prc4

This model is a fine-tuned version of distilgpt2 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.0000

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: 0.0002
• train_batch_size: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 500

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	1	1.4282
No log	2.0	2	0.6417
No log	3.0	3	0.5086
No log	4.0	4	0.2781
No log	5.0	5	0.1540
No log	6.0	6	0.0654
No log	7.0	7	0.0348
No log	8.0	8	0.0263
No log	9.0	9	0.0198
No log	10.0	10	0.0129
No log	11.0	11	0.0074
No log	12.0	12	0.0037
No log	13.0	13	0.0017
No log	14.0	14	0.0008
No log	15.0	15	0.0004
No log	16.0	16	0.0002
No log	17.0	17	0.0001
No log	18.0	18	0.0001
No log	19.0	19	0.0001
No log	20.0	20	0.0001
No log	21.0	21	0.0001
No log	22.0	22	0.0001
No log	23.0	23	0.0001
No log	24.0	24	0.0000
No log	25.0	25	0.0000
No log	26.0	26	0.0000
No log	27.0	27	0.0000
No log	28.0	28	0.0000
No log	29.0	29	0.0000
No log	30.0	30	0.0000
No log	31.0	31	0.0000
No log	32.0	32	0.0000
No log	33.0	33	0.0000
No log	34.0	34	0.0000
No log	35.0	35	0.0000
No log	36.0	36	0.0000
No log	37.0	37	0.0000
No log	38.0	38	0.0000
No log	39.0	39	0.0000
No log	40.0	40	0.0000
No log	41.0	41	0.0000
No log	42.0	42	0.0000
No log	43.0	43	0.0000
No log	44.0	44	0.0000
No log	45.0	45	0.0000
No log	46.0	46	0.0000
No log	47.0	47	0.0000
No log	48.0	48	0.0000
No log	49.0	49	0.0000
No log	50.0	50	0.0000
No log	51.0	51	0.0000
No log	52.0	52	0.0000
No log	53.0	53	0.0000
No log	54.0	54	0.0000
No log	55.0	55	0.0000
No log	56.0	56	0.0000
No log	57.0	57	0.0001
No log	58.0	58	0.0000
No log	59.0	59	0.0000
No log	60.0	60	0.0000
No log	61.0	61	0.0000
No log	62.0	62	0.0000
No log	63.0	63	0.0000
No log	64.0	64	0.0000
No log	65.0	65	0.0000
No log	66.0	66	0.0000
No log	67.0	67	0.0000
No log	68.0	68	0.0000
No log	69.0	69	0.0000
No log	70.0	70	0.0000
No log	71.0	71	0.0000
No log	72.0	72	0.0000
No log	73.0	73	0.0000
No log	74.0	74	0.0000
No log	75.0	75	0.0000
No log	76.0	76	0.0000
No log	77.0	77	0.0000
No log	78.0	78	0.0000
No log	79.0	79	0.0000
No log	80.0	80	0.0000
No log	81.0	81	0.0000
No log	82.0	82	0.0000
No log	83.0	83	0.0000
No log	84.0	84	0.0000
No log	85.0	85	0.0000
No log	86.0	86	0.0000
No log	87.0	87	0.0000
No log	88.0	88	0.0000
No log	89.0	89	0.0000
No log	90.0	90	0.0000
No log	91.0	91	0.0000
No log	92.0	92	0.0000
No log	93.0	93	0.0000
No log	94.0	94	0.0000
No log	95.0	95	0.0000
No log	96.0	96	0.0000
No log	97.0	97	0.0000
No log	98.0	98	0.0000
No log	99.0	99	0.0000
No log	100.0	100	0.0000
No log	101.0	101	0.0000
No log	102.0	102	0.0000
No log	103.0	103	0.0000
No log	104.0	104	0.0000
No log	105.0	105	0.0000
No log	106.0	106	0.0000
No log	107.0	107	0.0000
No log	108.0	108	0.0000
No log	109.0	109	0.0000
No log	110.0	110	0.0000
No log	111.0	111	0.0000
No log	112.0	112	0.0000
No log	113.0	113	0.0000
No log	114.0	114	0.0000
No log	115.0	115	0.0000
No log	116.0	116	0.0000
No log	117.0	117	0.0000
No log	118.0	118	0.0000
No log	119.0	119	0.0000
No log	120.0	120	0.0000
No log	121.0	121	0.0000
No log	122.0	122	0.0000
No log	123.0	123	0.0001
No log	124.0	124	0.0001
No log	125.0	125	0.0002
No log	126.0	126	0.0002
No log	127.0	127	0.0002
No log	128.0	128	0.0002
No log	129.0	129	0.0001
No log	130.0	130	0.0001
No log	131.0	131	0.0001
No log	132.0	132	0.0001
No log	133.0	133	0.0000
No log	134.0	134	0.0001
No log	135.0	135	0.0001
No log	136.0	136	0.0001
No log	137.0	137	0.0001
No log	138.0	138	0.0001
No log	139.0	139	0.0001
No log	140.0	140	0.0001
No log	141.0	141	0.0001
No log	142.0	142	0.0001
No log	143.0	143	0.0001
No log	144.0	144	0.0001
No log	145.0	145	0.0001
No log	146.0	146	0.0000
No log	147.0	147	0.0000
No log	148.0	148	0.0000
No log	149.0	149	0.0000
No log	150.0	150	0.0000
No log	151.0	151	0.0000
No log	152.0	152	0.0000
No log	153.0	153	0.0000
No log	154.0	154	0.0000
No log	155.0	155	0.0000
No log	156.0	156	0.0000
No log	157.0	157	0.0000
No log	158.0	158	0.0000
No log	159.0	159	0.0000
No log	160.0	160	0.0000
No log	161.0	161	0.0000
No log	162.0	162	0.0000
No log	163.0	163	0.0000
No log	164.0	164	0.0000
No log	165.0	165	0.0000
No log	166.0	166	0.0000
No log	167.0	167	0.0000
No log	168.0	168	0.0000
No log	169.0	169	0.0000
No log	170.0	170	0.0000
No log	171.0	171	0.0000
No log	172.0	172	0.0000
No log	173.0	173	0.0000
No log	174.0	174	0.0000
No log	175.0	175	0.0000
No log	176.0	176	0.0000
No log	177.0	177	0.0000
No log	178.0	178	0.0000
No log	179.0	179	0.0000
No log	180.0	180	0.0000
No log	181.0	181	0.0000
No log	182.0	182	0.0000
No log	183.0	183	0.0000
No log	184.0	184	0.0000
No log	185.0	185	0.0000
No log	186.0	186	0.0000
No log	187.0	187	0.0000
No log	188.0	188	0.0000
No log	189.0	189	0.0000
No log	190.0	190	0.0000
No log	191.0	191	0.0000
No log	192.0	192	0.0000
No log	193.0	193	0.0000
No log	194.0	194	0.0000
No log	195.0	195	0.0000
No log	196.0	196	0.0000
No log	197.0	197	0.0000
No log	198.0	198	0.0000
No log	199.0	199	0.0000
No log	200.0	200	0.0000
No log	201.0	201	0.0000
No log	202.0	202	0.0000
No log	203.0	203	0.0000
No log	204.0	204	0.0000
No log	205.0	205	0.0000
No log	206.0	206	0.0000
No log	207.0	207	0.0000
No log	208.0	208	0.0000
No log	209.0	209	0.0000
No log	210.0	210	0.0000
No log	211.0	211	0.0000
No log	212.0	212	0.0000
No log	213.0	213	0.0000
No log	214.0	214	0.0000
No log	215.0	215	0.0000
No log	216.0	216	0.0000
No log	217.0	217	0.0000
No log	218.0	218	0.0000
No log	219.0	219	0.0000
No log	220.0	220	0.0000
No log	221.0	221	0.0000
No log	222.0	222	0.0000
No log	223.0	223	0.0000
No log	224.0	224	0.0000
No log	225.0	225	0.0000
No log	226.0	226	0.0000
No log	227.0	227	0.0000
No log	228.0	228	0.0000
No log	229.0	229	0.0000
No log	230.0	230	0.0000
No log	231.0	231	0.0000
No log	232.0	232	0.0000
No log	233.0	233	0.0000
No log	234.0	234	0.0000
No log	235.0	235	0.0000
No log	236.0	236	0.0000
No log	237.0	237	0.0000
No log	238.0	238	0.0000
No log	239.0	239	0.0000
No log	240.0	240	0.0000
No log	241.0	241	0.0000
No log	242.0	242	0.0000
No log	243.0	243	0.0000
No log	244.0	244	0.0000
No log	245.0	245	0.0000
No log	246.0	246	0.0000
No log	247.0	247	0.0000
No log	248.0	248	0.0000
No log	249.0	249	0.0000
No log	250.0	250	0.0000
No log	251.0	251	0.0000
No log	252.0	252	0.0000
No log	253.0	253	0.0000
No log	254.0	254	0.0000
No log	255.0	255	0.0000
No log	256.0	256	0.0000
No log	257.0	257	0.0000
No log	258.0	258	0.0000
No log	259.0	259	0.0000
No log	260.0	260	0.0000
No log	261.0	261	0.0000
No log	262.0	262	0.0000
No log	263.0	263	0.0000
No log	264.0	264	0.0000
No log	265.0	265	0.0000
No log	266.0	266	0.0000
No log	267.0	267	0.0000
No log	268.0	268	0.0000
No log	269.0	269	0.0000
No log	270.0	270	0.0000
No log	271.0	271	0.0000
No log	272.0	272	0.0000
No log	273.0	273	0.0000
No log	274.0	274	0.0000
No log	275.0	275	0.0000
No log	276.0	276	0.0000
No log	277.0	277	0.0000
No log	278.0	278	0.0000
No log	279.0	279	0.0000
No log	280.0	280	0.0000
No log	281.0	281	0.0000
No log	282.0	282	0.0000
No log	283.0	283	0.0000
No log	284.0	284	0.0000
No log	285.0	285	0.0000
No log	286.0	286	0.0000
No log	287.0	287	0.0000
No log	288.0	288	0.0000
No log	289.0	289	0.0000
No log	290.0	290	0.0000
No log	291.0	291	0.0000
No log	292.0	292	0.0000
No log	293.0	293	0.0000
No log	294.0	294	0.0000
No log	295.0	295	0.0000
No log	296.0	296	0.0000
No log	297.0	297	0.0000
No log	298.0	298	0.0000
No log	299.0	299	0.0000
No log	300.0	300	0.0000
No log	301.0	301	0.0000
No log	302.0	302	0.0000
No log	303.0	303	0.0000
No log	304.0	304	0.0000
No log	305.0	305	0.0000
No log	306.0	306	0.0000
No log	307.0	307	0.0000
No log	308.0	308	0.0000
No log	309.0	309	0.0000
No log	310.0	310	0.0000
No log	311.0	311	0.0000
No log	312.0	312	0.0000
No log	313.0	313	0.0000
No log	314.0	314	0.0000
No log	315.0	315	0.0000
No log	316.0	316	0.0000
No log	317.0	317	0.0000
No log	318.0	318	0.0000
No log	319.0	319	0.0000
No log	320.0	320	0.0000
No log	321.0	321	0.0000
No log	322.0	322	0.0000
No log	323.0	323	0.0000
No log	324.0	324	0.0000
No log	325.0	325	0.0000
No log	326.0	326	0.0000
No log	327.0	327	0.0000
No log	328.0	328	0.0000
No log	329.0	329	0.0000
No log	330.0	330	0.0000
No log	331.0	331	0.0000
No log	332.0	332	0.0000
No log	333.0	333	0.0000
No log	334.0	334	0.0000
No log	335.0	335	0.0000
No log	336.0	336	0.0000
No log	337.0	337	0.0000
No log	338.0	338	0.0000
No log	339.0	339	0.0000
No log	340.0	340	0.0000
No log	341.0	341	0.0000
No log	342.0	342	0.0000
No log	343.0	343	0.0000
No log	344.0	344	0.0000
No log	345.0	345	0.0000
No log	346.0	346	0.0000
No log	347.0	347	0.0000
No log	348.0	348	0.0000
No log	349.0	349	0.0000
No log	350.0	350	0.0000
No log	351.0	351	0.0000
No log	352.0	352	0.0000
No log	353.0	353	0.0000
No log	354.0	354	0.0000
No log	355.0	355	0.0000
No log	356.0	356	0.0000
No log	357.0	357	0.0000
No log	358.0	358	0.0000
No log	359.0	359	0.0000
No log	360.0	360	0.0000
No log	361.0	361	0.0000
No log	362.0	362	0.0000
No log	363.0	363	0.0000
No log	364.0	364	0.0000
No log	365.0	365	0.0000
No log	366.0	366	0.0000
No log	367.0	367	0.0000
No log	368.0	368	0.0000
No log	369.0	369	0.0000
No log	370.0	370	0.0000
No log	371.0	371	0.0000
No log	372.0	372	0.0000
No log	373.0	373	0.0000
No log	374.0	374	0.0000
No log	375.0	375	0.0000
No log	376.0	376	0.0000
No log	377.0	377	0.0000
No log	378.0	378	0.0000
No log	379.0	379	0.0000
No log	380.0	380	0.0000
No log	381.0	381	0.0000
No log	382.0	382	0.0000
No log	383.0	383	0.0000
No log	384.0	384	0.0000
No log	385.0	385	0.0000
No log	386.0	386	0.0000
No log	387.0	387	0.0000
No log	388.0	388	0.0000
No log	389.0	389	0.0000
No log	390.0	390	0.0000
No log	391.0	391	0.0000
No log	392.0	392	0.0000
No log	393.0	393	0.0000
No log	394.0	394	0.0000
No log	395.0	395	0.0000
No log	396.0	396	0.0000
No log	397.0	397	0.0000
No log	398.0	398	0.0000
No log	399.0	399	0.0000
No log	400.0	400	0.0000
No log	401.0	401	0.0000
No log	402.0	402	0.0000
No log	403.0	403	0.0000
No log	404.0	404	0.0000
No log	405.0	405	0.0000
No log	406.0	406	0.0000
No log	407.0	407	0.0000
No log	408.0	408	0.0000
No log	409.0	409	0.0000
No log	410.0	410	0.0000
No log	411.0	411	0.0000
No log	412.0	412	0.0000
No log	413.0	413	0.0000
No log	414.0	414	0.0000
No log	415.0	415	0.0000
No log	416.0	416	0.0000
No log	417.0	417	0.0000
No log	418.0	418	0.0000
No log	419.0	419	0.0000
No log	420.0	420	0.0000
No log	421.0	421	0.0000
No log	422.0	422	0.0000
No log	423.0	423	0.0000
No log	424.0	424	0.0000
No log	425.0	425	0.0000
No log	426.0	426	0.0000
No log	427.0	427	0.0000
No log	428.0	428	0.0000
No log	429.0	429	0.0000
No log	430.0	430	0.0000
No log	431.0	431	0.0000
No log	432.0	432	0.0000
No log	433.0	433	0.0000
No log	434.0	434	0.0000
No log	435.0	435	0.0000
No log	436.0	436	0.0000
No log	437.0	437	0.0000
No log	438.0	438	0.0000
No log	439.0	439	0.0000
No log	440.0	440	0.0000
No log	441.0	441	0.0000
No log	442.0	442	0.0000
No log	443.0	443	0.0000
No log	444.0	444	0.0000
No log	445.0	445	0.0000
No log	446.0	446	0.0000
No log	447.0	447	0.0000
No log	448.0	448	0.0000
No log	449.0	449	0.0000
No log	450.0	450	0.0000
No log	451.0	451	0.0000
No log	452.0	452	0.0000
No log	453.0	453	0.0000
No log	454.0	454	0.0000
No log	455.0	455	0.0000
No log	456.0	456	0.0000
No log	457.0	457	0.0000
No log	458.0	458	0.0000
No log	459.0	459	0.0000
No log	460.0	460	0.0000
No log	461.0	461	0.0000
No log	462.0	462	0.0000
No log	463.0	463	0.0000
No log	464.0	464	0.0000
No log	465.0	465	0.0000
No log	466.0	466	0.0000
No log	467.0	467	0.0000
No log	468.0	468	0.0000
No log	469.0	469	0.0000
No log	470.0	470	0.0000
No log	471.0	471	0.0000
No log	472.0	472	0.0000
No log	473.0	473	0.0000
No log	474.0	474	0.0000
No log	475.0	475	0.0000
No log	476.0	476	0.0000
No log	477.0	477	0.0000
No log	478.0	478	0.0000
No log	479.0	479	0.0000
No log	480.0	480	0.0000
No log	481.0	481	0.0000
No log	482.0	482	0.0000
No log	483.0	483	0.0000
No log	484.0	484	0.0000
No log	485.0	485	0.0000
No log	486.0	486	0.0000
No log	487.0	487	0.0000
No log	488.0	488	0.0000
No log	489.0	489	0.0000
No log	490.0	490	0.0000
No log	491.0	491	0.0000
No log	492.0	492	0.0000
No log	493.0	493	0.0000
No log	494.0	494	0.0000
No log	495.0	495	0.0000
No log	496.0	496	0.0000
No log	497.0	497	0.0000
No log	498.0	498	0.0000
No log	499.0	499	0.0000
0.01	500.0	500	0.0000

Framework versions

• Transformers 4.38.2
• Pytorch 2.2.1+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2