finetuned-baseline-phase-0.1

This model is a fine-tuned version of ishwarbb23/finetuned-baseline-phase-0.0 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 3.0837

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: 0.0001
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 16
• total_train_batch_size: 64
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss
3.9044	0.14	5	3.5150
3.6543	0.29	10	3.4614
3.6345	0.43	15	3.4248
3.6121	0.57	20	3.3929
3.5874	0.72	25	3.3687
3.5709	0.86	30	3.3519
3.5185	1.01	35	3.3363
3.484	1.15	40	3.3250
3.4515	1.29	45	3.3153
3.4944	1.44	50	3.3051
3.4387	1.58	55	3.2956
3.4965	1.72	60	3.2867
3.4745	1.87	65	3.2791
3.4252	2.01	70	3.2736
3.499	2.15	75	3.2668
3.4885	2.3	80	3.2614
3.3934	2.44	85	3.2578
3.4112	2.59	90	3.2539
3.3843	2.73	95	3.2487
3.3753	2.87	100	3.2421
3.3824	3.02	105	3.2344
3.3801	3.16	110	3.2293
3.3943	3.3	115	3.2258
3.3946	3.45	120	3.2230
3.3178	3.59	125	3.2212
3.3325	3.73	130	3.2184
3.3925	3.88	135	3.2140
3.3453	4.02	140	3.2086
3.346	4.17	145	3.2048
3.3575	4.31	150	3.2019
3.4051	4.45	155	3.1983
3.3307	4.6	160	3.1959
3.3328	4.74	165	3.1932
3.2993	4.88	170	3.1910
3.3636	5.03	175	3.1885
3.3118	5.17	180	3.1874
3.3351	5.31	185	3.1844
3.2868	5.46	190	3.1798
3.3262	5.6	195	3.1757
3.3524	5.75	200	3.1728
3.3378	5.89	205	3.1706
3.2928	6.03	210	3.1694
3.2715	6.18	215	3.1681
3.2448	6.32	220	3.1650
3.3084	6.46	225	3.1620
3.3209	6.61	230	3.1597
3.2942	6.75	235	3.1573
3.3388	6.89	240	3.1555
3.273	7.04	245	3.1544
3.3283	7.18	250	3.1520
3.1891	7.32	255	3.1514
3.2671	7.47	260	3.1504
3.2802	7.61	265	3.1486
3.316	7.76	270	3.1462
3.2761	7.9	275	3.1445
3.2772	8.04	280	3.1436
3.2263	8.19	285	3.1429
3.2242	8.33	290	3.1389
3.256	8.47	295	3.1376
3.3119	8.62	300	3.1370
3.2445	8.76	305	3.1336
3.2314	8.9	310	3.1311
3.2631	9.05	315	3.1298
3.2825	9.19	320	3.1313
3.1922	9.34	325	3.1324
3.2144	9.48	330	3.1289
3.2273	9.62	335	3.1246
3.1995	9.77	340	3.1223
3.2356	9.91	345	3.1216
3.2254	10.05	350	3.1224
3.2555	10.2	355	3.1230
3.1581	10.34	360	3.1221
3.2334	10.48	365	3.1177
3.2064	10.63	370	3.1162
3.277	10.77	375	3.1153
3.2614	10.92	380	3.1115
3.2386	11.06	385	3.1105
3.2357	11.2	390	3.1100
3.2005	11.35	395	3.1099
3.2146	11.49	400	3.1104
3.19	11.63	405	3.1110
3.1835	11.78	410	3.1109
3.2247	11.92	415	3.1100
3.2138	12.06	420	3.1082
3.2105	12.21	425	3.1079
3.2074	12.35	430	3.1077
3.1758	12.5	435	3.1057
3.2357	12.64	440	3.1034
3.1556	12.78	445	3.1018
3.2014	12.93	450	3.1007
3.1641	13.07	455	3.1000
3.2082	13.21	460	3.1000
3.1841	13.36	465	3.1003
3.2168	13.5	470	3.1003
3.202	13.64	475	3.0995
3.253	13.79	480	3.0975
3.1916	13.93	485	3.0966
3.2383	14.08	490	3.0949
3.2758	14.22	495	3.0938
3.1513	14.36	500	3.0934
3.1907	14.51	505	3.0929
3.1482	14.65	510	3.0926
3.1781	14.79	515	3.0927
3.167	14.94	520	3.0917
3.209	15.08	525	3.0909
3.1433	15.22	530	3.0900
3.1615	15.37	535	3.0896
3.1727	15.51	540	3.0895
3.1608	15.66	545	3.0897
3.2079	15.8	550	3.0895
3.1996	15.94	555	3.0888
3.2229	16.09	560	3.0874
3.2007	16.23	565	3.0864
3.1452	16.37	570	3.0860
3.1491	16.52	575	3.0858
3.1616	16.66	580	3.0862
3.1639	16.8	585	3.0862
3.1946	16.95	590	3.0856
3.1553	17.09	595	3.0854
3.1203	17.24	600	3.0851
3.2122	17.38	605	3.0849
3.2104	17.52	610	3.0843
3.2037	17.67	615	3.0844
3.1389	17.81	620	3.0843
3.1264	17.95	625	3.0845
3.1723	18.1	630	3.0845
3.1485	18.24	635	3.0848
3.1838	18.38	640	3.0850
3.2078	18.53	645	3.0848
3.1725	18.67	650	3.0845
3.1422	18.82	655	3.0843
3.128	18.96	660	3.0841
3.2523	19.1	665	3.0839
3.2098	19.25	670	3.0838
3.1384	19.39	675	3.0837
3.1944	19.53	680	3.0837

Framework versions

• Transformers 4.34.1
• Pytorch 2.1.0+cu118
• Datasets 2.14.6
• Tokenizers 0.14.1