tmp

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: 1.3192

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: 1.41e-05
• train_batch_size: 2
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 3.0

Training results

Training Loss	Epoch	Step	Validation Loss
1.5915	0.0134	50	1.2903
1.3717	0.0268	100	1.2596
1.0418	0.0401	150	1.2804
1.2548	0.0535	200	1.2606
1.3994	0.0669	250	1.2454
1.1584	0.0803	300	1.2351
1.0075	0.0937	350	1.2278
1.3926	0.1070	400	1.2254
1.2131	0.1204	450	1.2212
1.3407	0.1338	500	1.2100
1.042	0.1472	550	1.2228
1.398	0.1606	600	1.2049
0.9886	0.1739	650	1.2033
1.3415	0.1873	700	1.1979
1.414	0.2007	750	1.1973
1.0634	0.2141	800	1.1925
0.9591	0.2275	850	1.1846
1.4814	0.2408	900	1.1816
1.4658	0.2542	950	1.1804
1.3086	0.2676	1000	1.1789
0.9067	0.2810	1050	1.1678
1.0266	0.2944	1100	1.1679
1.6225	0.3077	1150	1.1694
1.206	0.3211	1200	1.1668
1.2348	0.3345	1250	1.1628
1.3967	0.3479	1300	1.1572
1.3526	0.3613	1350	1.1558
1.0515	0.3746	1400	1.1578
1.2215	0.3880	1450	1.1574
0.8743	0.4014	1500	1.1516
1.5303	0.4148	1550	1.1461
1.1828	0.4282	1600	1.1523
0.9266	0.4415	1650	1.1443
1.3904	0.4549	1700	1.1358
1.138	0.4683	1750	1.1440
1.3723	0.4817	1800	1.1389
1.2073	0.4950	1850	1.1416
1.1665	0.5084	1900	1.1335
1.2742	0.5218	1950	1.1289
1.1677	0.5352	2000	1.1286
1.0681	0.5486	2050	1.1289
0.8086	0.5619	2100	1.1200
0.79	0.5753	2150	1.1245
0.9748	0.5887	2200	1.1275
1.2156	0.6021	2250	1.1204
0.8723	0.6155	2300	1.1151
0.9383	0.6288	2350	1.1160
1.0047	0.6422	2400	1.1169
0.9831	0.6556	2450	1.1192
0.7517	0.6690	2500	1.1098
1.3771	0.6824	2550	1.1128
1.0822	0.6957	2600	1.1158
1.0965	0.7091	2650	1.1073
1.0562	0.7225	2700	1.1108
1.0419	0.7359	2750	1.1184
0.8352	0.7493	2800	1.1060
1.0286	0.7626	2850	1.1043
0.9745	0.7760	2900	1.1019
0.9868	0.7894	2950	1.0965
1.0109	0.8028	3000	1.0978
1.437	0.8162	3050	1.0969
0.8	0.8295	3100	1.0882
1.1526	0.8429	3150	1.0912
1.052	0.8563	3200	1.0922
1.1689	0.8697	3250	1.0871
1.3413	0.8831	3300	1.0851
1.1188	0.8964	3350	1.0833
1.625	0.9098	3400	1.0867
1.3762	0.9232	3450	1.0816
1.0802	0.9366	3500	1.0825
0.9063	0.9500	3550	1.0767
1.0199	0.9633	3600	1.0783
1.5628	0.9767	3650	1.0750
1.0558	0.9901	3700	1.0774
0.7092	1.0035	3750	1.0841
0.7194	1.0169	3800	1.1159
0.8033	1.0302	3850	1.1189
0.5744	1.0436	3900	1.1321
0.6601	1.0570	3950	1.1199
0.8371	1.0704	4000	1.1241
0.8107	1.0838	4050	1.1225
0.6045	1.0971	4100	1.1291
0.6476	1.1105	4150	1.1280
0.6125	1.1239	4200	1.1228
0.5005	1.1373	4250	1.1239
0.7029	1.1507	4300	1.1302
0.7131	1.1640	4350	1.1217
0.7028	1.1774	4400	1.1266
0.7679	1.1908	4450	1.1164
0.7504	1.2042	4500	1.1235
0.7788	1.2176	4550	1.1253
0.6972	1.2309	4600	1.1166
1.0489	1.2443	4650	1.1204
0.4751	1.2577	4700	1.1185
0.5464	1.2711	4750	1.1254
0.7255	1.2845	4800	1.1202
0.8914	1.2978	4850	1.1193
0.5107	1.3112	4900	1.1252
0.8114	1.3246	4950	1.1243
0.6298	1.3380	5000	1.1261
0.9236	1.3514	5050	1.1245
0.7085	1.3647	5100	1.1213
0.7505	1.3781	5150	1.1127
0.7309	1.3915	5200	1.1178
0.5225	1.4049	5250	1.1216
0.8705	1.4182	5300	1.1134
0.5532	1.4316	5350	1.1193
0.4079	1.4450	5400	1.1142
0.5628	1.4584	5450	1.1138
0.716	1.4718	5500	1.1126
0.382	1.4851	5550	1.1150
0.6474	1.4985	5600	1.1143
0.6119	1.5119	5650	1.1112
0.4815	1.5253	5700	1.1047
0.8477	1.5387	5750	1.1158
0.8981	1.5520	5800	1.1108
0.639	1.5654	5850	1.1141
0.727	1.5788	5900	1.1137
0.8175	1.5922	5950	1.1116
0.7431	1.6056	6000	1.1152
0.6324	1.6189	6050	1.1145
1.0941	1.6323	6100	1.1142
0.6437	1.6457	6150	1.1082
0.5857	1.6591	6200	1.1103
0.4056	1.6725	6250	1.1137
0.6483	1.6858	6300	1.1069
0.6741	1.6992	6350	1.1027
0.7587	1.7126	6400	1.1087
0.7206	1.7260	6450	1.1156
0.451	1.7394	6500	1.1074
0.8237	1.7527	6550	1.1055
0.6333	1.7661	6600	1.1078
0.6317	1.7795	6650	1.1049
0.6688	1.7929	6700	1.1011
0.6598	1.8063	6750	1.1030
0.642	1.8196	6800	1.1059
0.587	1.8330	6850	1.1002
0.7726	1.8464	6900	1.0966
0.8227	1.8598	6950	1.1014
0.9093	1.8732	7000	1.1011
0.6117	1.8865	7050	1.0999
0.8338	1.8999	7100	1.0937
0.7215	1.9133	7150	1.0935
0.6242	1.9267	7200	1.0909
0.571	1.9401	7250	1.0990
0.7773	1.9534	7300	1.0955
0.7082	1.9668	7350	1.0955
0.7165	1.9802	7400	1.0982
0.5604	1.9936	7450	1.0985
0.3232	2.0070	7500	1.1841
0.3628	2.0203	7550	1.2569
0.4465	2.0337	7600	1.2687
0.3233	2.0471	7650	1.2720
0.281	2.0605	7700	1.2859
0.2199	2.0739	7750	1.2808
0.4787	2.0872	7800	1.2839
0.4288	2.1006	7850	1.2918
0.2966	2.1140	7900	1.3063
0.4248	2.1274	7950	1.3061
0.2717	2.1408	8000	1.2926
0.3561	2.1541	8050	1.3054
0.3736	2.1675	8100	1.2947
0.2936	2.1809	8150	1.3021
0.3316	2.1943	8200	1.2981
0.2931	2.2077	8250	1.3007
0.4591	2.2210	8300	1.2972
0.3023	2.2344	8350	1.3127
0.3407	2.2478	8400	1.3110
0.2361	2.2612	8450	1.3071
0.3509	2.2746	8500	1.3021
0.3868	2.2879	8550	1.3168
0.3218	2.3013	8600	1.3156
0.2913	2.3147	8650	1.3034
0.437	2.3281	8700	1.3214
0.4314	2.3415	8750	1.3136
0.3151	2.3548	8800	1.3085
0.3236	2.3682	8850	1.3100
0.3416	2.3816	8900	1.3050
0.3333	2.3950	8950	1.3151
0.2742	2.4083	9000	1.3153
0.3143	2.4217	9050	1.3243
0.4152	2.4351	9100	1.3164
0.219	2.4485	9150	1.3233
0.4057	2.4619	9200	1.3073
0.3571	2.4752	9250	1.3084
0.3163	2.4886	9300	1.3184
0.3185	2.5020	9350	1.3092
0.4474	2.5154	9400	1.3185
0.1927	2.5288	9450	1.3158
0.2362	2.5421	9500	1.3093
0.3651	2.5555	9550	1.3116
0.2531	2.5689	9600	1.3121
0.2219	2.5823	9650	1.3192
0.2546	2.5957	9700	1.3170
0.2841	2.6090	9750	1.3180
0.3039	2.6224	9800	1.3188
0.3866	2.6358	9850	1.3253
0.378	2.6492	9900	1.3143
0.2671	2.6626	9950	1.3143
0.2715	2.6759	10000	1.3220
0.2104	2.6893	10050	1.3275
0.2663	2.7027	10100	1.3186
0.3433	2.7161	10150	1.3201
0.3493	2.7295	10200	1.3169
0.3615	2.7428	10250	1.3184
0.2843	2.7562	10300	1.3196
0.263	2.7696	10350	1.3158
0.2971	2.7830	10400	1.3136
0.2198	2.7964	10450	1.3231
0.1814	2.8097	10500	1.3187
0.303	2.8231	10550	1.3175
0.4044	2.8365	10600	1.3171
0.2374	2.8499	10650	1.3212
0.2155	2.8633	10700	1.3229
0.2656	2.8766	10750	1.3251
0.2552	2.8900	10800	1.3184
0.2838	2.9034	10850	1.3198
0.2824	2.9168	10900	1.3192
0.2748	2.9302	10950	1.3172
0.2951	2.9435	11000	1.3193
0.3339	2.9569	11050	1.3196
0.3167	2.9703	11100	1.3195
0.2751	2.9837	11150	1.3192
0.3687	2.9971	11200	1.3192

Framework versions

• Transformers 4.45.2
• Pytorch 2.4.1+cu121
• Datasets 3.0.1
• Tokenizers 0.20.1