You can deploy this model and start earning money today!

abdukuzi45/
qwen3.5-4b-amharic-sft

Name: qwen3.5-4b-amharic-sft
Availability: InStock

rodrigomt/Qwen3.5-4B-Uncensored-Aggressive

Views

No views yet

qwen3.5-4b-amharic-sft

This model is a fine-tuned version of rodrigomt/Qwen3.5-4B-Uncensored-Aggressive on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.9129

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: 4
eval_batch_size: 4
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 16
optimizer: Use OptimizerNames.ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 2000
num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss
0.9783	0.0048	500	1.1055
0.7885	0.0095	1000	1.0728
0.8665	0.0143	1500	1.0569
0.7903	0.0190	2000	1.0447
0.9127	0.0238	2500	1.0358
1.0222	0.0286	3000	1.0299
0.9411	0.0333	3500	1.0249
0.7615	0.0381	4000	1.0201
0.9558	0.0429	4500	1.0161
0.8941	0.0476	5000	1.0125
0.9904	0.0524	5500	1.0096
0.9445	0.0571	6000	1.0072
0.9025	0.0619	6500	1.0040
0.8491	0.0667	7000	1.0022
1.0229	0.0714	7500	0.9993
0.9753	0.0762	8000	0.9976
0.8347	0.0810	8500	0.9954
0.9455	0.0857	9000	0.9938
0.8080	0.0905	9500	0.9924
0.8473	0.0952	10000	0.9904
0.9663	0.1000	10500	0.9886
0.8637	0.1048	11000	0.9869
0.9498	0.1095	11500	0.9859
0.8873	0.1143	12000	0.9845
0.8302	0.1191	12500	0.9830
0.8512	0.1238	13000	0.9815
0.8519	0.1286	13500	0.9801
0.9411	0.1333	14000	0.9787
0.8841	0.1381	14500	0.9778
0.9019	0.1429	15000	0.9764
0.8912	0.1476	15500	0.9749
0.7940	0.1524	16000	0.9746
0.8687	0.1572	16500	0.9730
0.8975	0.1619	17000	0.9719
0.8034	0.1667	17500	0.9710
0.9155	0.1714	18000	0.9697
1.0111	0.1762	18500	0.9683
0.8701	0.1810	19000	0.9676
0.9612	0.1857	19500	0.9664
0.8613	0.1905	20000	0.9655
0.9037	0.1953	20500	0.9643
0.9640	0.2000	21000	0.9635
0.9517	0.2048	21500	0.9623
0.8436	0.2095	22000	0.9621
0.8581	0.2143	22500	0.9605
0.7853	0.2191	23000	0.9597
0.8109	0.2238	23500	0.9585
0.9610	0.2286	24000	0.9577
0.9287	0.2333	24500	0.9569
0.8676	0.2381	25000	0.9567
0.8379	0.2429	25500	0.9560
0.9694	0.2476	26000	0.9549
0.9347	0.2524	26500	0.9544
0.8988	0.2572	27000	0.9533
1.0526	0.2619	27500	0.9530
0.8792	0.2667	28000	0.9522
0.8639	0.2714	28500	0.9512
0.8075	0.2762	29000	0.9513
0.9530	0.2810	29500	0.9502
0.9089	0.2857	30000	0.9495
0.8826	0.2905	30500	0.9487
0.8074	0.2953	31000	0.9480
0.9022	0.3000	31500	0.9478
0.8179	0.3048	32000	0.9474
0.8492	0.3095	32500	0.9462
0.8752	0.3143	33000	0.9459
0.7500	0.3191	33500	0.9453
0.7247	0.3238	34000	0.9451
0.9445	0.3286	34500	0.9440
0.8038	0.3334	35000	0.9438
0.8360	0.3381	35500	0.9430
0.9285	0.3429	36000	0.9423
0.8626	0.3476	36500	0.9420
0.8432	0.3524	37000	0.9414
0.8513	0.3572	37500	0.9408
0.8562	0.3619	38000	0.9409
0.8223	0.3667	38500	0.9399
0.8689	0.3715	39000	0.9396
0.8963	0.3762	39500	0.9391
0.8877	0.3810	40000	0.9386
0.8809	0.3857	40500	0.9381
0.9183	0.3905	41000	0.9375
0.8198	0.3953	41500	0.9373
0.9095	0.4000	42000	0.9372
0.9248	0.4048	42500	0.9363
0.8974	0.4096	43000	0.9361
0.9825	0.4143	43500	0.9357
0.8790	0.4191	44000	0.9352
0.7921	0.4238	44500	0.9349
0.8284	0.4286	45000	0.9342
0.8564	0.4334	45500	0.9338
0.7322	0.4381	46000	0.9337
0.9439	0.4429	46500	0.9332
0.8393	0.4476	47000	0.9326
0.8429	0.4524	47500	0.9326
0.8361	0.4572	48000	0.9320
0.8740	0.4619	48500	0.9319
0.7704	0.4667	49000	0.9317
0.8227	0.4715	49500	0.9312
0.8017	0.4762	50000	0.9306
0.8554	0.4810	50500	0.9308
0.8479	0.4857	51000	0.9299
0.8771	0.4905	51500	0.9297
0.8195	0.4953	52000	0.9293
0.8442	0.5000	52500	0.9289
0.9754	0.5048	53000	0.9287
0.8338	0.5096	53500	0.9286
0.8628	0.5143	54000	0.9281
0.8782	0.5191	54500	0.9275
0.8274	0.5238	55000	0.9273
0.8855	0.5286	55500	0.9273
0.8431	0.5334	56000	0.9269
0.7938	0.5381	56500	0.9268
0.8797	0.5429	57000	0.9264
0.9037	0.5477	57500	0.9261
0.8206	0.5524	58000	0.9259
0.8704	0.5572	58500	0.9257
0.8609	0.5619	59000	0.9252
0.8279	0.5667	59500	0.9249
0.8822	0.5715	60000	0.9247
0.9002	0.5762	60500	0.9247
0.8806	0.5810	61000	0.9245
0.8331	0.5858	61500	0.9243
0.7674	0.5905	62000	0.9240
0.8917	0.5953	62500	0.9233
0.8056	0.6000	63000	0.9237
0.9389	0.6048	63500	0.9236
0.9153	0.6096	64000	0.9231
0.8578	0.6143	64500	0.9226
0.8353	0.6191	65000	0.9227
0.7434	0.6239	65500	0.9226
0.8597	0.6286	66000	0.9224
0.8331	0.6334	66500	0.9221
0.8524	0.6381	67000	0.9218
0.8269	0.6429	67500	0.9216
0.8183	0.6477	68000	0.9217
0.8445	0.6524	68500	0.9212
0.8735	0.6572	69000	0.9207
0.7930	0.6619	69500	0.9207
0.8069	0.6667	70000	0.9205
0.8498	0.6715	70500	0.9203
0.8306	0.6762	71000	0.9201
0.8932	0.6810	71500	0.9197
0.8015	0.6858	72000	0.9196
0.9119	0.6905	72500	0.9195
0.8716	0.6953	73000	0.9193
0.9422	0.7000	73500	0.9191
0.9981	0.7048	74000	0.9188
0.8686	0.7096	74500	0.9190
0.7906	0.7143	75000	0.9185
0.8408	0.7191	75500	0.9185
0.8016	0.7239	76000	0.9181
0.9668	0.7286	76500	0.9182
0.8195	0.7334	77000	0.9180
0.9168	0.7381	77500	0.9178
0.7715	0.7429	78000	0.9178
0.8131	0.7477	78500	0.9175
0.8532	0.7524	79000	0.9174
0.7908	0.7572	79500	0.9175
0.8993	0.7620	80000	0.9173
0.8437	0.7667	80500	0.9169
0.7925	0.7715	81000	0.9168
0.8448	0.7762	81500	0.9167
0.8336	0.7810	82000	0.9167
0.8560	0.7858	82500	0.9163
0.7818	0.7905	83000	0.9163
0.8670	0.7953	83500	0.9161
0.7766	0.8001	84000	0.9158
0.8323	0.8048	84500	0.9157
0.8154	0.8096	85000	0.9157
0.8168	0.8143	85500	0.9155
0.8747	0.8191	86000	0.9153
0.9030	0.8239	86500	0.9154
0.9013	0.8286	87000	0.9151
0.8988	0.8334	87500	0.9151
0.7868	0.8382	88000	0.9150
0.7361	0.8429	88500	0.9149
0.8644	0.8477	89000	0.9149
0.8439	0.8524	89500	0.9147
0.7697	0.8572	90000	0.9147
0.9044	0.8620	90500	0.9145
0.7912	0.8667	91000	0.9144
0.7964	0.8715	91500	0.9144
0.9045	0.8762	92000	0.9141
0.8180	0.8810	92500	0.9142
0.8857	0.8858	93000	0.9141
0.8326	0.8905	93500	0.9140
0.8142	0.8953	94000	0.9138
0.8994	0.9001	94500	0.9139
0.8333	0.9048	95000	0.9138
0.9026	0.9096	95500	0.9137
0.7925	0.9143	96000	0.9136
0.9397	0.9191	96500	0.9136
0.8458	0.9239	97000	0.9135
0.8173	0.9286	97500	0.9133
0.7917	0.9334	98000	0.9134
0.7977	0.9382	98500	0.9133
0.7887	0.9429	99000	0.9133
0.7961	0.9477	99500	0.9132
0.9029	0.9524	100000	0.9131
0.7917	0.9572	100500	0.9130
0.8296	0.9620	101000	0.9130
0.7581	0.9667	101500	0.9130
0.8590	0.9715	102000	0.9130
0.9194	0.9763	102500	0.9130
0.8314	0.9810	103000	0.9129
0.8958	0.9858	103500	0.9129
0.8673	0.9905	104000	0.9129
0.8053	0.9953	104500	0.9128
0.8942	1.0	104993	0.9129

Framework versions

PEFT 0.20.0
Transformers 5.5.0
Pytorch 2.11.0+cu130
Datasets 4.3.0
Tokenizers 0.22.2

abdukuzi45/qwen3.5-4b-amharic-sft

qwen3.5-4b-amharic-sft

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

abdukuzi45/
qwen3.5-4b-amharic-sft