tfa_output_2025_m05_d13_t13h_01m_39s

This model is a fine-tuned version of Qwen/Qwen3-8B on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.1960

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: 1e-07
• train_batch_size: 1
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 8
• optimizer: Use OptimizerNames.PAGED_ADAMW with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: constant_with_warmup
• lr_scheduler_warmup_ratio: 0.05
• num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0	0	1.1976
2.246	0.0049	25	1.1977
2.2727	0.0098	50	1.1977
2.2721	0.0148	75	1.1977
2.1365	0.0197	100	1.1980
2.5064	0.0246	125	1.1976
2.1168	0.0295	150	1.1977
2.0195	0.0344	175	1.1977
2.1274	0.0393	200	1.1973
2.1423	0.0443	225	1.1975
2.0581	0.0492	250	1.1973
2.3088	0.0541	275	1.1971
2.2377	0.0590	300	1.1975
2.0745	0.0639	325	1.1972
2.3906	0.0689	350	1.1972
2.2249	0.0738	375	1.1968
2.0537	0.0787	400	1.1970
2.4452	0.0836	425	1.1968
2.5002	0.0885	450	1.1965
2.1056	0.0934	475	1.1967
2.139	0.0984	500	1.1969
2.448	0.1033	525	1.1969
2.3778	0.1082	550	1.1968
2.0933	0.1131	575	1.1966
2.2988	0.1180	600	1.1966
2.3635	0.1230	625	1.1966
2.0839	0.1279	650	1.1967
2.2946	0.1328	675	1.1965
2.2107	0.1377	700	1.1967
2.2321	0.1426	725	1.1963
2.1609	0.1475	750	1.1964
2.0338	0.1525	775	1.1963
2.0854	0.1574	800	1.1965
2.4936	0.1623	825	1.1965
2.3859	0.1672	850	1.1963
2.4055	0.1721	875	1.1967
2.1933	0.1771	900	1.1962
2.1406	0.1820	925	1.1966
2.3661	0.1869	950	1.1962
2.1484	0.1918	975	1.1964
2.3269	0.1967	1000	1.1962
2.2781	0.2016	1025	1.1963
2.2589	0.2066	1050	1.1963
2.14	0.2115	1075	1.1965
2.0599	0.2164	1100	1.1964
2.2361	0.2213	1125	1.1962
2.2609	0.2262	1150	1.1967
2.4061	0.2312	1175	1.1966
2.3443	0.2361	1200	1.1962
2.3939	0.2410	1225	1.1965
2.2703	0.2459	1250	1.1964
2.4083	0.2508	1275	1.1963
1.9759	0.2557	1300	1.1964
2.0368	0.2607	1325	1.1964
2.3993	0.2656	1350	1.1965
2.3491	0.2705	1375	1.1961
2.2197	0.2754	1400	1.1959
2.1712	0.2803	1425	1.1963
2.2401	0.2853	1450	1.1963
2.3364	0.2902	1475	1.1960
2.2556	0.2951	1500	1.1963
2.482	0.3000	1525	1.1961
2.1299	0.3049	1550	1.1960
2.1765	0.3098	1575	1.1962
2.2247	0.3148	1600	1.1962
2.3216	0.3197	1625	1.1962
2.0913	0.3246	1650	1.1960
2.2222	0.3295	1675	1.1963
2.1564	0.3344	1700	1.1964
2.1817	0.3394	1725	1.1961
2.2866	0.3443	1750	1.1965
2.1426	0.3492	1775	1.1963
2.3738	0.3541	1800	1.1963
2.334	0.3590	1825	1.1960
2.1325	0.3639	1850	1.1964
2.1522	0.3689	1875	1.1960
2.0358	0.3738	1900	1.1958
2.2019	0.3787	1925	1.1959
2.2238	0.3836	1950	1.1961
2.1258	0.3885	1975	1.1961
2.3393	0.3935	2000	1.1961
2.0858	0.3984	2025	1.1963
2.1936	0.4033	2050	1.1959
2.1086	0.4082	2075	1.1963
2.0318	0.4131	2100	1.1961
2.1221	0.4180	2125	1.1963
2.2419	0.4230	2150	1.1959
2.2179	0.4279	2175	1.1961
2.1388	0.4328	2200	1.1963
2.3871	0.4377	2225	1.1962
2.3968	0.4426	2250	1.1962
2.3812	0.4476	2275	1.1959
2.1811	0.4525	2300	1.1959
2.2433	0.4574	2325	1.1959
2.2599	0.4623	2350	1.1963
2.3472	0.4672	2375	1.1959
2.2542	0.4722	2400	1.1957
2.1694	0.4771	2425	1.1960
2.2399	0.4820	2450	1.1960
2.2255	0.4869	2475	1.1959
2.3706	0.4918	2500	1.1957
2.382	0.4967	2525	1.1962
2.2745	0.5017	2550	1.1960
2.0935	0.5066	2575	1.1960
2.2579	0.5115	2600	1.1963
2.3317	0.5164	2625	1.1959
2.4675	0.5213	2650	1.1962
2.3471	0.5263	2675	1.1963
2.3394	0.5312	2700	1.1960
2.1928	0.5361	2725	1.1964
2.3198	0.5410	2750	1.1961
2.2023	0.5459	2775	1.1960
2.1285	0.5508	2800	1.1956
2.3145	0.5558	2825	1.1960
2.2811	0.5607	2850	1.1961
2.3009	0.5656	2875	1.1957
2.1485	0.5705	2900	1.1959
2.2421	0.5754	2925	1.1962
2.341	0.5804	2950	1.1960
2.061	0.5853	2975	1.1959
2.2235	0.5902	3000	1.1960
2.156	0.5951	3025	1.1963
2.1171	0.6000	3050	1.1959
2.1974	0.6049	3075	1.1958
2.202	0.6099	3100	1.1961
2.2813	0.6148	3125	1.1958
2.2252	0.6197	3150	1.1956
2.1522	0.6246	3175	1.1958
2.4226	0.6295	3200	1.1960
2.1715	0.6345	3225	1.1961
2.0513	0.6394	3250	1.1959
2.0935	0.6443	3275	1.1960
2.122	0.6492	3300	1.1958
2.2468	0.6541	3325	1.1962
2.2454	0.6590	3350	1.1960
2.1698	0.6640	3375	1.1960
2.3447	0.6689	3400	1.1960
2.2465	0.6738	3425	1.1961
2.3927	0.6787	3450	1.1962
2.2866	0.6836	3475	1.1958
2.1289	0.6886	3500	1.1959
2.1554	0.6935	3525	1.1962
2.199	0.6984	3550	1.1959
2.1435	0.7033	3575	1.1957
2.2876	0.7082	3600	1.1961
2.0832	0.7131	3625	1.1959
2.2221	0.7181	3650	1.1956
2.4723	0.7230	3675	1.1955
2.2343	0.7279	3700	1.1959
2.4596	0.7328	3725	1.1959
2.2936	0.7377	3750	1.1960
2.3877	0.7427	3775	1.1958
2.2913	0.7476	3800	1.1961
2.363	0.7525	3825	1.1961
2.2781	0.7574	3850	1.1955
2.2674	0.7623	3875	1.1958
2.2614	0.7672	3900	1.1959
2.2656	0.7722	3925	1.1958
2.0995	0.7771	3950	1.1962
2.3779	0.7820	3975	1.1963
2.1707	0.7869	4000	1.1959
2.1654	0.7918	4025	1.1960
2.2345	0.7968	4050	1.1959
2.2606	0.8017	4075	1.1960
2.1682	0.8066	4100	1.1958
2.377	0.8115	4125	1.1957
2.1217	0.8164	4150	1.1960
2.0862	0.8213	4175	1.1958
2.4084	0.8263	4200	1.1955
2.3288	0.8312	4225	1.1962
2.1782	0.8361	4250	1.1960
2.095	0.8410	4275	1.1959
2.1659	0.8459	4300	1.1962
2.216	0.8509	4325	1.1957
2.185	0.8558	4350	1.1961
2.1729	0.8607	4375	1.1957
2.302	0.8656	4400	1.1959
2.1731	0.8705	4425	1.1959
2.4731	0.8754	4450	1.1961
2.3024	0.8804	4475	1.1959
2.255	0.8853	4500	1.1960
2.4396	0.8902	4525	1.1955
2.1763	0.8951	4550	1.1958
2.5524	0.9000	4575	1.1958
2.2964	0.9050	4600	1.1959
2.1957	0.9099	4625	1.1957
2.1413	0.9148	4650	1.1957
2.3669	0.9197	4675	1.1960
2.4035	0.9246	4700	1.1956
2.2217	0.9295	4725	1.1958
2.3217	0.9345	4750	1.1961
2.1792	0.9394	4775	1.1957
2.0124	0.9443	4800	1.1955
2.1503	0.9492	4825	1.1960
2.2102	0.9541	4850	1.1958
2.2302	0.9591	4875	1.1960
2.2598	0.9640	4900	1.1960
2.0807	0.9689	4925	1.1957
2.3987	0.9738	4950	1.1959
2.2453	0.9787	4975	1.1959
2.2694	0.9836	5000	1.1961
2.4709	0.9886	5025	1.1959
2.2237	0.9935	5050	1.1957
2.1821	0.9984	5075	1.1960

Framework versions

• Transformers 4.51.3
• Pytorch 2.1.2+cu121
• Datasets 3.6.0
• Tokenizers 0.21.1