abte-restaurants-conv1d

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

• Loss: 0.4207
• F1-score: 0.4809

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
1.049	1.0	8	0.9959	0.1132
0.9836	2.0	16	0.9339	0.1441
0.9196	3.0	24	0.8801	0.1973
0.8701	4.0	32	0.8333	0.2290
0.8317	5.0	40	0.7927	0.2480
0.7934	6.0	48	0.7575	0.2669
0.7613	7.0	56	0.7267	0.2716
0.7252	8.0	64	0.6998	0.2727
0.7041	9.0	72	0.6765	0.2805
0.673	10.0	80	0.6561	0.2878
0.6481	11.0	88	0.6383	0.2995
0.6288	12.0	96	0.6227	0.3047
0.6111	13.0	104	0.6088	0.3062
0.6028	14.0	112	0.5963	0.3146
0.5846	15.0	120	0.5849	0.3222
0.572	16.0	128	0.5748	0.3228
0.5626	17.0	136	0.5658	0.3247
0.553	18.0	144	0.5574	0.3379
0.5337	19.0	152	0.5495	0.3445
0.5267	20.0	160	0.5422	0.3517
0.5284	21.0	168	0.5353	0.3531
0.5182	22.0	176	0.5289	0.3588
0.5141	23.0	184	0.5228	0.3611
0.4954	24.0	192	0.5170	0.3630
0.4907	25.0	200	0.5117	0.3664
0.4872	26.0	208	0.5069	0.3689
0.4809	27.0	216	0.5028	0.3771
0.4759	28.0	224	0.4987	0.3828
0.4755	29.0	232	0.4947	0.3885
0.4619	30.0	240	0.4911	0.3880
0.4581	31.0	248	0.4879	0.3889
0.4489	32.0	256	0.4845	0.3901
0.448	33.0	264	0.4811	0.3941
0.4459	34.0	272	0.4782	0.3965
0.442	35.0	280	0.4753	0.3976
0.4414	36.0	288	0.4724	0.3996
0.4237	37.0	296	0.4696	0.4047
0.4302	38.0	304	0.4670	0.4075
0.4203	39.0	312	0.4643	0.4105
0.4231	40.0	320	0.4618	0.4168
0.4214	41.0	328	0.4598	0.4191
0.4174	42.0	336	0.4583	0.4202
0.4121	43.0	344	0.4568	0.4244
0.4074	44.0	352	0.4548	0.4277
0.4009	45.0	360	0.4530	0.4322
0.3963	46.0	368	0.4513	0.4331
0.4023	47.0	376	0.4498	0.4342
0.4058	48.0	384	0.4483	0.4393
0.3866	49.0	392	0.4464	0.4398
0.3924	50.0	400	0.4450	0.4428
0.384	51.0	408	0.4439	0.4449
0.3905	52.0	416	0.4428	0.4475
0.3792	53.0	424	0.4417	0.4471
0.3737	54.0	432	0.4408	0.4463
0.3747	55.0	440	0.4399	0.4471
0.3769	56.0	448	0.4391	0.4479
0.3676	57.0	456	0.4383	0.4491
0.3701	58.0	464	0.4374	0.4494
0.3739	59.0	472	0.4366	0.4525
0.3693	60.0	480	0.4359	0.4592
0.3673	61.0	488	0.4349	0.4596
0.3634	62.0	496	0.4338	0.4647
0.356	63.0	504	0.4327	0.4687
0.3611	64.0	512	0.4319	0.4691
0.3565	65.0	520	0.4312	0.4694
0.356	66.0	528	0.4305	0.4729
0.3572	67.0	536	0.4297	0.4761
0.351	68.0	544	0.4289	0.4752
0.3485	69.0	552	0.4282	0.4761
0.3548	70.0	560	0.4278	0.4755
0.3509	71.0	568	0.4272	0.4757
0.3566	72.0	576	0.4267	0.4772
0.3428	73.0	584	0.4262	0.4767
0.3491	74.0	592	0.4259	0.4760
0.3378	75.0	600	0.4257	0.4760
0.3524	76.0	608	0.4255	0.4766
0.3596	77.0	616	0.4252	0.4772
0.3431	78.0	624	0.4248	0.4770
0.3645	79.0	632	0.4242	0.4760
0.3455	80.0	640	0.4236	0.4756
0.3435	81.0	648	0.4233	0.4759
0.3467	82.0	656	0.4229	0.4768
0.3403	83.0	664	0.4227	0.4778
0.3455	84.0	672	0.4224	0.4789
0.3415	85.0	680	0.4221	0.4787
0.3406	86.0	688	0.4219	0.4784
0.3378	87.0	696	0.4217	0.4791
0.3441	88.0	704	0.4215	0.4795
0.3389	89.0	712	0.4214	0.4795
0.3425	90.0	720	0.4213	0.4798
0.3412	91.0	728	0.4213	0.4799
0.3328	92.0	736	0.4211	0.4799
0.3392	93.0	744	0.4210	0.4799
0.3419	94.0	752	0.4209	0.4799
0.3297	95.0	760	0.4208	0.4799
0.3371	96.0	768	0.4208	0.4803
0.3358	97.0	776	0.4207	0.4803
0.3295	98.0	784	0.4207	0.4803
0.3405	99.0	792	0.4207	0.4809
0.3338	100.0	800	0.4207	0.4809

Framework versions

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