djt6w2b4_20250703_010013

donoway/djt6w2b4_20250703_010013

djt6w2b4_20250703_010013 is a machine learning model from donoway. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft. The card lists the license as llama3.2.

should probably proofread and complete it, then remove this comment. --

Downloads · 30 days

18% of all-time downloads

All-time downloads

Public

Repo size

198 MB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors180 MB · 91%

At a glance

Library: peft
License: llama3.2
Access: Public
Created: Jul 3, 2025
Updated: Jul 3, 2025
SHA: f2b02cf4

Base models

meta-llama/Llama-3.2-1B

Model card

From the Hugging Face model README

djt6w2b4_20250703_010013

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: 1.2776
Model Preparation Time: 0.0078
Move Accuracy: 0.0331
Token Accuracy: 0.5095
Accuracy: 0.0331

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: 0.0005
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	0.0078	0.0	0.0000	0.0
1.8824	0.0098	100	1.8814	0.0078	0.0006	0.3164	0.0006
1.594	0.0196	200	1.5555	0.0078	0.0064	0.4090	0.0064
1.4127	0.0295	300	1.4472	0.0078	0.0050	0.4462	0.0050
1.3507	0.0393	400	1.4133	0.0078	0.0075	0.4627	0.0075
1.3631	0.0491	500	1.3908	0.0078	0.0145	0.4666	0.0145
1.2753	0.0589	600	1.3304	0.0078	0.0212	0.4925	0.0212
1.2862	0.0687	700	1.3124	0.0078	0.0271	0.4954	0.0271
1.3429	0.0785	800	1.2845	0.0078	0.0284	0.5051	0.0284
1.2912	0.0884	900	1.2776	0.0078	0.0331	0.5095	0.0331
1.2814	0.0982	1000	1.2958	0.0078	0.0304	0.5086	0.0304
1.2372	0.1080	1100	1.2652	0.0078	0.0293	0.5117	0.0293
1.2665	0.1178	1200	1.3114	0.0078	0.0193	0.4921	0.0193
1.3714	0.1276	1300	1.3755	0.0078	0.0101	0.4613	0.0101
1.4697	0.1374	1400	1.4542	0.0078	0.0044	0.4328	0.0044
1.4376	0.1473	1500	1.4355	0.0078	0.0070	0.4345	0.0070
1.4635	0.1571	1600	1.4405	0.0078	0.0079	0.4341	0.0079
1.4976	0.1669	1700	1.4882	0.0078	0.0056	0.4153	0.0056
1.4587	0.1767	1800	1.4701	0.0078	0.0040	0.4197	0.0040
1.4365	0.1865	1900	1.4401	0.0078	0.0053	0.4302	0.0053
1.4271	0.1963	2000	1.4630	0.0078	0.0072	0.4321	0.0072
1.4536	0.2062	2100	1.4440	0.0078	0.0083	0.4355	0.0083
1.4593	0.2160	2200	1.4722	0.0078	0.0034	0.4217	0.0034
1.4409	0.2258	2300	1.4480	0.0078	0.0041	0.4355	0.0041
1.4283	0.2356	2400	1.4602	0.0078	0.0077	0.4255	0.0077
1.5308	0.2454	2500	1.5826	0.0078	0.0032	0.3727	0.0032
1.5071	0.2553	2600	1.4775	0.0078	0.0025	0.4267	0.0025
1.4885	0.2651	2700	1.4641	0.0078	0.0005	0.4290	0.0005
1.4756	0.2749	2800	1.4895	0.0078	0.0032	0.4229	0.0032
1.4356	0.2847	2900	1.4428	0.0078	0.0071	0.4355	0.0071
1.4386	0.2945	3000	1.4538	0.0078	0.0134	0.4292	0.0134
1.5128	0.3043	3100	1.5128	0.0078	0.0038	0.4133	0.0038
1.4581	0.3142	3200	1.4713	0.0078	0.0033	0.4256	0.0033
1.5054	0.3240	3300	1.4867	0.0078	0.0043	0.4179	0.0043
1.5353	0.3338	3400	1.4906	0.0078	0.0017	0.4125	0.0017
1.4279	0.3436	3500	1.4991	0.0078	0.0002	0.4249	0.0002
1.5716	0.3534	3600	1.5143	0.0078	0.0041	0.4119	0.0041
1.6004	0.3632	3700	1.5423	0.0078	0.0075	0.3934	0.0075
1.5434	0.3731	3800	1.4724	0.0078	0.0012	0.4260	0.0012
1.8342	0.3829	3900	1.7355	0.0078	0.0001	0.4019	0.0001
3.6221	0.3927	4000	3.3800	0.0078	0.0001	0.2706	0.0001
2.2118	0.4025	4100	2.1216	0.0078	0.0	0.2738	0.0
1.7579	0.4123	4200	1.7787	0.0078	0.0001	0.2959	0.0001
1.7056	0.4221	4300	1.7081	0.0078	0.0	0.3274	0.0
2.2442	0.4320	4400	2.0720	0.0078	0.0	0.3068	0.0
1.9175	0.4418	4500	1.9059	0.0078	0.0	0.3019	0.0
1.8231	0.4516	4600	1.9020	0.0078	0.0006	0.2867	0.0006
1.8126	0.4614	4700	1.7560	0.0078	0.0	0.3042	0.0
1.7526	0.4712	4800	1.7206	0.0078	0.0	0.3141	0.0
1.8529	0.4811	4900	1.8412	0.0078	0.0	0.2880	0.0
1.8225	0.4909	5000	1.8084	0.0078	0.0	0.3022	0.0
2.0292	0.5007	5100	1.9513	0.0078	0.0001	0.2999	0.0001
3.749	0.5105	5200	3.5389	0.0078	0.0	0.2154	0.0
2.1046	0.5203	5300	2.1675	0.0078	0.0	0.2573	0.0
2.2037	0.5301	5400	2.2687	0.0078	0.0	0.2665	0.0
3.3405	0.5400	5500	3.3841	0.0078	0.0	0.2599	0.0
1.8169	0.5498	5600	1.8139	0.0078	0.0006	0.3120	0.0006
2.4293	0.5596	5700	2.4521	0.0078	0.0	0.2521	0.0
2.0367	0.5694	5800	1.9990	0.0078	0.0	0.2992	0.0
2.0037	0.5792	5900	2.0361	0.0078	0.0	0.2823	0.0
1.7508	0.5890	6000	1.7837	0.0078	0.0	0.3089	0.0
1.8308	0.5989	6100	1.7989	0.0078	0.0006	0.3105	0.0006
1.8895	0.6087	6200	1.8617	0.0078	0.0	0.3058	0.0
1.895	0.6185	6300	1.9454	0.0078	0.0	0.3007	0.0
2.0118	0.6283	6400	1.9961	0.0078	0.0	0.2875	0.0
1.9606	0.6381	6500	1.9635	0.0078	0.0	0.2886	0.0
1.9441	0.6479	6600	1.9363	0.0078	0.0	0.2781	0.0
1.9044	0.6578	6700	1.9231	0.0078	0.0	0.2824	0.0
1.9237	0.6676	6800	1.9286	0.0078	0.0	0.2813	0.0
1.9594	0.6774	6900	1.9527	0.0078	0.0	0.2883	0.0
1.9465	0.6872	7000	1.9657	0.0078	0.0	0.2865	0.0
1.9471	0.6970	7100	1.9416	0.0078	0.0	0.2834	0.0
1.9192	0.7069	7200	1.9365	0.0078	0.0	0.2900	0.0
1.8879	0.7167	7300	1.8842	0.0078	0.0	0.2800	0.0
1.8191	0.7265	7400	1.8233	0.0078	0.0	0.2780	0.0
3.4521	0.7363	7500	3.0725	0.0078	0.0015	0.1996	0.0015
4.8817	0.7461	7600	5.0935	0.0078	0.0	0.2554	0.0
3.0782	0.7559	7700	3.0871	0.0078	0.0	0.2096	0.0
2.8546	0.7658	7800	2.7414	0.0078	0.0	0.2294	0.0
3.1133	0.7756	7900	3.0926	0.0078	0.0	0.2169	0.0
2.2426	0.7854	8000	2.0991	0.0078	0.0	0.2465	0.0
2.3783	0.7952	8100	2.3327	0.0078	0.0	0.2408	0.0
2.5783	0.8050	8200	2.5641	0.0078	0.0	0.1996	0.0
2.1073	0.8148	8300	2.1027	0.0078	0.0	0.2512	0.0
2.7377	0.8247	8400	2.7857	0.0078	0.0	0.2398	0.0
2.4076	0.8345	8500	2.4704	0.0078	0.0	0.2279	0.0
4.3735	0.8443	8600	4.3213	0.0078	0.0	0.1912	0.0
2.5489	0.8541	8700	2.5429	0.0078	0.0	0.2351	0.0
2.3223	0.8639	8800	2.4023	0.0078	0.0	0.2492	0.0
2.542	0.8737	8900	2.6886	0.0078	0.0	0.2466	0.0
2.3313	0.8836	9000	2.3201	0.0078	0.0	0.2335	0.0
2.1456	0.8934	9100	2.1673	0.0078	0.0	0.2482	0.0
2.4443	0.9032	9200	2.4611	0.0078	0.0	0.1916	0.0
2.2046	0.9130	9300	2.2318	0.0078	0.0	0.2481	0.0
2.1737	0.9228	9400	2.1581	0.0078	0.0	0.2564	0.0
2.1452	0.9327	9500	2.1426	0.0078	0.0	0.2561	0.0
2.1378	0.9425	9600	2.1400	0.0078	0.0	0.2546	0.0
2.0777	0.9523	9700	2.0768	0.0078	0.0	0.2490	0.0
2.1997	0.9621	9800	2.3008	0.0078	0.0	0.2545	0.0
2.3975	0.9719	9900	2.3790	0.0078	0.0	0.2484	0.0
2.5389	0.9817	10000	2.7908	0.0078	0.0	0.1931	0.0
2.063	0.9916	10100	2.0657	0.0078	0.0	0.2533	0.0
3.2919	1.0014	10200	3.5386	0.0078	0.0	0.1981	0.0
2.411	1.0112	10300	2.3723	0.0078	0.0	0.2070	0.0
6.5058	1.0210	10400	6.5152	0.0078	0.0	0.2005	0.0
3.1536	1.0308	10500	3.2315	0.0078	0.0	0.2182	0.0
2.9084	1.0406	10600	2.9040	0.0078	0.0	0.2242	0.0
3.0218	1.0505	10700	2.9373	0.0078	0.0	0.2274	0.0
2.9291	1.0603	10800	2.9322	0.0078	0.0	0.2175	0.0
2.9923	1.0701	10900	2.9752	0.0078	0.0	0.2137	0.0
3.6629	1.0799	11000	3.6151	0.0078	0.0	0.1831	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

Library: peft
License: llama3.2
Created: Jul 3, 2025
Updated: Jul 3, 2025