developer_uid: robert_irvine
submission_id: nitral-ai-hathor-tahsin-_9764_v4
model_name: nitral-ai-hathor-tahsin-_9764_v4
model_group: Nitral-AI/Hathor_Tahsin-
status: torndown
timestamp: 2024-08-05T01:02:14+00:00
num_battles: 167881
num_wins: 87204
celo_rating: 1214.59
family_friendly_score: 0.0
submission_type: basic
model_repo: Nitral-AI/Hathor_Tahsin-L3-8B-v0.9
model_architecture: LlamaForCausalLM
reward_repo: ChaiML/gpt2_xl_pairwise_89m_step_347634
model_num_parameters: 8030261248.0
best_of: 4
max_input_tokens: 512
max_output_tokens: 64
display_name: nitral-ai-hathor-tahsin-_9764_v4
is_internal_developer: True
language_model: Nitral-AI/Hathor_Tahsin-L3-8B-v0.9
model_size: 8B
ranking_group: single
us_pacific_date: 2024-08-04
win_ratio: 0.5194393647881536
generation_params: {'temperature': 1.2, 'top_p': 1.0, 'min_p': 0.1, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|end_header_id|>,', '<|eot_id|>,', '\n\n{user_name}', 'You:', '\n\n'], 'max_input_tokens': 512, 'best_of': 4, 'max_output_tokens': 64, 'reward_max_token_input': 256}
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: {message}\n', 'memory_template': '', 'prompt_template': '', 'response_template': 'Bot:', 'truncate_by_message': False, 'user_template': 'User: {message}\n'}
Resubmit model
Running pipeline stage MKMLizer
Starting job with name nitral-ai-hathor-tahsin-9764-v4-mkmlizer
Waiting for job on nitral-ai-hathor-tahsin-9764-v4-mkmlizer to finish
Stopping job with name nitral-ai-hathor-tahsin-9764-v4-mkmlizer
%s, retrying in %s seconds...
Starting job with name nitral-ai-hathor-tahsin-9764-v4-mkmlizer
Waiting for job on nitral-ai-hathor-tahsin-9764-v4-mkmlizer to finish
nitral-ai-hathor-tahsin-9764-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
nitral-ai-hathor-tahsin-9764-v4-mkmlizer: ║ _____ __ __ ║
nitral-ai-hathor-tahsin-9764-v4-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
nitral-ai-hathor-tahsin-9764-v4-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
nitral-ai-hathor-tahsin-9764-v4-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
nitral-ai-hathor-tahsin-9764-v4-mkmlizer: ║ /___/ ║
nitral-ai-hathor-tahsin-9764-v4-mkmlizer: ║ ║
nitral-ai-hathor-tahsin-9764-v4-mkmlizer: ║ Version: 0.9.9 ║
nitral-ai-hathor-tahsin-9764-v4-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
nitral-ai-hathor-tahsin-9764-v4-mkmlizer: ║ https://mk1.ai ║
nitral-ai-hathor-tahsin-9764-v4-mkmlizer: ║ ║
nitral-ai-hathor-tahsin-9764-v4-mkmlizer: ║ The license key for the current software has been verified as ║
nitral-ai-hathor-tahsin-9764-v4-mkmlizer: ║ belonging to: ║
nitral-ai-hathor-tahsin-9764-v4-mkmlizer: ║ ║
nitral-ai-hathor-tahsin-9764-v4-mkmlizer: ║ Chai Research Corp. ║
nitral-ai-hathor-tahsin-9764-v4-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
nitral-ai-hathor-tahsin-9764-v4-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
nitral-ai-hathor-tahsin-9764-v4-mkmlizer: ║ ║
nitral-ai-hathor-tahsin-9764-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
nitral-ai-hathor-tahsin-9764-v4-mkmlizer: Downloaded to shared memory in 31.664s
nitral-ai-hathor-tahsin-9764-v4-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpv3efdfyk, device:0
nitral-ai-hathor-tahsin-9764-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
nitral-ai-hathor-tahsin-9764-v4-mkmlizer: quantized model in 26.267s
nitral-ai-hathor-tahsin-9764-v4-mkmlizer: Processed model Nitral-AI/Hathor_Tahsin-L3-8B-v0.9 in 57.931s
nitral-ai-hathor-tahsin-9764-v4-mkmlizer: creating bucket guanaco-mkml-models
nitral-ai-hathor-tahsin-9764-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
nitral-ai-hathor-tahsin-9764-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/nitral-ai-hathor-tahsin-9764-v4
nitral-ai-hathor-tahsin-9764-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/nitral-ai-hathor-tahsin-9764-v4/config.json
nitral-ai-hathor-tahsin-9764-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/nitral-ai-hathor-tahsin-9764-v4/special_tokens_map.json
nitral-ai-hathor-tahsin-9764-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/nitral-ai-hathor-tahsin-9764-v4/tokenizer_config.json
nitral-ai-hathor-tahsin-9764-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/nitral-ai-hathor-tahsin-9764-v4/tokenizer.json
nitral-ai-hathor-tahsin-9764-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/nitral-ai-hathor-tahsin-9764-v4/flywheel_model.0.safetensors
nitral-ai-hathor-tahsin-9764-v4-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
nitral-ai-hathor-tahsin-9764-v4-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<11:37, 2.41s/it] Loading 0: 2%|▏ | 6/291 [00:04<03:05, 1.54it/s] Loading 0: 4%|▍ | 13/291 [00:05<01:06, 4.20it/s] Loading 0: 6%|▌ | 18/291 [00:05<00:41, 6.59it/s] Loading 0: 8%|▊ | 24/291 [00:05<00:27, 9.86it/s] Loading 0: 11%|█▏ | 33/291 [00:05<00:16, 15.82it/s] Loading 0: 14%|█▍ | 41/291 [00:05<00:11, 22.49it/s] Loading 0: 16%|█▌ | 47/291 [00:05<00:09, 25.89it/s] Loading 0: 18%|█▊ | 53/291 [00:05<00:07, 30.23it/s] Loading 0: 21%|██ | 60/291 [00:06<00:09, 25.47it/s] Loading 0: 23%|██▎ | 68/291 [00:06<00:06, 33.06it/s] Loading 0: 25%|██▌ | 74/291 [00:06<00:06, 34.80it/s] Loading 0: 27%|██▋ | 79/291 [00:06<00:05, 36.65it/s] Loading 0: 30%|██▉ | 86/291 [00:06<00:04, 42.35it/s] Loading 0: 32%|███▏ | 92/291 [00:06<00:04, 42.16it/s] Loading 0: 33%|███▎ | 97/291 [00:06<00:04, 43.45it/s] Loading 0: 36%|███▌ | 104/291 [00:07<00:03, 49.66it/s] Loading 0: 38%|███▊ | 110/291 [00:07<00:03, 46.13it/s] Loading 0: 40%|███▉ | 116/291 [00:07<00:03, 47.91it/s] Loading 0: 42%|████▏ | 123/291 [00:07<00:03, 45.36it/s] Loading 0: 45%|████▍ | 130/291 [00:07<00:03, 50.89it/s] Loading 0: 47%|████▋ | 136/291 [00:07<00:03, 51.03it/s] Loading 0: 49%|████▉ | 142/291 [00:07<00:03, 45.24it/s] Loading 0: 51%|█████ | 149/291 [00:08<00:02, 50.73it/s] Loading 0: 53%|█████▎ | 155/291 [00:08<00:02, 46.12it/s] Loading 0: 55%|█████▍ | 160/291 [00:08<00:02, 45.36it/s] Loading 0: 57%|█████▋ | 166/291 [00:08<00:03, 35.66it/s] Loading 0: 59%|█████▉ | 171/291 [00:08<00:03, 38.23it/s] Loading 0: 60%|██████ | 176/291 [00:08<00:02, 40.60it/s] Loading 0: 63%|██████▎ | 182/291 [00:08<00:02, 40.07it/s] Loading 0: 64%|██████▍ | 187/291 [00:09<00:02, 40.58it/s] Loading 0: 67%|██████▋ | 194/291 [00:09<00:02, 46.55it/s] Loading 0: 69%|██████▊ | 200/291 [00:09<00:02, 44.45it/s] Loading 0: 70%|███████ | 205/291 [00:09<00:01, 44.85it/s] Loading 0: 73%|███████▎ | 212/291 [00:09<00:01, 49.84it/s] Loading 0: 75%|███████▍ | 218/291 [00:09<00:01, 46.27it/s] Loading 0: 77%|███████▋ | 223/291 [00:09<00:01, 46.44it/s] Loading 0: 79%|███████▉ | 230/291 [00:09<00:01, 51.14it/s] Loading 0: 81%|████████ | 236/291 [00:10<00:01, 47.31it/s] Loading 0: 83%|████████▎ | 241/291 [00:10<00:01, 46.63it/s] Loading 0: 85%|████████▌ | 248/291 [00:10<00:00, 51.37it/s] Loading 0: 87%|████████▋ | 254/291 [00:10<00:00, 46.83it/s] Loading 0: 89%|████████▉ | 259/291 [00:10<00:00, 45.47it/s] Loading 0: 91%|█████████ | 265/291 [00:10<00:00, 48.47it/s] Loading 0: 93%|█████████▎| 270/291 [00:10<00:00, 32.61it/s] Loading 0: 95%|█████████▍| 275/291 [00:10<00:00, 35.96it/s] Loading 0: 97%|█████████▋| 281/291 [00:11<00:00, 37.56it/s] Loading 0: 98%|█████████▊| 286/291 [00:11<00:00, 39.41it/s] /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:957: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
nitral-ai-hathor-tahsin-9764-v4-mkmlizer: warnings.warn(
nitral-ai-hathor-tahsin-9764-v4-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:785: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
nitral-ai-hathor-tahsin-9764-v4-mkmlizer: warnings.warn(
nitral-ai-hathor-tahsin-9764-v4-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py:469: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
nitral-ai-hathor-tahsin-9764-v4-mkmlizer: warnings.warn(
nitral-ai-hathor-tahsin-9764-v4-mkmlizer: Downloading shards: 0%| | 0/2 [00:00<?, ?it/s] Downloading shards: 50%|█████ | 1/2 [00:05<00:05, 5.47s/it] Downloading shards: 100%|██████████| 2/2 [00:08<00:00, 4.11s/it] Downloading shards: 100%|██████████| 2/2 [00:08<00:00, 4.32s/it]
nitral-ai-hathor-tahsin-9764-v4-mkmlizer: Loading checkpoint shards: 0%| | 0/2 [00:00<?, ?it/s] Loading checkpoint shards: 50%|█████ | 1/2 [00:00<00:00, 2.45it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 4.04it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 3.68it/s]
nitral-ai-hathor-tahsin-9764-v4-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
nitral-ai-hathor-tahsin-9764-v4-mkmlizer: Saving duration: 1.344s
nitral-ai-hathor-tahsin-9764-v4-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 13.468s
nitral-ai-hathor-tahsin-9764-v4-mkmlizer: creating bucket guanaco-reward-models
nitral-ai-hathor-tahsin-9764-v4-mkmlizer: Bucket 's3://guanaco-reward-models/' created
nitral-ai-hathor-tahsin-9764-v4-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/nitral-ai-hathor-tahsin-9764-v4_reward
nitral-ai-hathor-tahsin-9764-v4-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/nitral-ai-hathor-tahsin-9764-v4_reward/config.json
nitral-ai-hathor-tahsin-9764-v4-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/nitral-ai-hathor-tahsin-9764-v4_reward/special_tokens_map.json
nitral-ai-hathor-tahsin-9764-v4-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/nitral-ai-hathor-tahsin-9764-v4_reward/tokenizer_config.json
nitral-ai-hathor-tahsin-9764-v4-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/nitral-ai-hathor-tahsin-9764-v4_reward/merges.txt
nitral-ai-hathor-tahsin-9764-v4-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/nitral-ai-hathor-tahsin-9764-v4_reward/vocab.json
nitral-ai-hathor-tahsin-9764-v4-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/nitral-ai-hathor-tahsin-9764-v4_reward/tokenizer.json
nitral-ai-hathor-tahsin-9764-v4-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/nitral-ai-hathor-tahsin-9764-v4_reward/reward.tensors
Job nitral-ai-hathor-tahsin-9764-v4-mkmlizer completed after 104.91s with status: succeeded
Stopping job with name nitral-ai-hathor-tahsin-9764-v4-mkmlizer
Pipeline stage MKMLizer completed in 106.58s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service nitral-ai-hathor-tahsin-9764-v4
Waiting for inference service nitral-ai-hathor-tahsin-9764-v4 to be ready
LLM-Router throws exception ConnectionError(ProtocolError('Connection aborted.', RemoteDisconnected('Remote end closed connection without response'))) for fourier
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service nitral-ai-hathor-tahsin-9764-v4 ready after 251.51614713668823s
Pipeline stage ISVCDeployer completed in 253.30s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.913877010345459s
Received healthy response to inference request in 1.0991969108581543s
Received healthy response to inference request in 1.1321754455566406s
Received healthy response to inference request in 1.0690932273864746s
Received healthy response to inference request in 1.0968551635742188s
5 requests
0 failed requests
5th percentile: 1.0746456146240235
10th percentile: 1.0801980018615722
20th percentile: 1.0913027763366698
30th percentile: 1.097323513031006
40th percentile: 1.0982602119445801
50th percentile: 1.0991969108581543
60th percentile: 1.1123883247375488
70th percentile: 1.1255797386169433
80th percentile: 1.2885157585144045
90th percentile: 1.6011963844299317
95th percentile: 1.7575366973876951
99th percentile: 1.8826089477539063
mean time: 1.2622395515441895
Pipeline stage StressChecker completed in 7.01s
nitral-ai-hathor-tahsin-_9764_v4 status is now deployed due to DeploymentManager action
nitral-ai-hathor-tahsin-_9764_v4 status is now inactive due to auto deactivation removed underperforming models
nitral-ai-hathor-tahsin-_9764_v4 status is now torndown due to DeploymentManager action