developer_uid: robert_irvine
submission_id: nitral-ai-hathor-l3-8b-v-01_v50
model_name: nitral-ai-hathor-l3-8b-v-01_v50
model_group: Nitral-AI/Hathor-L3-8B-v
status: torndown
timestamp: 2024-07-08T21:19:37+00:00
num_battles: 31103
num_wins: 17653
celo_rating: 1234.65
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: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: nitral-ai-hathor-l3-8b-v-01_v50
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: 0.5675658296627335
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-v50-mkmlizer
Waiting for job on nitral-ai-hathor-l3-8b-v-01-v50-mkmlizer to finish
Stopping job with name nitral-ai-hathor-l3-8b-v-01-v50-mkmlizer
%s, retrying in %s seconds...
Starting job with name nitral-ai-hathor-l3-8b-v-01-v50-mkmlizer
Waiting for job on nitral-ai-hathor-l3-8b-v-01-v50-mkmlizer to finish
Stopping job with name nitral-ai-hathor-l3-8b-v-01-v50-mkmlizer
%s, retrying in %s seconds...
Starting job with name nitral-ai-hathor-l3-8b-v-01-v50-mkmlizer
Waiting for job on nitral-ai-hathor-l3-8b-v-01-v50-mkmlizer to finish
nitral-ai-hathor-l3-8b-v-01-v50-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
nitral-ai-hathor-l3-8b-v-01-v50-mkmlizer: ║ _____ __ __ ║
nitral-ai-hathor-l3-8b-v-01-v50-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
nitral-ai-hathor-l3-8b-v-01-v50-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
nitral-ai-hathor-l3-8b-v-01-v50-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
nitral-ai-hathor-l3-8b-v-01-v50-mkmlizer: ║ /___/ ║
nitral-ai-hathor-l3-8b-v-01-v50-mkmlizer: ║ ║
nitral-ai-hathor-l3-8b-v-01-v50-mkmlizer: ║ Version: 0.8.14 ║
nitral-ai-hathor-l3-8b-v-01-v50-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
nitral-ai-hathor-l3-8b-v-01-v50-mkmlizer: ║ https://mk1.ai ║
nitral-ai-hathor-l3-8b-v-01-v50-mkmlizer: ║ ║
nitral-ai-hathor-l3-8b-v-01-v50-mkmlizer: ║ The license key for the current software has been verified as ║
nitral-ai-hathor-l3-8b-v-01-v50-mkmlizer: ║ belonging to: ║
nitral-ai-hathor-l3-8b-v-01-v50-mkmlizer: ║ ║
nitral-ai-hathor-l3-8b-v-01-v50-mkmlizer: ║ Chai Research Corp. ║
nitral-ai-hathor-l3-8b-v-01-v50-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
nitral-ai-hathor-l3-8b-v-01-v50-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
nitral-ai-hathor-l3-8b-v-01-v50-mkmlizer: ║ ║
nitral-ai-hathor-l3-8b-v-01-v50-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
nitral-ai-hathor-l3-8b-v-01-v50-mkmlizer: Downloaded to shared memory in 27.925s
nitral-ai-hathor-l3-8b-v-01-v50-mkmlizer: quantizing model to /dev/shm/model_cache
nitral-ai-hathor-l3-8b-v-01-v50-mkmlizer: Saving flywheel model at /dev/shm/model_cache
nitral-ai-hathor-l3-8b-v-01-v50-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:05<13:38, 2.83s/it] Loading 0: 5%|▍ | 14/291 [00:05<01:24, 3.28it/s] Loading 0: 9%|▉ | 26/291 [00:05<00:36, 7.22it/s] Loading 0: 14%|█▎ | 40/291 [00:05<00:18, 13.27it/s] Loading 0: 18%|█▊ | 51/291 [00:06<00:12, 19.11it/s] Loading 0: 21%|██▏ | 62/291 [00:06<00:11, 20.57it/s] Loading 0: 26%|██▌ | 76/291 [00:06<00:07, 30.23it/s] Loading 0: 30%|██▉ | 87/291 [00:06<00:05, 38.22it/s] Loading 0: 35%|███▌ | 103/291 [00:06<00:03, 53.57it/s] Loading 0: 40%|███▉ | 115/291 [00:06<00:02, 62.91it/s] Loading 0: 45%|████▍ | 130/291 [00:07<00:02, 77.65it/s] Loading 0: 49%|████▉ | 143/291 [00:07<00:01, 85.96it/s] Loading 0: 54%|█████▍ | 157/291 [00:07<00:01, 97.54it/s] Loading 0: 58%|█████▊ | 170/291 [00:07<00:02, 56.76it/s] Loading 0: 63%|██████▎ | 184/291 [00:07<00:01, 69.27it/s] Loading 0: 67%|██████▋ | 195/291 [00:07<00:01, 74.16it/s] Loading 0: 71%|███████ | 207/291 [00:08<00:01, 72.59it/s] Loading 0: 76%|███████▌ | 220/291 [00:08<00:00, 82.69it/s] Loading 0: 79%|███████▉ | 231/291 [00:08<00:00, 84.60it/s] Loading 0: 85%|████████▍ | 247/291 [00:08<00:00, 100.05it/s] Loading 0: 89%|████████▉ | 259/291 [00:08<00:00, 101.96it/s] Loading 0: 93%|█████████▎| 271/291 [00:09<00:00, 56.13it/s] Loading 0: 98%|█████████▊| 284/291 [00:09<00:00, 66.49it/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-v50-mkmlizer: quantized model in 29.558s
nitral-ai-hathor-l3-8b-v-01-v50-mkmlizer: Processed model Nitral-AI/Hathor-L3-8B-v.01 in 57.484s
nitral-ai-hathor-l3-8b-v-01-v50-mkmlizer: creating bucket guanaco-mkml-models
nitral-ai-hathor-l3-8b-v-01-v50-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
nitral-ai-hathor-l3-8b-v-01-v50-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v50
nitral-ai-hathor-l3-8b-v-01-v50-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v50/config.json
nitral-ai-hathor-l3-8b-v-01-v50-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v50/special_tokens_map.json
nitral-ai-hathor-l3-8b-v-01-v50-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v50/tokenizer_config.json
nitral-ai-hathor-l3-8b-v-01-v50-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v50/tokenizer.json
nitral-ai-hathor-l3-8b-v-01-v50-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v50/flywheel_model.0.safetensors
nitral-ai-hathor-l3-8b-v-01-v50-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
nitral-ai-hathor-l3-8b-v-01-v50-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-v50-mkmlizer: warnings.warn(
nitral-ai-hathor-l3-8b-v-01-v50-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-v50-mkmlizer: warnings.warn(
nitral-ai-hathor-l3-8b-v-01-v50-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-v50-mkmlizer: warnings.warn(
nitral-ai-hathor-l3-8b-v-01-v50-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-v50-mkmlizer: warnings.warn(
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
nitral-ai-hathor-l3-8b-v-01-v50-mkmlizer: Downloading shards: 0%| | 0/2 [00:00<?, ?it/s] Downloading shards: 50%|█████ | 1/2 [00:07<00:07, 7.12s/it] Downloading shards: 100%|██████████| 2/2 [00:09<00:00, 4.32s/it] Downloading shards: 100%|██████████| 2/2 [00:09<00:00, 4.74s/it]
nitral-ai-hathor-l3-8b-v-01-v50-mkmlizer: Loading checkpoint shards: 0%| | 0/2 [00:00<?, ?it/s] Loading checkpoint shards: 50%|█████ | 1/2 [00:00<00:00, 1.63it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 2.68it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 2.44it/s]
nitral-ai-hathor-l3-8b-v-01-v50-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
nitral-ai-hathor-l3-8b-v-01-v50-mkmlizer: Saving duration: 2.185s
nitral-ai-hathor-l3-8b-v-01-v50-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 13.936s
nitral-ai-hathor-l3-8b-v-01-v50-mkmlizer: creating bucket guanaco-reward-models
nitral-ai-hathor-l3-8b-v-01-v50-mkmlizer: Bucket 's3://guanaco-reward-models/' created
nitral-ai-hathor-l3-8b-v-01-v50-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v50_reward
nitral-ai-hathor-l3-8b-v-01-v50-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v50_reward/merges.txt
nitral-ai-hathor-l3-8b-v-01-v50-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v50_reward/tokenizer_config.json
nitral-ai-hathor-l3-8b-v-01-v50-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v50_reward/special_tokens_map.json
nitral-ai-hathor-l3-8b-v-01-v50-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v50_reward/config.json
nitral-ai-hathor-l3-8b-v-01-v50-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v50_reward/vocab.json
nitral-ai-hathor-l3-8b-v-01-v50-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v50_reward/tokenizer.json
nitral-ai-hathor-l3-8b-v-01-v50-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v50_reward/reward.tensors
Job nitral-ai-hathor-l3-8b-v-01-v50-mkmlizer completed after 104.36s with status: succeeded
Stopping job with name nitral-ai-hathor-l3-8b-v-01-v50-mkmlizer
Pipeline stage MKMLizer completed in 108.46s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service nitral-ai-hathor-l3-8b-v-01-v50
Waiting for inference service nitral-ai-hathor-l3-8b-v-01-v50 to be ready
Inference service nitral-ai-hathor-l3-8b-v-01-v50 ready after 40.21499752998352s
Pipeline stage ISVCDeployer completed in 47.46s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0468077659606934s
Received healthy response to inference request in 1.399336576461792s
Received healthy response to inference request in 1.3695778846740723s
Received healthy response to inference request in 1.3460931777954102s
Received healthy response to inference request in 1.4091405868530273s
5 requests
0 failed requests
5th percentile: 1.3507901191711427
10th percentile: 1.355487060546875
20th percentile: 1.3648809432983398
30th percentile: 1.3755296230316163
40th percentile: 1.3874330997467041
50th percentile: 1.399336576461792
60th percentile: 1.4032581806182862
70th percentile: 1.4071797847747802
80th percentile: 1.5366740226745605
90th percentile: 1.791740894317627
95th percentile: 1.9192743301391602
99th percentile: 2.0213010787963865
mean time: 1.514191198348999
Pipeline stage StressChecker completed in 8.24s
nitral-ai-hathor-l3-8b-v-01_v50 status is now deployed due to DeploymentManager action
Connection pool is full, discarding connection: %s
nitral-ai-hathor-l3-8b-v-01_v50 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of nitral-ai-hathor-l3-8b-v-01_v50
Running pipeline stage ISVCDeleter
Checking if service nitral-ai-hathor-l3-8b-v-01-v50 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.59s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key nitral-ai-hathor-l3-8b-v-01-v50/config.json from bucket guanaco-mkml-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v50/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v50/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v50/tokenizer.json from bucket guanaco-mkml-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v50/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key nitral-ai-hathor-l3-8b-v-01-v50_reward/config.json from bucket guanaco-reward-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v50_reward/merges.txt from bucket guanaco-reward-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v50_reward/reward.tensors from bucket guanaco-reward-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v50_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v50_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v50_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v50_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.56s
nitral-ai-hathor-l3-8b-v-01_v50 status is now torndown due to DeploymentManager action