hist-l2_tenK_finetune-itemseg_v9

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

• Loss: 30.0797
• Accuracy: 0.9452
• Macro F1: 0.9401

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: 0.0001
• train_batch_size: 8
• eval_batch_size: 8
• 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
• lr_scheduler_warmup_steps: 7477
• training_steps: 74775

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Macro F1
3.3204	0.0050	373	35.5777	0.2910	0.0560
2.9919	1.0050	746	35.2845	0.3834	0.0801
2.8005	2.0050	1119	35.1272	0.4028	0.0895
2.5893	3.0049	1492	34.8641	0.4652	0.1150
2.5367	4.0049	1865	34.7028	0.5061	0.1248
2.4497	5.0049	2238	34.6290	0.5209	0.1349
2.3947	6.0049	2611	34.4605	0.5770	0.1616
2.2024	7.0049	2984	34.3384	0.6018	0.1888
1.9885	8.0049	3357	34.1500	0.6413	0.2395
1.8094	9.0049	3730	34.0592	0.6566	0.2894
1.8758	10.0049	4103	33.8544	0.7156	0.3499
1.6137	11.0048	4476	33.7209	0.7340	0.3991
1.4809	12.0048	4849	33.6789	0.7495	0.4356
1.5602	13.0048	5222	33.5163	0.7738	0.4847
1.4096	14.0048	5595	33.4063	0.7812	0.5035
1.3791	15.0048	5968	33.2649	0.8013	0.5422
1.3647	16.0048	6341	33.1827	0.8157	0.5728
1.2477	17.0048	6714	33.1244	0.8164	0.5901
1.2492	18.0047	7087	32.9853	0.8339	0.6098
1.199	19.0047	7460	32.8985	0.8246	0.6202
1.1552	20.0047	7833	32.8290	0.8468	0.6431
1.1178	21.0047	8206	32.6965	0.8501	0.6550
1.0551	22.0047	8579	32.6283	0.8507	0.6594
1.0005	23.0047	8952	32.5718	0.8592	0.6779
0.9994	24.0047	9325	32.4964	0.8652	0.6904
0.9343	25.0047	9698	32.4118	0.8683	0.7172
0.9223	26.0046	10071	32.4083	0.8631	0.7049
0.94	27.0046	10444	32.3562	0.8838	0.7175
0.8796	28.0046	10817	32.2513	0.8890	0.7276
0.8566	29.0046	11190	32.1818	0.8896	0.7261
0.8536	30.0046	11563	32.1475	0.8909	0.7394
0.8271	31.0046	11936	32.1000	0.8859	0.7566
0.8385	32.0046	12309	32.0268	0.8981	0.7867
0.8312	33.0045	12682	31.9795	0.9038	0.7802
0.8138	34.0045	13055	31.9209	0.9071	0.8038
0.8094	35.0045	13428	31.8696	0.9113	0.7801
0.831	36.0045	13801	31.8666	0.9107	0.7840
0.8875	37.0045	14174	31.8027	0.9098	0.7938
0.8024	38.0045	14547	31.7494	0.9154	0.8014
0.825	39.0045	14920	31.7010	0.9105	0.8029
0.8104	40.0045	15293	31.6897	0.9023	0.8220
0.7797	41.0044	15666	31.6302	0.9077	0.8150
0.7959	42.0044	16039	31.5812	0.9093	0.8227
0.7812	43.0044	16412	31.5688	0.9067	0.8219
0.7902	44.0044	16785	31.5217	0.9166	0.8151
0.7795	45.0044	17158	31.4536	0.9163	0.8190
0.8003	46.0044	17531	31.4451	0.9188	0.8212
0.7552	47.0044	17904	31.3800	0.9137	0.8436
0.7854	48.0043	18277	31.3036	0.9298	0.8402
0.7506	49.0043	18650	31.3603	0.9315	0.8354
0.8699	50.0043	19023	31.3006	0.9327	0.8318
0.7541	51.0043	19396	31.2755	0.9278	0.8394
0.8152	52.0043	19769	31.2666	0.9198	0.8656
0.7447	53.0043	20142	31.1644	0.9352	0.8525
0.8262	54.0043	20515	31.1528	0.9349	0.8429
0.7308	55.0043	20888	31.1659	0.9271	0.8490
0.7403	56.0042	21261	31.1045	0.9343	0.8397
0.7469	57.0042	21634	31.0692	0.9379	0.8469
0.7251	58.0042	22007	31.0146	0.9349	0.8530
0.7375	59.0042	22380	31.0354	0.9336	0.8538
0.7279	60.0042	22753	30.9804	0.9329	0.8715
0.7484	61.0042	23126	30.9869	0.9369	0.8495
0.7297	62.0042	23499	30.9263	0.9400	0.8566
0.7477	63.0041	23872	30.8964	0.9419	0.8613
0.7379	64.0041	24245	30.8940	0.9353	0.8572
0.9224	65.0041	24618	30.8494	0.9349	0.8547
0.7366	66.0041	24991	30.8112	0.9378	0.8630
0.7341	67.0041	25364	30.8354	0.9356	0.8623
0.73	68.0041	25737	30.8367	0.9324	0.8671
0.7735	69.0041	26110	30.7886	0.9338	0.8662
0.7282	70.0041	26483	30.7990	0.9170	0.8490
0.7243	71.0040	26856	30.6740	0.9353	0.8981
0.7302	72.0040	27229	30.6913	0.9396	0.8821
0.7303	73.0040	27602	30.6730	0.9235	0.8972
0.7242	74.0040	27975	30.6560	0.9366	0.8790
0.7266	75.0040	28348	30.6015	0.9331	0.8940
0.718	76.0040	28721	30.6204	0.9229	0.9059
0.7247	77.0040	29094	30.5747	0.9353	0.8892
0.7718	78.0039	29467	30.5780	0.9369	0.9018
0.7816	79.0039	29840	30.5818	0.9238	0.9056
0.7416	80.0039	30213	30.5578	0.9312	0.8931
0.7707	81.0039	30586	30.6160	0.9046	0.8950
0.7942	82.0039	30959	30.5498	0.9237	0.9035
0.7537	83.0039	31332	30.5228	0.9343	0.9067
0.8531	84.0039	31705	30.5133	0.9287	0.9115
0.724	85.0039	32078	30.4458	0.9384	0.9101
0.7119	86.0038	32451	30.4319	0.9299	0.8988
0.7389	87.0038	32824	30.4093	0.9443	0.9183
0.7158	88.0038	33197	30.4406	0.9264	0.9139
0.7075	89.0038	33570	30.4394	0.9311	0.9106
0.7164	90.0038	33943	30.3753	0.9471	0.8939
0.7049	91.0038	34316	30.3673	0.9439	0.9079
0.7062	92.0038	34689	30.3602	0.9433	0.8959
0.7214	93.0037	35062	30.4061	0.9354	0.9162
0.7035	94.0037	35435	30.3311	0.9496	0.9163
0.7097	95.0037	35808	30.3786	0.9327	0.9150
0.706	96.0037	36181	30.3342	0.9513	0.9070
0.7048	97.0037	36554	30.3522	0.9464	0.8939
0.7064	98.0037	36927	30.3285	0.9376	0.9049
0.7108	99.0037	37300	30.3779	0.9341	0.9136
0.7045	100.0037	37673	30.2899	0.9428	0.9136
0.7046	101.0036	38046	30.3061	0.9372	0.8991
0.7031	102.0036	38419	30.2602	0.9470	0.9107
0.714	103.0036	38792	30.2532	0.9406	0.9078
0.7008	104.0036	39165	30.2654	0.9518	0.9008
0.7046	105.0036	39538	30.3206	0.9411	0.9157
0.7067	106.0036	39911	30.2335	0.9482	0.9182
0.7116	107.0036	40284	30.2195	0.9446	0.9042
0.709	108.0035	40657	30.2665	0.9317	0.9008
0.7083	109.0035	41030	30.2031	0.9449	0.9198
0.7172	110.0035	41403	30.1820	0.9494	0.9037
0.7056	111.0035	41776	30.1901	0.9457	0.9215
0.7505	112.0035	42149	30.1998	0.9408	0.9000
0.7077	113.0035	42522	30.1639	0.9448	0.9170
0.7452	114.0035	42895	30.2123	0.9365	0.9129
0.7067	115.0035	43268	30.1726	0.9417	0.9120
0.7057	116.0034	43641	30.1480	0.9474	0.9101
0.7047	117.0034	44014	30.1211	0.9501	0.9161
0.7088	118.0034	44387	30.1850	0.9301	0.9184
0.7146	119.0034	44760	30.1403	0.9376	0.9164
0.7048	120.0034	45133	30.1495	0.9454	0.9324
0.703	121.0034	45506	30.1554	0.9376	0.9178
0.7074	122.0034	45879	30.1711	0.9377	0.9235
0.7027	123.0033	46252	30.1800	0.9347	0.9188
0.7262	124.0033	46625	30.2160	0.9282	0.9238
0.703	125.0033	46998	30.1370	0.9389	0.9255
0.7111	126.0033	47371	30.1535	0.9408	0.9289
0.7182	127.0033	47744	30.1792	0.9323	0.9117
0.7178	128.0033	48117	30.0683	0.9455	0.9251
0.7323	129.0033	48490	30.0664	0.9417	0.9329
0.7155	130.0032	48863	30.1346	0.9344	0.9234
0.6988	131.0032	49236	30.1241	0.9330	0.9376
0.7156	132.0032	49609	30.0784	0.9452	0.9401
0.7025	133.0032	49982	30.0397	0.9502	0.9284
0.6999	134.0032	50355	30.1191	0.9325	0.9308
0.7008	135.0032	50728	30.0423	0.9498	0.9365
0.6983	136.0032	51101	30.0453	0.9455	0.9275
0.7005	137.0032	51474	30.0937	0.9376	0.9242
0.7115	138.0031	51847	30.0198	0.9489	0.9226
0.699	139.0031	52220	30.0654	0.9410	0.9303
0.715	140.0031	52593	30.0809	0.9366	0.9342
0.7514	141.0031	52966	30.0494	0.9387	0.9322
0.7606	142.0031	53339	30.0488	0.9345	0.9306
0.7063	143.0031	53712	30.0311	0.9353	0.9252
0.7062	144.0031	54085	30.0138	0.9410	0.9278
0.697	145.0030	54458	30.0378	0.9366	0.9283
0.7107	146.0030	54831	30.0008	0.9418	0.9314
0.771	147.0030	55204	30.0554	0.9353	0.9278
0.6927	148.0030	55577	30.0387	0.9337	0.9263
0.6933	149.0030	55950	30.0187	0.9424	0.9328
0.6934	150.0030	56323	29.9749	0.9463	0.9358
0.6935	151.0030	56696	30.0122	0.9378	0.9342
0.6916	152.0030	57069	30.0206	0.9400	0.9350
0.693	153.0029	57442	30.0004	0.9450	0.9354
0.6932	154.0029	57815	30.0045	0.9346	0.9338
0.695	155.0029	58188	29.9917	0.9380	0.9326
0.6946	156.0029	58561	29.9946	0.9370	0.9348
0.6931	157.0029	58934	29.9609	0.9451	0.9378
0.6951	158.0029	59307	30.0012	0.9343	0.9344
0.6925	159.0029	59680	30.0255	0.9347	0.9261
0.6958	160.0028	60053	30.0111	0.9316	0.9292
0.6929	161.0028	60426	30.0227	0.9353	0.9294
0.6927	162.0028	60799	29.9590	0.9480	0.9342

Framework versions

• Transformers 4.46.0
• Pytorch 2.3.1+cu121
• Datasets 2.20.0
• Tokenizers 0.20.1