abte-restaurants-lstm

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

• Loss: 0.4099
• F1-score: 0.5148

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
1.0573	1.0	8	0.9615	0.1989
0.9191	2.0	16	0.8449	0.2300
0.8101	3.0	24	0.7552	0.2088
0.7196	4.0	32	0.6882	0.1698
0.6586	5.0	40	0.6394	0.1228
0.5985	6.0	48	0.6045	0.1066
0.5498	7.0	56	0.5796	0.1183
0.5097	8.0	64	0.5627	0.1419
0.5015	9.0	72	0.5508	0.1808
0.4727	10.0	80	0.5408	0.2222
0.4533	11.0	88	0.5324	0.2581
0.4421	12.0	96	0.5252	0.2852
0.4268	13.0	104	0.5187	0.3074
0.4193	14.0	112	0.5135	0.3224
0.4214	15.0	120	0.5084	0.3212
0.4113	16.0	128	0.5040	0.3290
0.4012	17.0	136	0.5001	0.3365
0.397	18.0	144	0.4965	0.3454
0.374	19.0	152	0.4929	0.3518
0.3881	20.0	160	0.4896	0.3569
0.3929	21.0	168	0.4860	0.3671
0.381	22.0	176	0.4823	0.3775
0.3842	23.0	184	0.4785	0.3819
0.3674	24.0	192	0.4753	0.3936
0.3664	25.0	200	0.4727	0.3952
0.3627	26.0	208	0.4701	0.4013
0.3595	27.0	216	0.4679	0.4024
0.358	28.0	224	0.4654	0.4065
0.3687	29.0	232	0.4628	0.4125
0.3517	30.0	240	0.4606	0.4170
0.349	31.0	248	0.4593	0.4229
0.3447	32.0	256	0.4580	0.4354
0.3407	33.0	264	0.4559	0.4382
0.3413	34.0	272	0.4544	0.4392
0.3516	35.0	280	0.4521	0.4469
0.3475	36.0	288	0.4491	0.4569
0.3273	37.0	296	0.4459	0.4571
0.3333	38.0	304	0.4440	0.4593
0.325	39.0	312	0.4423	0.4615
0.3357	40.0	320	0.4408	0.4637
0.3259	41.0	328	0.4396	0.4628
0.3274	42.0	336	0.4394	0.4667
0.3281	43.0	344	0.4389	0.4665
0.3222	44.0	352	0.4373	0.4635
0.3177	45.0	360	0.4358	0.4681
0.3164	46.0	368	0.4346	0.4715
0.3163	47.0	376	0.4333	0.4748
0.3189	48.0	384	0.4319	0.4759
0.3058	49.0	392	0.4301	0.4777
0.3111	50.0	400	0.4290	0.4784
0.3066	51.0	408	0.4288	0.4791
0.3158	52.0	416	0.4281	0.4802
0.3041	53.0	424	0.4273	0.4807
0.2957	54.0	432	0.4268	0.4822
0.2976	55.0	440	0.4263	0.4812
0.2962	56.0	448	0.4262	0.4833
0.297	57.0	456	0.4257	0.4851
0.294	58.0	464	0.4249	0.4882
0.2937	59.0	472	0.4243	0.4900
0.2972	60.0	480	0.4239	0.4906
0.2982	61.0	488	0.4227	0.4907
0.2919	62.0	496	0.4214	0.4907
0.2906	63.0	504	0.4207	0.4940
0.2946	64.0	512	0.4203	0.4937
0.2929	65.0	520	0.4198	0.4916
0.2926	66.0	528	0.4193	0.4932
0.2889	67.0	536	0.4188	0.4929
0.2837	68.0	544	0.4183	0.4930
0.2852	69.0	552	0.4181	0.4940
0.2863	70.0	560	0.4181	0.4959
0.2893	71.0	568	0.4177	0.4969
0.2945	72.0	576	0.4168	0.4979
0.2785	73.0	584	0.4161	0.4971
0.28	74.0	592	0.4157	0.4998
0.2781	75.0	600	0.4156	0.4989
0.2834	76.0	608	0.4157	0.4999
0.2967	77.0	616	0.4154	0.5003
0.2852	78.0	624	0.4146	0.5033
0.2961	79.0	632	0.4138	0.5039
0.2804	80.0	640	0.4130	0.5049
0.286	81.0	648	0.4127	0.5068
0.2829	82.0	656	0.4124	0.5077
0.2794	83.0	664	0.4120	0.5117
0.2813	84.0	672	0.4117	0.5101
0.282	85.0	680	0.4113	0.5127
0.2765	86.0	688	0.4110	0.5130
0.2802	87.0	696	0.4110	0.5127
0.2847	88.0	704	0.4108	0.5127
0.2804	89.0	712	0.4106	0.5133
0.2788	90.0	720	0.4105	0.5145
0.2785	91.0	728	0.4104	0.5145
0.2792	92.0	736	0.4103	0.5148
0.2836	93.0	744	0.4101	0.5148
0.279	94.0	752	0.4099	0.5148
0.2722	95.0	760	0.4099	0.5148
0.2794	96.0	768	0.4098	0.5148
0.2761	97.0	776	0.4098	0.5148
0.2709	98.0	784	0.4099	0.5148
0.2794	99.0	792	0.4099	0.5148
0.2728	100.0	800	0.4099	0.5148

Framework versions

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