T5_fine_tune

This model is a fine-tuned version of VietAI/vit5-base on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.0000
• Score: 42.9309
• Counts: [2102, 1955, 1808, 1661]
• Totals: [2107, 1960, 1813, 1666]
• Precisions: [99.76269577598481, 99.74489795918367, 99.72421400992829, 99.69987995198079]
• Bp: 0.4305
• Sys Len: 2107
• Ref Len: 3883

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: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Score	Counts	Totals	Precisions	Bp	Sys Len	Ref Len
No log	1.0	71	0.3075	34.0719	[1898, 1601, 1364, 1147]	[2129, 1982, 1835, 1688]	[89.14983560356976, 80.77699293642785, 74.33242506811989, 67.95023696682465]	0.4387	2129	3883
No log	2.0	142	0.1994	36.2148	[1925, 1676, 1483, 1299]	[2111, 1964, 1817, 1670]	[91.18900994789199, 85.33604887983707, 81.61805173362686, 77.78443113772455]	0.4320	2111	3883
No log	3.0	213	0.1269	39.1074	[2013, 1802, 1615, 1433]	[2116, 1969, 1822, 1675]	[95.13232514177693, 91.5185373285932, 88.63885839736554, 85.55223880597015]	0.4338	2116	3883
No log	4.0	284	0.0988	41.3658	[2074, 1879, 1696, 1517]	[2152, 2005, 1858, 1711]	[96.37546468401487, 93.71571072319202, 91.28094725511302, 88.66160140268849]	0.4474	2152	3883
No log	5.0	355	0.0777	41.4395	[2069, 1893, 1724, 1557]	[2121, 1974, 1827, 1680]	[97.54832626119754, 95.8966565349544, 94.36234263820471, 92.67857142857143]	0.4357	2121	3883
No log	6.0	426	0.0626	41.6053	[2074, 1902, 1742, 1582]	[2108, 1961, 1814, 1667]	[98.38709677419355, 96.99133095359511, 96.03087100330761, 94.90101979604079]	0.4308	2108	3883
No log	7.0	497	0.0534	42.1461	[2087, 1925, 1763, 1601]	[2115, 1968, 1821, 1674]	[98.67612293144208, 97.8150406504065, 96.81493684788578, 95.63918757467144]	0.4335	2115	3883
0.3652	8.0	568	0.0380	42.5312	[2096, 1936, 1781, 1625]	[2116, 1969, 1822, 1675]	[99.05482041587902, 98.32402234636872, 97.74972557628979, 97.01492537313433]	0.4338	2116	3883
0.3652	9.0	639	0.0361	42.3028	[2088, 1929, 1773, 1616]	[2113, 1966, 1819, 1672]	[98.81684808329389, 98.11800610376399, 97.47113798790544, 96.65071770334929]	0.4327	2113	3883
0.3652	10.0	710	0.0299	42.5382	[2097, 1942, 1789, 1635]	[2106, 1959, 1812, 1665]	[99.57264957264957, 99.13221031138336, 98.73068432671081, 98.1981981981982]	0.4301	2106	3883
0.3652	11.0	781	0.0319	42.5551	[2097, 1944, 1790, 1635]	[2106, 1959, 1812, 1665]	[99.57264957264957, 99.23430321592649, 98.78587196467991, 98.1981981981982]	0.4301	2106	3883
0.3652	12.0	852	0.0193	42.6258	[2095, 1942, 1790, 1638]	[2111, 1964, 1817, 1670]	[99.24206537186167, 98.87983706720978, 98.51403412217941, 98.08383233532935]	0.4320	2111	3883
0.3652	13.0	923	0.0178	42.7370	[2099, 1949, 1799, 1649]	[2106, 1959, 1812, 1665]	[99.667616334283, 99.48953547728433, 99.28256070640177, 99.03903903903904]	0.4301	2106	3883
0.3652	14.0	994	0.0156	42.5704	[2094, 1940, 1788, 1636]	[2110, 1963, 1816, 1669]	[99.24170616113744, 98.82832399388691, 98.45814977973568, 98.02276812462553]	0.4316	2110	3883
0.0716	15.0	1065	0.0120	42.7573	[2099, 1949, 1797, 1645]	[2110, 1963, 1816, 1669]	[99.47867298578198, 99.28680590932247, 98.95374449339207, 98.56201318154584]	0.4316	2110	3883
0.0716	16.0	1136	0.0094	42.8327	[2100, 1950, 1800, 1650]	[2111, 1964, 1817, 1670]	[99.4789199431549, 99.28716904276986, 99.06439185470556, 98.80239520958084]	0.4320	2111	3883
0.0716	17.0	1207	0.0064	42.7937	[2097, 1949, 1801, 1653]	[2108, 1961, 1814, 1667]	[99.47817836812145, 99.38806731259561, 99.28335170893054, 99.16016796640672]	0.4308	2108	3883
0.0716	18.0	1278	0.0077	42.9044	[2102, 1954, 1805, 1656]	[2109, 1962, 1815, 1668]	[99.66808914177335, 99.59225280326197, 99.44903581267218, 99.28057553956835]	0.4312	2109	3883
0.0716	19.0	1349	0.0073	42.9494	[2104, 1957, 1807, 1657]	[2109, 1962, 1815, 1668]	[99.76292081555239, 99.74515800203874, 99.55922865013774, 99.34052757793765]	0.4312	2109	3883
0.0716	20.0	1420	0.0071	42.9063	[2100, 1952, 1804, 1656]	[2111, 1964, 1817, 1670]	[99.4789199431549, 99.38900203665987, 99.28453494771601, 99.16167664670658]	0.4320	2111	3883
0.0716	21.0	1491	0.0031	42.9309	[2102, 1955, 1808, 1661]	[2107, 1960, 1813, 1666]	[99.76269577598481, 99.74489795918367, 99.72421400992829, 99.69987995198079]	0.4305	2107	3883
0.032	22.0	1562	0.0076	42.8573	[2102, 1953, 1804, 1655]	[2107, 1960, 1813, 1666]	[99.76269577598481, 99.64285714285714, 99.50358521787093, 99.33973589435774]	0.4305	2107	3883
0.032	23.0	1633	0.0033	42.8941	[2102, 1954, 1806, 1658]	[2107, 1960, 1813, 1666]	[99.76269577598481, 99.6938775510204, 99.61389961389962, 99.51980792316927]	0.4305	2107	3883
0.032	24.0	1704	0.0016	42.8573	[2102, 1953, 1804, 1655]	[2107, 1960, 1813, 1666]	[99.76269577598481, 99.64285714285714, 99.50358521787093, 99.33973589435774]	0.4305	2107	3883
0.032	25.0	1775	0.0029	42.9087	[2102, 1954, 1806, 1658]	[2108, 1961, 1814, 1667]	[99.71537001897534, 99.64303926568077, 99.55898566703418, 99.46010797840432]	0.4308	2108	3883
0.032	26.0	1846	0.0030	42.9309	[2102, 1955, 1808, 1661]	[2107, 1960, 1813, 1666]	[99.76269577598481, 99.74489795918367, 99.72421400992829, 99.69987995198079]	0.4305	2107	3883
0.032	27.0	1917	0.0021	42.9309	[2102, 1955, 1808, 1661]	[2107, 1960, 1813, 1666]	[99.76269577598481, 99.74489795918367, 99.72421400992829, 99.69987995198079]	0.4305	2107	3883
0.032	28.0	1988	0.0014	42.9496	[2103, 1956, 1808, 1660]	[2108, 1961, 1814, 1667]	[99.76280834914611, 99.74502804691484, 99.66923925027564, 99.58008398320337]	0.4308	2108	3883
0.0174	29.0	2059	0.0009	42.9309	[2102, 1955, 1808, 1661]	[2107, 1960, 1813, 1666]	[99.76269577598481, 99.74489795918367, 99.72421400992829, 99.69987995198079]	0.4305	2107	3883
0.0174	30.0	2130	0.0009	42.9309	[2102, 1955, 1808, 1661]	[2107, 1960, 1813, 1666]	[99.76269577598481, 99.74489795918367, 99.72421400992829, 99.69987995198079]	0.4305	2107	3883
0.0174	31.0	2201	0.0007	42.9309	[2102, 1955, 1808, 1661]	[2107, 1960, 1813, 1666]	[99.76269577598481, 99.74489795918367, 99.72421400992829, 99.69987995198079]	0.4305	2107	3883
0.0174	32.0	2272	0.0011	42.9309	[2102, 1955, 1808, 1661]	[2107, 1960, 1813, 1666]	[99.76269577598481, 99.74489795918367, 99.72421400992829, 99.69987995198079]	0.4305	2107	3883
0.0174	33.0	2343	0.0024	42.9309	[2102, 1955, 1808, 1661]	[2107, 1960, 1813, 1666]	[99.76269577598481, 99.74489795918367, 99.72421400992829, 99.69987995198079]	0.4305	2107	3883
0.0174	34.0	2414	0.0022	42.9309	[2102, 1955, 1808, 1661]	[2107, 1960, 1813, 1666]	[99.76269577598481, 99.74489795918367, 99.72421400992829, 99.69987995198079]	0.4305	2107	3883
0.0174	35.0	2485	0.0006	42.9309	[2102, 1955, 1808, 1661]	[2107, 1960, 1813, 1666]	[99.76269577598481, 99.74489795918367, 99.72421400992829, 99.69987995198079]	0.4305	2107	3883
0.0109	36.0	2556	0.0003	42.9309	[2102, 1955, 1808, 1661]	[2107, 1960, 1813, 1666]	[99.76269577598481, 99.74489795918367, 99.72421400992829, 99.69987995198079]	0.4305	2107	3883
0.0109	37.0	2627	0.0001	42.9309	[2102, 1955, 1808, 1661]	[2107, 1960, 1813, 1666]	[99.76269577598481, 99.74489795918367, 99.72421400992829, 99.69987995198079]	0.4305	2107	3883
0.0109	38.0	2698	0.0005	42.9309	[2102, 1955, 1808, 1661]	[2107, 1960, 1813, 1666]	[99.76269577598481, 99.74489795918367, 99.72421400992829, 99.69987995198079]	0.4305	2107	3883
0.0109	39.0	2769	0.0003	42.9309	[2102, 1955, 1808, 1661]	[2107, 1960, 1813, 1666]	[99.76269577598481, 99.74489795918367, 99.72421400992829, 99.69987995198079]	0.4305	2107	3883
0.0109	40.0	2840	0.0012	42.9496	[2103, 1956, 1808, 1660]	[2108, 1961, 1814, 1667]	[99.76280834914611, 99.74502804691484, 99.66923925027564, 99.58008398320337]	0.4308	2108	3883
0.0109	41.0	2911	0.0002	42.9309	[2102, 1955, 1808, 1661]	[2107, 1960, 1813, 1666]	[99.76269577598481, 99.74489795918367, 99.72421400992829, 99.69987995198079]	0.4305	2107	3883
0.0109	42.0	2982	0.0003	42.9309	[2102, 1955, 1808, 1661]	[2107, 1960, 1813, 1666]	[99.76269577598481, 99.74489795918367, 99.72421400992829, 99.69987995198079]	0.4305	2107	3883
0.0073	43.0	3053	0.0001	42.9309	[2102, 1955, 1808, 1661]	[2107, 1960, 1813, 1666]	[99.76269577598481, 99.74489795918367, 99.72421400992829, 99.69987995198079]	0.4305	2107	3883
0.0073	44.0	3124	0.0000	42.9309	[2102, 1955, 1808, 1661]	[2107, 1960, 1813, 1666]	[99.76269577598481, 99.74489795918367, 99.72421400992829, 99.69987995198079]	0.4305	2107	3883
0.0073	45.0	3195	0.0001	42.9309	[2102, 1955, 1808, 1661]	[2107, 1960, 1813, 1666]	[99.76269577598481, 99.74489795918367, 99.72421400992829, 99.69987995198079]	0.4305	2107	3883
0.0073	46.0	3266	0.0000	42.9309	[2102, 1955, 1808, 1661]	[2107, 1960, 1813, 1666]	[99.76269577598481, 99.74489795918367, 99.72421400992829, 99.69987995198079]	0.4305	2107	3883
0.0073	47.0	3337	0.0000	42.9309	[2102, 1955, 1808, 1661]	[2107, 1960, 1813, 1666]	[99.76269577598481, 99.74489795918367, 99.72421400992829, 99.69987995198079]	0.4305	2107	3883
0.0073	48.0	3408	0.0000	42.9309	[2102, 1955, 1808, 1661]	[2107, 1960, 1813, 1666]	[99.76269577598481, 99.74489795918367, 99.72421400992829, 99.69987995198079]	0.4305	2107	3883
0.0073	49.0	3479	0.0000	42.9309	[2102, 1955, 1808, 1661]	[2107, 1960, 1813, 1666]	[99.76269577598481, 99.74489795918367, 99.72421400992829, 99.69987995198079]	0.4305	2107	3883
0.0047	50.0	3550	0.0000	42.9309	[2102, 1955, 1808, 1661]	[2107, 1960, 1813, 1666]	[99.76269577598481, 99.74489795918367, 99.72421400992829, 99.69987995198079]	0.4305	2107	3883

Framework versions

• Transformers 4.36.2
• Pytorch 2.0.0
• Datasets 2.1.0
• Tokenizers 0.15.0