developer_uid: robert_irvine
submission_id: nitral-ai-hathor-l3-8b-v-01_v60
model_name: nitral-ai-hathor-l3-8b-v-01_v60
model_group: Nitral-AI/Hathor-L3-8B-v
status: torndown
timestamp: 2024-07-09T17:33:32+00:00
num_battles: 33510
num_wins: 14676
celo_rating: 1148.25
family_friendly_score: 0.0
submission_type: basic
model_repo: Nitral-AI/Hathor-L3-8B-v.01
model_architecture: LlamaForCausalLM
reward_repo: ChaiML/gpt2_xl_pairwise_89m_step_347634
model_num_parameters: 8030261248.0
best_of: 1
max_input_tokens: 512
max_output_tokens: 64
display_name: nitral-ai-hathor-l3-8b-v-01_v60
is_internal_developer: True
language_model: Nitral-AI/Hathor-L3-8B-v.01
model_size: 8B
ranking_group: single
us_pacific_date: 2024-07-09
win_ratio: 0.43795881826320504
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': 1, '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-v60-mkmlizer
Waiting for job on nitral-ai-hathor-l3-8b-v-01-v60-mkmlizer to finish
nitral-ai-hathor-l3-8b-v-01-v60-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
nitral-ai-hathor-l3-8b-v-01-v60-mkmlizer: ║ _____ __ __ ║
nitral-ai-hathor-l3-8b-v-01-v60-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
nitral-ai-hathor-l3-8b-v-01-v60-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
nitral-ai-hathor-l3-8b-v-01-v60-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
nitral-ai-hathor-l3-8b-v-01-v60-mkmlizer: ║ /___/ ║
nitral-ai-hathor-l3-8b-v-01-v60-mkmlizer: ║ ║
nitral-ai-hathor-l3-8b-v-01-v60-mkmlizer: ║ Version: 0.8.14 ║
nitral-ai-hathor-l3-8b-v-01-v60-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
nitral-ai-hathor-l3-8b-v-01-v60-mkmlizer: ║ https://mk1.ai ║
nitral-ai-hathor-l3-8b-v-01-v60-mkmlizer: ║ ║
nitral-ai-hathor-l3-8b-v-01-v60-mkmlizer: ║ The license key for the current software has been verified as ║
nitral-ai-hathor-l3-8b-v-01-v60-mkmlizer: ║ belonging to: ║
nitral-ai-hathor-l3-8b-v-01-v60-mkmlizer: ║ ║
nitral-ai-hathor-l3-8b-v-01-v60-mkmlizer: ║ Chai Research Corp. ║
nitral-ai-hathor-l3-8b-v-01-v60-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
nitral-ai-hathor-l3-8b-v-01-v60-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
nitral-ai-hathor-l3-8b-v-01-v60-mkmlizer: ║ ║
nitral-ai-hathor-l3-8b-v-01-v60-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
nitral-ai-hathor-l3-8b-v-01-v60-mkmlizer: Downloaded to shared memory in 24.868s
nitral-ai-hathor-l3-8b-v-01-v60-mkmlizer: quantizing model to /dev/shm/model_cache
nitral-ai-hathor-l3-8b-v-01-v60-mkmlizer: Saving flywheel model at /dev/shm/model_cache
nitral-ai-hathor-l3-8b-v-01-v60-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:05<13:39, 2.84s/it] Loading 0: 5%|▍ | 14/291 [00:05<01:24, 3.28it/s] Loading 0: 10%|▉ | 28/291 [00:05<00:33, 7.89it/s] Loading 0: 14%|█▍ | 41/291 [00:06<00:18, 13.43it/s] Loading 0: 19%|█▊ | 54/291 [00:06<00:11, 20.57it/s] Loading 0: 23%|██▎ | 66/291 [00:06<00:10, 21.77it/s] Loading 0: 26%|██▌ | 76/291 [00:06<00:07, 27.72it/s] Loading 0: 30%|██▉ | 86/291 [00:06<00:05, 34.55it/s] Loading 0: 33%|███▎ | 96/291 [00:06<00:04, 41.85it/s] Loading 0: 37%|███▋ | 108/291 [00:07<00:03, 53.39it/s] Loading 0: 42%|████▏ | 121/291 [00:07<00:02, 64.30it/s] Loading 0: 45%|████▌ | 131/291 [00:07<00:02, 69.75it/s] Loading 0: 48%|████▊ | 141/291 [00:07<00:01, 75.22it/s] Loading 0: 53%|█████▎ | 155/291 [00:07<00:01, 90.12it/s] Loading 0: 57%|█████▋ | 166/291 [00:08<00:02, 42.79it/s] Loading 0: 61%|██████ | 177/291 [00:08<00:02, 51.02it/s] Loading 0: 66%|██████▋ | 193/291 [00:08<00:01, 67.67it/s] Loading 0: 70%|███████ | 204/291 [00:08<00:01, 73.74it/s] Loading 0: 76%|███████▌ | 220/291 [00:08<00:00, 89.91it/s] Loading 0: 80%|███████▉ | 232/291 [00:08<00:00, 92.87it/s] Loading 0: 85%|████████▍ | 247/291 [00:08<00:00, 103.20it/s] Loading 0: 89%|████████▉ | 259/291 [00:08<00:00, 102.27it/s] Loading 0: 93%|█████████▎| 271/291 [00:09<00:00, 57.60it/s] Loading 0: 98%|█████████▊| 284/291 [00:09<00:00, 67.58it/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-v60-mkmlizer: quantized model in 29.636s
nitral-ai-hathor-l3-8b-v-01-v60-mkmlizer: Processed model Nitral-AI/Hathor-L3-8B-v.01 in 54.504s
nitral-ai-hathor-l3-8b-v-01-v60-mkmlizer: creating bucket guanaco-mkml-models
nitral-ai-hathor-l3-8b-v-01-v60-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
nitral-ai-hathor-l3-8b-v-01-v60-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v60
nitral-ai-hathor-l3-8b-v-01-v60-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v60/special_tokens_map.json
nitral-ai-hathor-l3-8b-v-01-v60-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v60/config.json
nitral-ai-hathor-l3-8b-v-01-v60-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v60/tokenizer_config.json
nitral-ai-hathor-l3-8b-v-01-v60-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v60/tokenizer.json
nitral-ai-hathor-l3-8b-v-01-v60-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v60/flywheel_model.0.safetensors
nitral-ai-hathor-l3-8b-v-01-v60-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
nitral-ai-hathor-l3-8b-v-01-v60-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:919: 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-v60-mkmlizer: warnings.warn(
nitral-ai-hathor-l3-8b-v-01-v60-mkmlizer: /opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py:1132: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`.
nitral-ai-hathor-l3-8b-v-01-v60-mkmlizer: warnings.warn(
nitral-ai-hathor-l3-8b-v-01-v60-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.
nitral-ai-hathor-l3-8b-v-01-v60-mkmlizer: warnings.warn(
nitral-ai-hathor-l3-8b-v-01-v60-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.
nitral-ai-hathor-l3-8b-v-01-v60-mkmlizer: warnings.warn(
nitral-ai-hathor-l3-8b-v-01-v60-mkmlizer: Downloading shards: 0%| | 0/2 [00:00<?, ?it/s] Downloading shards: 50%|█████ | 1/2 [00:06<00:06, 6.87s/it] Downloading shards: 100%|██████████| 2/2 [00:09<00:00, 4.16s/it] Downloading shards: 100%|██████████| 2/2 [00:09<00:00, 4.57s/it]
nitral-ai-hathor-l3-8b-v-01-v60-mkmlizer: Loading checkpoint shards: 0%| | 0/2 [00:00<?, ?it/s] Loading checkpoint shards: 50%|█████ | 1/2 [00:00<00:00, 1.52it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 2.49it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 2.27it/s]
nitral-ai-hathor-l3-8b-v-01-v60-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
nitral-ai-hathor-l3-8b-v-01-v60-mkmlizer: Saving duration: 2.162s
nitral-ai-hathor-l3-8b-v-01-v60-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 13.574s
nitral-ai-hathor-l3-8b-v-01-v60-mkmlizer: creating bucket guanaco-reward-models
nitral-ai-hathor-l3-8b-v-01-v60-mkmlizer: Bucket 's3://guanaco-reward-models/' created
nitral-ai-hathor-l3-8b-v-01-v60-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v60_reward
nitral-ai-hathor-l3-8b-v-01-v60-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v60_reward/special_tokens_map.json
nitral-ai-hathor-l3-8b-v-01-v60-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v60_reward/merges.txt
nitral-ai-hathor-l3-8b-v-01-v60-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v60_reward/config.json
nitral-ai-hathor-l3-8b-v-01-v60-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v60_reward/tokenizer_config.json
nitral-ai-hathor-l3-8b-v-01-v60-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v60_reward/tokenizer.json
nitral-ai-hathor-l3-8b-v-01-v60-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v60_reward/vocab.json
nitral-ai-hathor-l3-8b-v-01-v60-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v60_reward/reward.tensors
Job nitral-ai-hathor-l3-8b-v-01-v60-mkmlizer completed after 94.17s with status: succeeded
Stopping job with name nitral-ai-hathor-l3-8b-v-01-v60-mkmlizer
Pipeline stage MKMLizer completed in 95.04s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service nitral-ai-hathor-l3-8b-v-01-v60
Waiting for inference service nitral-ai-hathor-l3-8b-v-01-v60 to be ready
Inference service nitral-ai-hathor-l3-8b-v-01-v60 ready after 50.30137658119202s
Pipeline stage ISVCDeployer completed in 57.18s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.4373037815093994s
Received healthy response to inference request in 1.101618766784668s
Received healthy response to inference request in 0.9629607200622559s
Received healthy response to inference request in 0.5918786525726318s
Received healthy response to inference request in 1.1013844013214111s
5 requests
0 failed requests
5th percentile: 0.6660950660705567
10th percentile: 0.7403114795684814
20th percentile: 0.888744306564331
30th percentile: 0.990645456314087
40th percentile: 1.046014928817749
50th percentile: 1.1013844013214111
60th percentile: 1.101478147506714
70th percentile: 1.1015718936920167
80th percentile: 1.1687557697296143
90th percentile: 1.3030297756195068
95th percentile: 1.3701667785644531
99th percentile: 1.4238763809204102
mean time: 1.0390292644500732
Pipeline stage StressChecker completed in 5.88s
nitral-ai-hathor-l3-8b-v-01_v60 status is now deployed due to DeploymentManager action
nitral-ai-hathor-l3-8b-v-01_v60 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of nitral-ai-hathor-l3-8b-v-01_v60
Running pipeline stage ISVCDeleter
Checking if service nitral-ai-hathor-l3-8b-v-01-v60 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.09s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key nitral-ai-hathor-l3-8b-v-01-v60/config.json from bucket guanaco-mkml-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v60/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v60/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v60/tokenizer.json from bucket guanaco-mkml-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v60/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key nitral-ai-hathor-l3-8b-v-01-v60_reward/config.json from bucket guanaco-reward-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v60_reward/merges.txt from bucket guanaco-reward-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v60_reward/reward.tensors from bucket guanaco-reward-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v60_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v60_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v60_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v60_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.43s
nitral-ai-hathor-l3-8b-v-01_v60 status is now torndown due to DeploymentManager action