careerbot_PG6_google_flan-t5-small_model

This model is a fine-tuned version of google/flan-t5-small on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.6685

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 1e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 1
• training_steps: 3372

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	105	21.1784
No log	2.0	211	7.1162
No log	3.0	316	4.7947
No log	4.0	422	4.4165
No log	5.0	527	4.1394
No log	6.0	633	3.7892
No log	7.0	738	3.5130
No log	8.0	844	3.2547
No log	9.0	949	3.0385
No log	10.0	1055	2.8504
No log	11.0	1160	2.6901
No log	12.0	1266	2.5468
No log	13.0	1371	2.4245
No log	14.0	1477	2.3141
No log	15.0	1582	2.2212
No log	16.0	1688	2.1392
No log	17.0	1793	2.0683
No log	18.0	1899	2.0034
No log	19.0	2004	1.9474
No log	20.0	2110	1.9004
No log	21.0	2215	1.8585
No log	22.0	2321	1.8215
No log	23.0	2426	1.7892
No log	24.0	2532	1.7609
No log	25.0	2637	1.7387
No log	26.0	2743	1.7178
No log	27.0	2848	1.7033
No log	28.0	2954	1.6899
No log	29.0	3059	1.6804
No log	30.0	3165	1.6734
No log	31.0	3270	1.6694
No log	31.96	3372	1.6685

Framework versions

• Transformers 4.35.0
• Pytorch 2.5.0+cu124
• Datasets 2.19.0
• Tokenizers 0.14.1