submission_id: nitral-ai-hathor-l3-8b-v-01_v55
developer_uid: robert_irvine
best_of: 16
celo_rating: 1236.36
display_name: nitral-ai-hathor-l3-8b-v-01_v55
family_friendly_score: 0.0
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}
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}
is_internal_developer: True
language_model: Nitral-AI/Hathor-L3-8B-v.01
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: Nitral-AI/Hathor-L3-8B-v
model_name: nitral-ai-hathor-l3-8b-v-01_v55
model_num_parameters: 8030261248.0
model_repo: Nitral-AI/Hathor-L3-8B-v.01
model_size: 8B
num_battles: 30205
num_wins: 17072
ranking_group: single
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'}
reward_repo: ChaiML/gpt2_xl_pairwise_89m_step_347634
status: torndown
submission_type: basic
timestamp: 2024-07-09T17:20:42+00:00
us_pacific_date: 2024-07-09
win_ratio: 0.5652044363515975
Resubmit model
Running pipeline stage MKMLizer
Starting job with name nitral-ai-hathor-l3-8b-v-01-v55-mkmlizer
Waiting for job on nitral-ai-hathor-l3-8b-v-01-v55-mkmlizer to finish
Stopping job with name nitral-ai-hathor-l3-8b-v-01-v55-mkmlizer
%s, retrying in %s seconds...
Starting job with name nitral-ai-hathor-l3-8b-v-01-v55-mkmlizer
Waiting for job on nitral-ai-hathor-l3-8b-v-01-v55-mkmlizer to finish
nitral-ai-hathor-l3-8b-v-01-v55-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
nitral-ai-hathor-l3-8b-v-01-v55-mkmlizer: ║ _____ __ __ ║
nitral-ai-hathor-l3-8b-v-01-v55-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
nitral-ai-hathor-l3-8b-v-01-v55-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
nitral-ai-hathor-l3-8b-v-01-v55-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
nitral-ai-hathor-l3-8b-v-01-v55-mkmlizer: ║ /___/ ║
nitral-ai-hathor-l3-8b-v-01-v55-mkmlizer: ║ ║
nitral-ai-hathor-l3-8b-v-01-v55-mkmlizer: ║ Version: 0.8.14 ║
nitral-ai-hathor-l3-8b-v-01-v55-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
nitral-ai-hathor-l3-8b-v-01-v55-mkmlizer: ║ https://mk1.ai ║
nitral-ai-hathor-l3-8b-v-01-v55-mkmlizer: ║ ║
nitral-ai-hathor-l3-8b-v-01-v55-mkmlizer: ║ The license key for the current software has been verified as ║
nitral-ai-hathor-l3-8b-v-01-v55-mkmlizer: ║ belonging to: ║
nitral-ai-hathor-l3-8b-v-01-v55-mkmlizer: ║ ║
nitral-ai-hathor-l3-8b-v-01-v55-mkmlizer: ║ Chai Research Corp. ║
nitral-ai-hathor-l3-8b-v-01-v55-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
nitral-ai-hathor-l3-8b-v-01-v55-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
nitral-ai-hathor-l3-8b-v-01-v55-mkmlizer: ║ ║
nitral-ai-hathor-l3-8b-v-01-v55-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
nitral-ai-hathor-l3-8b-v-01-v55-mkmlizer: Downloaded to shared memory in 25.683s
nitral-ai-hathor-l3-8b-v-01-v55-mkmlizer: quantizing model to /dev/shm/model_cache
nitral-ai-hathor-l3-8b-v-01-v55-mkmlizer: Saving flywheel model at /dev/shm/model_cache
nitral-ai-hathor-l3-8b-v-01-v55-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:05<13:27, 2.80s/it] Loading 0: 5%|▍ | 14/291 [00:05<01:23, 3.33it/s] Loading 0: 10%|▉ | 28/291 [00:05<00:32, 8.02it/s] Loading 0: 14%|█▍ | 41/291 [00:05<00:18, 13.67it/s] Loading 0: 19%|█▉ | 55/291 [00:06<00:10, 21.54it/s] Loading 0: 23%|██▎ | 67/291 [00:06<00:09, 22.86it/s] Loading 0: 27%|██▋ | 78/291 [00:06<00:07, 29.91it/s] Loading 0: 32%|███▏ | 94/291 [00:06<00:04, 43.39it/s] Loading 0: 36%|███▋ | 106/291 [00:06<00:03, 52.78it/s] Loading 0: 42%|████▏ | 121/291 [00:06<00:02, 67.54it/s] Loading 0: 46%|████▌ | 134/291 [00:07<00:02, 77.58it/s] Loading 0: 51%|█████ | 148/291 [00:07<00:01, 89.46it/s] Loading 0: 55%|█████▌ | 161/291 [00:07<00:01, 95.93it/s] Loading 0: 60%|█████▉ | 174/291 [00:07<00:02, 57.98it/s] Loading 0: 64%|██████▎ | 185/291 [00:07<00:01, 65.46it/s] Loading 0: 68%|██████▊ | 199/291 [00:07<00:01, 78.76it/s] Loading 0: 73%|███████▎ | 212/291 [00:07<00:00, 86.82it/s] Loading 0: 78%|███████▊ | 226/291 [00:08<00:00, 98.19it/s] Loading 0: 82%|████████▏ | 239/291 [00:08<00:00, 103.70it/s] Loading 0: 87%|████████▋ | 253/291 [00:08<00:00, 111.89it/s] Loading 0: 91%|█████████▏| 266/291 [00:08<00:00, 59.65it/s] Loading 0: 96%|█████████▌| 280/291 [00:08<00:00, 72.31it/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-v55-mkmlizer: quantized model in 30.439s
nitral-ai-hathor-l3-8b-v-01-v55-mkmlizer: Processed model Nitral-AI/Hathor-L3-8B-v.01 in 56.123s
nitral-ai-hathor-l3-8b-v-01-v55-mkmlizer: creating bucket guanaco-mkml-models
nitral-ai-hathor-l3-8b-v-01-v55-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
nitral-ai-hathor-l3-8b-v-01-v55-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v55
nitral-ai-hathor-l3-8b-v-01-v55-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v55/config.json
nitral-ai-hathor-l3-8b-v-01-v55-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v55/tokenizer_config.json
nitral-ai-hathor-l3-8b-v-01-v55-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v55/special_tokens_map.json
nitral-ai-hathor-l3-8b-v-01-v55-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v55/tokenizer.json
nitral-ai-hathor-l3-8b-v-01-v55-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v55/flywheel_model.0.safetensors
nitral-ai-hathor-l3-8b-v-01-v55-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
nitral-ai-hathor-l3-8b-v-01-v55-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-v55-mkmlizer: warnings.warn(
nitral-ai-hathor-l3-8b-v-01-v55-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-v55-mkmlizer: warnings.warn(
nitral-ai-hathor-l3-8b-v-01-v55-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-v55-mkmlizer: warnings.warn(
nitral-ai-hathor-l3-8b-v-01-v55-mkmlizer: Downloading shards: 0%| | 0/2 [00:00<?, ?it/s] Downloading shards: 50%|█████ | 1/2 [00:07<00:07, 7.50s/it] Downloading shards: 100%|██████████| 2/2 [00:09<00:00, 4.37s/it] Downloading shards: 100%|██████████| 2/2 [00:09<00:00, 4.84s/it]
nitral-ai-hathor-l3-8b-v-01-v55-mkmlizer: Loading checkpoint shards: 0%| | 0/2 [00:00<?, ?it/s] Loading checkpoint shards: 50%|█████ | 1/2 [00:00<00:00, 1.25it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:01<00:00, 2.13it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:01<00:00, 1.93it/s]
nitral-ai-hathor-l3-8b-v-01-v55-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
nitral-ai-hathor-l3-8b-v-01-v55-mkmlizer: Saving duration: 2.267s
nitral-ai-hathor-l3-8b-v-01-v55-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 14.344s
nitral-ai-hathor-l3-8b-v-01-v55-mkmlizer: creating bucket guanaco-reward-models
nitral-ai-hathor-l3-8b-v-01-v55-mkmlizer: Bucket 's3://guanaco-reward-models/' created
nitral-ai-hathor-l3-8b-v-01-v55-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v55_reward
nitral-ai-hathor-l3-8b-v-01-v55-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v55_reward/config.json
nitral-ai-hathor-l3-8b-v-01-v55-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v55_reward/special_tokens_map.json
nitral-ai-hathor-l3-8b-v-01-v55-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v55_reward/tokenizer_config.json
nitral-ai-hathor-l3-8b-v-01-v55-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v55_reward/merges.txt
nitral-ai-hathor-l3-8b-v-01-v55-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v55_reward/vocab.json
nitral-ai-hathor-l3-8b-v-01-v55-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v55_reward/tokenizer.json
nitral-ai-hathor-l3-8b-v-01-v55-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v55_reward/reward.tensors
Job nitral-ai-hathor-l3-8b-v-01-v55-mkmlizer completed after 159.81s with status: succeeded
Stopping job with name nitral-ai-hathor-l3-8b-v-01-v55-mkmlizer
Pipeline stage MKMLizer completed in 161.44s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service nitral-ai-hathor-l3-8b-v-01-v55
Waiting for inference service nitral-ai-hathor-l3-8b-v-01-v55 to be ready
Inference service nitral-ai-hathor-l3-8b-v-01-v55 ready after 40.303771018981934s
Pipeline stage ISVCDeployer completed in 47.12s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9624099731445312s
Received healthy response to inference request in 1.3949832916259766s
Received healthy response to inference request in 1.3622050285339355s
Received healthy response to inference request in 1.3323049545288086s
Received healthy response to inference request in 1.4109923839569092s
5 requests
0 failed requests
5th percentile: 1.338284969329834
10th percentile: 1.3442649841308594
20th percentile: 1.3562250137329102
30th percentile: 1.3687606811523438
40th percentile: 1.3818719863891602
50th percentile: 1.3949832916259766
60th percentile: 1.4013869285583496
70th percentile: 1.4077905654907226
80th percentile: 1.5212759017944337
90th percentile: 1.7418429374694824
95th percentile: 1.8521264553070067
99th percentile: 1.9403532695770263
mean time: 1.4925791263580321
Pipeline stage StressChecker completed in 8.24s
nitral-ai-hathor-l3-8b-v-01_v55 status is now deployed due to DeploymentManager action
nitral-ai-hathor-l3-8b-v-01_v55 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of nitral-ai-hathor-l3-8b-v-01_v55
Running pipeline stage ISVCDeleter
Checking if service nitral-ai-hathor-l3-8b-v-01-v55 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.81s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key nitral-ai-hathor-l3-8b-v-01-v55/config.json from bucket guanaco-mkml-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v55/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v55/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v55/tokenizer.json from bucket guanaco-mkml-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v55/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key nitral-ai-hathor-l3-8b-v-01-v55_reward/config.json from bucket guanaco-reward-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v55_reward/merges.txt from bucket guanaco-reward-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v55_reward/reward.tensors from bucket guanaco-reward-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v55_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v55_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v55_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v55_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.42s
nitral-ai-hathor-l3-8b-v-01_v55 status is now torndown due to DeploymentManager action