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: 12.1938

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
14.5846	0.02	2	12.5510
14.468	0.04	4	12.5510
14.4251	0.06	6	12.5510
14.6378	0.08	8	12.5510
14.443	0.1	10	12.5510
14.5909	0.12	12	12.5510
14.5579	0.14	14	12.5510
14.4454	0.16	16	12.6131
10.7114	0.18	18	12.6513
9.1931	0.2	20	12.6244
10.4008	0.22	22	12.5203
6.5057	0.24	24	12.4152
5.5451	0.26	26	12.4541
5.0467	0.28	28	12.4998
4.64	0.3	30	12.4883
4.3282	0.32	32	12.5538
4.1035	0.34	34	12.7219
3.9833	0.36	36	12.9668
3.8832	0.38	38	13.3342
3.7675	0.4	40	13.3764
3.8377	0.42	42	13.5608
3.6798	0.44	44	13.6919
3.7186	0.46	46	13.6767
3.6791	0.48	48	13.8984
3.6634	0.5	50	14.0111
3.6488	0.52	52	14.1239
3.578	0.54	54	14.2522
3.5888	0.56	56	14.2451
3.5254	0.58	58	14.2527
3.7055	0.6	60	14.2049
3.6245	0.62	62	14.2823
3.6299	0.64	64	14.1549
3.5388	0.66	66	14.0448
3.5826	0.68	68	13.9470
3.5218	0.7	70	13.6879
3.4519	0.72	72	13.3748
3.4956	0.74	74	13.2794
3.5382	0.76	76	13.2250
3.5477	0.78	78	13.0469
3.4603	0.8	80	12.8025
3.4213	0.82	82	12.7112
3.4765	0.84	84	12.6294
3.3727	0.86	86	12.5883
3.3544	0.88	88	12.5217
3.5387	0.9	90	12.4911
3.4989	0.92	92	12.5620
3.28	0.94	94	12.7427
3.4194	0.96	96	12.8913
3.4668	0.98	98	12.9513
3.3742	1.0	100	13.1141
3.3316	1.02	102	13.2051
3.2817	1.04	104	13.1961
3.386	1.06	106	13.1769
3.3561	1.08	108	13.1745
3.3844	1.1	110	13.1554
3.3807	1.12	112	13.0076
3.3244	1.1400	114	12.7831
3.2908	1.16	116	12.5908
3.3604	1.18	118	12.4804
3.3556	1.2	120	12.3017
3.4155	1.22	122	12.1508
3.1569	1.24	124	12.0773
3.3675	1.26	126	12.0507
3.2654	1.28	128	12.0523
3.289	1.3	130	12.1813
3.381	1.32	132	12.3513
3.3602	1.34	134	12.4629
3.3875	1.3600	136	12.4320
3.3635	1.38	138	12.3350
3.3044	1.4	140	12.3510
3.2265	1.42	142	12.3965
3.4321	1.44	144	12.4767
3.207	1.46	146	12.5359
3.3842	1.48	148	12.5051
3.3296	1.5	150	12.4519
3.4277	1.52	152	12.3719
3.3442	1.54	154	12.2787
3.378	1.56	156	12.1766
3.3881	1.58	158	12.1205
3.3717	1.6	160	12.1152
3.3728	1.62	162	12.1410
3.3085	1.6400	164	12.1542
3.2928	1.6600	166	12.1586
3.3765	1.6800	168	12.1536
3.3737	1.7	170	12.2204
3.3219	1.72	172	12.3614
3.2886	1.74	174	12.4496
3.3835	1.76	176	12.4409
3.3472	1.78	178	12.3931
3.2938	1.8	180	12.3618
3.3198	1.8200	182	12.3083
3.312	1.8400	184	12.2877
3.3339	1.8600	186	12.2854
3.2852	1.88	188	12.3501
3.2673	1.9	190	12.4067
3.302	1.92	192	12.4240
3.3393	1.94	194	12.4016
3.37	1.96	196	12.4183
3.3096	1.98	198	12.4348
3.2883	2.0	200	12.2726
3.3541	2.02	202	12.1794
3.2213	2.04	204	12.1240
3.2405	2.06	206	12.0807
3.245	2.08	208	12.0731
3.3157	2.1	210	12.1227
3.3316	2.12	212	12.1254
3.3174	2.14	214	12.1388
3.367	2.16	216	12.1169
3.2852	2.18	218	12.0866
3.3265	2.2	220	12.0615
3.3527	2.22	222	12.0531
3.3487	2.24	224	12.0528
3.313	2.26	226	12.0721
3.2742	2.2800	228	12.0398
3.3542	2.3	230	12.0108
3.3401	2.32	232	12.0166
3.3099	2.34	234	12.0229
3.3104	2.36	236	12.0112
3.2891	2.38	238	12.0196
3.2921	2.4	240	12.0865
3.2757	2.42	242	12.1653
3.33	2.44	244	12.2339
3.3114	2.46	246	12.2706
3.3022	2.48	248	12.2732
3.2404	2.5	250	12.2629
3.2765	2.52	252	12.2720
3.2463	2.54	254	12.2674
3.3108	2.56	256	12.2363
3.3136	2.58	258	12.1803
3.2327	2.6	260	12.1294
3.265	2.62	262	12.0993
3.2821	2.64	264	12.1062
3.2388	2.66	266	12.1057
3.3352	2.68	268	12.0979
3.3368	2.7	270	12.0667
3.2806	2.7200	272	12.0045
3.3687	2.74	274	11.9141
3.3256	2.76	276	11.8386
3.3315	2.7800	278	11.8078
3.3879	2.8	280	11.7429
3.2741	2.82	282	11.6633
3.2734	2.84	284	11.6124
3.2259	2.86	286	11.6239
3.2545	2.88	288	11.6557
3.2805	2.9	290	11.7027
3.2612	2.92	292	11.7813
3.2988	2.94	294	11.8330
3.3182	2.96	296	11.9141
3.2649	2.98	298	11.9544
3.2909	3.0	300	11.9640
3.2449	3.02	302	11.9469
3.3403	3.04	304	11.9383
3.2276	3.06	306	11.9341
3.2733	3.08	308	11.9214
3.288	3.1	310	11.8931
3.3205	3.12	312	11.8712
3.278	3.14	314	11.8402
3.2325	3.16	316	11.8021
3.2571	3.18	318	11.7737
3.2572	3.2	320	11.8027
3.2931	3.22	322	11.8887
3.2625	3.24	324	11.9586
3.3046	3.26	326	12.0337
3.2918	3.2800	328	12.0550
3.3463	3.3	330	12.0700
3.3634	3.32	332	12.0629
3.2913	3.34	334	12.0422
3.3339	3.36	336	12.0205
3.242	3.38	338	11.9989
3.2528	3.4	340	11.9722
3.2605	3.42	342	11.9340
3.3276	3.44	344	11.9130
3.2338	3.46	346	11.8739
3.3826	3.48	348	11.8478
3.2436	3.5	350	11.8421
3.2724	3.52	352	11.9347
3.3278	3.54	354	12.0060
3.2615	3.56	356	12.0694
3.2534	3.58	358	12.0853
3.2594	3.6	360	12.0825
3.2852	3.62	362	12.0942
3.188	3.64	364	12.0672
3.3372	3.66	366	12.0729
3.3333	3.68	368	12.1122
3.1916	3.7	370	12.1468
3.2173	3.7200	372	12.1691
3.2688	3.74	374	12.1923
3.2398	3.76	376	12.2055
3.3139	3.7800	378	12.2089
3.2849	3.8	380	12.2071
3.3402	3.82	382	12.1834
3.2343	3.84	384	12.1798
3.3217	3.86	386	12.1926
3.2866	3.88	388	12.1950
3.3121	3.9	390	12.2041
3.164	3.92	392	12.2241
3.3101	3.94	394	12.2740
3.303	3.96	396	12.3077
3.2521	3.98	398	12.3382
3.2108	4.0	400	12.3363
3.2939	4.02	402	12.3124
3.2416	4.04	404	12.3055
3.2816	4.06	406	12.2913
3.3309	4.08	408	12.2864
3.2337	4.1	410	12.2931
3.2912	4.12	412	12.2908
3.2301	4.14	414	12.2751
3.2979	4.16	416	12.2490
3.2676	4.18	418	12.2612
3.2009	4.2	420	12.2703
3.2956	4.22	422	12.2880
3.1826	4.24	424	12.3034
3.3055	4.26	426	12.3167
3.2454	4.28	428	12.3217
3.2812	4.3	430	12.3254
3.2864	4.32	432	12.3223
3.3054	4.34	434	12.3280
3.3591	4.36	436	12.3250
3.2739	4.38	438	12.3287
3.2294	4.4	440	12.3243
3.2179	4.42	442	12.3041
3.2259	4.44	444	12.2886
3.3263	4.46	446	12.2663
3.2458	4.48	448	12.2746
3.2093	4.5	450	12.2941
3.2572	4.52	452	12.3111
3.2295	4.54	454	12.3422
3.3031	4.5600	456	12.3921
3.2631	4.58	458	12.4233
3.258	4.6	460	12.4227
3.2539	4.62	462	12.3893
3.2268	4.64	464	12.3588
3.2862	4.66	466	12.3315
3.3209	4.68	468	12.3050
3.2463	4.7	470	12.2888
3.2904	4.72	472	12.2546
3.2734	4.74	474	12.2306
3.207	4.76	476	12.1888
3.2524	4.78	478	12.1574
3.2837	4.8	480	12.1193
3.3393	4.82	482	12.0942
3.2915	4.84	484	12.0849
3.3004	4.86	486	12.0907
3.2988	4.88	488	12.1043
3.2231	4.9	490	12.1281
3.3471	4.92	492	12.1207
3.3422	4.9400	494	12.1507
3.3066	4.96	496	12.1768
3.306	4.98	498	12.2020
3.3441	5.0	500	12.2120
3.2595	5.02	502	12.2063
3.3335	5.04	504	12.2100
3.3278	5.06	506	12.2190
3.309	5.08	508	12.2156
3.2973	5.1	510	12.2266
3.3634	5.12	512	12.2382
3.2832	5.14	514	12.2679
3.2977	5.16	516	12.2996
3.2821	5.18	518	12.3265
3.2888	5.2	520	12.3268
3.2997	5.22	522	12.2878
3.3083	5.24	524	12.2549
3.3359	5.26	526	12.2223
3.2564	5.28	528	12.1863
3.2886	5.3	530	12.1664
3.3135	5.32	532	12.1607
3.3531	5.34	534	12.1516
3.2994	5.36	536	12.1253
3.2922	5.38	538	12.1128
3.2843	5.4	540	12.0960
3.2173	5.42	542	12.0910
3.2495	5.44	544	12.0783
3.2832	5.46	546	12.0840
3.294	5.48	548	12.0885
3.2995	5.5	550	12.0980
3.283	5.52	552	12.1269
3.2931	5.54	554	12.1491
3.2804	5.5600	556	12.1882
3.2815	5.58	558	12.2243
3.2461	5.6	560	12.2630
3.3092	5.62	562	12.3149
3.3292	5.64	564	12.3672
3.3493	5.66	566	12.4010
3.2776	5.68	568	12.4319
3.2621	5.7	570	12.4358
3.253	5.72	572	12.4312
3.1947	5.74	574	12.4244
3.2793	5.76	576	12.4122
3.27	5.78	578	12.3920
3.2818	5.8	580	12.3820
3.315	5.82	582	12.3736
3.2268	5.84	584	12.3683
3.2419	5.86	586	12.3634
3.3287	5.88	588	12.3742
3.1879	5.9	590	12.3778
3.3136	5.92	592	12.3781
3.2456	5.9400	594	12.3807
3.2783	5.96	596	12.3800
3.2946	5.98	598	12.3855
3.2302	6.0	600	12.3980
3.3143	6.02	602	12.4018
3.2578	6.04	604	12.4033
3.3136	6.06	606	12.4104
3.3571	6.08	608	12.4330
3.2996	6.1	610	12.4541
3.2823	6.12	612	12.4677
3.3274	6.14	614	12.4725
3.2578	6.16	616	12.4670
3.2045	6.18	618	12.4688
3.3116	6.2	620	12.4687
3.2589	6.22	622	12.4691
3.2897	6.24	624	12.4666
3.2094	6.26	626	12.4475
3.251	6.28	628	12.4250
3.3356	6.3	630	12.4149
3.3197	6.32	632	12.4100
3.3368	6.34	634	12.4025
3.1573	6.36	636	12.3982
3.33	6.38	638	12.4016
3.1688	6.4	640	12.3888
3.2561	6.42	642	12.3757
3.2013	6.44	644	12.3825
3.2559	6.46	646	12.3892
3.2722	6.48	648	12.3750
3.3148	6.5	650	12.3570
3.1945	6.52	652	12.3406
3.3197	6.54	654	12.3269
3.2995	6.5600	656	12.3230
3.238	6.58	658	12.3218
3.1384	6.6	660	12.3082
3.3538	6.62	662	12.2990
3.2958	6.64	664	12.2879
3.2693	6.66	666	12.2621
3.2906	6.68	668	12.2557
3.2496	6.7	670	12.2461
3.309	6.72	672	12.2395
3.2522	6.74	674	12.2229
3.2767	6.76	676	12.2101
3.2906	6.78	678	12.2166
3.3073	6.8	680	12.2254
3.2648	6.82	682	12.2396
3.1792	6.84	684	12.2524
3.2843	6.86	686	12.2439
3.2857	6.88	688	12.2372
3.2611	6.9	690	12.2292
3.2687	6.92	692	12.2254
3.2307	6.9400	694	12.2373
3.2564	6.96	696	12.2563
3.2699	6.98	698	12.2690
3.3105	7.0	700	12.2721
3.2747	7.02	702	12.2764
3.3334	7.04	704	12.2706
3.2797	7.06	706	12.2714
3.2492	7.08	708	12.2812
3.2785	7.1	710	12.3033
3.3202	7.12	712	12.3118
3.2952	7.14	714	12.3250
3.2343	7.16	716	12.3151
3.3491	7.18	718	12.3063
3.3019	7.2	720	12.2948
3.1397	7.22	722	12.2807
3.2334	7.24	724	12.2501
3.2846	7.26	726	12.2227
3.2859	7.28	728	12.1908
3.3106	7.3	730	12.1541
3.3557	7.32	732	12.1292
3.2437	7.34	734	12.1164
3.2449	7.36	736	12.1090
3.372	7.38	738	12.0975
3.2262	7.4	740	12.0989
3.3145	7.42	742	12.0954
3.292	7.44	744	12.0880
3.3256	7.46	746	12.0827
3.2452	7.48	748	12.0765
3.3251	7.5	750	12.0671
3.2338	7.52	752	12.0546
3.2837	7.54	754	12.0496
3.296	7.5600	756	12.0492
3.2283	7.58	758	12.0465
3.2627	7.6	760	12.0453
3.2426	7.62	762	12.0424
3.2416	7.64	764	12.0483
3.3272	7.66	766	12.0545
3.3199	7.68	768	12.0665
3.2178	7.7	770	12.0849
3.3196	7.72	772	12.0954
3.3283	7.74	774	12.1083
3.3002	7.76	776	12.1082
3.326	7.78	778	12.1118
3.2802	7.8	780	12.1240
3.2694	7.82	782	12.1435
3.1772	7.84	784	12.1485
3.3252	7.86	786	12.1444
3.2671	7.88	788	12.1529
3.2885	7.9	790	12.1722
3.2617	7.92	792	12.2015
3.1658	7.9400	794	12.2317
3.3317	7.96	796	12.2634
3.3258	7.98	798	12.2906
3.2754	8.0	800	12.3193
3.3093	8.02	802	12.3451
3.2241	8.04	804	12.3542
3.3689	8.06	806	12.3568
3.3201	8.08	808	12.3560
3.3338	8.1	810	12.3539
3.2994	8.12	812	12.3529
3.3171	8.14	814	12.3510
3.2864	8.16	816	12.3432
3.3305	8.18	818	12.3428
3.2656	8.2	820	12.3436
3.3031	8.22	822	12.3485
3.2901	8.24	824	12.3442
3.2114	8.26	826	12.3342
3.304	8.28	828	12.3205
3.2342	8.3	830	12.3103
3.2524	8.32	832	12.2966
3.3644	8.34	834	12.2846
3.2956	8.36	836	12.2684
3.2389	8.38	838	12.2591
3.3065	8.4	840	12.2494
3.3139	8.42	842	12.2471
3.2532	8.44	844	12.2469
3.2664	8.46	846	12.2613
3.3063	8.48	848	12.2673
3.2888	8.5	850	12.2764
3.2435	8.52	852	12.2772
3.3448	8.54	854	12.2723
3.2086	8.56	856	12.2745
3.3009	8.58	858	12.2680
3.2358	8.6	860	12.2636
3.3036	8.62	862	12.2569
3.2769	8.64	864	12.2506
3.2585	8.66	866	12.2369
3.2936	8.68	868	12.2234
3.2736	8.7	870	12.2117
3.238	8.72	872	12.2156
3.2791	8.74	874	12.2186
3.2505	8.76	876	12.2196
3.333	8.78	878	12.2228
3.2544	8.8	880	12.2307
3.2707	8.82	882	12.2347
3.1691	8.84	884	12.2395
3.1813	8.86	886	12.2450
3.371	8.88	888	12.2514
3.3087	8.9	890	12.2589
3.2601	8.92	892	12.2621
3.2469	8.94	894	12.2546
3.3018	8.96	896	12.2525
3.2543	8.98	898	12.2514
3.2697	9.0	900	12.2546
3.3076	9.02	902	12.2605
3.2983	9.04	904	12.2656
3.1828	9.06	906	12.2733
3.2779	9.08	908	12.2817
3.343	9.1	910	12.2836
3.2114	9.12	912	12.2846
3.3172	9.14	914	12.2849
3.2922	9.16	916	12.2853
3.3081	9.18	918	12.2853
3.2763	9.2	920	12.2864
3.3132	9.22	922	12.2842
3.2811	9.24	924	12.2847
3.2715	9.26	926	12.2866
3.2769	9.28	928	12.2916
3.2589	9.3	930	12.2924
3.259	9.32	932	12.2896
3.2891	9.34	934	12.2840
3.3134	9.36	936	12.2845
3.2664	9.38	938	12.2812
3.201	9.4	940	12.2740
3.3038	9.42	942	12.2699
3.3048	9.44	944	12.2666
3.3398	9.46	946	12.2591
3.2914	9.48	948	12.2456
3.2824	9.5	950	12.2315
3.2709	9.52	952	12.2176
3.2623	9.54	954	12.2079
3.242	9.56	956	12.2015
3.2452	9.58	958	12.1950
3.272	9.6	960	12.1882
3.3035	9.62	962	12.1847
3.2149	9.64	964	12.1788
3.1639	9.66	966	12.1767
3.3223	9.68	968	12.1733
3.2028	9.7	970	12.1720
3.315	9.72	972	12.1691
3.3037	9.74	974	12.1712
3.2582	9.76	976	12.1765
3.2573	9.78	978	12.1833
3.1872	9.8	980	12.1850
3.2535	9.82	982	12.1891
3.2517	9.84	984	12.1912
3.2707	9.86	986	12.1951
3.2839	9.88	988	12.1965
3.2803	9.9	990	12.1972
3.3007	9.92	992	12.1966
3.2306	9.94	994	12.1969
3.23	9.96	996	12.1948
3.2706	9.98	998	12.1954
3.2526	10.0	1000	12.1938

Framework versions

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