developer_uid: Nitral-AI
submission_id: nitral-ai-hathor-l3-8b-v-01_v10
model_name: nitral-ai-hathor-l3-8b-v-01_v1
model_group: Nitral-AI/Hathor-L3-8B-v
status: torndown
timestamp: 2024-06-22T22:44:55+00:00
num_battles: 22752
num_wins: 12220
celo_rating: 1220.24
family_friendly_score: 0.0
submission_type: basic
model_repo: Nitral-AI/Hathor-L3-8B-v.01
model_architecture: LlamaForCausalLM
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
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_v1
is_internal_developer: False
language_model: Nitral-AI/Hathor-L3-8B-v.01
model_size: 8B
ranking_group: single
us_pacific_date: 2024-06-22
win_ratio: 0.5370956399437412
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': '<|im_start|>system\n{memory}<|im_end|>\n', 'prompt_template': '<|im_start|>user\n{prompt}<|im_end|>\n', 'bot_template': '<|im_start|>assistant\n{bot_name}: {message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{user_name}: {message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n{bot_name}:', 'truncate_by_message': False}
reward_formatter: {'bot_template': '{bot_name}: {message}\n', 'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', '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-v10-mkmlizer
Waiting for job on nitral-ai-hathor-l3-8b-v-01-v10-mkmlizer to finish
nitral-ai-hathor-l3-8b-v-01-v10-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
nitral-ai-hathor-l3-8b-v-01-v10-mkmlizer: ║ _____ __ __ ║
nitral-ai-hathor-l3-8b-v-01-v10-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
nitral-ai-hathor-l3-8b-v-01-v10-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
nitral-ai-hathor-l3-8b-v-01-v10-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
nitral-ai-hathor-l3-8b-v-01-v10-mkmlizer: ║ /___/ ║
nitral-ai-hathor-l3-8b-v-01-v10-mkmlizer: ║ ║
nitral-ai-hathor-l3-8b-v-01-v10-mkmlizer: ║ Version: 0.8.14 ║
nitral-ai-hathor-l3-8b-v-01-v10-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
nitral-ai-hathor-l3-8b-v-01-v10-mkmlizer: ║ https://mk1.ai ║
nitral-ai-hathor-l3-8b-v-01-v10-mkmlizer: ║ ║
nitral-ai-hathor-l3-8b-v-01-v10-mkmlizer: ║ The license key for the current software has been verified as ║
nitral-ai-hathor-l3-8b-v-01-v10-mkmlizer: ║ belonging to: ║
nitral-ai-hathor-l3-8b-v-01-v10-mkmlizer: ║ ║
nitral-ai-hathor-l3-8b-v-01-v10-mkmlizer: ║ Chai Research Corp. ║
nitral-ai-hathor-l3-8b-v-01-v10-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
nitral-ai-hathor-l3-8b-v-01-v10-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
nitral-ai-hathor-l3-8b-v-01-v10-mkmlizer: ║ ║
nitral-ai-hathor-l3-8b-v-01-v10-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
nitral-ai-hathor-l3-8b-v-01-v10-mkmlizer: /opt/conda/lib/python3.10/site-packages/huggingface_hub/utils/_deprecation.py:131: FutureWarning: 'list_files_info' (from 'huggingface_hub.hf_api') is deprecated and will be removed from version '0.23'. Use `list_repo_tree` and `get_paths_info` instead.
nitral-ai-hathor-l3-8b-v-01-v10-mkmlizer: warnings.warn(warning_message, FutureWarning)
nitral-ai-hathor-l3-8b-v-01-v10-mkmlizer: Downloaded to shared memory in 23.080s
nitral-ai-hathor-l3-8b-v-01-v10-mkmlizer: quantizing model to /dev/shm/model_cache
nitral-ai-hathor-l3-8b-v-01-v10-mkmlizer: Saving flywheel model at /dev/shm/model_cache
nitral-ai-hathor-l3-8b-v-01-v10-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<10:54, 2.26s/it] Loading 0: 6%|▌ | 17/291 [00:04<00:54, 5.02it/s] Loading 0: 11%|█▏ | 33/291 [00:04<00:22, 11.48it/s] Loading 0: 18%|█▊ | 51/291 [00:04<00:11, 20.91it/s] Loading 0: 22%|██▏ | 65/291 [00:05<00:08, 25.44it/s] Loading 0: 28%|██▊ | 81/291 [00:05<00:05, 36.62it/s] Loading 0: 33%|███▎ | 96/291 [00:05<00:04, 48.62it/s] Loading 0: 39%|███▉ | 114/291 [00:05<00:02, 64.77it/s] Loading 0: 45%|████▌ | 131/291 [00:05<00:01, 81.06it/s] Loading 0: 51%|█████ | 149/291 [00:05<00:01, 97.33it/s] Loading 0: 57%|█████▋ | 166/291 [00:06<00:01, 74.64it/s] Loading 0: 63%|██████▎ | 184/291 [00:06<00:01, 88.96it/s] Loading 0: 68%|██████▊ | 198/291 [00:06<00:01, 90.96it/s] Loading 0: 73%|███████▎ | 213/291 [00:06<00:00, 101.62it/s] Loading 0: 79%|███████▉ | 231/291 [00:06<00:00, 117.04it/s] Loading 0: 86%|████████▌ | 249/291 [00:06<00:00, 129.44it/s] Loading 0: 91%|█████████▏| 266/291 [00:06<00:00, 86.73it/s] Loading 0: 97%|█████████▋| 283/291 [00:07<00:00, 100.51it/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-v10-mkmlizer: quantized model in 23.423s
nitral-ai-hathor-l3-8b-v-01-v10-mkmlizer: Processed model Nitral-AI/Hathor-L3-8B-v.01 in 48.964s
nitral-ai-hathor-l3-8b-v-01-v10-mkmlizer: creating bucket guanaco-mkml-models
nitral-ai-hathor-l3-8b-v-01-v10-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
nitral-ai-hathor-l3-8b-v-01-v10-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v10
nitral-ai-hathor-l3-8b-v-01-v10-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v10/config.json
nitral-ai-hathor-l3-8b-v-01-v10-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v10/special_tokens_map.json
nitral-ai-hathor-l3-8b-v-01-v10-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v10/tokenizer_config.json
nitral-ai-hathor-l3-8b-v-01-v10-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v10/tokenizer.json
nitral-ai-hathor-l3-8b-v-01-v10-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v10/flywheel_model.0.safetensors
nitral-ai-hathor-l3-8b-v-01-v10-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:757: 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-v10-mkmlizer: warnings.warn(
nitral-ai-hathor-l3-8b-v-01-v10-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-v10-mkmlizer: warnings.warn(
nitral-ai-hathor-l3-8b-v-01-v10-mkmlizer: /opt/conda/lib/python3.10/site-packages/torch/_utils.py:831: UserWarning: TypedStorage is deprecated. It will be removed in the future and UntypedStorage will be the only storage class. This should only matter to you if you are using storages directly. To access UntypedStorage directly, use tensor.untyped_storage() instead of tensor.storage()
nitral-ai-hathor-l3-8b-v-01-v10-mkmlizer: return self.fget.__get__(instance, owner)()
nitral-ai-hathor-l3-8b-v-01-v10-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
nitral-ai-hathor-l3-8b-v-01-v10-mkmlizer: Saving duration: 0.390s
nitral-ai-hathor-l3-8b-v-01-v10-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.096s
nitral-ai-hathor-l3-8b-v-01-v10-mkmlizer: creating bucket guanaco-reward-models
nitral-ai-hathor-l3-8b-v-01-v10-mkmlizer: Bucket 's3://guanaco-reward-models/' created
nitral-ai-hathor-l3-8b-v-01-v10-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v10_reward
nitral-ai-hathor-l3-8b-v-01-v10-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v10_reward/config.json
nitral-ai-hathor-l3-8b-v-01-v10-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v10_reward/merges.txt
nitral-ai-hathor-l3-8b-v-01-v10-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v10_reward/tokenizer_config.json
nitral-ai-hathor-l3-8b-v-01-v10-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v10_reward/special_tokens_map.json
nitral-ai-hathor-l3-8b-v-01-v10-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v10_reward/vocab.json
nitral-ai-hathor-l3-8b-v-01-v10-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v10_reward/tokenizer.json
nitral-ai-hathor-l3-8b-v-01-v10-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v10_reward/reward.tensors
Job nitral-ai-hathor-l3-8b-v-01-v10-mkmlizer completed after 83.39s with status: succeeded
Stopping job with name nitral-ai-hathor-l3-8b-v-01-v10-mkmlizer
Pipeline stage MKMLizer completed in 83.80s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.13s
Running pipeline stage ISVCDeployer
Creating inference service nitral-ai-hathor-l3-8b-v-01-v10
Waiting for inference service nitral-ai-hathor-l3-8b-v-01-v10 to be ready
Inference service nitral-ai-hathor-l3-8b-v-01-v10 ready after 40.233784675598145s
Pipeline stage ISVCDeployer completed in 45.96s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.167536497116089s
Received healthy response to inference request in 1.4888415336608887s
Received healthy response to inference request in 1.2637608051300049s
Received healthy response to inference request in 1.2666711807250977s
Received healthy response to inference request in 1.2551579475402832s
5 requests
0 failed requests
5th percentile: 1.2568785190582275
10th percentile: 1.258599090576172
20th percentile: 1.2620402336120606
30th percentile: 1.2643428802490235
40th percentile: 1.2655070304870606
50th percentile: 1.2666711807250977
60th percentile: 1.355539321899414
70th percentile: 1.4444074630737305
80th percentile: 1.6245805263519288
90th percentile: 1.896058511734009
95th percentile: 2.0317975044250485
99th percentile: 2.140388698577881
mean time: 1.4883935928344727
Pipeline stage StressChecker completed in 8.24s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.05s
nitral-ai-hathor-l3-8b-v-01_v10 status is now deployed due to DeploymentManager action
nitral-ai-hathor-l3-8b-v-01_v10 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of nitral-ai-hathor-l3-8b-v-01_v10
Running pipeline stage ISVCDeleter
Checking if service nitral-ai-hathor-l3-8b-v-01-v10 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.47s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key nitral-ai-hathor-l3-8b-v-01-v10/config.json from bucket guanaco-mkml-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v10/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v10/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v10/tokenizer.json from bucket guanaco-mkml-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v10/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key nitral-ai-hathor-l3-8b-v-01-v10_reward/config.json from bucket guanaco-reward-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v10_reward/merges.txt from bucket guanaco-reward-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v10_reward/reward.tensors from bucket guanaco-reward-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v10_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v10_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v10_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v10_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.41s
nitral-ai-hathor-l3-8b-v-01_v10 status is now torndown due to DeploymentManager action