developer_uid: chai_backend_admin
submission_id: chaiml-elo-alignment-run-3_v27
model_name: chaiml-elo-alignment-run-3_v3
model_group: ChaiML/elo_alignment_run
status: torndown
timestamp: 2024-08-05T23:02:10+00:00
num_battles: 12793
num_wins: 7186
celo_rating: 1256.58
family_friendly_score: 0.0
submission_type: basic
model_repo: ChaiML/elo_alignment_run_3
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: chaiml-elo-alignment-run-3_v3
is_internal_developer: True
language_model: ChaiML/elo_alignment_run_3
model_size: 8B
ranking_group: single
us_pacific_date: 2024-08-05
win_ratio: 0.561713437035879
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, 'reward_max_token_input': 256}
formatter: {'memory_template': '', 'prompt_template': "{bot_name}'s Persona: {memory}\n####\n{prompt}\n<START>\n", 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': True}
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 chaiml-elo-alignment-run-3-v27-mkmlizer
Waiting for job on chaiml-elo-alignment-run-3-v27-mkmlizer to finish
Stopping job with name chaiml-elo-alignment-run-3-v27-mkmlizer
%s, retrying in %s seconds...
Starting job with name chaiml-elo-alignment-run-3-v27-mkmlizer
Waiting for job on chaiml-elo-alignment-run-3-v27-mkmlizer to finish
Stopping job with name chaiml-elo-alignment-run-3-v27-mkmlizer
%s, retrying in %s seconds...
Starting job with name chaiml-elo-alignment-run-3-v27-mkmlizer
Waiting for job on chaiml-elo-alignment-run-3-v27-mkmlizer to finish
chaiml-elo-alignment-run-3-v27-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-elo-alignment-run-3-v27-mkmlizer: ║ _____ __ __ ║
chaiml-elo-alignment-run-3-v27-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-elo-alignment-run-3-v27-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-elo-alignment-run-3-v27-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-elo-alignment-run-3-v27-mkmlizer: ║ /___/ ║
chaiml-elo-alignment-run-3-v27-mkmlizer: ║ ║
chaiml-elo-alignment-run-3-v27-mkmlizer: ║ Version: 0.9.9 ║
chaiml-elo-alignment-run-3-v27-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-elo-alignment-run-3-v27-mkmlizer: ║ https://mk1.ai ║
chaiml-elo-alignment-run-3-v27-mkmlizer: ║ ║
chaiml-elo-alignment-run-3-v27-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-elo-alignment-run-3-v27-mkmlizer: ║ belonging to: ║
chaiml-elo-alignment-run-3-v27-mkmlizer: ║ ║
chaiml-elo-alignment-run-3-v27-mkmlizer: ║ Chai Research Corp. ║
chaiml-elo-alignment-run-3-v27-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-elo-alignment-run-3-v27-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
chaiml-elo-alignment-run-3-v27-mkmlizer: ║ ║
chaiml-elo-alignment-run-3-v27-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-elo-alignment-run-3-v27-mkmlizer: Downloaded to shared memory in 49.675s
chaiml-elo-alignment-run-3-v27-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpnnz_okeo, device:0
chaiml-elo-alignment-run-3-v27-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-elo-alignment-run-3-v27-mkmlizer: quantized model in 29.130s
chaiml-elo-alignment-run-3-v27-mkmlizer: Processed model ChaiML/elo_alignment_run_3 in 78.805s
chaiml-elo-alignment-run-3-v27-mkmlizer: creating bucket guanaco-mkml-models
chaiml-elo-alignment-run-3-v27-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-elo-alignment-run-3-v27-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v27
chaiml-elo-alignment-run-3-v27-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v27/config.json
chaiml-elo-alignment-run-3-v27-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v27/special_tokens_map.json
chaiml-elo-alignment-run-3-v27-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v27/tokenizer_config.json
chaiml-elo-alignment-run-3-v27-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v27/tokenizer.json
chaiml-elo-alignment-run-3-v27-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v27/flywheel_model.0.safetensors
chaiml-elo-alignment-run-3-v27-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
chaiml-elo-alignment-run-3-v27-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 2%|▏ | 5/291 [00:00<00:10, 26.37it/s] Loading 0: 4%|▍ | 12/291 [00:00<00:08, 34.71it/s] Loading 0: 5%|▌ | 16/291 [00:00<00:08, 32.12it/s] Loading 0: 7%|▋ | 21/291 [00:00<00:07, 34.79it/s] Loading 0: 9%|▊ | 25/291 [00:00<00:08, 31.85it/s] Loading 0: 10%|█ | 30/291 [00:00<00:07, 36.10it/s] Loading 0: 12%|█▏ | 34/291 [00:01<00:10, 24.55it/s] Loading 0: 13%|█▎ | 37/291 [00:01<00:10, 24.45it/s] Loading 0: 14%|█▍ | 41/291 [00:01<00:10, 24.37it/s] Loading 0: 16%|█▋ | 48/291 [00:01<00:07, 31.56it/s] Loading 0: 18%|█▊ | 52/291 [00:01<00:07, 31.22it/s] Loading 0: 20%|█▉ | 57/291 [00:01<00:06, 33.45it/s] Loading 0: 21%|██ | 61/291 [00:01<00:07, 32.34it/s] Loading 0: 23%|██▎ | 66/291 [00:02<00:06, 34.82it/s] Loading 0: 24%|██▍ | 70/291 [00:02<00:06, 33.08it/s] Loading 0: 25%|██▌ | 74/291 [00:02<00:06, 32.90it/s] Loading 0: 27%|██▋ | 78/291 [00:02<00:06, 32.97it/s] Loading 0: 28%|██▊ | 82/291 [00:02<00:09, 22.74it/s] Loading 0: 29%|██▉ | 85/291 [00:02<00:08, 23.55it/s] Loading 0: 31%|███ | 90/291 [00:03<00:07, 27.60it/s] Loading 0: 32%|███▏ | 94/291 [00:03<00:06, 28.26it/s] Loading 0: 34%|███▍ | 99/291 [00:03<00:06, 31.81it/s] Loading 0: 35%|███▌ | 103/291 [00:03<00:06, 30.75it/s] Loading 0: 37%|███▋ | 108/291 [00:03<00:05, 33.51it/s] Loading 0: 38%|███▊ | 112/291 [00:03<00:05, 32.64it/s] Loading 0: 40%|███▉ | 116/291 [00:03<00:05, 32.91it/s] Loading 0: 42%|████▏ | 122/291 [00:03<00:04, 36.65it/s] Loading 0: 44%|████▎ | 127/291 [00:04<00:04, 34.44it/s] Loading 0: 46%|████▌ | 133/291 [00:04<00:05, 28.45it/s] Loading 0: 47%|████▋ | 137/291 [00:04<00:05, 29.05it/s] Loading 0: 48%|████▊ | 141/291 [00:04<00:05, 27.61it/s] Loading 0: 51%|█████ | 147/291 [00:04<00:04, 31.63it/s] Loading 0: 52%|█████▏ | 151/291 [00:04<00:04, 31.33it/s] Loading 0: 54%|█████▎ | 156/291 [00:05<00:03, 34.33it/s] Loading 0: 55%|█████▍ | 160/291 [00:05<00:03, 33.22it/s] Loading 0: 57%|█████▋ | 165/291 [00:05<00:03, 35.89it/s] Loading 0: 58%|█████▊ | 169/291 [00:05<00:03, 33.49it/s] Loading 0: 60%|█████▉ | 174/291 [00:05<00:03, 36.10it/s] Loading 0: 61%|██████ | 178/291 [00:05<00:03, 33.80it/s] Loading 0: 63%|██████▎ | 184/291 [00:05<00:02, 39.85it/s] Loading 0: 65%|██████▍ | 189/291 [00:06<00:04, 23.50it/s] Loading 0: 67%|██████▋ | 194/291 [00:06<00:03, 25.40it/s] Loading 0: 69%|██████▉ | 201/291 [00:06<00:02, 31.68it/s] Loading 0: 70%|███████ | 205/291 [00:06<00:02, 30.92it/s] Loading 0: 72%|███████▏ | 210/291 [00:06<00:02, 33.47it/s] Loading 0: 74%|███████▎ | 214/291 [00:06<00:02, 32.52it/s] Loading 0: 75%|███████▌ | 219/291 [00:07<00:02, 34.54it/s] Loading 0: 77%|███████▋ | 223/291 [00:07<00:02, 32.99it/s] Loading 0: 78%|███████▊ | 227/291 [00:07<00:01, 32.71it/s] Loading 0: 79%|███████▉ | 231/291 [00:07<00:01, 32.90it/s] Loading 0: 81%|████████ | 235/291 [00:07<00:02, 24.56it/s] Loading 0: 82%|████████▏ | 239/291 [00:07<00:02, 24.63it/s] Loading 0: 85%|████████▍ | 246/291 [00:07<00:01, 31.82it/s] Loading 0: 86%|████████▌ | 250/291 [00:08<00:01, 31.22it/s] Loading 0: 88%|████████▊ | 255/291 [00:08<00:01, 33.80it/s] Loading 0: 89%|████████▉ | 259/291 [00:08<00:00, 32.33it/s] Loading 0: 91%|█████████ | 264/291 [00:08<00:00, 35.27it/s] Loading 0: 92%|█████████▏| 268/291 [00:08<00:00, 32.97it/s] Loading 0: 94%|█████████▍| 273/291 [00:08<00:00, 34.97it/s] Loading 0: 95%|█████████▌| 277/291 [00:08<00:00, 33.18it/s] Loading 0: 97%|█████████▋| 281/291 [00:09<00:00, 33.03it/s] Loading 0: 98%|█████████▊| 286/291 [00:14<00:01, 2.56it/s] Loading 0: 99%|█████████▉| 289/291 [00:14<00:00, 3.18it/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.
chaiml-elo-alignment-run-3-v27-mkmlizer: warnings.warn(
chaiml-elo-alignment-run-3-v27-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.
chaiml-elo-alignment-run-3-v27-mkmlizer: warnings.warn(
chaiml-elo-alignment-run-3-v27-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.
chaiml-elo-alignment-run-3-v27-mkmlizer: warnings.warn(
chaiml-elo-alignment-run-3-v27-mkmlizer: Downloading shards: 0%| | 0/2 [00:00<?, ?it/s] Downloading shards: 50%|█████ | 1/2 [00:05<00:05, 5.15s/it] Downloading shards: 100%|██████████| 2/2 [00:07<00:00, 3.65s/it] Downloading shards: 100%|██████████| 2/2 [00:07<00:00, 3.88s/it]
chaiml-elo-alignment-run-3-v27-mkmlizer: Loading checkpoint shards: 0%| | 0/2 [00:00<?, ?it/s] Loading checkpoint shards: 50%|█████ | 1/2 [00:00<00:00, 2.38it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 3.92it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 3.57it/s]
chaiml-elo-alignment-run-3-v27-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
chaiml-elo-alignment-run-3-v27-mkmlizer: Saving duration: 1.358s
chaiml-elo-alignment-run-3-v27-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 13.452s
chaiml-elo-alignment-run-3-v27-mkmlizer: creating bucket guanaco-reward-models
chaiml-elo-alignment-run-3-v27-mkmlizer: Bucket 's3://guanaco-reward-models/' created
chaiml-elo-alignment-run-3-v27-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/chaiml-elo-alignment-run-3-v27_reward
chaiml-elo-alignment-run-3-v27-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/chaiml-elo-alignment-run-3-v27_reward/config.json
chaiml-elo-alignment-run-3-v27-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/chaiml-elo-alignment-run-3-v27_reward/special_tokens_map.json
chaiml-elo-alignment-run-3-v27-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/chaiml-elo-alignment-run-3-v27_reward/tokenizer_config.json
chaiml-elo-alignment-run-3-v27-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/chaiml-elo-alignment-run-3-v27_reward/merges.txt
chaiml-elo-alignment-run-3-v27-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/chaiml-elo-alignment-run-3-v27_reward/vocab.json
chaiml-elo-alignment-run-3-v27-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/chaiml-elo-alignment-run-3-v27_reward/tokenizer.json
chaiml-elo-alignment-run-3-v27-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/chaiml-elo-alignment-run-3-v27_reward/reward.tensors
Job chaiml-elo-alignment-run-3-v27-mkmlizer completed after 125.46s with status: succeeded
Stopping job with name chaiml-elo-alignment-run-3-v27-mkmlizer
Pipeline stage MKMLizer completed in 138.55s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service chaiml-elo-alignment-run-3-v27
Failed to get response for submission mistralai-mixtral-8x7b_3473_v117: ('http://mistralai-mixtral-8x7b-3473-v117-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '{"error":"ValueError : [TypeError(\\"\'numpy.int64\' object is not iterable\\"), TypeError(\'vars() argument must have __dict__ attribute\')]"}')
Waiting for inference service chaiml-elo-alignment-run-3-v27 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service chaiml-elo-alignment-run-3-v27 ready after 181.21833062171936s
Pipeline stage ISVCDeployer completed in 183.23s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.277395248413086s
Received healthy response to inference request in 1.3714802265167236s
Received healthy response to inference request in 1.4140732288360596s
Received healthy response to inference request in 1.401961326599121s
Received healthy response to inference request in 1.3959324359893799s
5 requests
0 failed requests
5th percentile: 1.3763706684112549
10th percentile: 1.3812611103057861
20th percentile: 1.3910419940948486
30th percentile: 1.3971382141113282
40th percentile: 1.3995497703552247
50th percentile: 1.401961326599121
60th percentile: 1.4068060874938966
70th percentile: 1.4116508483886718
80th percentile: 1.586737632751465
90th percentile: 1.9320664405822754
95th percentile: 2.1047308444976807
99th percentile: 2.242862367630005
mean time: 1.572168493270874
Pipeline stage StressChecker completed in 8.58s
chaiml-elo-alignment-run-3_v27 status is now deployed due to DeploymentManager action
chaiml-elo-alignment-run-3_v27 status is now inactive due to auto deactivation removed underperforming models
chaiml-elo-alignment-run-3_v27 status is now deployed due to admin request
chaiml-elo-alignment-run-3_v27 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of chaiml-elo-alignment-run-3_v27
Running pipeline stage ISVCDeleter
Checking if service chaiml-elo-alignment-run-3-v27 is running
Tearing down inference service chaiml-elo-alignment-run-3-v27
Service chaiml-elo-alignment-run-3-v27 has been torndown
Pipeline stage ISVCDeleter completed in 5.72s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key chaiml-elo-alignment-run-3-v27/config.json from bucket guanaco-mkml-models
Deleting key chaiml-elo-alignment-run-3-v27/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key chaiml-elo-alignment-run-3-v27/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key chaiml-elo-alignment-run-3-v27/tokenizer.json from bucket guanaco-mkml-models
Deleting key chaiml-elo-alignment-run-3-v27/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key chaiml-elo-alignment-run-3-v27_reward/config.json from bucket guanaco-reward-models
Deleting key chaiml-elo-alignment-run-3-v27_reward/merges.txt from bucket guanaco-reward-models
Deleting key chaiml-elo-alignment-run-3-v27_reward/reward.tensors from bucket guanaco-reward-models
Deleting key chaiml-elo-alignment-run-3-v27_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key chaiml-elo-alignment-run-3-v27_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key chaiml-elo-alignment-run-3-v27_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key chaiml-elo-alignment-run-3-v27_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.19s
chaiml-elo-alignment-run-3_v27 status is now torndown due to DeploymentManager action