abte-restaurants-transformer

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

• Loss: 0.4235
• F1-score: 0.5421

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: 512
• eval_batch_size: 512
• seed: 42
• optimizer: Use 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	F1-score
0.7388	1.0	8	0.6483	0.0
0.5755	2.0	16	0.6447	0.0
0.558	3.0	24	0.6260	0.0
0.5373	4.0	32	0.6089	0.0
0.5429	5.0	40	0.6016	0.0
0.5312	6.0	48	0.5928	0.0
0.5186	7.0	56	0.5816	0.0007
0.4968	8.0	64	0.5678	0.0241
0.5044	9.0	72	0.5551	0.1569
0.4782	10.0	80	0.5470	0.1896
0.4593	11.0	88	0.5316	0.2667
0.4484	12.0	96	0.5223	0.3096
0.4292	13.0	104	0.5255	0.3096
0.4232	14.0	112	0.5056	0.3716
0.416	15.0	120	0.5070	0.3669
0.4142	16.0	128	0.5082	0.3830
0.4018	17.0	136	0.4959	0.4371
0.3924	18.0	144	0.4946	0.4415
0.3683	19.0	152	0.4900	0.4552
0.3854	20.0	160	0.4850	0.4703
0.4049	21.0	168	0.4875	0.4669
0.381	22.0	176	0.4785	0.4831
0.3789	23.0	184	0.4740	0.4917
0.3683	24.0	192	0.4786	0.4856
0.3689	25.0	200	0.4694	0.4983
0.3646	26.0	208	0.4741	0.4937
0.3585	27.0	216	0.4643	0.5025
0.3602	28.0	224	0.4617	0.5050
0.3685	29.0	232	0.4683	0.5004
0.352	30.0	240	0.4591	0.5036
0.3542	31.0	248	0.4551	0.5086
0.3536	32.0	256	0.4600	0.5045
0.344	33.0	264	0.4589	0.5061
0.3453	34.0	272	0.4500	0.5122
0.354	35.0	280	0.4594	0.5075
0.3528	36.0	288	0.4536	0.5199
0.3316	37.0	296	0.4535	0.5190
0.3397	38.0	304	0.4469	0.5209
0.3292	39.0	312	0.4493	0.5211
0.3276	40.0	320	0.4477	0.5217
0.3308	41.0	328	0.4519	0.5208
0.3301	42.0	336	0.4392	0.5208
0.3272	43.0	344	0.4492	0.5199
0.3273	44.0	352	0.4484	0.5210
0.3193	45.0	360	0.4406	0.5264
0.3268	46.0	368	0.4444	0.5268
0.3184	47.0	376	0.4399	0.5278
0.3229	48.0	384	0.4374	0.5271
0.3061	49.0	392	0.4439	0.5288
0.3176	50.0	400	0.4358	0.5257
0.3133	51.0	408	0.4346	0.5255
0.317	52.0	416	0.4392	0.5278
0.3025	53.0	424	0.4336	0.5261
0.2933	54.0	432	0.4340	0.5261
0.2991	55.0	440	0.4391	0.5274
0.2989	56.0	448	0.4323	0.5291
0.2984	57.0	456	0.4304	0.5321
0.2961	58.0	464	0.4390	0.5296
0.3014	59.0	472	0.4296	0.5298
0.2992	60.0	480	0.4302	0.5299
0.305	61.0	488	0.4315	0.5327
0.2959	62.0	496	0.4353	0.5343
0.2901	63.0	504	0.4292	0.5335
0.2977	64.0	512	0.4323	0.5341
0.2979	65.0	520	0.4257	0.5343
0.2887	66.0	528	0.4309	0.5357
0.2922	67.0	536	0.4282	0.5361
0.287	68.0	544	0.4300	0.5374
0.2866	69.0	552	0.4269	0.5374
0.2904	70.0	560	0.4266	0.5375
0.293	71.0	568	0.4274	0.5368
0.2974	72.0	576	0.4263	0.5351
0.2822	73.0	584	0.4295	0.5383
0.2865	74.0	592	0.4252	0.5369
0.284	75.0	600	0.4292	0.5384
0.2889	76.0	608	0.4245	0.5374
0.3004	77.0	616	0.4256	0.5387
0.2854	78.0	624	0.4252	0.5405
0.3023	79.0	632	0.4241	0.5412
0.2856	80.0	640	0.4251	0.5407
0.283	81.0	648	0.4258	0.5405
0.2882	82.0	656	0.4224	0.5393
0.281	83.0	664	0.4263	0.5403
0.2873	84.0	672	0.4267	0.5401
0.2788	85.0	680	0.4226	0.5398
0.2805	86.0	688	0.4261	0.5400
0.2854	87.0	696	0.4242	0.5408
0.296	88.0	704	0.4217	0.5406
0.2804	89.0	712	0.4248	0.5410
0.2815	90.0	720	0.4230	0.5426
0.2852	91.0	728	0.4221	0.5431
0.2874	92.0	736	0.4225	0.5413
0.2825	93.0	744	0.4238	0.5411
0.2833	94.0	752	0.4247	0.5414
0.2756	95.0	760	0.4234	0.5416
0.2789	96.0	768	0.4227	0.5420
0.2775	97.0	776	0.4232	0.5419
0.2787	98.0	784	0.4234	0.5419
0.2778	99.0	792	0.4236	0.5416
0.2805	100.0	800	0.4235	0.5421

Framework versions

• Transformers 4.47.0
• Pytorch 2.5.1+cu121
• Datasets 3.2.0
• Tokenizers 0.21.0