qwen3-32b-tos-game-docs-c4-lora-round2 API & Inference Endpoint

More information needed

More information needed

More information needed

The following hyperparameters were used during training:

learning_rate: 3.5e-05
train_batch_size: 1
eval_batch_size: 1
seed: 42
distributed_type: multi-GPU
num_devices: 4
gradient_accumulation_steps: 2
total_train_batch_size: 8
total_eval_batch_size: 4
optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 64
training_steps: 2148

Table with columns: Training Loss, Epoch, Step, Validation Loss
Training Loss	Epoch	Step	Validation Loss
No log	0	0	1.7482
1.8044	1.0	716	1.2268
1.7514	2.0	1432	1.1939
1.7276	3.0	2148	1.1895

More information needed

More information needed

More information needed

The following hyperparameters were used during training:

learning_rate: 3.5e-05
train_batch_size: 1
eval_batch_size: 1
seed: 42
distributed_type: multi-GPU
num_devices: 4
gradient_accumulation_steps: 2
total_train_batch_size: 8
total_eval_batch_size: 4
optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 64
training_steps: 2148

Table with columns: Training Loss, Epoch, Step, Validation Loss
Training Loss	Epoch	Step	Validation Loss
No log	0	0	1.7482
1.8044	1.0	716	1.2268
1.7514	2.0	1432	1.1939
1.7276	3.0	2148	1.1895

qwen3-32b-tos-game-docs-c4-lora-round2