english-telugu-colloquial-translator

This model is a fine-tuned version of unsloth/tinyllama-chat-bnb-4bit on the None dataset. It achieves the following results on the evaluation set:

• Loss: 12.0875

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: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 8
• 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: linear
• lr_scheduler_warmup_steps: 2
• num_epochs: 10
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
14.5531	0.02	2	12.6014
14.5438	0.04	4	12.6014
14.5304	0.06	6	12.6014
14.6476	0.08	8	12.6014
14.4543	0.1	10	12.6014
14.5643	0.12	12	12.6014
14.6583	0.14	14	12.6014
14.4291	0.16	16	12.6377
10.7279	0.18	18	12.6615
10.3811	0.2	20	12.6900
10.3238	0.22	22	12.6801
9.7967	0.24	24	12.6610
8.2375	0.26	26	12.6487
7.8972	0.28	28	12.6577
7.5191	0.3	30	12.6819
7.0038	0.32	32	12.7159
6.3357	0.34	34	12.7615
5.6149	0.36	36	12.7306
5.1256	0.38	38	12.7255
4.8512	0.4	40	12.7456
4.6452	0.42	42	12.8322
4.3896	0.44	44	12.8700
4.1132	0.46	46	13.0261
4.0525	0.48	48	13.0932
3.9196	0.5	50	13.2738
3.8698	0.52	52	13.4854
3.87	0.54	54	13.6945
3.7688	0.56	56	13.9230
3.8013	0.58	58	14.0024
3.7769	0.6	60	14.0958
3.7168	0.62	62	14.1539
3.6478	0.64	64	14.1336
3.6173	0.66	66	14.1170
3.5889	0.68	68	14.1506
3.6539	0.7	70	14.0984
3.569	0.72	72	14.0717
3.575	0.74	74	14.0859
3.5359	0.76	76	14.0402
3.493	0.78	78	13.9845
3.5494	0.8	80	14.0767
3.4911	0.82	82	13.9851
3.5181	0.84	84	13.9844
3.5747	0.86	86	13.9028
3.5011	0.88	88	13.7966
3.5176	0.9	90	13.7319
3.435	0.92	92	13.6152
3.4537	0.94	94	13.5217
3.5923	0.96	96	13.4117
3.4661	0.98	98	13.4709
3.4357	1.0	100	13.4526
3.3457	1.02	102	13.2060
3.4694	1.04	104	12.9044
3.3835	1.06	106	12.7492
3.3926	1.08	108	12.6022
3.3657	1.1	110	12.7361
3.4122	1.12	112	12.7930
3.3449	1.1400	114	12.6786
3.3599	1.16	116	12.5936
3.4088	1.18	118	12.5638
3.2674	1.2	120	12.4628
3.3579	1.22	122	12.3988
3.4685	1.24	124	12.4006
3.3865	1.26	126	12.4935
3.3898	1.28	128	12.5905
3.369	1.3	130	12.6106
3.4314	1.32	132	12.5862
3.3603	1.34	134	12.5651
3.3907	1.3600	136	12.5957
3.3758	1.38	138	12.6477
3.4252	1.4	140	12.7087
3.3071	1.42	142	12.6606
3.331	1.44	144	12.5663
3.4304	1.46	146	12.5268
3.3324	1.48	148	12.6252
3.4492	1.5	150	12.7579
3.2818	1.52	152	12.8290
3.3266	1.54	154	12.8191
3.3858	1.56	156	12.8332
3.4243	1.58	158	12.8793
3.407	1.6	160	12.8541
3.3113	1.62	162	12.7160
3.3866	1.6400	164	12.6564
3.3963	1.6600	166	12.6894
3.3142	1.6800	168	12.6886
3.4255	1.7	170	12.6870
3.4166	1.72	172	12.5875
3.4741	1.74	174	12.4336
3.3589	1.76	176	12.3957
3.2826	1.78	178	12.3018
3.2824	1.8	180	12.2414
3.3683	1.8200	182	12.2175
3.3208	1.8400	184	12.1681
3.259	1.8600	186	12.0882
3.3038	1.88	188	12.0351
3.239	1.9	190	11.9007
3.4067	1.92	192	11.8250
3.2361	1.94	194	11.8146
3.2919	1.96	196	11.8501
3.2731	1.98	198	12.0283
3.3297	2.0	200	12.0674
3.3888	2.02	202	12.0235
3.3474	2.04	204	11.9122
3.3192	2.06	206	11.8064
3.3615	2.08	208	11.7424
3.3157	2.1	210	11.7439
3.3557	2.12	212	11.8962
3.257	2.14	214	12.0477
3.2553	2.16	216	12.1394
3.3172	2.18	218	12.0854
3.3437	2.2	220	11.9797
3.2498	2.22	222	11.8623
3.3727	2.24	224	11.8133
3.3552	2.26	226	11.8207
3.276	2.2800	228	11.8520
3.2846	2.3	230	11.8378
3.3161	2.32	232	11.7854
3.3394	2.34	234	11.7265
3.2819	2.36	236	11.7905
3.3208	2.38	238	11.7830
3.311	2.4	240	11.7694
3.2612	2.42	242	11.7205
3.337	2.44	244	11.6739
3.2572	2.46	246	11.6186
3.352	2.48	248	11.5797
3.3386	2.5	250	11.6983
3.23	2.52	252	11.8297
3.2362	2.54	254	11.8812
3.356	2.56	256	11.8730
3.324	2.58	258	11.8454
3.2459	2.6	260	11.7585
3.3291	2.62	262	11.7125
3.3124	2.64	264	11.6896
3.2954	2.66	266	11.6460
3.4054	2.68	268	11.6470
3.2824	2.7	270	11.6621
3.243	2.7200	272	11.6653
3.2759	2.74	274	11.6649
3.2967	2.76	276	11.6434
3.2635	2.7800	278	11.5875
3.3382	2.8	280	11.5428
3.3042	2.82	282	11.5161
3.294	2.84	284	11.5343
3.2946	2.86	286	11.5622
3.3227	2.88	288	11.6000
3.3163	2.9	290	11.6305
3.2779	2.92	292	11.6502
3.2473	2.94	294	11.6962
3.3132	2.96	296	11.6897
3.2646	2.98	298	11.6621
3.264	3.0	300	11.7223
3.2831	3.02	302	11.7606
3.2811	3.04	304	11.7846
3.311	3.06	306	11.8190
3.2841	3.08	308	11.8498
3.2866	3.1	310	11.8603
3.2812	3.12	312	11.8623
3.3049	3.14	314	11.8334
3.2697	3.16	316	11.7929
3.2848	3.18	318	11.7647
3.3016	3.2	320	11.7231
3.2965	3.22	322	11.6713
3.3814	3.24	324	11.6619
3.3301	3.26	326	11.6825
3.2856	3.2800	328	11.6878
3.2986	3.3	330	11.6984
3.3232	3.32	332	11.7256
3.3027	3.34	334	11.7231
3.2647	3.36	336	11.6778
3.2607	3.38	338	11.6213
3.2642	3.4	340	11.5595
3.3528	3.42	342	11.4890
3.3236	3.44	344	11.4436
3.3361	3.46	346	11.5116
3.2158	3.48	348	11.5957
3.2805	3.5	350	11.6434
3.3629	3.52	352	11.6535
3.2424	3.54	354	11.6726
3.2742	3.56	356	11.6832
3.3758	3.58	358	11.6980
3.3679	3.6	360	11.7046
3.3049	3.62	362	11.6718
3.3386	3.64	364	11.6526
3.2201	3.66	366	11.6451
3.3085	3.68	368	11.6509
3.294	3.7	370	11.6290
3.2985	3.7200	372	11.6221
3.2542	3.74	374	11.6268
3.3054	3.76	376	11.6409
3.2653	3.7800	378	11.6504
3.2744	3.8	380	11.6544
3.3502	3.82	382	11.6510
3.3622	3.84	384	11.6679
3.2909	3.86	386	11.6650
3.2785	3.88	388	11.6746
3.2817	3.9	390	11.7087
3.3501	3.92	392	11.7265
3.2982	3.94	394	11.7431
3.27	3.96	396	11.7566
3.2608	3.98	398	11.7733
3.2845	4.0	400	11.8081
3.2537	4.02	402	11.8236
3.2962	4.04	404	11.7943
3.235	4.06	406	11.7524
3.3525	4.08	408	11.7265
3.3095	4.1	410	11.7284
3.3173	4.12	412	11.7184
3.25	4.14	414	11.6853
3.2963	4.16	416	11.6574
3.2665	4.18	418	11.6897
3.2727	4.2	420	11.7378
3.2854	4.22	422	11.7992
3.3536	4.24	424	11.8367
3.3259	4.26	426	11.8277
3.2568	4.28	428	11.8311
3.2896	4.3	430	11.8554
3.2636	4.32	432	11.8983
3.2438	4.34	434	11.9509
3.2663	4.36	436	12.0057
3.3239	4.38	438	12.0505
3.2385	4.4	440	12.0775
3.3135	4.42	442	12.0789
3.2832	4.44	444	12.0442
3.383	4.46	446	11.9843
3.2686	4.48	448	11.9345
3.3495	4.5	450	11.8651
3.3294	4.52	452	11.8080
3.2314	4.54	454	11.7570
3.3242	4.5600	456	11.7246
3.334	4.58	458	11.7251
3.2614	4.6	460	11.7150
3.3601	4.62	462	11.7077
3.2978	4.64	464	11.6892
3.2891	4.66	466	11.6758
3.3128	4.68	468	11.6679
3.2551	4.7	470	11.6513
3.3503	4.72	472	11.6563
3.2567	4.74	474	11.6602
3.2719	4.76	476	11.6619
3.2959	4.78	478	11.6577
3.4016	4.8	480	11.6625
3.3399	4.82	482	11.6747
3.3271	4.84	484	11.6839
3.3497	4.86	486	11.6985
3.3459	4.88	488	11.7071
3.3003	4.9	490	11.7242
3.3245	4.92	492	11.7588
3.3153	4.9400	494	11.7915
3.3016	4.96	496	11.8359
3.342	4.98	498	11.8648
3.3189	5.0	500	11.8929
3.2986	5.02	502	11.9180
3.3575	5.04	504	11.9406
3.3506	5.06	506	11.9583
3.241	5.08	508	11.9464
3.2923	5.1	510	11.9408
3.2885	5.12	512	11.9539
3.3319	5.14	514	11.9705
3.3434	5.16	516	11.9849
3.308	5.18	518	12.0009
3.369	5.2	520	12.0155
3.3016	5.22	522	12.0241
3.2664	5.24	524	12.0097
3.289	5.26	526	11.9818
3.2634	5.28	528	11.9613
3.3302	5.3	530	11.9450
3.3118	5.32	532	11.9303
3.2404	5.34	534	11.9144
3.3318	5.36	536	11.8935
3.3303	5.38	538	11.8752
3.2925	5.4	540	11.8733
3.2311	5.42	542	11.8669
3.2698	5.44	544	11.8755
3.3497	5.46	546	11.8977
3.2173	5.48	548	11.9211
3.2811	5.5	550	11.9364
3.3311	5.52	552	11.9603
3.2434	5.54	554	11.9724
3.3314	5.5600	556	11.9889
3.3726	5.58	558	11.9958
3.322	5.6	560	11.9985
3.3083	5.62	562	11.9939
3.2722	5.64	564	11.9810
3.3156	5.66	566	11.9692
3.3086	5.68	568	11.9507
3.2941	5.7	570	11.9313
3.3247	5.72	572	11.9336
3.3249	5.74	574	11.9441
3.2893	5.76	576	11.9541
3.2279	5.78	578	11.9692
3.3537	5.8	580	11.9915
3.3144	5.82	582	12.0050
3.2935	5.84	584	12.0004
3.1943	5.86	586	11.9895
3.3126	5.88	588	11.9875
3.3804	5.9	590	11.9816
3.2378	5.92	592	11.9590
3.3098	5.9400	594	11.9295
3.3187	5.96	596	11.9093
3.3159	5.98	598	11.9039
3.2491	6.0	600	11.9208
3.2977	6.02	602	11.9335
3.3124	6.04	604	11.9517
3.3841	6.06	606	11.9705
3.2482	6.08	608	11.9843
3.2664	6.1	610	11.9877
3.2788	6.12	612	11.9807
3.3345	6.14	614	11.9786
3.2834	6.16	616	11.9748
3.297	6.18	618	11.9637
3.2086	6.2	620	11.9547
3.3423	6.22	622	11.9641
3.3759	6.24	624	11.9639
3.2633	6.26	626	11.9614
3.2467	6.28	628	11.9525
3.2749	6.3	630	11.9509
3.2938	6.32	632	11.9540
3.2832	6.34	634	11.9491
3.3524	6.36	636	11.9573
3.3323	6.38	638	11.9559
3.3725	6.4	640	11.9544
3.3	6.42	642	11.9561
3.2336	6.44	644	11.9694
3.3106	6.46	646	11.9843
3.3212	6.48	648	11.9918
3.2931	6.5	650	11.9894
3.3186	6.52	652	11.9958
3.2939	6.54	654	12.0039
3.2535	6.5600	656	12.0201
3.3274	6.58	658	12.0478
3.2974	6.6	660	12.0750
3.2947	6.62	662	12.1043
3.3003	6.64	664	12.1158
3.2884	6.66	666	12.1164
3.2844	6.68	668	12.1093
3.2908	6.7	670	12.1004
3.2691	6.72	672	12.0890
3.2713	6.74	674	12.0609
3.2987	6.76	676	12.0261
3.3321	6.78	678	12.0050
3.3511	6.8	680	11.9872
3.2478	6.82	682	11.9773
3.3638	6.84	684	11.9579
3.3509	6.86	686	11.9381
3.2971	6.88	688	11.9260
3.2831	6.9	690	11.9218
3.2082	6.92	692	11.9266
3.2706	6.9400	694	11.9317
3.2674	6.96	696	11.9375
3.3714	6.98	698	11.9429
3.4031	7.0	700	11.9426
3.2971	7.02	702	11.9449
3.324	7.04	704	11.9418
3.3417	7.06	706	11.9375
3.2827	7.08	708	11.9304
3.312	7.1	710	11.9297
3.3466	7.12	712	11.9166
3.2802	7.14	714	11.9202
3.3044	7.16	716	11.9327
3.3214	7.18	718	11.9385
3.3134	7.2	720	11.9390
3.2394	7.22	722	11.9450
3.2663	7.24	724	11.9349
3.2937	7.26	726	11.9313
3.341	7.28	728	11.9228
3.3056	7.3	730	11.9140
3.2781	7.32	732	11.9154
3.2592	7.34	734	11.9184
3.2782	7.36	736	11.9170
3.2763	7.38	738	11.9362
3.2452	7.4	740	11.9626
3.3707	7.42	742	11.9858
3.2901	7.44	744	11.9937
3.2939	7.46	746	11.9872
3.3458	7.48	748	11.9741
3.3546	7.5	750	11.9698
3.2344	7.52	752	11.9761
3.2932	7.54	754	11.9811
3.3247	7.5600	756	11.9899
3.3052	7.58	758	11.9940
3.1382	7.6	760	12.0114
3.2433	7.62	762	12.0345
3.2343	7.64	764	12.0538
3.2632	7.66	766	12.0733
3.3221	7.68	768	12.0837
3.3628	7.7	770	12.0885
3.3591	7.72	772	12.0714
3.3538	7.74	774	12.0439
3.3086	7.76	776	12.0195
3.2278	7.78	778	11.9933
3.314	7.8	780	11.9793
3.3345	7.82	782	11.9645
3.2829	7.84	784	11.9525
3.3188	7.86	786	11.9489
3.3213	7.88	788	11.9523
3.2973	7.9	790	11.9600
3.2196	7.92	792	11.9721
3.2662	7.9400	794	11.9869
3.2958	7.96	796	11.9999
3.3321	7.98	798	12.0109
3.3159	8.0	800	12.0169
3.2353	8.02	802	12.0472
3.3223	8.04	804	12.0754
3.3285	8.06	806	12.0900
3.3272	8.08	808	12.1061
3.3628	8.1	810	12.1177
3.3072	8.12	812	12.1208
3.2064	8.14	814	12.1233
3.2286	8.16	816	12.1364
3.307	8.18	818	12.1506
3.2556	8.2	820	12.1609
3.2232	8.22	822	12.1659
3.2777	8.24	824	12.1716
3.3069	8.26	826	12.1714
3.3215	8.28	828	12.1694
3.2872	8.3	830	12.1643
3.3157	8.32	832	12.1566
3.1961	8.34	834	12.1460
3.324	8.36	836	12.1284
3.3255	8.38	838	12.0996
3.2946	8.4	840	12.0783
3.2628	8.42	842	12.0625
3.3217	8.44	844	12.0376
3.3528	8.46	846	12.0235
3.314	8.48	848	12.0103
3.3081	8.5	850	12.0000
3.2948	8.52	852	11.9952
3.3018	8.54	854	12.0006
3.2725	8.56	856	12.0175
3.2546	8.58	858	12.0317
3.3365	8.6	860	12.0482
3.3128	8.62	862	12.0633
3.3179	8.64	864	12.0742
3.344	8.66	866	12.0827
3.3167	8.68	868	12.0842
3.2757	8.7	870	12.0833
3.2976	8.72	872	12.0795
3.2958	8.74	874	12.0807
3.2459	8.76	876	12.0832
3.2143	8.78	878	12.0937
3.3088	8.8	880	12.1034
3.255	8.82	882	12.1180
3.2823	8.84	884	12.1286
3.3121	8.86	886	12.1276
3.3109	8.88	888	12.1257
3.2915	8.9	890	12.1249
3.2949	8.92	892	12.1236
3.3324	8.94	894	12.1166
3.2857	8.96	896	12.1021
3.2676	8.98	898	12.0892
3.3286	9.0	900	12.0885
3.1767	9.02	902	12.0871
3.3101	9.04	904	12.0867
3.2522	9.06	906	12.0893
3.281	9.08	908	12.0960
3.293	9.1	910	12.0985
3.3749	9.12	912	12.0968
3.2125	9.14	914	12.0924
3.3003	9.16	916	12.0876
3.2901	9.18	918	12.0882
3.3774	9.2	920	12.0825
3.1848	9.22	922	12.0757
3.3189	9.24	924	12.0753
3.283	9.26	926	12.0753
3.3167	9.28	928	12.0821
3.3859	9.3	930	12.0843
3.3641	9.32	932	12.0806
3.2083	9.34	934	12.0791
3.2662	9.36	936	12.0766
3.2898	9.38	938	12.0713
3.3507	9.4	940	12.0699
3.2931	9.42	942	12.0734
3.2993	9.44	944	12.0792
3.2843	9.46	946	12.0838
3.3334	9.48	948	12.0828
3.2112	9.5	950	12.0837
3.2545	9.52	952	12.0862
3.3359	9.54	954	12.0836
3.3186	9.56	956	12.0772
3.2492	9.58	958	12.0764
3.344	9.6	960	12.0752
3.3335	9.62	962	12.0730
3.2533	9.64	964	12.0726
3.297	9.66	966	12.0742
3.297	9.68	968	12.0774
3.2625	9.7	970	12.0804
3.2612	9.72	972	12.0831
3.3212	9.74	974	12.0868
3.2499	9.76	976	12.0853
3.2922	9.78	978	12.0841
3.3216	9.8	980	12.0811
3.3238	9.82	982	12.0799
3.3391	9.84	984	12.0746
3.3102	9.86	986	12.0738
3.3185	9.88	988	12.0742
3.1738	9.9	990	12.0771
3.2787	9.92	992	12.0794
3.2612	9.94	994	12.0830
3.2791	9.96	996	12.0853
3.3187	9.98	998	12.0869
3.3375	10.0	1000	12.0875

Framework versions

• PEFT 0.14.0
• Transformers 4.48.3
• Pytorch 2.6.0+cu124
• Datasets 3.3.2
• Tokenizers 0.21.0