developer_uid: zonemercy
submission_id: chaiml-elo-run-3-cp7000_v1
model_name: nitral-ai-hathor-l3-8b-v-01_v1
model_group: ChaiML/elo_run_3_cp7000
status: torndown
timestamp: 2024-07-12T20:42:10+00:00
num_battles: 24560
num_wins: 15161
celo_rating: 1275.62
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: 2024-07-12
win_ratio: 0.6173045602605863
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: {'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-v1-mkmlizer
Waiting for job on chaiml-elo-run-3-cp7000-v1-mkmlizer to finish
chaiml-elo-run-3-cp7000-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-elo-run-3-cp7000-v1-mkmlizer: ║ _____ __ __ ║
chaiml-elo-run-3-cp7000-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-elo-run-3-cp7000-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-elo-run-3-cp7000-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-elo-run-3-cp7000-v1-mkmlizer: ║ /___/ ║
chaiml-elo-run-3-cp7000-v1-mkmlizer: ║ ║
chaiml-elo-run-3-cp7000-v1-mkmlizer: ║ Version: 0.8.14 ║
chaiml-elo-run-3-cp7000-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-elo-run-3-cp7000-v1-mkmlizer: ║ https://mk1.ai ║
chaiml-elo-run-3-cp7000-v1-mkmlizer: ║ ║
chaiml-elo-run-3-cp7000-v1-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-elo-run-3-cp7000-v1-mkmlizer: ║ belonging to: ║
chaiml-elo-run-3-cp7000-v1-mkmlizer: ║ ║
chaiml-elo-run-3-cp7000-v1-mkmlizer: ║ Chai Research Corp. ║
chaiml-elo-run-3-cp7000-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-elo-run-3-cp7000-v1-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
chaiml-elo-run-3-cp7000-v1-mkmlizer: ║ ║
chaiml-elo-run-3-cp7000-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
chaiml-elo-run-3-cp7000-v1-mkmlizer: Downloaded to shared memory in 70.188s
chaiml-elo-run-3-cp7000-v1-mkmlizer: quantizing model to /dev/shm/model_cache
chaiml-elo-run-3-cp7000-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-elo-run-3-cp7000-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 3%|▎ | 9/291 [00:00<00:03, 85.19it/s] Loading 0: 6%|▌ | 18/291 [00:00<00:03, 86.60it/s] Loading 0: 9%|▉ | 27/291 [00:00<00:03, 85.29it/s] Loading 0: 12%|█▏ | 36/291 [00:00<00:05, 43.53it/s] Loading 0: 15%|█▌ | 45/291 [00:00<00:04, 53.16it/s] Loading 0: 18%|█▊ | 53/291 [00:00<00:04, 59.32it/s] Loading 0: 21%|██ | 61/291 [00:00<00:03, 64.32it/s] Loading 0: 24%|██▎ | 69/291 [00:01<00:03, 67.74it/s] Loading 0: 27%|██▋ | 80/291 [00:01<00:04, 48.96it/s] Loading 0: 30%|██▉ | 87/291 [00:01<00:03, 52.21it/s] Loading 0: 33%|███▎ | 96/291 [00:01<00:03, 59.88it/s] Loading 0: 36%|███▌ | 105/291 [00:01<00:02, 65.73it/s] Loading 0: 39%|███▉ | 113/291 [00:01<00:02, 68.08it/s] Loading 0: 43%|████▎ | 125/291 [00:01<00:02, 77.85it/s] Loading 0: 46%|████▌ | 134/291 [00:02<00:03, 49.62it/s] Loading 0: 48%|████▊ | 141/291 [00:02<00:02, 51.76it/s] Loading 0: 52%|█████▏ | 150/291 [00:02<00:02, 59.47it/s] Loading 0: 54%|█████▍ | 158/291 [00:02<00:02, 63.79it/s] Loading 0: 57%|█████▋ | 167/291 [00:02<00:01, 69.52it/s] Loading 0: 60%|██████ | 176/291 [00:02<00:01, 73.33it/s] Loading 0: 64%|██████▍ | 186/291 [00:03<00:01, 53.90it/s] Loading 0: 66%|██████▋ | 193/291 [00:03<00:01, 52.20it/s] Loading 0: 69%|██████▉ | 202/291 [00:03<00:01, 58.89it/s] Loading 0: 73%|███████▎ | 211/291 [00:03<00:01, 64.55it/s] Loading 0: 76%|███████▌ | 220/291 [00:03<00:01, 70.22it/s] Loading 0: 78%|███████▊ | 228/291 [00:03<00:00, 71.75it/s] Loading 0: 81%|████████ | 236/291 [00:03<00:01, 49.09it/s] Loading 0: 84%|████████▎ | 243/291 [00:04<00:00, 52.74it/s] Loading 0: 87%|████████▋ | 252/291 [00:04<00:00, 60.43it/s] Loading 0: 89%|████████▉ | 260/291 [00:04<00:00, 64.64it/s] Loading 0: 92%|█████████▏| 269/291 [00:04<00:00, 70.78it/s] Loading 0: 96%|█████████▌| 278/291 [00:04<00:00, 75.09it/s] Loading 0: 99%|█████████▊| 287/291 [00:10<00:00, 5.02it/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-v1-mkmlizer: quantized model in 25.142s
chaiml-elo-run-3-cp7000-v1-mkmlizer: Processed model ChaiML/elo_run_3_cp7000 in 95.330s
chaiml-elo-run-3-cp7000-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-elo-run-3-cp7000-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-elo-run-3-cp7000-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-elo-run-3-cp7000-v1
chaiml-elo-run-3-cp7000-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-elo-run-3-cp7000-v1/tokenizer_config.json
chaiml-elo-run-3-cp7000-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-elo-run-3-cp7000-v1/config.json
chaiml-elo-run-3-cp7000-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-elo-run-3-cp7000-v1/tokenizer.json
chaiml-elo-run-3-cp7000-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-elo-run-3-cp7000-v1/special_tokens_map.json
chaiml-elo-run-3-cp7000-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-elo-run-3-cp7000-v1/flywheel_model.0.safetensors
chaiml-elo-run-3-cp7000-v1-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-v1-mkmlizer: warnings.warn(
chaiml-elo-run-3-cp7000-v1-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-v1-mkmlizer: warnings.warn(
chaiml-elo-run-3-cp7000-v1-mkmlizer: Downloading shards: 0%| | 0/2 [00:00<?, ?it/s] Downloading shards: 50%|█████ | 1/2 [00:06<00:06, 6.05s/it] Downloading shards: 100%|██████████| 2/2 [00:07<00:00, 3.47s/it] Downloading shards: 100%|██████████| 2/2 [00:07<00:00, 3.85s/it]
chaiml-elo-run-3-cp7000-v1-mkmlizer: Loading checkpoint shards: 0%| | 0/2 [00:00<?, ?it/s] Loading checkpoint shards: 50%|█████ | 1/2 [00:00<00:00, 2.06it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 2.89it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 2.72it/s]
chaiml-elo-run-3-cp7000-v1-mkmlizer: Saving duration: 4.372s
chaiml-elo-run-3-cp7000-v1-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 14.658s
chaiml-elo-run-3-cp7000-v1-mkmlizer: creating bucket guanaco-reward-models
chaiml-elo-run-3-cp7000-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
chaiml-elo-run-3-cp7000-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/chaiml-elo-run-3-cp7000-v1_reward
chaiml-elo-run-3-cp7000-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/chaiml-elo-run-3-cp7000-v1_reward/special_tokens_map.json
chaiml-elo-run-3-cp7000-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/chaiml-elo-run-3-cp7000-v1_reward/tokenizer_config.json
chaiml-elo-run-3-cp7000-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/chaiml-elo-run-3-cp7000-v1_reward/config.json
chaiml-elo-run-3-cp7000-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/chaiml-elo-run-3-cp7000-v1_reward/vocab.json
chaiml-elo-run-3-cp7000-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/chaiml-elo-run-3-cp7000-v1_reward/merges.txt
chaiml-elo-run-3-cp7000-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/chaiml-elo-run-3-cp7000-v1_reward/tokenizer.json
chaiml-elo-run-3-cp7000-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/chaiml-elo-run-3-cp7000-v1_reward/reward.tensors
Connection pool is full, discarding connection: %s
Job chaiml-elo-run-3-cp7000-v1-mkmlizer completed after 753.06s with status: succeeded
Stopping job with name chaiml-elo-run-3-cp7000-v1-mkmlizer
Pipeline stage MKMLizer completed in 753.96s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service chaiml-elo-run-3-cp7000-v1
Waiting for inference service chaiml-elo-run-3-cp7000-v1 to be ready
Inference service chaiml-elo-run-3-cp7000-v1 ready after 50.3446626663208s
Pipeline stage ISVCDeployer completed in 57.37s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.2933075428009033s
Received healthy response to inference request in 1.584897518157959s
Received healthy response to inference request in 1.5559334754943848s
Received healthy response to inference request in 1.5464141368865967s
Received healthy response to inference request in 1.598454475402832s
5 requests
0 failed requests
5th percentile: 1.5483180046081544
10th percentile: 1.5502218723297119
20th percentile: 1.554029607772827
30th percentile: 1.5617262840270996
40th percentile: 1.5733119010925294
50th percentile: 1.584897518157959
60th percentile: 1.5903203010559082
70th percentile: 1.5957430839538573
80th percentile: 1.9374250888824465
90th percentile: 2.615366315841675
95th percentile: 2.954336929321289
99th percentile: 3.2255134201049804
mean time: 1.915801429748535
Pipeline stage StressChecker completed in 10.31s
chaiml-elo-run-3-cp7000_v1 status is now deployed due to DeploymentManager action
chaiml-elo-run-3-cp7000_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of chaiml-elo-run-3-cp7000_v1
Running pipeline stage ISVCDeleter
Checking if service chaiml-elo-run-3-cp7000-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.04s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key chaiml-elo-run-3-cp7000-v1/config.json from bucket guanaco-mkml-models
Deleting key chaiml-elo-run-3-cp7000-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key chaiml-elo-run-3-cp7000-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key chaiml-elo-run-3-cp7000-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key chaiml-elo-run-3-cp7000-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key chaiml-elo-run-3-cp7000-v1_reward/config.json from bucket guanaco-reward-models
Deleting key chaiml-elo-run-3-cp7000-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key chaiml-elo-run-3-cp7000-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key chaiml-elo-run-3-cp7000-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key chaiml-elo-run-3-cp7000-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key chaiml-elo-run-3-cp7000-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key chaiml-elo-run-3-cp7000-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.51s
chaiml-elo-run-3-cp7000_v1 status is now torndown due to DeploymentManager action