fine_tuned_eli5_callback10

This model is a fine-tuned version of Qwen/Qwen2-1.5B on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.1230
• Accuracy: 0.9747

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: 2e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• 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: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.7967	0.0210	100	0.3296	0.8710
0.5957	0.0421	200	0.5430	0.8329
0.386	0.0631	300	0.6117	0.8694
0.3981	0.0841	400	0.3349	0.9129
0.3357	0.1052	500	0.2388	0.9117
0.2831	0.1262	600	0.4056	0.9063
0.4625	0.1472	700	0.2346	0.9058
0.3478	0.1683	800	0.1944	0.9259
0.2524	0.1893	900	0.3200	0.9203
0.3523	0.2103	1000	0.3342	0.9113
0.2756	0.2314	1100	0.2443	0.9423
0.2814	0.2524	1200	0.2346	0.9349
0.2636	0.2735	1300	0.5285	0.9018
0.2491	0.2945	1400	0.1802	0.9472
0.2328	0.3155	1500	0.2347	0.9468
0.2113	0.3366	1600	0.2146	0.9453
0.2342	0.3576	1700	0.2253	0.9406
0.2102	0.3786	1800	0.1987	0.9515
0.1518	0.3997	1900	0.2878	0.9373
0.2326	0.4207	2000	0.2071	0.9489
0.2018	0.4417	2100	0.1554	0.9498
0.1924	0.4628	2200	0.1812	0.9515
0.2139	0.4838	2300	0.3613	0.9302
0.2801	0.5048	2400	0.1490	0.9527
0.1979	0.5259	2500	0.1786	0.9546
0.1695	0.5469	2600	0.1765	0.9536
0.1541	0.5679	2700	0.1390	0.9631
0.1527	0.5890	2800	0.1198	0.9598
0.1711	0.6100	2900	0.1841	0.9593
0.2014	0.6310	3000	0.1497	0.9621
0.1174	0.6521	3100	0.1464	0.9671
0.1452	0.6731	3200	0.1323	0.9652
0.1367	0.6942	3300	0.1316	0.9659
0.1798	0.7152	3400	0.2200	0.9553
0.1683	0.7362	3500	0.1399	0.9655
0.1426	0.7573	3600	0.1146	0.9726
0.203	0.7783	3700	0.1601	0.9666
0.1452	0.7993	3800	0.1491	0.9692
0.1602	0.8204	3900	0.1251	0.9740
0.1451	0.8414	4000	0.1192	0.9747
0.14	0.8624	4100	0.1441	0.9695
0.158	0.8835	4200	0.1428	0.9692
0.1211	0.9045	4300	0.1841	0.9619
0.1324	0.9255	4400	0.1587	0.9657
0.1153	0.9466	4500	0.1411	0.9697
0.1321	0.9676	4600	0.1230	0.9747

Framework versions

• Transformers 4.49.0
• Pytorch 2.6.0+cu126
• Datasets 3.3.2
• Tokenizers 0.21.0