results

This model is a fine-tuned version of google/flan-t5-small on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 3.4951

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: 5e-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
• training_steps: 375

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	1	3.0323
No log	2.0	2	3.0014
No log	3.0	3	2.9748
No log	4.0	4	2.9521
No log	5.0	5	2.9321
No log	6.0	6	2.9143
No log	7.0	7	2.8985
No log	8.0	8	2.8840
No log	9.0	9	2.8708
3.2243	10.0	10	2.8585
3.2243	11.0	11	2.8466
3.2243	12.0	12	2.8353
3.2243	13.0	13	2.8244
3.2243	14.0	14	2.8137
3.2243	15.0	15	2.8033
3.2243	16.0	16	2.7937
3.2243	17.0	17	2.7849
3.2243	18.0	18	2.7768
3.2243	19.0	19	2.7694
2.886	20.0	20	2.7625
2.886	21.0	21	2.7558
2.886	22.0	22	2.7495
2.886	23.0	23	2.7437
2.886	24.0	24	2.7382
2.886	25.0	25	2.7328
2.886	26.0	26	2.7277
2.886	27.0	27	2.7228
2.886	28.0	28	2.7184
2.886	29.0	29	2.7143
2.6559	30.0	30	2.7104
2.6559	31.0	31	2.7070
2.6559	32.0	32	2.7038
2.6559	33.0	33	2.7009
2.6559	34.0	34	2.6978
2.6559	35.0	35	2.6951
2.6559	36.0	36	2.6927
2.6559	37.0	37	2.6902
2.6559	38.0	38	2.6879
2.6559	39.0	39	2.6859
2.4547	40.0	40	2.6839
2.4547	41.0	41	2.6822
2.4547	42.0	42	2.6807
2.4547	43.0	43	2.6792
2.4547	44.0	44	2.6775
2.4547	45.0	45	2.6761
2.4547	46.0	46	2.6748
2.4547	47.0	47	2.6741
2.4547	48.0	48	2.6738
2.4547	49.0	49	2.6737
2.297	50.0	50	2.6737
2.297	51.0	51	2.6737
2.297	52.0	52	2.6737
2.297	53.0	53	2.6734
2.297	54.0	54	2.6738
2.297	55.0	55	2.6744
2.297	56.0	56	2.6752
2.297	57.0	57	2.6765
2.297	58.0	58	2.6779
2.297	59.0	59	2.6792
2.1517	60.0	60	2.6800
2.1517	61.0	61	2.6811
2.1517	62.0	62	2.6815
2.1517	63.0	63	2.6820
2.1517	64.0	64	2.6828
2.1517	65.0	65	2.6842
2.1517	66.0	66	2.6852
2.1517	67.0	67	2.6862
2.1517	68.0	68	2.6866
2.1517	69.0	69	2.6867
2.0233	70.0	70	2.6875
2.0233	71.0	71	2.6883
2.0233	72.0	72	2.6899
2.0233	73.0	73	2.6918
2.0233	74.0	74	2.6943
2.0233	75.0	75	2.6963
2.0233	76.0	76	2.6985
2.0233	77.0	77	2.7009
2.0233	78.0	78	2.7033
2.0233	79.0	79	2.7062
1.899	80.0	80	2.7089
1.899	81.0	81	2.7122
1.899	82.0	82	2.7157
1.899	83.0	83	2.7191
1.899	84.0	84	2.7230
1.899	85.0	85	2.7267
1.899	86.0	86	2.7292
1.899	87.0	87	2.7318
1.899	88.0	88	2.7326
1.899	89.0	89	2.7328
1.8018	90.0	90	2.7328
1.8018	91.0	91	2.7325
1.8018	92.0	92	2.7333
1.8018	93.0	93	2.7347
1.8018	94.0	94	2.7372
1.8018	95.0	95	2.7399
1.8018	96.0	96	2.7438
1.8018	97.0	97	2.7483
1.8018	98.0	98	2.7522
1.8018	99.0	99	2.7560
1.7204	100.0	100	2.7602
1.7204	101.0	101	2.7642
1.7204	102.0	102	2.7673
1.7204	103.0	103	2.7714
1.7204	104.0	104	2.7748
1.7204	105.0	105	2.7779
1.7204	106.0	106	2.7795
1.7204	107.0	107	2.7821
1.7204	108.0	108	2.7837
1.7204	109.0	109	2.7844
1.6329	110.0	110	2.7858
1.6329	111.0	111	2.7889
1.6329	112.0	112	2.7926
1.6329	113.0	113	2.7967
1.6329	114.0	114	2.8012
1.6329	115.0	115	2.8056
1.6329	116.0	116	2.8107
1.6329	117.0	117	2.8161
1.6329	118.0	118	2.8217
1.6329	119.0	119	2.8263
1.5426	120.0	120	2.8313
1.5426	121.0	121	2.8359
1.5426	122.0	122	2.8410
1.5426	123.0	123	2.8460
1.5426	124.0	124	2.8503
1.5426	125.0	125	2.8551
1.5426	126.0	126	2.8581
1.5426	127.0	127	2.8607
1.5426	128.0	128	2.8638
1.5426	129.0	129	2.8649
1.4806	130.0	130	2.8652
1.4806	131.0	131	2.8658
1.4806	132.0	132	2.8661
1.4806	133.0	133	2.8679
1.4806	134.0	134	2.8711
1.4806	135.0	135	2.8742
1.4806	136.0	136	2.8769
1.4806	137.0	137	2.8805
1.4806	138.0	138	2.8848
1.4806	139.0	139	2.8910
1.4225	140.0	140	2.8969
1.4225	141.0	141	2.9047
1.4225	142.0	142	2.9119
1.4225	143.0	143	2.9190
1.4225	144.0	144	2.9258
1.4225	145.0	145	2.9333
1.4225	146.0	146	2.9406
1.4225	147.0	147	2.9476
1.4225	148.0	148	2.9547
1.4225	149.0	149	2.9615
1.3577	150.0	150	2.9674
1.3577	151.0	151	2.9735
1.3577	152.0	152	2.9799
1.3577	153.0	153	2.9856
1.3577	154.0	154	2.9907
1.3577	155.0	155	2.9933
1.3577	156.0	156	2.9952
1.3577	157.0	157	2.9961
1.3577	158.0	158	2.9969
1.3577	159.0	159	2.9983
1.3091	160.0	160	2.9997
1.3091	161.0	161	3.0013
1.3091	162.0	162	3.0031
1.3091	163.0	163	3.0046
1.3091	164.0	164	3.0063
1.3091	165.0	165	3.0085
1.3091	166.0	166	3.0117
1.3091	167.0	167	3.0149
1.3091	168.0	168	3.0182
1.3091	169.0	169	3.0234
1.2555	170.0	170	3.0283
1.2555	171.0	171	3.0347
1.2555	172.0	172	3.0402
1.2555	173.0	173	3.0444
1.2555	174.0	174	3.0474
1.2555	175.0	175	3.0506
1.2555	176.0	176	3.0541
1.2555	177.0	177	3.0587
1.2555	178.0	178	3.0638
1.2555	179.0	179	3.0681
1.2212	180.0	180	3.0716
1.2212	181.0	181	3.0763
1.2212	182.0	182	3.0801
1.2212	183.0	183	3.0839
1.2212	184.0	184	3.0882
1.2212	185.0	185	3.0935
1.2212	186.0	186	3.0991
1.2212	187.0	187	3.1058
1.2212	188.0	188	3.1132
1.2212	189.0	189	3.1182
1.1692	190.0	190	3.1226
1.1692	191.0	191	3.1272
1.1692	192.0	192	3.1332
1.1692	193.0	193	3.1396
1.1692	194.0	194	3.1446
1.1692	195.0	195	3.1485
1.1692	196.0	196	3.1525
1.1692	197.0	197	3.1551
1.1692	198.0	198	3.1563
1.1692	199.0	199	3.1571
1.1401	200.0	200	3.1570
1.1401	201.0	201	3.1568
1.1401	202.0	202	3.1568
1.1401	203.0	203	3.1575
1.1401	204.0	204	3.1597
1.1401	205.0	205	3.1628
1.1401	206.0	206	3.1658
1.1401	207.0	207	3.1691
1.1401	208.0	208	3.1724
1.1401	209.0	209	3.1752
1.1036	210.0	210	3.1793
1.1036	211.0	211	3.1832
1.1036	212.0	212	3.1890
1.1036	213.0	213	3.1951
1.1036	214.0	214	3.2021
1.1036	215.0	215	3.2082
1.1036	216.0	216	3.2148
1.1036	217.0	217	3.2227
1.1036	218.0	218	3.2294
1.1036	219.0	219	3.2364
1.063	220.0	220	3.2406
1.063	221.0	221	3.2433
1.063	222.0	222	3.2458
1.063	223.0	223	3.2474
1.063	224.0	224	3.2486
1.063	225.0	225	3.2484
1.063	226.0	226	3.2505
1.063	227.0	227	3.2519
1.063	228.0	228	3.2522
1.063	229.0	229	3.2527
1.0407	230.0	230	3.2534
1.0407	231.0	231	3.2542
1.0407	232.0	232	3.2545
1.0407	233.0	233	3.2567
1.0407	234.0	234	3.2595
1.0407	235.0	235	3.2635
1.0407	236.0	236	3.2681
1.0407	237.0	237	3.2739
1.0407	238.0	238	3.2789
1.0407	239.0	239	3.2845
1.0236	240.0	240	3.2895
1.0236	241.0	241	3.2955
1.0236	242.0	242	3.3016
1.0236	243.0	243	3.3069
1.0236	244.0	244	3.3102
1.0236	245.0	245	3.3137
1.0236	246.0	246	3.3181
1.0236	247.0	247	3.3216
1.0236	248.0	248	3.3238
1.0236	249.0	249	3.3258
0.9908	250.0	250	3.3291
0.9908	251.0	251	3.3333
0.9908	252.0	252	3.3374
0.9908	253.0	253	3.3410
0.9908	254.0	254	3.3438
0.9908	255.0	255	3.3480
0.9908	256.0	256	3.3525
0.9908	257.0	257	3.3556
0.9908	258.0	258	3.3572
0.9908	259.0	259	3.3589
0.9643	260.0	260	3.3604
0.9643	261.0	261	3.3609
0.9643	262.0	262	3.3613
0.9643	263.0	263	3.3626
0.9643	264.0	264	3.3647
0.9643	265.0	265	3.3669
0.9643	266.0	266	3.3699
0.9643	267.0	267	3.3733
0.9643	268.0	268	3.3772
0.9643	269.0	269	3.3801
0.9543	270.0	270	3.3835
0.9543	271.0	271	3.3867
0.9543	272.0	272	3.3902
0.9543	273.0	273	3.3935
0.9543	274.0	274	3.3974
0.9543	275.0	275	3.4006
0.9543	276.0	276	3.4037
0.9543	277.0	277	3.4068
0.9543	278.0	278	3.4087
0.9543	279.0	279	3.4107
0.9381	280.0	280	3.4118
0.9381	281.0	281	3.4127
0.9381	282.0	282	3.4131
0.9381	283.0	283	3.4143
0.9381	284.0	284	3.4152
0.9381	285.0	285	3.4164
0.9381	286.0	286	3.4180
0.9381	287.0	287	3.4196
0.9381	288.0	288	3.4224
0.9381	289.0	289	3.4259
0.9228	290.0	290	3.4285
0.9228	291.0	291	3.4313
0.9228	292.0	292	3.4340
0.9228	293.0	293	3.4359
0.9228	294.0	294	3.4371
0.9228	295.0	295	3.4385
0.9228	296.0	296	3.4395
0.9228	297.0	297	3.4399
0.9228	298.0	298	3.4400
0.9228	299.0	299	3.4403
0.9105	300.0	300	3.4410
0.9105	301.0	301	3.4422
0.9105	302.0	302	3.4429
0.9105	303.0	303	3.4441
0.9105	304.0	304	3.4448
0.9105	305.0	305	3.4452
0.9105	306.0	306	3.4456
0.9105	307.0	307	3.4459
0.9105	308.0	308	3.4469
0.9105	309.0	309	3.4480
0.8954	310.0	310	3.4497
0.8954	311.0	311	3.4513
0.8954	312.0	312	3.4527
0.8954	313.0	313	3.4547
0.8954	314.0	314	3.4567
0.8954	315.0	315	3.4591
0.8954	316.0	316	3.4613
0.8954	317.0	317	3.4634
0.8954	318.0	318	3.4649
0.8954	319.0	319	3.4659
0.881	320.0	320	3.4672
0.881	321.0	321	3.4684
0.881	322.0	322	3.4698
0.881	323.0	323	3.4707
0.881	324.0	324	3.4716
0.881	325.0	325	3.4722
0.881	326.0	326	3.4723
0.881	327.0	327	3.4729
0.881	328.0	328	3.4730
0.881	329.0	329	3.4733
0.8773	330.0	330	3.4737
0.8773	331.0	331	3.4750
0.8773	332.0	332	3.4764
0.8773	333.0	333	3.4775
0.8773	334.0	334	3.4786
0.8773	335.0	335	3.4799
0.8773	336.0	336	3.4809
0.8773	337.0	337	3.4816
0.8773	338.0	338	3.4822
0.8773	339.0	339	3.4826
0.8711	340.0	340	3.4828
0.8711	341.0	341	3.4832
0.8711	342.0	342	3.4836
0.8711	343.0	343	3.4842
0.8711	344.0	344	3.4845
0.8711	345.0	345	3.4847
0.8711	346.0	346	3.4848
0.8711	347.0	347	3.4848
0.8711	348.0	348	3.4851
0.8711	349.0	349	3.4854
0.8665	350.0	350	3.4859
0.8665	351.0	351	3.4861
0.8665	352.0	352	3.4866
0.8665	353.0	353	3.4870
0.8665	354.0	354	3.4875
0.8665	355.0	355	3.4880
0.8665	356.0	356	3.4885
0.8665	357.0	357	3.4890
0.8665	358.0	358	3.4896
0.8665	359.0	359	3.4903
0.8569	360.0	360	3.4909
0.8569	361.0	361	3.4914
0.8569	362.0	362	3.4918
0.8569	363.0	363	3.4922
0.8569	364.0	364	3.4926
0.8569	365.0	365	3.4930
0.8569	366.0	366	3.4933
0.8569	367.0	367	3.4936
0.8569	368.0	368	3.4939
0.8569	369.0	369	3.4942
0.8623	370.0	370	3.4945
0.8623	371.0	371	3.4947
0.8623	372.0	372	3.4949
0.8623	373.0	373	3.4950
0.8623	374.0	374	3.4951
0.8623	375.0	375	3.4951

Framework versions

• Transformers 4.49.0
• Pytorch 2.6.0+cu124
• Datasets 3.4.1
• Tokenizers 0.21.1