learning_rate: 0.0002
train_batch_size: 16
eval_batch_size: 16
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 64
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: cosine
lr_scheduler_warmup_steps: 500
num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss
2.7806	0.0139	500	2.6662
2.6846	0.0278	1000	2.6040
2.6394	0.0417	1500	2.5778
2.6248	0.0556	2000	2.5622
2.6107	0.0695	2500	2.5486
2.6022	0.0834	3000	2.5420
2.5840	0.0973	3500	2.5322
2.5784	0.1113	4000	2.5274
2.5746	0.1252	4500	2.5202
2.5635	0.1391	5000	2.5179
2.5555	0.1530	5500	2.5121
2.5521	0.1669	6000	2.5087
2.5404	0.1808	6500	2.5073
2.5461	0.1947	7000	2.5019
2.5329	0.2086	7500	2.4984
2.5344	0.2225	8000	2.4977
2.5258	0.2364	8500	2.4944
2.5082	0.2503	9000	2.4943
2.5238	0.2642	9500	2.4875
2.5205	0.2781	10000	2.4861
2.5008	0.2920	10500	2.4808
2.5110	0.3059	11000	2.4803
2.4947	0.3199	11500	2.4819
2.4990	0.3338	12000	2.4760
2.4874	0.3477	12500	2.4719
2.4877	0.3616	13000	2.4731
2.4816	0.3755	13500	2.4710
2.4870	0.3894	14000	2.4659
2.4717	0.4033	14500	2.4668
2.4777	0.4172	15000	2.4611
2.4699	0.4311	15500	2.4595
2.4702	0.4450	16000	2.4566
2.4666	0.4589	16500	2.4607
2.4608	0.4728	17000	2.4514
2.4503	0.4867	17500	2.4522
2.4545	0.5006	18000	2.4501
2.4376	0.5145	18500	2.4499
2.4377	0.5285	19000	2.4472
2.4508	0.5424	19500	2.4442
2.4320	0.5563	20000	2.4428
2.4452	0.5702	20500	2.4350
2.4217	0.5841	21000	2.4382
2.4202	0.5980	21500	2.4315
2.4235	0.6119	22000	2.4332
2.4107	0.6258	22500	2.4316
2.4116	0.6397	23000	2.4305
2.4101	0.6536	23500	2.4286
2.3993	0.6675	24000	2.4237
2.4113	0.6814	24500	2.4265
2.4006	0.6953	25000	2.4251
2.4074	0.7092	25500	2.4195
2.3896	0.7232	26000	2.4166
2.4019	0.7371	26500	2.4147
2.3899	0.7510	27000	2.4129
2.3919	0.7649	27500	2.4133
2.3677	0.7788	28000	2.4100
2.3761	0.7927	28500	2.4079
2.3716	0.8066	29000	2.4108
2.3629	0.8205	29500	2.4064
2.3567	0.8344	30000	2.4046
2.3699	0.8483	30500	2.4060
2.3300	0.8622	31000	2.3999
2.3329	0.8761	31500	2.4010
2.3310	0.8900	32000	2.3970
2.3616	0.9039	32500	2.3968
2.3479	0.9178	33000	2.4002
2.3412	0.9318	33500	2.3933
2.3462	0.9457	34000	2.3896
2.3416	0.9596	34500	2.3965
2.3353	0.9735	35000	2.3873
2.3392	0.9874	35500	2.3871
2.3287	1.0013	36000	2.3883
2.3317	1.0152	36500	2.3842
2.3240	1.0291	37000	2.3842
2.3260	1.0430	37500	2.3848
2.3172	1.0569	38000	2.3833
2.3028	1.0708	38500	2.3851
2.3086	1.0847	39000	2.3788
2.3100	1.0986	39500	2.3760
2.3110	1.1125	40000	2.3755
2.2885	1.1264	40500	2.3761
2.2944	1.1403	41000	2.3744
2.3108	1.1543	41500	2.3732
2.3028	1.1682	42000	2.3757
2.2976	1.1821	42500	2.3748
2.3035	1.1960	43000	2.3712
2.2910	1.2099	43500	2.3686
2.2714	1.2238	44000	2.3705
2.3097	1.2377	44500	2.3627
2.2926	1.2516	45000	2.3645
2.2625	1.2655	45500	2.3628
2.2669	1.2794	46000	2.3625
2.2770	1.2933	46500	2.3656
2.2755	1.3072	47000	2.3564
2.2791	1.3211	47500	2.3551
2.2767	1.3350	48000	2.3560
2.2821	1.3489	48500	2.3529
2.2759	1.3629	49000	2.3555
2.2660	1.3768	49500	2.3539
2.2585	1.3907	50000	2.3551
2.2612	1.4046	50500	2.3551
2.2619	1.4185	51000	2.3505
2.2557	1.4324	51500	2.3635
2.2462	1.4463	52000	2.3473
2.2477	1.4602	52500	2.3456
2.2712	1.4741	53000	2.3449
2.2853	1.4880	53500	2.3457
2.2516	1.5019	54000	2.3440
2.2444	1.5158	54500	2.3444
2.2217	1.5297	55000	2.3411
2.2484	1.5436	55500	2.3406
2.2488	1.5575	56000	2.3394
2.2325	1.5715	56500	2.3397
2.2646	1.5854	57000	2.3385
2.2369	1.5993	57500	2.3397
2.2083	1.6132	58000	2.3384
2.2516	1.6271	58500	2.3344
2.2263	1.6410	59000	2.3357
2.2355	1.6549	59500	2.3347
2.2191	1.6688	60000	2.3347
2.2205	1.6827	60500	2.3327
2.2175	1.6966	61000	2.3308
2.2283	1.7105	61500	2.3310
2.2351	1.7244	62000	2.3292
2.2308	1.7383	62500	2.3276
2.2381	1.7522	63000	2.3277
2.2267	1.7662	63500	2.3269
2.2222	1.7801	64000	2.3267
2.2056	1.7940	64500	2.3267
2.2139	1.8079	65000	2.3249
2.2048	1.8218	65500	2.3243
2.2353	1.8357	66000	2.3267
2.2127	1.8496	66500	2.3233
2.2315	1.8635	67000	2.3212
2.2198	1.8774	67500	2.3225
2.1935	1.8913	68000	2.3215
2.2077	1.9052	68500	2.3213
2.1898	1.9191	69000	2.3209
2.2096	1.9330	69500	2.3195
2.2199	1.9469	70000	2.3214
2.2071	1.9608	70500	2.3182
2.2239	1.9748	71000	2.3193
2.2289	1.9887	71500	2.3162
2.2062	2.0026	72000	2.3172
2.2141	2.0165	72500	2.3174
2.1995	2.0304	73000	2.3171
2.1773	2.0443	73500	2.3161
2.2178	2.0582	74000	2.3163
2.2063	2.0721	74500	2.3141
2.2219	2.0860	75000	2.3150
2.1872	2.0999	75500	2.3152
2.2119	2.1138	76000	2.3176
2.2196	2.1277	76500	2.3142
2.1905	2.1416	77000	2.3145
2.2035	2.1555	77500	2.3144
2.2043	2.1694	78000	2.3172
2.1886	2.1833	78500	2.3154
2.2000	2.1973	79000	2.3152
2.2043	2.2112	79500	2.3146
2.2007	2.2251	80000	2.3143
2.2078	2.2390	80500	2.3131
2.1617	2.2529	81000	2.3147
2.2062	2.2668	81500	2.3136
2.1916	2.2807	82000	2.3113
2.1866	2.2946	82500	2.3142
2.1881	2.3085	83000	2.3125
2.1815	2.3224	83500	2.3134
2.1918	2.3363	84000	2.3099
2.1914	2.3502	84500	2.3099
2.1895	2.3641	85000	2.3098
2.1805	2.3780	85500	2.3089
2.1800	2.3919	86000	2.3088
2.1853	2.4059	86500	2.3103
2.1736	2.4198	87000	2.3088
2.1655	2.4337	87500	2.3085
2.1732	2.4476	88000	2.3084
2.2044	2.4615	88500	2.3079
2.1918	2.4754	89000	2.3077
2.1643	2.4893	89500	2.3080
2.1753	2.5032	90000	2.3069
2.1883	2.5171	90500	2.3073
2.2015	2.5310	91000	2.3068
2.1864	2.5449	91500	2.3070
2.1870	2.5588	92000	2.3058
2.1854	2.5727	92500	2.3069
2.1689	2.5866	93000	2.3061
2.1704	2.6005	93500	2.3054
2.1682	2.6145	94000	2.3060
2.1915	2.6284	94500	2.3054
2.1963	2.6423	95000	2.3052
2.2090	2.6562	95500	2.3061
2.1817	2.6701	96000	2.3057
2.1773	2.6840	96500	2.3062
2.2022	2.6979	97000	2.3051
2.1860	2.7118	97500	2.3057
2.1695	2.7257	98000	2.3064
2.1943	2.7396	98500	2.3060
2.1621	2.7535	99000	2.3057
2.1790	2.7674	99500	2.3055
2.1930	2.7813	100000	2.3050
2.1943	2.7952	100500	2.3053
2.1882	2.8092	101000	2.3050
2.1870	2.8231	101500	2.3050
2.1826	2.8370	102000	2.3047
2.1681	2.8509	102500	2.3052
2.1894	2.8648	103000	2.3051
2.2013	2.8787	103500	2.3051
2.2105	2.8926	104000	2.3051
2.1853	2.9065	104500	2.3052
2.2133	2.9204	105000	2.3051
2.1781	2.9343	105500	2.3051
2.1912	2.9482	106000	2.3051
2.1886	2.9621	106500	2.3051
2.1610	2.9760	107000	2.3051
2.1681	2.9899	107500	2.3051
2.2018	3.0	107862	2.3051

Framework versions

Transformers 5.8.1
Pytorch 2.11.0+cu128
Datasets 3.1.0
Tokenizers 0.22.2

khairi/life2lang-base-wo-pt-it

life2lang-base-wo-pt-it

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

khairi/
life2lang-base-wo-pt-it