AMD-bot:Cutomer support automation

This model is a fine-tuned version of openai-community/gpt2 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.5349

Model description

FineTuned gpt2-127M

Intended uses & limitations

This model is strictly licensed to be used for AMD Customer Support Automation

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 0.001
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 16
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 100

Training results

Training Loss	Epoch	Step	Validation Loss
0.8271	1.0	523	1.5899
0.5972	2.0	1046	1.1333
0.4294	3.0	1569	0.9262
0.3194	4.0	2092	0.7871
0.2746	5.0	2615	0.7179
0.2798	6.0	3138	0.6662
0.2385	7.0	3661	0.6456
0.2246	8.0	4184	0.6130
0.2104	9.0	4707	0.6052
0.2086	10.0	5230	0.5823
0.2237	11.0	5753	0.5626
0.1805	12.0	6276	0.5662
0.1748	13.0	6799	0.5578
0.1779	14.0	7322	0.5472
0.191	15.0	7845	0.5309
0.1615	16.0	8368	0.5256
0.159	17.0	8891	0.5271
0.158	18.0	9414	0.5349

Framework versions

• Transformers 4.55.0
• Pytorch 2.6.0+cu124
• Datasets 2.19.1
• Tokenizers 0.21.2