submission_id: nitral-ai-hathor-l3-8b-v-01_v63
developer_uid: robert_irvine
status: inactive
model_repo: Nitral-AI/Hathor-L3-8B-v.01
reward_repo: ChaiML/gpt2_xl_pairwise_89m_step_347634
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': 4, '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: {'memory_template': '', 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': False}
timestamp: 2024-07-09T17:40:54+00:00
model_name: nitral-ai-hathor-l3-8b-v-01_v63
model_group: Nitral-AI/Hathor-L3-8B-v
num_battles: 33146
num_wins: 16838
celo_rating: 1198.21
alignment_score: None
alignment_samples: 0
propriety_score: 0.7207893370261381
propriety_total_count: 5777.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 4
max_input_tokens: 512
max_output_tokens: 64
display_name: nitral-ai-hathor-l3-8b-v-01_v63
ineligible_reason: None
language_model: Nitral-AI/Hathor-L3-8B-v.01
model_size: 8B
reward_model: ChaiML/gpt2_xl_pairwise_89m_step_347634
us_pacific_date: 2024-07-09
win_ratio: 0.507994931515115
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name nitral-ai-hathor-l3-8b-v-01-v63-mkmlizer
Waiting for job on nitral-ai-hathor-l3-8b-v-01-v63-mkmlizer to finish
nitral-ai-hathor-l3-8b-v-01-v63-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
nitral-ai-hathor-l3-8b-v-01-v63-mkmlizer: ║ _____ __ __ ║
nitral-ai-hathor-l3-8b-v-01-v63-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
nitral-ai-hathor-l3-8b-v-01-v63-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
nitral-ai-hathor-l3-8b-v-01-v63-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
nitral-ai-hathor-l3-8b-v-01-v63-mkmlizer: ║ /___/ ║
nitral-ai-hathor-l3-8b-v-01-v63-mkmlizer: ║ ║
nitral-ai-hathor-l3-8b-v-01-v63-mkmlizer: ║ Version: 0.8.14 ║
nitral-ai-hathor-l3-8b-v-01-v63-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
nitral-ai-hathor-l3-8b-v-01-v63-mkmlizer: ║ https://mk1.ai ║
nitral-ai-hathor-l3-8b-v-01-v63-mkmlizer: ║ ║
nitral-ai-hathor-l3-8b-v-01-v63-mkmlizer: ║ The license key for the current software has been verified as ║
nitral-ai-hathor-l3-8b-v-01-v63-mkmlizer: ║ belonging to: ║
nitral-ai-hathor-l3-8b-v-01-v63-mkmlizer: ║ ║
nitral-ai-hathor-l3-8b-v-01-v63-mkmlizer: ║ Chai Research Corp. ║
nitral-ai-hathor-l3-8b-v-01-v63-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
nitral-ai-hathor-l3-8b-v-01-v63-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
nitral-ai-hathor-l3-8b-v-01-v63-mkmlizer: ║ ║
nitral-ai-hathor-l3-8b-v-01-v63-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
nitral-ai-hathor-l3-8b-v-01-v63-mkmlizer: Downloaded to shared memory in 29.947s
nitral-ai-hathor-l3-8b-v-01-v63-mkmlizer: quantizing model to /dev/shm/model_cache
nitral-ai-hathor-l3-8b-v-01-v63-mkmlizer: Saving flywheel model at /dev/shm/model_cache
nitral-ai-hathor-l3-8b-v-01-v63-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:05<13:34, 2.82s/it] Loading 0: 5%|▍ | 14/291 [00:05<01:23, 3.30it/s] Loading 0: 9%|▉ | 27/291 [00:05<00:34, 7.60it/s] Loading 0: 14%|█▍ | 41/291 [00:05<00:18, 13.61it/s] Loading 0: 19%|█▉ | 55/291 [00:06<00:11, 21.33it/s] Loading 0: 23%|██▎ | 67/291 [00:06<00:10, 22.21it/s] Loading 0: 27%|██▋ | 78/291 [00:06<00:07, 29.02it/s] Loading 0: 32%|███▏ | 94/291 [00:06<00:04, 42.01it/s] Loading 0: 36%|███▌ | 105/291 [00:06<00:03, 49.83it/s] Loading 0: 42%|████▏ | 121/291 [00:07<00:02, 65.38it/s] Loading 0: 46%|████▌ | 133/291 [00:07<00:02, 73.43it/s] Loading 0: 51%|█████ | 148/291 [00:07<00:01, 87.58it/s] Loading 0: 55%|█████▌ | 161/291 [00:07<00:01, 93.39it/s] Loading 0: 59%|█████▉ | 173/291 [00:07<00:02, 53.34it/s] Loading 0: 63%|██████▎ | 184/291 [00:07<00:01, 61.09it/s] Loading 0: 67%|██████▋ | 195/291 [00:08<00:01, 67.97it/s] Loading 0: 73%|███████▎ | 211/291 [00:08<00:00, 84.26it/s] Loading 0: 76%|███████▋ | 222/291 [00:08<00:00, 75.51it/s] Loading 0: 82%|████████▏ | 238/291 [00:08<00:00, 91.44it/s] Loading 0: 86%|████████▌ | 250/291 [00:08<00:00, 94.57it/s] Loading 0: 91%|█████████ | 265/291 [00:08<00:00, 105.85it/s] Loading 0: 95%|█████████▌| 277/291 [00:09<00:00, 57.28it/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-v63-mkmlizer: quantized model in 29.175s
nitral-ai-hathor-l3-8b-v-01-v63-mkmlizer: Processed model Nitral-AI/Hathor-L3-8B-v.01 in 59.122s
nitral-ai-hathor-l3-8b-v-01-v63-mkmlizer: creating bucket guanaco-mkml-models
nitral-ai-hathor-l3-8b-v-01-v63-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
nitral-ai-hathor-l3-8b-v-01-v63-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v63
nitral-ai-hathor-l3-8b-v-01-v63-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v63/tokenizer_config.json
nitral-ai-hathor-l3-8b-v-01-v63-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v63/special_tokens_map.json
nitral-ai-hathor-l3-8b-v-01-v63-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v63/config.json
nitral-ai-hathor-l3-8b-v-01-v63-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v63/tokenizer.json
nitral-ai-hathor-l3-8b-v-01-v63-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v63/flywheel_model.0.safetensors
nitral-ai-hathor-l3-8b-v-01-v63-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
nitral-ai-hathor-l3-8b-v-01-v63-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-v63-mkmlizer: warnings.warn(
nitral-ai-hathor-l3-8b-v-01-v63-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-v63-mkmlizer: warnings.warn(
nitral-ai-hathor-l3-8b-v-01-v63-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-v63-mkmlizer: warnings.warn(
nitral-ai-hathor-l3-8b-v-01-v63-mkmlizer: Downloading shards: 0%| | 0/2 [00:00<?, ?it/s] Downloading shards: 50%|█████ | 1/2 [00:06<00:06, 6.67s/it] Downloading shards: 100%|██████████| 2/2 [00:08<00:00, 4.09s/it] Downloading shards: 100%|██████████| 2/2 [00:08<00:00, 4.48s/it]
nitral-ai-hathor-l3-8b-v-01-v63-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, 2.66it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 2.43it/s]
nitral-ai-hathor-l3-8b-v-01-v63-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
nitral-ai-hathor-l3-8b-v-01-v63-mkmlizer: Saving duration: 2.184s
nitral-ai-hathor-l3-8b-v-01-v63-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 13.267s
nitral-ai-hathor-l3-8b-v-01-v63-mkmlizer: creating bucket guanaco-reward-models
nitral-ai-hathor-l3-8b-v-01-v63-mkmlizer: Bucket 's3://guanaco-reward-models/' created
nitral-ai-hathor-l3-8b-v-01-v63-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v63_reward
nitral-ai-hathor-l3-8b-v-01-v63-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v63_reward/special_tokens_map.json
nitral-ai-hathor-l3-8b-v-01-v63-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v63_reward/config.json
nitral-ai-hathor-l3-8b-v-01-v63-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v63_reward/tokenizer_config.json
nitral-ai-hathor-l3-8b-v-01-v63-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v63_reward/merges.txt
nitral-ai-hathor-l3-8b-v-01-v63-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v63_reward/vocab.json
nitral-ai-hathor-l3-8b-v-01-v63-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v63_reward/tokenizer.json
nitral-ai-hathor-l3-8b-v-01-v63-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v63_reward/reward.tensors
Job nitral-ai-hathor-l3-8b-v-01-v63-mkmlizer completed after 115.49s with status: succeeded
Stopping job with name nitral-ai-hathor-l3-8b-v-01-v63-mkmlizer
Pipeline stage MKMLizer completed in 116.36s
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-v63
Waiting for inference service nitral-ai-hathor-l3-8b-v-01-v63 to be ready
Inference service nitral-ai-hathor-l3-8b-v-01-v63 ready after 50.32425308227539s
Pipeline stage ISVCDeployer completed in 56.97s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9387130737304688s
Received healthy response to inference request in 1.1390070915222168s
Received healthy response to inference request in 1.1506903171539307s
Received healthy response to inference request in 1.1272690296173096s
Received healthy response to inference request in 1.1482229232788086s
5 requests
0 failed requests
5th percentile: 1.129616641998291
10th percentile: 1.1319642543792725
20th percentile: 1.1366594791412354
30th percentile: 1.1408502578735351
40th percentile: 1.144536590576172
50th percentile: 1.1482229232788086
60th percentile: 1.1492098808288573
70th percentile: 1.1501968383789063
80th percentile: 1.3082948684692384
90th percentile: 1.6235039710998536
95th percentile: 1.781108522415161
99th percentile: 1.9071921634674072
mean time: 1.3007804870605468
Pipeline stage StressChecker completed in 7.30s
nitral-ai-hathor-l3-8b-v-01_v63 status is now deployed due to DeploymentManager action
nitral-ai-hathor-l3-8b-v-01_v63 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics