tfa_output_2025_m05_d13_t13h_51m_30s

This model is a fine-tuned version of internlm/internlm2-math-plus-1_8b on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.2781

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	1.2781
2.6109	0.0049	25	1.2778
2.6952	0.0098	50	1.2779
2.8036	0.0147	75	1.2780
2.8808	0.0196	100	1.2780
3.0941	0.0245	125	1.2781
2.4797	0.0294	150	1.2779
2.7034	0.0343	175	1.2778
3.0358	0.0392	200	1.2781
2.6713	0.0441	225	1.2779
2.8436	0.0490	250	1.2779
2.8396	0.0539	275	1.2779
2.8333	0.0588	300	1.2779
2.9845	0.0637	325	1.2782
2.6105	0.0686	350	1.2780
2.8874	0.0735	375	1.2781
2.626	0.0784	400	1.2779
2.6437	0.0833	425	1.2779
2.8082	0.0882	450	1.2781
2.7265	0.0931	475	1.2781
2.3798	0.0981	500	1.2779
2.677	0.1030	525	1.2781
2.6383	0.1079	550	1.2781
2.7663	0.1128	575	1.2779
2.6638	0.1177	600	1.2780
2.7337	0.1226	625	1.2779
2.801	0.1275	650	1.2781
2.6107	0.1324	675	1.2781
2.745	0.1373	700	1.2779
2.7384	0.1422	725	1.2780
2.7729	0.1471	750	1.2780
2.9625	0.1520	775	1.2781
2.4783	0.1569	800	1.2780
3.0425	0.1618	825	1.2782
2.6405	0.1667	850	1.2778
2.9304	0.1716	875	1.2780
2.9427	0.1765	900	1.2779
2.5965	0.1814	925	1.2779
2.8121	0.1863	950	1.2781
2.6972	0.1912	975	1.2780
2.7454	0.1961	1000	1.2780
2.6769	0.2010	1025	1.2779
3.0904	0.2059	1050	1.2779
2.9542	0.2108	1075	1.2779
2.8049	0.2157	1100	1.2780
2.668	0.2206	1125	1.2780
2.8104	0.2255	1150	1.2780
2.5648	0.2304	1175	1.2780
2.6159	0.2353	1200	1.2781
2.8947	0.2402	1225	1.2781
2.6045	0.2451	1250	1.2780
2.767	0.2500	1275	1.2780
2.9516	0.2549	1300	1.2778
2.7013	0.2598	1325	1.2782
2.9801	0.2647	1350	1.2779
2.4982	0.2696	1375	1.2780
3.023	0.2745	1400	1.2780
2.7095	0.2794	1425	1.2780
2.6959	0.2843	1450	1.2779
2.5794	0.2893	1475	1.2779
3.0798	0.2942	1500	1.2782
2.5299	0.2991	1525	1.2781
2.8247	0.3040	1550	1.2780
2.6481	0.3089	1575	1.2778
2.3977	0.3138	1600	1.2780
2.626	0.3187	1625	1.2778
2.8101	0.3236	1650	1.2780
2.7166	0.3285	1675	1.2780
2.9789	0.3334	1700	1.2779
2.9734	0.3383	1725	1.2780
2.6497	0.3432	1750	1.2781
2.7752	0.3481	1775	1.2780
3.0049	0.3530	1800	1.2778
2.7946	0.3579	1825	1.2778
2.7212	0.3628	1850	1.2780
2.7503	0.3677	1875	1.2778
2.6616	0.3726	1900	1.2781
3.1099	0.3775	1925	1.2781
2.7114	0.3824	1950	1.2781
2.6648	0.3873	1975	1.2781
2.8947	0.3922	2000	1.2780
2.5636	0.3971	2025	1.2780
2.618	0.4020	2050	1.2780
2.6153	0.4069	2075	1.2779
2.7458	0.4118	2100	1.2780
2.896	0.4167	2125	1.2779
2.9055	0.4216	2150	1.2781
2.8312	0.4265	2175	1.2781
2.6273	0.4314	2200	1.2781
2.7673	0.4363	2225	1.2780
2.887	0.4412	2250	1.2780
2.7996	0.4461	2275	1.2780
2.6026	0.4510	2300	1.2780
2.8637	0.4559	2325	1.2779
2.6673	0.4608	2350	1.2780
2.7375	0.4657	2375	1.2780
2.7014	0.4706	2400	1.2780
3.0431	0.4755	2425	1.2780
2.7895	0.4805	2450	1.2780
2.5445	0.4854	2475	1.2781
2.8042	0.4903	2500	1.2781
2.4517	0.4952	2525	1.2779
3.0145	0.5001	2550	1.2779
2.8011	0.5050	2575	1.2779
2.7895	0.5099	2600	1.2779
2.8871	0.5148	2625	1.2779
2.7724	0.5197	2650	1.2779
2.5841	0.5246	2675	1.2780
2.7891	0.5295	2700	1.2779
2.9153	0.5344	2725	1.2779
3.0127	0.5393	2750	1.2780
2.8079	0.5442	2775	1.2778
2.8522	0.5491	2800	1.2780
2.6897	0.5540	2825	1.2779
2.822	0.5589	2850	1.2777
2.8534	0.5638	2875	1.2778
2.5255	0.5687	2900	1.2778
2.6427	0.5736	2925	1.2780
3.0485	0.5785	2950	1.2782
3.0283	0.5834	2975	1.2779
2.9914	0.5883	3000	1.2780
2.9151	0.5932	3025	1.2783
2.397	0.5981	3050	1.2780
2.8832	0.6030	3075	1.2780
2.8657	0.6079	3100	1.2780
2.5352	0.6128	3125	1.2779
2.8679	0.6177	3150	1.2778
2.6386	0.6226	3175	1.2780
2.9986	0.6275	3200	1.2779
2.842	0.6324	3225	1.2779
2.6134	0.6373	3250	1.2780
2.8062	0.6422	3275	1.2781
2.8878	0.6471	3300	1.2780
2.6385	0.6520	3325	1.2780
2.7413	0.6569	3350	1.2780
2.8832	0.6618	3375	1.2781
2.782	0.6667	3400	1.2780
2.7907	0.6717	3425	1.2779
2.7367	0.6766	3450	1.2781
2.8375	0.6815	3475	1.2780
2.8279	0.6864	3500	1.2780
2.7932	0.6913	3525	1.2781
2.6823	0.6962	3550	1.2780
2.7605	0.7011	3575	1.2779
2.8804	0.7060	3600	1.2780
2.769	0.7109	3625	1.2781
2.6696	0.7158	3650	1.2783
2.7543	0.7207	3675	1.2781
2.7719	0.7256	3700	1.2780
2.7031	0.7305	3725	1.2782
2.9465	0.7354	3750	1.2780
2.9159	0.7403	3775	1.2780
2.8126	0.7452	3800	1.2780
2.8721	0.7501	3825	1.2781
2.875	0.7550	3850	1.2781
2.7	0.7599	3875	1.2781
2.8479	0.7648	3900	1.2782
2.7953	0.7697	3925	1.2779
2.7945	0.7746	3950	1.2778
2.8429	0.7795	3975	1.2777
2.8151	0.7844	4000	1.2779
2.9726	0.7893	4025	1.2779
2.6825	0.7942	4050	1.2781
2.425	0.7991	4075	1.2781
2.5809	0.8040	4100	1.2778
3.0961	0.8089	4125	1.2780
2.8323	0.8138	4150	1.2780
2.7579	0.8187	4175	1.2781
2.8227	0.8236	4200	1.2780
3.046	0.8285	4225	1.2780
2.593	0.8334	4250	1.2779
3.0566	0.8383	4275	1.2779
2.4772	0.8432	4300	1.2780
2.9035	0.8481	4325	1.2779
2.6611	0.8530	4350	1.2780
2.789	0.8579	4375	1.2780
2.5477	0.8629	4400	1.2781
2.65	0.8678	4425	1.2780
2.7394	0.8727	4450	1.2779
2.9178	0.8776	4475	1.2781
2.6875	0.8825	4500	1.2781
2.6716	0.8874	4525	1.2780
2.66	0.8923	4550	1.2783
3.0137	0.8972	4575	1.2780
2.714	0.9021	4600	1.2779
2.8224	0.9070	4625	1.2780
2.8566	0.9119	4650	1.2782
2.6979	0.9168	4675	1.2781
3.0773	0.9217	4700	1.2780
2.7923	0.9266	4725	1.2780
2.6275	0.9315	4750	1.2781
2.8812	0.9364	4775	1.2779
2.8417	0.9413	4800	1.2780
2.8717	0.9462	4825	1.2780
2.6871	0.9511	4850	1.2780
2.8382	0.9560	4875	1.2781
2.8615	0.9609	4900	1.2779
2.9204	0.9658	4925	1.2779
2.7162	0.9707	4950	1.2781
2.5257	0.9756	4975	1.2780
2.7771	0.9805	5000	1.2779
2.8008	0.9854	5025	1.2780
2.8659	0.9903	5050	1.2778
2.8939	0.9952	5075	1.2781

Framework versions

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