developer_uid: chai_backend_admin
submission_id: chaiml-gspo-glm47-chai-_96852_v1
model_name: chaiml-gspo-glm47-chai-_96852_v1
model_group: ChaiML/gspo-glm47-chai-r
status: torndown
timestamp: 2026-03-20T22:21:32+00:00
num_battles: 10640
num_wins: 5976
celo_rating: 1338.12
family_friendly_score: 0.0
family_friendly_standard_error: 0.0
submission_type: basic
model_repo: ChaiML/gspo-glm47-chai-rm-zy-data-step400
model_architecture: Glm4MoeForCausalLM
model_num_parameters: 24110003200.0
best_of: 8
max_input_tokens: 1500
max_output_tokens: 80
reward_model: default
display_name: chaiml-gspo-glm47-chai-_96852_v1
ineligible_reason: max_output_tokens!=64
is_internal_developer: True
language_model: ChaiML/gspo-glm47-chai-rm-zy-data-step400
model_size: 24B
ranking_group: single
us_pacific_date: 2026-03-17
win_ratio: 0.5616541353383459
generation_params: {'temperature': 1.0, 'top_p': 0.95, 'min_p': 0.0, 'top_k': 60, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['####', '<|user|>', '<|assistant|>', '</s>', '<|im_end|>'], 'max_input_tokens': 1500, 'best_of': 8, 'max_output_tokens': 80}
formatter: {'memory_template': "[gMASK]<sop><|system|>\n{bot_name}'s persona: {memory}", 'prompt_template': '', 'bot_template': '<|assistant|>\n{bot_name}: {message}', 'user_template': '<|user|>\n{message}', 'response_template': '<|assistant|>\n<think></think>\n{bot_name}:', 'truncate_by_message': True}
Resubmit model
Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline %s
run pipeline stage %s
Running pipeline stage VLLMUploader
Starting job with name chaiml-gspo-glm47-chai-96852-v1-uploader
Waiting for job on chaiml-gspo-glm47-chai-96852-v1-uploader to finish
chaiml-gspo-glm47-chai-96852-v1-uploader: Using quantization_mode: fp8
chaiml-gspo-glm47-chai-96852-v1-uploader: Checking if ChaiML/gspo-glm47-chai-rm-zy-data-step400-FP8 already exists in ChaiML
chaiml-gspo-glm47-chai-96852-v1-uploader: Downloading snapshot of ChaiML/gspo-glm47-chai-rm-zy-data-step400...
2026-03-17T17:21:40.822542+00:00 monitor updated for chaiml-gspo-glm47-chai-_96852_v1
2026-03-17T17:22:40.928688+00:00 monitor updated for chaiml-gspo-glm47-chai-_96852_v1
2026-03-17T17:23:41.027960+00:00 monitor updated for chaiml-gspo-glm47-chai-_96852_v1
2026-03-17T17:24:41.127316+00:00 monitor updated for chaiml-gspo-glm47-chai-_96852_v1
2026-03-17T17:25:41.234515+00:00 monitor updated for chaiml-gspo-glm47-chai-_96852_v1
chaiml-gspo-glm47-chai-96852-v1-uploader: Downloaded in 266.941s
chaiml-gspo-glm47-chai-96852-v1-uploader: Loading /tmp/model_input...
chaiml-gspo-glm47-chai-96852-v1-uploader: The tokenizer you are loading from '/tmp/model_input' with an incorrect regex pattern: https://huggingface.co/mistralai/Mistral-Small-3.1-24B-Instruct-2503/discussions/84#69121093e8b480e709447d5e. This will lead to incorrect tokenization. You should set the `fix_mistral_regex=True` flag when loading this tokenizer to fix this issue.
chaiml-gspo-glm47-chai-96852-v1-uploader: `torch_dtype` is deprecated! Use `dtype` instead!
2026-03-17T17:26:41.341467+00:00 monitor updated for chaiml-gspo-glm47-chai-_96852_v1
chaiml-gspo-glm47-chai-96852-v1-uploader: Some parameters are on the meta device because they were offloaded to the cpu.
chaiml-gspo-glm47-chai-96852-v1-uploader: Applying quantization...
chaiml-gspo-glm47-chai-96852-v1-uploader: The tokenizer you are loading from '/tmp/model_input' with an incorrect regex pattern: https://huggingface.co/mistralai/Mistral-Small-3.1-24B-Instruct-2503/discussions/84#69121093e8b480e709447d5e. This will lead to incorrect tokenization. You should set the `fix_mistral_regex=True` flag when loading this tokenizer to fix this issue.
chaiml-gspo-glm47-chai-96852-v1-uploader: 2026-03-17T10:26:36.500969-0700 | reset | INFO - Compression lifecycle reset
chaiml-gspo-glm47-chai-96852-v1-uploader: 2026-03-17T10:26:36.583076-0700 | from_modifiers | INFO - Creating recipe from modifiers
chaiml-gspo-glm47-chai-96852-v1-uploader: 2026-03-17T10:27:33.157253-0700 | initialize | INFO - Compression lifecycle initialized for 1 modifiers
chaiml-gspo-glm47-chai-96852-v1-uploader: 2026-03-17T10:27:33.157753-0700 | IndependentPipeline | INFO - Inferred `DataFreePipeline` for `QuantizationModifier`
2026-03-17T17:27:41.446095+00:00 monitor updated for chaiml-gspo-glm47-chai-_96852_v1
chaiml-gspo-glm47-chai-96852-v1-uploader: Some parameters are on the meta device because they were offloaded to the cpu.
2026-03-17T17:28:41.530885+00:00 monitor updated for chaiml-gspo-glm47-chai-_96852_v1
2026-03-17T17:29:41.615819+00:00 monitor updated for chaiml-gspo-glm47-chai-_96852_v1
2026-03-17T17:30:41.702838+00:00 monitor updated for chaiml-gspo-glm47-chai-_96852_v1
2026-03-17T17:31:41.794366+00:00 monitor updated for chaiml-gspo-glm47-chai-_96852_v1
2026-03-17T17:32:41.884193+00:00 monitor updated for chaiml-gspo-glm47-chai-_96852_v1
2026-03-17T17:33:41.971352+00:00 monitor updated for chaiml-gspo-glm47-chai-_96852_v1
chaiml-gspo-glm47-chai-96852-v1-uploader: 2026-03-17T10:34:08.712895-0700 | finalize | INFO - Compression lifecycle finalized for 1 modifiers
chaiml-gspo-glm47-chai-96852-v1-uploader: 2026-03-17T10:34:15.686053-0700 | post_process | WARNING - Optimized model is not saved. To save, please provide`output_dir` as input arg.Ex. `oneshot(..., output_dir=...)`
chaiml-gspo-glm47-chai-96852-v1-uploader: Saving to /dev/shm/model_output...
chaiml-gspo-glm47-chai-96852-v1-uploader: 2026-03-17T10:34:15.720889-0700 | get_model_compressor | INFO - skip_sparsity_compression_stats set to True. Skipping sparsity compression statistic calculations. No sparsity compressor will be applied.
2026-03-17T17:34:42.061234+00:00 monitor updated for chaiml-gspo-glm47-chai-_96852_v1
2026-03-17T17:35:42.151342+00:00 monitor updated for chaiml-gspo-glm47-chai-_96852_v1
chaiml-gspo-glm47-chai-_96852_v1 status is now deployed due to DeploymentManager action
chaiml-gspo-glm47-chai-_96852_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-gspo-glm47-chai-_96852_v1 status is now torndown due to DeploymentManager action