developer_uid: robert_irvine
submission_id: nitral-ai-hathor-l3-8b-v-01_v53
model_name: nitral-ai-hathor-l3-8b-v-01_v53
model_group: Nitral-AI/Hathor-L3-8B-v
status: torndown
timestamp: 2024-07-08T21:30:42+00:00
num_battles: 30810
num_wins: 12694
celo_rating: 1134.97
family_friendly_score: 0.0
submission_type: basic
model_repo: Nitral-AI/Hathor-L3-8B-v.01
model_architecture: LlamaForCausalLM
reward_repo: Jellywibble/CHAI_alignment_reward_model
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_v53
is_internal_developer: True
language_model: Nitral-AI/Hathor-L3-8B-v.01
model_size: 8B
ranking_group: single
us_pacific_date: 2024-07-08
win_ratio: 0.41200908795845503
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': '', '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 nitral-ai-hathor-l3-8b-v-01-v53-mkmlizer
Waiting for job on nitral-ai-hathor-l3-8b-v-01-v53-mkmlizer to finish
nitral-ai-hathor-l3-8b-v-01-v53-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
nitral-ai-hathor-l3-8b-v-01-v53-mkmlizer: ║ _____ __ __ ║
nitral-ai-hathor-l3-8b-v-01-v53-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
nitral-ai-hathor-l3-8b-v-01-v53-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
nitral-ai-hathor-l3-8b-v-01-v53-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
nitral-ai-hathor-l3-8b-v-01-v53-mkmlizer: ║ /___/ ║
nitral-ai-hathor-l3-8b-v-01-v53-mkmlizer: ║ ║
nitral-ai-hathor-l3-8b-v-01-v53-mkmlizer: ║ Version: 0.8.14 ║
nitral-ai-hathor-l3-8b-v-01-v53-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
nitral-ai-hathor-l3-8b-v-01-v53-mkmlizer: ║ https://mk1.ai ║
nitral-ai-hathor-l3-8b-v-01-v53-mkmlizer: ║ ║
nitral-ai-hathor-l3-8b-v-01-v53-mkmlizer: ║ The license key for the current software has been verified as ║
nitral-ai-hathor-l3-8b-v-01-v53-mkmlizer: ║ belonging to: ║
nitral-ai-hathor-l3-8b-v-01-v53-mkmlizer: ║ ║
nitral-ai-hathor-l3-8b-v-01-v53-mkmlizer: ║ Chai Research Corp. ║
nitral-ai-hathor-l3-8b-v-01-v53-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
nitral-ai-hathor-l3-8b-v-01-v53-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
nitral-ai-hathor-l3-8b-v-01-v53-mkmlizer: ║ ║
nitral-ai-hathor-l3-8b-v-01-v53-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
nitral-ai-hathor-l3-8b-v-01-v53-mkmlizer: Downloaded to shared memory in 23.048s
nitral-ai-hathor-l3-8b-v-01-v53-mkmlizer: quantizing model to /dev/shm/model_cache
nitral-ai-hathor-l3-8b-v-01-v53-mkmlizer: Saving flywheel model at /dev/shm/model_cache
nitral-ai-hathor-l3-8b-v-01-v53-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<11:56, 2.48s/it] Loading 0: 4%|▍ | 13/291 [00:05<01:20, 3.46it/s] Loading 0: 8%|▊ | 23/291 [00:05<00:37, 7.15it/s] Loading 0: 13%|█▎ | 37/291 [00:05<00:18, 14.03it/s] Loading 0: 17%|█▋ | 50/291 [00:05<00:10, 21.96it/s] Loading 0: 21%|██ | 61/291 [00:05<00:09, 24.01it/s] Loading 0: 25%|██▍ | 72/291 [00:05<00:06, 31.91it/s] Loading 0: 30%|██▉ | 86/291 [00:05<00:04, 43.98it/s] Loading 0: 35%|███▍ | 101/291 [00:06<00:03, 59.00it/s] Loading 0: 39%|███▉ | 113/291 [00:06<00:02, 68.99it/s] Loading 0: 45%|████▍ | 130/291 [00:06<00:01, 85.75it/s] Loading 0: 49%|████▉ | 143/291 [00:06<00:01, 94.14it/s] Loading 0: 54%|█████▍ | 158/291 [00:06<00:01, 104.01it/s] Loading 0: 59%|█████▉ | 171/291 [00:06<00:01, 68.49it/s] Loading 0: 63%|██████▎ | 182/291 [00:06<00:01, 75.18it/s] Loading 0: 66%|██████▋ | 193/291 [00:07<00:01, 78.90it/s] Loading 0: 70%|██████▉ | 203/291 [00:07<00:01, 80.39it/s] Loading 0: 73%|███████▎ | 213/291 [00:07<00:00, 79.62it/s] Loading 0: 77%|███████▋ | 225/291 [00:07<00:00, 88.56it/s] Loading 0: 82%|████████▏ | 239/291 [00:07<00:00, 98.33it/s] Loading 0: 88%|████████▊ | 256/291 [00:07<00:00, 111.77it/s] Loading 0: 92%|█████████▏| 268/291 [00:08<00:00, 68.54it/s] Loading 0: 96%|█████████▌| 280/291 [00:08<00:00, 77.23it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
nitral-ai-hathor-l3-8b-v-01-v53-mkmlizer: quantized model in 24.854s
nitral-ai-hathor-l3-8b-v-01-v53-mkmlizer: Processed model Nitral-AI/Hathor-L3-8B-v.01 in 47.902s
nitral-ai-hathor-l3-8b-v-01-v53-mkmlizer: creating bucket guanaco-mkml-models
nitral-ai-hathor-l3-8b-v-01-v53-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
nitral-ai-hathor-l3-8b-v-01-v53-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v53
nitral-ai-hathor-l3-8b-v-01-v53-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v53/tokenizer_config.json
nitral-ai-hathor-l3-8b-v-01-v53-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v53/special_tokens_map.json
nitral-ai-hathor-l3-8b-v-01-v53-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v53/config.json
nitral-ai-hathor-l3-8b-v-01-v53-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v53/tokenizer.json
nitral-ai-hathor-l3-8b-v-01-v53-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.
nitral-ai-hathor-l3-8b-v-01-v53-mkmlizer: warnings.warn(
nitral-ai-hathor-l3-8b-v-01-v53-mkmlizer: loading reward model from Jellywibble/CHAI_alignment_reward_model
nitral-ai-hathor-l3-8b-v-01-v53-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.
nitral-ai-hathor-l3-8b-v-01-v53-mkmlizer: warnings.warn(
nitral-ai-hathor-l3-8b-v-01-v53-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.
nitral-ai-hathor-l3-8b-v-01-v53-mkmlizer: warnings.warn(
nitral-ai-hathor-l3-8b-v-01-v53-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
nitral-ai-hathor-l3-8b-v-01-v53-mkmlizer: Saving duration: 0.167s
nitral-ai-hathor-l3-8b-v-01-v53-mkmlizer: Processed model Jellywibble/CHAI_alignment_reward_model in 2.518s
nitral-ai-hathor-l3-8b-v-01-v53-mkmlizer: creating bucket guanaco-reward-models
nitral-ai-hathor-l3-8b-v-01-v53-mkmlizer: Bucket 's3://guanaco-reward-models/' created
nitral-ai-hathor-l3-8b-v-01-v53-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v53_reward
nitral-ai-hathor-l3-8b-v-01-v53-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v53_reward/config.json
nitral-ai-hathor-l3-8b-v-01-v53-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v53_reward/special_tokens_map.json
nitral-ai-hathor-l3-8b-v-01-v53-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v53_reward/tokenizer_config.json
nitral-ai-hathor-l3-8b-v-01-v53-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v53_reward/merges.txt
nitral-ai-hathor-l3-8b-v-01-v53-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v53_reward/vocab.json
nitral-ai-hathor-l3-8b-v-01-v53-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v53_reward/tokenizer.json
nitral-ai-hathor-l3-8b-v-01-v53-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v53_reward/reward.tensors
Job nitral-ai-hathor-l3-8b-v-01-v53-mkmlizer completed after 80.16s with status: succeeded
Stopping job with name nitral-ai-hathor-l3-8b-v-01-v53-mkmlizer
Pipeline stage MKMLizer completed in 81.50s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.30s
Running pipeline stage ISVCDeployer
Creating inference service nitral-ai-hathor-l3-8b-v-01-v53
Waiting for inference service nitral-ai-hathor-l3-8b-v-01-v53 to be ready
Inference service nitral-ai-hathor-l3-8b-v-01-v53 ready after 60.835179567337036s
Pipeline stage ISVCDeployer completed in 66.95s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9389162063598633s
Received healthy response to inference request in 1.445288896560669s
Received healthy response to inference request in 1.4274585247039795s
Received healthy response to inference request in 1.3330461978912354s
Received healthy response to inference request in 1.4282970428466797s
5 requests
0 failed requests
5th percentile: 1.3519286632537841
10th percentile: 1.370811128616333
20th percentile: 1.4085760593414307
30th percentile: 1.4276262283325196
40th percentile: 1.4279616355895997
50th percentile: 1.4282970428466797
60th percentile: 1.4350937843322753
70th percentile: 1.4418905258178711
80th percentile: 1.544014358520508
90th percentile: 1.7414652824401855
95th percentile: 1.8401907444000243
99th percentile: 1.9191711139678955
mean time: 1.5146013736724853
Pipeline stage StressChecker completed in 10.01s
nitral-ai-hathor-l3-8b-v-01_v53 status is now deployed due to DeploymentManager action
nitral-ai-hathor-l3-8b-v-01_v53 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of nitral-ai-hathor-l3-8b-v-01_v53
Running pipeline stage ISVCDeleter
Checking if service nitral-ai-hathor-l3-8b-v-01-v53 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 3.95s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key nitral-ai-hathor-l3-8b-v-01-v53/config.json from bucket guanaco-mkml-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v53/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v53/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v53/tokenizer.json from bucket guanaco-mkml-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v53/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key nitral-ai-hathor-l3-8b-v-01-v53_reward/config.json from bucket guanaco-reward-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v53_reward/merges.txt from bucket guanaco-reward-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v53_reward/reward.tensors from bucket guanaco-reward-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v53_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v53_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v53_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v53_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.47s
nitral-ai-hathor-l3-8b-v-01_v53 status is now torndown due to DeploymentManager action