9ijlbny9_20250704_074211

This model is a fine-tuned version of meta-llama/Llama-3.2-1B on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.0933
• Model Preparation Time: 0.0084
• Move Accuracy: 0.0625
• Token Accuracy: 0.5816
• Accuracy: 0.0625

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: 0.0003
• train_batch_size: 128
• eval_batch_size: 256
• 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: constant_with_warmup
• lr_scheduler_warmup_ratio: 0.001
• num_epochs: 100

Training results

Training Loss	Epoch	Step	Validation Loss	Model Preparation Time	Move Accuracy	Token Accuracy	Accuracy
No log	0	0	11.9474	0.0084	0.0	0.0000	0.0
2.065	0.0098	100	2.0474	0.0084	0.0	0.2914	0.0
1.6297	0.0196	200	1.5867	0.0084	0.0014	0.3896	0.0014
1.4158	0.0295	300	1.4600	0.0084	0.0097	0.4390	0.0097
1.4018	0.0393	400	1.4424	0.0084	0.0050	0.4484	0.0050
1.3811	0.0491	500	1.4269	0.0084	0.0052	0.4493	0.0052
1.3154	0.0589	600	1.3629	0.0084	0.0116	0.4764	0.0116
1.3229	0.0687	700	1.3269	0.0084	0.0256	0.4940	0.0256
1.3557	0.0785	800	1.3086	0.0084	0.0251	0.4990	0.0251
1.2703	0.0884	900	1.2613	0.0084	0.0367	0.5174	0.0367
1.2708	0.0982	1000	1.2597	0.0084	0.0367	0.5181	0.0367
1.1866	0.1080	1100	1.2246	0.0084	0.0445	0.5299	0.0445
1.1367	0.1178	1200	1.1978	0.0084	0.0502	0.5411	0.0502
1.1711	0.1276	1300	1.1930	0.0084	0.0454	0.5413	0.0454
1.2022	0.1374	1400	1.1712	0.0084	0.0537	0.5536	0.0537
1.1191	0.1473	1500	1.1563	0.0084	0.0549	0.5587	0.0549
1.1173	0.1571	1600	1.1286	0.0084	0.0557	0.5677	0.0557
1.1074	0.1669	1700	1.1240	0.0084	0.0566	0.5699	0.0566
1.1314	0.1767	1800	1.1178	0.0084	0.0548	0.5688	0.0548
1.071	0.1865	1900	1.1124	0.0084	0.0603	0.5727	0.0603
1.0726	0.1963	2000	1.1116	0.0084	0.0571	0.5742	0.0571
1.093	0.2062	2100	1.1103	0.0084	0.0558	0.5709	0.0558
1.1121	0.2160	2200	1.0985	0.0084	0.0623	0.5769	0.0623
1.1308	0.2258	2300	1.1009	0.0084	0.0606	0.5781	0.0606
1.0199	0.2356	2400	1.0933	0.0084	0.0625	0.5816	0.0625
1.0705	0.2454	2500	1.1059	0.0084	0.0588	0.5761	0.0588
1.0801	0.2553	2600	1.1104	0.0084	0.0600	0.5757	0.0600
1.1865	0.2651	2700	1.1280	0.0084	0.0589	0.5681	0.0589
1.1163	0.2749	2800	1.1411	0.0084	0.0510	0.5597	0.0510
1.1195	0.2847	2900	1.1493	0.0084	0.0473	0.5543	0.0473
1.1404	0.2945	3000	1.1494	0.0084	0.0475	0.5600	0.0475
1.1655	0.3043	3100	1.1738	0.0084	0.0389	0.5427	0.0389
1.173	0.3142	3200	1.1643	0.0084	0.0414	0.5499	0.0414
1.2128	0.3240	3300	1.1975	0.0084	0.0382	0.5348	0.0382
1.2039	0.3338	3400	1.2143	0.0084	0.0289	0.5301	0.0289
1.175	0.3436	3500	1.2469	0.0084	0.0246	0.5154	0.0246
1.2885	0.3534	3600	1.2495	0.0084	0.0250	0.5129	0.0250
1.2412	0.3632	3700	1.2598	0.0084	0.0284	0.5085	0.0284
1.3328	0.3731	3800	1.2620	0.0084	0.0269	0.5121	0.0269
1.2451	0.3829	3900	1.2359	0.0084	0.0286	0.5228	0.0286
1.3301	0.3927	4000	1.2657	0.0084	0.0207	0.5019	0.0207
1.3234	0.4025	4100	1.3131	0.0084	0.0087	0.4832	0.0087
1.3299	0.4123	4200	1.3618	0.0084	0.0130	0.4651	0.0130
1.2686	0.4221	4300	1.3132	0.0084	0.0161	0.4831	0.0161
1.4038	0.4320	4400	1.3702	0.0084	0.0113	0.4622	0.0113
1.3146	0.4418	4500	1.3508	0.0084	0.0117	0.4735	0.0117
1.3373	0.4516	4600	1.3603	0.0084	0.0123	0.4664	0.0123
1.3495	0.4614	4700	1.3391	0.0084	0.0099	0.4755	0.0099
1.2884	0.4712	4800	1.3312	0.0084	0.0133	0.4752	0.0133
1.3968	0.4811	4900	1.4090	0.0084	0.0059	0.4441	0.0059
1.3645	0.4909	5000	1.3649	0.0084	0.0142	0.4653	0.0142
1.4202	0.5007	5100	1.3491	0.0084	0.0080	0.4638	0.0080
1.4521	0.5105	5200	1.4018	0.0084	0.0054	0.4453	0.0054
1.4335	0.5203	5300	1.3938	0.0084	0.0069	0.4543	0.0069
1.4216	0.5301	5400	1.4144	0.0084	0.0110	0.4425	0.0110
1.4142	0.5400	5500	1.4218	0.0084	0.0050	0.4397	0.0050
1.3516	0.5498	5600	1.3850	0.0084	0.0122	0.4598	0.0122
1.411	0.5596	5700	1.3980	0.0084	0.0146	0.4494	0.0146
1.42	0.5694	5800	1.3979	0.0084	0.0101	0.4554	0.0101
1.4441	0.5792	5900	1.4581	0.0084	0.0081	0.4353	0.0081
1.3896	0.5890	6000	1.4123	0.0084	0.0105	0.4426	0.0105
1.3489	0.5989	6100	1.3930	0.0084	0.0056	0.4484	0.0056
1.455	0.6087	6200	1.4000	0.0084	0.0043	0.4478	0.0043
1.4246	0.6185	6300	1.3904	0.0084	0.0079	0.4546	0.0079
1.3833	0.6283	6400	1.4159	0.0084	0.0038	0.4437	0.0038
1.4032	0.6381	6500	1.4113	0.0084	0.0092	0.4524	0.0092
1.3945	0.6479	6600	1.3830	0.0084	0.0134	0.4534	0.0134
1.3616	0.6578	6700	1.3861	0.0084	0.0092	0.4578	0.0092
1.3626	0.6676	6800	1.4036	0.0084	0.0077	0.4516	0.0077
1.4142	0.6774	6900	1.4018	0.0084	0.0050	0.4528	0.0050
1.3891	0.6872	7000	1.4063	0.0084	0.0063	0.4444	0.0063
1.4352	0.6970	7100	1.4834	0.0084	0.0081	0.4152	0.0081
1.4278	0.7069	7200	1.4239	0.0084	0.0070	0.4394	0.0070
1.4465	0.7167	7300	1.4672	0.0084	0.0081	0.4313	0.0081
1.4482	0.7265	7400	1.4154	0.0084	0.0091	0.4462	0.0091
1.4573	0.7363	7500	1.4571	0.0084	0.0047	0.4317	0.0047
1.4574	0.7461	7600	1.4343	0.0084	0.0090	0.4381	0.0090
1.4506	0.7559	7700	1.4271	0.0084	0.0060	0.4426	0.0060
1.3924	0.7658	7800	1.4286	0.0084	0.0048	0.4375	0.0048
1.4367	0.7756	7900	1.4696	0.0084	0.0041	0.4271	0.0041
1.3813	0.7854	8000	1.4162	0.0084	0.0067	0.4517	0.0067
1.4997	0.7952	8100	1.5320	0.0084	0.0008	0.4061	0.0008
1.483	0.8050	8200	1.4721	0.0084	0.0041	0.4176	0.0041
1.42	0.8148	8300	1.4358	0.0084	0.0031	0.4309	0.0031
1.4299	0.8247	8400	1.4142	0.0084	0.0095	0.4509	0.0095
1.411	0.8345	8500	1.4148	0.0084	0.0064	0.4372	0.0064
1.4073	0.8443	8600	1.4124	0.0084	0.0048	0.4456	0.0048
1.6194	0.8541	8700	1.6128	0.0084	0.0037	0.3800	0.0037
1.538	0.8639	8800	1.5642	0.0084	0.0014	0.3870	0.0014
1.5653	0.8737	8900	1.5667	0.0084	0.0007	0.3722	0.0007
1.4384	0.8836	9000	1.4753	0.0084	0.0035	0.4201	0.0035
1.579	0.8934	9100	1.5560	0.0084	0.0021	0.3800	0.0021
1.6234	0.9032	9200	1.5844	0.0084	0.0010	0.3701	0.0010
1.5555	0.9130	9300	1.5427	0.0084	0.0003	0.3966	0.0003
1.573	0.9228	9400	1.5540	0.0084	0.0007	0.3845	0.0007
1.5048	0.9327	9500	1.4893	0.0084	0.0001	0.4160	0.0001
1.4974	0.9425	9600	1.5039	0.0084	0.0104	0.4083	0.0104
1.5694	0.9523	9700	1.5196	0.0084	0.0012	0.3921	0.0012
1.4874	0.9621	9800	1.5037	0.0084	0.0004	0.4088	0.0004
1.4913	0.9719	9900	1.4961	0.0084	0.0	0.4125	0.0
1.5462	0.9817	10000	1.5394	0.0084	0.0014	0.3985	0.0014
1.5129	0.9916	10100	1.4783	0.0084	0.0006	0.4236	0.0006
1.4826	1.0014	10200	1.4884	0.0084	0.0006	0.4204	0.0006
1.5046	1.0112	10300	1.4761	0.0084	0.0031	0.4172	0.0031
1.5294	1.0210	10400	1.5032	0.0084	0.0049	0.4150	0.0049
1.5021	1.0308	10500	1.4630	0.0084	0.0017	0.4296	0.0017
1.4886	1.0406	10600	1.4856	0.0084	0.0108	0.4200	0.0108
1.482	1.0505	10700	1.4665	0.0084	0.0121	0.4222	0.0121
1.4923	1.0603	10800	1.4755	0.0084	0.0026	0.4261	0.0026
2.664	1.0701	10900	2.6829	0.0084	0.0	0.2999	0.0
1.7143	1.0799	11000	1.7749	0.0084	0.0026	0.3128	0.0026
1.7416	1.0897	11100	1.7182	0.0084	0.0	0.3223	0.0
1.8168	1.0995	11200	1.7728	0.0084	0.0	0.3227	0.0
1.6764	1.1094	11300	1.6721	0.0084	0.0008	0.3198	0.0008
2.4537	1.1192	11400	2.4713	0.0084	0.0	0.2414	0.0
1.7833	1.1290	11500	1.7453	0.0084	0.0012	0.3081	0.0012
1.726	1.1388	11600	1.7262	0.0084	0.0	0.3188	0.0
1.7723	1.1486	11700	1.7217	0.0084	0.0003	0.3080	0.0003
2.1355	1.1585	11800	2.1391	0.0084	0.0	0.3136	0.0
1.6861	1.1683	11900	1.6877	0.0084	0.0	0.3210	0.0
1.705	1.1781	12000	1.6816	0.0084	0.0002	0.3261	0.0002
1.6691	1.1879	12100	1.6619	0.0084	0.0	0.3175	0.0
1.6514	1.1977	12200	1.6760	0.0084	0.0006	0.3209	0.0006
1.652	1.2075	12300	1.6695	0.0084	0.0001	0.3330	0.0001
2.9753	1.2174	12400	3.4229	0.0084	0.0	0.2561	0.0
1.9972	1.2272	12500	1.9578	0.0084	0.0	0.2615	0.0

Framework versions

• PEFT 0.15.2
• Transformers 4.51.3
• Pytorch 2.6.0+cu124
• Datasets 3.5.0
• Tokenizers 0.21.1