v4 status is now deployed due to DeploymentManager action
chaiml-elo-run-3-cp7000_v4 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of chaiml-elo-run-3-cp7000_v4
Running pipeline stage ISVCDeleter
Checking if service chaiml-elo-run-3-cp7000-v4 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 5.38s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key chaiml-elo-run-3-cp7000-v4/config.json from bucket guanaco-mkml-models
Deleting key chaiml-elo-run-3-cp7000-v4/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key chaiml-elo-run-3-cp7000-v4/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key chaiml-elo-run-3-cp7000-v4/tokenizer.json from bucket guanaco-mkml-models
Deleting key chaiml-elo-run-3-cp7000-v4/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key chaiml-elo-run-3-cp7000-v4_reward/config.json from bucket guanaco-reward-models
Deleting key chaiml-elo-run-3-cp7000-v4_reward/merges.txt from bucket guanaco-reward-models
Deleting key chaiml-elo-run-3-cp7000-v4_reward/reward.tensors from bucket guanaco-reward-models
Deleting key chaiml-elo-run-3-cp7000-v4_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key chaiml-elo-run-3-cp7000-v4_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key chaiml-elo-run-3-cp7000-v4_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key chaiml-elo-run-3-cp7000-v4_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.62s
chaiml-elo-run-3-cp7000_v4 status is now torndown due to DeploymentManager action